diff --git a/._README.md b/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..d74ad48046b4f7d5b52818e468b98cb7ffd945be Binary files /dev/null and b/._README.md differ diff --git a/._adapter_config.json b/._adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0d40ecaf0930be9d6eb791fadfa3385593976330 Binary files /dev/null and b/._adapter_config.json differ diff --git a/._adapter_model.safetensors b/._adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..892011722e73d69cc583eecde482ebb3195ce482 --- /dev/null +++ b/._adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ceee33650c019c72f610b058071aa1d2e33dadba329c1b3f9a1d160376431cd +size 4096 diff --git a/._all_results.json b/._all_results.json new file mode 100644 index 0000000000000000000000000000000000000000..3993d43e9a6e4a3932f9355f18caeee234499f1a Binary files /dev/null and b/._all_results.json differ diff --git a/._special_tokens_map.json b/._special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..c8afb2bccd70ddc824c562322f25d4810185661b Binary files /dev/null and b/._special_tokens_map.json differ diff --git a/._tokenizer.json b/._tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..78f1715f940b078d015346403e5f924831986a2b Binary files /dev/null and b/._tokenizer.json differ diff --git a/._tokenizer_config.json b/._tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d01e7422987a57bc9cb16d714952d1d6ab9e8e7 Binary files /dev/null and b/._tokenizer_config.json differ diff --git a/._train_results.json b/._train_results.json new file mode 100644 index 0000000000000000000000000000000000000000..d171bd16c893e9dcb970929f0f4378cfa92381a1 Binary files /dev/null and b/._train_results.json differ diff --git a/._trainer_log.jsonl b/._trainer_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f49881f8d351b9fd2f32d42bd548f36c41a89c51 Binary files /dev/null and b/._trainer_log.jsonl differ diff --git a/._trainer_state.json b/._trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1accf022bbc15fcfac98a3f0121f657710ddf7e8 Binary files /dev/null and b/._trainer_state.json differ diff --git a/._training_args.bin b/._training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..d8f4b591e9d36407d96a5744950cb7f88ce3f4f7 --- /dev/null +++ b/._training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8c5f0239ecd2427b8f8febf9db4f9931e3d54661787513d472979bdb401631 +size 4096 diff --git a/._training_loss.png b/._training_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..e79517d0f5f98b5d4f93e25c0ef163f09d9f915a Binary files /dev/null and b/._training_loss.png differ diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..4b8077b67672972fb74c163e9ac41cc7ec0160c6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-477/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 32897cd3e640101ba184f8c4ccd896981de3804a..c505e5aed602108e32bfaa2c329bb57b5de37c8b 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,59 @@ --- -license: mit +library_name: peft +license: other +base_model: meta-llama/Llama-3.3-70B-Instruct +tags: +- llama-factory +- lora +- generated_from_trainer +model-index: +- name: openpi_entity + results: [] --- + + + +# openpi_entity + +This model is a fine-tuned version of [/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422](https://huggingface.co//scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422) on the openpi_entity_guided dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-05 +- train_batch_size: 32 +- eval_batch_size: 8 +- seed: 42 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 128 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 3.0 + +### Training results + + + +### Framework versions + +- PEFT 0.12.0 +- Transformers 4.46.1 +- Pytorch 2.5.1+cu124 +- Datasets 3.1.0 +- Tokenizers 0.20.3 diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b43c336eadd307192f9ebaaca58b283a56db147d --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "v_proj", + "up_proj", + "q_proj", + "down_proj", + "gate_proj", + "o_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e872e4418291ae61abb876583d1ff2ba3eec50bd --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bece6d03c76862ade6a34424dc0b56bef9eb9dd0aa67e970a38725cbd0ac1c74 +size 414337624 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000000000000000000000000000000000000..c87deff6d17db6fb6cdaafdce5ff4448767c1c16 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 4.746880321608352e+18, + "train_loss": 0.7064950698576633, + "train_runtime": 33423.533, + "train_samples_per_second": 1.825, + "train_steps_per_second": 0.014 +} \ No newline at end of file diff --git a/checkpoint-100/._README.md b/checkpoint-100/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..f50345605a2a66c8bdf46beaff9461c5a12275a3 Binary files /dev/null and b/checkpoint-100/._README.md differ diff --git a/checkpoint-100/._adapter_config.json b/checkpoint-100/._adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e53e59588510bcd9dc11ecc309fa50f236c7ee86 Binary files /dev/null and b/checkpoint-100/._adapter_config.json differ diff --git a/checkpoint-100/._adapter_model.safetensors b/checkpoint-100/._adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bece98e133ce305659527ab65ef60b2ae0d44ec --- /dev/null +++ b/checkpoint-100/._adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9bf844708c9c38f91e69c6b3667746911d5320e04dba972cdee50f14e1abf0 +size 4096 diff --git a/checkpoint-100/._optimizer.pt b/checkpoint-100/._optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..913b85e1f27e67eca504f86dc1c57bdaab2a4e88 --- /dev/null +++ b/checkpoint-100/._optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:855721b260ea05eefcea4493094403485558dff11226ce3c86d97010f5048639 +size 4096 diff --git a/checkpoint-100/._rng_state.pth b/checkpoint-100/._rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e517bcffab1cf25b0c9c5c9d9e58f641fee85fc --- /dev/null +++ b/checkpoint-100/._rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefeb102786ee8ca1a321fed3886c5b94313a981f17da29a2162066b497a2642 +size 4096 diff --git a/checkpoint-100/._scheduler.pt b/checkpoint-100/._scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f3fd8098c8047b50b4e72751c3fa09891a1fb0a --- /dev/null +++ b/checkpoint-100/._scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fc9e03250cb8b40a334530ad46fb2905470acdfb76e9e30328da5f2ef35270 +size 4096 diff --git a/checkpoint-100/._special_tokens_map.json b/checkpoint-100/._special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..da695c42653c7118cdf15e65463eeebed52b181d Binary files /dev/null and b/checkpoint-100/._special_tokens_map.json differ diff --git a/checkpoint-100/._tokenizer.json b/checkpoint-100/._tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..4496d22c384fdcd8b967364b9e1198b1a21b534e Binary files /dev/null and b/checkpoint-100/._tokenizer.json differ diff --git a/checkpoint-100/._tokenizer_config.json b/checkpoint-100/._tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ada16a74ffd7a1d917c0f429a35294d63af35608 Binary files /dev/null and b/checkpoint-100/._tokenizer_config.json differ diff --git a/checkpoint-100/._trainer_state.json b/checkpoint-100/._trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..786a0ac76ce7518c7148f7f9b92e038b258db2a9 Binary files /dev/null and b/checkpoint-100/._trainer_state.json differ diff --git a/checkpoint-100/._training_args.bin b/checkpoint-100/._training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f69cfa6741363be2b3070d62c621b8a3a73d7789 --- /dev/null +++ b/checkpoint-100/._training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7c87274cf04a0dac5db8749789eb9156ed58a0228485c615005c91083882b5 +size 4096 diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0d0f45d57897230f208f7d5fa62f85e8481f2f2f --- /dev/null +++ b/checkpoint-100/README.md @@ -0,0 +1,202 @@ +--- +base_model: /scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b43c336eadd307192f9ebaaca58b283a56db147d --- /dev/null +++ b/checkpoint-100/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "v_proj", + "up_proj", + "q_proj", + "down_proj", + "gate_proj", + "o_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4530cc5c89a274290ffb4e87562b58c5ca3f789 --- /dev/null +++ b/checkpoint-100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f1227b26c7980da6dad48508f55b5eef007b2915f4c3e2b8ad742301b526d2 +size 414337624 diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..95c0825c4d9b19ee128554d3984f11def79796aa --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea8e3850e584a0b9d70a548012dc1592b8742e7807239317ed4c2d35e5aa81d +size 829323250 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 +size 14244 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7470d6b8924fde07bb2a13ee0ae22ecf6b98f862 --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b772369581c5f5adb4366f211f1d14cfe1c25134b6b1c0e5994a549442634ce +size 1064 diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/checkpoint-100/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-100/tokenizer.json b/checkpoint-100/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/checkpoint-100/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1913e5051ba2d9c350141f19b01d55276096bc3 --- /dev/null +++ b/checkpoint-100/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..404cb2aee2ae5b69ba5d7da7cc1369d3e48afda1 --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,733 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6289308176100629, + "eval_steps": 500, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.006289308176100629, + "grad_norm": 4.8737874031066895, + "learning_rate": 1.0416666666666667e-06, + "loss": 3.6915, + "step": 1 + }, + { + "epoch": 0.012578616352201259, + "grad_norm": 4.941007137298584, + "learning_rate": 2.0833333333333334e-06, + "loss": 3.6352, + "step": 2 + }, + { + "epoch": 0.018867924528301886, + "grad_norm": 5.258031368255615, + "learning_rate": 3.125e-06, + "loss": 3.5816, + "step": 3 + }, + { + "epoch": 0.025157232704402517, + "grad_norm": 5.544358253479004, + "learning_rate": 4.166666666666667e-06, + "loss": 3.6233, + "step": 4 + }, + { + "epoch": 0.031446540880503145, + "grad_norm": 5.457708835601807, + "learning_rate": 5.208333333333334e-06, + "loss": 3.6107, + "step": 5 + }, + { + "epoch": 0.03773584905660377, + "grad_norm": 5.185223579406738, + "learning_rate": 6.25e-06, + "loss": 3.6277, + "step": 6 + }, + { + "epoch": 0.0440251572327044, + "grad_norm": 5.433485507965088, + "learning_rate": 7.2916666666666674e-06, + "loss": 3.4974, + "step": 7 + }, + { + "epoch": 0.050314465408805034, + "grad_norm": 5.38355016708374, + "learning_rate": 8.333333333333334e-06, + "loss": 3.5021, + "step": 8 + }, + { + "epoch": 0.05660377358490566, + "grad_norm": 5.851156234741211, + "learning_rate": 9.375000000000001e-06, + "loss": 3.5888, + "step": 9 + }, + { + "epoch": 0.06289308176100629, + "grad_norm": 8.335844993591309, + "learning_rate": 1.0416666666666668e-05, + "loss": 3.3652, + "step": 10 + }, + { + "epoch": 0.06918238993710692, + "grad_norm": 5.598583698272705, + "learning_rate": 1.1458333333333333e-05, + "loss": 3.1476, + "step": 11 + }, + { + "epoch": 0.07547169811320754, + "grad_norm": 6.811880588531494, + "learning_rate": 1.25e-05, + "loss": 3.6846, + "step": 12 + }, + { + "epoch": 0.08176100628930817, + "grad_norm": 5.962316513061523, + "learning_rate": 1.3541666666666666e-05, + "loss": 3.2959, + "step": 13 + }, + { + "epoch": 0.0880503144654088, + "grad_norm": 6.434226989746094, + "learning_rate": 1.4583333333333335e-05, + "loss": 3.3629, + "step": 14 + }, + { + "epoch": 0.09433962264150944, + "grad_norm": 5.959097862243652, + "learning_rate": 1.5625e-05, + "loss": 2.9799, + "step": 15 + }, + { + "epoch": 0.10062893081761007, + "grad_norm": 5.713625907897949, + "learning_rate": 1.6666666666666667e-05, + "loss": 2.8375, + "step": 16 + }, + { + "epoch": 0.1069182389937107, + "grad_norm": 4.679070472717285, + "learning_rate": 1.7708333333333335e-05, + "loss": 2.5298, + "step": 17 + }, + { + "epoch": 0.11320754716981132, + "grad_norm": 4.000007152557373, + "learning_rate": 1.8750000000000002e-05, + "loss": 2.4099, + "step": 18 + }, + { + "epoch": 0.11949685534591195, + "grad_norm": 3.6054141521453857, + "learning_rate": 1.9791666666666665e-05, + "loss": 2.1316, + "step": 19 + }, + { + "epoch": 0.12578616352201258, + "grad_norm": 3.1357152462005615, + "learning_rate": 2.0833333333333336e-05, + "loss": 1.8814, + "step": 20 + }, + { + "epoch": 0.1320754716981132, + "grad_norm": 2.848811149597168, + "learning_rate": 2.1875e-05, + "loss": 1.7786, + "step": 21 + }, + { + "epoch": 0.13836477987421383, + "grad_norm": 2.4006130695343018, + "learning_rate": 2.2916666666666667e-05, + "loss": 1.5133, + "step": 22 + }, + { + "epoch": 0.14465408805031446, + "grad_norm": 2.2537267208099365, + "learning_rate": 2.3958333333333334e-05, + "loss": 1.4229, + "step": 23 + }, + { + "epoch": 0.1509433962264151, + "grad_norm": 2.1117539405822754, + "learning_rate": 2.5e-05, + "loss": 1.3577, + "step": 24 + }, + { + "epoch": 0.15723270440251572, + "grad_norm": 1.5717436075210571, + "learning_rate": 2.604166666666667e-05, + "loss": 1.1501, + "step": 25 + }, + { + "epoch": 0.16352201257861634, + "grad_norm": 1.691366195678711, + "learning_rate": 2.7083333333333332e-05, + "loss": 1.292, + "step": 26 + }, + { + "epoch": 0.16981132075471697, + "grad_norm": 1.4936853647232056, + "learning_rate": 2.8125000000000003e-05, + "loss": 1.1469, + "step": 27 + }, + { + "epoch": 0.1761006289308176, + "grad_norm": 1.2858690023422241, + "learning_rate": 2.916666666666667e-05, + "loss": 1.0433, + "step": 28 + }, + { + "epoch": 0.18238993710691823, + "grad_norm": 1.148773193359375, + "learning_rate": 3.0208333333333334e-05, + "loss": 0.9627, + "step": 29 + }, + { + "epoch": 0.18867924528301888, + "grad_norm": 1.0097932815551758, + "learning_rate": 3.125e-05, + "loss": 0.9103, + "step": 30 + }, + { + "epoch": 0.1949685534591195, + "grad_norm": 0.9332402348518372, + "learning_rate": 3.229166666666667e-05, + "loss": 0.979, + "step": 31 + }, + { + "epoch": 0.20125786163522014, + "grad_norm": 0.8993248343467712, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.9553, + "step": 32 + }, + { + "epoch": 0.20754716981132076, + "grad_norm": 0.7925082445144653, + "learning_rate": 3.4375e-05, + "loss": 0.8379, + "step": 33 + }, + { + "epoch": 0.2138364779874214, + "grad_norm": 0.7847669720649719, + "learning_rate": 3.541666666666667e-05, + "loss": 0.9038, + "step": 34 + }, + { + "epoch": 0.22012578616352202, + "grad_norm": 0.800736665725708, + "learning_rate": 3.6458333333333336e-05, + "loss": 0.8354, + "step": 35 + }, + { + "epoch": 0.22641509433962265, + "grad_norm": 0.6036879420280457, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.8517, + "step": 36 + }, + { + "epoch": 0.23270440251572327, + "grad_norm": 0.6031014919281006, + "learning_rate": 3.854166666666667e-05, + "loss": 0.8702, + "step": 37 + }, + { + "epoch": 0.2389937106918239, + "grad_norm": 0.584917426109314, + "learning_rate": 3.958333333333333e-05, + "loss": 0.8812, + "step": 38 + }, + { + "epoch": 0.24528301886792453, + "grad_norm": 0.5815232396125793, + "learning_rate": 4.0625000000000005e-05, + "loss": 0.8336, + "step": 39 + }, + { + "epoch": 0.25157232704402516, + "grad_norm": 0.5307980179786682, + "learning_rate": 4.166666666666667e-05, + "loss": 0.7162, + "step": 40 + }, + { + "epoch": 0.2578616352201258, + "grad_norm": 0.49309515953063965, + "learning_rate": 4.270833333333333e-05, + "loss": 0.7433, + "step": 41 + }, + { + "epoch": 0.2641509433962264, + "grad_norm": 0.5215100646018982, + "learning_rate": 4.375e-05, + "loss": 0.738, + "step": 42 + }, + { + "epoch": 0.27044025157232704, + "grad_norm": 0.5361147522926331, + "learning_rate": 4.4791666666666673e-05, + "loss": 0.7884, + "step": 43 + }, + { + "epoch": 0.27672955974842767, + "grad_norm": 0.5043961405754089, + "learning_rate": 4.5833333333333334e-05, + "loss": 0.814, + "step": 44 + }, + { + "epoch": 0.2830188679245283, + "grad_norm": 0.476026713848114, + "learning_rate": 4.6875e-05, + "loss": 0.8249, + "step": 45 + }, + { + "epoch": 0.2893081761006289, + "grad_norm": 0.5099363923072815, + "learning_rate": 4.791666666666667e-05, + "loss": 0.7205, + "step": 46 + }, + { + "epoch": 0.29559748427672955, + "grad_norm": 0.4583563208580017, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.7646, + "step": 47 + }, + { + "epoch": 0.3018867924528302, + "grad_norm": 0.5203999876976013, + "learning_rate": 5e-05, + "loss": 0.6697, + "step": 48 + }, + { + "epoch": 0.3081761006289308, + "grad_norm": 0.5025014877319336, + "learning_rate": 4.9999329662935534e-05, + "loss": 0.8134, + "step": 49 + }, + { + "epoch": 0.31446540880503143, + "grad_norm": 0.5326013565063477, + "learning_rate": 4.999731868769027e-05, + "loss": 0.7665, + "step": 50 + }, + { + "epoch": 0.32075471698113206, + "grad_norm": 0.4914862811565399, + "learning_rate": 4.99939671821067e-05, + "loss": 0.7717, + "step": 51 + }, + { + "epoch": 0.3270440251572327, + "grad_norm": 0.567669689655304, + "learning_rate": 4.998927532591592e-05, + "loss": 0.677, + "step": 52 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.44353675842285156, + "learning_rate": 4.9983243370727914e-05, + "loss": 0.6829, + "step": 53 + }, + { + "epoch": 0.33962264150943394, + "grad_norm": 0.48537710309028625, + "learning_rate": 4.9975871640018154e-05, + "loss": 0.7817, + "step": 54 + }, + { + "epoch": 0.34591194968553457, + "grad_norm": 0.6286251544952393, + "learning_rate": 4.996716052911017e-05, + "loss": 0.6835, + "step": 55 + }, + { + "epoch": 0.3522012578616352, + "grad_norm": 0.44308704137802124, + "learning_rate": 4.99571105051544e-05, + "loss": 0.728, + "step": 56 + }, + { + "epoch": 0.3584905660377358, + "grad_norm": 0.4270545542240143, + "learning_rate": 4.994572210710315e-05, + "loss": 0.6448, + "step": 57 + }, + { + "epoch": 0.36477987421383645, + "grad_norm": 0.38012009859085083, + "learning_rate": 4.993299594568163e-05, + "loss": 0.675, + "step": 58 + }, + { + "epoch": 0.3710691823899371, + "grad_norm": 0.46653008460998535, + "learning_rate": 4.9918932703355256e-05, + "loss": 0.6821, + "step": 59 + }, + { + "epoch": 0.37735849056603776, + "grad_norm": 0.3612300753593445, + "learning_rate": 4.990353313429303e-05, + "loss": 0.7063, + "step": 60 + }, + { + "epoch": 0.3836477987421384, + "grad_norm": 0.5769712924957275, + "learning_rate": 4.988679806432712e-05, + "loss": 0.6941, + "step": 61 + }, + { + "epoch": 0.389937106918239, + "grad_norm": 0.431997150182724, + "learning_rate": 4.9868728390908526e-05, + "loss": 0.6544, + "step": 62 + }, + { + "epoch": 0.39622641509433965, + "grad_norm": 0.38126569986343384, + "learning_rate": 4.9849325083059e-05, + "loss": 0.6966, + "step": 63 + }, + { + "epoch": 0.4025157232704403, + "grad_norm": 0.40978091955184937, + "learning_rate": 4.982858918131906e-05, + "loss": 0.6866, + "step": 64 + }, + { + "epoch": 0.4088050314465409, + "grad_norm": 0.5318535566329956, + "learning_rate": 4.980652179769218e-05, + "loss": 0.7029, + "step": 65 + }, + { + "epoch": 0.41509433962264153, + "grad_norm": 0.5288330912590027, + "learning_rate": 4.978312411558518e-05, + "loss": 0.6553, + "step": 66 + }, + { + "epoch": 0.42138364779874216, + "grad_norm": 0.6496341824531555, + "learning_rate": 4.9758397389744734e-05, + "loss": 0.696, + "step": 67 + }, + { + "epoch": 0.4276729559748428, + "grad_norm": 0.5196901559829712, + "learning_rate": 4.973234294619011e-05, + "loss": 0.6676, + "step": 68 + }, + { + "epoch": 0.4339622641509434, + "grad_norm": 0.5431825518608093, + "learning_rate": 4.9704962182142044e-05, + "loss": 0.6337, + "step": 69 + }, + { + "epoch": 0.44025157232704404, + "grad_norm": 0.6981568932533264, + "learning_rate": 4.967625656594782e-05, + "loss": 0.7645, + "step": 70 + }, + { + "epoch": 0.44654088050314467, + "grad_norm": 0.4362429082393646, + "learning_rate": 4.9646227637002515e-05, + "loss": 0.647, + "step": 71 + }, + { + "epoch": 0.4528301886792453, + "grad_norm": 0.41873699426651, + "learning_rate": 4.961487700566646e-05, + "loss": 0.6342, + "step": 72 + }, + { + "epoch": 0.4591194968553459, + "grad_norm": 0.589474081993103, + "learning_rate": 4.958220635317886e-05, + "loss": 0.641, + "step": 73 + }, + { + "epoch": 0.46540880503144655, + "grad_norm": 0.5421208739280701, + "learning_rate": 4.9548217431567665e-05, + "loss": 0.8103, + "step": 74 + }, + { + "epoch": 0.4716981132075472, + "grad_norm": 0.48354727029800415, + "learning_rate": 4.95129120635556e-05, + "loss": 0.6205, + "step": 75 + }, + { + "epoch": 0.4779874213836478, + "grad_norm": 0.6121774911880493, + "learning_rate": 4.9476292142462374e-05, + "loss": 0.6678, + "step": 76 + }, + { + "epoch": 0.48427672955974843, + "grad_norm": 0.5440806150436401, + "learning_rate": 4.943835963210324e-05, + "loss": 0.6668, + "step": 77 + }, + { + "epoch": 0.49056603773584906, + "grad_norm": 0.40740126371383667, + "learning_rate": 4.939911656668361e-05, + "loss": 0.61, + "step": 78 + }, + { + "epoch": 0.4968553459119497, + "grad_norm": 0.5682631731033325, + "learning_rate": 4.9358565050689985e-05, + "loss": 0.6939, + "step": 79 + }, + { + "epoch": 0.5031446540880503, + "grad_norm": 0.43090444803237915, + "learning_rate": 4.93167072587771e-05, + "loss": 0.6698, + "step": 80 + }, + { + "epoch": 0.5094339622641509, + "grad_norm": 0.3859785795211792, + "learning_rate": 4.92735454356513e-05, + "loss": 0.5798, + "step": 81 + }, + { + "epoch": 0.5157232704402516, + "grad_norm": 0.4453634023666382, + "learning_rate": 4.922908189595018e-05, + "loss": 0.7936, + "step": 82 + }, + { + "epoch": 0.5220125786163522, + "grad_norm": 0.4291239380836487, + "learning_rate": 4.9183319024118415e-05, + "loss": 0.667, + "step": 83 + }, + { + "epoch": 0.5283018867924528, + "grad_norm": 0.44029664993286133, + "learning_rate": 4.9136259274279955e-05, + "loss": 0.6518, + "step": 84 + }, + { + "epoch": 0.5345911949685535, + "grad_norm": 0.44975465536117554, + "learning_rate": 4.908790517010636e-05, + "loss": 0.6105, + "step": 85 + }, + { + "epoch": 0.5408805031446541, + "grad_norm": 0.3954753577709198, + "learning_rate": 4.903825930468149e-05, + "loss": 0.6954, + "step": 86 + }, + { + "epoch": 0.5471698113207547, + "grad_norm": 0.3935467302799225, + "learning_rate": 4.898732434036244e-05, + "loss": 0.6614, + "step": 87 + }, + { + "epoch": 0.5534591194968553, + "grad_norm": 0.37667638063430786, + "learning_rate": 4.893510300863676e-05, + "loss": 0.6186, + "step": 88 + }, + { + "epoch": 0.559748427672956, + "grad_norm": 0.5198381543159485, + "learning_rate": 4.8881598109976004e-05, + "loss": 0.6153, + "step": 89 + }, + { + "epoch": 0.5660377358490566, + "grad_norm": 0.4063967764377594, + "learning_rate": 4.8826812513685487e-05, + "loss": 0.6472, + "step": 90 + }, + { + "epoch": 0.5723270440251572, + "grad_norm": 0.4114413857460022, + "learning_rate": 4.877074915775049e-05, + "loss": 0.6404, + "step": 91 + }, + { + "epoch": 0.5786163522012578, + "grad_norm": 0.37414512038230896, + "learning_rate": 4.8713411048678635e-05, + "loss": 0.6353, + "step": 92 + }, + { + "epoch": 0.5849056603773585, + "grad_norm": 0.3818528354167938, + "learning_rate": 4.865480126133872e-05, + "loss": 0.6289, + "step": 93 + }, + { + "epoch": 0.5911949685534591, + "grad_norm": 0.37088677287101746, + "learning_rate": 4.859492293879574e-05, + "loss": 0.6242, + "step": 94 + }, + { + "epoch": 0.5974842767295597, + "grad_norm": 0.43665146827697754, + "learning_rate": 4.853377929214243e-05, + "loss": 0.6055, + "step": 95 + }, + { + "epoch": 0.6037735849056604, + "grad_norm": 0.5932008028030396, + "learning_rate": 4.8471373600326996e-05, + "loss": 0.6354, + "step": 96 + }, + { + "epoch": 0.610062893081761, + "grad_norm": 0.46184536814689636, + "learning_rate": 4.8407709209977305e-05, + "loss": 0.7039, + "step": 97 + }, + { + "epoch": 0.6163522012578616, + "grad_norm": 0.44864600896835327, + "learning_rate": 4.834278953522138e-05, + "loss": 0.6679, + "step": 98 + }, + { + "epoch": 0.6226415094339622, + "grad_norm": 0.4060032069683075, + "learning_rate": 4.8276618057504376e-05, + "loss": 0.7479, + "step": 99 + }, + { + "epoch": 0.6289308176100629, + "grad_norm": 0.5088009834289551, + "learning_rate": 4.8209198325401815e-05, + "loss": 0.5923, + "step": 100 + } + ], + "logging_steps": 1, + "max_steps": 477, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.0055422264423219e+18, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f2a1106da97275ded3721a2b9ad28a19b5c9872 --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d245efe4cb1811ec2cffc23b4d3aa9a49d1d65e92b8d678bec9a399e5c1889e +size 5496 diff --git a/checkpoint-200/._README.md b/checkpoint-200/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..d3690153e68bc5aed269a8964b55f851e3c3c00a Binary files /dev/null and b/checkpoint-200/._README.md differ diff --git a/checkpoint-200/._adapter_config.json b/checkpoint-200/._adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c6ea9e07a0580e86007bd5b58e739d6d26cbe24e Binary files /dev/null and b/checkpoint-200/._adapter_config.json differ diff --git a/checkpoint-200/._adapter_model.safetensors b/checkpoint-200/._adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f7ce8877917204784a2410c26fbedd0aaf89248 --- /dev/null +++ b/checkpoint-200/._adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce0f0d3c6b4395774d04d94c2f831a74f064f584e4114671bdf2f89a6433e26 +size 4096 diff --git a/checkpoint-200/._optimizer.pt b/checkpoint-200/._optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b949a72b0c5c3fbe584f1feb08380bc98151934 --- /dev/null +++ b/checkpoint-200/._optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724cf3da645a6a374d0e84cb32688442760e404d646c4de0aff6cf0c4f22df89 +size 4096 diff --git a/checkpoint-200/._rng_state.pth b/checkpoint-200/._rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..63dd450cdba5b78ae81c7b9f06bc792ca0a06c97 --- /dev/null +++ b/checkpoint-200/._rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:439af6919d244cd9714004100c276a6f2f63511cc854841616e6be22aeb3b121 +size 4096 diff --git a/checkpoint-200/._scheduler.pt b/checkpoint-200/._scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..957ac48af3d0fd05f7ed5106ace74071b7d039cf --- /dev/null +++ b/checkpoint-200/._scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2597270f1faea51fed0acace098be0c99cd8f48c9aa626fefd9988acb7cd9f20 +size 4096 diff --git a/checkpoint-200/._special_tokens_map.json b/checkpoint-200/._special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..10c540ca075025825fc680566bf145573a498512 Binary files /dev/null and b/checkpoint-200/._special_tokens_map.json differ diff --git a/checkpoint-200/._tokenizer.json b/checkpoint-200/._tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1b0d8cdb7166b0339d70c96ade4f730abeded2bf Binary files /dev/null and b/checkpoint-200/._tokenizer.json differ diff --git a/checkpoint-200/._tokenizer_config.json b/checkpoint-200/._tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..aabd7e75a6671c0b3bb4abc2a4e8f92277f9ee26 Binary files /dev/null and b/checkpoint-200/._tokenizer_config.json differ diff --git a/checkpoint-200/._trainer_state.json b/checkpoint-200/._trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..09e938696d3fa28e753346e5d862f1ca62cd6c95 Binary files /dev/null and b/checkpoint-200/._trainer_state.json differ diff --git a/checkpoint-200/._training_args.bin b/checkpoint-200/._training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5aa7bd4aec42888bcce8e8809ed3a920868d429d --- /dev/null +++ b/checkpoint-200/._training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c3c192cf5f8b8113c0dff378e497b1f7921075b6d9430ff056e92cfb0fec03 +size 4096 diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0d0f45d57897230f208f7d5fa62f85e8481f2f2f --- /dev/null +++ b/checkpoint-200/README.md @@ -0,0 +1,202 @@ +--- +base_model: /scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b43c336eadd307192f9ebaaca58b283a56db147d --- /dev/null +++ b/checkpoint-200/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "v_proj", + "up_proj", + "q_proj", + "down_proj", + "gate_proj", + "o_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20a5acdbdeee3dffed90907ae50d158eaaa10d51 --- /dev/null +++ b/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b320d4dbc4379afd27ef405a8b2ae9e9628fd1d68cc71253f440538ceb110e77 +size 414337624 diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b5dd8fff1e37187d508b1b7d0f5f19541f43adc --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454cf842017d780c41ef555b246a11191489e9af2f86bc557674813e6cd1d8db +size 829323250 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36 +size 14244 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..79a1b403ed564d4b52a7df28132078630da1e0ff --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331da4e95d29bb0158f1a41cd38b65bb0a84eaa65fbe2e165009f16d2130e91f +size 1064 diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/checkpoint-200/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/checkpoint-200/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1913e5051ba2d9c350141f19b01d55276096bc3 --- /dev/null +++ b/checkpoint-200/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9c5bc75e311953bf178b01dabd748feacb7c3233 --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,1433 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.2578616352201257, + "eval_steps": 500, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.006289308176100629, + "grad_norm": 4.8737874031066895, + "learning_rate": 1.0416666666666667e-06, + "loss": 3.6915, + "step": 1 + }, + { + "epoch": 0.012578616352201259, + "grad_norm": 4.941007137298584, + "learning_rate": 2.0833333333333334e-06, + "loss": 3.6352, + "step": 2 + }, + { + "epoch": 0.018867924528301886, + "grad_norm": 5.258031368255615, + "learning_rate": 3.125e-06, + "loss": 3.5816, + "step": 3 + }, + { + "epoch": 0.025157232704402517, + "grad_norm": 5.544358253479004, + "learning_rate": 4.166666666666667e-06, + "loss": 3.6233, + "step": 4 + }, + { + "epoch": 0.031446540880503145, + "grad_norm": 5.457708835601807, + "learning_rate": 5.208333333333334e-06, + "loss": 3.6107, + "step": 5 + }, + { + "epoch": 0.03773584905660377, + "grad_norm": 5.185223579406738, + "learning_rate": 6.25e-06, + "loss": 3.6277, + "step": 6 + }, + { + "epoch": 0.0440251572327044, + "grad_norm": 5.433485507965088, + "learning_rate": 7.2916666666666674e-06, + "loss": 3.4974, + "step": 7 + }, + { + "epoch": 0.050314465408805034, + "grad_norm": 5.38355016708374, + "learning_rate": 8.333333333333334e-06, + "loss": 3.5021, + "step": 8 + }, + { + "epoch": 0.05660377358490566, + "grad_norm": 5.851156234741211, + "learning_rate": 9.375000000000001e-06, + "loss": 3.5888, + "step": 9 + }, + { + "epoch": 0.06289308176100629, + "grad_norm": 8.335844993591309, + "learning_rate": 1.0416666666666668e-05, + "loss": 3.3652, + "step": 10 + }, + { + "epoch": 0.06918238993710692, + "grad_norm": 5.598583698272705, + "learning_rate": 1.1458333333333333e-05, + "loss": 3.1476, + "step": 11 + }, + { + "epoch": 0.07547169811320754, + "grad_norm": 6.811880588531494, + "learning_rate": 1.25e-05, + "loss": 3.6846, + "step": 12 + }, + { + "epoch": 0.08176100628930817, + "grad_norm": 5.962316513061523, + "learning_rate": 1.3541666666666666e-05, + "loss": 3.2959, + "step": 13 + }, + { + "epoch": 0.0880503144654088, + "grad_norm": 6.434226989746094, + "learning_rate": 1.4583333333333335e-05, + "loss": 3.3629, + "step": 14 + }, + { + "epoch": 0.09433962264150944, + "grad_norm": 5.959097862243652, + "learning_rate": 1.5625e-05, + "loss": 2.9799, + "step": 15 + }, + { + "epoch": 0.10062893081761007, + "grad_norm": 5.713625907897949, + "learning_rate": 1.6666666666666667e-05, + "loss": 2.8375, + "step": 16 + }, + { + "epoch": 0.1069182389937107, + "grad_norm": 4.679070472717285, + "learning_rate": 1.7708333333333335e-05, + "loss": 2.5298, + "step": 17 + }, + { + "epoch": 0.11320754716981132, + "grad_norm": 4.000007152557373, + "learning_rate": 1.8750000000000002e-05, + "loss": 2.4099, + "step": 18 + }, + { + "epoch": 0.11949685534591195, + "grad_norm": 3.6054141521453857, + "learning_rate": 1.9791666666666665e-05, + "loss": 2.1316, + "step": 19 + }, + { + "epoch": 0.12578616352201258, + "grad_norm": 3.1357152462005615, + "learning_rate": 2.0833333333333336e-05, + "loss": 1.8814, + "step": 20 + }, + { + "epoch": 0.1320754716981132, + "grad_norm": 2.848811149597168, + "learning_rate": 2.1875e-05, + "loss": 1.7786, + "step": 21 + }, + { + "epoch": 0.13836477987421383, + "grad_norm": 2.4006130695343018, + "learning_rate": 2.2916666666666667e-05, + "loss": 1.5133, + "step": 22 + }, + { + "epoch": 0.14465408805031446, + "grad_norm": 2.2537267208099365, + "learning_rate": 2.3958333333333334e-05, + "loss": 1.4229, + "step": 23 + }, + { + "epoch": 0.1509433962264151, + "grad_norm": 2.1117539405822754, + "learning_rate": 2.5e-05, + "loss": 1.3577, + "step": 24 + }, + { + "epoch": 0.15723270440251572, + "grad_norm": 1.5717436075210571, + "learning_rate": 2.604166666666667e-05, + "loss": 1.1501, + "step": 25 + }, + { + "epoch": 0.16352201257861634, + "grad_norm": 1.691366195678711, + "learning_rate": 2.7083333333333332e-05, + "loss": 1.292, + "step": 26 + }, + { + "epoch": 0.16981132075471697, + "grad_norm": 1.4936853647232056, + "learning_rate": 2.8125000000000003e-05, + "loss": 1.1469, + "step": 27 + }, + { + "epoch": 0.1761006289308176, + "grad_norm": 1.2858690023422241, + "learning_rate": 2.916666666666667e-05, + "loss": 1.0433, + "step": 28 + }, + { + "epoch": 0.18238993710691823, + "grad_norm": 1.148773193359375, + "learning_rate": 3.0208333333333334e-05, + "loss": 0.9627, + "step": 29 + }, + { + "epoch": 0.18867924528301888, + "grad_norm": 1.0097932815551758, + "learning_rate": 3.125e-05, + "loss": 0.9103, + "step": 30 + }, + { + "epoch": 0.1949685534591195, + "grad_norm": 0.9332402348518372, + "learning_rate": 3.229166666666667e-05, + "loss": 0.979, + "step": 31 + }, + { + "epoch": 0.20125786163522014, + "grad_norm": 0.8993248343467712, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.9553, + "step": 32 + }, + { + "epoch": 0.20754716981132076, + "grad_norm": 0.7925082445144653, + "learning_rate": 3.4375e-05, + "loss": 0.8379, + "step": 33 + }, + { + "epoch": 0.2138364779874214, + "grad_norm": 0.7847669720649719, + "learning_rate": 3.541666666666667e-05, + "loss": 0.9038, + "step": 34 + }, + { + "epoch": 0.22012578616352202, + "grad_norm": 0.800736665725708, + "learning_rate": 3.6458333333333336e-05, + "loss": 0.8354, + "step": 35 + }, + { + "epoch": 0.22641509433962265, + "grad_norm": 0.6036879420280457, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.8517, + "step": 36 + }, + { + "epoch": 0.23270440251572327, + "grad_norm": 0.6031014919281006, + "learning_rate": 3.854166666666667e-05, + "loss": 0.8702, + "step": 37 + }, + { + "epoch": 0.2389937106918239, + "grad_norm": 0.584917426109314, + "learning_rate": 3.958333333333333e-05, + "loss": 0.8812, + "step": 38 + }, + { + "epoch": 0.24528301886792453, + "grad_norm": 0.5815232396125793, + "learning_rate": 4.0625000000000005e-05, + "loss": 0.8336, + "step": 39 + }, + { + "epoch": 0.25157232704402516, + "grad_norm": 0.5307980179786682, + "learning_rate": 4.166666666666667e-05, + "loss": 0.7162, + "step": 40 + }, + { + "epoch": 0.2578616352201258, + "grad_norm": 0.49309515953063965, + "learning_rate": 4.270833333333333e-05, + "loss": 0.7433, + "step": 41 + }, + { + "epoch": 0.2641509433962264, + "grad_norm": 0.5215100646018982, + "learning_rate": 4.375e-05, + "loss": 0.738, + "step": 42 + }, + { + "epoch": 0.27044025157232704, + "grad_norm": 0.5361147522926331, + "learning_rate": 4.4791666666666673e-05, + "loss": 0.7884, + "step": 43 + }, + { + "epoch": 0.27672955974842767, + "grad_norm": 0.5043961405754089, + "learning_rate": 4.5833333333333334e-05, + "loss": 0.814, + "step": 44 + }, + { + "epoch": 0.2830188679245283, + "grad_norm": 0.476026713848114, + "learning_rate": 4.6875e-05, + "loss": 0.8249, + "step": 45 + }, + { + "epoch": 0.2893081761006289, + "grad_norm": 0.5099363923072815, + "learning_rate": 4.791666666666667e-05, + "loss": 0.7205, + "step": 46 + }, + { + "epoch": 0.29559748427672955, + "grad_norm": 0.4583563208580017, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.7646, + "step": 47 + }, + { + "epoch": 0.3018867924528302, + "grad_norm": 0.5203999876976013, + "learning_rate": 5e-05, + "loss": 0.6697, + "step": 48 + }, + { + "epoch": 0.3081761006289308, + "grad_norm": 0.5025014877319336, + "learning_rate": 4.9999329662935534e-05, + "loss": 0.8134, + "step": 49 + }, + { + "epoch": 0.31446540880503143, + "grad_norm": 0.5326013565063477, + "learning_rate": 4.999731868769027e-05, + "loss": 0.7665, + "step": 50 + }, + { + "epoch": 0.32075471698113206, + "grad_norm": 0.4914862811565399, + "learning_rate": 4.99939671821067e-05, + "loss": 0.7717, + "step": 51 + }, + { + "epoch": 0.3270440251572327, + "grad_norm": 0.567669689655304, + "learning_rate": 4.998927532591592e-05, + "loss": 0.677, + "step": 52 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.44353675842285156, + "learning_rate": 4.9983243370727914e-05, + "loss": 0.6829, + "step": 53 + }, + { + "epoch": 0.33962264150943394, + "grad_norm": 0.48537710309028625, + "learning_rate": 4.9975871640018154e-05, + "loss": 0.7817, + "step": 54 + }, + { + "epoch": 0.34591194968553457, + "grad_norm": 0.6286251544952393, + "learning_rate": 4.996716052911017e-05, + "loss": 0.6835, + "step": 55 + }, + { + "epoch": 0.3522012578616352, + "grad_norm": 0.44308704137802124, + "learning_rate": 4.99571105051544e-05, + "loss": 0.728, + "step": 56 + }, + { + "epoch": 0.3584905660377358, + "grad_norm": 0.4270545542240143, + "learning_rate": 4.994572210710315e-05, + "loss": 0.6448, + "step": 57 + }, + { + "epoch": 0.36477987421383645, + "grad_norm": 0.38012009859085083, + "learning_rate": 4.993299594568163e-05, + "loss": 0.675, + "step": 58 + }, + { + "epoch": 0.3710691823899371, + "grad_norm": 0.46653008460998535, + "learning_rate": 4.9918932703355256e-05, + "loss": 0.6821, + "step": 59 + }, + { + "epoch": 0.37735849056603776, + "grad_norm": 0.3612300753593445, + "learning_rate": 4.990353313429303e-05, + "loss": 0.7063, + "step": 60 + }, + { + "epoch": 0.3836477987421384, + "grad_norm": 0.5769712924957275, + "learning_rate": 4.988679806432712e-05, + "loss": 0.6941, + "step": 61 + }, + { + "epoch": 0.389937106918239, + "grad_norm": 0.431997150182724, + "learning_rate": 4.9868728390908526e-05, + "loss": 0.6544, + "step": 62 + }, + { + "epoch": 0.39622641509433965, + "grad_norm": 0.38126569986343384, + "learning_rate": 4.9849325083059e-05, + "loss": 0.6966, + "step": 63 + }, + { + "epoch": 0.4025157232704403, + "grad_norm": 0.40978091955184937, + "learning_rate": 4.982858918131906e-05, + "loss": 0.6866, + "step": 64 + }, + { + "epoch": 0.4088050314465409, + "grad_norm": 0.5318535566329956, + "learning_rate": 4.980652179769218e-05, + "loss": 0.7029, + "step": 65 + }, + { + "epoch": 0.41509433962264153, + "grad_norm": 0.5288330912590027, + "learning_rate": 4.978312411558518e-05, + "loss": 0.6553, + "step": 66 + }, + { + "epoch": 0.42138364779874216, + "grad_norm": 0.6496341824531555, + "learning_rate": 4.9758397389744734e-05, + "loss": 0.696, + "step": 67 + }, + { + "epoch": 0.4276729559748428, + "grad_norm": 0.5196901559829712, + "learning_rate": 4.973234294619011e-05, + "loss": 0.6676, + "step": 68 + }, + { + "epoch": 0.4339622641509434, + "grad_norm": 0.5431825518608093, + "learning_rate": 4.9704962182142044e-05, + "loss": 0.6337, + "step": 69 + }, + { + "epoch": 0.44025157232704404, + "grad_norm": 0.6981568932533264, + "learning_rate": 4.967625656594782e-05, + "loss": 0.7645, + "step": 70 + }, + { + "epoch": 0.44654088050314467, + "grad_norm": 0.4362429082393646, + "learning_rate": 4.9646227637002515e-05, + "loss": 0.647, + "step": 71 + }, + { + "epoch": 0.4528301886792453, + "grad_norm": 0.41873699426651, + "learning_rate": 4.961487700566646e-05, + "loss": 0.6342, + "step": 72 + }, + { + "epoch": 0.4591194968553459, + "grad_norm": 0.589474081993103, + "learning_rate": 4.958220635317886e-05, + "loss": 0.641, + "step": 73 + }, + { + "epoch": 0.46540880503144655, + "grad_norm": 0.5421208739280701, + "learning_rate": 4.9548217431567665e-05, + "loss": 0.8103, + "step": 74 + }, + { + "epoch": 0.4716981132075472, + "grad_norm": 0.48354727029800415, + "learning_rate": 4.95129120635556e-05, + "loss": 0.6205, + "step": 75 + }, + { + "epoch": 0.4779874213836478, + "grad_norm": 0.6121774911880493, + "learning_rate": 4.9476292142462374e-05, + "loss": 0.6678, + "step": 76 + }, + { + "epoch": 0.48427672955974843, + "grad_norm": 0.5440806150436401, + "learning_rate": 4.943835963210324e-05, + "loss": 0.6668, + "step": 77 + }, + { + "epoch": 0.49056603773584906, + "grad_norm": 0.40740126371383667, + "learning_rate": 4.939911656668361e-05, + "loss": 0.61, + "step": 78 + }, + { + "epoch": 0.4968553459119497, + "grad_norm": 0.5682631731033325, + "learning_rate": 4.9358565050689985e-05, + "loss": 0.6939, + "step": 79 + }, + { + "epoch": 0.5031446540880503, + "grad_norm": 0.43090444803237915, + "learning_rate": 4.93167072587771e-05, + "loss": 0.6698, + "step": 80 + }, + { + "epoch": 0.5094339622641509, + "grad_norm": 0.3859785795211792, + "learning_rate": 4.92735454356513e-05, + "loss": 0.5798, + "step": 81 + }, + { + "epoch": 0.5157232704402516, + "grad_norm": 0.4453634023666382, + "learning_rate": 4.922908189595018e-05, + "loss": 0.7936, + "step": 82 + }, + { + "epoch": 0.5220125786163522, + "grad_norm": 0.4291239380836487, + "learning_rate": 4.9183319024118415e-05, + "loss": 0.667, + "step": 83 + }, + { + "epoch": 0.5283018867924528, + "grad_norm": 0.44029664993286133, + "learning_rate": 4.9136259274279955e-05, + "loss": 0.6518, + "step": 84 + }, + { + "epoch": 0.5345911949685535, + "grad_norm": 0.44975465536117554, + "learning_rate": 4.908790517010636e-05, + "loss": 0.6105, + "step": 85 + }, + { + "epoch": 0.5408805031446541, + "grad_norm": 0.3954753577709198, + "learning_rate": 4.903825930468149e-05, + "loss": 0.6954, + "step": 86 + }, + { + "epoch": 0.5471698113207547, + "grad_norm": 0.3935467302799225, + "learning_rate": 4.898732434036244e-05, + "loss": 0.6614, + "step": 87 + }, + { + "epoch": 0.5534591194968553, + "grad_norm": 0.37667638063430786, + "learning_rate": 4.893510300863676e-05, + "loss": 0.6186, + "step": 88 + }, + { + "epoch": 0.559748427672956, + "grad_norm": 0.5198381543159485, + "learning_rate": 4.8881598109976004e-05, + "loss": 0.6153, + "step": 89 + }, + { + "epoch": 0.5660377358490566, + "grad_norm": 0.4063967764377594, + "learning_rate": 4.8826812513685487e-05, + "loss": 0.6472, + "step": 90 + }, + { + "epoch": 0.5723270440251572, + "grad_norm": 0.4114413857460022, + "learning_rate": 4.877074915775049e-05, + "loss": 0.6404, + "step": 91 + }, + { + "epoch": 0.5786163522012578, + "grad_norm": 0.37414512038230896, + "learning_rate": 4.8713411048678635e-05, + "loss": 0.6353, + "step": 92 + }, + { + "epoch": 0.5849056603773585, + "grad_norm": 0.3818528354167938, + "learning_rate": 4.865480126133872e-05, + "loss": 0.6289, + "step": 93 + }, + { + "epoch": 0.5911949685534591, + "grad_norm": 0.37088677287101746, + "learning_rate": 4.859492293879574e-05, + "loss": 0.6242, + "step": 94 + }, + { + "epoch": 0.5974842767295597, + "grad_norm": 0.43665146827697754, + "learning_rate": 4.853377929214243e-05, + "loss": 0.6055, + "step": 95 + }, + { + "epoch": 0.6037735849056604, + "grad_norm": 0.5932008028030396, + "learning_rate": 4.8471373600326996e-05, + "loss": 0.6354, + "step": 96 + }, + { + "epoch": 0.610062893081761, + "grad_norm": 0.46184536814689636, + "learning_rate": 4.8407709209977305e-05, + "loss": 0.7039, + "step": 97 + }, + { + "epoch": 0.6163522012578616, + "grad_norm": 0.44864600896835327, + "learning_rate": 4.834278953522138e-05, + "loss": 0.6679, + "step": 98 + }, + { + "epoch": 0.6226415094339622, + "grad_norm": 0.4060032069683075, + "learning_rate": 4.8276618057504376e-05, + "loss": 0.7479, + "step": 99 + }, + { + "epoch": 0.6289308176100629, + "grad_norm": 0.5088009834289551, + "learning_rate": 4.8209198325401815e-05, + "loss": 0.5923, + "step": 100 + }, + { + "epoch": 0.6352201257861635, + "grad_norm": 0.4294343590736389, + "learning_rate": 4.8140533954429327e-05, + "loss": 0.6313, + "step": 101 + }, + { + "epoch": 0.6415094339622641, + "grad_norm": 0.5710806846618652, + "learning_rate": 4.8070628626848735e-05, + "loss": 0.6736, + "step": 102 + }, + { + "epoch": 0.6477987421383647, + "grad_norm": 0.40560534596443176, + "learning_rate": 4.799948609147061e-05, + "loss": 0.6173, + "step": 103 + }, + { + "epoch": 0.6540880503144654, + "grad_norm": 0.46361806988716125, + "learning_rate": 4.792711016345321e-05, + "loss": 0.6756, + "step": 104 + }, + { + "epoch": 0.660377358490566, + "grad_norm": 0.5206082463264465, + "learning_rate": 4.785350472409792e-05, + "loss": 0.6413, + "step": 105 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.42583200335502625, + "learning_rate": 4.777867372064105e-05, + "loss": 0.6201, + "step": 106 + }, + { + "epoch": 0.6729559748427673, + "grad_norm": 0.49348241090774536, + "learning_rate": 4.770262116604224e-05, + "loss": 0.5777, + "step": 107 + }, + { + "epoch": 0.6792452830188679, + "grad_norm": 0.43750065565109253, + "learning_rate": 4.762535113876917e-05, + "loss": 0.6326, + "step": 108 + }, + { + "epoch": 0.6855345911949685, + "grad_norm": 0.431643545627594, + "learning_rate": 4.754686778257891e-05, + "loss": 0.5849, + "step": 109 + }, + { + "epoch": 0.6918238993710691, + "grad_norm": 0.41906824707984924, + "learning_rate": 4.7467175306295655e-05, + "loss": 0.6779, + "step": 110 + }, + { + "epoch": 0.6981132075471698, + "grad_norm": 0.4261593222618103, + "learning_rate": 4.738627798358506e-05, + "loss": 0.565, + "step": 111 + }, + { + "epoch": 0.7044025157232704, + "grad_norm": 0.42877814173698425, + "learning_rate": 4.730418015272503e-05, + "loss": 0.6836, + "step": 112 + }, + { + "epoch": 0.710691823899371, + "grad_norm": 0.40995511412620544, + "learning_rate": 4.722088621637309e-05, + "loss": 0.5849, + "step": 113 + }, + { + "epoch": 0.7169811320754716, + "grad_norm": 0.5606467723846436, + "learning_rate": 4.713640064133025e-05, + "loss": 0.644, + "step": 114 + }, + { + "epoch": 0.7232704402515723, + "grad_norm": 0.48454752564430237, + "learning_rate": 4.7050727958301506e-05, + "loss": 0.5418, + "step": 115 + }, + { + "epoch": 0.7295597484276729, + "grad_norm": 0.4099617898464203, + "learning_rate": 4.6963872761652835e-05, + "loss": 0.6524, + "step": 116 + }, + { + "epoch": 0.7358490566037735, + "grad_norm": 0.47192293405532837, + "learning_rate": 4.687583970916487e-05, + "loss": 0.6134, + "step": 117 + }, + { + "epoch": 0.7421383647798742, + "grad_norm": 0.4925817549228668, + "learning_rate": 4.678663352178301e-05, + "loss": 0.6517, + "step": 118 + }, + { + "epoch": 0.7484276729559748, + "grad_norm": 0.41517379879951477, + "learning_rate": 4.6696258983364385e-05, + "loss": 0.5763, + "step": 119 + }, + { + "epoch": 0.7547169811320755, + "grad_norm": 0.6227956414222717, + "learning_rate": 4.660472094042121e-05, + "loss": 0.7349, + "step": 120 + }, + { + "epoch": 0.7610062893081762, + "grad_norm": 0.39108285307884216, + "learning_rate": 4.651202430186092e-05, + "loss": 0.6548, + "step": 121 + }, + { + "epoch": 0.7672955974842768, + "grad_norm": 0.40210628509521484, + "learning_rate": 4.641817403872293e-05, + "loss": 0.6135, + "step": 122 + }, + { + "epoch": 0.7735849056603774, + "grad_norm": 0.42835289239883423, + "learning_rate": 4.6323175183912024e-05, + "loss": 0.5227, + "step": 123 + }, + { + "epoch": 0.779874213836478, + "grad_norm": 0.6215445399284363, + "learning_rate": 4.6227032831928484e-05, + "loss": 0.5265, + "step": 124 + }, + { + "epoch": 0.7861635220125787, + "grad_norm": 0.43423891067504883, + "learning_rate": 4.6129752138594874e-05, + "loss": 0.5972, + "step": 125 + }, + { + "epoch": 0.7924528301886793, + "grad_norm": 0.4693637788295746, + "learning_rate": 4.6031338320779534e-05, + "loss": 0.6758, + "step": 126 + }, + { + "epoch": 0.7987421383647799, + "grad_norm": 0.47571077942848206, + "learning_rate": 4.5931796656116846e-05, + "loss": 0.6419, + "step": 127 + }, + { + "epoch": 0.8050314465408805, + "grad_norm": 0.5828564167022705, + "learning_rate": 4.5831132482724195e-05, + "loss": 0.6952, + "step": 128 + }, + { + "epoch": 0.8113207547169812, + "grad_norm": 0.5325509309768677, + "learning_rate": 4.572935119891571e-05, + "loss": 0.6093, + "step": 129 + }, + { + "epoch": 0.8176100628930818, + "grad_norm": 0.4476761519908905, + "learning_rate": 4.5626458262912745e-05, + "loss": 0.5688, + "step": 130 + }, + { + "epoch": 0.8238993710691824, + "grad_norm": 0.36771783232688904, + "learning_rate": 4.552245919255117e-05, + "loss": 0.5778, + "step": 131 + }, + { + "epoch": 0.8301886792452831, + "grad_norm": 0.3695763647556305, + "learning_rate": 4.541735956498554e-05, + "loss": 0.517, + "step": 132 + }, + { + "epoch": 0.8364779874213837, + "grad_norm": 0.46155717968940735, + "learning_rate": 4.5311165016389916e-05, + "loss": 0.631, + "step": 133 + }, + { + "epoch": 0.8427672955974843, + "grad_norm": 0.5536386966705322, + "learning_rate": 4.5203881241655644e-05, + "loss": 0.6309, + "step": 134 + }, + { + "epoch": 0.8490566037735849, + "grad_norm": 0.42256519198417664, + "learning_rate": 4.509551399408598e-05, + "loss": 0.6754, + "step": 135 + }, + { + "epoch": 0.8553459119496856, + "grad_norm": 0.41634511947631836, + "learning_rate": 4.498606908508754e-05, + "loss": 0.6547, + "step": 136 + }, + { + "epoch": 0.8616352201257862, + "grad_norm": 0.38796696066856384, + "learning_rate": 4.487555238385862e-05, + "loss": 0.5693, + "step": 137 + }, + { + "epoch": 0.8679245283018868, + "grad_norm": 0.43052586913108826, + "learning_rate": 4.476396981707453e-05, + "loss": 0.6655, + "step": 138 + }, + { + "epoch": 0.8742138364779874, + "grad_norm": 0.44500571489334106, + "learning_rate": 4.465132736856969e-05, + "loss": 0.6563, + "step": 139 + }, + { + "epoch": 0.8805031446540881, + "grad_norm": 0.44693946838378906, + "learning_rate": 4.453763107901675e-05, + "loss": 0.5729, + "step": 140 + }, + { + "epoch": 0.8867924528301887, + "grad_norm": 0.3982055187225342, + "learning_rate": 4.442288704560268e-05, + "loss": 0.6425, + "step": 141 + }, + { + "epoch": 0.8930817610062893, + "grad_norm": 0.5706686973571777, + "learning_rate": 4.430710142170176e-05, + "loss": 0.5732, + "step": 142 + }, + { + "epoch": 0.89937106918239, + "grad_norm": 0.4493609070777893, + "learning_rate": 4.419028041654559e-05, + "loss": 0.6507, + "step": 143 + }, + { + "epoch": 0.9056603773584906, + "grad_norm": 0.3834284543991089, + "learning_rate": 4.4072430294890174e-05, + "loss": 0.6883, + "step": 144 + }, + { + "epoch": 0.9119496855345912, + "grad_norm": 0.4243861138820648, + "learning_rate": 4.3953557376679856e-05, + "loss": 0.5818, + "step": 145 + }, + { + "epoch": 0.9182389937106918, + "grad_norm": 0.42064470052719116, + "learning_rate": 4.383366803670849e-05, + "loss": 0.5963, + "step": 146 + }, + { + "epoch": 0.9245283018867925, + "grad_norm": 0.46670740842819214, + "learning_rate": 4.371276870427753e-05, + "loss": 0.65, + "step": 147 + }, + { + "epoch": 0.9308176100628931, + "grad_norm": 0.44945597648620605, + "learning_rate": 4.359086586285127e-05, + "loss": 0.6554, + "step": 148 + }, + { + "epoch": 0.9371069182389937, + "grad_norm": 0.48251762986183167, + "learning_rate": 4.346796604970912e-05, + "loss": 0.6681, + "step": 149 + }, + { + "epoch": 0.9433962264150944, + "grad_norm": 0.4577901065349579, + "learning_rate": 4.3344075855595104e-05, + "loss": 0.6108, + "step": 150 + }, + { + "epoch": 0.949685534591195, + "grad_norm": 0.4710671603679657, + "learning_rate": 4.321920192436433e-05, + "loss": 0.6177, + "step": 151 + }, + { + "epoch": 0.9559748427672956, + "grad_norm": 0.4275747835636139, + "learning_rate": 4.309335095262676e-05, + "loss": 0.5881, + "step": 152 + }, + { + "epoch": 0.9622641509433962, + "grad_norm": 0.4541204571723938, + "learning_rate": 4.296652968938807e-05, + "loss": 0.6142, + "step": 153 + }, + { + "epoch": 0.9685534591194969, + "grad_norm": 0.4179267883300781, + "learning_rate": 4.283874493568772e-05, + "loss": 0.6463, + "step": 154 + }, + { + "epoch": 0.9748427672955975, + "grad_norm": 0.42434728145599365, + "learning_rate": 4.271000354423426e-05, + "loss": 0.5873, + "step": 155 + }, + { + "epoch": 0.9811320754716981, + "grad_norm": 0.44202134013175964, + "learning_rate": 4.258031241903778e-05, + "loss": 0.6046, + "step": 156 + }, + { + "epoch": 0.9874213836477987, + "grad_norm": 0.47817060351371765, + "learning_rate": 4.2449678515039747e-05, + "loss": 0.5989, + "step": 157 + }, + { + "epoch": 0.9937106918238994, + "grad_norm": 0.43847018480300903, + "learning_rate": 4.231810883773999e-05, + "loss": 0.6156, + "step": 158 + }, + { + "epoch": 1.0, + "grad_norm": 0.48976290225982666, + "learning_rate": 4.218561044282099e-05, + "loss": 0.6177, + "step": 159 + }, + { + "epoch": 1.0062893081761006, + "grad_norm": 0.4213927984237671, + "learning_rate": 4.2052190435769554e-05, + "loss": 0.5881, + "step": 160 + }, + { + "epoch": 1.0125786163522013, + "grad_norm": 0.3923173248767853, + "learning_rate": 4.191785597149577e-05, + "loss": 0.5354, + "step": 161 + }, + { + "epoch": 1.0188679245283019, + "grad_norm": 0.41947099566459656, + "learning_rate": 4.178261425394926e-05, + "loss": 0.5745, + "step": 162 + }, + { + "epoch": 1.0251572327044025, + "grad_norm": 0.45812028646469116, + "learning_rate": 4.1646472535732895e-05, + "loss": 0.5836, + "step": 163 + }, + { + "epoch": 1.0314465408805031, + "grad_norm": 0.4519791007041931, + "learning_rate": 4.1509438117713866e-05, + "loss": 0.6118, + "step": 164 + }, + { + "epoch": 1.0377358490566038, + "grad_norm": 0.5628229379653931, + "learning_rate": 4.137151834863213e-05, + "loss": 0.5811, + "step": 165 + }, + { + "epoch": 1.0440251572327044, + "grad_norm": 0.3987003564834595, + "learning_rate": 4.123272062470633e-05, + "loss": 0.5179, + "step": 166 + }, + { + "epoch": 1.050314465408805, + "grad_norm": 0.4499664604663849, + "learning_rate": 4.109305238923718e-05, + "loss": 0.548, + "step": 167 + }, + { + "epoch": 1.0566037735849056, + "grad_norm": 0.4336049556732178, + "learning_rate": 4.095252113220827e-05, + "loss": 0.5659, + "step": 168 + }, + { + "epoch": 1.0628930817610063, + "grad_norm": 0.5409331321716309, + "learning_rate": 4.0811134389884433e-05, + "loss": 0.5522, + "step": 169 + }, + { + "epoch": 1.069182389937107, + "grad_norm": 0.41802865266799927, + "learning_rate": 4.066889974440757e-05, + "loss": 0.542, + "step": 170 + }, + { + "epoch": 1.0754716981132075, + "grad_norm": 0.48149824142456055, + "learning_rate": 4.0525824823390045e-05, + "loss": 0.6131, + "step": 171 + }, + { + "epoch": 1.0817610062893082, + "grad_norm": 0.5059295296669006, + "learning_rate": 4.038191729950569e-05, + "loss": 0.5823, + "step": 172 + }, + { + "epoch": 1.0880503144654088, + "grad_norm": 0.5310669541358948, + "learning_rate": 4.0237184890078245e-05, + "loss": 0.6066, + "step": 173 + }, + { + "epoch": 1.0943396226415094, + "grad_norm": 0.5470696091651917, + "learning_rate": 4.009163535666761e-05, + "loss": 0.6407, + "step": 174 + }, + { + "epoch": 1.10062893081761, + "grad_norm": 0.4407522678375244, + "learning_rate": 3.994527650465352e-05, + "loss": 0.573, + "step": 175 + }, + { + "epoch": 1.1069182389937107, + "grad_norm": 0.4072059094905853, + "learning_rate": 3.979811618281706e-05, + "loss": 0.6349, + "step": 176 + }, + { + "epoch": 1.1132075471698113, + "grad_norm": 0.6410146355628967, + "learning_rate": 3.9650162282919655e-05, + "loss": 0.6036, + "step": 177 + }, + { + "epoch": 1.119496855345912, + "grad_norm": 0.4664185047149658, + "learning_rate": 3.9501422739279956e-05, + "loss": 0.5855, + "step": 178 + }, + { + "epoch": 1.1257861635220126, + "grad_norm": 0.7204552888870239, + "learning_rate": 3.9351905528348285e-05, + "loss": 0.5719, + "step": 179 + }, + { + "epoch": 1.1320754716981132, + "grad_norm": 0.47248926758766174, + "learning_rate": 3.920161866827889e-05, + "loss": 0.5764, + "step": 180 + }, + { + "epoch": 1.1383647798742138, + "grad_norm": 0.64155113697052, + "learning_rate": 3.90505702185e-05, + "loss": 0.644, + "step": 181 + }, + { + "epoch": 1.1446540880503144, + "grad_norm": 0.5559830665588379, + "learning_rate": 3.889876827928156e-05, + "loss": 0.5883, + "step": 182 + }, + { + "epoch": 1.150943396226415, + "grad_norm": 0.46357718110084534, + "learning_rate": 3.874622099130087e-05, + "loss": 0.5942, + "step": 183 + }, + { + "epoch": 1.1572327044025157, + "grad_norm": 0.4527578055858612, + "learning_rate": 3.859293653520604e-05, + "loss": 0.6086, + "step": 184 + }, + { + "epoch": 1.1635220125786163, + "grad_norm": 0.45968765020370483, + "learning_rate": 3.843892313117724e-05, + "loss": 0.6105, + "step": 185 + }, + { + "epoch": 1.169811320754717, + "grad_norm": 0.5293806791305542, + "learning_rate": 3.8284189038485936e-05, + "loss": 0.5622, + "step": 186 + }, + { + "epoch": 1.1761006289308176, + "grad_norm": 0.4499124586582184, + "learning_rate": 3.812874255505191e-05, + "loss": 0.5451, + "step": 187 + }, + { + "epoch": 1.1823899371069182, + "grad_norm": 0.5140619277954102, + "learning_rate": 3.797259201699833e-05, + "loss": 0.5864, + "step": 188 + }, + { + "epoch": 1.1886792452830188, + "grad_norm": 0.40918025374412537, + "learning_rate": 3.781574579820464e-05, + "loss": 0.5602, + "step": 189 + }, + { + "epoch": 1.1949685534591195, + "grad_norm": 0.4417194128036499, + "learning_rate": 3.765821230985758e-05, + "loss": 0.5556, + "step": 190 + }, + { + "epoch": 1.20125786163522, + "grad_norm": 0.4697968363761902, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.6491, + "step": 191 + }, + { + "epoch": 1.2075471698113207, + "grad_norm": 0.40187153220176697, + "learning_rate": 3.7341117353077966e-05, + "loss": 0.5797, + "step": 192 + }, + { + "epoch": 1.2138364779874213, + "grad_norm": 0.456836462020874, + "learning_rate": 3.718157288948563e-05, + "loss": 0.5613, + "step": 193 + }, + { + "epoch": 1.220125786163522, + "grad_norm": 0.45992621779441833, + "learning_rate": 3.702137516510838e-05, + "loss": 0.6301, + "step": 194 + }, + { + "epoch": 1.2264150943396226, + "grad_norm": 0.45000532269477844, + "learning_rate": 3.686053277086401e-05, + "loss": 0.5772, + "step": 195 + }, + { + "epoch": 1.2327044025157232, + "grad_norm": 0.4734075963497162, + "learning_rate": 3.669905433224199e-05, + "loss": 0.5452, + "step": 196 + }, + { + "epoch": 1.2389937106918238, + "grad_norm": 0.41561609506607056, + "learning_rate": 3.653694850884091e-05, + "loss": 0.5365, + "step": 197 + }, + { + "epoch": 1.2452830188679245, + "grad_norm": 0.469097763299942, + "learning_rate": 3.637422399390413e-05, + "loss": 0.5396, + "step": 198 + }, + { + "epoch": 1.251572327044025, + "grad_norm": 0.46705111861228943, + "learning_rate": 3.621088951385353e-05, + "loss": 0.6024, + "step": 199 + }, + { + "epoch": 1.2578616352201257, + "grad_norm": 0.5201407074928284, + "learning_rate": 3.604695382782159e-05, + "loss": 0.6905, + "step": 200 + } + ], + "logging_steps": 1, + "max_steps": 477, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.9942452289968538e+18, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f2a1106da97275ded3721a2b9ad28a19b5c9872 --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d245efe4cb1811ec2cffc23b4d3aa9a49d1d65e92b8d678bec9a399e5c1889e +size 5496 diff --git a/checkpoint-300/._README.md b/checkpoint-300/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..2e91ff0e412442af4a195acb83082631405d3aef Binary files /dev/null and b/checkpoint-300/._README.md differ diff --git a/checkpoint-300/._adapter_config.json b/checkpoint-300/._adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3737cdf4bd62d56819a3139a4423fab23caa287b Binary files /dev/null and b/checkpoint-300/._adapter_config.json differ diff --git a/checkpoint-300/._adapter_model.safetensors b/checkpoint-300/._adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a98a3921c0d6398f3062c85e16c7d45dcfafe4c1 --- /dev/null +++ b/checkpoint-300/._adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f9468d3f5827a336085a2c0939d9954897e4b10832410eef56431a821ba84c +size 4096 diff --git a/checkpoint-300/._optimizer.pt b/checkpoint-300/._optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..185a81e288be53c55283abd3137b711585d89728 --- /dev/null +++ b/checkpoint-300/._optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:030b5f13d1616cde105ab11fb8df2730c330ed5516bcff7e729c14b8452d64ed +size 4096 diff --git a/checkpoint-300/._rng_state.pth b/checkpoint-300/._rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f8edf399548989c05cf5b0b2b8b3acfe4c534ab --- /dev/null +++ b/checkpoint-300/._rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2404dd7290199cef9c67acae1779959fec164d6de763d605327df46d599d87d +size 4096 diff --git a/checkpoint-300/._scheduler.pt b/checkpoint-300/._scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..92067863ad55bded2b11111f92bb35d78f48e184 --- /dev/null +++ b/checkpoint-300/._scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88056011270d8e76542deffe42dfd30df5a29342863249c90318d5d65c199c27 +size 4096 diff --git a/checkpoint-300/._special_tokens_map.json b/checkpoint-300/._special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..655a718219d01a5cb80c4d31e30b9413df93fa49 Binary files /dev/null and b/checkpoint-300/._special_tokens_map.json differ diff --git a/checkpoint-300/._tokenizer.json b/checkpoint-300/._tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..56aadc8577b098c714f4ee7d5260067996e81272 Binary files /dev/null and b/checkpoint-300/._tokenizer.json differ diff --git a/checkpoint-300/._tokenizer_config.json b/checkpoint-300/._tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4a0d9736f575016e2171abf933b9a33524f4dd8c Binary files /dev/null and b/checkpoint-300/._tokenizer_config.json differ diff --git a/checkpoint-300/._trainer_state.json b/checkpoint-300/._trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c736c93078116a4e27bf40a66860d4c5d879b309 Binary files /dev/null and b/checkpoint-300/._trainer_state.json differ diff --git a/checkpoint-300/._training_args.bin b/checkpoint-300/._training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..71d20524044b2f99696c031ef7caa78545a72da5 --- /dev/null +++ b/checkpoint-300/._training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154377640541f0e225c459c85f473204db8ce7c0893fd429f1b1aaf343ce791c +size 4096 diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0d0f45d57897230f208f7d5fa62f85e8481f2f2f --- /dev/null +++ b/checkpoint-300/README.md @@ -0,0 +1,202 @@ +--- +base_model: /scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b43c336eadd307192f9ebaaca58b283a56db147d --- /dev/null +++ b/checkpoint-300/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "v_proj", + "up_proj", + "q_proj", + "down_proj", + "gate_proj", + "o_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bbf51140c9841c99bec89da903694869c5ff70e8 --- /dev/null +++ b/checkpoint-300/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72b54fb2174ff054591d42158854e935fc580510de62a91e513bc3e15546d17 +size 414337624 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..03fde97a50de383409300a597e1ab26f56c21128 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0c1be2a031385beef36d518716eee06673e06f0bee414da1f2467935d73dff +size 829323250 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36 +size 14244 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc6c0ad33eb928612a5cce846fdfa4104e8f5cb9 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0fa4b29838438e6be882681654e7c778cabd404df5f0ed02fd9a22870fa7c0 +size 1064 diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/checkpoint-300/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/checkpoint-300/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1913e5051ba2d9c350141f19b01d55276096bc3 --- /dev/null +++ b/checkpoint-300/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..48bc43df5a36e42bbbdb44b3241c0aec895487c8 --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,2133 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.8867924528301887, + "eval_steps": 500, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.006289308176100629, + "grad_norm": 4.8737874031066895, + "learning_rate": 1.0416666666666667e-06, + "loss": 3.6915, + "step": 1 + }, + { + "epoch": 0.012578616352201259, + "grad_norm": 4.941007137298584, + "learning_rate": 2.0833333333333334e-06, + "loss": 3.6352, + "step": 2 + }, + { + "epoch": 0.018867924528301886, + "grad_norm": 5.258031368255615, + "learning_rate": 3.125e-06, + "loss": 3.5816, + "step": 3 + }, + { + "epoch": 0.025157232704402517, + "grad_norm": 5.544358253479004, + "learning_rate": 4.166666666666667e-06, + "loss": 3.6233, + "step": 4 + }, + { + "epoch": 0.031446540880503145, + "grad_norm": 5.457708835601807, + "learning_rate": 5.208333333333334e-06, + "loss": 3.6107, + "step": 5 + }, + { + "epoch": 0.03773584905660377, + "grad_norm": 5.185223579406738, + "learning_rate": 6.25e-06, + "loss": 3.6277, + "step": 6 + }, + { + "epoch": 0.0440251572327044, + "grad_norm": 5.433485507965088, + "learning_rate": 7.2916666666666674e-06, + "loss": 3.4974, + "step": 7 + }, + { + "epoch": 0.050314465408805034, + "grad_norm": 5.38355016708374, + "learning_rate": 8.333333333333334e-06, + "loss": 3.5021, + "step": 8 + }, + { + "epoch": 0.05660377358490566, + "grad_norm": 5.851156234741211, + "learning_rate": 9.375000000000001e-06, + "loss": 3.5888, + "step": 9 + }, + { + "epoch": 0.06289308176100629, + "grad_norm": 8.335844993591309, + "learning_rate": 1.0416666666666668e-05, + "loss": 3.3652, + "step": 10 + }, + { + "epoch": 0.06918238993710692, + "grad_norm": 5.598583698272705, + "learning_rate": 1.1458333333333333e-05, + "loss": 3.1476, + "step": 11 + }, + { + "epoch": 0.07547169811320754, + "grad_norm": 6.811880588531494, + "learning_rate": 1.25e-05, + "loss": 3.6846, + "step": 12 + }, + { + "epoch": 0.08176100628930817, + "grad_norm": 5.962316513061523, + "learning_rate": 1.3541666666666666e-05, + "loss": 3.2959, + "step": 13 + }, + { + "epoch": 0.0880503144654088, + "grad_norm": 6.434226989746094, + "learning_rate": 1.4583333333333335e-05, + "loss": 3.3629, + "step": 14 + }, + { + "epoch": 0.09433962264150944, + "grad_norm": 5.959097862243652, + "learning_rate": 1.5625e-05, + "loss": 2.9799, + "step": 15 + }, + { + "epoch": 0.10062893081761007, + "grad_norm": 5.713625907897949, + "learning_rate": 1.6666666666666667e-05, + "loss": 2.8375, + "step": 16 + }, + { + "epoch": 0.1069182389937107, + "grad_norm": 4.679070472717285, + "learning_rate": 1.7708333333333335e-05, + "loss": 2.5298, + "step": 17 + }, + { + "epoch": 0.11320754716981132, + "grad_norm": 4.000007152557373, + "learning_rate": 1.8750000000000002e-05, + "loss": 2.4099, + "step": 18 + }, + { + "epoch": 0.11949685534591195, + "grad_norm": 3.6054141521453857, + "learning_rate": 1.9791666666666665e-05, + "loss": 2.1316, + "step": 19 + }, + { + "epoch": 0.12578616352201258, + "grad_norm": 3.1357152462005615, + "learning_rate": 2.0833333333333336e-05, + "loss": 1.8814, + "step": 20 + }, + { + "epoch": 0.1320754716981132, + "grad_norm": 2.848811149597168, + "learning_rate": 2.1875e-05, + "loss": 1.7786, + "step": 21 + }, + { + "epoch": 0.13836477987421383, + "grad_norm": 2.4006130695343018, + "learning_rate": 2.2916666666666667e-05, + "loss": 1.5133, + "step": 22 + }, + { + "epoch": 0.14465408805031446, + "grad_norm": 2.2537267208099365, + "learning_rate": 2.3958333333333334e-05, + "loss": 1.4229, + "step": 23 + }, + { + "epoch": 0.1509433962264151, + "grad_norm": 2.1117539405822754, + "learning_rate": 2.5e-05, + "loss": 1.3577, + "step": 24 + }, + { + "epoch": 0.15723270440251572, + "grad_norm": 1.5717436075210571, + "learning_rate": 2.604166666666667e-05, + "loss": 1.1501, + "step": 25 + }, + { + "epoch": 0.16352201257861634, + "grad_norm": 1.691366195678711, + "learning_rate": 2.7083333333333332e-05, + "loss": 1.292, + "step": 26 + }, + { + "epoch": 0.16981132075471697, + "grad_norm": 1.4936853647232056, + "learning_rate": 2.8125000000000003e-05, + "loss": 1.1469, + "step": 27 + }, + { + "epoch": 0.1761006289308176, + "grad_norm": 1.2858690023422241, + "learning_rate": 2.916666666666667e-05, + "loss": 1.0433, + "step": 28 + }, + { + "epoch": 0.18238993710691823, + "grad_norm": 1.148773193359375, + "learning_rate": 3.0208333333333334e-05, + "loss": 0.9627, + "step": 29 + }, + { + "epoch": 0.18867924528301888, + "grad_norm": 1.0097932815551758, + "learning_rate": 3.125e-05, + "loss": 0.9103, + "step": 30 + }, + { + "epoch": 0.1949685534591195, + "grad_norm": 0.9332402348518372, + "learning_rate": 3.229166666666667e-05, + "loss": 0.979, + "step": 31 + }, + { + "epoch": 0.20125786163522014, + "grad_norm": 0.8993248343467712, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.9553, + "step": 32 + }, + { + "epoch": 0.20754716981132076, + "grad_norm": 0.7925082445144653, + "learning_rate": 3.4375e-05, + "loss": 0.8379, + "step": 33 + }, + { + "epoch": 0.2138364779874214, + "grad_norm": 0.7847669720649719, + "learning_rate": 3.541666666666667e-05, + "loss": 0.9038, + "step": 34 + }, + { + "epoch": 0.22012578616352202, + "grad_norm": 0.800736665725708, + "learning_rate": 3.6458333333333336e-05, + "loss": 0.8354, + "step": 35 + }, + { + "epoch": 0.22641509433962265, + "grad_norm": 0.6036879420280457, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.8517, + "step": 36 + }, + { + "epoch": 0.23270440251572327, + "grad_norm": 0.6031014919281006, + "learning_rate": 3.854166666666667e-05, + "loss": 0.8702, + "step": 37 + }, + { + "epoch": 0.2389937106918239, + "grad_norm": 0.584917426109314, + "learning_rate": 3.958333333333333e-05, + "loss": 0.8812, + "step": 38 + }, + { + "epoch": 0.24528301886792453, + "grad_norm": 0.5815232396125793, + "learning_rate": 4.0625000000000005e-05, + "loss": 0.8336, + "step": 39 + }, + { + "epoch": 0.25157232704402516, + "grad_norm": 0.5307980179786682, + "learning_rate": 4.166666666666667e-05, + "loss": 0.7162, + "step": 40 + }, + { + "epoch": 0.2578616352201258, + "grad_norm": 0.49309515953063965, + "learning_rate": 4.270833333333333e-05, + "loss": 0.7433, + "step": 41 + }, + { + "epoch": 0.2641509433962264, + "grad_norm": 0.5215100646018982, + "learning_rate": 4.375e-05, + "loss": 0.738, + "step": 42 + }, + { + "epoch": 0.27044025157232704, + "grad_norm": 0.5361147522926331, + "learning_rate": 4.4791666666666673e-05, + "loss": 0.7884, + "step": 43 + }, + { + "epoch": 0.27672955974842767, + "grad_norm": 0.5043961405754089, + "learning_rate": 4.5833333333333334e-05, + "loss": 0.814, + "step": 44 + }, + { + "epoch": 0.2830188679245283, + "grad_norm": 0.476026713848114, + "learning_rate": 4.6875e-05, + "loss": 0.8249, + "step": 45 + }, + { + "epoch": 0.2893081761006289, + "grad_norm": 0.5099363923072815, + "learning_rate": 4.791666666666667e-05, + "loss": 0.7205, + "step": 46 + }, + { + "epoch": 0.29559748427672955, + "grad_norm": 0.4583563208580017, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.7646, + "step": 47 + }, + { + "epoch": 0.3018867924528302, + "grad_norm": 0.5203999876976013, + "learning_rate": 5e-05, + "loss": 0.6697, + "step": 48 + }, + { + "epoch": 0.3081761006289308, + "grad_norm": 0.5025014877319336, + "learning_rate": 4.9999329662935534e-05, + "loss": 0.8134, + "step": 49 + }, + { + "epoch": 0.31446540880503143, + "grad_norm": 0.5326013565063477, + "learning_rate": 4.999731868769027e-05, + "loss": 0.7665, + "step": 50 + }, + { + "epoch": 0.32075471698113206, + "grad_norm": 0.4914862811565399, + "learning_rate": 4.99939671821067e-05, + "loss": 0.7717, + "step": 51 + }, + { + "epoch": 0.3270440251572327, + "grad_norm": 0.567669689655304, + "learning_rate": 4.998927532591592e-05, + "loss": 0.677, + "step": 52 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.44353675842285156, + "learning_rate": 4.9983243370727914e-05, + "loss": 0.6829, + "step": 53 + }, + { + "epoch": 0.33962264150943394, + "grad_norm": 0.48537710309028625, + "learning_rate": 4.9975871640018154e-05, + "loss": 0.7817, + "step": 54 + }, + { + "epoch": 0.34591194968553457, + "grad_norm": 0.6286251544952393, + "learning_rate": 4.996716052911017e-05, + "loss": 0.6835, + "step": 55 + }, + { + "epoch": 0.3522012578616352, + "grad_norm": 0.44308704137802124, + "learning_rate": 4.99571105051544e-05, + "loss": 0.728, + "step": 56 + }, + { + "epoch": 0.3584905660377358, + "grad_norm": 0.4270545542240143, + "learning_rate": 4.994572210710315e-05, + "loss": 0.6448, + "step": 57 + }, + { + "epoch": 0.36477987421383645, + "grad_norm": 0.38012009859085083, + "learning_rate": 4.993299594568163e-05, + "loss": 0.675, + "step": 58 + }, + { + "epoch": 0.3710691823899371, + "grad_norm": 0.46653008460998535, + "learning_rate": 4.9918932703355256e-05, + "loss": 0.6821, + "step": 59 + }, + { + "epoch": 0.37735849056603776, + "grad_norm": 0.3612300753593445, + "learning_rate": 4.990353313429303e-05, + "loss": 0.7063, + "step": 60 + }, + { + "epoch": 0.3836477987421384, + "grad_norm": 0.5769712924957275, + "learning_rate": 4.988679806432712e-05, + "loss": 0.6941, + "step": 61 + }, + { + "epoch": 0.389937106918239, + "grad_norm": 0.431997150182724, + "learning_rate": 4.9868728390908526e-05, + "loss": 0.6544, + "step": 62 + }, + { + "epoch": 0.39622641509433965, + "grad_norm": 0.38126569986343384, + "learning_rate": 4.9849325083059e-05, + "loss": 0.6966, + "step": 63 + }, + { + "epoch": 0.4025157232704403, + "grad_norm": 0.40978091955184937, + "learning_rate": 4.982858918131906e-05, + "loss": 0.6866, + "step": 64 + }, + { + "epoch": 0.4088050314465409, + "grad_norm": 0.5318535566329956, + "learning_rate": 4.980652179769218e-05, + "loss": 0.7029, + "step": 65 + }, + { + "epoch": 0.41509433962264153, + "grad_norm": 0.5288330912590027, + "learning_rate": 4.978312411558518e-05, + "loss": 0.6553, + "step": 66 + }, + { + "epoch": 0.42138364779874216, + "grad_norm": 0.6496341824531555, + "learning_rate": 4.9758397389744734e-05, + "loss": 0.696, + "step": 67 + }, + { + "epoch": 0.4276729559748428, + "grad_norm": 0.5196901559829712, + "learning_rate": 4.973234294619011e-05, + "loss": 0.6676, + "step": 68 + }, + { + "epoch": 0.4339622641509434, + "grad_norm": 0.5431825518608093, + "learning_rate": 4.9704962182142044e-05, + "loss": 0.6337, + "step": 69 + }, + { + "epoch": 0.44025157232704404, + "grad_norm": 0.6981568932533264, + "learning_rate": 4.967625656594782e-05, + "loss": 0.7645, + "step": 70 + }, + { + "epoch": 0.44654088050314467, + "grad_norm": 0.4362429082393646, + "learning_rate": 4.9646227637002515e-05, + "loss": 0.647, + "step": 71 + }, + { + "epoch": 0.4528301886792453, + "grad_norm": 0.41873699426651, + "learning_rate": 4.961487700566646e-05, + "loss": 0.6342, + "step": 72 + }, + { + "epoch": 0.4591194968553459, + "grad_norm": 0.589474081993103, + "learning_rate": 4.958220635317886e-05, + "loss": 0.641, + "step": 73 + }, + { + "epoch": 0.46540880503144655, + "grad_norm": 0.5421208739280701, + "learning_rate": 4.9548217431567665e-05, + "loss": 0.8103, + "step": 74 + }, + { + "epoch": 0.4716981132075472, + "grad_norm": 0.48354727029800415, + "learning_rate": 4.95129120635556e-05, + "loss": 0.6205, + "step": 75 + }, + { + "epoch": 0.4779874213836478, + "grad_norm": 0.6121774911880493, + "learning_rate": 4.9476292142462374e-05, + "loss": 0.6678, + "step": 76 + }, + { + "epoch": 0.48427672955974843, + "grad_norm": 0.5440806150436401, + "learning_rate": 4.943835963210324e-05, + "loss": 0.6668, + "step": 77 + }, + { + "epoch": 0.49056603773584906, + "grad_norm": 0.40740126371383667, + "learning_rate": 4.939911656668361e-05, + "loss": 0.61, + "step": 78 + }, + { + "epoch": 0.4968553459119497, + "grad_norm": 0.5682631731033325, + "learning_rate": 4.9358565050689985e-05, + "loss": 0.6939, + "step": 79 + }, + { + "epoch": 0.5031446540880503, + "grad_norm": 0.43090444803237915, + "learning_rate": 4.93167072587771e-05, + "loss": 0.6698, + "step": 80 + }, + { + "epoch": 0.5094339622641509, + "grad_norm": 0.3859785795211792, + "learning_rate": 4.92735454356513e-05, + "loss": 0.5798, + "step": 81 + }, + { + "epoch": 0.5157232704402516, + "grad_norm": 0.4453634023666382, + "learning_rate": 4.922908189595018e-05, + "loss": 0.7936, + "step": 82 + }, + { + "epoch": 0.5220125786163522, + "grad_norm": 0.4291239380836487, + "learning_rate": 4.9183319024118415e-05, + "loss": 0.667, + "step": 83 + }, + { + "epoch": 0.5283018867924528, + "grad_norm": 0.44029664993286133, + "learning_rate": 4.9136259274279955e-05, + "loss": 0.6518, + "step": 84 + }, + { + "epoch": 0.5345911949685535, + "grad_norm": 0.44975465536117554, + "learning_rate": 4.908790517010636e-05, + "loss": 0.6105, + "step": 85 + }, + { + "epoch": 0.5408805031446541, + "grad_norm": 0.3954753577709198, + "learning_rate": 4.903825930468149e-05, + "loss": 0.6954, + "step": 86 + }, + { + "epoch": 0.5471698113207547, + "grad_norm": 0.3935467302799225, + "learning_rate": 4.898732434036244e-05, + "loss": 0.6614, + "step": 87 + }, + { + "epoch": 0.5534591194968553, + "grad_norm": 0.37667638063430786, + "learning_rate": 4.893510300863676e-05, + "loss": 0.6186, + "step": 88 + }, + { + "epoch": 0.559748427672956, + "grad_norm": 0.5198381543159485, + "learning_rate": 4.8881598109976004e-05, + "loss": 0.6153, + "step": 89 + }, + { + "epoch": 0.5660377358490566, + "grad_norm": 0.4063967764377594, + "learning_rate": 4.8826812513685487e-05, + "loss": 0.6472, + "step": 90 + }, + { + "epoch": 0.5723270440251572, + "grad_norm": 0.4114413857460022, + "learning_rate": 4.877074915775049e-05, + "loss": 0.6404, + "step": 91 + }, + { + "epoch": 0.5786163522012578, + "grad_norm": 0.37414512038230896, + "learning_rate": 4.8713411048678635e-05, + "loss": 0.6353, + "step": 92 + }, + { + "epoch": 0.5849056603773585, + "grad_norm": 0.3818528354167938, + "learning_rate": 4.865480126133872e-05, + "loss": 0.6289, + "step": 93 + }, + { + "epoch": 0.5911949685534591, + "grad_norm": 0.37088677287101746, + "learning_rate": 4.859492293879574e-05, + "loss": 0.6242, + "step": 94 + }, + { + "epoch": 0.5974842767295597, + "grad_norm": 0.43665146827697754, + "learning_rate": 4.853377929214243e-05, + "loss": 0.6055, + "step": 95 + }, + { + "epoch": 0.6037735849056604, + "grad_norm": 0.5932008028030396, + "learning_rate": 4.8471373600326996e-05, + "loss": 0.6354, + "step": 96 + }, + { + "epoch": 0.610062893081761, + "grad_norm": 0.46184536814689636, + "learning_rate": 4.8407709209977305e-05, + "loss": 0.7039, + "step": 97 + }, + { + "epoch": 0.6163522012578616, + "grad_norm": 0.44864600896835327, + "learning_rate": 4.834278953522138e-05, + "loss": 0.6679, + "step": 98 + }, + { + "epoch": 0.6226415094339622, + "grad_norm": 0.4060032069683075, + "learning_rate": 4.8276618057504376e-05, + "loss": 0.7479, + "step": 99 + }, + { + "epoch": 0.6289308176100629, + "grad_norm": 0.5088009834289551, + "learning_rate": 4.8209198325401815e-05, + "loss": 0.5923, + "step": 100 + }, + { + "epoch": 0.6352201257861635, + "grad_norm": 0.4294343590736389, + "learning_rate": 4.8140533954429327e-05, + "loss": 0.6313, + "step": 101 + }, + { + "epoch": 0.6415094339622641, + "grad_norm": 0.5710806846618652, + "learning_rate": 4.8070628626848735e-05, + "loss": 0.6736, + "step": 102 + }, + { + "epoch": 0.6477987421383647, + "grad_norm": 0.40560534596443176, + "learning_rate": 4.799948609147061e-05, + "loss": 0.6173, + "step": 103 + }, + { + "epoch": 0.6540880503144654, + "grad_norm": 0.46361806988716125, + "learning_rate": 4.792711016345321e-05, + "loss": 0.6756, + "step": 104 + }, + { + "epoch": 0.660377358490566, + "grad_norm": 0.5206082463264465, + "learning_rate": 4.785350472409792e-05, + "loss": 0.6413, + "step": 105 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.42583200335502625, + "learning_rate": 4.777867372064105e-05, + "loss": 0.6201, + "step": 106 + }, + { + "epoch": 0.6729559748427673, + "grad_norm": 0.49348241090774536, + "learning_rate": 4.770262116604224e-05, + "loss": 0.5777, + "step": 107 + }, + { + "epoch": 0.6792452830188679, + "grad_norm": 0.43750065565109253, + "learning_rate": 4.762535113876917e-05, + "loss": 0.6326, + "step": 108 + }, + { + "epoch": 0.6855345911949685, + "grad_norm": 0.431643545627594, + "learning_rate": 4.754686778257891e-05, + "loss": 0.5849, + "step": 109 + }, + { + "epoch": 0.6918238993710691, + "grad_norm": 0.41906824707984924, + "learning_rate": 4.7467175306295655e-05, + "loss": 0.6779, + "step": 110 + }, + { + "epoch": 0.6981132075471698, + "grad_norm": 0.4261593222618103, + "learning_rate": 4.738627798358506e-05, + "loss": 0.565, + "step": 111 + }, + { + "epoch": 0.7044025157232704, + "grad_norm": 0.42877814173698425, + "learning_rate": 4.730418015272503e-05, + "loss": 0.6836, + "step": 112 + }, + { + "epoch": 0.710691823899371, + "grad_norm": 0.40995511412620544, + "learning_rate": 4.722088621637309e-05, + "loss": 0.5849, + "step": 113 + }, + { + "epoch": 0.7169811320754716, + "grad_norm": 0.5606467723846436, + "learning_rate": 4.713640064133025e-05, + "loss": 0.644, + "step": 114 + }, + { + "epoch": 0.7232704402515723, + "grad_norm": 0.48454752564430237, + "learning_rate": 4.7050727958301506e-05, + "loss": 0.5418, + "step": 115 + }, + { + "epoch": 0.7295597484276729, + "grad_norm": 0.4099617898464203, + "learning_rate": 4.6963872761652835e-05, + "loss": 0.6524, + "step": 116 + }, + { + "epoch": 0.7358490566037735, + "grad_norm": 0.47192293405532837, + "learning_rate": 4.687583970916487e-05, + "loss": 0.6134, + "step": 117 + }, + { + "epoch": 0.7421383647798742, + "grad_norm": 0.4925817549228668, + "learning_rate": 4.678663352178301e-05, + "loss": 0.6517, + "step": 118 + }, + { + "epoch": 0.7484276729559748, + "grad_norm": 0.41517379879951477, + "learning_rate": 4.6696258983364385e-05, + "loss": 0.5763, + "step": 119 + }, + { + "epoch": 0.7547169811320755, + "grad_norm": 0.6227956414222717, + "learning_rate": 4.660472094042121e-05, + "loss": 0.7349, + "step": 120 + }, + { + "epoch": 0.7610062893081762, + "grad_norm": 0.39108285307884216, + "learning_rate": 4.651202430186092e-05, + "loss": 0.6548, + "step": 121 + }, + { + "epoch": 0.7672955974842768, + "grad_norm": 0.40210628509521484, + "learning_rate": 4.641817403872293e-05, + "loss": 0.6135, + "step": 122 + }, + { + "epoch": 0.7735849056603774, + "grad_norm": 0.42835289239883423, + "learning_rate": 4.6323175183912024e-05, + "loss": 0.5227, + "step": 123 + }, + { + "epoch": 0.779874213836478, + "grad_norm": 0.6215445399284363, + "learning_rate": 4.6227032831928484e-05, + "loss": 0.5265, + "step": 124 + }, + { + "epoch": 0.7861635220125787, + "grad_norm": 0.43423891067504883, + "learning_rate": 4.6129752138594874e-05, + "loss": 0.5972, + "step": 125 + }, + { + "epoch": 0.7924528301886793, + "grad_norm": 0.4693637788295746, + "learning_rate": 4.6031338320779534e-05, + "loss": 0.6758, + "step": 126 + }, + { + "epoch": 0.7987421383647799, + "grad_norm": 0.47571077942848206, + "learning_rate": 4.5931796656116846e-05, + "loss": 0.6419, + "step": 127 + }, + { + "epoch": 0.8050314465408805, + "grad_norm": 0.5828564167022705, + "learning_rate": 4.5831132482724195e-05, + "loss": 0.6952, + "step": 128 + }, + { + "epoch": 0.8113207547169812, + "grad_norm": 0.5325509309768677, + "learning_rate": 4.572935119891571e-05, + "loss": 0.6093, + "step": 129 + }, + { + "epoch": 0.8176100628930818, + "grad_norm": 0.4476761519908905, + "learning_rate": 4.5626458262912745e-05, + "loss": 0.5688, + "step": 130 + }, + { + "epoch": 0.8238993710691824, + "grad_norm": 0.36771783232688904, + "learning_rate": 4.552245919255117e-05, + "loss": 0.5778, + "step": 131 + }, + { + "epoch": 0.8301886792452831, + "grad_norm": 0.3695763647556305, + "learning_rate": 4.541735956498554e-05, + "loss": 0.517, + "step": 132 + }, + { + "epoch": 0.8364779874213837, + "grad_norm": 0.46155717968940735, + "learning_rate": 4.5311165016389916e-05, + "loss": 0.631, + "step": 133 + }, + { + "epoch": 0.8427672955974843, + "grad_norm": 0.5536386966705322, + "learning_rate": 4.5203881241655644e-05, + "loss": 0.6309, + "step": 134 + }, + { + "epoch": 0.8490566037735849, + "grad_norm": 0.42256519198417664, + "learning_rate": 4.509551399408598e-05, + "loss": 0.6754, + "step": 135 + }, + { + "epoch": 0.8553459119496856, + "grad_norm": 0.41634511947631836, + "learning_rate": 4.498606908508754e-05, + "loss": 0.6547, + "step": 136 + }, + { + "epoch": 0.8616352201257862, + "grad_norm": 0.38796696066856384, + "learning_rate": 4.487555238385862e-05, + "loss": 0.5693, + "step": 137 + }, + { + "epoch": 0.8679245283018868, + "grad_norm": 0.43052586913108826, + "learning_rate": 4.476396981707453e-05, + "loss": 0.6655, + "step": 138 + }, + { + "epoch": 0.8742138364779874, + "grad_norm": 0.44500571489334106, + "learning_rate": 4.465132736856969e-05, + "loss": 0.6563, + "step": 139 + }, + { + "epoch": 0.8805031446540881, + "grad_norm": 0.44693946838378906, + "learning_rate": 4.453763107901675e-05, + "loss": 0.5729, + "step": 140 + }, + { + "epoch": 0.8867924528301887, + "grad_norm": 0.3982055187225342, + "learning_rate": 4.442288704560268e-05, + "loss": 0.6425, + "step": 141 + }, + { + "epoch": 0.8930817610062893, + "grad_norm": 0.5706686973571777, + "learning_rate": 4.430710142170176e-05, + "loss": 0.5732, + "step": 142 + }, + { + "epoch": 0.89937106918239, + "grad_norm": 0.4493609070777893, + "learning_rate": 4.419028041654559e-05, + "loss": 0.6507, + "step": 143 + }, + { + "epoch": 0.9056603773584906, + "grad_norm": 0.3834284543991089, + "learning_rate": 4.4072430294890174e-05, + "loss": 0.6883, + "step": 144 + }, + { + "epoch": 0.9119496855345912, + "grad_norm": 0.4243861138820648, + "learning_rate": 4.3953557376679856e-05, + "loss": 0.5818, + "step": 145 + }, + { + "epoch": 0.9182389937106918, + "grad_norm": 0.42064470052719116, + "learning_rate": 4.383366803670849e-05, + "loss": 0.5963, + "step": 146 + }, + { + "epoch": 0.9245283018867925, + "grad_norm": 0.46670740842819214, + "learning_rate": 4.371276870427753e-05, + "loss": 0.65, + "step": 147 + }, + { + "epoch": 0.9308176100628931, + "grad_norm": 0.44945597648620605, + "learning_rate": 4.359086586285127e-05, + "loss": 0.6554, + "step": 148 + }, + { + "epoch": 0.9371069182389937, + "grad_norm": 0.48251762986183167, + "learning_rate": 4.346796604970912e-05, + "loss": 0.6681, + "step": 149 + }, + { + "epoch": 0.9433962264150944, + "grad_norm": 0.4577901065349579, + "learning_rate": 4.3344075855595104e-05, + "loss": 0.6108, + "step": 150 + }, + { + "epoch": 0.949685534591195, + "grad_norm": 0.4710671603679657, + "learning_rate": 4.321920192436433e-05, + "loss": 0.6177, + "step": 151 + }, + { + "epoch": 0.9559748427672956, + "grad_norm": 0.4275747835636139, + "learning_rate": 4.309335095262676e-05, + "loss": 0.5881, + "step": 152 + }, + { + "epoch": 0.9622641509433962, + "grad_norm": 0.4541204571723938, + "learning_rate": 4.296652968938807e-05, + "loss": 0.6142, + "step": 153 + }, + { + "epoch": 0.9685534591194969, + "grad_norm": 0.4179267883300781, + "learning_rate": 4.283874493568772e-05, + "loss": 0.6463, + "step": 154 + }, + { + "epoch": 0.9748427672955975, + "grad_norm": 0.42434728145599365, + "learning_rate": 4.271000354423426e-05, + "loss": 0.5873, + "step": 155 + }, + { + "epoch": 0.9811320754716981, + "grad_norm": 0.44202134013175964, + "learning_rate": 4.258031241903778e-05, + "loss": 0.6046, + "step": 156 + }, + { + "epoch": 0.9874213836477987, + "grad_norm": 0.47817060351371765, + "learning_rate": 4.2449678515039747e-05, + "loss": 0.5989, + "step": 157 + }, + { + "epoch": 0.9937106918238994, + "grad_norm": 0.43847018480300903, + "learning_rate": 4.231810883773999e-05, + "loss": 0.6156, + "step": 158 + }, + { + "epoch": 1.0, + "grad_norm": 0.48976290225982666, + "learning_rate": 4.218561044282099e-05, + "loss": 0.6177, + "step": 159 + }, + { + "epoch": 1.0062893081761006, + "grad_norm": 0.4213927984237671, + "learning_rate": 4.2052190435769554e-05, + "loss": 0.5881, + "step": 160 + }, + { + "epoch": 1.0125786163522013, + "grad_norm": 0.3923173248767853, + "learning_rate": 4.191785597149577e-05, + "loss": 0.5354, + "step": 161 + }, + { + "epoch": 1.0188679245283019, + "grad_norm": 0.41947099566459656, + "learning_rate": 4.178261425394926e-05, + "loss": 0.5745, + "step": 162 + }, + { + "epoch": 1.0251572327044025, + "grad_norm": 0.45812028646469116, + "learning_rate": 4.1646472535732895e-05, + "loss": 0.5836, + "step": 163 + }, + { + "epoch": 1.0314465408805031, + "grad_norm": 0.4519791007041931, + "learning_rate": 4.1509438117713866e-05, + "loss": 0.6118, + "step": 164 + }, + { + "epoch": 1.0377358490566038, + "grad_norm": 0.5628229379653931, + "learning_rate": 4.137151834863213e-05, + "loss": 0.5811, + "step": 165 + }, + { + "epoch": 1.0440251572327044, + "grad_norm": 0.3987003564834595, + "learning_rate": 4.123272062470633e-05, + "loss": 0.5179, + "step": 166 + }, + { + "epoch": 1.050314465408805, + "grad_norm": 0.4499664604663849, + "learning_rate": 4.109305238923718e-05, + "loss": 0.548, + "step": 167 + }, + { + "epoch": 1.0566037735849056, + "grad_norm": 0.4336049556732178, + "learning_rate": 4.095252113220827e-05, + "loss": 0.5659, + "step": 168 + }, + { + "epoch": 1.0628930817610063, + "grad_norm": 0.5409331321716309, + "learning_rate": 4.0811134389884433e-05, + "loss": 0.5522, + "step": 169 + }, + { + "epoch": 1.069182389937107, + "grad_norm": 0.41802865266799927, + "learning_rate": 4.066889974440757e-05, + "loss": 0.542, + "step": 170 + }, + { + "epoch": 1.0754716981132075, + "grad_norm": 0.48149824142456055, + "learning_rate": 4.0525824823390045e-05, + "loss": 0.6131, + "step": 171 + }, + { + "epoch": 1.0817610062893082, + "grad_norm": 0.5059295296669006, + "learning_rate": 4.038191729950569e-05, + "loss": 0.5823, + "step": 172 + }, + { + "epoch": 1.0880503144654088, + "grad_norm": 0.5310669541358948, + "learning_rate": 4.0237184890078245e-05, + "loss": 0.6066, + "step": 173 + }, + { + "epoch": 1.0943396226415094, + "grad_norm": 0.5470696091651917, + "learning_rate": 4.009163535666761e-05, + "loss": 0.6407, + "step": 174 + }, + { + "epoch": 1.10062893081761, + "grad_norm": 0.4407522678375244, + "learning_rate": 3.994527650465352e-05, + "loss": 0.573, + "step": 175 + }, + { + "epoch": 1.1069182389937107, + "grad_norm": 0.4072059094905853, + "learning_rate": 3.979811618281706e-05, + "loss": 0.6349, + "step": 176 + }, + { + "epoch": 1.1132075471698113, + "grad_norm": 0.6410146355628967, + "learning_rate": 3.9650162282919655e-05, + "loss": 0.6036, + "step": 177 + }, + { + "epoch": 1.119496855345912, + "grad_norm": 0.4664185047149658, + "learning_rate": 3.9501422739279956e-05, + "loss": 0.5855, + "step": 178 + }, + { + "epoch": 1.1257861635220126, + "grad_norm": 0.7204552888870239, + "learning_rate": 3.9351905528348285e-05, + "loss": 0.5719, + "step": 179 + }, + { + "epoch": 1.1320754716981132, + "grad_norm": 0.47248926758766174, + "learning_rate": 3.920161866827889e-05, + "loss": 0.5764, + "step": 180 + }, + { + "epoch": 1.1383647798742138, + "grad_norm": 0.64155113697052, + "learning_rate": 3.90505702185e-05, + "loss": 0.644, + "step": 181 + }, + { + "epoch": 1.1446540880503144, + "grad_norm": 0.5559830665588379, + "learning_rate": 3.889876827928156e-05, + "loss": 0.5883, + "step": 182 + }, + { + "epoch": 1.150943396226415, + "grad_norm": 0.46357718110084534, + "learning_rate": 3.874622099130087e-05, + "loss": 0.5942, + "step": 183 + }, + { + "epoch": 1.1572327044025157, + "grad_norm": 0.4527578055858612, + "learning_rate": 3.859293653520604e-05, + "loss": 0.6086, + "step": 184 + }, + { + "epoch": 1.1635220125786163, + "grad_norm": 0.45968765020370483, + "learning_rate": 3.843892313117724e-05, + "loss": 0.6105, + "step": 185 + }, + { + "epoch": 1.169811320754717, + "grad_norm": 0.5293806791305542, + "learning_rate": 3.8284189038485936e-05, + "loss": 0.5622, + "step": 186 + }, + { + "epoch": 1.1761006289308176, + "grad_norm": 0.4499124586582184, + "learning_rate": 3.812874255505191e-05, + "loss": 0.5451, + "step": 187 + }, + { + "epoch": 1.1823899371069182, + "grad_norm": 0.5140619277954102, + "learning_rate": 3.797259201699833e-05, + "loss": 0.5864, + "step": 188 + }, + { + "epoch": 1.1886792452830188, + "grad_norm": 0.40918025374412537, + "learning_rate": 3.781574579820464e-05, + "loss": 0.5602, + "step": 189 + }, + { + "epoch": 1.1949685534591195, + "grad_norm": 0.4417194128036499, + "learning_rate": 3.765821230985758e-05, + "loss": 0.5556, + "step": 190 + }, + { + "epoch": 1.20125786163522, + "grad_norm": 0.4697968363761902, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.6491, + "step": 191 + }, + { + "epoch": 1.2075471698113207, + "grad_norm": 0.40187153220176697, + "learning_rate": 3.7341117353077966e-05, + "loss": 0.5797, + "step": 192 + }, + { + "epoch": 1.2138364779874213, + "grad_norm": 0.456836462020874, + "learning_rate": 3.718157288948563e-05, + "loss": 0.5613, + "step": 193 + }, + { + "epoch": 1.220125786163522, + "grad_norm": 0.45992621779441833, + "learning_rate": 3.702137516510838e-05, + "loss": 0.6301, + "step": 194 + }, + { + "epoch": 1.2264150943396226, + "grad_norm": 0.45000532269477844, + "learning_rate": 3.686053277086401e-05, + "loss": 0.5772, + "step": 195 + }, + { + "epoch": 1.2327044025157232, + "grad_norm": 0.4734075963497162, + "learning_rate": 3.669905433224199e-05, + "loss": 0.5452, + "step": 196 + }, + { + "epoch": 1.2389937106918238, + "grad_norm": 0.41561609506607056, + "learning_rate": 3.653694850884091e-05, + "loss": 0.5365, + "step": 197 + }, + { + "epoch": 1.2452830188679245, + "grad_norm": 0.469097763299942, + "learning_rate": 3.637422399390413e-05, + "loss": 0.5396, + "step": 198 + }, + { + "epoch": 1.251572327044025, + "grad_norm": 0.46705111861228943, + "learning_rate": 3.621088951385353e-05, + "loss": 0.6024, + "step": 199 + }, + { + "epoch": 1.2578616352201257, + "grad_norm": 0.5201407074928284, + "learning_rate": 3.604695382782159e-05, + "loss": 0.6905, + "step": 200 + }, + { + "epoch": 1.2641509433962264, + "grad_norm": 0.4639309346675873, + "learning_rate": 3.588242572718162e-05, + "loss": 0.5909, + "step": 201 + }, + { + "epoch": 1.270440251572327, + "grad_norm": 0.4756741225719452, + "learning_rate": 3.5717314035076355e-05, + "loss": 0.5745, + "step": 202 + }, + { + "epoch": 1.2767295597484276, + "grad_norm": 0.5243765115737915, + "learning_rate": 3.5551627605944745e-05, + "loss": 0.6439, + "step": 203 + }, + { + "epoch": 1.2830188679245282, + "grad_norm": 0.4495748281478882, + "learning_rate": 3.5385375325047166e-05, + "loss": 0.5611, + "step": 204 + }, + { + "epoch": 1.2893081761006289, + "grad_norm": 0.47336816787719727, + "learning_rate": 3.521856610798887e-05, + "loss": 0.5846, + "step": 205 + }, + { + "epoch": 1.2955974842767295, + "grad_norm": 0.4667642116546631, + "learning_rate": 3.505120890024195e-05, + "loss": 0.5982, + "step": 206 + }, + { + "epoch": 1.3018867924528301, + "grad_norm": 0.4477729797363281, + "learning_rate": 3.4883312676665536e-05, + "loss": 0.6265, + "step": 207 + }, + { + "epoch": 1.3081761006289307, + "grad_norm": 0.5078469514846802, + "learning_rate": 3.4714886441024574e-05, + "loss": 0.5161, + "step": 208 + }, + { + "epoch": 1.3144654088050314, + "grad_norm": 0.5072935819625854, + "learning_rate": 3.4545939225506934e-05, + "loss": 0.5408, + "step": 209 + }, + { + "epoch": 1.320754716981132, + "grad_norm": 0.5006597638130188, + "learning_rate": 3.437648009023905e-05, + "loss": 0.5715, + "step": 210 + }, + { + "epoch": 1.3270440251572326, + "grad_norm": 0.44206503033638, + "learning_rate": 3.420651812280006e-05, + "loss": 0.5694, + "step": 211 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.4964762032032013, + "learning_rate": 3.4036062437734484e-05, + "loss": 0.5203, + "step": 212 + }, + { + "epoch": 1.3396226415094339, + "grad_norm": 0.4342876076698303, + "learning_rate": 3.386512217606339e-05, + "loss": 0.5778, + "step": 213 + }, + { + "epoch": 1.3459119496855345, + "grad_norm": 0.46520864963531494, + "learning_rate": 3.369370650479425e-05, + "loss": 0.5757, + "step": 214 + }, + { + "epoch": 1.3522012578616351, + "grad_norm": 0.5179557204246521, + "learning_rate": 3.3521824616429285e-05, + "loss": 0.5348, + "step": 215 + }, + { + "epoch": 1.3584905660377358, + "grad_norm": 0.45922955870628357, + "learning_rate": 3.3349485728472535e-05, + "loss": 0.5982, + "step": 216 + }, + { + "epoch": 1.3647798742138364, + "grad_norm": 0.5132372975349426, + "learning_rate": 3.3176699082935545e-05, + "loss": 0.6131, + "step": 217 + }, + { + "epoch": 1.371069182389937, + "grad_norm": 0.4740884602069855, + "learning_rate": 3.300347394584172e-05, + "loss": 0.6194, + "step": 218 + }, + { + "epoch": 1.3773584905660377, + "grad_norm": 0.45677605271339417, + "learning_rate": 3.282981960672948e-05, + "loss": 0.5938, + "step": 219 + }, + { + "epoch": 1.3836477987421385, + "grad_norm": 0.4545290172100067, + "learning_rate": 3.265574537815398e-05, + "loss": 0.5634, + "step": 220 + }, + { + "epoch": 1.389937106918239, + "grad_norm": 0.4439068138599396, + "learning_rate": 3.248126059518785e-05, + "loss": 0.5543, + "step": 221 + }, + { + "epoch": 1.3962264150943398, + "grad_norm": 0.4973136782646179, + "learning_rate": 3.230637461492043e-05, + "loss": 0.549, + "step": 222 + }, + { + "epoch": 1.4025157232704402, + "grad_norm": 0.5018147826194763, + "learning_rate": 3.213109681595612e-05, + "loss": 0.5799, + "step": 223 + }, + { + "epoch": 1.408805031446541, + "grad_norm": 0.4906245768070221, + "learning_rate": 3.195543659791132e-05, + "loss": 0.5788, + "step": 224 + }, + { + "epoch": 1.4150943396226414, + "grad_norm": 0.5228400826454163, + "learning_rate": 3.177940338091043e-05, + "loss": 0.4883, + "step": 225 + }, + { + "epoch": 1.4213836477987423, + "grad_norm": 0.5177304148674011, + "learning_rate": 3.160300660508064e-05, + "loss": 0.5737, + "step": 226 + }, + { + "epoch": 1.4276729559748427, + "grad_norm": 0.4641788899898529, + "learning_rate": 3.14262557300457e-05, + "loss": 0.5416, + "step": 227 + }, + { + "epoch": 1.4339622641509435, + "grad_norm": 0.49331700801849365, + "learning_rate": 3.124916023441865e-05, + "loss": 0.5747, + "step": 228 + }, + { + "epoch": 1.440251572327044, + "grad_norm": 0.4671120345592499, + "learning_rate": 3.107172961529343e-05, + "loss": 0.508, + "step": 229 + }, + { + "epoch": 1.4465408805031448, + "grad_norm": 0.5811720490455627, + "learning_rate": 3.0893973387735687e-05, + "loss": 0.6929, + "step": 230 + }, + { + "epoch": 1.4528301886792452, + "grad_norm": 0.48253801465034485, + "learning_rate": 3.071590108427244e-05, + "loss": 0.6467, + "step": 231 + }, + { + "epoch": 1.459119496855346, + "grad_norm": 0.5044742226600647, + "learning_rate": 3.0537522254380905e-05, + "loss": 0.5067, + "step": 232 + }, + { + "epoch": 1.4654088050314464, + "grad_norm": 0.5015671849250793, + "learning_rate": 3.0358846463976372e-05, + "loss": 0.6052, + "step": 233 + }, + { + "epoch": 1.4716981132075473, + "grad_norm": 0.5023432374000549, + "learning_rate": 3.017988329489923e-05, + "loss": 0.5961, + "step": 234 + }, + { + "epoch": 1.4779874213836477, + "grad_norm": 0.5157131552696228, + "learning_rate": 3.0000642344401113e-05, + "loss": 0.6285, + "step": 235 + }, + { + "epoch": 1.4842767295597485, + "grad_norm": 0.5081720948219299, + "learning_rate": 2.9821133224630226e-05, + "loss": 0.4634, + "step": 236 + }, + { + "epoch": 1.490566037735849, + "grad_norm": 0.4940662086009979, + "learning_rate": 2.9641365562115887e-05, + "loss": 0.5288, + "step": 237 + }, + { + "epoch": 1.4968553459119498, + "grad_norm": 0.6005929708480835, + "learning_rate": 2.9461348997252265e-05, + "loss": 0.5748, + "step": 238 + }, + { + "epoch": 1.5031446540880502, + "grad_norm": 0.5340356230735779, + "learning_rate": 2.9281093183781403e-05, + "loss": 0.5944, + "step": 239 + }, + { + "epoch": 1.509433962264151, + "grad_norm": 0.5056872367858887, + "learning_rate": 2.9100607788275545e-05, + "loss": 0.5549, + "step": 240 + }, + { + "epoch": 1.5157232704402515, + "grad_norm": 0.5385233759880066, + "learning_rate": 2.891990248961871e-05, + "loss": 0.5345, + "step": 241 + }, + { + "epoch": 1.5220125786163523, + "grad_norm": 0.48144999146461487, + "learning_rate": 2.8738986978487625e-05, + "loss": 0.5839, + "step": 242 + }, + { + "epoch": 1.5283018867924527, + "grad_norm": 0.5069999098777771, + "learning_rate": 2.8557870956832132e-05, + "loss": 0.4931, + "step": 243 + }, + { + "epoch": 1.5345911949685536, + "grad_norm": 0.4660912752151489, + "learning_rate": 2.8376564137354795e-05, + "loss": 0.5598, + "step": 244 + }, + { + "epoch": 1.540880503144654, + "grad_norm": 0.5416334271430969, + "learning_rate": 2.8195076242990122e-05, + "loss": 0.5894, + "step": 245 + }, + { + "epoch": 1.5471698113207548, + "grad_norm": 0.49134501814842224, + "learning_rate": 2.8013417006383076e-05, + "loss": 0.6345, + "step": 246 + }, + { + "epoch": 1.5534591194968552, + "grad_norm": 0.5861812829971313, + "learning_rate": 2.783159616936723e-05, + "loss": 0.6519, + "step": 247 + }, + { + "epoch": 1.559748427672956, + "grad_norm": 0.47188055515289307, + "learning_rate": 2.764962348244228e-05, + "loss": 0.5658, + "step": 248 + }, + { + "epoch": 1.5660377358490565, + "grad_norm": 0.4838746190071106, + "learning_rate": 2.7467508704251137e-05, + "loss": 0.5934, + "step": 249 + }, + { + "epoch": 1.5723270440251573, + "grad_norm": 0.516981840133667, + "learning_rate": 2.7285261601056698e-05, + "loss": 0.5341, + "step": 250 + }, + { + "epoch": 1.5786163522012577, + "grad_norm": 0.4871889352798462, + "learning_rate": 2.7102891946217994e-05, + "loss": 0.5885, + "step": 251 + }, + { + "epoch": 1.5849056603773586, + "grad_norm": 0.47121965885162354, + "learning_rate": 2.6920409519666174e-05, + "loss": 0.5988, + "step": 252 + }, + { + "epoch": 1.591194968553459, + "grad_norm": 0.5421566367149353, + "learning_rate": 2.6737824107379948e-05, + "loss": 0.6635, + "step": 253 + }, + { + "epoch": 1.5974842767295598, + "grad_norm": 0.5449573993682861, + "learning_rate": 2.655514550086086e-05, + "loss": 0.5365, + "step": 254 + }, + { + "epoch": 1.6037735849056602, + "grad_norm": 0.5301252007484436, + "learning_rate": 2.637238349660819e-05, + "loss": 0.6854, + "step": 255 + }, + { + "epoch": 1.610062893081761, + "grad_norm": 0.41109421849250793, + "learning_rate": 2.6189547895593562e-05, + "loss": 0.5234, + "step": 256 + }, + { + "epoch": 1.6163522012578615, + "grad_norm": 0.5346055626869202, + "learning_rate": 2.600664850273538e-05, + "loss": 0.5962, + "step": 257 + }, + { + "epoch": 1.6226415094339623, + "grad_norm": 0.5180861949920654, + "learning_rate": 2.582369512637302e-05, + "loss": 0.5396, + "step": 258 + }, + { + "epoch": 1.6289308176100628, + "grad_norm": 0.49982312321662903, + "learning_rate": 2.564069757774082e-05, + "loss": 0.4889, + "step": 259 + }, + { + "epoch": 1.6352201257861636, + "grad_norm": 0.5226275324821472, + "learning_rate": 2.545766567044194e-05, + "loss": 0.5893, + "step": 260 + }, + { + "epoch": 1.641509433962264, + "grad_norm": 0.47939932346343994, + "learning_rate": 2.527460921992209e-05, + "loss": 0.566, + "step": 261 + }, + { + "epoch": 1.6477987421383649, + "grad_norm": 0.536264955997467, + "learning_rate": 2.509153804294318e-05, + "loss": 0.5598, + "step": 262 + }, + { + "epoch": 1.6540880503144653, + "grad_norm": 0.5297203660011292, + "learning_rate": 2.490846195705683e-05, + "loss": 0.552, + "step": 263 + }, + { + "epoch": 1.6603773584905661, + "grad_norm": 0.5188955664634705, + "learning_rate": 2.4725390780077908e-05, + "loss": 0.6233, + "step": 264 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.4677969217300415, + "learning_rate": 2.4542334329558077e-05, + "loss": 0.4968, + "step": 265 + }, + { + "epoch": 1.6729559748427674, + "grad_norm": 0.5716769099235535, + "learning_rate": 2.435930242225919e-05, + "loss": 0.5315, + "step": 266 + }, + { + "epoch": 1.6792452830188678, + "grad_norm": 0.5071538090705872, + "learning_rate": 2.4176304873626985e-05, + "loss": 0.5622, + "step": 267 + }, + { + "epoch": 1.6855345911949686, + "grad_norm": 0.523229718208313, + "learning_rate": 2.399335149726463e-05, + "loss": 0.5999, + "step": 268 + }, + { + "epoch": 1.691823899371069, + "grad_norm": 0.5254403948783875, + "learning_rate": 2.3810452104406444e-05, + "loss": 0.6351, + "step": 269 + }, + { + "epoch": 1.6981132075471699, + "grad_norm": 0.53160560131073, + "learning_rate": 2.3627616503391814e-05, + "loss": 0.5754, + "step": 270 + }, + { + "epoch": 1.7044025157232703, + "grad_norm": 0.5396912693977356, + "learning_rate": 2.3444854499139142e-05, + "loss": 0.5635, + "step": 271 + }, + { + "epoch": 1.7106918238993711, + "grad_norm": 0.5528764724731445, + "learning_rate": 2.3262175892620065e-05, + "loss": 0.5368, + "step": 272 + }, + { + "epoch": 1.7169811320754715, + "grad_norm": 0.4812920093536377, + "learning_rate": 2.307959048033383e-05, + "loss": 0.5508, + "step": 273 + }, + { + "epoch": 1.7232704402515724, + "grad_norm": 0.5467996001243591, + "learning_rate": 2.2897108053782e-05, + "loss": 0.6073, + "step": 274 + }, + { + "epoch": 1.7295597484276728, + "grad_norm": 0.5203157663345337, + "learning_rate": 2.271473839894331e-05, + "loss": 0.5326, + "step": 275 + }, + { + "epoch": 1.7358490566037736, + "grad_norm": 0.4970155358314514, + "learning_rate": 2.253249129574887e-05, + "loss": 0.5444, + "step": 276 + }, + { + "epoch": 1.742138364779874, + "grad_norm": 0.5279742479324341, + "learning_rate": 2.2350376517557727e-05, + "loss": 0.5778, + "step": 277 + }, + { + "epoch": 1.748427672955975, + "grad_norm": 0.5293897986412048, + "learning_rate": 2.216840383063277e-05, + "loss": 0.5786, + "step": 278 + }, + { + "epoch": 1.7547169811320755, + "grad_norm": 0.565350353717804, + "learning_rate": 2.1986582993616926e-05, + "loss": 0.5877, + "step": 279 + }, + { + "epoch": 1.7610062893081762, + "grad_norm": 0.47762683033943176, + "learning_rate": 2.1804923757009884e-05, + "loss": 0.5419, + "step": 280 + }, + { + "epoch": 1.7672955974842768, + "grad_norm": 0.5171676278114319, + "learning_rate": 2.1623435862645204e-05, + "loss": 0.5418, + "step": 281 + }, + { + "epoch": 1.7735849056603774, + "grad_norm": 0.45764029026031494, + "learning_rate": 2.1442129043167874e-05, + "loss": 0.5487, + "step": 282 + }, + { + "epoch": 1.779874213836478, + "grad_norm": 0.5272729396820068, + "learning_rate": 2.126101302151238e-05, + "loss": 0.5317, + "step": 283 + }, + { + "epoch": 1.7861635220125787, + "grad_norm": 0.49889740347862244, + "learning_rate": 2.1080097510381298e-05, + "loss": 0.6046, + "step": 284 + }, + { + "epoch": 1.7924528301886793, + "grad_norm": 0.5512136220932007, + "learning_rate": 2.089939221172446e-05, + "loss": 0.6541, + "step": 285 + }, + { + "epoch": 1.79874213836478, + "grad_norm": 0.5187536478042603, + "learning_rate": 2.07189068162186e-05, + "loss": 0.5646, + "step": 286 + }, + { + "epoch": 1.8050314465408805, + "grad_norm": 0.4920225143432617, + "learning_rate": 2.0538651002747744e-05, + "loss": 0.5561, + "step": 287 + }, + { + "epoch": 1.8113207547169812, + "grad_norm": 0.5807557702064514, + "learning_rate": 2.0358634437884112e-05, + "loss": 0.6087, + "step": 288 + }, + { + "epoch": 1.8176100628930818, + "grad_norm": 0.48779597878456116, + "learning_rate": 2.0178866775369777e-05, + "loss": 0.5801, + "step": 289 + }, + { + "epoch": 1.8238993710691824, + "grad_norm": 0.47587329149246216, + "learning_rate": 1.9999357655598893e-05, + "loss": 0.6003, + "step": 290 + }, + { + "epoch": 1.830188679245283, + "grad_norm": 0.5073649883270264, + "learning_rate": 1.9820116705100777e-05, + "loss": 0.5838, + "step": 291 + }, + { + "epoch": 1.8364779874213837, + "grad_norm": 0.5661832690238953, + "learning_rate": 1.9641153536023644e-05, + "loss": 0.6054, + "step": 292 + }, + { + "epoch": 1.8427672955974843, + "grad_norm": 0.4822792410850525, + "learning_rate": 1.9462477745619108e-05, + "loss": 0.5515, + "step": 293 + }, + { + "epoch": 1.849056603773585, + "grad_norm": 0.5438389182090759, + "learning_rate": 1.928409891572757e-05, + "loss": 0.6225, + "step": 294 + }, + { + "epoch": 1.8553459119496856, + "grad_norm": 0.4644525647163391, + "learning_rate": 1.9106026612264316e-05, + "loss": 0.6214, + "step": 295 + }, + { + "epoch": 1.8616352201257862, + "grad_norm": 0.477500855922699, + "learning_rate": 1.8928270384706584e-05, + "loss": 0.6164, + "step": 296 + }, + { + "epoch": 1.8679245283018868, + "grad_norm": 0.4944886267185211, + "learning_rate": 1.875083976558136e-05, + "loss": 0.5533, + "step": 297 + }, + { + "epoch": 1.8742138364779874, + "grad_norm": 0.5480766892433167, + "learning_rate": 1.8573744269954298e-05, + "loss": 0.6305, + "step": 298 + }, + { + "epoch": 1.880503144654088, + "grad_norm": 0.5053893327713013, + "learning_rate": 1.8396993394919372e-05, + "loss": 0.574, + "step": 299 + }, + { + "epoch": 1.8867924528301887, + "grad_norm": 0.559573233127594, + "learning_rate": 1.8220596619089576e-05, + "loss": 0.7138, + "step": 300 + } + ], + "logging_steps": 1, + "max_steps": 477, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.988668221887873e+18, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f2a1106da97275ded3721a2b9ad28a19b5c9872 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d245efe4cb1811ec2cffc23b4d3aa9a49d1d65e92b8d678bec9a399e5c1889e +size 5496 diff --git a/checkpoint-400/._README.md b/checkpoint-400/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..a267f7cd012a279d5a6bfc56e3822df8e6fdb52a Binary files /dev/null and b/checkpoint-400/._README.md differ diff --git a/checkpoint-400/._adapter_config.json b/checkpoint-400/._adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c716c4feb9a9692f34ec5ffa7389fe31dd790ef3 Binary files /dev/null and b/checkpoint-400/._adapter_config.json differ diff --git a/checkpoint-400/._adapter_model.safetensors b/checkpoint-400/._adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6424fc39c8a50510c116697a344b284c6290a4b7 --- /dev/null +++ b/checkpoint-400/._adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7fa4bd30ad6b03e2424e9e75b28ca71fe1ab67baf5c55afd091a30a62e783b +size 4096 diff --git a/checkpoint-400/._optimizer.pt b/checkpoint-400/._optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..b2883ccc7c68c650e601cd40f2cf75602d1962eb --- /dev/null +++ b/checkpoint-400/._optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed5149efa0dac7a9026f8924efad0e253103731ab62bae56758a0b63f96344f +size 4096 diff --git a/checkpoint-400/._rng_state.pth b/checkpoint-400/._rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa1288f2cbc5a8a1c53656f05e056a31e96b7541 --- /dev/null +++ b/checkpoint-400/._rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c6eadfcba473a497015c0e04d8ead5e55dd4f8e823518305e2eedfa150eee9 +size 4096 diff --git a/checkpoint-400/._scheduler.pt b/checkpoint-400/._scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..63e776cbfd43ed2a83dc181f486c8e9a3ad9a6c8 --- /dev/null +++ b/checkpoint-400/._scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a293fe239ae90163fca6880d7bcb57f0f7e9022c34e429ce1cab2a9b11bbc1d +size 4096 diff --git a/checkpoint-400/._special_tokens_map.json b/checkpoint-400/._special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..08c633f005eb574e9358a055e77897ceb85e452e Binary files /dev/null and b/checkpoint-400/._special_tokens_map.json differ diff --git a/checkpoint-400/._tokenizer.json b/checkpoint-400/._tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..10f602b5cabb000f7b856736b44b12a27eddfafc Binary files /dev/null and b/checkpoint-400/._tokenizer.json differ diff --git a/checkpoint-400/._tokenizer_config.json b/checkpoint-400/._tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..865d7b675ea3affd966f0c12837710c8f54be6d2 Binary files /dev/null and b/checkpoint-400/._tokenizer_config.json differ diff --git a/checkpoint-400/._trainer_state.json b/checkpoint-400/._trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..993d428620db2f219896d28df86502d1ac40fb7a Binary files /dev/null and b/checkpoint-400/._trainer_state.json differ diff --git a/checkpoint-400/._training_args.bin b/checkpoint-400/._training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..02add18f7ff5f1416c4eb7a9897e98961e8d72ea --- /dev/null +++ b/checkpoint-400/._training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d224c84e76b7154a3d120273c59cd9aa988de1dcd0d55f15f7982b7086b57530 +size 4096 diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0d0f45d57897230f208f7d5fa62f85e8481f2f2f --- /dev/null +++ b/checkpoint-400/README.md @@ -0,0 +1,202 @@ +--- +base_model: /scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b43c336eadd307192f9ebaaca58b283a56db147d --- /dev/null +++ b/checkpoint-400/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "v_proj", + "up_proj", + "q_proj", + "down_proj", + "gate_proj", + "o_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..41aa23cec4518f13baede25312823b17b7b399f1 --- /dev/null +++ b/checkpoint-400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468976733083cd9d419685b486714d9df34d72c807d8797f535511c46947213c +size 414337624 diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6058a5f457daf31ab4aca0e2aa2cac95460ca60 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19fdd23c0564893471dbd2d7f05903fe1966e88ae1dc12dc1acb5d43ccd6ee6e +size 829323250 diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5 --- /dev/null +++ b/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d +size 14244 diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f12b83187b89c57d535dccffa167054645a866b8 --- /dev/null +++ b/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7accd2b144684401635f6ef9918888cc6c2175a9211006d40fbbca912b37bf +size 1064 diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/checkpoint-400/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-400/tokenizer.json b/checkpoint-400/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/checkpoint-400/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1913e5051ba2d9c350141f19b01d55276096bc3 --- /dev/null +++ b/checkpoint-400/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a42e3cbcf9a52cc565673bea8c45795955e68507 --- /dev/null +++ b/checkpoint-400/trainer_state.json @@ -0,0 +1,2833 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.5157232704402515, + "eval_steps": 500, + "global_step": 400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.006289308176100629, + "grad_norm": 4.8737874031066895, + "learning_rate": 1.0416666666666667e-06, + "loss": 3.6915, + "step": 1 + }, + { + "epoch": 0.012578616352201259, + "grad_norm": 4.941007137298584, + "learning_rate": 2.0833333333333334e-06, + "loss": 3.6352, + "step": 2 + }, + { + "epoch": 0.018867924528301886, + "grad_norm": 5.258031368255615, + "learning_rate": 3.125e-06, + "loss": 3.5816, + "step": 3 + }, + { + "epoch": 0.025157232704402517, + "grad_norm": 5.544358253479004, + "learning_rate": 4.166666666666667e-06, + "loss": 3.6233, + "step": 4 + }, + { + "epoch": 0.031446540880503145, + "grad_norm": 5.457708835601807, + "learning_rate": 5.208333333333334e-06, + "loss": 3.6107, + "step": 5 + }, + { + "epoch": 0.03773584905660377, + "grad_norm": 5.185223579406738, + "learning_rate": 6.25e-06, + "loss": 3.6277, + "step": 6 + }, + { + "epoch": 0.0440251572327044, + "grad_norm": 5.433485507965088, + "learning_rate": 7.2916666666666674e-06, + "loss": 3.4974, + "step": 7 + }, + { + "epoch": 0.050314465408805034, + "grad_norm": 5.38355016708374, + "learning_rate": 8.333333333333334e-06, + "loss": 3.5021, + "step": 8 + }, + { + "epoch": 0.05660377358490566, + "grad_norm": 5.851156234741211, + "learning_rate": 9.375000000000001e-06, + "loss": 3.5888, + "step": 9 + }, + { + "epoch": 0.06289308176100629, + "grad_norm": 8.335844993591309, + "learning_rate": 1.0416666666666668e-05, + "loss": 3.3652, + "step": 10 + }, + { + "epoch": 0.06918238993710692, + "grad_norm": 5.598583698272705, + "learning_rate": 1.1458333333333333e-05, + "loss": 3.1476, + "step": 11 + }, + { + "epoch": 0.07547169811320754, + "grad_norm": 6.811880588531494, + "learning_rate": 1.25e-05, + "loss": 3.6846, + "step": 12 + }, + { + "epoch": 0.08176100628930817, + "grad_norm": 5.962316513061523, + "learning_rate": 1.3541666666666666e-05, + "loss": 3.2959, + "step": 13 + }, + { + "epoch": 0.0880503144654088, + "grad_norm": 6.434226989746094, + "learning_rate": 1.4583333333333335e-05, + "loss": 3.3629, + "step": 14 + }, + { + "epoch": 0.09433962264150944, + "grad_norm": 5.959097862243652, + "learning_rate": 1.5625e-05, + "loss": 2.9799, + "step": 15 + }, + { + "epoch": 0.10062893081761007, + "grad_norm": 5.713625907897949, + "learning_rate": 1.6666666666666667e-05, + "loss": 2.8375, + "step": 16 + }, + { + "epoch": 0.1069182389937107, + "grad_norm": 4.679070472717285, + "learning_rate": 1.7708333333333335e-05, + "loss": 2.5298, + "step": 17 + }, + { + "epoch": 0.11320754716981132, + "grad_norm": 4.000007152557373, + "learning_rate": 1.8750000000000002e-05, + "loss": 2.4099, + "step": 18 + }, + { + "epoch": 0.11949685534591195, + "grad_norm": 3.6054141521453857, + "learning_rate": 1.9791666666666665e-05, + "loss": 2.1316, + "step": 19 + }, + { + "epoch": 0.12578616352201258, + "grad_norm": 3.1357152462005615, + "learning_rate": 2.0833333333333336e-05, + "loss": 1.8814, + "step": 20 + }, + { + "epoch": 0.1320754716981132, + "grad_norm": 2.848811149597168, + "learning_rate": 2.1875e-05, + "loss": 1.7786, + "step": 21 + }, + { + "epoch": 0.13836477987421383, + "grad_norm": 2.4006130695343018, + "learning_rate": 2.2916666666666667e-05, + "loss": 1.5133, + "step": 22 + }, + { + "epoch": 0.14465408805031446, + "grad_norm": 2.2537267208099365, + "learning_rate": 2.3958333333333334e-05, + "loss": 1.4229, + "step": 23 + }, + { + "epoch": 0.1509433962264151, + "grad_norm": 2.1117539405822754, + "learning_rate": 2.5e-05, + "loss": 1.3577, + "step": 24 + }, + { + "epoch": 0.15723270440251572, + "grad_norm": 1.5717436075210571, + "learning_rate": 2.604166666666667e-05, + "loss": 1.1501, + "step": 25 + }, + { + "epoch": 0.16352201257861634, + "grad_norm": 1.691366195678711, + "learning_rate": 2.7083333333333332e-05, + "loss": 1.292, + "step": 26 + }, + { + "epoch": 0.16981132075471697, + "grad_norm": 1.4936853647232056, + "learning_rate": 2.8125000000000003e-05, + "loss": 1.1469, + "step": 27 + }, + { + "epoch": 0.1761006289308176, + "grad_norm": 1.2858690023422241, + "learning_rate": 2.916666666666667e-05, + "loss": 1.0433, + "step": 28 + }, + { + "epoch": 0.18238993710691823, + "grad_norm": 1.148773193359375, + "learning_rate": 3.0208333333333334e-05, + "loss": 0.9627, + "step": 29 + }, + { + "epoch": 0.18867924528301888, + "grad_norm": 1.0097932815551758, + "learning_rate": 3.125e-05, + "loss": 0.9103, + "step": 30 + }, + { + "epoch": 0.1949685534591195, + "grad_norm": 0.9332402348518372, + "learning_rate": 3.229166666666667e-05, + "loss": 0.979, + "step": 31 + }, + { + "epoch": 0.20125786163522014, + "grad_norm": 0.8993248343467712, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.9553, + "step": 32 + }, + { + "epoch": 0.20754716981132076, + "grad_norm": 0.7925082445144653, + "learning_rate": 3.4375e-05, + "loss": 0.8379, + "step": 33 + }, + { + "epoch": 0.2138364779874214, + "grad_norm": 0.7847669720649719, + "learning_rate": 3.541666666666667e-05, + "loss": 0.9038, + "step": 34 + }, + { + "epoch": 0.22012578616352202, + "grad_norm": 0.800736665725708, + "learning_rate": 3.6458333333333336e-05, + "loss": 0.8354, + "step": 35 + }, + { + "epoch": 0.22641509433962265, + "grad_norm": 0.6036879420280457, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.8517, + "step": 36 + }, + { + "epoch": 0.23270440251572327, + "grad_norm": 0.6031014919281006, + "learning_rate": 3.854166666666667e-05, + "loss": 0.8702, + "step": 37 + }, + { + "epoch": 0.2389937106918239, + "grad_norm": 0.584917426109314, + "learning_rate": 3.958333333333333e-05, + "loss": 0.8812, + "step": 38 + }, + { + "epoch": 0.24528301886792453, + "grad_norm": 0.5815232396125793, + "learning_rate": 4.0625000000000005e-05, + "loss": 0.8336, + "step": 39 + }, + { + "epoch": 0.25157232704402516, + "grad_norm": 0.5307980179786682, + "learning_rate": 4.166666666666667e-05, + "loss": 0.7162, + "step": 40 + }, + { + "epoch": 0.2578616352201258, + "grad_norm": 0.49309515953063965, + "learning_rate": 4.270833333333333e-05, + "loss": 0.7433, + "step": 41 + }, + { + "epoch": 0.2641509433962264, + "grad_norm": 0.5215100646018982, + "learning_rate": 4.375e-05, + "loss": 0.738, + "step": 42 + }, + { + "epoch": 0.27044025157232704, + "grad_norm": 0.5361147522926331, + "learning_rate": 4.4791666666666673e-05, + "loss": 0.7884, + "step": 43 + }, + { + "epoch": 0.27672955974842767, + "grad_norm": 0.5043961405754089, + "learning_rate": 4.5833333333333334e-05, + "loss": 0.814, + "step": 44 + }, + { + "epoch": 0.2830188679245283, + "grad_norm": 0.476026713848114, + "learning_rate": 4.6875e-05, + "loss": 0.8249, + "step": 45 + }, + { + "epoch": 0.2893081761006289, + "grad_norm": 0.5099363923072815, + "learning_rate": 4.791666666666667e-05, + "loss": 0.7205, + "step": 46 + }, + { + "epoch": 0.29559748427672955, + "grad_norm": 0.4583563208580017, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.7646, + "step": 47 + }, + { + "epoch": 0.3018867924528302, + "grad_norm": 0.5203999876976013, + "learning_rate": 5e-05, + "loss": 0.6697, + "step": 48 + }, + { + "epoch": 0.3081761006289308, + "grad_norm": 0.5025014877319336, + "learning_rate": 4.9999329662935534e-05, + "loss": 0.8134, + "step": 49 + }, + { + "epoch": 0.31446540880503143, + "grad_norm": 0.5326013565063477, + "learning_rate": 4.999731868769027e-05, + "loss": 0.7665, + "step": 50 + }, + { + "epoch": 0.32075471698113206, + "grad_norm": 0.4914862811565399, + "learning_rate": 4.99939671821067e-05, + "loss": 0.7717, + "step": 51 + }, + { + "epoch": 0.3270440251572327, + "grad_norm": 0.567669689655304, + "learning_rate": 4.998927532591592e-05, + "loss": 0.677, + "step": 52 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.44353675842285156, + "learning_rate": 4.9983243370727914e-05, + "loss": 0.6829, + "step": 53 + }, + { + "epoch": 0.33962264150943394, + "grad_norm": 0.48537710309028625, + "learning_rate": 4.9975871640018154e-05, + "loss": 0.7817, + "step": 54 + }, + { + "epoch": 0.34591194968553457, + "grad_norm": 0.6286251544952393, + "learning_rate": 4.996716052911017e-05, + "loss": 0.6835, + "step": 55 + }, + { + "epoch": 0.3522012578616352, + "grad_norm": 0.44308704137802124, + "learning_rate": 4.99571105051544e-05, + "loss": 0.728, + "step": 56 + }, + { + "epoch": 0.3584905660377358, + "grad_norm": 0.4270545542240143, + "learning_rate": 4.994572210710315e-05, + "loss": 0.6448, + "step": 57 + }, + { + "epoch": 0.36477987421383645, + "grad_norm": 0.38012009859085083, + "learning_rate": 4.993299594568163e-05, + "loss": 0.675, + "step": 58 + }, + { + "epoch": 0.3710691823899371, + "grad_norm": 0.46653008460998535, + "learning_rate": 4.9918932703355256e-05, + "loss": 0.6821, + "step": 59 + }, + { + "epoch": 0.37735849056603776, + "grad_norm": 0.3612300753593445, + "learning_rate": 4.990353313429303e-05, + "loss": 0.7063, + "step": 60 + }, + { + "epoch": 0.3836477987421384, + "grad_norm": 0.5769712924957275, + "learning_rate": 4.988679806432712e-05, + "loss": 0.6941, + "step": 61 + }, + { + "epoch": 0.389937106918239, + "grad_norm": 0.431997150182724, + "learning_rate": 4.9868728390908526e-05, + "loss": 0.6544, + "step": 62 + }, + { + "epoch": 0.39622641509433965, + "grad_norm": 0.38126569986343384, + "learning_rate": 4.9849325083059e-05, + "loss": 0.6966, + "step": 63 + }, + { + "epoch": 0.4025157232704403, + "grad_norm": 0.40978091955184937, + "learning_rate": 4.982858918131906e-05, + "loss": 0.6866, + "step": 64 + }, + { + "epoch": 0.4088050314465409, + "grad_norm": 0.5318535566329956, + "learning_rate": 4.980652179769218e-05, + "loss": 0.7029, + "step": 65 + }, + { + "epoch": 0.41509433962264153, + "grad_norm": 0.5288330912590027, + "learning_rate": 4.978312411558518e-05, + "loss": 0.6553, + "step": 66 + }, + { + "epoch": 0.42138364779874216, + "grad_norm": 0.6496341824531555, + "learning_rate": 4.9758397389744734e-05, + "loss": 0.696, + "step": 67 + }, + { + "epoch": 0.4276729559748428, + "grad_norm": 0.5196901559829712, + "learning_rate": 4.973234294619011e-05, + "loss": 0.6676, + "step": 68 + }, + { + "epoch": 0.4339622641509434, + "grad_norm": 0.5431825518608093, + "learning_rate": 4.9704962182142044e-05, + "loss": 0.6337, + "step": 69 + }, + { + "epoch": 0.44025157232704404, + "grad_norm": 0.6981568932533264, + "learning_rate": 4.967625656594782e-05, + "loss": 0.7645, + "step": 70 + }, + { + "epoch": 0.44654088050314467, + "grad_norm": 0.4362429082393646, + "learning_rate": 4.9646227637002515e-05, + "loss": 0.647, + "step": 71 + }, + { + "epoch": 0.4528301886792453, + "grad_norm": 0.41873699426651, + "learning_rate": 4.961487700566646e-05, + "loss": 0.6342, + "step": 72 + }, + { + "epoch": 0.4591194968553459, + "grad_norm": 0.589474081993103, + "learning_rate": 4.958220635317886e-05, + "loss": 0.641, + "step": 73 + }, + { + "epoch": 0.46540880503144655, + "grad_norm": 0.5421208739280701, + "learning_rate": 4.9548217431567665e-05, + "loss": 0.8103, + "step": 74 + }, + { + "epoch": 0.4716981132075472, + "grad_norm": 0.48354727029800415, + "learning_rate": 4.95129120635556e-05, + "loss": 0.6205, + "step": 75 + }, + { + "epoch": 0.4779874213836478, + "grad_norm": 0.6121774911880493, + "learning_rate": 4.9476292142462374e-05, + "loss": 0.6678, + "step": 76 + }, + { + "epoch": 0.48427672955974843, + "grad_norm": 0.5440806150436401, + "learning_rate": 4.943835963210324e-05, + "loss": 0.6668, + "step": 77 + }, + { + "epoch": 0.49056603773584906, + "grad_norm": 0.40740126371383667, + "learning_rate": 4.939911656668361e-05, + "loss": 0.61, + "step": 78 + }, + { + "epoch": 0.4968553459119497, + "grad_norm": 0.5682631731033325, + "learning_rate": 4.9358565050689985e-05, + "loss": 0.6939, + "step": 79 + }, + { + "epoch": 0.5031446540880503, + "grad_norm": 0.43090444803237915, + "learning_rate": 4.93167072587771e-05, + "loss": 0.6698, + "step": 80 + }, + { + "epoch": 0.5094339622641509, + "grad_norm": 0.3859785795211792, + "learning_rate": 4.92735454356513e-05, + "loss": 0.5798, + "step": 81 + }, + { + "epoch": 0.5157232704402516, + "grad_norm": 0.4453634023666382, + "learning_rate": 4.922908189595018e-05, + "loss": 0.7936, + "step": 82 + }, + { + "epoch": 0.5220125786163522, + "grad_norm": 0.4291239380836487, + "learning_rate": 4.9183319024118415e-05, + "loss": 0.667, + "step": 83 + }, + { + "epoch": 0.5283018867924528, + "grad_norm": 0.44029664993286133, + "learning_rate": 4.9136259274279955e-05, + "loss": 0.6518, + "step": 84 + }, + { + "epoch": 0.5345911949685535, + "grad_norm": 0.44975465536117554, + "learning_rate": 4.908790517010636e-05, + "loss": 0.6105, + "step": 85 + }, + { + "epoch": 0.5408805031446541, + "grad_norm": 0.3954753577709198, + "learning_rate": 4.903825930468149e-05, + "loss": 0.6954, + "step": 86 + }, + { + "epoch": 0.5471698113207547, + "grad_norm": 0.3935467302799225, + "learning_rate": 4.898732434036244e-05, + "loss": 0.6614, + "step": 87 + }, + { + "epoch": 0.5534591194968553, + "grad_norm": 0.37667638063430786, + "learning_rate": 4.893510300863676e-05, + "loss": 0.6186, + "step": 88 + }, + { + "epoch": 0.559748427672956, + "grad_norm": 0.5198381543159485, + "learning_rate": 4.8881598109976004e-05, + "loss": 0.6153, + "step": 89 + }, + { + "epoch": 0.5660377358490566, + "grad_norm": 0.4063967764377594, + "learning_rate": 4.8826812513685487e-05, + "loss": 0.6472, + "step": 90 + }, + { + "epoch": 0.5723270440251572, + "grad_norm": 0.4114413857460022, + "learning_rate": 4.877074915775049e-05, + "loss": 0.6404, + "step": 91 + }, + { + "epoch": 0.5786163522012578, + "grad_norm": 0.37414512038230896, + "learning_rate": 4.8713411048678635e-05, + "loss": 0.6353, + "step": 92 + }, + { + "epoch": 0.5849056603773585, + "grad_norm": 0.3818528354167938, + "learning_rate": 4.865480126133872e-05, + "loss": 0.6289, + "step": 93 + }, + { + "epoch": 0.5911949685534591, + "grad_norm": 0.37088677287101746, + "learning_rate": 4.859492293879574e-05, + "loss": 0.6242, + "step": 94 + }, + { + "epoch": 0.5974842767295597, + "grad_norm": 0.43665146827697754, + "learning_rate": 4.853377929214243e-05, + "loss": 0.6055, + "step": 95 + }, + { + "epoch": 0.6037735849056604, + "grad_norm": 0.5932008028030396, + "learning_rate": 4.8471373600326996e-05, + "loss": 0.6354, + "step": 96 + }, + { + "epoch": 0.610062893081761, + "grad_norm": 0.46184536814689636, + "learning_rate": 4.8407709209977305e-05, + "loss": 0.7039, + "step": 97 + }, + { + "epoch": 0.6163522012578616, + "grad_norm": 0.44864600896835327, + "learning_rate": 4.834278953522138e-05, + "loss": 0.6679, + "step": 98 + }, + { + "epoch": 0.6226415094339622, + "grad_norm": 0.4060032069683075, + "learning_rate": 4.8276618057504376e-05, + "loss": 0.7479, + "step": 99 + }, + { + "epoch": 0.6289308176100629, + "grad_norm": 0.5088009834289551, + "learning_rate": 4.8209198325401815e-05, + "loss": 0.5923, + "step": 100 + }, + { + "epoch": 0.6352201257861635, + "grad_norm": 0.4294343590736389, + "learning_rate": 4.8140533954429327e-05, + "loss": 0.6313, + "step": 101 + }, + { + "epoch": 0.6415094339622641, + "grad_norm": 0.5710806846618652, + "learning_rate": 4.8070628626848735e-05, + "loss": 0.6736, + "step": 102 + }, + { + "epoch": 0.6477987421383647, + "grad_norm": 0.40560534596443176, + "learning_rate": 4.799948609147061e-05, + "loss": 0.6173, + "step": 103 + }, + { + "epoch": 0.6540880503144654, + "grad_norm": 0.46361806988716125, + "learning_rate": 4.792711016345321e-05, + "loss": 0.6756, + "step": 104 + }, + { + "epoch": 0.660377358490566, + "grad_norm": 0.5206082463264465, + "learning_rate": 4.785350472409792e-05, + "loss": 0.6413, + "step": 105 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.42583200335502625, + "learning_rate": 4.777867372064105e-05, + "loss": 0.6201, + "step": 106 + }, + { + "epoch": 0.6729559748427673, + "grad_norm": 0.49348241090774536, + "learning_rate": 4.770262116604224e-05, + "loss": 0.5777, + "step": 107 + }, + { + "epoch": 0.6792452830188679, + "grad_norm": 0.43750065565109253, + "learning_rate": 4.762535113876917e-05, + "loss": 0.6326, + "step": 108 + }, + { + "epoch": 0.6855345911949685, + "grad_norm": 0.431643545627594, + "learning_rate": 4.754686778257891e-05, + "loss": 0.5849, + "step": 109 + }, + { + "epoch": 0.6918238993710691, + "grad_norm": 0.41906824707984924, + "learning_rate": 4.7467175306295655e-05, + "loss": 0.6779, + "step": 110 + }, + { + "epoch": 0.6981132075471698, + "grad_norm": 0.4261593222618103, + "learning_rate": 4.738627798358506e-05, + "loss": 0.565, + "step": 111 + }, + { + "epoch": 0.7044025157232704, + "grad_norm": 0.42877814173698425, + "learning_rate": 4.730418015272503e-05, + "loss": 0.6836, + "step": 112 + }, + { + "epoch": 0.710691823899371, + "grad_norm": 0.40995511412620544, + "learning_rate": 4.722088621637309e-05, + "loss": 0.5849, + "step": 113 + }, + { + "epoch": 0.7169811320754716, + "grad_norm": 0.5606467723846436, + "learning_rate": 4.713640064133025e-05, + "loss": 0.644, + "step": 114 + }, + { + "epoch": 0.7232704402515723, + "grad_norm": 0.48454752564430237, + "learning_rate": 4.7050727958301506e-05, + "loss": 0.5418, + "step": 115 + }, + { + "epoch": 0.7295597484276729, + "grad_norm": 0.4099617898464203, + "learning_rate": 4.6963872761652835e-05, + "loss": 0.6524, + "step": 116 + }, + { + "epoch": 0.7358490566037735, + "grad_norm": 0.47192293405532837, + "learning_rate": 4.687583970916487e-05, + "loss": 0.6134, + "step": 117 + }, + { + "epoch": 0.7421383647798742, + "grad_norm": 0.4925817549228668, + "learning_rate": 4.678663352178301e-05, + "loss": 0.6517, + "step": 118 + }, + { + "epoch": 0.7484276729559748, + "grad_norm": 0.41517379879951477, + "learning_rate": 4.6696258983364385e-05, + "loss": 0.5763, + "step": 119 + }, + { + "epoch": 0.7547169811320755, + "grad_norm": 0.6227956414222717, + "learning_rate": 4.660472094042121e-05, + "loss": 0.7349, + "step": 120 + }, + { + "epoch": 0.7610062893081762, + "grad_norm": 0.39108285307884216, + "learning_rate": 4.651202430186092e-05, + "loss": 0.6548, + "step": 121 + }, + { + "epoch": 0.7672955974842768, + "grad_norm": 0.40210628509521484, + "learning_rate": 4.641817403872293e-05, + "loss": 0.6135, + "step": 122 + }, + { + "epoch": 0.7735849056603774, + "grad_norm": 0.42835289239883423, + "learning_rate": 4.6323175183912024e-05, + "loss": 0.5227, + "step": 123 + }, + { + "epoch": 0.779874213836478, + "grad_norm": 0.6215445399284363, + "learning_rate": 4.6227032831928484e-05, + "loss": 0.5265, + "step": 124 + }, + { + "epoch": 0.7861635220125787, + "grad_norm": 0.43423891067504883, + "learning_rate": 4.6129752138594874e-05, + "loss": 0.5972, + "step": 125 + }, + { + "epoch": 0.7924528301886793, + "grad_norm": 0.4693637788295746, + "learning_rate": 4.6031338320779534e-05, + "loss": 0.6758, + "step": 126 + }, + { + "epoch": 0.7987421383647799, + "grad_norm": 0.47571077942848206, + "learning_rate": 4.5931796656116846e-05, + "loss": 0.6419, + "step": 127 + }, + { + "epoch": 0.8050314465408805, + "grad_norm": 0.5828564167022705, + "learning_rate": 4.5831132482724195e-05, + "loss": 0.6952, + "step": 128 + }, + { + "epoch": 0.8113207547169812, + "grad_norm": 0.5325509309768677, + "learning_rate": 4.572935119891571e-05, + "loss": 0.6093, + "step": 129 + }, + { + "epoch": 0.8176100628930818, + "grad_norm": 0.4476761519908905, + "learning_rate": 4.5626458262912745e-05, + "loss": 0.5688, + "step": 130 + }, + { + "epoch": 0.8238993710691824, + "grad_norm": 0.36771783232688904, + "learning_rate": 4.552245919255117e-05, + "loss": 0.5778, + "step": 131 + }, + { + "epoch": 0.8301886792452831, + "grad_norm": 0.3695763647556305, + "learning_rate": 4.541735956498554e-05, + "loss": 0.517, + "step": 132 + }, + { + "epoch": 0.8364779874213837, + "grad_norm": 0.46155717968940735, + "learning_rate": 4.5311165016389916e-05, + "loss": 0.631, + "step": 133 + }, + { + "epoch": 0.8427672955974843, + "grad_norm": 0.5536386966705322, + "learning_rate": 4.5203881241655644e-05, + "loss": 0.6309, + "step": 134 + }, + { + "epoch": 0.8490566037735849, + "grad_norm": 0.42256519198417664, + "learning_rate": 4.509551399408598e-05, + "loss": 0.6754, + "step": 135 + }, + { + "epoch": 0.8553459119496856, + "grad_norm": 0.41634511947631836, + "learning_rate": 4.498606908508754e-05, + "loss": 0.6547, + "step": 136 + }, + { + "epoch": 0.8616352201257862, + "grad_norm": 0.38796696066856384, + "learning_rate": 4.487555238385862e-05, + "loss": 0.5693, + "step": 137 + }, + { + "epoch": 0.8679245283018868, + "grad_norm": 0.43052586913108826, + "learning_rate": 4.476396981707453e-05, + "loss": 0.6655, + "step": 138 + }, + { + "epoch": 0.8742138364779874, + "grad_norm": 0.44500571489334106, + "learning_rate": 4.465132736856969e-05, + "loss": 0.6563, + "step": 139 + }, + { + "epoch": 0.8805031446540881, + "grad_norm": 0.44693946838378906, + "learning_rate": 4.453763107901675e-05, + "loss": 0.5729, + "step": 140 + }, + { + "epoch": 0.8867924528301887, + "grad_norm": 0.3982055187225342, + "learning_rate": 4.442288704560268e-05, + "loss": 0.6425, + "step": 141 + }, + { + "epoch": 0.8930817610062893, + "grad_norm": 0.5706686973571777, + "learning_rate": 4.430710142170176e-05, + "loss": 0.5732, + "step": 142 + }, + { + "epoch": 0.89937106918239, + "grad_norm": 0.4493609070777893, + "learning_rate": 4.419028041654559e-05, + "loss": 0.6507, + "step": 143 + }, + { + "epoch": 0.9056603773584906, + "grad_norm": 0.3834284543991089, + "learning_rate": 4.4072430294890174e-05, + "loss": 0.6883, + "step": 144 + }, + { + "epoch": 0.9119496855345912, + "grad_norm": 0.4243861138820648, + "learning_rate": 4.3953557376679856e-05, + "loss": 0.5818, + "step": 145 + }, + { + "epoch": 0.9182389937106918, + "grad_norm": 0.42064470052719116, + "learning_rate": 4.383366803670849e-05, + "loss": 0.5963, + "step": 146 + }, + { + "epoch": 0.9245283018867925, + "grad_norm": 0.46670740842819214, + "learning_rate": 4.371276870427753e-05, + "loss": 0.65, + "step": 147 + }, + { + "epoch": 0.9308176100628931, + "grad_norm": 0.44945597648620605, + "learning_rate": 4.359086586285127e-05, + "loss": 0.6554, + "step": 148 + }, + { + "epoch": 0.9371069182389937, + "grad_norm": 0.48251762986183167, + "learning_rate": 4.346796604970912e-05, + "loss": 0.6681, + "step": 149 + }, + { + "epoch": 0.9433962264150944, + "grad_norm": 0.4577901065349579, + "learning_rate": 4.3344075855595104e-05, + "loss": 0.6108, + "step": 150 + }, + { + "epoch": 0.949685534591195, + "grad_norm": 0.4710671603679657, + "learning_rate": 4.321920192436433e-05, + "loss": 0.6177, + "step": 151 + }, + { + "epoch": 0.9559748427672956, + "grad_norm": 0.4275747835636139, + "learning_rate": 4.309335095262676e-05, + "loss": 0.5881, + "step": 152 + }, + { + "epoch": 0.9622641509433962, + "grad_norm": 0.4541204571723938, + "learning_rate": 4.296652968938807e-05, + "loss": 0.6142, + "step": 153 + }, + { + "epoch": 0.9685534591194969, + "grad_norm": 0.4179267883300781, + "learning_rate": 4.283874493568772e-05, + "loss": 0.6463, + "step": 154 + }, + { + "epoch": 0.9748427672955975, + "grad_norm": 0.42434728145599365, + "learning_rate": 4.271000354423426e-05, + "loss": 0.5873, + "step": 155 + }, + { + "epoch": 0.9811320754716981, + "grad_norm": 0.44202134013175964, + "learning_rate": 4.258031241903778e-05, + "loss": 0.6046, + "step": 156 + }, + { + "epoch": 0.9874213836477987, + "grad_norm": 0.47817060351371765, + "learning_rate": 4.2449678515039747e-05, + "loss": 0.5989, + "step": 157 + }, + { + "epoch": 0.9937106918238994, + "grad_norm": 0.43847018480300903, + "learning_rate": 4.231810883773999e-05, + "loss": 0.6156, + "step": 158 + }, + { + "epoch": 1.0, + "grad_norm": 0.48976290225982666, + "learning_rate": 4.218561044282099e-05, + "loss": 0.6177, + "step": 159 + }, + { + "epoch": 1.0062893081761006, + "grad_norm": 0.4213927984237671, + "learning_rate": 4.2052190435769554e-05, + "loss": 0.5881, + "step": 160 + }, + { + "epoch": 1.0125786163522013, + "grad_norm": 0.3923173248767853, + "learning_rate": 4.191785597149577e-05, + "loss": 0.5354, + "step": 161 + }, + { + "epoch": 1.0188679245283019, + "grad_norm": 0.41947099566459656, + "learning_rate": 4.178261425394926e-05, + "loss": 0.5745, + "step": 162 + }, + { + "epoch": 1.0251572327044025, + "grad_norm": 0.45812028646469116, + "learning_rate": 4.1646472535732895e-05, + "loss": 0.5836, + "step": 163 + }, + { + "epoch": 1.0314465408805031, + "grad_norm": 0.4519791007041931, + "learning_rate": 4.1509438117713866e-05, + "loss": 0.6118, + "step": 164 + }, + { + "epoch": 1.0377358490566038, + "grad_norm": 0.5628229379653931, + "learning_rate": 4.137151834863213e-05, + "loss": 0.5811, + "step": 165 + }, + { + "epoch": 1.0440251572327044, + "grad_norm": 0.3987003564834595, + "learning_rate": 4.123272062470633e-05, + "loss": 0.5179, + "step": 166 + }, + { + "epoch": 1.050314465408805, + "grad_norm": 0.4499664604663849, + "learning_rate": 4.109305238923718e-05, + "loss": 0.548, + "step": 167 + }, + { + "epoch": 1.0566037735849056, + "grad_norm": 0.4336049556732178, + "learning_rate": 4.095252113220827e-05, + "loss": 0.5659, + "step": 168 + }, + { + "epoch": 1.0628930817610063, + "grad_norm": 0.5409331321716309, + "learning_rate": 4.0811134389884433e-05, + "loss": 0.5522, + "step": 169 + }, + { + "epoch": 1.069182389937107, + "grad_norm": 0.41802865266799927, + "learning_rate": 4.066889974440757e-05, + "loss": 0.542, + "step": 170 + }, + { + "epoch": 1.0754716981132075, + "grad_norm": 0.48149824142456055, + "learning_rate": 4.0525824823390045e-05, + "loss": 0.6131, + "step": 171 + }, + { + "epoch": 1.0817610062893082, + "grad_norm": 0.5059295296669006, + "learning_rate": 4.038191729950569e-05, + "loss": 0.5823, + "step": 172 + }, + { + "epoch": 1.0880503144654088, + "grad_norm": 0.5310669541358948, + "learning_rate": 4.0237184890078245e-05, + "loss": 0.6066, + "step": 173 + }, + { + "epoch": 1.0943396226415094, + "grad_norm": 0.5470696091651917, + "learning_rate": 4.009163535666761e-05, + "loss": 0.6407, + "step": 174 + }, + { + "epoch": 1.10062893081761, + "grad_norm": 0.4407522678375244, + "learning_rate": 3.994527650465352e-05, + "loss": 0.573, + "step": 175 + }, + { + "epoch": 1.1069182389937107, + "grad_norm": 0.4072059094905853, + "learning_rate": 3.979811618281706e-05, + "loss": 0.6349, + "step": 176 + }, + { + "epoch": 1.1132075471698113, + "grad_norm": 0.6410146355628967, + "learning_rate": 3.9650162282919655e-05, + "loss": 0.6036, + "step": 177 + }, + { + "epoch": 1.119496855345912, + "grad_norm": 0.4664185047149658, + "learning_rate": 3.9501422739279956e-05, + "loss": 0.5855, + "step": 178 + }, + { + "epoch": 1.1257861635220126, + "grad_norm": 0.7204552888870239, + "learning_rate": 3.9351905528348285e-05, + "loss": 0.5719, + "step": 179 + }, + { + "epoch": 1.1320754716981132, + "grad_norm": 0.47248926758766174, + "learning_rate": 3.920161866827889e-05, + "loss": 0.5764, + "step": 180 + }, + { + "epoch": 1.1383647798742138, + "grad_norm": 0.64155113697052, + "learning_rate": 3.90505702185e-05, + "loss": 0.644, + "step": 181 + }, + { + "epoch": 1.1446540880503144, + "grad_norm": 0.5559830665588379, + "learning_rate": 3.889876827928156e-05, + "loss": 0.5883, + "step": 182 + }, + { + "epoch": 1.150943396226415, + "grad_norm": 0.46357718110084534, + "learning_rate": 3.874622099130087e-05, + "loss": 0.5942, + "step": 183 + }, + { + "epoch": 1.1572327044025157, + "grad_norm": 0.4527578055858612, + "learning_rate": 3.859293653520604e-05, + "loss": 0.6086, + "step": 184 + }, + { + "epoch": 1.1635220125786163, + "grad_norm": 0.45968765020370483, + "learning_rate": 3.843892313117724e-05, + "loss": 0.6105, + "step": 185 + }, + { + "epoch": 1.169811320754717, + "grad_norm": 0.5293806791305542, + "learning_rate": 3.8284189038485936e-05, + "loss": 0.5622, + "step": 186 + }, + { + "epoch": 1.1761006289308176, + "grad_norm": 0.4499124586582184, + "learning_rate": 3.812874255505191e-05, + "loss": 0.5451, + "step": 187 + }, + { + "epoch": 1.1823899371069182, + "grad_norm": 0.5140619277954102, + "learning_rate": 3.797259201699833e-05, + "loss": 0.5864, + "step": 188 + }, + { + "epoch": 1.1886792452830188, + "grad_norm": 0.40918025374412537, + "learning_rate": 3.781574579820464e-05, + "loss": 0.5602, + "step": 189 + }, + { + "epoch": 1.1949685534591195, + "grad_norm": 0.4417194128036499, + "learning_rate": 3.765821230985758e-05, + "loss": 0.5556, + "step": 190 + }, + { + "epoch": 1.20125786163522, + "grad_norm": 0.4697968363761902, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.6491, + "step": 191 + }, + { + "epoch": 1.2075471698113207, + "grad_norm": 0.40187153220176697, + "learning_rate": 3.7341117353077966e-05, + "loss": 0.5797, + "step": 192 + }, + { + "epoch": 1.2138364779874213, + "grad_norm": 0.456836462020874, + "learning_rate": 3.718157288948563e-05, + "loss": 0.5613, + "step": 193 + }, + { + "epoch": 1.220125786163522, + "grad_norm": 0.45992621779441833, + "learning_rate": 3.702137516510838e-05, + "loss": 0.6301, + "step": 194 + }, + { + "epoch": 1.2264150943396226, + "grad_norm": 0.45000532269477844, + "learning_rate": 3.686053277086401e-05, + "loss": 0.5772, + "step": 195 + }, + { + "epoch": 1.2327044025157232, + "grad_norm": 0.4734075963497162, + "learning_rate": 3.669905433224199e-05, + "loss": 0.5452, + "step": 196 + }, + { + "epoch": 1.2389937106918238, + "grad_norm": 0.41561609506607056, + "learning_rate": 3.653694850884091e-05, + "loss": 0.5365, + "step": 197 + }, + { + "epoch": 1.2452830188679245, + "grad_norm": 0.469097763299942, + "learning_rate": 3.637422399390413e-05, + "loss": 0.5396, + "step": 198 + }, + { + "epoch": 1.251572327044025, + "grad_norm": 0.46705111861228943, + "learning_rate": 3.621088951385353e-05, + "loss": 0.6024, + "step": 199 + }, + { + "epoch": 1.2578616352201257, + "grad_norm": 0.5201407074928284, + "learning_rate": 3.604695382782159e-05, + "loss": 0.6905, + "step": 200 + }, + { + "epoch": 1.2641509433962264, + "grad_norm": 0.4639309346675873, + "learning_rate": 3.588242572718162e-05, + "loss": 0.5909, + "step": 201 + }, + { + "epoch": 1.270440251572327, + "grad_norm": 0.4756741225719452, + "learning_rate": 3.5717314035076355e-05, + "loss": 0.5745, + "step": 202 + }, + { + "epoch": 1.2767295597484276, + "grad_norm": 0.5243765115737915, + "learning_rate": 3.5551627605944745e-05, + "loss": 0.6439, + "step": 203 + }, + { + "epoch": 1.2830188679245282, + "grad_norm": 0.4495748281478882, + "learning_rate": 3.5385375325047166e-05, + "loss": 0.5611, + "step": 204 + }, + { + "epoch": 1.2893081761006289, + "grad_norm": 0.47336816787719727, + "learning_rate": 3.521856610798887e-05, + "loss": 0.5846, + "step": 205 + }, + { + "epoch": 1.2955974842767295, + "grad_norm": 0.4667642116546631, + "learning_rate": 3.505120890024195e-05, + "loss": 0.5982, + "step": 206 + }, + { + "epoch": 1.3018867924528301, + "grad_norm": 0.4477729797363281, + "learning_rate": 3.4883312676665536e-05, + "loss": 0.6265, + "step": 207 + }, + { + "epoch": 1.3081761006289307, + "grad_norm": 0.5078469514846802, + "learning_rate": 3.4714886441024574e-05, + "loss": 0.5161, + "step": 208 + }, + { + "epoch": 1.3144654088050314, + "grad_norm": 0.5072935819625854, + "learning_rate": 3.4545939225506934e-05, + "loss": 0.5408, + "step": 209 + }, + { + "epoch": 1.320754716981132, + "grad_norm": 0.5006597638130188, + "learning_rate": 3.437648009023905e-05, + "loss": 0.5715, + "step": 210 + }, + { + "epoch": 1.3270440251572326, + "grad_norm": 0.44206503033638, + "learning_rate": 3.420651812280006e-05, + "loss": 0.5694, + "step": 211 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.4964762032032013, + "learning_rate": 3.4036062437734484e-05, + "loss": 0.5203, + "step": 212 + }, + { + "epoch": 1.3396226415094339, + "grad_norm": 0.4342876076698303, + "learning_rate": 3.386512217606339e-05, + "loss": 0.5778, + "step": 213 + }, + { + "epoch": 1.3459119496855345, + "grad_norm": 0.46520864963531494, + "learning_rate": 3.369370650479425e-05, + "loss": 0.5757, + "step": 214 + }, + { + "epoch": 1.3522012578616351, + "grad_norm": 0.5179557204246521, + "learning_rate": 3.3521824616429285e-05, + "loss": 0.5348, + "step": 215 + }, + { + "epoch": 1.3584905660377358, + "grad_norm": 0.45922955870628357, + "learning_rate": 3.3349485728472535e-05, + "loss": 0.5982, + "step": 216 + }, + { + "epoch": 1.3647798742138364, + "grad_norm": 0.5132372975349426, + "learning_rate": 3.3176699082935545e-05, + "loss": 0.6131, + "step": 217 + }, + { + "epoch": 1.371069182389937, + "grad_norm": 0.4740884602069855, + "learning_rate": 3.300347394584172e-05, + "loss": 0.6194, + "step": 218 + }, + { + "epoch": 1.3773584905660377, + "grad_norm": 0.45677605271339417, + "learning_rate": 3.282981960672948e-05, + "loss": 0.5938, + "step": 219 + }, + { + "epoch": 1.3836477987421385, + "grad_norm": 0.4545290172100067, + "learning_rate": 3.265574537815398e-05, + "loss": 0.5634, + "step": 220 + }, + { + "epoch": 1.389937106918239, + "grad_norm": 0.4439068138599396, + "learning_rate": 3.248126059518785e-05, + "loss": 0.5543, + "step": 221 + }, + { + "epoch": 1.3962264150943398, + "grad_norm": 0.4973136782646179, + "learning_rate": 3.230637461492043e-05, + "loss": 0.549, + "step": 222 + }, + { + "epoch": 1.4025157232704402, + "grad_norm": 0.5018147826194763, + "learning_rate": 3.213109681595612e-05, + "loss": 0.5799, + "step": 223 + }, + { + "epoch": 1.408805031446541, + "grad_norm": 0.4906245768070221, + "learning_rate": 3.195543659791132e-05, + "loss": 0.5788, + "step": 224 + }, + { + "epoch": 1.4150943396226414, + "grad_norm": 0.5228400826454163, + "learning_rate": 3.177940338091043e-05, + "loss": 0.4883, + "step": 225 + }, + { + "epoch": 1.4213836477987423, + "grad_norm": 0.5177304148674011, + "learning_rate": 3.160300660508064e-05, + "loss": 0.5737, + "step": 226 + }, + { + "epoch": 1.4276729559748427, + "grad_norm": 0.4641788899898529, + "learning_rate": 3.14262557300457e-05, + "loss": 0.5416, + "step": 227 + }, + { + "epoch": 1.4339622641509435, + "grad_norm": 0.49331700801849365, + "learning_rate": 3.124916023441865e-05, + "loss": 0.5747, + "step": 228 + }, + { + "epoch": 1.440251572327044, + "grad_norm": 0.4671120345592499, + "learning_rate": 3.107172961529343e-05, + "loss": 0.508, + "step": 229 + }, + { + "epoch": 1.4465408805031448, + "grad_norm": 0.5811720490455627, + "learning_rate": 3.0893973387735687e-05, + "loss": 0.6929, + "step": 230 + }, + { + "epoch": 1.4528301886792452, + "grad_norm": 0.48253801465034485, + "learning_rate": 3.071590108427244e-05, + "loss": 0.6467, + "step": 231 + }, + { + "epoch": 1.459119496855346, + "grad_norm": 0.5044742226600647, + "learning_rate": 3.0537522254380905e-05, + "loss": 0.5067, + "step": 232 + }, + { + "epoch": 1.4654088050314464, + "grad_norm": 0.5015671849250793, + "learning_rate": 3.0358846463976372e-05, + "loss": 0.6052, + "step": 233 + }, + { + "epoch": 1.4716981132075473, + "grad_norm": 0.5023432374000549, + "learning_rate": 3.017988329489923e-05, + "loss": 0.5961, + "step": 234 + }, + { + "epoch": 1.4779874213836477, + "grad_norm": 0.5157131552696228, + "learning_rate": 3.0000642344401113e-05, + "loss": 0.6285, + "step": 235 + }, + { + "epoch": 1.4842767295597485, + "grad_norm": 0.5081720948219299, + "learning_rate": 2.9821133224630226e-05, + "loss": 0.4634, + "step": 236 + }, + { + "epoch": 1.490566037735849, + "grad_norm": 0.4940662086009979, + "learning_rate": 2.9641365562115887e-05, + "loss": 0.5288, + "step": 237 + }, + { + "epoch": 1.4968553459119498, + "grad_norm": 0.6005929708480835, + "learning_rate": 2.9461348997252265e-05, + "loss": 0.5748, + "step": 238 + }, + { + "epoch": 1.5031446540880502, + "grad_norm": 0.5340356230735779, + "learning_rate": 2.9281093183781403e-05, + "loss": 0.5944, + "step": 239 + }, + { + "epoch": 1.509433962264151, + "grad_norm": 0.5056872367858887, + "learning_rate": 2.9100607788275545e-05, + "loss": 0.5549, + "step": 240 + }, + { + "epoch": 1.5157232704402515, + "grad_norm": 0.5385233759880066, + "learning_rate": 2.891990248961871e-05, + "loss": 0.5345, + "step": 241 + }, + { + "epoch": 1.5220125786163523, + "grad_norm": 0.48144999146461487, + "learning_rate": 2.8738986978487625e-05, + "loss": 0.5839, + "step": 242 + }, + { + "epoch": 1.5283018867924527, + "grad_norm": 0.5069999098777771, + "learning_rate": 2.8557870956832132e-05, + "loss": 0.4931, + "step": 243 + }, + { + "epoch": 1.5345911949685536, + "grad_norm": 0.4660912752151489, + "learning_rate": 2.8376564137354795e-05, + "loss": 0.5598, + "step": 244 + }, + { + "epoch": 1.540880503144654, + "grad_norm": 0.5416334271430969, + "learning_rate": 2.8195076242990122e-05, + "loss": 0.5894, + "step": 245 + }, + { + "epoch": 1.5471698113207548, + "grad_norm": 0.49134501814842224, + "learning_rate": 2.8013417006383076e-05, + "loss": 0.6345, + "step": 246 + }, + { + "epoch": 1.5534591194968552, + "grad_norm": 0.5861812829971313, + "learning_rate": 2.783159616936723e-05, + "loss": 0.6519, + "step": 247 + }, + { + "epoch": 1.559748427672956, + "grad_norm": 0.47188055515289307, + "learning_rate": 2.764962348244228e-05, + "loss": 0.5658, + "step": 248 + }, + { + "epoch": 1.5660377358490565, + "grad_norm": 0.4838746190071106, + "learning_rate": 2.7467508704251137e-05, + "loss": 0.5934, + "step": 249 + }, + { + "epoch": 1.5723270440251573, + "grad_norm": 0.516981840133667, + "learning_rate": 2.7285261601056698e-05, + "loss": 0.5341, + "step": 250 + }, + { + "epoch": 1.5786163522012577, + "grad_norm": 0.4871889352798462, + "learning_rate": 2.7102891946217994e-05, + "loss": 0.5885, + "step": 251 + }, + { + "epoch": 1.5849056603773586, + "grad_norm": 0.47121965885162354, + "learning_rate": 2.6920409519666174e-05, + "loss": 0.5988, + "step": 252 + }, + { + "epoch": 1.591194968553459, + "grad_norm": 0.5421566367149353, + "learning_rate": 2.6737824107379948e-05, + "loss": 0.6635, + "step": 253 + }, + { + "epoch": 1.5974842767295598, + "grad_norm": 0.5449573993682861, + "learning_rate": 2.655514550086086e-05, + "loss": 0.5365, + "step": 254 + }, + { + "epoch": 1.6037735849056602, + "grad_norm": 0.5301252007484436, + "learning_rate": 2.637238349660819e-05, + "loss": 0.6854, + "step": 255 + }, + { + "epoch": 1.610062893081761, + "grad_norm": 0.41109421849250793, + "learning_rate": 2.6189547895593562e-05, + "loss": 0.5234, + "step": 256 + }, + { + "epoch": 1.6163522012578615, + "grad_norm": 0.5346055626869202, + "learning_rate": 2.600664850273538e-05, + "loss": 0.5962, + "step": 257 + }, + { + "epoch": 1.6226415094339623, + "grad_norm": 0.5180861949920654, + "learning_rate": 2.582369512637302e-05, + "loss": 0.5396, + "step": 258 + }, + { + "epoch": 1.6289308176100628, + "grad_norm": 0.49982312321662903, + "learning_rate": 2.564069757774082e-05, + "loss": 0.4889, + "step": 259 + }, + { + "epoch": 1.6352201257861636, + "grad_norm": 0.5226275324821472, + "learning_rate": 2.545766567044194e-05, + "loss": 0.5893, + "step": 260 + }, + { + "epoch": 1.641509433962264, + "grad_norm": 0.47939932346343994, + "learning_rate": 2.527460921992209e-05, + "loss": 0.566, + "step": 261 + }, + { + "epoch": 1.6477987421383649, + "grad_norm": 0.536264955997467, + "learning_rate": 2.509153804294318e-05, + "loss": 0.5598, + "step": 262 + }, + { + "epoch": 1.6540880503144653, + "grad_norm": 0.5297203660011292, + "learning_rate": 2.490846195705683e-05, + "loss": 0.552, + "step": 263 + }, + { + "epoch": 1.6603773584905661, + "grad_norm": 0.5188955664634705, + "learning_rate": 2.4725390780077908e-05, + "loss": 0.6233, + "step": 264 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.4677969217300415, + "learning_rate": 2.4542334329558077e-05, + "loss": 0.4968, + "step": 265 + }, + { + "epoch": 1.6729559748427674, + "grad_norm": 0.5716769099235535, + "learning_rate": 2.435930242225919e-05, + "loss": 0.5315, + "step": 266 + }, + { + "epoch": 1.6792452830188678, + "grad_norm": 0.5071538090705872, + "learning_rate": 2.4176304873626985e-05, + "loss": 0.5622, + "step": 267 + }, + { + "epoch": 1.6855345911949686, + "grad_norm": 0.523229718208313, + "learning_rate": 2.399335149726463e-05, + "loss": 0.5999, + "step": 268 + }, + { + "epoch": 1.691823899371069, + "grad_norm": 0.5254403948783875, + "learning_rate": 2.3810452104406444e-05, + "loss": 0.6351, + "step": 269 + }, + { + "epoch": 1.6981132075471699, + "grad_norm": 0.53160560131073, + "learning_rate": 2.3627616503391814e-05, + "loss": 0.5754, + "step": 270 + }, + { + "epoch": 1.7044025157232703, + "grad_norm": 0.5396912693977356, + "learning_rate": 2.3444854499139142e-05, + "loss": 0.5635, + "step": 271 + }, + { + "epoch": 1.7106918238993711, + "grad_norm": 0.5528764724731445, + "learning_rate": 2.3262175892620065e-05, + "loss": 0.5368, + "step": 272 + }, + { + "epoch": 1.7169811320754715, + "grad_norm": 0.4812920093536377, + "learning_rate": 2.307959048033383e-05, + "loss": 0.5508, + "step": 273 + }, + { + "epoch": 1.7232704402515724, + "grad_norm": 0.5467996001243591, + "learning_rate": 2.2897108053782e-05, + "loss": 0.6073, + "step": 274 + }, + { + "epoch": 1.7295597484276728, + "grad_norm": 0.5203157663345337, + "learning_rate": 2.271473839894331e-05, + "loss": 0.5326, + "step": 275 + }, + { + "epoch": 1.7358490566037736, + "grad_norm": 0.4970155358314514, + "learning_rate": 2.253249129574887e-05, + "loss": 0.5444, + "step": 276 + }, + { + "epoch": 1.742138364779874, + "grad_norm": 0.5279742479324341, + "learning_rate": 2.2350376517557727e-05, + "loss": 0.5778, + "step": 277 + }, + { + "epoch": 1.748427672955975, + "grad_norm": 0.5293897986412048, + "learning_rate": 2.216840383063277e-05, + "loss": 0.5786, + "step": 278 + }, + { + "epoch": 1.7547169811320755, + "grad_norm": 0.565350353717804, + "learning_rate": 2.1986582993616926e-05, + "loss": 0.5877, + "step": 279 + }, + { + "epoch": 1.7610062893081762, + "grad_norm": 0.47762683033943176, + "learning_rate": 2.1804923757009884e-05, + "loss": 0.5419, + "step": 280 + }, + { + "epoch": 1.7672955974842768, + "grad_norm": 0.5171676278114319, + "learning_rate": 2.1623435862645204e-05, + "loss": 0.5418, + "step": 281 + }, + { + "epoch": 1.7735849056603774, + "grad_norm": 0.45764029026031494, + "learning_rate": 2.1442129043167874e-05, + "loss": 0.5487, + "step": 282 + }, + { + "epoch": 1.779874213836478, + "grad_norm": 0.5272729396820068, + "learning_rate": 2.126101302151238e-05, + "loss": 0.5317, + "step": 283 + }, + { + "epoch": 1.7861635220125787, + "grad_norm": 0.49889740347862244, + "learning_rate": 2.1080097510381298e-05, + "loss": 0.6046, + "step": 284 + }, + { + "epoch": 1.7924528301886793, + "grad_norm": 0.5512136220932007, + "learning_rate": 2.089939221172446e-05, + "loss": 0.6541, + "step": 285 + }, + { + "epoch": 1.79874213836478, + "grad_norm": 0.5187536478042603, + "learning_rate": 2.07189068162186e-05, + "loss": 0.5646, + "step": 286 + }, + { + "epoch": 1.8050314465408805, + "grad_norm": 0.4920225143432617, + "learning_rate": 2.0538651002747744e-05, + "loss": 0.5561, + "step": 287 + }, + { + "epoch": 1.8113207547169812, + "grad_norm": 0.5807557702064514, + "learning_rate": 2.0358634437884112e-05, + "loss": 0.6087, + "step": 288 + }, + { + "epoch": 1.8176100628930818, + "grad_norm": 0.48779597878456116, + "learning_rate": 2.0178866775369777e-05, + "loss": 0.5801, + "step": 289 + }, + { + "epoch": 1.8238993710691824, + "grad_norm": 0.47587329149246216, + "learning_rate": 1.9999357655598893e-05, + "loss": 0.6003, + "step": 290 + }, + { + "epoch": 1.830188679245283, + "grad_norm": 0.5073649883270264, + "learning_rate": 1.9820116705100777e-05, + "loss": 0.5838, + "step": 291 + }, + { + "epoch": 1.8364779874213837, + "grad_norm": 0.5661832690238953, + "learning_rate": 1.9641153536023644e-05, + "loss": 0.6054, + "step": 292 + }, + { + "epoch": 1.8427672955974843, + "grad_norm": 0.4822792410850525, + "learning_rate": 1.9462477745619108e-05, + "loss": 0.5515, + "step": 293 + }, + { + "epoch": 1.849056603773585, + "grad_norm": 0.5438389182090759, + "learning_rate": 1.928409891572757e-05, + "loss": 0.6225, + "step": 294 + }, + { + "epoch": 1.8553459119496856, + "grad_norm": 0.4644525647163391, + "learning_rate": 1.9106026612264316e-05, + "loss": 0.6214, + "step": 295 + }, + { + "epoch": 1.8616352201257862, + "grad_norm": 0.477500855922699, + "learning_rate": 1.8928270384706584e-05, + "loss": 0.6164, + "step": 296 + }, + { + "epoch": 1.8679245283018868, + "grad_norm": 0.4944886267185211, + "learning_rate": 1.875083976558136e-05, + "loss": 0.5533, + "step": 297 + }, + { + "epoch": 1.8742138364779874, + "grad_norm": 0.5480766892433167, + "learning_rate": 1.8573744269954298e-05, + "loss": 0.6305, + "step": 298 + }, + { + "epoch": 1.880503144654088, + "grad_norm": 0.5053893327713013, + "learning_rate": 1.8396993394919372e-05, + "loss": 0.574, + "step": 299 + }, + { + "epoch": 1.8867924528301887, + "grad_norm": 0.559573233127594, + "learning_rate": 1.8220596619089576e-05, + "loss": 0.7138, + "step": 300 + }, + { + "epoch": 1.8930817610062893, + "grad_norm": 0.5412449836730957, + "learning_rate": 1.8044563402088684e-05, + "loss": 0.6108, + "step": 301 + }, + { + "epoch": 1.89937106918239, + "grad_norm": 0.49840930104255676, + "learning_rate": 1.7868903184043887e-05, + "loss": 0.546, + "step": 302 + }, + { + "epoch": 1.9056603773584906, + "grad_norm": 0.6073680520057678, + "learning_rate": 1.7693625385079577e-05, + "loss": 0.5597, + "step": 303 + }, + { + "epoch": 1.9119496855345912, + "grad_norm": 0.5452404022216797, + "learning_rate": 1.7518739404812155e-05, + "loss": 0.6107, + "step": 304 + }, + { + "epoch": 1.9182389937106918, + "grad_norm": 0.48530417680740356, + "learning_rate": 1.7344254621846016e-05, + "loss": 0.5671, + "step": 305 + }, + { + "epoch": 1.9245283018867925, + "grad_norm": 0.47276559472084045, + "learning_rate": 1.7170180393270532e-05, + "loss": 0.5503, + "step": 306 + }, + { + "epoch": 1.930817610062893, + "grad_norm": 0.4949149191379547, + "learning_rate": 1.699652605415828e-05, + "loss": 0.4958, + "step": 307 + }, + { + "epoch": 1.9371069182389937, + "grad_norm": 0.5216560363769531, + "learning_rate": 1.682330091706446e-05, + "loss": 0.58, + "step": 308 + }, + { + "epoch": 1.9433962264150944, + "grad_norm": 0.5286461710929871, + "learning_rate": 1.6650514271527468e-05, + "loss": 0.5293, + "step": 309 + }, + { + "epoch": 1.949685534591195, + "grad_norm": 0.4912795424461365, + "learning_rate": 1.647817538357072e-05, + "loss": 0.5666, + "step": 310 + }, + { + "epoch": 1.9559748427672956, + "grad_norm": 0.5797849297523499, + "learning_rate": 1.630629349520576e-05, + "loss": 0.5493, + "step": 311 + }, + { + "epoch": 1.9622641509433962, + "grad_norm": 0.5302536487579346, + "learning_rate": 1.613487782393661e-05, + "loss": 0.5516, + "step": 312 + }, + { + "epoch": 1.9685534591194969, + "grad_norm": 0.5543875694274902, + "learning_rate": 1.5963937562265525e-05, + "loss": 0.5358, + "step": 313 + }, + { + "epoch": 1.9748427672955975, + "grad_norm": 0.5673121809959412, + "learning_rate": 1.5793481877199946e-05, + "loss": 0.5332, + "step": 314 + }, + { + "epoch": 1.9811320754716981, + "grad_norm": 0.508794367313385, + "learning_rate": 1.5623519909760954e-05, + "loss": 0.5968, + "step": 315 + }, + { + "epoch": 1.9874213836477987, + "grad_norm": 0.5409150719642639, + "learning_rate": 1.5454060774493068e-05, + "loss": 0.6077, + "step": 316 + }, + { + "epoch": 1.9937106918238994, + "grad_norm": 0.5045109987258911, + "learning_rate": 1.528511355897543e-05, + "loss": 0.5503, + "step": 317 + }, + { + "epoch": 2.0, + "grad_norm": 0.6411352157592773, + "learning_rate": 1.5116687323334467e-05, + "loss": 0.6122, + "step": 318 + }, + { + "epoch": 2.006289308176101, + "grad_norm": 0.5026600360870361, + "learning_rate": 1.4948791099758052e-05, + "loss": 0.5369, + "step": 319 + }, + { + "epoch": 2.0125786163522013, + "grad_norm": 0.511720597743988, + "learning_rate": 1.4781433892011131e-05, + "loss": 0.5291, + "step": 320 + }, + { + "epoch": 2.018867924528302, + "grad_norm": 0.48618605732917786, + "learning_rate": 1.4614624674952842e-05, + "loss": 0.5378, + "step": 321 + }, + { + "epoch": 2.0251572327044025, + "grad_norm": 0.545242190361023, + "learning_rate": 1.4448372394055249e-05, + "loss": 0.5048, + "step": 322 + }, + { + "epoch": 2.0314465408805034, + "grad_norm": 0.5334264636039734, + "learning_rate": 1.4282685964923642e-05, + "loss": 0.5401, + "step": 323 + }, + { + "epoch": 2.0377358490566038, + "grad_norm": 0.5524183511734009, + "learning_rate": 1.4117574272818388e-05, + "loss": 0.5099, + "step": 324 + }, + { + "epoch": 2.0440251572327046, + "grad_norm": 0.48006343841552734, + "learning_rate": 1.3953046172178414e-05, + "loss": 0.4566, + "step": 325 + }, + { + "epoch": 2.050314465408805, + "grad_norm": 0.45758774876594543, + "learning_rate": 1.378911048614647e-05, + "loss": 0.4861, + "step": 326 + }, + { + "epoch": 2.056603773584906, + "grad_norm": 0.583585262298584, + "learning_rate": 1.3625776006095881e-05, + "loss": 0.5896, + "step": 327 + }, + { + "epoch": 2.0628930817610063, + "grad_norm": 0.5123708844184875, + "learning_rate": 1.3463051491159096e-05, + "loss": 0.5174, + "step": 328 + }, + { + "epoch": 2.069182389937107, + "grad_norm": 0.5508242845535278, + "learning_rate": 1.3300945667758014e-05, + "loss": 0.5042, + "step": 329 + }, + { + "epoch": 2.0754716981132075, + "grad_norm": 0.5526241660118103, + "learning_rate": 1.3139467229135999e-05, + "loss": 0.5457, + "step": 330 + }, + { + "epoch": 2.0817610062893084, + "grad_norm": 0.5903204083442688, + "learning_rate": 1.2978624834891628e-05, + "loss": 0.5299, + "step": 331 + }, + { + "epoch": 2.088050314465409, + "grad_norm": 0.5764947533607483, + "learning_rate": 1.281842711051438e-05, + "loss": 0.512, + "step": 332 + }, + { + "epoch": 2.0943396226415096, + "grad_norm": 0.5653167963027954, + "learning_rate": 1.2658882646922034e-05, + "loss": 0.5131, + "step": 333 + }, + { + "epoch": 2.10062893081761, + "grad_norm": 0.5843393206596375, + "learning_rate": 1.2500000000000006e-05, + "loss": 0.5383, + "step": 334 + }, + { + "epoch": 2.106918238993711, + "grad_norm": 0.6287145614624023, + "learning_rate": 1.2341787690142437e-05, + "loss": 0.5715, + "step": 335 + }, + { + "epoch": 2.1132075471698113, + "grad_norm": 0.5734768509864807, + "learning_rate": 1.2184254201795365e-05, + "loss": 0.548, + "step": 336 + }, + { + "epoch": 2.119496855345912, + "grad_norm": 0.5723345279693604, + "learning_rate": 1.2027407983001681e-05, + "loss": 0.4989, + "step": 337 + }, + { + "epoch": 2.1257861635220126, + "grad_norm": 0.6128413677215576, + "learning_rate": 1.1871257444948098e-05, + "loss": 0.5775, + "step": 338 + }, + { + "epoch": 2.1320754716981134, + "grad_norm": 0.7310327887535095, + "learning_rate": 1.1715810961514073e-05, + "loss": 0.5642, + "step": 339 + }, + { + "epoch": 2.138364779874214, + "grad_norm": 0.6413530707359314, + "learning_rate": 1.1561076868822756e-05, + "loss": 0.571, + "step": 340 + }, + { + "epoch": 2.1446540880503147, + "grad_norm": 0.6232360601425171, + "learning_rate": 1.1407063464793966e-05, + "loss": 0.4891, + "step": 341 + }, + { + "epoch": 2.150943396226415, + "grad_norm": 0.5760077238082886, + "learning_rate": 1.1253779008699131e-05, + "loss": 0.5196, + "step": 342 + }, + { + "epoch": 2.157232704402516, + "grad_norm": 0.5411508083343506, + "learning_rate": 1.1101231720718442e-05, + "loss": 0.479, + "step": 343 + }, + { + "epoch": 2.1635220125786163, + "grad_norm": 0.5932305455207825, + "learning_rate": 1.09494297815e-05, + "loss": 0.4888, + "step": 344 + }, + { + "epoch": 2.169811320754717, + "grad_norm": 0.5784667730331421, + "learning_rate": 1.0798381331721109e-05, + "loss": 0.5119, + "step": 345 + }, + { + "epoch": 2.1761006289308176, + "grad_norm": 0.663508415222168, + "learning_rate": 1.0648094471651724e-05, + "loss": 0.497, + "step": 346 + }, + { + "epoch": 2.1823899371069184, + "grad_norm": 0.5773563981056213, + "learning_rate": 1.049857726072005e-05, + "loss": 0.5013, + "step": 347 + }, + { + "epoch": 2.188679245283019, + "grad_norm": 0.697320282459259, + "learning_rate": 1.034983771708035e-05, + "loss": 0.6453, + "step": 348 + }, + { + "epoch": 2.1949685534591197, + "grad_norm": 0.5786930918693542, + "learning_rate": 1.020188381718295e-05, + "loss": 0.5044, + "step": 349 + }, + { + "epoch": 2.20125786163522, + "grad_norm": 0.6295438408851624, + "learning_rate": 1.0054723495346482e-05, + "loss": 0.594, + "step": 350 + }, + { + "epoch": 2.207547169811321, + "grad_norm": 0.6185433864593506, + "learning_rate": 9.908364643332399e-06, + "loss": 0.5059, + "step": 351 + }, + { + "epoch": 2.2138364779874213, + "grad_norm": 0.6029584407806396, + "learning_rate": 9.762815109921761e-06, + "loss": 0.5069, + "step": 352 + }, + { + "epoch": 2.220125786163522, + "grad_norm": 0.6533452272415161, + "learning_rate": 9.618082700494319e-06, + "loss": 0.5232, + "step": 353 + }, + { + "epoch": 2.2264150943396226, + "grad_norm": 0.6175459027290344, + "learning_rate": 9.474175176609956e-06, + "loss": 0.5466, + "step": 354 + }, + { + "epoch": 2.2327044025157234, + "grad_norm": 0.5657399892807007, + "learning_rate": 9.331100255592437e-06, + "loss": 0.4564, + "step": 355 + }, + { + "epoch": 2.238993710691824, + "grad_norm": 0.6779638528823853, + "learning_rate": 9.18886561011557e-06, + "loss": 0.5621, + "step": 356 + }, + { + "epoch": 2.2452830188679247, + "grad_norm": 0.5873716473579407, + "learning_rate": 9.047478867791732e-06, + "loss": 0.4575, + "step": 357 + }, + { + "epoch": 2.251572327044025, + "grad_norm": 0.5723773837089539, + "learning_rate": 8.906947610762825e-06, + "loss": 0.4867, + "step": 358 + }, + { + "epoch": 2.257861635220126, + "grad_norm": 0.6322399377822876, + "learning_rate": 8.767279375293672e-06, + "loss": 0.5453, + "step": 359 + }, + { + "epoch": 2.2641509433962264, + "grad_norm": 0.6071794033050537, + "learning_rate": 8.628481651367876e-06, + "loss": 0.5465, + "step": 360 + }, + { + "epoch": 2.270440251572327, + "grad_norm": 0.7954049110412598, + "learning_rate": 8.490561882286136e-06, + "loss": 0.5327, + "step": 361 + }, + { + "epoch": 2.2767295597484276, + "grad_norm": 0.5613401532173157, + "learning_rate": 8.353527464267104e-06, + "loss": 0.4759, + "step": 362 + }, + { + "epoch": 2.2830188679245285, + "grad_norm": 0.677384614944458, + "learning_rate": 8.217385746050742e-06, + "loss": 0.5186, + "step": 363 + }, + { + "epoch": 2.289308176100629, + "grad_norm": 0.6257275938987732, + "learning_rate": 8.082144028504233e-06, + "loss": 0.5786, + "step": 364 + }, + { + "epoch": 2.2955974842767297, + "grad_norm": 0.6544857025146484, + "learning_rate": 7.947809564230445e-06, + "loss": 0.4792, + "step": 365 + }, + { + "epoch": 2.30188679245283, + "grad_norm": 0.6507861614227295, + "learning_rate": 7.814389557179017e-06, + "loss": 0.5567, + "step": 366 + }, + { + "epoch": 2.308176100628931, + "grad_norm": 0.6414310336112976, + "learning_rate": 7.681891162260015e-06, + "loss": 0.5227, + "step": 367 + }, + { + "epoch": 2.3144654088050314, + "grad_norm": 0.6640331149101257, + "learning_rate": 7.5503214849602516e-06, + "loss": 0.5339, + "step": 368 + }, + { + "epoch": 2.3207547169811322, + "grad_norm": 0.6685804128646851, + "learning_rate": 7.419687580962223e-06, + "loss": 0.4857, + "step": 369 + }, + { + "epoch": 2.3270440251572326, + "grad_norm": 0.6468353271484375, + "learning_rate": 7.289996455765749e-06, + "loss": 0.4588, + "step": 370 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.5642632842063904, + "learning_rate": 7.161255064312283e-06, + "loss": 0.4676, + "step": 371 + }, + { + "epoch": 2.339622641509434, + "grad_norm": 0.583641529083252, + "learning_rate": 7.033470310611945e-06, + "loss": 0.5441, + "step": 372 + }, + { + "epoch": 2.3459119496855347, + "grad_norm": 0.6600673198699951, + "learning_rate": 6.906649047373246e-06, + "loss": 0.5144, + "step": 373 + }, + { + "epoch": 2.352201257861635, + "grad_norm": 0.6383036971092224, + "learning_rate": 6.780798075635675e-06, + "loss": 0.454, + "step": 374 + }, + { + "epoch": 2.358490566037736, + "grad_norm": 0.5476061105728149, + "learning_rate": 6.655924144404907e-06, + "loss": 0.4471, + "step": 375 + }, + { + "epoch": 2.3647798742138364, + "grad_norm": 0.6322336792945862, + "learning_rate": 6.532033950290886e-06, + "loss": 0.525, + "step": 376 + }, + { + "epoch": 2.3710691823899372, + "grad_norm": 0.6242497563362122, + "learning_rate": 6.409134137148737e-06, + "loss": 0.5181, + "step": 377 + }, + { + "epoch": 2.3773584905660377, + "grad_norm": 0.6529743075370789, + "learning_rate": 6.28723129572247e-06, + "loss": 0.5105, + "step": 378 + }, + { + "epoch": 2.3836477987421385, + "grad_norm": 0.6641661524772644, + "learning_rate": 6.166331963291519e-06, + "loss": 0.4859, + "step": 379 + }, + { + "epoch": 2.389937106918239, + "grad_norm": 0.6310985088348389, + "learning_rate": 6.046442623320145e-06, + "loss": 0.5136, + "step": 380 + }, + { + "epoch": 2.3962264150943398, + "grad_norm": 0.7812454104423523, + "learning_rate": 5.927569705109828e-06, + "loss": 0.4837, + "step": 381 + }, + { + "epoch": 2.40251572327044, + "grad_norm": 0.7382704019546509, + "learning_rate": 5.809719583454415e-06, + "loss": 0.4962, + "step": 382 + }, + { + "epoch": 2.408805031446541, + "grad_norm": 0.6249539256095886, + "learning_rate": 5.692898578298253e-06, + "loss": 0.5138, + "step": 383 + }, + { + "epoch": 2.4150943396226414, + "grad_norm": 0.6593284010887146, + "learning_rate": 5.577112954397321e-06, + "loss": 0.5097, + "step": 384 + }, + { + "epoch": 2.4213836477987423, + "grad_norm": 0.6821117997169495, + "learning_rate": 5.462368920983249e-06, + "loss": 0.5655, + "step": 385 + }, + { + "epoch": 2.4276729559748427, + "grad_norm": 0.7341055274009705, + "learning_rate": 5.348672631430318e-06, + "loss": 0.511, + "step": 386 + }, + { + "epoch": 2.4339622641509435, + "grad_norm": 0.676941454410553, + "learning_rate": 5.236030182925475e-06, + "loss": 0.4494, + "step": 387 + }, + { + "epoch": 2.440251572327044, + "grad_norm": 0.6467084288597107, + "learning_rate": 5.124447616141381e-06, + "loss": 0.4407, + "step": 388 + }, + { + "epoch": 2.4465408805031448, + "grad_norm": 0.6168628931045532, + "learning_rate": 5.013930914912476e-06, + "loss": 0.5424, + "step": 389 + }, + { + "epoch": 2.452830188679245, + "grad_norm": 0.6204650402069092, + "learning_rate": 4.9044860059140275e-06, + "loss": 0.5222, + "step": 390 + }, + { + "epoch": 2.459119496855346, + "grad_norm": 0.6808157563209534, + "learning_rate": 4.796118758344354e-06, + "loss": 0.5181, + "step": 391 + }, + { + "epoch": 2.4654088050314464, + "grad_norm": 0.6607468128204346, + "learning_rate": 4.6888349836100825e-06, + "loss": 0.5849, + "step": 392 + }, + { + "epoch": 2.4716981132075473, + "grad_norm": 0.6367841362953186, + "learning_rate": 4.58264043501446e-06, + "loss": 0.4938, + "step": 393 + }, + { + "epoch": 2.4779874213836477, + "grad_norm": 0.7117082476615906, + "learning_rate": 4.477540807448832e-06, + "loss": 0.4862, + "step": 394 + }, + { + "epoch": 2.4842767295597485, + "grad_norm": 0.662056565284729, + "learning_rate": 4.373541737087264e-06, + "loss": 0.5753, + "step": 395 + }, + { + "epoch": 2.490566037735849, + "grad_norm": 0.6686725616455078, + "learning_rate": 4.270648801084296e-06, + "loss": 0.555, + "step": 396 + }, + { + "epoch": 2.49685534591195, + "grad_norm": 0.7704941034317017, + "learning_rate": 4.1688675172758064e-06, + "loss": 0.6513, + "step": 397 + }, + { + "epoch": 2.50314465408805, + "grad_norm": 0.6105798482894897, + "learning_rate": 4.068203343883159e-06, + "loss": 0.4985, + "step": 398 + }, + { + "epoch": 2.509433962264151, + "grad_norm": 0.6414272785186768, + "learning_rate": 3.968661679220468e-06, + "loss": 0.4736, + "step": 399 + }, + { + "epoch": 2.5157232704402515, + "grad_norm": 0.6939327120780945, + "learning_rate": 3.8702478614051355e-06, + "loss": 0.567, + "step": 400 + } + ], + "logging_steps": 1, + "max_steps": 477, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.9770270895097774e+18, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f2a1106da97275ded3721a2b9ad28a19b5c9872 --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d245efe4cb1811ec2cffc23b4d3aa9a49d1d65e92b8d678bec9a399e5c1889e +size 5496 diff --git a/checkpoint-477/._README.md b/checkpoint-477/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..be8a7e5e2aff782609471f4bc90c72af6dcf030e Binary files /dev/null and b/checkpoint-477/._README.md differ diff --git a/checkpoint-477/._adapter_config.json b/checkpoint-477/._adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..797c6ac604e37e31ff433277847276cc850c6a68 Binary files /dev/null and b/checkpoint-477/._adapter_config.json differ diff --git a/checkpoint-477/._adapter_model.safetensors b/checkpoint-477/._adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce9150750322a969f436e0c667f46edb786a2167 --- /dev/null +++ b/checkpoint-477/._adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc74048b19171b313073e3f09c52bb756b5044cafd7b33f6e5458fa2f6f091b4 +size 4096 diff --git a/checkpoint-477/._optimizer.pt b/checkpoint-477/._optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c58c1ad8c579d94c3908629996afec89ceadd781 --- /dev/null +++ b/checkpoint-477/._optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a0066481aaaf4d5998dc0d883660c96629f987bcc71aff5a1faefa5f08f935 +size 4096 diff --git a/checkpoint-477/._rng_state.pth b/checkpoint-477/._rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..27665b593c5f1427d5cf848a0ca376e766647dfd --- /dev/null +++ b/checkpoint-477/._rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3712ebba4e30cfd05bb958bee3a690cc405e590ffddc86de200692e3cfa851a0 +size 4096 diff --git a/checkpoint-477/._scheduler.pt b/checkpoint-477/._scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..385d60c3b27d77e8444ffa4236a51e0151776b0b --- /dev/null +++ b/checkpoint-477/._scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb7505ff7e968c5e18b351abdddd2436882d5d92e7ad2581f8c72e7bf1a3c632 +size 4096 diff --git a/checkpoint-477/._special_tokens_map.json b/checkpoint-477/._special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..7d7f0784e948e0f418fbde8de7560cb74f12f08e Binary files /dev/null and b/checkpoint-477/._special_tokens_map.json differ diff --git a/checkpoint-477/._tokenizer.json b/checkpoint-477/._tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..66a319b7ac32648af244a1af9462754898661dc2 Binary files /dev/null and b/checkpoint-477/._tokenizer.json differ diff --git a/checkpoint-477/._tokenizer_config.json b/checkpoint-477/._tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8703ca96d12fb994a2ee0063d2cdf5b6eacf42d Binary files /dev/null and b/checkpoint-477/._tokenizer_config.json differ diff --git a/checkpoint-477/._trainer_state.json b/checkpoint-477/._trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..4c1bca321a83d667adab807779d9e42807259c94 Binary files /dev/null and b/checkpoint-477/._trainer_state.json differ diff --git a/checkpoint-477/._training_args.bin b/checkpoint-477/._training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b42476c04ff5db9865d51b3c0adcb93a87e59fa6 --- /dev/null +++ b/checkpoint-477/._training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17480afbb455652e533a7595b39ad32b78ef0e0c6623c57b251c04d5a54035c +size 4096 diff --git a/checkpoint-477/README.md b/checkpoint-477/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0d0f45d57897230f208f7d5fa62f85e8481f2f2f --- /dev/null +++ b/checkpoint-477/README.md @@ -0,0 +1,202 @@ +--- +base_model: /scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-477/adapter_config.json b/checkpoint-477/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b43c336eadd307192f9ebaaca58b283a56db147d --- /dev/null +++ b/checkpoint-477/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/scratch_tmp/prj/inf_llmcache/hf_cache/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/38ff4e01a70559264c95945aa04b900a11e68422", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "v_proj", + "up_proj", + "q_proj", + "down_proj", + "gate_proj", + "o_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-477/adapter_model.safetensors b/checkpoint-477/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e872e4418291ae61abb876583d1ff2ba3eec50bd --- /dev/null +++ b/checkpoint-477/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bece6d03c76862ade6a34424dc0b56bef9eb9dd0aa67e970a38725cbd0ac1c74 +size 414337624 diff --git a/checkpoint-477/optimizer.pt b/checkpoint-477/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a750e4ef706685f88693b124bc2889ca4ac7eac --- /dev/null +++ b/checkpoint-477/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e5d399f06bb891e10074a9027d5eac802d6356bd9e3555a0adfdc859aabaa6 +size 829323250 diff --git a/checkpoint-477/rng_state.pth b/checkpoint-477/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5 --- /dev/null +++ b/checkpoint-477/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d +size 14244 diff --git a/checkpoint-477/scheduler.pt b/checkpoint-477/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..640169baea292b5a5c7f2589685e6053c1f5932b --- /dev/null +++ b/checkpoint-477/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ba0347d090a41d2915bf6aa0e050446da1cbf84ecae1dc840d5399e99aacd7 +size 1064 diff --git a/checkpoint-477/special_tokens_map.json b/checkpoint-477/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/checkpoint-477/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-477/tokenizer.json b/checkpoint-477/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/checkpoint-477/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/checkpoint-477/tokenizer_config.json b/checkpoint-477/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1913e5051ba2d9c350141f19b01d55276096bc3 --- /dev/null +++ b/checkpoint-477/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-477/trainer_state.json b/checkpoint-477/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..72870be7991b77d747804aa55498417fad528f09 --- /dev/null +++ b/checkpoint-477/trainer_state.json @@ -0,0 +1,3372 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 477, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.006289308176100629, + "grad_norm": 4.8737874031066895, + "learning_rate": 1.0416666666666667e-06, + "loss": 3.6915, + "step": 1 + }, + { + "epoch": 0.012578616352201259, + "grad_norm": 4.941007137298584, + "learning_rate": 2.0833333333333334e-06, + "loss": 3.6352, + "step": 2 + }, + { + "epoch": 0.018867924528301886, + "grad_norm": 5.258031368255615, + "learning_rate": 3.125e-06, + "loss": 3.5816, + "step": 3 + }, + { + "epoch": 0.025157232704402517, + "grad_norm": 5.544358253479004, + "learning_rate": 4.166666666666667e-06, + "loss": 3.6233, + "step": 4 + }, + { + "epoch": 0.031446540880503145, + "grad_norm": 5.457708835601807, + "learning_rate": 5.208333333333334e-06, + "loss": 3.6107, + "step": 5 + }, + { + "epoch": 0.03773584905660377, + "grad_norm": 5.185223579406738, + "learning_rate": 6.25e-06, + "loss": 3.6277, + "step": 6 + }, + { + "epoch": 0.0440251572327044, + "grad_norm": 5.433485507965088, + "learning_rate": 7.2916666666666674e-06, + "loss": 3.4974, + "step": 7 + }, + { + "epoch": 0.050314465408805034, + "grad_norm": 5.38355016708374, + "learning_rate": 8.333333333333334e-06, + "loss": 3.5021, + "step": 8 + }, + { + "epoch": 0.05660377358490566, + "grad_norm": 5.851156234741211, + "learning_rate": 9.375000000000001e-06, + "loss": 3.5888, + "step": 9 + }, + { + "epoch": 0.06289308176100629, + "grad_norm": 8.335844993591309, + "learning_rate": 1.0416666666666668e-05, + "loss": 3.3652, + "step": 10 + }, + { + "epoch": 0.06918238993710692, + "grad_norm": 5.598583698272705, + "learning_rate": 1.1458333333333333e-05, + "loss": 3.1476, + "step": 11 + }, + { + "epoch": 0.07547169811320754, + "grad_norm": 6.811880588531494, + "learning_rate": 1.25e-05, + "loss": 3.6846, + "step": 12 + }, + { + "epoch": 0.08176100628930817, + "grad_norm": 5.962316513061523, + "learning_rate": 1.3541666666666666e-05, + "loss": 3.2959, + "step": 13 + }, + { + "epoch": 0.0880503144654088, + "grad_norm": 6.434226989746094, + "learning_rate": 1.4583333333333335e-05, + "loss": 3.3629, + "step": 14 + }, + { + "epoch": 0.09433962264150944, + "grad_norm": 5.959097862243652, + "learning_rate": 1.5625e-05, + "loss": 2.9799, + "step": 15 + }, + { + "epoch": 0.10062893081761007, + "grad_norm": 5.713625907897949, + "learning_rate": 1.6666666666666667e-05, + "loss": 2.8375, + "step": 16 + }, + { + "epoch": 0.1069182389937107, + "grad_norm": 4.679070472717285, + "learning_rate": 1.7708333333333335e-05, + "loss": 2.5298, + "step": 17 + }, + { + "epoch": 0.11320754716981132, + "grad_norm": 4.000007152557373, + "learning_rate": 1.8750000000000002e-05, + "loss": 2.4099, + "step": 18 + }, + { + "epoch": 0.11949685534591195, + "grad_norm": 3.6054141521453857, + "learning_rate": 1.9791666666666665e-05, + "loss": 2.1316, + "step": 19 + }, + { + "epoch": 0.12578616352201258, + "grad_norm": 3.1357152462005615, + "learning_rate": 2.0833333333333336e-05, + "loss": 1.8814, + "step": 20 + }, + { + "epoch": 0.1320754716981132, + "grad_norm": 2.848811149597168, + "learning_rate": 2.1875e-05, + "loss": 1.7786, + "step": 21 + }, + { + "epoch": 0.13836477987421383, + "grad_norm": 2.4006130695343018, + "learning_rate": 2.2916666666666667e-05, + "loss": 1.5133, + "step": 22 + }, + { + "epoch": 0.14465408805031446, + "grad_norm": 2.2537267208099365, + "learning_rate": 2.3958333333333334e-05, + "loss": 1.4229, + "step": 23 + }, + { + "epoch": 0.1509433962264151, + "grad_norm": 2.1117539405822754, + "learning_rate": 2.5e-05, + "loss": 1.3577, + "step": 24 + }, + { + "epoch": 0.15723270440251572, + "grad_norm": 1.5717436075210571, + "learning_rate": 2.604166666666667e-05, + "loss": 1.1501, + "step": 25 + }, + { + "epoch": 0.16352201257861634, + "grad_norm": 1.691366195678711, + "learning_rate": 2.7083333333333332e-05, + "loss": 1.292, + "step": 26 + }, + { + "epoch": 0.16981132075471697, + "grad_norm": 1.4936853647232056, + "learning_rate": 2.8125000000000003e-05, + "loss": 1.1469, + "step": 27 + }, + { + "epoch": 0.1761006289308176, + "grad_norm": 1.2858690023422241, + "learning_rate": 2.916666666666667e-05, + "loss": 1.0433, + "step": 28 + }, + { + "epoch": 0.18238993710691823, + "grad_norm": 1.148773193359375, + "learning_rate": 3.0208333333333334e-05, + "loss": 0.9627, + "step": 29 + }, + { + "epoch": 0.18867924528301888, + "grad_norm": 1.0097932815551758, + "learning_rate": 3.125e-05, + "loss": 0.9103, + "step": 30 + }, + { + "epoch": 0.1949685534591195, + "grad_norm": 0.9332402348518372, + "learning_rate": 3.229166666666667e-05, + "loss": 0.979, + "step": 31 + }, + { + "epoch": 0.20125786163522014, + "grad_norm": 0.8993248343467712, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.9553, + "step": 32 + }, + { + "epoch": 0.20754716981132076, + "grad_norm": 0.7925082445144653, + "learning_rate": 3.4375e-05, + "loss": 0.8379, + "step": 33 + }, + { + "epoch": 0.2138364779874214, + "grad_norm": 0.7847669720649719, + "learning_rate": 3.541666666666667e-05, + "loss": 0.9038, + "step": 34 + }, + { + "epoch": 0.22012578616352202, + "grad_norm": 0.800736665725708, + "learning_rate": 3.6458333333333336e-05, + "loss": 0.8354, + "step": 35 + }, + { + "epoch": 0.22641509433962265, + "grad_norm": 0.6036879420280457, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.8517, + "step": 36 + }, + { + "epoch": 0.23270440251572327, + "grad_norm": 0.6031014919281006, + "learning_rate": 3.854166666666667e-05, + "loss": 0.8702, + "step": 37 + }, + { + "epoch": 0.2389937106918239, + "grad_norm": 0.584917426109314, + "learning_rate": 3.958333333333333e-05, + "loss": 0.8812, + "step": 38 + }, + { + "epoch": 0.24528301886792453, + "grad_norm": 0.5815232396125793, + "learning_rate": 4.0625000000000005e-05, + "loss": 0.8336, + "step": 39 + }, + { + "epoch": 0.25157232704402516, + "grad_norm": 0.5307980179786682, + "learning_rate": 4.166666666666667e-05, + "loss": 0.7162, + "step": 40 + }, + { + "epoch": 0.2578616352201258, + "grad_norm": 0.49309515953063965, + "learning_rate": 4.270833333333333e-05, + "loss": 0.7433, + "step": 41 + }, + { + "epoch": 0.2641509433962264, + "grad_norm": 0.5215100646018982, + "learning_rate": 4.375e-05, + "loss": 0.738, + "step": 42 + }, + { + "epoch": 0.27044025157232704, + "grad_norm": 0.5361147522926331, + "learning_rate": 4.4791666666666673e-05, + "loss": 0.7884, + "step": 43 + }, + { + "epoch": 0.27672955974842767, + "grad_norm": 0.5043961405754089, + "learning_rate": 4.5833333333333334e-05, + "loss": 0.814, + "step": 44 + }, + { + "epoch": 0.2830188679245283, + "grad_norm": 0.476026713848114, + "learning_rate": 4.6875e-05, + "loss": 0.8249, + "step": 45 + }, + { + "epoch": 0.2893081761006289, + "grad_norm": 0.5099363923072815, + "learning_rate": 4.791666666666667e-05, + "loss": 0.7205, + "step": 46 + }, + { + "epoch": 0.29559748427672955, + "grad_norm": 0.4583563208580017, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.7646, + "step": 47 + }, + { + "epoch": 0.3018867924528302, + "grad_norm": 0.5203999876976013, + "learning_rate": 5e-05, + "loss": 0.6697, + "step": 48 + }, + { + "epoch": 0.3081761006289308, + "grad_norm": 0.5025014877319336, + "learning_rate": 4.9999329662935534e-05, + "loss": 0.8134, + "step": 49 + }, + { + "epoch": 0.31446540880503143, + "grad_norm": 0.5326013565063477, + "learning_rate": 4.999731868769027e-05, + "loss": 0.7665, + "step": 50 + }, + { + "epoch": 0.32075471698113206, + "grad_norm": 0.4914862811565399, + "learning_rate": 4.99939671821067e-05, + "loss": 0.7717, + "step": 51 + }, + { + "epoch": 0.3270440251572327, + "grad_norm": 0.567669689655304, + "learning_rate": 4.998927532591592e-05, + "loss": 0.677, + "step": 52 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.44353675842285156, + "learning_rate": 4.9983243370727914e-05, + "loss": 0.6829, + "step": 53 + }, + { + "epoch": 0.33962264150943394, + "grad_norm": 0.48537710309028625, + "learning_rate": 4.9975871640018154e-05, + "loss": 0.7817, + "step": 54 + }, + { + "epoch": 0.34591194968553457, + "grad_norm": 0.6286251544952393, + "learning_rate": 4.996716052911017e-05, + "loss": 0.6835, + "step": 55 + }, + { + "epoch": 0.3522012578616352, + "grad_norm": 0.44308704137802124, + "learning_rate": 4.99571105051544e-05, + "loss": 0.728, + "step": 56 + }, + { + "epoch": 0.3584905660377358, + "grad_norm": 0.4270545542240143, + "learning_rate": 4.994572210710315e-05, + "loss": 0.6448, + "step": 57 + }, + { + "epoch": 0.36477987421383645, + "grad_norm": 0.38012009859085083, + "learning_rate": 4.993299594568163e-05, + "loss": 0.675, + "step": 58 + }, + { + "epoch": 0.3710691823899371, + "grad_norm": 0.46653008460998535, + "learning_rate": 4.9918932703355256e-05, + "loss": 0.6821, + "step": 59 + }, + { + "epoch": 0.37735849056603776, + "grad_norm": 0.3612300753593445, + "learning_rate": 4.990353313429303e-05, + "loss": 0.7063, + "step": 60 + }, + { + "epoch": 0.3836477987421384, + "grad_norm": 0.5769712924957275, + "learning_rate": 4.988679806432712e-05, + "loss": 0.6941, + "step": 61 + }, + { + "epoch": 0.389937106918239, + "grad_norm": 0.431997150182724, + "learning_rate": 4.9868728390908526e-05, + "loss": 0.6544, + "step": 62 + }, + { + "epoch": 0.39622641509433965, + "grad_norm": 0.38126569986343384, + "learning_rate": 4.9849325083059e-05, + "loss": 0.6966, + "step": 63 + }, + { + "epoch": 0.4025157232704403, + "grad_norm": 0.40978091955184937, + "learning_rate": 4.982858918131906e-05, + "loss": 0.6866, + "step": 64 + }, + { + "epoch": 0.4088050314465409, + "grad_norm": 0.5318535566329956, + "learning_rate": 4.980652179769218e-05, + "loss": 0.7029, + "step": 65 + }, + { + "epoch": 0.41509433962264153, + "grad_norm": 0.5288330912590027, + "learning_rate": 4.978312411558518e-05, + "loss": 0.6553, + "step": 66 + }, + { + "epoch": 0.42138364779874216, + "grad_norm": 0.6496341824531555, + "learning_rate": 4.9758397389744734e-05, + "loss": 0.696, + "step": 67 + }, + { + "epoch": 0.4276729559748428, + "grad_norm": 0.5196901559829712, + "learning_rate": 4.973234294619011e-05, + "loss": 0.6676, + "step": 68 + }, + { + "epoch": 0.4339622641509434, + "grad_norm": 0.5431825518608093, + "learning_rate": 4.9704962182142044e-05, + "loss": 0.6337, + "step": 69 + }, + { + "epoch": 0.44025157232704404, + "grad_norm": 0.6981568932533264, + "learning_rate": 4.967625656594782e-05, + "loss": 0.7645, + "step": 70 + }, + { + "epoch": 0.44654088050314467, + "grad_norm": 0.4362429082393646, + "learning_rate": 4.9646227637002515e-05, + "loss": 0.647, + "step": 71 + }, + { + "epoch": 0.4528301886792453, + "grad_norm": 0.41873699426651, + "learning_rate": 4.961487700566646e-05, + "loss": 0.6342, + "step": 72 + }, + { + "epoch": 0.4591194968553459, + "grad_norm": 0.589474081993103, + "learning_rate": 4.958220635317886e-05, + "loss": 0.641, + "step": 73 + }, + { + "epoch": 0.46540880503144655, + "grad_norm": 0.5421208739280701, + "learning_rate": 4.9548217431567665e-05, + "loss": 0.8103, + "step": 74 + }, + { + "epoch": 0.4716981132075472, + "grad_norm": 0.48354727029800415, + "learning_rate": 4.95129120635556e-05, + "loss": 0.6205, + "step": 75 + }, + { + "epoch": 0.4779874213836478, + "grad_norm": 0.6121774911880493, + "learning_rate": 4.9476292142462374e-05, + "loss": 0.6678, + "step": 76 + }, + { + "epoch": 0.48427672955974843, + "grad_norm": 0.5440806150436401, + "learning_rate": 4.943835963210324e-05, + "loss": 0.6668, + "step": 77 + }, + { + "epoch": 0.49056603773584906, + "grad_norm": 0.40740126371383667, + "learning_rate": 4.939911656668361e-05, + "loss": 0.61, + "step": 78 + }, + { + "epoch": 0.4968553459119497, + "grad_norm": 0.5682631731033325, + "learning_rate": 4.9358565050689985e-05, + "loss": 0.6939, + "step": 79 + }, + { + "epoch": 0.5031446540880503, + "grad_norm": 0.43090444803237915, + "learning_rate": 4.93167072587771e-05, + "loss": 0.6698, + "step": 80 + }, + { + "epoch": 0.5094339622641509, + "grad_norm": 0.3859785795211792, + "learning_rate": 4.92735454356513e-05, + "loss": 0.5798, + "step": 81 + }, + { + "epoch": 0.5157232704402516, + "grad_norm": 0.4453634023666382, + "learning_rate": 4.922908189595018e-05, + "loss": 0.7936, + "step": 82 + }, + { + "epoch": 0.5220125786163522, + "grad_norm": 0.4291239380836487, + "learning_rate": 4.9183319024118415e-05, + "loss": 0.667, + "step": 83 + }, + { + "epoch": 0.5283018867924528, + "grad_norm": 0.44029664993286133, + "learning_rate": 4.9136259274279955e-05, + "loss": 0.6518, + "step": 84 + }, + { + "epoch": 0.5345911949685535, + "grad_norm": 0.44975465536117554, + "learning_rate": 4.908790517010636e-05, + "loss": 0.6105, + "step": 85 + }, + { + "epoch": 0.5408805031446541, + "grad_norm": 0.3954753577709198, + "learning_rate": 4.903825930468149e-05, + "loss": 0.6954, + "step": 86 + }, + { + "epoch": 0.5471698113207547, + "grad_norm": 0.3935467302799225, + "learning_rate": 4.898732434036244e-05, + "loss": 0.6614, + "step": 87 + }, + { + "epoch": 0.5534591194968553, + "grad_norm": 0.37667638063430786, + "learning_rate": 4.893510300863676e-05, + "loss": 0.6186, + "step": 88 + }, + { + "epoch": 0.559748427672956, + "grad_norm": 0.5198381543159485, + "learning_rate": 4.8881598109976004e-05, + "loss": 0.6153, + "step": 89 + }, + { + "epoch": 0.5660377358490566, + "grad_norm": 0.4063967764377594, + "learning_rate": 4.8826812513685487e-05, + "loss": 0.6472, + "step": 90 + }, + { + "epoch": 0.5723270440251572, + "grad_norm": 0.4114413857460022, + "learning_rate": 4.877074915775049e-05, + "loss": 0.6404, + "step": 91 + }, + { + "epoch": 0.5786163522012578, + "grad_norm": 0.37414512038230896, + "learning_rate": 4.8713411048678635e-05, + "loss": 0.6353, + "step": 92 + }, + { + "epoch": 0.5849056603773585, + "grad_norm": 0.3818528354167938, + "learning_rate": 4.865480126133872e-05, + "loss": 0.6289, + "step": 93 + }, + { + "epoch": 0.5911949685534591, + "grad_norm": 0.37088677287101746, + "learning_rate": 4.859492293879574e-05, + "loss": 0.6242, + "step": 94 + }, + { + "epoch": 0.5974842767295597, + "grad_norm": 0.43665146827697754, + "learning_rate": 4.853377929214243e-05, + "loss": 0.6055, + "step": 95 + }, + { + "epoch": 0.6037735849056604, + "grad_norm": 0.5932008028030396, + "learning_rate": 4.8471373600326996e-05, + "loss": 0.6354, + "step": 96 + }, + { + "epoch": 0.610062893081761, + "grad_norm": 0.46184536814689636, + "learning_rate": 4.8407709209977305e-05, + "loss": 0.7039, + "step": 97 + }, + { + "epoch": 0.6163522012578616, + "grad_norm": 0.44864600896835327, + "learning_rate": 4.834278953522138e-05, + "loss": 0.6679, + "step": 98 + }, + { + "epoch": 0.6226415094339622, + "grad_norm": 0.4060032069683075, + "learning_rate": 4.8276618057504376e-05, + "loss": 0.7479, + "step": 99 + }, + { + "epoch": 0.6289308176100629, + "grad_norm": 0.5088009834289551, + "learning_rate": 4.8209198325401815e-05, + "loss": 0.5923, + "step": 100 + }, + { + "epoch": 0.6352201257861635, + "grad_norm": 0.4294343590736389, + "learning_rate": 4.8140533954429327e-05, + "loss": 0.6313, + "step": 101 + }, + { + "epoch": 0.6415094339622641, + "grad_norm": 0.5710806846618652, + "learning_rate": 4.8070628626848735e-05, + "loss": 0.6736, + "step": 102 + }, + { + "epoch": 0.6477987421383647, + "grad_norm": 0.40560534596443176, + "learning_rate": 4.799948609147061e-05, + "loss": 0.6173, + "step": 103 + }, + { + "epoch": 0.6540880503144654, + "grad_norm": 0.46361806988716125, + "learning_rate": 4.792711016345321e-05, + "loss": 0.6756, + "step": 104 + }, + { + "epoch": 0.660377358490566, + "grad_norm": 0.5206082463264465, + "learning_rate": 4.785350472409792e-05, + "loss": 0.6413, + "step": 105 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.42583200335502625, + "learning_rate": 4.777867372064105e-05, + "loss": 0.6201, + "step": 106 + }, + { + "epoch": 0.6729559748427673, + "grad_norm": 0.49348241090774536, + "learning_rate": 4.770262116604224e-05, + "loss": 0.5777, + "step": 107 + }, + { + "epoch": 0.6792452830188679, + "grad_norm": 0.43750065565109253, + "learning_rate": 4.762535113876917e-05, + "loss": 0.6326, + "step": 108 + }, + { + "epoch": 0.6855345911949685, + "grad_norm": 0.431643545627594, + "learning_rate": 4.754686778257891e-05, + "loss": 0.5849, + "step": 109 + }, + { + "epoch": 0.6918238993710691, + "grad_norm": 0.41906824707984924, + "learning_rate": 4.7467175306295655e-05, + "loss": 0.6779, + "step": 110 + }, + { + "epoch": 0.6981132075471698, + "grad_norm": 0.4261593222618103, + "learning_rate": 4.738627798358506e-05, + "loss": 0.565, + "step": 111 + }, + { + "epoch": 0.7044025157232704, + "grad_norm": 0.42877814173698425, + "learning_rate": 4.730418015272503e-05, + "loss": 0.6836, + "step": 112 + }, + { + "epoch": 0.710691823899371, + "grad_norm": 0.40995511412620544, + "learning_rate": 4.722088621637309e-05, + "loss": 0.5849, + "step": 113 + }, + { + "epoch": 0.7169811320754716, + "grad_norm": 0.5606467723846436, + "learning_rate": 4.713640064133025e-05, + "loss": 0.644, + "step": 114 + }, + { + "epoch": 0.7232704402515723, + "grad_norm": 0.48454752564430237, + "learning_rate": 4.7050727958301506e-05, + "loss": 0.5418, + "step": 115 + }, + { + "epoch": 0.7295597484276729, + "grad_norm": 0.4099617898464203, + "learning_rate": 4.6963872761652835e-05, + "loss": 0.6524, + "step": 116 + }, + { + "epoch": 0.7358490566037735, + "grad_norm": 0.47192293405532837, + "learning_rate": 4.687583970916487e-05, + "loss": 0.6134, + "step": 117 + }, + { + "epoch": 0.7421383647798742, + "grad_norm": 0.4925817549228668, + "learning_rate": 4.678663352178301e-05, + "loss": 0.6517, + "step": 118 + }, + { + "epoch": 0.7484276729559748, + "grad_norm": 0.41517379879951477, + "learning_rate": 4.6696258983364385e-05, + "loss": 0.5763, + "step": 119 + }, + { + "epoch": 0.7547169811320755, + "grad_norm": 0.6227956414222717, + "learning_rate": 4.660472094042121e-05, + "loss": 0.7349, + "step": 120 + }, + { + "epoch": 0.7610062893081762, + "grad_norm": 0.39108285307884216, + "learning_rate": 4.651202430186092e-05, + "loss": 0.6548, + "step": 121 + }, + { + "epoch": 0.7672955974842768, + "grad_norm": 0.40210628509521484, + "learning_rate": 4.641817403872293e-05, + "loss": 0.6135, + "step": 122 + }, + { + "epoch": 0.7735849056603774, + "grad_norm": 0.42835289239883423, + "learning_rate": 4.6323175183912024e-05, + "loss": 0.5227, + "step": 123 + }, + { + "epoch": 0.779874213836478, + "grad_norm": 0.6215445399284363, + "learning_rate": 4.6227032831928484e-05, + "loss": 0.5265, + "step": 124 + }, + { + "epoch": 0.7861635220125787, + "grad_norm": 0.43423891067504883, + "learning_rate": 4.6129752138594874e-05, + "loss": 0.5972, + "step": 125 + }, + { + "epoch": 0.7924528301886793, + "grad_norm": 0.4693637788295746, + "learning_rate": 4.6031338320779534e-05, + "loss": 0.6758, + "step": 126 + }, + { + "epoch": 0.7987421383647799, + "grad_norm": 0.47571077942848206, + "learning_rate": 4.5931796656116846e-05, + "loss": 0.6419, + "step": 127 + }, + { + "epoch": 0.8050314465408805, + "grad_norm": 0.5828564167022705, + "learning_rate": 4.5831132482724195e-05, + "loss": 0.6952, + "step": 128 + }, + { + "epoch": 0.8113207547169812, + "grad_norm": 0.5325509309768677, + "learning_rate": 4.572935119891571e-05, + "loss": 0.6093, + "step": 129 + }, + { + "epoch": 0.8176100628930818, + "grad_norm": 0.4476761519908905, + "learning_rate": 4.5626458262912745e-05, + "loss": 0.5688, + "step": 130 + }, + { + "epoch": 0.8238993710691824, + "grad_norm": 0.36771783232688904, + "learning_rate": 4.552245919255117e-05, + "loss": 0.5778, + "step": 131 + }, + { + "epoch": 0.8301886792452831, + "grad_norm": 0.3695763647556305, + "learning_rate": 4.541735956498554e-05, + "loss": 0.517, + "step": 132 + }, + { + "epoch": 0.8364779874213837, + "grad_norm": 0.46155717968940735, + "learning_rate": 4.5311165016389916e-05, + "loss": 0.631, + "step": 133 + }, + { + "epoch": 0.8427672955974843, + "grad_norm": 0.5536386966705322, + "learning_rate": 4.5203881241655644e-05, + "loss": 0.6309, + "step": 134 + }, + { + "epoch": 0.8490566037735849, + "grad_norm": 0.42256519198417664, + "learning_rate": 4.509551399408598e-05, + "loss": 0.6754, + "step": 135 + }, + { + "epoch": 0.8553459119496856, + "grad_norm": 0.41634511947631836, + "learning_rate": 4.498606908508754e-05, + "loss": 0.6547, + "step": 136 + }, + { + "epoch": 0.8616352201257862, + "grad_norm": 0.38796696066856384, + "learning_rate": 4.487555238385862e-05, + "loss": 0.5693, + "step": 137 + }, + { + "epoch": 0.8679245283018868, + "grad_norm": 0.43052586913108826, + "learning_rate": 4.476396981707453e-05, + "loss": 0.6655, + "step": 138 + }, + { + "epoch": 0.8742138364779874, + "grad_norm": 0.44500571489334106, + "learning_rate": 4.465132736856969e-05, + "loss": 0.6563, + "step": 139 + }, + { + "epoch": 0.8805031446540881, + "grad_norm": 0.44693946838378906, + "learning_rate": 4.453763107901675e-05, + "loss": 0.5729, + "step": 140 + }, + { + "epoch": 0.8867924528301887, + "grad_norm": 0.3982055187225342, + "learning_rate": 4.442288704560268e-05, + "loss": 0.6425, + "step": 141 + }, + { + "epoch": 0.8930817610062893, + "grad_norm": 0.5706686973571777, + "learning_rate": 4.430710142170176e-05, + "loss": 0.5732, + "step": 142 + }, + { + "epoch": 0.89937106918239, + "grad_norm": 0.4493609070777893, + "learning_rate": 4.419028041654559e-05, + "loss": 0.6507, + "step": 143 + }, + { + "epoch": 0.9056603773584906, + "grad_norm": 0.3834284543991089, + "learning_rate": 4.4072430294890174e-05, + "loss": 0.6883, + "step": 144 + }, + { + "epoch": 0.9119496855345912, + "grad_norm": 0.4243861138820648, + "learning_rate": 4.3953557376679856e-05, + "loss": 0.5818, + "step": 145 + }, + { + "epoch": 0.9182389937106918, + "grad_norm": 0.42064470052719116, + "learning_rate": 4.383366803670849e-05, + "loss": 0.5963, + "step": 146 + }, + { + "epoch": 0.9245283018867925, + "grad_norm": 0.46670740842819214, + "learning_rate": 4.371276870427753e-05, + "loss": 0.65, + "step": 147 + }, + { + "epoch": 0.9308176100628931, + "grad_norm": 0.44945597648620605, + "learning_rate": 4.359086586285127e-05, + "loss": 0.6554, + "step": 148 + }, + { + "epoch": 0.9371069182389937, + "grad_norm": 0.48251762986183167, + "learning_rate": 4.346796604970912e-05, + "loss": 0.6681, + "step": 149 + }, + { + "epoch": 0.9433962264150944, + "grad_norm": 0.4577901065349579, + "learning_rate": 4.3344075855595104e-05, + "loss": 0.6108, + "step": 150 + }, + { + "epoch": 0.949685534591195, + "grad_norm": 0.4710671603679657, + "learning_rate": 4.321920192436433e-05, + "loss": 0.6177, + "step": 151 + }, + { + "epoch": 0.9559748427672956, + "grad_norm": 0.4275747835636139, + "learning_rate": 4.309335095262676e-05, + "loss": 0.5881, + "step": 152 + }, + { + "epoch": 0.9622641509433962, + "grad_norm": 0.4541204571723938, + "learning_rate": 4.296652968938807e-05, + "loss": 0.6142, + "step": 153 + }, + { + "epoch": 0.9685534591194969, + "grad_norm": 0.4179267883300781, + "learning_rate": 4.283874493568772e-05, + "loss": 0.6463, + "step": 154 + }, + { + "epoch": 0.9748427672955975, + "grad_norm": 0.42434728145599365, + "learning_rate": 4.271000354423426e-05, + "loss": 0.5873, + "step": 155 + }, + { + "epoch": 0.9811320754716981, + "grad_norm": 0.44202134013175964, + "learning_rate": 4.258031241903778e-05, + "loss": 0.6046, + "step": 156 + }, + { + "epoch": 0.9874213836477987, + "grad_norm": 0.47817060351371765, + "learning_rate": 4.2449678515039747e-05, + "loss": 0.5989, + "step": 157 + }, + { + "epoch": 0.9937106918238994, + "grad_norm": 0.43847018480300903, + "learning_rate": 4.231810883773999e-05, + "loss": 0.6156, + "step": 158 + }, + { + "epoch": 1.0, + "grad_norm": 0.48976290225982666, + "learning_rate": 4.218561044282099e-05, + "loss": 0.6177, + "step": 159 + }, + { + "epoch": 1.0062893081761006, + "grad_norm": 0.4213927984237671, + "learning_rate": 4.2052190435769554e-05, + "loss": 0.5881, + "step": 160 + }, + { + "epoch": 1.0125786163522013, + "grad_norm": 0.3923173248767853, + "learning_rate": 4.191785597149577e-05, + "loss": 0.5354, + "step": 161 + }, + { + "epoch": 1.0188679245283019, + "grad_norm": 0.41947099566459656, + "learning_rate": 4.178261425394926e-05, + "loss": 0.5745, + "step": 162 + }, + { + "epoch": 1.0251572327044025, + "grad_norm": 0.45812028646469116, + "learning_rate": 4.1646472535732895e-05, + "loss": 0.5836, + "step": 163 + }, + { + "epoch": 1.0314465408805031, + "grad_norm": 0.4519791007041931, + "learning_rate": 4.1509438117713866e-05, + "loss": 0.6118, + "step": 164 + }, + { + "epoch": 1.0377358490566038, + "grad_norm": 0.5628229379653931, + "learning_rate": 4.137151834863213e-05, + "loss": 0.5811, + "step": 165 + }, + { + "epoch": 1.0440251572327044, + "grad_norm": 0.3987003564834595, + "learning_rate": 4.123272062470633e-05, + "loss": 0.5179, + "step": 166 + }, + { + "epoch": 1.050314465408805, + "grad_norm": 0.4499664604663849, + "learning_rate": 4.109305238923718e-05, + "loss": 0.548, + "step": 167 + }, + { + "epoch": 1.0566037735849056, + "grad_norm": 0.4336049556732178, + "learning_rate": 4.095252113220827e-05, + "loss": 0.5659, + "step": 168 + }, + { + "epoch": 1.0628930817610063, + "grad_norm": 0.5409331321716309, + "learning_rate": 4.0811134389884433e-05, + "loss": 0.5522, + "step": 169 + }, + { + "epoch": 1.069182389937107, + "grad_norm": 0.41802865266799927, + "learning_rate": 4.066889974440757e-05, + "loss": 0.542, + "step": 170 + }, + { + "epoch": 1.0754716981132075, + "grad_norm": 0.48149824142456055, + "learning_rate": 4.0525824823390045e-05, + "loss": 0.6131, + "step": 171 + }, + { + "epoch": 1.0817610062893082, + "grad_norm": 0.5059295296669006, + "learning_rate": 4.038191729950569e-05, + "loss": 0.5823, + "step": 172 + }, + { + "epoch": 1.0880503144654088, + "grad_norm": 0.5310669541358948, + "learning_rate": 4.0237184890078245e-05, + "loss": 0.6066, + "step": 173 + }, + { + "epoch": 1.0943396226415094, + "grad_norm": 0.5470696091651917, + "learning_rate": 4.009163535666761e-05, + "loss": 0.6407, + "step": 174 + }, + { + "epoch": 1.10062893081761, + "grad_norm": 0.4407522678375244, + "learning_rate": 3.994527650465352e-05, + "loss": 0.573, + "step": 175 + }, + { + "epoch": 1.1069182389937107, + "grad_norm": 0.4072059094905853, + "learning_rate": 3.979811618281706e-05, + "loss": 0.6349, + "step": 176 + }, + { + "epoch": 1.1132075471698113, + "grad_norm": 0.6410146355628967, + "learning_rate": 3.9650162282919655e-05, + "loss": 0.6036, + "step": 177 + }, + { + "epoch": 1.119496855345912, + "grad_norm": 0.4664185047149658, + "learning_rate": 3.9501422739279956e-05, + "loss": 0.5855, + "step": 178 + }, + { + "epoch": 1.1257861635220126, + "grad_norm": 0.7204552888870239, + "learning_rate": 3.9351905528348285e-05, + "loss": 0.5719, + "step": 179 + }, + { + "epoch": 1.1320754716981132, + "grad_norm": 0.47248926758766174, + "learning_rate": 3.920161866827889e-05, + "loss": 0.5764, + "step": 180 + }, + { + "epoch": 1.1383647798742138, + "grad_norm": 0.64155113697052, + "learning_rate": 3.90505702185e-05, + "loss": 0.644, + "step": 181 + }, + { + "epoch": 1.1446540880503144, + "grad_norm": 0.5559830665588379, + "learning_rate": 3.889876827928156e-05, + "loss": 0.5883, + "step": 182 + }, + { + "epoch": 1.150943396226415, + "grad_norm": 0.46357718110084534, + "learning_rate": 3.874622099130087e-05, + "loss": 0.5942, + "step": 183 + }, + { + "epoch": 1.1572327044025157, + "grad_norm": 0.4527578055858612, + "learning_rate": 3.859293653520604e-05, + "loss": 0.6086, + "step": 184 + }, + { + "epoch": 1.1635220125786163, + "grad_norm": 0.45968765020370483, + "learning_rate": 3.843892313117724e-05, + "loss": 0.6105, + "step": 185 + }, + { + "epoch": 1.169811320754717, + "grad_norm": 0.5293806791305542, + "learning_rate": 3.8284189038485936e-05, + "loss": 0.5622, + "step": 186 + }, + { + "epoch": 1.1761006289308176, + "grad_norm": 0.4499124586582184, + "learning_rate": 3.812874255505191e-05, + "loss": 0.5451, + "step": 187 + }, + { + "epoch": 1.1823899371069182, + "grad_norm": 0.5140619277954102, + "learning_rate": 3.797259201699833e-05, + "loss": 0.5864, + "step": 188 + }, + { + "epoch": 1.1886792452830188, + "grad_norm": 0.40918025374412537, + "learning_rate": 3.781574579820464e-05, + "loss": 0.5602, + "step": 189 + }, + { + "epoch": 1.1949685534591195, + "grad_norm": 0.4417194128036499, + "learning_rate": 3.765821230985758e-05, + "loss": 0.5556, + "step": 190 + }, + { + "epoch": 1.20125786163522, + "grad_norm": 0.4697968363761902, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.6491, + "step": 191 + }, + { + "epoch": 1.2075471698113207, + "grad_norm": 0.40187153220176697, + "learning_rate": 3.7341117353077966e-05, + "loss": 0.5797, + "step": 192 + }, + { + "epoch": 1.2138364779874213, + "grad_norm": 0.456836462020874, + "learning_rate": 3.718157288948563e-05, + "loss": 0.5613, + "step": 193 + }, + { + "epoch": 1.220125786163522, + "grad_norm": 0.45992621779441833, + "learning_rate": 3.702137516510838e-05, + "loss": 0.6301, + "step": 194 + }, + { + "epoch": 1.2264150943396226, + "grad_norm": 0.45000532269477844, + "learning_rate": 3.686053277086401e-05, + "loss": 0.5772, + "step": 195 + }, + { + "epoch": 1.2327044025157232, + "grad_norm": 0.4734075963497162, + "learning_rate": 3.669905433224199e-05, + "loss": 0.5452, + "step": 196 + }, + { + "epoch": 1.2389937106918238, + "grad_norm": 0.41561609506607056, + "learning_rate": 3.653694850884091e-05, + "loss": 0.5365, + "step": 197 + }, + { + "epoch": 1.2452830188679245, + "grad_norm": 0.469097763299942, + "learning_rate": 3.637422399390413e-05, + "loss": 0.5396, + "step": 198 + }, + { + "epoch": 1.251572327044025, + "grad_norm": 0.46705111861228943, + "learning_rate": 3.621088951385353e-05, + "loss": 0.6024, + "step": 199 + }, + { + "epoch": 1.2578616352201257, + "grad_norm": 0.5201407074928284, + "learning_rate": 3.604695382782159e-05, + "loss": 0.6905, + "step": 200 + }, + { + "epoch": 1.2641509433962264, + "grad_norm": 0.4639309346675873, + "learning_rate": 3.588242572718162e-05, + "loss": 0.5909, + "step": 201 + }, + { + "epoch": 1.270440251572327, + "grad_norm": 0.4756741225719452, + "learning_rate": 3.5717314035076355e-05, + "loss": 0.5745, + "step": 202 + }, + { + "epoch": 1.2767295597484276, + "grad_norm": 0.5243765115737915, + "learning_rate": 3.5551627605944745e-05, + "loss": 0.6439, + "step": 203 + }, + { + "epoch": 1.2830188679245282, + "grad_norm": 0.4495748281478882, + "learning_rate": 3.5385375325047166e-05, + "loss": 0.5611, + "step": 204 + }, + { + "epoch": 1.2893081761006289, + "grad_norm": 0.47336816787719727, + "learning_rate": 3.521856610798887e-05, + "loss": 0.5846, + "step": 205 + }, + { + "epoch": 1.2955974842767295, + "grad_norm": 0.4667642116546631, + "learning_rate": 3.505120890024195e-05, + "loss": 0.5982, + "step": 206 + }, + { + "epoch": 1.3018867924528301, + "grad_norm": 0.4477729797363281, + "learning_rate": 3.4883312676665536e-05, + "loss": 0.6265, + "step": 207 + }, + { + "epoch": 1.3081761006289307, + "grad_norm": 0.5078469514846802, + "learning_rate": 3.4714886441024574e-05, + "loss": 0.5161, + "step": 208 + }, + { + "epoch": 1.3144654088050314, + "grad_norm": 0.5072935819625854, + "learning_rate": 3.4545939225506934e-05, + "loss": 0.5408, + "step": 209 + }, + { + "epoch": 1.320754716981132, + "grad_norm": 0.5006597638130188, + "learning_rate": 3.437648009023905e-05, + "loss": 0.5715, + "step": 210 + }, + { + "epoch": 1.3270440251572326, + "grad_norm": 0.44206503033638, + "learning_rate": 3.420651812280006e-05, + "loss": 0.5694, + "step": 211 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.4964762032032013, + "learning_rate": 3.4036062437734484e-05, + "loss": 0.5203, + "step": 212 + }, + { + "epoch": 1.3396226415094339, + "grad_norm": 0.4342876076698303, + "learning_rate": 3.386512217606339e-05, + "loss": 0.5778, + "step": 213 + }, + { + "epoch": 1.3459119496855345, + "grad_norm": 0.46520864963531494, + "learning_rate": 3.369370650479425e-05, + "loss": 0.5757, + "step": 214 + }, + { + "epoch": 1.3522012578616351, + "grad_norm": 0.5179557204246521, + "learning_rate": 3.3521824616429285e-05, + "loss": 0.5348, + "step": 215 + }, + { + "epoch": 1.3584905660377358, + "grad_norm": 0.45922955870628357, + "learning_rate": 3.3349485728472535e-05, + "loss": 0.5982, + "step": 216 + }, + { + "epoch": 1.3647798742138364, + "grad_norm": 0.5132372975349426, + "learning_rate": 3.3176699082935545e-05, + "loss": 0.6131, + "step": 217 + }, + { + "epoch": 1.371069182389937, + "grad_norm": 0.4740884602069855, + "learning_rate": 3.300347394584172e-05, + "loss": 0.6194, + "step": 218 + }, + { + "epoch": 1.3773584905660377, + "grad_norm": 0.45677605271339417, + "learning_rate": 3.282981960672948e-05, + "loss": 0.5938, + "step": 219 + }, + { + "epoch": 1.3836477987421385, + "grad_norm": 0.4545290172100067, + "learning_rate": 3.265574537815398e-05, + "loss": 0.5634, + "step": 220 + }, + { + "epoch": 1.389937106918239, + "grad_norm": 0.4439068138599396, + "learning_rate": 3.248126059518785e-05, + "loss": 0.5543, + "step": 221 + }, + { + "epoch": 1.3962264150943398, + "grad_norm": 0.4973136782646179, + "learning_rate": 3.230637461492043e-05, + "loss": 0.549, + "step": 222 + }, + { + "epoch": 1.4025157232704402, + "grad_norm": 0.5018147826194763, + "learning_rate": 3.213109681595612e-05, + "loss": 0.5799, + "step": 223 + }, + { + "epoch": 1.408805031446541, + "grad_norm": 0.4906245768070221, + "learning_rate": 3.195543659791132e-05, + "loss": 0.5788, + "step": 224 + }, + { + "epoch": 1.4150943396226414, + "grad_norm": 0.5228400826454163, + "learning_rate": 3.177940338091043e-05, + "loss": 0.4883, + "step": 225 + }, + { + "epoch": 1.4213836477987423, + "grad_norm": 0.5177304148674011, + "learning_rate": 3.160300660508064e-05, + "loss": 0.5737, + "step": 226 + }, + { + "epoch": 1.4276729559748427, + "grad_norm": 0.4641788899898529, + "learning_rate": 3.14262557300457e-05, + "loss": 0.5416, + "step": 227 + }, + { + "epoch": 1.4339622641509435, + "grad_norm": 0.49331700801849365, + "learning_rate": 3.124916023441865e-05, + "loss": 0.5747, + "step": 228 + }, + { + "epoch": 1.440251572327044, + "grad_norm": 0.4671120345592499, + "learning_rate": 3.107172961529343e-05, + "loss": 0.508, + "step": 229 + }, + { + "epoch": 1.4465408805031448, + "grad_norm": 0.5811720490455627, + "learning_rate": 3.0893973387735687e-05, + "loss": 0.6929, + "step": 230 + }, + { + "epoch": 1.4528301886792452, + "grad_norm": 0.48253801465034485, + "learning_rate": 3.071590108427244e-05, + "loss": 0.6467, + "step": 231 + }, + { + "epoch": 1.459119496855346, + "grad_norm": 0.5044742226600647, + "learning_rate": 3.0537522254380905e-05, + "loss": 0.5067, + "step": 232 + }, + { + "epoch": 1.4654088050314464, + "grad_norm": 0.5015671849250793, + "learning_rate": 3.0358846463976372e-05, + "loss": 0.6052, + "step": 233 + }, + { + "epoch": 1.4716981132075473, + "grad_norm": 0.5023432374000549, + "learning_rate": 3.017988329489923e-05, + "loss": 0.5961, + "step": 234 + }, + { + "epoch": 1.4779874213836477, + "grad_norm": 0.5157131552696228, + "learning_rate": 3.0000642344401113e-05, + "loss": 0.6285, + "step": 235 + }, + { + "epoch": 1.4842767295597485, + "grad_norm": 0.5081720948219299, + "learning_rate": 2.9821133224630226e-05, + "loss": 0.4634, + "step": 236 + }, + { + "epoch": 1.490566037735849, + "grad_norm": 0.4940662086009979, + "learning_rate": 2.9641365562115887e-05, + "loss": 0.5288, + "step": 237 + }, + { + "epoch": 1.4968553459119498, + "grad_norm": 0.6005929708480835, + "learning_rate": 2.9461348997252265e-05, + "loss": 0.5748, + "step": 238 + }, + { + "epoch": 1.5031446540880502, + "grad_norm": 0.5340356230735779, + "learning_rate": 2.9281093183781403e-05, + "loss": 0.5944, + "step": 239 + }, + { + "epoch": 1.509433962264151, + "grad_norm": 0.5056872367858887, + "learning_rate": 2.9100607788275545e-05, + "loss": 0.5549, + "step": 240 + }, + { + "epoch": 1.5157232704402515, + "grad_norm": 0.5385233759880066, + "learning_rate": 2.891990248961871e-05, + "loss": 0.5345, + "step": 241 + }, + { + "epoch": 1.5220125786163523, + "grad_norm": 0.48144999146461487, + "learning_rate": 2.8738986978487625e-05, + "loss": 0.5839, + "step": 242 + }, + { + "epoch": 1.5283018867924527, + "grad_norm": 0.5069999098777771, + "learning_rate": 2.8557870956832132e-05, + "loss": 0.4931, + "step": 243 + }, + { + "epoch": 1.5345911949685536, + "grad_norm": 0.4660912752151489, + "learning_rate": 2.8376564137354795e-05, + "loss": 0.5598, + "step": 244 + }, + { + "epoch": 1.540880503144654, + "grad_norm": 0.5416334271430969, + "learning_rate": 2.8195076242990122e-05, + "loss": 0.5894, + "step": 245 + }, + { + "epoch": 1.5471698113207548, + "grad_norm": 0.49134501814842224, + "learning_rate": 2.8013417006383076e-05, + "loss": 0.6345, + "step": 246 + }, + { + "epoch": 1.5534591194968552, + "grad_norm": 0.5861812829971313, + "learning_rate": 2.783159616936723e-05, + "loss": 0.6519, + "step": 247 + }, + { + "epoch": 1.559748427672956, + "grad_norm": 0.47188055515289307, + "learning_rate": 2.764962348244228e-05, + "loss": 0.5658, + "step": 248 + }, + { + "epoch": 1.5660377358490565, + "grad_norm": 0.4838746190071106, + "learning_rate": 2.7467508704251137e-05, + "loss": 0.5934, + "step": 249 + }, + { + "epoch": 1.5723270440251573, + "grad_norm": 0.516981840133667, + "learning_rate": 2.7285261601056698e-05, + "loss": 0.5341, + "step": 250 + }, + { + "epoch": 1.5786163522012577, + "grad_norm": 0.4871889352798462, + "learning_rate": 2.7102891946217994e-05, + "loss": 0.5885, + "step": 251 + }, + { + "epoch": 1.5849056603773586, + "grad_norm": 0.47121965885162354, + "learning_rate": 2.6920409519666174e-05, + "loss": 0.5988, + "step": 252 + }, + { + "epoch": 1.591194968553459, + "grad_norm": 0.5421566367149353, + "learning_rate": 2.6737824107379948e-05, + "loss": 0.6635, + "step": 253 + }, + { + "epoch": 1.5974842767295598, + "grad_norm": 0.5449573993682861, + "learning_rate": 2.655514550086086e-05, + "loss": 0.5365, + "step": 254 + }, + { + "epoch": 1.6037735849056602, + "grad_norm": 0.5301252007484436, + "learning_rate": 2.637238349660819e-05, + "loss": 0.6854, + "step": 255 + }, + { + "epoch": 1.610062893081761, + "grad_norm": 0.41109421849250793, + "learning_rate": 2.6189547895593562e-05, + "loss": 0.5234, + "step": 256 + }, + { + "epoch": 1.6163522012578615, + "grad_norm": 0.5346055626869202, + "learning_rate": 2.600664850273538e-05, + "loss": 0.5962, + "step": 257 + }, + { + "epoch": 1.6226415094339623, + "grad_norm": 0.5180861949920654, + "learning_rate": 2.582369512637302e-05, + "loss": 0.5396, + "step": 258 + }, + { + "epoch": 1.6289308176100628, + "grad_norm": 0.49982312321662903, + "learning_rate": 2.564069757774082e-05, + "loss": 0.4889, + "step": 259 + }, + { + "epoch": 1.6352201257861636, + "grad_norm": 0.5226275324821472, + "learning_rate": 2.545766567044194e-05, + "loss": 0.5893, + "step": 260 + }, + { + "epoch": 1.641509433962264, + "grad_norm": 0.47939932346343994, + "learning_rate": 2.527460921992209e-05, + "loss": 0.566, + "step": 261 + }, + { + "epoch": 1.6477987421383649, + "grad_norm": 0.536264955997467, + "learning_rate": 2.509153804294318e-05, + "loss": 0.5598, + "step": 262 + }, + { + "epoch": 1.6540880503144653, + "grad_norm": 0.5297203660011292, + "learning_rate": 2.490846195705683e-05, + "loss": 0.552, + "step": 263 + }, + { + "epoch": 1.6603773584905661, + "grad_norm": 0.5188955664634705, + "learning_rate": 2.4725390780077908e-05, + "loss": 0.6233, + "step": 264 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.4677969217300415, + "learning_rate": 2.4542334329558077e-05, + "loss": 0.4968, + "step": 265 + }, + { + "epoch": 1.6729559748427674, + "grad_norm": 0.5716769099235535, + "learning_rate": 2.435930242225919e-05, + "loss": 0.5315, + "step": 266 + }, + { + "epoch": 1.6792452830188678, + "grad_norm": 0.5071538090705872, + "learning_rate": 2.4176304873626985e-05, + "loss": 0.5622, + "step": 267 + }, + { + "epoch": 1.6855345911949686, + "grad_norm": 0.523229718208313, + "learning_rate": 2.399335149726463e-05, + "loss": 0.5999, + "step": 268 + }, + { + "epoch": 1.691823899371069, + "grad_norm": 0.5254403948783875, + "learning_rate": 2.3810452104406444e-05, + "loss": 0.6351, + "step": 269 + }, + { + "epoch": 1.6981132075471699, + "grad_norm": 0.53160560131073, + "learning_rate": 2.3627616503391814e-05, + "loss": 0.5754, + "step": 270 + }, + { + "epoch": 1.7044025157232703, + "grad_norm": 0.5396912693977356, + "learning_rate": 2.3444854499139142e-05, + "loss": 0.5635, + "step": 271 + }, + { + "epoch": 1.7106918238993711, + "grad_norm": 0.5528764724731445, + "learning_rate": 2.3262175892620065e-05, + "loss": 0.5368, + "step": 272 + }, + { + "epoch": 1.7169811320754715, + "grad_norm": 0.4812920093536377, + "learning_rate": 2.307959048033383e-05, + "loss": 0.5508, + "step": 273 + }, + { + "epoch": 1.7232704402515724, + "grad_norm": 0.5467996001243591, + "learning_rate": 2.2897108053782e-05, + "loss": 0.6073, + "step": 274 + }, + { + "epoch": 1.7295597484276728, + "grad_norm": 0.5203157663345337, + "learning_rate": 2.271473839894331e-05, + "loss": 0.5326, + "step": 275 + }, + { + "epoch": 1.7358490566037736, + "grad_norm": 0.4970155358314514, + "learning_rate": 2.253249129574887e-05, + "loss": 0.5444, + "step": 276 + }, + { + "epoch": 1.742138364779874, + "grad_norm": 0.5279742479324341, + "learning_rate": 2.2350376517557727e-05, + "loss": 0.5778, + "step": 277 + }, + { + "epoch": 1.748427672955975, + "grad_norm": 0.5293897986412048, + "learning_rate": 2.216840383063277e-05, + "loss": 0.5786, + "step": 278 + }, + { + "epoch": 1.7547169811320755, + "grad_norm": 0.565350353717804, + "learning_rate": 2.1986582993616926e-05, + "loss": 0.5877, + "step": 279 + }, + { + "epoch": 1.7610062893081762, + "grad_norm": 0.47762683033943176, + "learning_rate": 2.1804923757009884e-05, + "loss": 0.5419, + "step": 280 + }, + { + "epoch": 1.7672955974842768, + "grad_norm": 0.5171676278114319, + "learning_rate": 2.1623435862645204e-05, + "loss": 0.5418, + "step": 281 + }, + { + "epoch": 1.7735849056603774, + "grad_norm": 0.45764029026031494, + "learning_rate": 2.1442129043167874e-05, + "loss": 0.5487, + "step": 282 + }, + { + "epoch": 1.779874213836478, + "grad_norm": 0.5272729396820068, + "learning_rate": 2.126101302151238e-05, + "loss": 0.5317, + "step": 283 + }, + { + "epoch": 1.7861635220125787, + "grad_norm": 0.49889740347862244, + "learning_rate": 2.1080097510381298e-05, + "loss": 0.6046, + "step": 284 + }, + { + "epoch": 1.7924528301886793, + "grad_norm": 0.5512136220932007, + "learning_rate": 2.089939221172446e-05, + "loss": 0.6541, + "step": 285 + }, + { + "epoch": 1.79874213836478, + "grad_norm": 0.5187536478042603, + "learning_rate": 2.07189068162186e-05, + "loss": 0.5646, + "step": 286 + }, + { + "epoch": 1.8050314465408805, + "grad_norm": 0.4920225143432617, + "learning_rate": 2.0538651002747744e-05, + "loss": 0.5561, + "step": 287 + }, + { + "epoch": 1.8113207547169812, + "grad_norm": 0.5807557702064514, + "learning_rate": 2.0358634437884112e-05, + "loss": 0.6087, + "step": 288 + }, + { + "epoch": 1.8176100628930818, + "grad_norm": 0.48779597878456116, + "learning_rate": 2.0178866775369777e-05, + "loss": 0.5801, + "step": 289 + }, + { + "epoch": 1.8238993710691824, + "grad_norm": 0.47587329149246216, + "learning_rate": 1.9999357655598893e-05, + "loss": 0.6003, + "step": 290 + }, + { + "epoch": 1.830188679245283, + "grad_norm": 0.5073649883270264, + "learning_rate": 1.9820116705100777e-05, + "loss": 0.5838, + "step": 291 + }, + { + "epoch": 1.8364779874213837, + "grad_norm": 0.5661832690238953, + "learning_rate": 1.9641153536023644e-05, + "loss": 0.6054, + "step": 292 + }, + { + "epoch": 1.8427672955974843, + "grad_norm": 0.4822792410850525, + "learning_rate": 1.9462477745619108e-05, + "loss": 0.5515, + "step": 293 + }, + { + "epoch": 1.849056603773585, + "grad_norm": 0.5438389182090759, + "learning_rate": 1.928409891572757e-05, + "loss": 0.6225, + "step": 294 + }, + { + "epoch": 1.8553459119496856, + "grad_norm": 0.4644525647163391, + "learning_rate": 1.9106026612264316e-05, + "loss": 0.6214, + "step": 295 + }, + { + "epoch": 1.8616352201257862, + "grad_norm": 0.477500855922699, + "learning_rate": 1.8928270384706584e-05, + "loss": 0.6164, + "step": 296 + }, + { + "epoch": 1.8679245283018868, + "grad_norm": 0.4944886267185211, + "learning_rate": 1.875083976558136e-05, + "loss": 0.5533, + "step": 297 + }, + { + "epoch": 1.8742138364779874, + "grad_norm": 0.5480766892433167, + "learning_rate": 1.8573744269954298e-05, + "loss": 0.6305, + "step": 298 + }, + { + "epoch": 1.880503144654088, + "grad_norm": 0.5053893327713013, + "learning_rate": 1.8396993394919372e-05, + "loss": 0.574, + "step": 299 + }, + { + "epoch": 1.8867924528301887, + "grad_norm": 0.559573233127594, + "learning_rate": 1.8220596619089576e-05, + "loss": 0.7138, + "step": 300 + }, + { + "epoch": 1.8930817610062893, + "grad_norm": 0.5412449836730957, + "learning_rate": 1.8044563402088684e-05, + "loss": 0.6108, + "step": 301 + }, + { + "epoch": 1.89937106918239, + "grad_norm": 0.49840930104255676, + "learning_rate": 1.7868903184043887e-05, + "loss": 0.546, + "step": 302 + }, + { + "epoch": 1.9056603773584906, + "grad_norm": 0.6073680520057678, + "learning_rate": 1.7693625385079577e-05, + "loss": 0.5597, + "step": 303 + }, + { + "epoch": 1.9119496855345912, + "grad_norm": 0.5452404022216797, + "learning_rate": 1.7518739404812155e-05, + "loss": 0.6107, + "step": 304 + }, + { + "epoch": 1.9182389937106918, + "grad_norm": 0.48530417680740356, + "learning_rate": 1.7344254621846016e-05, + "loss": 0.5671, + "step": 305 + }, + { + "epoch": 1.9245283018867925, + "grad_norm": 0.47276559472084045, + "learning_rate": 1.7170180393270532e-05, + "loss": 0.5503, + "step": 306 + }, + { + "epoch": 1.930817610062893, + "grad_norm": 0.4949149191379547, + "learning_rate": 1.699652605415828e-05, + "loss": 0.4958, + "step": 307 + }, + { + "epoch": 1.9371069182389937, + "grad_norm": 0.5216560363769531, + "learning_rate": 1.682330091706446e-05, + "loss": 0.58, + "step": 308 + }, + { + "epoch": 1.9433962264150944, + "grad_norm": 0.5286461710929871, + "learning_rate": 1.6650514271527468e-05, + "loss": 0.5293, + "step": 309 + }, + { + "epoch": 1.949685534591195, + "grad_norm": 0.4912795424461365, + "learning_rate": 1.647817538357072e-05, + "loss": 0.5666, + "step": 310 + }, + { + "epoch": 1.9559748427672956, + "grad_norm": 0.5797849297523499, + "learning_rate": 1.630629349520576e-05, + "loss": 0.5493, + "step": 311 + }, + { + "epoch": 1.9622641509433962, + "grad_norm": 0.5302536487579346, + "learning_rate": 1.613487782393661e-05, + "loss": 0.5516, + "step": 312 + }, + { + "epoch": 1.9685534591194969, + "grad_norm": 0.5543875694274902, + "learning_rate": 1.5963937562265525e-05, + "loss": 0.5358, + "step": 313 + }, + { + "epoch": 1.9748427672955975, + "grad_norm": 0.5673121809959412, + "learning_rate": 1.5793481877199946e-05, + "loss": 0.5332, + "step": 314 + }, + { + "epoch": 1.9811320754716981, + "grad_norm": 0.508794367313385, + "learning_rate": 1.5623519909760954e-05, + "loss": 0.5968, + "step": 315 + }, + { + "epoch": 1.9874213836477987, + "grad_norm": 0.5409150719642639, + "learning_rate": 1.5454060774493068e-05, + "loss": 0.6077, + "step": 316 + }, + { + "epoch": 1.9937106918238994, + "grad_norm": 0.5045109987258911, + "learning_rate": 1.528511355897543e-05, + "loss": 0.5503, + "step": 317 + }, + { + "epoch": 2.0, + "grad_norm": 0.6411352157592773, + "learning_rate": 1.5116687323334467e-05, + "loss": 0.6122, + "step": 318 + }, + { + "epoch": 2.006289308176101, + "grad_norm": 0.5026600360870361, + "learning_rate": 1.4948791099758052e-05, + "loss": 0.5369, + "step": 319 + }, + { + "epoch": 2.0125786163522013, + "grad_norm": 0.511720597743988, + "learning_rate": 1.4781433892011131e-05, + "loss": 0.5291, + "step": 320 + }, + { + "epoch": 2.018867924528302, + "grad_norm": 0.48618605732917786, + "learning_rate": 1.4614624674952842e-05, + "loss": 0.5378, + "step": 321 + }, + { + "epoch": 2.0251572327044025, + "grad_norm": 0.545242190361023, + "learning_rate": 1.4448372394055249e-05, + "loss": 0.5048, + "step": 322 + }, + { + "epoch": 2.0314465408805034, + "grad_norm": 0.5334264636039734, + "learning_rate": 1.4282685964923642e-05, + "loss": 0.5401, + "step": 323 + }, + { + "epoch": 2.0377358490566038, + "grad_norm": 0.5524183511734009, + "learning_rate": 1.4117574272818388e-05, + "loss": 0.5099, + "step": 324 + }, + { + "epoch": 2.0440251572327046, + "grad_norm": 0.48006343841552734, + "learning_rate": 1.3953046172178414e-05, + "loss": 0.4566, + "step": 325 + }, + { + "epoch": 2.050314465408805, + "grad_norm": 0.45758774876594543, + "learning_rate": 1.378911048614647e-05, + "loss": 0.4861, + "step": 326 + }, + { + "epoch": 2.056603773584906, + "grad_norm": 0.583585262298584, + "learning_rate": 1.3625776006095881e-05, + "loss": 0.5896, + "step": 327 + }, + { + "epoch": 2.0628930817610063, + "grad_norm": 0.5123708844184875, + "learning_rate": 1.3463051491159096e-05, + "loss": 0.5174, + "step": 328 + }, + { + "epoch": 2.069182389937107, + "grad_norm": 0.5508242845535278, + "learning_rate": 1.3300945667758014e-05, + "loss": 0.5042, + "step": 329 + }, + { + "epoch": 2.0754716981132075, + "grad_norm": 0.5526241660118103, + "learning_rate": 1.3139467229135999e-05, + "loss": 0.5457, + "step": 330 + }, + { + "epoch": 2.0817610062893084, + "grad_norm": 0.5903204083442688, + "learning_rate": 1.2978624834891628e-05, + "loss": 0.5299, + "step": 331 + }, + { + "epoch": 2.088050314465409, + "grad_norm": 0.5764947533607483, + "learning_rate": 1.281842711051438e-05, + "loss": 0.512, + "step": 332 + }, + { + "epoch": 2.0943396226415096, + "grad_norm": 0.5653167963027954, + "learning_rate": 1.2658882646922034e-05, + "loss": 0.5131, + "step": 333 + }, + { + "epoch": 2.10062893081761, + "grad_norm": 0.5843393206596375, + "learning_rate": 1.2500000000000006e-05, + "loss": 0.5383, + "step": 334 + }, + { + "epoch": 2.106918238993711, + "grad_norm": 0.6287145614624023, + "learning_rate": 1.2341787690142437e-05, + "loss": 0.5715, + "step": 335 + }, + { + "epoch": 2.1132075471698113, + "grad_norm": 0.5734768509864807, + "learning_rate": 1.2184254201795365e-05, + "loss": 0.548, + "step": 336 + }, + { + "epoch": 2.119496855345912, + "grad_norm": 0.5723345279693604, + "learning_rate": 1.2027407983001681e-05, + "loss": 0.4989, + "step": 337 + }, + { + "epoch": 2.1257861635220126, + "grad_norm": 0.6128413677215576, + "learning_rate": 1.1871257444948098e-05, + "loss": 0.5775, + "step": 338 + }, + { + "epoch": 2.1320754716981134, + "grad_norm": 0.7310327887535095, + "learning_rate": 1.1715810961514073e-05, + "loss": 0.5642, + "step": 339 + }, + { + "epoch": 2.138364779874214, + "grad_norm": 0.6413530707359314, + "learning_rate": 1.1561076868822756e-05, + "loss": 0.571, + "step": 340 + }, + { + "epoch": 2.1446540880503147, + "grad_norm": 0.6232360601425171, + "learning_rate": 1.1407063464793966e-05, + "loss": 0.4891, + "step": 341 + }, + { + "epoch": 2.150943396226415, + "grad_norm": 0.5760077238082886, + "learning_rate": 1.1253779008699131e-05, + "loss": 0.5196, + "step": 342 + }, + { + "epoch": 2.157232704402516, + "grad_norm": 0.5411508083343506, + "learning_rate": 1.1101231720718442e-05, + "loss": 0.479, + "step": 343 + }, + { + "epoch": 2.1635220125786163, + "grad_norm": 0.5932305455207825, + "learning_rate": 1.09494297815e-05, + "loss": 0.4888, + "step": 344 + }, + { + "epoch": 2.169811320754717, + "grad_norm": 0.5784667730331421, + "learning_rate": 1.0798381331721109e-05, + "loss": 0.5119, + "step": 345 + }, + { + "epoch": 2.1761006289308176, + "grad_norm": 0.663508415222168, + "learning_rate": 1.0648094471651724e-05, + "loss": 0.497, + "step": 346 + }, + { + "epoch": 2.1823899371069184, + "grad_norm": 0.5773563981056213, + "learning_rate": 1.049857726072005e-05, + "loss": 0.5013, + "step": 347 + }, + { + "epoch": 2.188679245283019, + "grad_norm": 0.697320282459259, + "learning_rate": 1.034983771708035e-05, + "loss": 0.6453, + "step": 348 + }, + { + "epoch": 2.1949685534591197, + "grad_norm": 0.5786930918693542, + "learning_rate": 1.020188381718295e-05, + "loss": 0.5044, + "step": 349 + }, + { + "epoch": 2.20125786163522, + "grad_norm": 0.6295438408851624, + "learning_rate": 1.0054723495346482e-05, + "loss": 0.594, + "step": 350 + }, + { + "epoch": 2.207547169811321, + "grad_norm": 0.6185433864593506, + "learning_rate": 9.908364643332399e-06, + "loss": 0.5059, + "step": 351 + }, + { + "epoch": 2.2138364779874213, + "grad_norm": 0.6029584407806396, + "learning_rate": 9.762815109921761e-06, + "loss": 0.5069, + "step": 352 + }, + { + "epoch": 2.220125786163522, + "grad_norm": 0.6533452272415161, + "learning_rate": 9.618082700494319e-06, + "loss": 0.5232, + "step": 353 + }, + { + "epoch": 2.2264150943396226, + "grad_norm": 0.6175459027290344, + "learning_rate": 9.474175176609956e-06, + "loss": 0.5466, + "step": 354 + }, + { + "epoch": 2.2327044025157234, + "grad_norm": 0.5657399892807007, + "learning_rate": 9.331100255592437e-06, + "loss": 0.4564, + "step": 355 + }, + { + "epoch": 2.238993710691824, + "grad_norm": 0.6779638528823853, + "learning_rate": 9.18886561011557e-06, + "loss": 0.5621, + "step": 356 + }, + { + "epoch": 2.2452830188679247, + "grad_norm": 0.5873716473579407, + "learning_rate": 9.047478867791732e-06, + "loss": 0.4575, + "step": 357 + }, + { + "epoch": 2.251572327044025, + "grad_norm": 0.5723773837089539, + "learning_rate": 8.906947610762825e-06, + "loss": 0.4867, + "step": 358 + }, + { + "epoch": 2.257861635220126, + "grad_norm": 0.6322399377822876, + "learning_rate": 8.767279375293672e-06, + "loss": 0.5453, + "step": 359 + }, + { + "epoch": 2.2641509433962264, + "grad_norm": 0.6071794033050537, + "learning_rate": 8.628481651367876e-06, + "loss": 0.5465, + "step": 360 + }, + { + "epoch": 2.270440251572327, + "grad_norm": 0.7954049110412598, + "learning_rate": 8.490561882286136e-06, + "loss": 0.5327, + "step": 361 + }, + { + "epoch": 2.2767295597484276, + "grad_norm": 0.5613401532173157, + "learning_rate": 8.353527464267104e-06, + "loss": 0.4759, + "step": 362 + }, + { + "epoch": 2.2830188679245285, + "grad_norm": 0.677384614944458, + "learning_rate": 8.217385746050742e-06, + "loss": 0.5186, + "step": 363 + }, + { + "epoch": 2.289308176100629, + "grad_norm": 0.6257275938987732, + "learning_rate": 8.082144028504233e-06, + "loss": 0.5786, + "step": 364 + }, + { + "epoch": 2.2955974842767297, + "grad_norm": 0.6544857025146484, + "learning_rate": 7.947809564230445e-06, + "loss": 0.4792, + "step": 365 + }, + { + "epoch": 2.30188679245283, + "grad_norm": 0.6507861614227295, + "learning_rate": 7.814389557179017e-06, + "loss": 0.5567, + "step": 366 + }, + { + "epoch": 2.308176100628931, + "grad_norm": 0.6414310336112976, + "learning_rate": 7.681891162260015e-06, + "loss": 0.5227, + "step": 367 + }, + { + "epoch": 2.3144654088050314, + "grad_norm": 0.6640331149101257, + "learning_rate": 7.5503214849602516e-06, + "loss": 0.5339, + "step": 368 + }, + { + "epoch": 2.3207547169811322, + "grad_norm": 0.6685804128646851, + "learning_rate": 7.419687580962223e-06, + "loss": 0.4857, + "step": 369 + }, + { + "epoch": 2.3270440251572326, + "grad_norm": 0.6468353271484375, + "learning_rate": 7.289996455765749e-06, + "loss": 0.4588, + "step": 370 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.5642632842063904, + "learning_rate": 7.161255064312283e-06, + "loss": 0.4676, + "step": 371 + }, + { + "epoch": 2.339622641509434, + "grad_norm": 0.583641529083252, + "learning_rate": 7.033470310611945e-06, + "loss": 0.5441, + "step": 372 + }, + { + "epoch": 2.3459119496855347, + "grad_norm": 0.6600673198699951, + "learning_rate": 6.906649047373246e-06, + "loss": 0.5144, + "step": 373 + }, + { + "epoch": 2.352201257861635, + "grad_norm": 0.6383036971092224, + "learning_rate": 6.780798075635675e-06, + "loss": 0.454, + "step": 374 + }, + { + "epoch": 2.358490566037736, + "grad_norm": 0.5476061105728149, + "learning_rate": 6.655924144404907e-06, + "loss": 0.4471, + "step": 375 + }, + { + "epoch": 2.3647798742138364, + "grad_norm": 0.6322336792945862, + "learning_rate": 6.532033950290886e-06, + "loss": 0.525, + "step": 376 + }, + { + "epoch": 2.3710691823899372, + "grad_norm": 0.6242497563362122, + "learning_rate": 6.409134137148737e-06, + "loss": 0.5181, + "step": 377 + }, + { + "epoch": 2.3773584905660377, + "grad_norm": 0.6529743075370789, + "learning_rate": 6.28723129572247e-06, + "loss": 0.5105, + "step": 378 + }, + { + "epoch": 2.3836477987421385, + "grad_norm": 0.6641661524772644, + "learning_rate": 6.166331963291519e-06, + "loss": 0.4859, + "step": 379 + }, + { + "epoch": 2.389937106918239, + "grad_norm": 0.6310985088348389, + "learning_rate": 6.046442623320145e-06, + "loss": 0.5136, + "step": 380 + }, + { + "epoch": 2.3962264150943398, + "grad_norm": 0.7812454104423523, + "learning_rate": 5.927569705109828e-06, + "loss": 0.4837, + "step": 381 + }, + { + "epoch": 2.40251572327044, + "grad_norm": 0.7382704019546509, + "learning_rate": 5.809719583454415e-06, + "loss": 0.4962, + "step": 382 + }, + { + "epoch": 2.408805031446541, + "grad_norm": 0.6249539256095886, + "learning_rate": 5.692898578298253e-06, + "loss": 0.5138, + "step": 383 + }, + { + "epoch": 2.4150943396226414, + "grad_norm": 0.6593284010887146, + "learning_rate": 5.577112954397321e-06, + "loss": 0.5097, + "step": 384 + }, + { + "epoch": 2.4213836477987423, + "grad_norm": 0.6821117997169495, + "learning_rate": 5.462368920983249e-06, + "loss": 0.5655, + "step": 385 + }, + { + "epoch": 2.4276729559748427, + "grad_norm": 0.7341055274009705, + "learning_rate": 5.348672631430318e-06, + "loss": 0.511, + "step": 386 + }, + { + "epoch": 2.4339622641509435, + "grad_norm": 0.676941454410553, + "learning_rate": 5.236030182925475e-06, + "loss": 0.4494, + "step": 387 + }, + { + "epoch": 2.440251572327044, + "grad_norm": 0.6467084288597107, + "learning_rate": 5.124447616141381e-06, + "loss": 0.4407, + "step": 388 + }, + { + "epoch": 2.4465408805031448, + "grad_norm": 0.6168628931045532, + "learning_rate": 5.013930914912476e-06, + "loss": 0.5424, + "step": 389 + }, + { + "epoch": 2.452830188679245, + "grad_norm": 0.6204650402069092, + "learning_rate": 4.9044860059140275e-06, + "loss": 0.5222, + "step": 390 + }, + { + "epoch": 2.459119496855346, + "grad_norm": 0.6808157563209534, + "learning_rate": 4.796118758344354e-06, + "loss": 0.5181, + "step": 391 + }, + { + "epoch": 2.4654088050314464, + "grad_norm": 0.6607468128204346, + "learning_rate": 4.6888349836100825e-06, + "loss": 0.5849, + "step": 392 + }, + { + "epoch": 2.4716981132075473, + "grad_norm": 0.6367841362953186, + "learning_rate": 4.58264043501446e-06, + "loss": 0.4938, + "step": 393 + }, + { + "epoch": 2.4779874213836477, + "grad_norm": 0.7117082476615906, + "learning_rate": 4.477540807448832e-06, + "loss": 0.4862, + "step": 394 + }, + { + "epoch": 2.4842767295597485, + "grad_norm": 0.662056565284729, + "learning_rate": 4.373541737087264e-06, + "loss": 0.5753, + "step": 395 + }, + { + "epoch": 2.490566037735849, + "grad_norm": 0.6686725616455078, + "learning_rate": 4.270648801084296e-06, + "loss": 0.555, + "step": 396 + }, + { + "epoch": 2.49685534591195, + "grad_norm": 0.7704941034317017, + "learning_rate": 4.1688675172758064e-06, + "loss": 0.6513, + "step": 397 + }, + { + "epoch": 2.50314465408805, + "grad_norm": 0.6105798482894897, + "learning_rate": 4.068203343883159e-06, + "loss": 0.4985, + "step": 398 + }, + { + "epoch": 2.509433962264151, + "grad_norm": 0.6414272785186768, + "learning_rate": 3.968661679220468e-06, + "loss": 0.4736, + "step": 399 + }, + { + "epoch": 2.5157232704402515, + "grad_norm": 0.6939327120780945, + "learning_rate": 3.8702478614051355e-06, + "loss": 0.567, + "step": 400 + }, + { + "epoch": 2.5220125786163523, + "grad_norm": 0.6539825797080994, + "learning_rate": 3.772967168071517e-06, + "loss": 0.4567, + "step": 401 + }, + { + "epoch": 2.5283018867924527, + "grad_norm": 0.6413926482200623, + "learning_rate": 3.6768248160879787e-06, + "loss": 0.5228, + "step": 402 + }, + { + "epoch": 2.5345911949685536, + "grad_norm": 0.6808522939682007, + "learning_rate": 3.5818259612770744e-06, + "loss": 0.5499, + "step": 403 + }, + { + "epoch": 2.540880503144654, + "grad_norm": 0.704112708568573, + "learning_rate": 3.487975698139084e-06, + "loss": 0.4901, + "step": 404 + }, + { + "epoch": 2.547169811320755, + "grad_norm": 0.7583079934120178, + "learning_rate": 3.3952790595787987e-06, + "loss": 0.5253, + "step": 405 + }, + { + "epoch": 2.5534591194968552, + "grad_norm": 0.6490894556045532, + "learning_rate": 3.3037410166356143e-06, + "loss": 0.5036, + "step": 406 + }, + { + "epoch": 2.559748427672956, + "grad_norm": 0.6950412392616272, + "learning_rate": 3.2133664782169948e-06, + "loss": 0.5155, + "step": 407 + }, + { + "epoch": 2.5660377358490565, + "grad_norm": 0.6417565941810608, + "learning_rate": 3.1241602908351404e-06, + "loss": 0.4473, + "step": 408 + }, + { + "epoch": 2.5723270440251573, + "grad_norm": 0.7289451360702515, + "learning_rate": 3.036127238347164e-06, + "loss": 0.5926, + "step": 409 + }, + { + "epoch": 2.5786163522012577, + "grad_norm": 0.6481583118438721, + "learning_rate": 2.9492720416985e-06, + "loss": 0.4606, + "step": 410 + }, + { + "epoch": 2.5849056603773586, + "grad_norm": 0.6715993881225586, + "learning_rate": 2.8635993586697553e-06, + "loss": 0.5701, + "step": 411 + }, + { + "epoch": 2.591194968553459, + "grad_norm": 0.6455919146537781, + "learning_rate": 2.779113783626916e-06, + "loss": 0.506, + "step": 412 + }, + { + "epoch": 2.59748427672956, + "grad_norm": 0.7350935935974121, + "learning_rate": 2.6958198472749717e-06, + "loss": 0.5624, + "step": 413 + }, + { + "epoch": 2.6037735849056602, + "grad_norm": 0.7309563755989075, + "learning_rate": 2.6137220164149435e-06, + "loss": 0.5052, + "step": 414 + }, + { + "epoch": 2.610062893081761, + "grad_norm": 0.6338467597961426, + "learning_rate": 2.5328246937043526e-06, + "loss": 0.5104, + "step": 415 + }, + { + "epoch": 2.6163522012578615, + "grad_norm": 0.6638092398643494, + "learning_rate": 2.4531322174210975e-06, + "loss": 0.5077, + "step": 416 + }, + { + "epoch": 2.6226415094339623, + "grad_norm": 0.6149672269821167, + "learning_rate": 2.37464886123083e-06, + "loss": 0.5086, + "step": 417 + }, + { + "epoch": 2.6289308176100628, + "grad_norm": 0.676372766494751, + "learning_rate": 2.2973788339577613e-06, + "loss": 0.5189, + "step": 418 + }, + { + "epoch": 2.6352201257861636, + "grad_norm": 0.6536609530448914, + "learning_rate": 2.2213262793589484e-06, + "loss": 0.4974, + "step": 419 + }, + { + "epoch": 2.641509433962264, + "grad_norm": 0.6942263245582581, + "learning_rate": 2.1464952759020855e-06, + "loss": 0.5648, + "step": 420 + }, + { + "epoch": 2.647798742138365, + "grad_norm": 0.642825722694397, + "learning_rate": 2.0728898365467903e-06, + "loss": 0.5149, + "step": 421 + }, + { + "epoch": 2.6540880503144653, + "grad_norm": 0.6079385876655579, + "learning_rate": 2.0005139085293945e-06, + "loss": 0.472, + "step": 422 + }, + { + "epoch": 2.660377358490566, + "grad_norm": 0.715664267539978, + "learning_rate": 1.9293713731512673e-06, + "loss": 0.5368, + "step": 423 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.655768871307373, + "learning_rate": 1.8594660455706763e-06, + "loss": 0.4948, + "step": 424 + }, + { + "epoch": 2.6729559748427674, + "grad_norm": 0.6798547506332397, + "learning_rate": 1.790801674598186e-06, + "loss": 0.5213, + "step": 425 + }, + { + "epoch": 2.6792452830188678, + "grad_norm": 0.7034783959388733, + "learning_rate": 1.7233819424956248e-06, + "loss": 0.6128, + "step": 426 + }, + { + "epoch": 2.6855345911949686, + "grad_norm": 0.6610020995140076, + "learning_rate": 1.6572104647786247e-06, + "loss": 0.5228, + "step": 427 + }, + { + "epoch": 2.691823899371069, + "grad_norm": 0.664659857749939, + "learning_rate": 1.5922907900227018e-06, + "loss": 0.4266, + "step": 428 + }, + { + "epoch": 2.69811320754717, + "grad_norm": 0.6232119202613831, + "learning_rate": 1.5286263996730026e-06, + "loss": 0.476, + "step": 429 + }, + { + "epoch": 2.7044025157232703, + "grad_norm": 0.653411328792572, + "learning_rate": 1.4662207078575684e-06, + "loss": 0.5145, + "step": 430 + }, + { + "epoch": 2.710691823899371, + "grad_norm": 0.7129037380218506, + "learning_rate": 1.40507706120426e-06, + "loss": 0.5546, + "step": 431 + }, + { + "epoch": 2.7169811320754715, + "grad_norm": 0.6307116150856018, + "learning_rate": 1.3451987386612851e-06, + "loss": 0.4598, + "step": 432 + }, + { + "epoch": 2.7232704402515724, + "grad_norm": 0.6527603268623352, + "learning_rate": 1.286588951321363e-06, + "loss": 0.5322, + "step": 433 + }, + { + "epoch": 2.729559748427673, + "grad_norm": 0.6609143018722534, + "learning_rate": 1.2292508422495158e-06, + "loss": 0.5306, + "step": 434 + }, + { + "epoch": 2.7358490566037736, + "grad_norm": 0.6827059388160706, + "learning_rate": 1.1731874863145143e-06, + "loss": 0.5109, + "step": 435 + }, + { + "epoch": 2.742138364779874, + "grad_norm": 0.6002165079116821, + "learning_rate": 1.1184018900240011e-06, + "loss": 0.4579, + "step": 436 + }, + { + "epoch": 2.748427672955975, + "grad_norm": 0.6269481182098389, + "learning_rate": 1.06489699136324e-06, + "loss": 0.4888, + "step": 437 + }, + { + "epoch": 2.7547169811320753, + "grad_norm": 0.6706013679504395, + "learning_rate": 1.0126756596375686e-06, + "loss": 0.5225, + "step": 438 + }, + { + "epoch": 2.761006289308176, + "grad_norm": 0.6613484025001526, + "learning_rate": 9.617406953185138e-07, + "loss": 0.5241, + "step": 439 + }, + { + "epoch": 2.767295597484277, + "grad_norm": 0.7121806740760803, + "learning_rate": 9.120948298936421e-07, + "loss": 0.4887, + "step": 440 + }, + { + "epoch": 2.7735849056603774, + "grad_norm": 0.6842261552810669, + "learning_rate": 8.637407257200497e-07, + "loss": 0.4912, + "step": 441 + }, + { + "epoch": 2.779874213836478, + "grad_norm": 0.70417320728302, + "learning_rate": 8.166809758815896e-07, + "loss": 0.5405, + "step": 442 + }, + { + "epoch": 2.7861635220125787, + "grad_norm": 0.6980416178703308, + "learning_rate": 7.709181040498254e-07, + "loss": 0.5058, + "step": 443 + }, + { + "epoch": 2.7924528301886795, + "grad_norm": 0.6587446331977844, + "learning_rate": 7.264545643486997e-07, + "loss": 0.5572, + "step": 444 + }, + { + "epoch": 2.79874213836478, + "grad_norm": 0.6442897319793701, + "learning_rate": 6.832927412229018e-07, + "loss": 0.5118, + "step": 445 + }, + { + "epoch": 2.8050314465408803, + "grad_norm": 0.6052460670471191, + "learning_rate": 6.41434949310013e-07, + "loss": 0.536, + "step": 446 + }, + { + "epoch": 2.811320754716981, + "grad_norm": 0.7546602487564087, + "learning_rate": 6.008834333163876e-07, + "loss": 0.5397, + "step": 447 + }, + { + "epoch": 2.817610062893082, + "grad_norm": 0.6202664375305176, + "learning_rate": 5.616403678967624e-07, + "loss": 0.4516, + "step": 448 + }, + { + "epoch": 2.8238993710691824, + "grad_norm": 0.6362593173980713, + "learning_rate": 5.237078575376336e-07, + "loss": 0.5106, + "step": 449 + }, + { + "epoch": 2.830188679245283, + "grad_norm": 0.6845952272415161, + "learning_rate": 4.870879364444109e-07, + "loss": 0.5153, + "step": 450 + }, + { + "epoch": 2.8364779874213837, + "grad_norm": 0.659001886844635, + "learning_rate": 4.517825684323324e-07, + "loss": 0.5075, + "step": 451 + }, + { + "epoch": 2.8427672955974845, + "grad_norm": 0.6748611927032471, + "learning_rate": 4.1779364682113796e-07, + "loss": 0.5354, + "step": 452 + }, + { + "epoch": 2.849056603773585, + "grad_norm": 0.6511921286582947, + "learning_rate": 3.851229943335394e-07, + "loss": 0.5468, + "step": 453 + }, + { + "epoch": 2.8553459119496853, + "grad_norm": 0.6114699244499207, + "learning_rate": 3.537723629974815e-07, + "loss": 0.4799, + "step": 454 + }, + { + "epoch": 2.861635220125786, + "grad_norm": 0.717573344707489, + "learning_rate": 3.237434340521789e-07, + "loss": 0.5604, + "step": 455 + }, + { + "epoch": 2.867924528301887, + "grad_norm": 0.6609371900558472, + "learning_rate": 2.9503781785795713e-07, + "loss": 0.4958, + "step": 456 + }, + { + "epoch": 2.8742138364779874, + "grad_norm": 0.7015553712844849, + "learning_rate": 2.6765705380989437e-07, + "loss": 0.551, + "step": 457 + }, + { + "epoch": 2.880503144654088, + "grad_norm": 0.6695305109024048, + "learning_rate": 2.416026102552732e-07, + "loss": 0.5316, + "step": 458 + }, + { + "epoch": 2.8867924528301887, + "grad_norm": 0.6004621386528015, + "learning_rate": 2.168758844148272e-07, + "loss": 0.5416, + "step": 459 + }, + { + "epoch": 2.8930817610062896, + "grad_norm": 0.6895103454589844, + "learning_rate": 1.93478202307823e-07, + "loss": 0.5319, + "step": 460 + }, + { + "epoch": 2.89937106918239, + "grad_norm": 0.6955282092094421, + "learning_rate": 1.7141081868094212e-07, + "loss": 0.5208, + "step": 461 + }, + { + "epoch": 2.9056603773584904, + "grad_norm": 0.6640160083770752, + "learning_rate": 1.5067491694100154e-07, + "loss": 0.5133, + "step": 462 + }, + { + "epoch": 2.911949685534591, + "grad_norm": 0.6678076982498169, + "learning_rate": 1.3127160909147672e-07, + "loss": 0.5107, + "step": 463 + }, + { + "epoch": 2.918238993710692, + "grad_norm": 0.7161384224891663, + "learning_rate": 1.1320193567288529e-07, + "loss": 0.5842, + "step": 464 + }, + { + "epoch": 2.9245283018867925, + "grad_norm": 0.712955117225647, + "learning_rate": 9.646686570697061e-08, + "loss": 0.5275, + "step": 465 + }, + { + "epoch": 2.930817610062893, + "grad_norm": 0.711218535900116, + "learning_rate": 8.106729664475176e-08, + "loss": 0.4815, + "step": 466 + }, + { + "epoch": 2.9371069182389937, + "grad_norm": 0.6556484699249268, + "learning_rate": 6.700405431837587e-08, + "loss": 0.4802, + "step": 467 + }, + { + "epoch": 2.9433962264150946, + "grad_norm": 0.6334600448608398, + "learning_rate": 5.4277892896853476e-08, + "loss": 0.5044, + "step": 468 + }, + { + "epoch": 2.949685534591195, + "grad_norm": 0.6841341257095337, + "learning_rate": 4.2889494845599344e-08, + "loss": 0.5601, + "step": 469 + }, + { + "epoch": 2.9559748427672954, + "grad_norm": 0.6439110040664673, + "learning_rate": 3.283947088983663e-08, + "loss": 0.4279, + "step": 470 + }, + { + "epoch": 2.9622641509433962, + "grad_norm": 0.593614935874939, + "learning_rate": 2.4128359981850924e-08, + "loss": 0.483, + "step": 471 + }, + { + "epoch": 2.968553459119497, + "grad_norm": 0.6519297957420349, + "learning_rate": 1.6756629272085545e-08, + "loss": 0.5921, + "step": 472 + }, + { + "epoch": 2.9748427672955975, + "grad_norm": 0.6468663215637207, + "learning_rate": 1.0724674084083841e-08, + "loss": 0.4751, + "step": 473 + }, + { + "epoch": 2.981132075471698, + "grad_norm": 0.6676617860794067, + "learning_rate": 6.032817893297793e-09, + "loss": 0.4994, + "step": 474 + }, + { + "epoch": 2.9874213836477987, + "grad_norm": 0.6803402900695801, + "learning_rate": 2.681312309735229e-09, + "loss": 0.5308, + "step": 475 + }, + { + "epoch": 2.9937106918238996, + "grad_norm": 0.6511867642402649, + "learning_rate": 6.703370644706164e-10, + "loss": 0.5177, + "step": 476 + }, + { + "epoch": 3.0, + "grad_norm": 0.7002833485603333, + "learning_rate": 0.0, + "loss": 0.4149, + "step": 477 + } + ], + "logging_steps": 1, + "max_steps": 477, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 4.746880321608352e+18, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-477/training_args.bin b/checkpoint-477/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f2a1106da97275ded3721a2b9ad28a19b5c9872 --- /dev/null +++ b/checkpoint-477/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d245efe4cb1811ec2cffc23b4d3aa9a49d1d65e92b8d678bec9a399e5c1889e +size 5496 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1913e5051ba2d9c350141f19b01d55276096bc3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000000000000000000000000000000000000..c87deff6d17db6fb6cdaafdce5ff4448767c1c16 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 4.746880321608352e+18, + "train_loss": 0.7064950698576633, + "train_runtime": 33423.533, + "train_samples_per_second": 1.825, + "train_steps_per_second": 0.014 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e3015f00e1128aa783329959fd3de4f259c07e88 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,478 @@ +{"current_steps": 1, "total_steps": 477, "loss": 3.6915, "lr": 1.0416666666666667e-06, "epoch": 0.006289308176100629, "percentage": 0.21, "elapsed_time": "0:01:14", "remaining_time": "9:47:54"} +{"current_steps": 2, "total_steps": 477, "loss": 3.6352, "lr": 2.0833333333333334e-06, "epoch": 0.012578616352201259, "percentage": 0.42, "elapsed_time": "0:02:27", "remaining_time": "9:43:54"} +{"current_steps": 3, "total_steps": 477, "loss": 3.5816, "lr": 3.125e-06, "epoch": 0.018867924528301886, "percentage": 0.63, "elapsed_time": "0:03:45", "remaining_time": "9:54:49"} +{"current_steps": 4, "total_steps": 477, "loss": 3.6233, "lr": 4.166666666666667e-06, "epoch": 0.025157232704402517, "percentage": 0.84, "elapsed_time": "0:04:53", "remaining_time": "9:37:53"} +{"current_steps": 5, "total_steps": 477, "loss": 3.6107, "lr": 5.208333333333334e-06, "epoch": 0.031446540880503145, "percentage": 1.05, "elapsed_time": "0:06:08", "remaining_time": "9:39:58"} +{"current_steps": 6, "total_steps": 477, "loss": 3.6277, "lr": 6.25e-06, "epoch": 0.03773584905660377, "percentage": 1.26, "elapsed_time": "0:07:19", "remaining_time": "9:34:28"} +{"current_steps": 7, "total_steps": 477, "loss": 3.4974, "lr": 7.2916666666666674e-06, "epoch": 0.0440251572327044, "percentage": 1.47, "elapsed_time": "0:08:33", "remaining_time": "9:34:12"} +{"current_steps": 8, "total_steps": 477, "loss": 3.5021, "lr": 8.333333333333334e-06, "epoch": 0.050314465408805034, "percentage": 1.68, "elapsed_time": "0:09:40", "remaining_time": "9:27:28"} +{"current_steps": 9, "total_steps": 477, "loss": 3.5888, "lr": 9.375000000000001e-06, "epoch": 0.05660377358490566, "percentage": 1.89, "elapsed_time": "0:10:44", "remaining_time": "9:18:57"} +{"current_steps": 10, "total_steps": 477, "loss": 3.3652, "lr": 1.0416666666666668e-05, "epoch": 0.06289308176100629, "percentage": 2.1, "elapsed_time": "0:12:00", "remaining_time": "9:20:55"} +{"current_steps": 11, "total_steps": 477, "loss": 3.1476, "lr": 1.1458333333333333e-05, "epoch": 0.06918238993710692, "percentage": 2.31, "elapsed_time": "0:13:07", "remaining_time": "9:15:59"} +{"current_steps": 12, "total_steps": 477, "loss": 3.6846, "lr": 1.25e-05, "epoch": 0.07547169811320754, "percentage": 2.52, "elapsed_time": "0:14:35", "remaining_time": "9:25:11"} +{"current_steps": 13, "total_steps": 477, "loss": 3.2959, "lr": 1.3541666666666666e-05, "epoch": 0.08176100628930817, "percentage": 2.73, "elapsed_time": "0:15:48", "remaining_time": "9:24:21"} +{"current_steps": 14, "total_steps": 477, "loss": 3.3629, "lr": 1.4583333333333335e-05, "epoch": 0.0880503144654088, "percentage": 2.94, "elapsed_time": "0:16:58", "remaining_time": "9:21:16"} +{"current_steps": 15, "total_steps": 477, "loss": 2.9799, "lr": 1.5625e-05, "epoch": 0.09433962264150944, "percentage": 3.14, "elapsed_time": "0:18:11", "remaining_time": "9:20:24"} +{"current_steps": 16, "total_steps": 477, "loss": 2.8375, "lr": 1.6666666666666667e-05, "epoch": 0.10062893081761007, "percentage": 3.35, "elapsed_time": "0:19:17", "remaining_time": "9:15:56"} +{"current_steps": 17, "total_steps": 477, "loss": 2.5298, "lr": 1.7708333333333335e-05, "epoch": 0.1069182389937107, "percentage": 3.56, "elapsed_time": "0:20:37", "remaining_time": "9:18:13"} +{"current_steps": 18, "total_steps": 477, "loss": 2.4099, "lr": 1.8750000000000002e-05, "epoch": 0.11320754716981132, "percentage": 3.77, "elapsed_time": "0:21:55", "remaining_time": "9:19:00"} +{"current_steps": 19, "total_steps": 477, "loss": 2.1316, "lr": 1.9791666666666665e-05, "epoch": 0.11949685534591195, "percentage": 3.98, "elapsed_time": "0:23:07", "remaining_time": "9:17:16"} +{"current_steps": 20, "total_steps": 477, "loss": 1.8814, "lr": 2.0833333333333336e-05, "epoch": 0.12578616352201258, "percentage": 4.19, "elapsed_time": "0:24:11", "remaining_time": "9:12:51"} +{"current_steps": 21, "total_steps": 477, "loss": 1.7786, "lr": 2.1875e-05, "epoch": 0.1320754716981132, "percentage": 4.4, "elapsed_time": "0:25:23", "remaining_time": "9:11:14"} +{"current_steps": 22, "total_steps": 477, "loss": 1.5133, "lr": 2.2916666666666667e-05, "epoch": 0.13836477987421383, "percentage": 4.61, "elapsed_time": "0:26:41", "remaining_time": "9:12:11"} +{"current_steps": 23, "total_steps": 477, "loss": 1.4229, "lr": 2.3958333333333334e-05, "epoch": 0.14465408805031446, "percentage": 4.82, "elapsed_time": "0:27:50", "remaining_time": "9:09:38"} +{"current_steps": 24, "total_steps": 477, "loss": 1.3577, "lr": 2.5e-05, "epoch": 0.1509433962264151, "percentage": 5.03, "elapsed_time": "0:29:03", "remaining_time": "9:08:27"} +{"current_steps": 25, "total_steps": 477, "loss": 1.1501, "lr": 2.604166666666667e-05, "epoch": 0.15723270440251572, "percentage": 5.24, "elapsed_time": "0:30:10", "remaining_time": "9:05:39"} +{"current_steps": 26, "total_steps": 477, "loss": 1.292, "lr": 2.7083333333333332e-05, "epoch": 0.16352201257861634, "percentage": 5.45, "elapsed_time": "0:31:21", "remaining_time": "9:03:48"} +{"current_steps": 27, "total_steps": 477, "loss": 1.1469, "lr": 2.8125000000000003e-05, "epoch": 0.16981132075471697, "percentage": 5.66, "elapsed_time": "0:32:32", "remaining_time": "9:02:16"} +{"current_steps": 28, "total_steps": 477, "loss": 1.0433, "lr": 2.916666666666667e-05, "epoch": 0.1761006289308176, "percentage": 5.87, "elapsed_time": "0:33:40", "remaining_time": "9:00:06"} +{"current_steps": 29, "total_steps": 477, "loss": 0.9627, "lr": 3.0208333333333334e-05, "epoch": 0.18238993710691823, "percentage": 6.08, "elapsed_time": "0:34:46", "remaining_time": "8:57:13"} +{"current_steps": 30, "total_steps": 477, "loss": 0.9103, "lr": 3.125e-05, "epoch": 0.18867924528301888, "percentage": 6.29, "elapsed_time": "0:35:55", "remaining_time": "8:55:15"} +{"current_steps": 31, "total_steps": 477, "loss": 0.979, "lr": 3.229166666666667e-05, "epoch": 0.1949685534591195, "percentage": 6.5, "elapsed_time": "0:37:10", "remaining_time": "8:54:43"} +{"current_steps": 32, "total_steps": 477, "loss": 0.9553, "lr": 3.3333333333333335e-05, "epoch": 0.20125786163522014, "percentage": 6.71, "elapsed_time": "0:38:22", "remaining_time": "8:53:35"} +{"current_steps": 33, "total_steps": 477, "loss": 0.8379, "lr": 3.4375e-05, "epoch": 0.20754716981132076, "percentage": 6.92, "elapsed_time": "0:39:26", "remaining_time": "8:50:45"} +{"current_steps": 34, "total_steps": 477, "loss": 0.9038, "lr": 3.541666666666667e-05, "epoch": 0.2138364779874214, "percentage": 7.13, "elapsed_time": "0:40:33", "remaining_time": "8:48:27"} +{"current_steps": 35, "total_steps": 477, "loss": 0.8354, "lr": 3.6458333333333336e-05, "epoch": 0.22012578616352202, "percentage": 7.34, "elapsed_time": "0:41:45", "remaining_time": "8:47:21"} +{"current_steps": 36, "total_steps": 477, "loss": 0.8517, "lr": 3.7500000000000003e-05, "epoch": 0.22641509433962265, "percentage": 7.55, "elapsed_time": "0:42:57", "remaining_time": "8:46:19"} +{"current_steps": 37, "total_steps": 477, "loss": 0.8702, "lr": 3.854166666666667e-05, "epoch": 0.23270440251572327, "percentage": 7.76, "elapsed_time": "0:44:04", "remaining_time": "8:44:11"} +{"current_steps": 38, "total_steps": 477, "loss": 0.8812, "lr": 3.958333333333333e-05, "epoch": 0.2389937106918239, "percentage": 7.97, "elapsed_time": "0:45:21", "remaining_time": "8:43:56"} +{"current_steps": 39, "total_steps": 477, "loss": 0.8336, "lr": 4.0625000000000005e-05, "epoch": 0.24528301886792453, "percentage": 8.18, "elapsed_time": "0:46:27", "remaining_time": "8:41:50"} +{"current_steps": 40, "total_steps": 477, "loss": 0.7162, "lr": 4.166666666666667e-05, "epoch": 0.25157232704402516, "percentage": 8.39, "elapsed_time": "0:47:48", "remaining_time": "8:42:21"} +{"current_steps": 41, "total_steps": 477, "loss": 0.7433, "lr": 4.270833333333333e-05, "epoch": 0.2578616352201258, "percentage": 8.6, "elapsed_time": "0:48:56", "remaining_time": "8:40:23"} +{"current_steps": 42, "total_steps": 477, "loss": 0.738, "lr": 4.375e-05, "epoch": 0.2641509433962264, "percentage": 8.81, "elapsed_time": "0:50:03", "remaining_time": "8:38:22"} +{"current_steps": 43, "total_steps": 477, "loss": 0.7884, "lr": 4.4791666666666673e-05, "epoch": 0.27044025157232704, "percentage": 9.01, "elapsed_time": "0:51:14", "remaining_time": "8:37:07"} +{"current_steps": 44, "total_steps": 477, "loss": 0.814, "lr": 4.5833333333333334e-05, "epoch": 0.27672955974842767, "percentage": 9.22, "elapsed_time": "0:52:22", "remaining_time": "8:35:22"} +{"current_steps": 45, "total_steps": 477, "loss": 0.8249, "lr": 4.6875e-05, "epoch": 0.2830188679245283, "percentage": 9.43, "elapsed_time": "0:53:30", "remaining_time": "8:33:38"} +{"current_steps": 46, "total_steps": 477, "loss": 0.7205, "lr": 4.791666666666667e-05, "epoch": 0.2893081761006289, "percentage": 9.64, "elapsed_time": "0:54:46", "remaining_time": "8:33:15"} +{"current_steps": 47, "total_steps": 477, "loss": 0.7646, "lr": 4.8958333333333335e-05, "epoch": 0.29559748427672955, "percentage": 9.85, "elapsed_time": "0:55:53", "remaining_time": "8:31:22"} +{"current_steps": 48, "total_steps": 477, "loss": 0.6697, "lr": 5e-05, "epoch": 0.3018867924528302, "percentage": 10.06, "elapsed_time": "0:57:02", "remaining_time": "8:29:45"} +{"current_steps": 49, "total_steps": 477, "loss": 0.8134, "lr": 4.9999329662935534e-05, "epoch": 0.3081761006289308, "percentage": 10.27, "elapsed_time": "0:58:15", "remaining_time": "8:28:52"} +{"current_steps": 50, "total_steps": 477, "loss": 0.7665, "lr": 4.999731868769027e-05, "epoch": 0.31446540880503143, "percentage": 10.48, "elapsed_time": "0:59:22", "remaining_time": "8:27:01"} +{"current_steps": 51, "total_steps": 477, "loss": 0.7717, "lr": 4.99939671821067e-05, "epoch": 0.32075471698113206, "percentage": 10.69, "elapsed_time": "1:00:24", "remaining_time": "8:24:35"} +{"current_steps": 52, "total_steps": 477, "loss": 0.677, "lr": 4.998927532591592e-05, "epoch": 0.3270440251572327, "percentage": 10.9, "elapsed_time": "1:01:36", "remaining_time": "8:23:33"} +{"current_steps": 53, "total_steps": 477, "loss": 0.6829, "lr": 4.9983243370727914e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "1:02:46", "remaining_time": "8:22:09"} +{"current_steps": 54, "total_steps": 477, "loss": 0.7817, "lr": 4.9975871640018154e-05, "epoch": 0.33962264150943394, "percentage": 11.32, "elapsed_time": "1:04:04", "remaining_time": "8:21:58"} +{"current_steps": 55, "total_steps": 477, "loss": 0.6835, "lr": 4.996716052911017e-05, "epoch": 0.34591194968553457, "percentage": 11.53, "elapsed_time": "1:05:09", "remaining_time": "8:19:57"} +{"current_steps": 56, "total_steps": 477, "loss": 0.728, "lr": 4.99571105051544e-05, "epoch": 0.3522012578616352, "percentage": 11.74, "elapsed_time": "1:06:18", "remaining_time": "8:18:28"} +{"current_steps": 57, "total_steps": 477, "loss": 0.6448, "lr": 4.994572210710315e-05, "epoch": 0.3584905660377358, "percentage": 11.95, "elapsed_time": "1:07:23", "remaining_time": "8:16:32"} +{"current_steps": 58, "total_steps": 477, "loss": 0.675, "lr": 4.993299594568163e-05, "epoch": 0.36477987421383645, "percentage": 12.16, "elapsed_time": "1:08:31", "remaining_time": "8:15:01"} +{"current_steps": 59, "total_steps": 477, "loss": 0.6821, "lr": 4.9918932703355256e-05, "epoch": 0.3710691823899371, "percentage": 12.37, "elapsed_time": "1:09:43", "remaining_time": "8:13:59"} +{"current_steps": 60, "total_steps": 477, "loss": 0.7063, "lr": 4.990353313429303e-05, "epoch": 0.37735849056603776, "percentage": 12.58, "elapsed_time": "1:10:53", "remaining_time": "8:12:39"} +{"current_steps": 61, "total_steps": 477, "loss": 0.6941, "lr": 4.988679806432712e-05, "epoch": 0.3836477987421384, "percentage": 12.79, "elapsed_time": "1:11:57", "remaining_time": "8:10:46"} +{"current_steps": 62, "total_steps": 477, "loss": 0.6544, "lr": 4.9868728390908526e-05, "epoch": 0.389937106918239, "percentage": 13.0, "elapsed_time": "1:13:07", "remaining_time": "8:09:27"} +{"current_steps": 63, "total_steps": 477, "loss": 0.6966, "lr": 4.9849325083059e-05, "epoch": 0.39622641509433965, "percentage": 13.21, "elapsed_time": "1:14:20", "remaining_time": "8:08:35"} +{"current_steps": 64, "total_steps": 477, "loss": 0.6866, "lr": 4.982858918131906e-05, "epoch": 0.4025157232704403, "percentage": 13.42, "elapsed_time": "1:15:32", "remaining_time": "8:07:27"} +{"current_steps": 65, "total_steps": 477, "loss": 0.7029, "lr": 4.980652179769218e-05, "epoch": 0.4088050314465409, "percentage": 13.63, "elapsed_time": "1:16:41", "remaining_time": "8:06:05"} +{"current_steps": 66, "total_steps": 477, "loss": 0.6553, "lr": 4.978312411558518e-05, "epoch": 0.41509433962264153, "percentage": 13.84, "elapsed_time": "1:18:00", "remaining_time": "8:05:43"} +{"current_steps": 67, "total_steps": 477, "loss": 0.696, "lr": 4.9758397389744734e-05, "epoch": 0.42138364779874216, "percentage": 14.05, "elapsed_time": "1:19:23", "remaining_time": "8:05:49"} +{"current_steps": 68, "total_steps": 477, "loss": 0.6676, "lr": 4.973234294619011e-05, "epoch": 0.4276729559748428, "percentage": 14.26, "elapsed_time": "1:20:35", "remaining_time": "8:04:45"} +{"current_steps": 69, "total_steps": 477, "loss": 0.6337, "lr": 4.9704962182142044e-05, "epoch": 0.4339622641509434, "percentage": 14.47, "elapsed_time": "1:21:42", "remaining_time": "8:03:07"} +{"current_steps": 70, "total_steps": 477, "loss": 0.7645, "lr": 4.967625656594782e-05, "epoch": 0.44025157232704404, "percentage": 14.68, "elapsed_time": "1:22:57", "remaining_time": "8:02:21"} +{"current_steps": 71, "total_steps": 477, "loss": 0.647, "lr": 4.9646227637002515e-05, "epoch": 0.44654088050314467, "percentage": 14.88, "elapsed_time": "1:24:07", "remaining_time": "8:01:05"} +{"current_steps": 72, "total_steps": 477, "loss": 0.6342, "lr": 4.961487700566646e-05, "epoch": 0.4528301886792453, "percentage": 15.09, "elapsed_time": "1:25:15", "remaining_time": "7:59:35"} +{"current_steps": 73, "total_steps": 477, "loss": 0.641, "lr": 4.958220635317886e-05, "epoch": 0.4591194968553459, "percentage": 15.3, "elapsed_time": "1:26:23", "remaining_time": "7:58:04"} +{"current_steps": 74, "total_steps": 477, "loss": 0.8103, "lr": 4.9548217431567665e-05, "epoch": 0.46540880503144655, "percentage": 15.51, "elapsed_time": "1:27:28", "remaining_time": "7:56:22"} +{"current_steps": 75, "total_steps": 477, "loss": 0.6205, "lr": 4.95129120635556e-05, "epoch": 0.4716981132075472, "percentage": 15.72, "elapsed_time": "1:28:39", "remaining_time": "7:55:11"} +{"current_steps": 76, "total_steps": 477, "loss": 0.6678, "lr": 4.9476292142462374e-05, "epoch": 0.4779874213836478, "percentage": 15.93, "elapsed_time": "1:29:43", "remaining_time": "7:53:27"} +{"current_steps": 77, "total_steps": 477, "loss": 0.6668, "lr": 4.943835963210324e-05, "epoch": 0.48427672955974843, "percentage": 16.14, "elapsed_time": "1:30:59", "remaining_time": "7:52:40"} +{"current_steps": 78, "total_steps": 477, "loss": 0.61, "lr": 4.939911656668361e-05, "epoch": 0.49056603773584906, "percentage": 16.35, "elapsed_time": "1:32:19", "remaining_time": "7:52:17"} +{"current_steps": 79, "total_steps": 477, "loss": 0.6939, "lr": 4.9358565050689985e-05, "epoch": 0.4968553459119497, "percentage": 16.56, "elapsed_time": "1:33:26", "remaining_time": "7:50:43"} +{"current_steps": 80, "total_steps": 477, "loss": 0.6698, "lr": 4.93167072587771e-05, "epoch": 0.5031446540880503, "percentage": 16.77, "elapsed_time": "1:34:41", "remaining_time": "7:49:52"} +{"current_steps": 81, "total_steps": 477, "loss": 0.5798, "lr": 4.92735454356513e-05, "epoch": 0.5094339622641509, "percentage": 16.98, "elapsed_time": "1:35:55", "remaining_time": "7:48:59"} +{"current_steps": 82, "total_steps": 477, "loss": 0.7936, "lr": 4.922908189595018e-05, "epoch": 0.5157232704402516, "percentage": 17.19, "elapsed_time": "1:37:11", "remaining_time": "7:48:13"} +{"current_steps": 83, "total_steps": 477, "loss": 0.667, "lr": 4.9183319024118415e-05, "epoch": 0.5220125786163522, "percentage": 17.4, "elapsed_time": "1:38:25", "remaining_time": "7:47:11"} +{"current_steps": 84, "total_steps": 477, "loss": 0.6518, "lr": 4.9136259274279955e-05, "epoch": 0.5283018867924528, "percentage": 17.61, "elapsed_time": "1:39:30", "remaining_time": "7:45:33"} +{"current_steps": 85, "total_steps": 477, "loss": 0.6105, "lr": 4.908790517010636e-05, "epoch": 0.5345911949685535, "percentage": 17.82, "elapsed_time": "1:40:37", "remaining_time": "7:44:01"} +{"current_steps": 86, "total_steps": 477, "loss": 0.6954, "lr": 4.903825930468149e-05, "epoch": 0.5408805031446541, "percentage": 18.03, "elapsed_time": "1:41:43", "remaining_time": "7:42:29"} +{"current_steps": 87, "total_steps": 477, "loss": 0.6614, "lr": 4.898732434036244e-05, "epoch": 0.5471698113207547, "percentage": 18.24, "elapsed_time": "1:42:53", "remaining_time": "7:41:13"} +{"current_steps": 88, "total_steps": 477, "loss": 0.6186, "lr": 4.893510300863676e-05, "epoch": 0.5534591194968553, "percentage": 18.45, "elapsed_time": "1:44:07", "remaining_time": "7:40:15"} +{"current_steps": 89, "total_steps": 477, "loss": 0.6153, "lr": 4.8881598109976004e-05, "epoch": 0.559748427672956, "percentage": 18.66, "elapsed_time": "1:45:13", "remaining_time": "7:38:42"} +{"current_steps": 90, "total_steps": 477, "loss": 0.6472, "lr": 4.8826812513685487e-05, "epoch": 0.5660377358490566, "percentage": 18.87, "elapsed_time": "1:46:19", "remaining_time": "7:37:12"} +{"current_steps": 91, "total_steps": 477, "loss": 0.6404, "lr": 4.877074915775049e-05, "epoch": 0.5723270440251572, "percentage": 19.08, "elapsed_time": "1:47:25", "remaining_time": "7:35:40"} +{"current_steps": 92, "total_steps": 477, "loss": 0.6353, "lr": 4.8713411048678635e-05, "epoch": 0.5786163522012578, "percentage": 19.29, "elapsed_time": "1:48:37", "remaining_time": "7:34:34"} +{"current_steps": 93, "total_steps": 477, "loss": 0.6289, "lr": 4.865480126133872e-05, "epoch": 0.5849056603773585, "percentage": 19.5, "elapsed_time": "1:49:45", "remaining_time": "7:33:10"} +{"current_steps": 94, "total_steps": 477, "loss": 0.6242, "lr": 4.859492293879574e-05, "epoch": 0.5911949685534591, "percentage": 19.71, "elapsed_time": "1:50:53", "remaining_time": "7:31:48"} +{"current_steps": 95, "total_steps": 477, "loss": 0.6055, "lr": 4.853377929214243e-05, "epoch": 0.5974842767295597, "percentage": 19.92, "elapsed_time": "1:52:00", "remaining_time": "7:30:25"} +{"current_steps": 96, "total_steps": 477, "loss": 0.6354, "lr": 4.8471373600326996e-05, "epoch": 0.6037735849056604, "percentage": 20.13, "elapsed_time": "1:53:24", "remaining_time": "7:30:06"} +{"current_steps": 97, "total_steps": 477, "loss": 0.7039, "lr": 4.8407709209977305e-05, "epoch": 0.610062893081761, "percentage": 20.34, "elapsed_time": "1:54:34", "remaining_time": "7:28:50"} +{"current_steps": 98, "total_steps": 477, "loss": 0.6679, "lr": 4.834278953522138e-05, "epoch": 0.6163522012578616, "percentage": 20.55, "elapsed_time": "1:55:45", "remaining_time": "7:27:39"} +{"current_steps": 99, "total_steps": 477, "loss": 0.7479, "lr": 4.8276618057504376e-05, "epoch": 0.6226415094339622, "percentage": 20.75, "elapsed_time": "1:56:51", "remaining_time": "7:26:10"} +{"current_steps": 100, "total_steps": 477, "loss": 0.5923, "lr": 4.8209198325401815e-05, "epoch": 0.6289308176100629, "percentage": 20.96, "elapsed_time": "1:58:03", "remaining_time": "7:25:04"} +{"current_steps": 101, "total_steps": 477, "loss": 0.6313, "lr": 4.8140533954429327e-05, "epoch": 0.6352201257861635, "percentage": 21.17, "elapsed_time": "1:59:15", "remaining_time": "7:23:57"} +{"current_steps": 102, "total_steps": 477, "loss": 0.6736, "lr": 4.8070628626848735e-05, "epoch": 0.6415094339622641, "percentage": 21.38, "elapsed_time": "2:00:22", "remaining_time": "7:22:33"} +{"current_steps": 103, "total_steps": 477, "loss": 0.6173, "lr": 4.799948609147061e-05, "epoch": 0.6477987421383647, "percentage": 21.59, "elapsed_time": "2:01:34", "remaining_time": "7:21:25"} +{"current_steps": 104, "total_steps": 477, "loss": 0.6756, "lr": 4.792711016345321e-05, "epoch": 0.6540880503144654, "percentage": 21.8, "elapsed_time": "2:02:36", "remaining_time": "7:19:43"} +{"current_steps": 105, "total_steps": 477, "loss": 0.6413, "lr": 4.785350472409792e-05, "epoch": 0.660377358490566, "percentage": 22.01, "elapsed_time": "2:03:48", "remaining_time": "7:18:37"} +{"current_steps": 106, "total_steps": 477, "loss": 0.6201, "lr": 4.777867372064105e-05, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "2:04:48", "remaining_time": "7:16:51"} +{"current_steps": 107, "total_steps": 477, "loss": 0.5777, "lr": 4.770262116604224e-05, "epoch": 0.6729559748427673, "percentage": 22.43, "elapsed_time": "2:05:49", "remaining_time": "7:15:06"} +{"current_steps": 108, "total_steps": 477, "loss": 0.6326, "lr": 4.762535113876917e-05, "epoch": 0.6792452830188679, "percentage": 22.64, "elapsed_time": "2:07:02", "remaining_time": "7:14:02"} +{"current_steps": 109, "total_steps": 477, "loss": 0.5849, "lr": 4.754686778257891e-05, "epoch": 0.6855345911949685, "percentage": 22.85, "elapsed_time": "2:08:15", "remaining_time": "7:12:59"} +{"current_steps": 110, "total_steps": 477, "loss": 0.6779, "lr": 4.7467175306295655e-05, "epoch": 0.6918238993710691, "percentage": 23.06, "elapsed_time": "2:09:25", "remaining_time": "7:11:49"} +{"current_steps": 111, "total_steps": 477, "loss": 0.565, "lr": 4.738627798358506e-05, "epoch": 0.6981132075471698, "percentage": 23.27, "elapsed_time": "2:10:40", "remaining_time": "7:10:51"} +{"current_steps": 112, "total_steps": 477, "loss": 0.6836, "lr": 4.730418015272503e-05, "epoch": 0.7044025157232704, "percentage": 23.48, "elapsed_time": "2:11:52", "remaining_time": "7:09:45"} +{"current_steps": 113, "total_steps": 477, "loss": 0.5849, "lr": 4.722088621637309e-05, "epoch": 0.710691823899371, "percentage": 23.69, "elapsed_time": "2:13:01", "remaining_time": "7:08:31"} +{"current_steps": 114, "total_steps": 477, "loss": 0.644, "lr": 4.713640064133025e-05, "epoch": 0.7169811320754716, "percentage": 23.9, "elapsed_time": "2:14:15", "remaining_time": "7:07:30"} +{"current_steps": 115, "total_steps": 477, "loss": 0.5418, "lr": 4.7050727958301506e-05, "epoch": 0.7232704402515723, "percentage": 24.11, "elapsed_time": "2:15:26", "remaining_time": "7:06:19"} +{"current_steps": 116, "total_steps": 477, "loss": 0.6524, "lr": 4.6963872761652835e-05, "epoch": 0.7295597484276729, "percentage": 24.32, "elapsed_time": "2:16:35", "remaining_time": "7:05:05"} +{"current_steps": 117, "total_steps": 477, "loss": 0.6134, "lr": 4.687583970916487e-05, "epoch": 0.7358490566037735, "percentage": 24.53, "elapsed_time": "2:17:46", "remaining_time": "7:03:55"} +{"current_steps": 118, "total_steps": 477, "loss": 0.6517, "lr": 4.678663352178301e-05, "epoch": 0.7421383647798742, "percentage": 24.74, "elapsed_time": "2:19:04", "remaining_time": "7:03:06"} +{"current_steps": 119, "total_steps": 477, "loss": 0.5763, "lr": 4.6696258983364385e-05, "epoch": 0.7484276729559748, "percentage": 24.95, "elapsed_time": "2:20:08", "remaining_time": "7:01:34"} +{"current_steps": 120, "total_steps": 477, "loss": 0.7349, "lr": 4.660472094042121e-05, "epoch": 0.7547169811320755, "percentage": 25.16, "elapsed_time": "2:21:22", "remaining_time": "7:00:34"} +{"current_steps": 121, "total_steps": 477, "loss": 0.6548, "lr": 4.651202430186092e-05, "epoch": 0.7610062893081762, "percentage": 25.37, "elapsed_time": "2:22:22", "remaining_time": "6:58:54"} +{"current_steps": 122, "total_steps": 477, "loss": 0.6135, "lr": 4.641817403872293e-05, "epoch": 0.7672955974842768, "percentage": 25.58, "elapsed_time": "2:23:35", "remaining_time": "6:57:50"} +{"current_steps": 123, "total_steps": 477, "loss": 0.5227, "lr": 4.6323175183912024e-05, "epoch": 0.7735849056603774, "percentage": 25.79, "elapsed_time": "2:24:40", "remaining_time": "6:56:21"} +{"current_steps": 124, "total_steps": 477, "loss": 0.5265, "lr": 4.6227032831928484e-05, "epoch": 0.779874213836478, "percentage": 26.0, "elapsed_time": "2:25:42", "remaining_time": "6:54:46"} +{"current_steps": 125, "total_steps": 477, "loss": 0.5972, "lr": 4.6129752138594874e-05, "epoch": 0.7861635220125787, "percentage": 26.21, "elapsed_time": "2:26:57", "remaining_time": "6:53:50"} +{"current_steps": 126, "total_steps": 477, "loss": 0.6758, "lr": 4.6031338320779534e-05, "epoch": 0.7924528301886793, "percentage": 26.42, "elapsed_time": "2:28:07", "remaining_time": "6:52:38"} +{"current_steps": 127, "total_steps": 477, "loss": 0.6419, "lr": 4.5931796656116846e-05, "epoch": 0.7987421383647799, "percentage": 26.62, "elapsed_time": "2:29:13", "remaining_time": "6:51:15"} +{"current_steps": 128, "total_steps": 477, "loss": 0.6952, "lr": 4.5831132482724195e-05, "epoch": 0.8050314465408805, "percentage": 26.83, "elapsed_time": "2:30:17", "remaining_time": "6:49:45"} +{"current_steps": 129, "total_steps": 477, "loss": 0.6093, "lr": 4.572935119891571e-05, "epoch": 0.8113207547169812, "percentage": 27.04, "elapsed_time": "2:31:25", "remaining_time": "6:48:28"} +{"current_steps": 130, "total_steps": 477, "loss": 0.5688, "lr": 4.5626458262912745e-05, "epoch": 0.8176100628930818, "percentage": 27.25, "elapsed_time": "2:32:30", "remaining_time": "6:47:04"} +{"current_steps": 131, "total_steps": 477, "loss": 0.5778, "lr": 4.552245919255117e-05, "epoch": 0.8238993710691824, "percentage": 27.46, "elapsed_time": "2:33:37", "remaining_time": "6:45:46"} +{"current_steps": 132, "total_steps": 477, "loss": 0.517, "lr": 4.541735956498554e-05, "epoch": 0.8301886792452831, "percentage": 27.67, "elapsed_time": "2:34:42", "remaining_time": "6:44:20"} +{"current_steps": 133, "total_steps": 477, "loss": 0.631, "lr": 4.5311165016389916e-05, "epoch": 0.8364779874213837, "percentage": 27.88, "elapsed_time": "2:35:58", "remaining_time": "6:43:26"} +{"current_steps": 134, "total_steps": 477, "loss": 0.6309, "lr": 4.5203881241655644e-05, "epoch": 0.8427672955974843, "percentage": 28.09, "elapsed_time": "2:37:12", "remaining_time": "6:42:23"} +{"current_steps": 135, "total_steps": 477, "loss": 0.6754, "lr": 4.509551399408598e-05, "epoch": 0.8490566037735849, "percentage": 28.3, "elapsed_time": "2:38:17", "remaining_time": "6:41:00"} +{"current_steps": 136, "total_steps": 477, "loss": 0.6547, "lr": 4.498606908508754e-05, "epoch": 0.8553459119496856, "percentage": 28.51, "elapsed_time": "2:39:32", "remaining_time": "6:40:01"} +{"current_steps": 137, "total_steps": 477, "loss": 0.5693, "lr": 4.487555238385862e-05, "epoch": 0.8616352201257862, "percentage": 28.72, "elapsed_time": "2:40:40", "remaining_time": "6:38:44"} +{"current_steps": 138, "total_steps": 477, "loss": 0.6655, "lr": 4.476396981707453e-05, "epoch": 0.8679245283018868, "percentage": 28.93, "elapsed_time": "2:41:55", "remaining_time": "6:37:46"} +{"current_steps": 139, "total_steps": 477, "loss": 0.6563, "lr": 4.465132736856969e-05, "epoch": 0.8742138364779874, "percentage": 29.14, "elapsed_time": "2:43:06", "remaining_time": "6:36:38"} +{"current_steps": 140, "total_steps": 477, "loss": 0.5729, "lr": 4.453763107901675e-05, "epoch": 0.8805031446540881, "percentage": 29.35, "elapsed_time": "2:44:11", "remaining_time": "6:35:12"} +{"current_steps": 141, "total_steps": 477, "loss": 0.6425, "lr": 4.442288704560268e-05, "epoch": 0.8867924528301887, "percentage": 29.56, "elapsed_time": "2:45:35", "remaining_time": "6:34:35"} +{"current_steps": 142, "total_steps": 477, "loss": 0.5732, "lr": 4.430710142170176e-05, "epoch": 0.8930817610062893, "percentage": 29.77, "elapsed_time": "2:46:47", "remaining_time": "6:33:30"} +{"current_steps": 143, "total_steps": 477, "loss": 0.6507, "lr": 4.419028041654559e-05, "epoch": 0.89937106918239, "percentage": 29.98, "elapsed_time": "2:47:59", "remaining_time": "6:32:22"} +{"current_steps": 144, "total_steps": 477, "loss": 0.6883, "lr": 4.4072430294890174e-05, "epoch": 0.9056603773584906, "percentage": 30.19, "elapsed_time": "2:49:09", "remaining_time": "6:31:10"} +{"current_steps": 145, "total_steps": 477, "loss": 0.5818, "lr": 4.3953557376679856e-05, "epoch": 0.9119496855345912, "percentage": 30.4, "elapsed_time": "2:50:24", "remaining_time": "6:30:11"} +{"current_steps": 146, "total_steps": 477, "loss": 0.5963, "lr": 4.383366803670849e-05, "epoch": 0.9182389937106918, "percentage": 30.61, "elapsed_time": "2:51:44", "remaining_time": "6:29:20"} +{"current_steps": 147, "total_steps": 477, "loss": 0.65, "lr": 4.371276870427753e-05, "epoch": 0.9245283018867925, "percentage": 30.82, "elapsed_time": "2:52:49", "remaining_time": "6:27:58"} +{"current_steps": 148, "total_steps": 477, "loss": 0.6554, "lr": 4.359086586285127e-05, "epoch": 0.9308176100628931, "percentage": 31.03, "elapsed_time": "2:53:58", "remaining_time": "6:26:44"} +{"current_steps": 149, "total_steps": 477, "loss": 0.6681, "lr": 4.346796604970912e-05, "epoch": 0.9371069182389937, "percentage": 31.24, "elapsed_time": "2:55:05", "remaining_time": "6:25:25"} +{"current_steps": 150, "total_steps": 477, "loss": 0.6108, "lr": 4.3344075855595104e-05, "epoch": 0.9433962264150944, "percentage": 31.45, "elapsed_time": "2:56:11", "remaining_time": "6:24:05"} +{"current_steps": 151, "total_steps": 477, "loss": 0.6177, "lr": 4.321920192436433e-05, "epoch": 0.949685534591195, "percentage": 31.66, "elapsed_time": "2:57:24", "remaining_time": "6:23:01"} +{"current_steps": 152, "total_steps": 477, "loss": 0.5881, "lr": 4.309335095262676e-05, "epoch": 0.9559748427672956, "percentage": 31.87, "elapsed_time": "2:58:39", "remaining_time": "6:21:59"} +{"current_steps": 153, "total_steps": 477, "loss": 0.6142, "lr": 4.296652968938807e-05, "epoch": 0.9622641509433962, "percentage": 32.08, "elapsed_time": "2:59:49", "remaining_time": "6:20:49"} +{"current_steps": 154, "total_steps": 477, "loss": 0.6463, "lr": 4.283874493568772e-05, "epoch": 0.9685534591194969, "percentage": 32.29, "elapsed_time": "3:01:00", "remaining_time": "6:19:38"} +{"current_steps": 155, "total_steps": 477, "loss": 0.5873, "lr": 4.271000354423426e-05, "epoch": 0.9748427672955975, "percentage": 32.49, "elapsed_time": "3:02:02", "remaining_time": "6:18:10"} +{"current_steps": 156, "total_steps": 477, "loss": 0.6046, "lr": 4.258031241903778e-05, "epoch": 0.9811320754716981, "percentage": 32.7, "elapsed_time": "3:03:13", "remaining_time": "6:17:01"} +{"current_steps": 157, "total_steps": 477, "loss": 0.5989, "lr": 4.2449678515039747e-05, "epoch": 0.9874213836477987, "percentage": 32.91, "elapsed_time": "3:04:23", "remaining_time": "6:15:49"} +{"current_steps": 158, "total_steps": 477, "loss": 0.6156, "lr": 4.231810883773999e-05, "epoch": 0.9937106918238994, "percentage": 33.12, "elapsed_time": "3:05:42", "remaining_time": "6:14:56"} +{"current_steps": 159, "total_steps": 477, "loss": 0.6177, "lr": 4.218561044282099e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:06:45", "remaining_time": "6:13:31"} +{"current_steps": 160, "total_steps": 477, "loss": 0.5881, "lr": 4.2052190435769554e-05, "epoch": 1.0062893081761006, "percentage": 33.54, "elapsed_time": "3:07:57", "remaining_time": "6:12:24"} +{"current_steps": 161, "total_steps": 477, "loss": 0.5354, "lr": 4.191785597149577e-05, "epoch": 1.0125786163522013, "percentage": 33.75, "elapsed_time": "3:09:12", "remaining_time": "6:11:21"} +{"current_steps": 162, "total_steps": 477, "loss": 0.5745, "lr": 4.178261425394926e-05, "epoch": 1.0188679245283019, "percentage": 33.96, "elapsed_time": "3:10:22", "remaining_time": "6:10:10"} +{"current_steps": 163, "total_steps": 477, "loss": 0.5836, "lr": 4.1646472535732895e-05, "epoch": 1.0251572327044025, "percentage": 34.17, "elapsed_time": "3:11:47", "remaining_time": "6:09:27"} +{"current_steps": 164, "total_steps": 477, "loss": 0.6118, "lr": 4.1509438117713866e-05, "epoch": 1.0314465408805031, "percentage": 34.38, "elapsed_time": "3:13:00", "remaining_time": "6:08:22"} +{"current_steps": 165, "total_steps": 477, "loss": 0.5811, "lr": 4.137151834863213e-05, "epoch": 1.0377358490566038, "percentage": 34.59, "elapsed_time": "3:14:16", "remaining_time": "6:07:20"} +{"current_steps": 166, "total_steps": 477, "loss": 0.5179, "lr": 4.123272062470633e-05, "epoch": 1.0440251572327044, "percentage": 34.8, "elapsed_time": "3:15:23", "remaining_time": "6:06:04"} +{"current_steps": 167, "total_steps": 477, "loss": 0.548, "lr": 4.109305238923718e-05, "epoch": 1.050314465408805, "percentage": 35.01, "elapsed_time": "3:16:31", "remaining_time": "6:04:48"} +{"current_steps": 168, "total_steps": 477, "loss": 0.5659, "lr": 4.095252113220827e-05, "epoch": 1.0566037735849056, "percentage": 35.22, "elapsed_time": "3:17:41", "remaining_time": "6:03:37"} +{"current_steps": 169, "total_steps": 477, "loss": 0.5522, "lr": 4.0811134389884433e-05, "epoch": 1.0628930817610063, "percentage": 35.43, "elapsed_time": "3:18:44", "remaining_time": "6:02:11"} +{"current_steps": 170, "total_steps": 477, "loss": 0.542, "lr": 4.066889974440757e-05, "epoch": 1.069182389937107, "percentage": 35.64, "elapsed_time": "3:19:59", "remaining_time": "6:01:09"} +{"current_steps": 171, "total_steps": 477, "loss": 0.6131, "lr": 4.0525824823390045e-05, "epoch": 1.0754716981132075, "percentage": 35.85, "elapsed_time": "3:21:04", "remaining_time": "5:59:49"} +{"current_steps": 172, "total_steps": 477, "loss": 0.5823, "lr": 4.038191729950569e-05, "epoch": 1.0817610062893082, "percentage": 36.06, "elapsed_time": "3:22:17", "remaining_time": "5:58:42"} +{"current_steps": 173, "total_steps": 477, "loss": 0.6066, "lr": 4.0237184890078245e-05, "epoch": 1.0880503144654088, "percentage": 36.27, "elapsed_time": "3:23:21", "remaining_time": "5:57:20"} +{"current_steps": 174, "total_steps": 477, "loss": 0.6407, "lr": 4.009163535666761e-05, "epoch": 1.0943396226415094, "percentage": 36.48, "elapsed_time": "3:24:22", "remaining_time": "5:55:53"} +{"current_steps": 175, "total_steps": 477, "loss": 0.573, "lr": 3.994527650465352e-05, "epoch": 1.10062893081761, "percentage": 36.69, "elapsed_time": "3:25:34", "remaining_time": "5:54:46"} +{"current_steps": 176, "total_steps": 477, "loss": 0.6349, "lr": 3.979811618281706e-05, "epoch": 1.1069182389937107, "percentage": 36.9, "elapsed_time": "3:26:50", "remaining_time": "5:53:45"} +{"current_steps": 177, "total_steps": 477, "loss": 0.6036, "lr": 3.9650162282919655e-05, "epoch": 1.1132075471698113, "percentage": 37.11, "elapsed_time": "3:27:56", "remaining_time": "5:52:26"} +{"current_steps": 178, "total_steps": 477, "loss": 0.5855, "lr": 3.9501422739279956e-05, "epoch": 1.119496855345912, "percentage": 37.32, "elapsed_time": "3:29:03", "remaining_time": "5:51:10"} +{"current_steps": 179, "total_steps": 477, "loss": 0.5719, "lr": 3.9351905528348285e-05, "epoch": 1.1257861635220126, "percentage": 37.53, "elapsed_time": "3:30:07", "remaining_time": "5:49:48"} +{"current_steps": 180, "total_steps": 477, "loss": 0.5764, "lr": 3.920161866827889e-05, "epoch": 1.1320754716981132, "percentage": 37.74, "elapsed_time": "3:31:12", "remaining_time": "5:48:28"} +{"current_steps": 181, "total_steps": 477, "loss": 0.644, "lr": 3.90505702185e-05, "epoch": 1.1383647798742138, "percentage": 37.95, "elapsed_time": "3:32:19", "remaining_time": "5:47:13"} +{"current_steps": 182, "total_steps": 477, "loss": 0.5883, "lr": 3.889876827928156e-05, "epoch": 1.1446540880503144, "percentage": 38.16, "elapsed_time": "3:33:26", "remaining_time": "5:45:57"} +{"current_steps": 183, "total_steps": 477, "loss": 0.5942, "lr": 3.874622099130087e-05, "epoch": 1.150943396226415, "percentage": 38.36, "elapsed_time": "3:34:36", "remaining_time": "5:44:47"} +{"current_steps": 184, "total_steps": 477, "loss": 0.6086, "lr": 3.859293653520604e-05, "epoch": 1.1572327044025157, "percentage": 38.57, "elapsed_time": "3:35:41", "remaining_time": "5:43:28"} +{"current_steps": 185, "total_steps": 477, "loss": 0.6105, "lr": 3.843892313117724e-05, "epoch": 1.1635220125786163, "percentage": 38.78, "elapsed_time": "3:36:59", "remaining_time": "5:42:29"} +{"current_steps": 186, "total_steps": 477, "loss": 0.5622, "lr": 3.8284189038485936e-05, "epoch": 1.169811320754717, "percentage": 38.99, "elapsed_time": "3:38:08", "remaining_time": "5:41:17"} +{"current_steps": 187, "total_steps": 477, "loss": 0.5451, "lr": 3.812874255505191e-05, "epoch": 1.1761006289308176, "percentage": 39.2, "elapsed_time": "3:39:21", "remaining_time": "5:40:10"} +{"current_steps": 188, "total_steps": 477, "loss": 0.5864, "lr": 3.797259201699833e-05, "epoch": 1.1823899371069182, "percentage": 39.41, "elapsed_time": "3:40:22", "remaining_time": "5:38:45"} +{"current_steps": 189, "total_steps": 477, "loss": 0.5602, "lr": 3.781574579820464e-05, "epoch": 1.1886792452830188, "percentage": 39.62, "elapsed_time": "3:41:30", "remaining_time": "5:37:32"} +{"current_steps": 190, "total_steps": 477, "loss": 0.5556, "lr": 3.765821230985758e-05, "epoch": 1.1949685534591195, "percentage": 39.83, "elapsed_time": "3:42:45", "remaining_time": "5:36:29"} +{"current_steps": 191, "total_steps": 477, "loss": 0.6491, "lr": 3.7500000000000003e-05, "epoch": 1.20125786163522, "percentage": 40.04, "elapsed_time": "3:43:48", "remaining_time": "5:35:07"} +{"current_steps": 192, "total_steps": 477, "loss": 0.5797, "lr": 3.7341117353077966e-05, "epoch": 1.2075471698113207, "percentage": 40.25, "elapsed_time": "3:45:01", "remaining_time": "5:34:01"} +{"current_steps": 193, "total_steps": 477, "loss": 0.5613, "lr": 3.718157288948563e-05, "epoch": 1.2138364779874213, "percentage": 40.46, "elapsed_time": "3:46:11", "remaining_time": "5:32:49"} +{"current_steps": 194, "total_steps": 477, "loss": 0.6301, "lr": 3.702137516510838e-05, "epoch": 1.220125786163522, "percentage": 40.67, "elapsed_time": "3:47:27", "remaining_time": "5:31:49"} +{"current_steps": 195, "total_steps": 477, "loss": 0.5772, "lr": 3.686053277086401e-05, "epoch": 1.2264150943396226, "percentage": 40.88, "elapsed_time": "3:48:35", "remaining_time": "5:30:34"} +{"current_steps": 196, "total_steps": 477, "loss": 0.5452, "lr": 3.669905433224199e-05, "epoch": 1.2327044025157232, "percentage": 41.09, "elapsed_time": "3:49:44", "remaining_time": "5:29:22"} +{"current_steps": 197, "total_steps": 477, "loss": 0.5365, "lr": 3.653694850884091e-05, "epoch": 1.2389937106918238, "percentage": 41.3, "elapsed_time": "3:50:48", "remaining_time": "5:28:03"} +{"current_steps": 198, "total_steps": 477, "loss": 0.5396, "lr": 3.637422399390413e-05, "epoch": 1.2452830188679245, "percentage": 41.51, "elapsed_time": "3:52:02", "remaining_time": "5:26:57"} +{"current_steps": 199, "total_steps": 477, "loss": 0.6024, "lr": 3.621088951385353e-05, "epoch": 1.251572327044025, "percentage": 41.72, "elapsed_time": "3:53:11", "remaining_time": "5:25:46"} +{"current_steps": 200, "total_steps": 477, "loss": 0.6905, "lr": 3.604695382782159e-05, "epoch": 1.2578616352201257, "percentage": 41.93, "elapsed_time": "3:54:24", "remaining_time": "5:24:39"} +{"current_steps": 201, "total_steps": 477, "loss": 0.5909, "lr": 3.588242572718162e-05, "epoch": 1.2641509433962264, "percentage": 42.14, "elapsed_time": "3:55:35", "remaining_time": "5:23:29"} +{"current_steps": 202, "total_steps": 477, "loss": 0.5745, "lr": 3.5717314035076355e-05, "epoch": 1.270440251572327, "percentage": 42.35, "elapsed_time": "3:56:42", "remaining_time": "5:22:14"} +{"current_steps": 203, "total_steps": 477, "loss": 0.6439, "lr": 3.5551627605944745e-05, "epoch": 1.2767295597484276, "percentage": 42.56, "elapsed_time": "3:57:57", "remaining_time": "5:21:11"} +{"current_steps": 204, "total_steps": 477, "loss": 0.5611, "lr": 3.5385375325047166e-05, "epoch": 1.2830188679245282, "percentage": 42.77, "elapsed_time": "3:58:59", "remaining_time": "5:19:50"} +{"current_steps": 205, "total_steps": 477, "loss": 0.5846, "lr": 3.521856610798887e-05, "epoch": 1.2893081761006289, "percentage": 42.98, "elapsed_time": "4:00:04", "remaining_time": "5:18:32"} +{"current_steps": 206, "total_steps": 477, "loss": 0.5982, "lr": 3.505120890024195e-05, "epoch": 1.2955974842767295, "percentage": 43.19, "elapsed_time": "4:01:09", "remaining_time": "5:17:15"} +{"current_steps": 207, "total_steps": 477, "loss": 0.6265, "lr": 3.4883312676665536e-05, "epoch": 1.3018867924528301, "percentage": 43.4, "elapsed_time": "4:02:18", "remaining_time": "5:16:03"} +{"current_steps": 208, "total_steps": 477, "loss": 0.5161, "lr": 3.4714886441024574e-05, "epoch": 1.3081761006289307, "percentage": 43.61, "elapsed_time": "4:03:26", "remaining_time": "5:14:49"} +{"current_steps": 209, "total_steps": 477, "loss": 0.5408, "lr": 3.4545939225506934e-05, "epoch": 1.3144654088050314, "percentage": 43.82, "elapsed_time": "4:04:43", "remaining_time": "5:13:48"} +{"current_steps": 210, "total_steps": 477, "loss": 0.5715, "lr": 3.437648009023905e-05, "epoch": 1.320754716981132, "percentage": 44.03, "elapsed_time": "4:06:00", "remaining_time": "5:12:47"} +{"current_steps": 211, "total_steps": 477, "loss": 0.5694, "lr": 3.420651812280006e-05, "epoch": 1.3270440251572326, "percentage": 44.23, "elapsed_time": "4:07:11", "remaining_time": "5:11:37"} +{"current_steps": 212, "total_steps": 477, "loss": 0.5203, "lr": 3.4036062437734484e-05, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "4:08:22", "remaining_time": "5:10:28"} +{"current_steps": 213, "total_steps": 477, "loss": 0.5778, "lr": 3.386512217606339e-05, "epoch": 1.3396226415094339, "percentage": 44.65, "elapsed_time": "4:09:31", "remaining_time": "5:09:16"} +{"current_steps": 214, "total_steps": 477, "loss": 0.5757, "lr": 3.369370650479425e-05, "epoch": 1.3459119496855345, "percentage": 44.86, "elapsed_time": "4:10:51", "remaining_time": "5:08:18"} +{"current_steps": 215, "total_steps": 477, "loss": 0.5348, "lr": 3.3521824616429285e-05, "epoch": 1.3522012578616351, "percentage": 45.07, "elapsed_time": "4:12:06", "remaining_time": "5:07:13"} +{"current_steps": 216, "total_steps": 477, "loss": 0.5982, "lr": 3.3349485728472535e-05, "epoch": 1.3584905660377358, "percentage": 45.28, "elapsed_time": "4:13:10", "remaining_time": "5:05:55"} +{"current_steps": 217, "total_steps": 477, "loss": 0.6131, "lr": 3.3176699082935545e-05, "epoch": 1.3647798742138364, "percentage": 45.49, "elapsed_time": "4:14:21", "remaining_time": "5:04:45"} +{"current_steps": 218, "total_steps": 477, "loss": 0.6194, "lr": 3.300347394584172e-05, "epoch": 1.371069182389937, "percentage": 45.7, "elapsed_time": "4:15:33", "remaining_time": "5:03:37"} +{"current_steps": 219, "total_steps": 477, "loss": 0.5938, "lr": 3.282981960672948e-05, "epoch": 1.3773584905660377, "percentage": 45.91, "elapsed_time": "4:16:54", "remaining_time": "5:02:39"} +{"current_steps": 220, "total_steps": 477, "loss": 0.5634, "lr": 3.265574537815398e-05, "epoch": 1.3836477987421385, "percentage": 46.12, "elapsed_time": "4:17:58", "remaining_time": "5:01:21"} +{"current_steps": 221, "total_steps": 477, "loss": 0.5543, "lr": 3.248126059518785e-05, "epoch": 1.389937106918239, "percentage": 46.33, "elapsed_time": "4:19:05", "remaining_time": "5:00:07"} +{"current_steps": 222, "total_steps": 477, "loss": 0.549, "lr": 3.230637461492043e-05, "epoch": 1.3962264150943398, "percentage": 46.54, "elapsed_time": "4:20:21", "remaining_time": "4:59:03"} +{"current_steps": 223, "total_steps": 477, "loss": 0.5799, "lr": 3.213109681595612e-05, "epoch": 1.4025157232704402, "percentage": 46.75, "elapsed_time": "4:21:25", "remaining_time": "4:57:46"} +{"current_steps": 224, "total_steps": 477, "loss": 0.5788, "lr": 3.195543659791132e-05, "epoch": 1.408805031446541, "percentage": 46.96, "elapsed_time": "4:22:35", "remaining_time": "4:56:35"} +{"current_steps": 225, "total_steps": 477, "loss": 0.4883, "lr": 3.177940338091043e-05, "epoch": 1.4150943396226414, "percentage": 47.17, "elapsed_time": "4:23:48", "remaining_time": "4:55:28"} +{"current_steps": 226, "total_steps": 477, "loss": 0.5737, "lr": 3.160300660508064e-05, "epoch": 1.4213836477987423, "percentage": 47.38, "elapsed_time": "4:24:57", "remaining_time": "4:54:16"} +{"current_steps": 227, "total_steps": 477, "loss": 0.5416, "lr": 3.14262557300457e-05, "epoch": 1.4276729559748427, "percentage": 47.59, "elapsed_time": "4:26:02", "remaining_time": "4:52:59"} +{"current_steps": 228, "total_steps": 477, "loss": 0.5747, "lr": 3.124916023441865e-05, "epoch": 1.4339622641509435, "percentage": 47.8, "elapsed_time": "4:27:07", "remaining_time": "4:51:43"} +{"current_steps": 229, "total_steps": 477, "loss": 0.508, "lr": 3.107172961529343e-05, "epoch": 1.440251572327044, "percentage": 48.01, "elapsed_time": "4:28:12", "remaining_time": "4:50:28"} +{"current_steps": 230, "total_steps": 477, "loss": 0.6929, "lr": 3.0893973387735687e-05, "epoch": 1.4465408805031448, "percentage": 48.22, "elapsed_time": "4:29:29", "remaining_time": "4:49:24"} +{"current_steps": 231, "total_steps": 477, "loss": 0.6467, "lr": 3.071590108427244e-05, "epoch": 1.4528301886792452, "percentage": 48.43, "elapsed_time": "4:30:35", "remaining_time": "4:48:09"} +{"current_steps": 232, "total_steps": 477, "loss": 0.5067, "lr": 3.0537522254380905e-05, "epoch": 1.459119496855346, "percentage": 48.64, "elapsed_time": "4:31:44", "remaining_time": "4:46:58"} +{"current_steps": 233, "total_steps": 477, "loss": 0.6052, "lr": 3.0358846463976372e-05, "epoch": 1.4654088050314464, "percentage": 48.85, "elapsed_time": "4:33:09", "remaining_time": "4:46:03"} +{"current_steps": 234, "total_steps": 477, "loss": 0.5961, "lr": 3.017988329489923e-05, "epoch": 1.4716981132075473, "percentage": 49.06, "elapsed_time": "4:34:17", "remaining_time": "4:44:50"} +{"current_steps": 235, "total_steps": 477, "loss": 0.6285, "lr": 3.0000642344401113e-05, "epoch": 1.4779874213836477, "percentage": 49.27, "elapsed_time": "4:35:20", "remaining_time": "4:43:33"} +{"current_steps": 236, "total_steps": 477, "loss": 0.4634, "lr": 2.9821133224630226e-05, "epoch": 1.4842767295597485, "percentage": 49.48, "elapsed_time": "4:36:21", "remaining_time": "4:42:12"} +{"current_steps": 237, "total_steps": 477, "loss": 0.5288, "lr": 2.9641365562115887e-05, "epoch": 1.490566037735849, "percentage": 49.69, "elapsed_time": "4:37:34", "remaining_time": "4:41:05"} +{"current_steps": 238, "total_steps": 477, "loss": 0.5748, "lr": 2.9461348997252265e-05, "epoch": 1.4968553459119498, "percentage": 49.9, "elapsed_time": "4:38:46", "remaining_time": "4:39:56"} +{"current_steps": 239, "total_steps": 477, "loss": 0.5944, "lr": 2.9281093183781403e-05, "epoch": 1.5031446540880502, "percentage": 50.1, "elapsed_time": "4:40:04", "remaining_time": "4:38:53"} +{"current_steps": 240, "total_steps": 477, "loss": 0.5549, "lr": 2.9100607788275545e-05, "epoch": 1.509433962264151, "percentage": 50.31, "elapsed_time": "4:41:12", "remaining_time": "4:37:41"} +{"current_steps": 241, "total_steps": 477, "loss": 0.5345, "lr": 2.891990248961871e-05, "epoch": 1.5157232704402515, "percentage": 50.52, "elapsed_time": "4:42:24", "remaining_time": "4:36:32"} +{"current_steps": 242, "total_steps": 477, "loss": 0.5839, "lr": 2.8738986978487625e-05, "epoch": 1.5220125786163523, "percentage": 50.73, "elapsed_time": "4:43:27", "remaining_time": "4:35:16"} +{"current_steps": 243, "total_steps": 477, "loss": 0.4931, "lr": 2.8557870956832132e-05, "epoch": 1.5283018867924527, "percentage": 50.94, "elapsed_time": "4:44:35", "remaining_time": "4:34:03"} +{"current_steps": 244, "total_steps": 477, "loss": 0.5598, "lr": 2.8376564137354795e-05, "epoch": 1.5345911949685536, "percentage": 51.15, "elapsed_time": "4:45:49", "remaining_time": "4:32:55"} +{"current_steps": 245, "total_steps": 477, "loss": 0.5894, "lr": 2.8195076242990122e-05, "epoch": 1.540880503144654, "percentage": 51.36, "elapsed_time": "4:47:01", "remaining_time": "4:31:48"} +{"current_steps": 246, "total_steps": 477, "loss": 0.6345, "lr": 2.8013417006383076e-05, "epoch": 1.5471698113207548, "percentage": 51.57, "elapsed_time": "4:48:15", "remaining_time": "4:30:41"} +{"current_steps": 247, "total_steps": 477, "loss": 0.6519, "lr": 2.783159616936723e-05, "epoch": 1.5534591194968552, "percentage": 51.78, "elapsed_time": "4:49:23", "remaining_time": "4:29:28"} +{"current_steps": 248, "total_steps": 477, "loss": 0.5658, "lr": 2.764962348244228e-05, "epoch": 1.559748427672956, "percentage": 51.99, "elapsed_time": "4:50:30", "remaining_time": "4:28:15"} +{"current_steps": 249, "total_steps": 477, "loss": 0.5934, "lr": 2.7467508704251137e-05, "epoch": 1.5660377358490565, "percentage": 52.2, "elapsed_time": "4:51:38", "remaining_time": "4:27:02"} +{"current_steps": 250, "total_steps": 477, "loss": 0.5341, "lr": 2.7285261601056698e-05, "epoch": 1.5723270440251573, "percentage": 52.41, "elapsed_time": "4:52:44", "remaining_time": "4:25:48"} +{"current_steps": 251, "total_steps": 477, "loss": 0.5885, "lr": 2.7102891946217994e-05, "epoch": 1.5786163522012577, "percentage": 52.62, "elapsed_time": "4:53:50", "remaining_time": "4:24:34"} +{"current_steps": 252, "total_steps": 477, "loss": 0.5988, "lr": 2.6920409519666174e-05, "epoch": 1.5849056603773586, "percentage": 52.83, "elapsed_time": "4:54:53", "remaining_time": "4:23:17"} +{"current_steps": 253, "total_steps": 477, "loss": 0.6635, "lr": 2.6737824107379948e-05, "epoch": 1.591194968553459, "percentage": 53.04, "elapsed_time": "4:55:55", "remaining_time": "4:22:00"} +{"current_steps": 254, "total_steps": 477, "loss": 0.5365, "lr": 2.655514550086086e-05, "epoch": 1.5974842767295598, "percentage": 53.25, "elapsed_time": "4:57:07", "remaining_time": "4:20:51"} +{"current_steps": 255, "total_steps": 477, "loss": 0.6854, "lr": 2.637238349660819e-05, "epoch": 1.6037735849056602, "percentage": 53.46, "elapsed_time": "4:58:12", "remaining_time": "4:19:36"} +{"current_steps": 256, "total_steps": 477, "loss": 0.5234, "lr": 2.6189547895593562e-05, "epoch": 1.610062893081761, "percentage": 53.67, "elapsed_time": "4:59:27", "remaining_time": "4:18:30"} +{"current_steps": 257, "total_steps": 477, "loss": 0.5962, "lr": 2.600664850273538e-05, "epoch": 1.6163522012578615, "percentage": 53.88, "elapsed_time": "5:00:36", "remaining_time": "4:17:19"} +{"current_steps": 258, "total_steps": 477, "loss": 0.5396, "lr": 2.582369512637302e-05, "epoch": 1.6226415094339623, "percentage": 54.09, "elapsed_time": "5:01:46", "remaining_time": "4:16:09"} +{"current_steps": 259, "total_steps": 477, "loss": 0.4889, "lr": 2.564069757774082e-05, "epoch": 1.6289308176100628, "percentage": 54.3, "elapsed_time": "5:03:06", "remaining_time": "4:15:07"} +{"current_steps": 260, "total_steps": 477, "loss": 0.5893, "lr": 2.545766567044194e-05, "epoch": 1.6352201257861636, "percentage": 54.51, "elapsed_time": "5:04:11", "remaining_time": "4:13:53"} +{"current_steps": 261, "total_steps": 477, "loss": 0.566, "lr": 2.527460921992209e-05, "epoch": 1.641509433962264, "percentage": 54.72, "elapsed_time": "5:05:28", "remaining_time": "4:12:48"} +{"current_steps": 262, "total_steps": 477, "loss": 0.5598, "lr": 2.509153804294318e-05, "epoch": 1.6477987421383649, "percentage": 54.93, "elapsed_time": "5:06:32", "remaining_time": "4:11:33"} +{"current_steps": 263, "total_steps": 477, "loss": 0.552, "lr": 2.490846195705683e-05, "epoch": 1.6540880503144653, "percentage": 55.14, "elapsed_time": "5:07:34", "remaining_time": "4:10:16"} +{"current_steps": 264, "total_steps": 477, "loss": 0.6233, "lr": 2.4725390780077908e-05, "epoch": 1.6603773584905661, "percentage": 55.35, "elapsed_time": "5:08:45", "remaining_time": "4:09:06"} +{"current_steps": 265, "total_steps": 477, "loss": 0.4968, "lr": 2.4542334329558077e-05, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "5:10:06", "remaining_time": "4:08:05"} +{"current_steps": 266, "total_steps": 477, "loss": 0.5315, "lr": 2.435930242225919e-05, "epoch": 1.6729559748427674, "percentage": 55.77, "elapsed_time": "5:11:19", "remaining_time": "4:06:57"} +{"current_steps": 267, "total_steps": 477, "loss": 0.5622, "lr": 2.4176304873626985e-05, "epoch": 1.6792452830188678, "percentage": 55.97, "elapsed_time": "5:12:25", "remaining_time": "4:05:43"} +{"current_steps": 268, "total_steps": 477, "loss": 0.5999, "lr": 2.399335149726463e-05, "epoch": 1.6855345911949686, "percentage": 56.18, "elapsed_time": "5:13:35", "remaining_time": "4:04:33"} +{"current_steps": 269, "total_steps": 477, "loss": 0.6351, "lr": 2.3810452104406444e-05, "epoch": 1.691823899371069, "percentage": 56.39, "elapsed_time": "5:14:52", "remaining_time": "4:03:28"} +{"current_steps": 270, "total_steps": 477, "loss": 0.5754, "lr": 2.3627616503391814e-05, "epoch": 1.6981132075471699, "percentage": 56.6, "elapsed_time": "5:16:09", "remaining_time": "4:02:23"} +{"current_steps": 271, "total_steps": 477, "loss": 0.5635, "lr": 2.3444854499139142e-05, "epoch": 1.7044025157232703, "percentage": 56.81, "elapsed_time": "5:17:15", "remaining_time": "4:01:09"} +{"current_steps": 272, "total_steps": 477, "loss": 0.5368, "lr": 2.3262175892620065e-05, "epoch": 1.7106918238993711, "percentage": 57.02, "elapsed_time": "5:18:29", "remaining_time": "4:00:02"} +{"current_steps": 273, "total_steps": 477, "loss": 0.5508, "lr": 2.307959048033383e-05, "epoch": 1.7169811320754715, "percentage": 57.23, "elapsed_time": "5:19:34", "remaining_time": "3:58:48"} +{"current_steps": 274, "total_steps": 477, "loss": 0.6073, "lr": 2.2897108053782e-05, "epoch": 1.7232704402515724, "percentage": 57.44, "elapsed_time": "5:20:44", "remaining_time": "3:57:37"} +{"current_steps": 275, "total_steps": 477, "loss": 0.5326, "lr": 2.271473839894331e-05, "epoch": 1.7295597484276728, "percentage": 57.65, "elapsed_time": "5:21:52", "remaining_time": "3:56:25"} +{"current_steps": 276, "total_steps": 477, "loss": 0.5444, "lr": 2.253249129574887e-05, "epoch": 1.7358490566037736, "percentage": 57.86, "elapsed_time": "5:23:00", "remaining_time": "3:55:13"} +{"current_steps": 277, "total_steps": 477, "loss": 0.5778, "lr": 2.2350376517557727e-05, "epoch": 1.742138364779874, "percentage": 58.07, "elapsed_time": "5:23:59", "remaining_time": "3:53:55"} +{"current_steps": 278, "total_steps": 477, "loss": 0.5786, "lr": 2.216840383063277e-05, "epoch": 1.748427672955975, "percentage": 58.28, "elapsed_time": "5:25:17", "remaining_time": "3:52:51"} +{"current_steps": 279, "total_steps": 477, "loss": 0.5877, "lr": 2.1986582993616926e-05, "epoch": 1.7547169811320755, "percentage": 58.49, "elapsed_time": "5:26:23", "remaining_time": "3:51:37"} +{"current_steps": 280, "total_steps": 477, "loss": 0.5419, "lr": 2.1804923757009884e-05, "epoch": 1.7610062893081762, "percentage": 58.7, "elapsed_time": "5:27:34", "remaining_time": "3:50:28"} +{"current_steps": 281, "total_steps": 477, "loss": 0.5418, "lr": 2.1623435862645204e-05, "epoch": 1.7672955974842768, "percentage": 58.91, "elapsed_time": "5:28:40", "remaining_time": "3:49:15"} +{"current_steps": 282, "total_steps": 477, "loss": 0.5487, "lr": 2.1442129043167874e-05, "epoch": 1.7735849056603774, "percentage": 59.12, "elapsed_time": "5:29:46", "remaining_time": "3:48:01"} +{"current_steps": 283, "total_steps": 477, "loss": 0.5317, "lr": 2.126101302151238e-05, "epoch": 1.779874213836478, "percentage": 59.33, "elapsed_time": "5:30:53", "remaining_time": "3:46:49"} +{"current_steps": 284, "total_steps": 477, "loss": 0.6046, "lr": 2.1080097510381298e-05, "epoch": 1.7861635220125787, "percentage": 59.54, "elapsed_time": "5:31:59", "remaining_time": "3:45:36"} +{"current_steps": 285, "total_steps": 477, "loss": 0.6541, "lr": 2.089939221172446e-05, "epoch": 1.7924528301886793, "percentage": 59.75, "elapsed_time": "5:33:11", "remaining_time": "3:44:27"} +{"current_steps": 286, "total_steps": 477, "loss": 0.5646, "lr": 2.07189068162186e-05, "epoch": 1.79874213836478, "percentage": 59.96, "elapsed_time": "5:34:22", "remaining_time": "3:43:18"} +{"current_steps": 287, "total_steps": 477, "loss": 0.5561, "lr": 2.0538651002747744e-05, "epoch": 1.8050314465408805, "percentage": 60.17, "elapsed_time": "5:35:36", "remaining_time": "3:42:10"} +{"current_steps": 288, "total_steps": 477, "loss": 0.6087, "lr": 2.0358634437884112e-05, "epoch": 1.8113207547169812, "percentage": 60.38, "elapsed_time": "5:36:38", "remaining_time": "3:40:54"} +{"current_steps": 289, "total_steps": 477, "loss": 0.5801, "lr": 2.0178866775369777e-05, "epoch": 1.8176100628930818, "percentage": 60.59, "elapsed_time": "5:37:45", "remaining_time": "3:39:43"} +{"current_steps": 290, "total_steps": 477, "loss": 0.6003, "lr": 1.9999357655598893e-05, "epoch": 1.8238993710691824, "percentage": 60.8, "elapsed_time": "5:39:04", "remaining_time": "3:38:38"} +{"current_steps": 291, "total_steps": 477, "loss": 0.5838, "lr": 1.9820116705100777e-05, "epoch": 1.830188679245283, "percentage": 61.01, "elapsed_time": "5:40:16", "remaining_time": "3:37:29"} +{"current_steps": 292, "total_steps": 477, "loss": 0.6054, "lr": 1.9641153536023644e-05, "epoch": 1.8364779874213837, "percentage": 61.22, "elapsed_time": "5:41:36", "remaining_time": "3:36:25"} +{"current_steps": 293, "total_steps": 477, "loss": 0.5515, "lr": 1.9462477745619108e-05, "epoch": 1.8427672955974843, "percentage": 61.43, "elapsed_time": "5:42:43", "remaining_time": "3:35:13"} +{"current_steps": 294, "total_steps": 477, "loss": 0.6225, "lr": 1.928409891572757e-05, "epoch": 1.849056603773585, "percentage": 61.64, "elapsed_time": "5:43:54", "remaining_time": "3:34:04"} +{"current_steps": 295, "total_steps": 477, "loss": 0.6214, "lr": 1.9106026612264316e-05, "epoch": 1.8553459119496856, "percentage": 61.84, "elapsed_time": "5:45:12", "remaining_time": "3:32:58"} +{"current_steps": 296, "total_steps": 477, "loss": 0.6164, "lr": 1.8928270384706584e-05, "epoch": 1.8616352201257862, "percentage": 62.05, "elapsed_time": "5:46:17", "remaining_time": "3:31:45"} +{"current_steps": 297, "total_steps": 477, "loss": 0.5533, "lr": 1.875083976558136e-05, "epoch": 1.8679245283018868, "percentage": 62.26, "elapsed_time": "5:47:21", "remaining_time": "3:30:31"} +{"current_steps": 298, "total_steps": 477, "loss": 0.6305, "lr": 1.8573744269954298e-05, "epoch": 1.8742138364779874, "percentage": 62.47, "elapsed_time": "5:48:34", "remaining_time": "3:29:22"} +{"current_steps": 299, "total_steps": 477, "loss": 0.574, "lr": 1.8396993394919372e-05, "epoch": 1.880503144654088, "percentage": 62.68, "elapsed_time": "5:49:51", "remaining_time": "3:28:16"} +{"current_steps": 300, "total_steps": 477, "loss": 0.7138, "lr": 1.8220596619089576e-05, "epoch": 1.8867924528301887, "percentage": 62.89, "elapsed_time": "5:50:56", "remaining_time": "3:27:03"} +{"current_steps": 301, "total_steps": 477, "loss": 0.6108, "lr": 1.8044563402088684e-05, "epoch": 1.8930817610062893, "percentage": 63.1, "elapsed_time": "5:52:03", "remaining_time": "3:25:51"} +{"current_steps": 302, "total_steps": 477, "loss": 0.546, "lr": 1.7868903184043887e-05, "epoch": 1.89937106918239, "percentage": 63.31, "elapsed_time": "5:53:09", "remaining_time": "3:24:38"} +{"current_steps": 303, "total_steps": 477, "loss": 0.5597, "lr": 1.7693625385079577e-05, "epoch": 1.9056603773584906, "percentage": 63.52, "elapsed_time": "5:54:24", "remaining_time": "3:23:31"} +{"current_steps": 304, "total_steps": 477, "loss": 0.6107, "lr": 1.7518739404812155e-05, "epoch": 1.9119496855345912, "percentage": 63.73, "elapsed_time": "5:55:31", "remaining_time": "3:22:19"} +{"current_steps": 305, "total_steps": 477, "loss": 0.5671, "lr": 1.7344254621846016e-05, "epoch": 1.9182389937106918, "percentage": 63.94, "elapsed_time": "5:56:45", "remaining_time": "3:21:11"} +{"current_steps": 306, "total_steps": 477, "loss": 0.5503, "lr": 1.7170180393270532e-05, "epoch": 1.9245283018867925, "percentage": 64.15, "elapsed_time": "5:57:57", "remaining_time": "3:20:01"} +{"current_steps": 307, "total_steps": 477, "loss": 0.4958, "lr": 1.699652605415828e-05, "epoch": 1.930817610062893, "percentage": 64.36, "elapsed_time": "5:59:01", "remaining_time": "3:18:48"} +{"current_steps": 308, "total_steps": 477, "loss": 0.58, "lr": 1.682330091706446e-05, "epoch": 1.9371069182389937, "percentage": 64.57, "elapsed_time": "6:00:07", "remaining_time": "3:17:36"} +{"current_steps": 309, "total_steps": 477, "loss": 0.5293, "lr": 1.6650514271527468e-05, "epoch": 1.9433962264150944, "percentage": 64.78, "elapsed_time": "6:01:16", "remaining_time": "3:16:25"} +{"current_steps": 310, "total_steps": 477, "loss": 0.5666, "lr": 1.647817538357072e-05, "epoch": 1.949685534591195, "percentage": 64.99, "elapsed_time": "6:02:19", "remaining_time": "3:15:11"} +{"current_steps": 311, "total_steps": 477, "loss": 0.5493, "lr": 1.630629349520576e-05, "epoch": 1.9559748427672956, "percentage": 65.2, "elapsed_time": "6:03:42", "remaining_time": "3:14:07"} +{"current_steps": 312, "total_steps": 477, "loss": 0.5516, "lr": 1.613487782393661e-05, "epoch": 1.9622641509433962, "percentage": 65.41, "elapsed_time": "6:05:03", "remaining_time": "3:13:03"} +{"current_steps": 313, "total_steps": 477, "loss": 0.5358, "lr": 1.5963937562265525e-05, "epoch": 1.9685534591194969, "percentage": 65.62, "elapsed_time": "6:06:13", "remaining_time": "3:11:53"} +{"current_steps": 314, "total_steps": 477, "loss": 0.5332, "lr": 1.5793481877199946e-05, "epoch": 1.9748427672955975, "percentage": 65.83, "elapsed_time": "6:07:18", "remaining_time": "3:10:40"} +{"current_steps": 315, "total_steps": 477, "loss": 0.5968, "lr": 1.5623519909760954e-05, "epoch": 1.9811320754716981, "percentage": 66.04, "elapsed_time": "6:08:21", "remaining_time": "3:09:26"} +{"current_steps": 316, "total_steps": 477, "loss": 0.6077, "lr": 1.5454060774493068e-05, "epoch": 1.9874213836477987, "percentage": 66.25, "elapsed_time": "6:09:27", "remaining_time": "3:08:14"} +{"current_steps": 317, "total_steps": 477, "loss": 0.5503, "lr": 1.528511355897543e-05, "epoch": 1.9937106918238994, "percentage": 66.46, "elapsed_time": "6:10:40", "remaining_time": "3:07:05"} +{"current_steps": 318, "total_steps": 477, "loss": 0.6122, "lr": 1.5116687323334467e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "6:11:51", "remaining_time": "3:05:55"} +{"current_steps": 319, "total_steps": 477, "loss": 0.5369, "lr": 1.4948791099758052e-05, "epoch": 2.006289308176101, "percentage": 66.88, "elapsed_time": "6:12:55", "remaining_time": "3:04:42"} +{"current_steps": 320, "total_steps": 477, "loss": 0.5291, "lr": 1.4781433892011131e-05, "epoch": 2.0125786163522013, "percentage": 67.09, "elapsed_time": "6:14:07", "remaining_time": "3:03:33"} +{"current_steps": 321, "total_steps": 477, "loss": 0.5378, "lr": 1.4614624674952842e-05, "epoch": 2.018867924528302, "percentage": 67.3, "elapsed_time": "6:15:12", "remaining_time": "3:02:20"} +{"current_steps": 322, "total_steps": 477, "loss": 0.5048, "lr": 1.4448372394055249e-05, "epoch": 2.0251572327044025, "percentage": 67.51, "elapsed_time": "6:16:24", "remaining_time": "3:01:11"} +{"current_steps": 323, "total_steps": 477, "loss": 0.5401, "lr": 1.4282685964923642e-05, "epoch": 2.0314465408805034, "percentage": 67.71, "elapsed_time": "6:17:32", "remaining_time": "3:00:00"} +{"current_steps": 324, "total_steps": 477, "loss": 0.5099, "lr": 1.4117574272818388e-05, "epoch": 2.0377358490566038, "percentage": 67.92, "elapsed_time": "6:18:42", "remaining_time": "2:58:49"} +{"current_steps": 325, "total_steps": 477, "loss": 0.4566, "lr": 1.3953046172178414e-05, "epoch": 2.0440251572327046, "percentage": 68.13, "elapsed_time": "6:19:47", "remaining_time": "2:57:37"} +{"current_steps": 326, "total_steps": 477, "loss": 0.4861, "lr": 1.378911048614647e-05, "epoch": 2.050314465408805, "percentage": 68.34, "elapsed_time": "6:21:08", "remaining_time": "2:56:32"} +{"current_steps": 327, "total_steps": 477, "loss": 0.5896, "lr": 1.3625776006095881e-05, "epoch": 2.056603773584906, "percentage": 68.55, "elapsed_time": "6:22:10", "remaining_time": "2:55:18"} +{"current_steps": 328, "total_steps": 477, "loss": 0.5174, "lr": 1.3463051491159096e-05, "epoch": 2.0628930817610063, "percentage": 68.76, "elapsed_time": "6:23:25", "remaining_time": "2:54:10"} +{"current_steps": 329, "total_steps": 477, "loss": 0.5042, "lr": 1.3300945667758014e-05, "epoch": 2.069182389937107, "percentage": 68.97, "elapsed_time": "6:24:31", "remaining_time": "2:52:58"} +{"current_steps": 330, "total_steps": 477, "loss": 0.5457, "lr": 1.3139467229135999e-05, "epoch": 2.0754716981132075, "percentage": 69.18, "elapsed_time": "6:25:39", "remaining_time": "2:51:47"} +{"current_steps": 331, "total_steps": 477, "loss": 0.5299, "lr": 1.2978624834891628e-05, "epoch": 2.0817610062893084, "percentage": 69.39, "elapsed_time": "6:26:44", "remaining_time": "2:50:35"} +{"current_steps": 332, "total_steps": 477, "loss": 0.512, "lr": 1.281842711051438e-05, "epoch": 2.088050314465409, "percentage": 69.6, "elapsed_time": "6:27:51", "remaining_time": "2:49:23"} +{"current_steps": 333, "total_steps": 477, "loss": 0.5131, "lr": 1.2658882646922034e-05, "epoch": 2.0943396226415096, "percentage": 69.81, "elapsed_time": "6:29:02", "remaining_time": "2:48:14"} +{"current_steps": 334, "total_steps": 477, "loss": 0.5383, "lr": 1.2500000000000006e-05, "epoch": 2.10062893081761, "percentage": 70.02, "elapsed_time": "6:30:08", "remaining_time": "2:47:02"} +{"current_steps": 335, "total_steps": 477, "loss": 0.5715, "lr": 1.2341787690142437e-05, "epoch": 2.106918238993711, "percentage": 70.23, "elapsed_time": "6:31:21", "remaining_time": "2:45:53"} +{"current_steps": 336, "total_steps": 477, "loss": 0.548, "lr": 1.2184254201795365e-05, "epoch": 2.1132075471698113, "percentage": 70.44, "elapsed_time": "6:32:34", "remaining_time": "2:44:44"} +{"current_steps": 337, "total_steps": 477, "loss": 0.4989, "lr": 1.2027407983001681e-05, "epoch": 2.119496855345912, "percentage": 70.65, "elapsed_time": "6:33:41", "remaining_time": "2:43:33"} +{"current_steps": 338, "total_steps": 477, "loss": 0.5775, "lr": 1.1871257444948098e-05, "epoch": 2.1257861635220126, "percentage": 70.86, "elapsed_time": "6:34:49", "remaining_time": "2:42:22"} +{"current_steps": 339, "total_steps": 477, "loss": 0.5642, "lr": 1.1715810961514073e-05, "epoch": 2.1320754716981134, "percentage": 71.07, "elapsed_time": "6:36:05", "remaining_time": "2:41:14"} +{"current_steps": 340, "total_steps": 477, "loss": 0.571, "lr": 1.1561076868822756e-05, "epoch": 2.138364779874214, "percentage": 71.28, "elapsed_time": "6:37:19", "remaining_time": "2:40:05"} +{"current_steps": 341, "total_steps": 477, "loss": 0.4891, "lr": 1.1407063464793966e-05, "epoch": 2.1446540880503147, "percentage": 71.49, "elapsed_time": "6:38:31", "remaining_time": "2:38:56"} +{"current_steps": 342, "total_steps": 477, "loss": 0.5196, "lr": 1.1253779008699131e-05, "epoch": 2.150943396226415, "percentage": 71.7, "elapsed_time": "6:39:41", "remaining_time": "2:37:46"} +{"current_steps": 343, "total_steps": 477, "loss": 0.479, "lr": 1.1101231720718442e-05, "epoch": 2.157232704402516, "percentage": 71.91, "elapsed_time": "6:40:49", "remaining_time": "2:36:35"} +{"current_steps": 344, "total_steps": 477, "loss": 0.4888, "lr": 1.09494297815e-05, "epoch": 2.1635220125786163, "percentage": 72.12, "elapsed_time": "6:41:59", "remaining_time": "2:35:25"} +{"current_steps": 345, "total_steps": 477, "loss": 0.5119, "lr": 1.0798381331721109e-05, "epoch": 2.169811320754717, "percentage": 72.33, "elapsed_time": "6:43:01", "remaining_time": "2:34:11"} +{"current_steps": 346, "total_steps": 477, "loss": 0.497, "lr": 1.0648094471651724e-05, "epoch": 2.1761006289308176, "percentage": 72.54, "elapsed_time": "6:44:13", "remaining_time": "2:33:02"} +{"current_steps": 347, "total_steps": 477, "loss": 0.5013, "lr": 1.049857726072005e-05, "epoch": 2.1823899371069184, "percentage": 72.75, "elapsed_time": "6:45:22", "remaining_time": "2:31:52"} +{"current_steps": 348, "total_steps": 477, "loss": 0.6453, "lr": 1.034983771708035e-05, "epoch": 2.188679245283019, "percentage": 72.96, "elapsed_time": "6:46:32", "remaining_time": "2:30:42"} +{"current_steps": 349, "total_steps": 477, "loss": 0.5044, "lr": 1.020188381718295e-05, "epoch": 2.1949685534591197, "percentage": 73.17, "elapsed_time": "6:47:45", "remaining_time": "2:29:32"} +{"current_steps": 350, "total_steps": 477, "loss": 0.594, "lr": 1.0054723495346482e-05, "epoch": 2.20125786163522, "percentage": 73.38, "elapsed_time": "6:48:53", "remaining_time": "2:28:21"} +{"current_steps": 351, "total_steps": 477, "loss": 0.5059, "lr": 9.908364643332399e-06, "epoch": 2.207547169811321, "percentage": 73.58, "elapsed_time": "6:50:13", "remaining_time": "2:27:15"} +{"current_steps": 352, "total_steps": 477, "loss": 0.5069, "lr": 9.762815109921761e-06, "epoch": 2.2138364779874213, "percentage": 73.79, "elapsed_time": "6:51:28", "remaining_time": "2:26:07"} +{"current_steps": 353, "total_steps": 477, "loss": 0.5232, "lr": 9.618082700494319e-06, "epoch": 2.220125786163522, "percentage": 74.0, "elapsed_time": "6:52:36", "remaining_time": "2:24:56"} +{"current_steps": 354, "total_steps": 477, "loss": 0.5466, "lr": 9.474175176609956e-06, "epoch": 2.2264150943396226, "percentage": 74.21, "elapsed_time": "6:54:01", "remaining_time": "2:23:51"} +{"current_steps": 355, "total_steps": 477, "loss": 0.4564, "lr": 9.331100255592437e-06, "epoch": 2.2327044025157234, "percentage": 74.42, "elapsed_time": "6:55:08", "remaining_time": "2:22:39"} +{"current_steps": 356, "total_steps": 477, "loss": 0.5621, "lr": 9.18886561011557e-06, "epoch": 2.238993710691824, "percentage": 74.63, "elapsed_time": "6:56:15", "remaining_time": "2:21:29"} +{"current_steps": 357, "total_steps": 477, "loss": 0.4575, "lr": 9.047478867791732e-06, "epoch": 2.2452830188679247, "percentage": 74.84, "elapsed_time": "6:57:27", "remaining_time": "2:20:19"} +{"current_steps": 358, "total_steps": 477, "loss": 0.4867, "lr": 8.906947610762825e-06, "epoch": 2.251572327044025, "percentage": 75.05, "elapsed_time": "6:58:35", "remaining_time": "2:19:08"} +{"current_steps": 359, "total_steps": 477, "loss": 0.5453, "lr": 8.767279375293672e-06, "epoch": 2.257861635220126, "percentage": 75.26, "elapsed_time": "6:59:47", "remaining_time": "2:17:58"} +{"current_steps": 360, "total_steps": 477, "loss": 0.5465, "lr": 8.628481651367876e-06, "epoch": 2.2641509433962264, "percentage": 75.47, "elapsed_time": "7:00:52", "remaining_time": "2:16:47"} +{"current_steps": 361, "total_steps": 477, "loss": 0.5327, "lr": 8.490561882286136e-06, "epoch": 2.270440251572327, "percentage": 75.68, "elapsed_time": "7:02:05", "remaining_time": "2:15:37"} +{"current_steps": 362, "total_steps": 477, "loss": 0.4759, "lr": 8.353527464267104e-06, "epoch": 2.2767295597484276, "percentage": 75.89, "elapsed_time": "7:03:09", "remaining_time": "2:14:25"} +{"current_steps": 363, "total_steps": 477, "loss": 0.5186, "lr": 8.217385746050742e-06, "epoch": 2.2830188679245285, "percentage": 76.1, "elapsed_time": "7:04:20", "remaining_time": "2:13:15"} +{"current_steps": 364, "total_steps": 477, "loss": 0.5786, "lr": 8.082144028504233e-06, "epoch": 2.289308176100629, "percentage": 76.31, "elapsed_time": "7:05:30", "remaining_time": "2:12:05"} +{"current_steps": 365, "total_steps": 477, "loss": 0.4792, "lr": 7.947809564230445e-06, "epoch": 2.2955974842767297, "percentage": 76.52, "elapsed_time": "7:06:39", "remaining_time": "2:10:55"} +{"current_steps": 366, "total_steps": 477, "loss": 0.5567, "lr": 7.814389557179017e-06, "epoch": 2.30188679245283, "percentage": 76.73, "elapsed_time": "7:07:50", "remaining_time": "2:09:45"} +{"current_steps": 367, "total_steps": 477, "loss": 0.5227, "lr": 7.681891162260015e-06, "epoch": 2.308176100628931, "percentage": 76.94, "elapsed_time": "7:08:57", "remaining_time": "2:08:34"} +{"current_steps": 368, "total_steps": 477, "loss": 0.5339, "lr": 7.5503214849602516e-06, "epoch": 2.3144654088050314, "percentage": 77.15, "elapsed_time": "7:10:08", "remaining_time": "2:07:24"} +{"current_steps": 369, "total_steps": 477, "loss": 0.4857, "lr": 7.419687580962223e-06, "epoch": 2.3207547169811322, "percentage": 77.36, "elapsed_time": "7:11:17", "remaining_time": "2:06:13"} +{"current_steps": 370, "total_steps": 477, "loss": 0.4588, "lr": 7.289996455765749e-06, "epoch": 2.3270440251572326, "percentage": 77.57, "elapsed_time": "7:12:27", "remaining_time": "2:05:03"} +{"current_steps": 371, "total_steps": 477, "loss": 0.4676, "lr": 7.161255064312283e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "7:13:46", "remaining_time": "2:03:56"} +{"current_steps": 372, "total_steps": 477, "loss": 0.5441, "lr": 7.033470310611945e-06, "epoch": 2.339622641509434, "percentage": 77.99, "elapsed_time": "7:14:51", "remaining_time": "2:02:44"} +{"current_steps": 373, "total_steps": 477, "loss": 0.5144, "lr": 6.906649047373246e-06, "epoch": 2.3459119496855347, "percentage": 78.2, "elapsed_time": "7:15:57", "remaining_time": "2:01:33"} +{"current_steps": 374, "total_steps": 477, "loss": 0.454, "lr": 6.780798075635675e-06, "epoch": 2.352201257861635, "percentage": 78.41, "elapsed_time": "7:17:05", "remaining_time": "2:00:22"} +{"current_steps": 375, "total_steps": 477, "loss": 0.4471, "lr": 6.655924144404907e-06, "epoch": 2.358490566037736, "percentage": 78.62, "elapsed_time": "7:18:20", "remaining_time": "1:59:13"} +{"current_steps": 376, "total_steps": 477, "loss": 0.525, "lr": 6.532033950290886e-06, "epoch": 2.3647798742138364, "percentage": 78.83, "elapsed_time": "7:19:26", "remaining_time": "1:58:02"} +{"current_steps": 377, "total_steps": 477, "loss": 0.5181, "lr": 6.409134137148737e-06, "epoch": 2.3710691823899372, "percentage": 79.04, "elapsed_time": "7:20:40", "remaining_time": "1:56:53"} +{"current_steps": 378, "total_steps": 477, "loss": 0.5105, "lr": 6.28723129572247e-06, "epoch": 2.3773584905660377, "percentage": 79.25, "elapsed_time": "7:21:52", "remaining_time": "1:55:43"} +{"current_steps": 379, "total_steps": 477, "loss": 0.4859, "lr": 6.166331963291519e-06, "epoch": 2.3836477987421385, "percentage": 79.45, "elapsed_time": "7:23:05", "remaining_time": "1:54:34"} +{"current_steps": 380, "total_steps": 477, "loss": 0.5136, "lr": 6.046442623320145e-06, "epoch": 2.389937106918239, "percentage": 79.66, "elapsed_time": "7:24:17", "remaining_time": "1:53:24"} +{"current_steps": 381, "total_steps": 477, "loss": 0.4837, "lr": 5.927569705109828e-06, "epoch": 2.3962264150943398, "percentage": 79.87, "elapsed_time": "7:25:24", "remaining_time": "1:52:13"} +{"current_steps": 382, "total_steps": 477, "loss": 0.4962, "lr": 5.809719583454415e-06, "epoch": 2.40251572327044, "percentage": 80.08, "elapsed_time": "7:26:28", "remaining_time": "1:51:02"} +{"current_steps": 383, "total_steps": 477, "loss": 0.5138, "lr": 5.692898578298253e-06, "epoch": 2.408805031446541, "percentage": 80.29, "elapsed_time": "7:27:38", "remaining_time": "1:49:51"} +{"current_steps": 384, "total_steps": 477, "loss": 0.5097, "lr": 5.577112954397321e-06, "epoch": 2.4150943396226414, "percentage": 80.5, "elapsed_time": "7:28:47", "remaining_time": "1:48:41"} +{"current_steps": 385, "total_steps": 477, "loss": 0.5655, "lr": 5.462368920983249e-06, "epoch": 2.4213836477987423, "percentage": 80.71, "elapsed_time": "7:29:57", "remaining_time": "1:47:31"} +{"current_steps": 386, "total_steps": 477, "loss": 0.511, "lr": 5.348672631430318e-06, "epoch": 2.4276729559748427, "percentage": 80.92, "elapsed_time": "7:31:05", "remaining_time": "1:46:20"} +{"current_steps": 387, "total_steps": 477, "loss": 0.4494, "lr": 5.236030182925475e-06, "epoch": 2.4339622641509435, "percentage": 81.13, "elapsed_time": "7:32:12", "remaining_time": "1:45:09"} +{"current_steps": 388, "total_steps": 477, "loss": 0.4407, "lr": 5.124447616141381e-06, "epoch": 2.440251572327044, "percentage": 81.34, "elapsed_time": "7:33:16", "remaining_time": "1:43:58"} +{"current_steps": 389, "total_steps": 477, "loss": 0.5424, "lr": 5.013930914912476e-06, "epoch": 2.4465408805031448, "percentage": 81.55, "elapsed_time": "7:34:24", "remaining_time": "1:42:47"} +{"current_steps": 390, "total_steps": 477, "loss": 0.5222, "lr": 4.9044860059140275e-06, "epoch": 2.452830188679245, "percentage": 81.76, "elapsed_time": "7:35:28", "remaining_time": "1:41:36"} +{"current_steps": 391, "total_steps": 477, "loss": 0.5181, "lr": 4.796118758344354e-06, "epoch": 2.459119496855346, "percentage": 81.97, "elapsed_time": "7:36:35", "remaining_time": "1:40:25"} +{"current_steps": 392, "total_steps": 477, "loss": 0.5849, "lr": 4.6888349836100825e-06, "epoch": 2.4654088050314464, "percentage": 82.18, "elapsed_time": "7:37:45", "remaining_time": "1:39:15"} +{"current_steps": 393, "total_steps": 477, "loss": 0.4938, "lr": 4.58264043501446e-06, "epoch": 2.4716981132075473, "percentage": 82.39, "elapsed_time": "7:38:51", "remaining_time": "1:38:04"} +{"current_steps": 394, "total_steps": 477, "loss": 0.4862, "lr": 4.477540807448832e-06, "epoch": 2.4779874213836477, "percentage": 82.6, "elapsed_time": "7:39:53", "remaining_time": "1:36:52"} +{"current_steps": 395, "total_steps": 477, "loss": 0.5753, "lr": 4.373541737087264e-06, "epoch": 2.4842767295597485, "percentage": 82.81, "elapsed_time": "7:41:02", "remaining_time": "1:35:42"} +{"current_steps": 396, "total_steps": 477, "loss": 0.555, "lr": 4.270648801084296e-06, "epoch": 2.490566037735849, "percentage": 83.02, "elapsed_time": "7:42:12", "remaining_time": "1:34:32"} +{"current_steps": 397, "total_steps": 477, "loss": 0.6513, "lr": 4.1688675172758064e-06, "epoch": 2.49685534591195, "percentage": 83.23, "elapsed_time": "7:43:19", "remaining_time": "1:33:21"} +{"current_steps": 398, "total_steps": 477, "loss": 0.4985, "lr": 4.068203343883159e-06, "epoch": 2.50314465408805, "percentage": 83.44, "elapsed_time": "7:44:21", "remaining_time": "1:32:10"} +{"current_steps": 399, "total_steps": 477, "loss": 0.4736, "lr": 3.968661679220468e-06, "epoch": 2.509433962264151, "percentage": 83.65, "elapsed_time": "7:45:27", "remaining_time": "1:30:59"} +{"current_steps": 400, "total_steps": 477, "loss": 0.567, "lr": 3.8702478614051355e-06, "epoch": 2.5157232704402515, "percentage": 83.86, "elapsed_time": "7:46:49", "remaining_time": "1:29:51"} +{"current_steps": 401, "total_steps": 477, "loss": 0.4567, "lr": 3.772967168071517e-06, "epoch": 2.5220125786163523, "percentage": 84.07, "elapsed_time": "7:48:05", "remaining_time": "1:28:42"} +{"current_steps": 402, "total_steps": 477, "loss": 0.5228, "lr": 3.6768248160879787e-06, "epoch": 2.5283018867924527, "percentage": 84.28, "elapsed_time": "7:49:19", "remaining_time": "1:27:33"} +{"current_steps": 403, "total_steps": 477, "loss": 0.5499, "lr": 3.5818259612770744e-06, "epoch": 2.5345911949685536, "percentage": 84.49, "elapsed_time": "7:50:28", "remaining_time": "1:26:23"} +{"current_steps": 404, "total_steps": 477, "loss": 0.4901, "lr": 3.487975698139084e-06, "epoch": 2.540880503144654, "percentage": 84.7, "elapsed_time": "7:51:39", "remaining_time": "1:25:13"} +{"current_steps": 405, "total_steps": 477, "loss": 0.5253, "lr": 3.3952790595787987e-06, "epoch": 2.547169811320755, "percentage": 84.91, "elapsed_time": "7:52:43", "remaining_time": "1:24:02"} +{"current_steps": 406, "total_steps": 477, "loss": 0.5036, "lr": 3.3037410166356143e-06, "epoch": 2.5534591194968552, "percentage": 85.12, "elapsed_time": "7:53:49", "remaining_time": "1:22:51"} +{"current_steps": 407, "total_steps": 477, "loss": 0.5155, "lr": 3.2133664782169948e-06, "epoch": 2.559748427672956, "percentage": 85.32, "elapsed_time": "7:54:55", "remaining_time": "1:21:40"} +{"current_steps": 408, "total_steps": 477, "loss": 0.4473, "lr": 3.1241602908351404e-06, "epoch": 2.5660377358490565, "percentage": 85.53, "elapsed_time": "7:56:01", "remaining_time": "1:20:30"} +{"current_steps": 409, "total_steps": 477, "loss": 0.5926, "lr": 3.036127238347164e-06, "epoch": 2.5723270440251573, "percentage": 85.74, "elapsed_time": "7:57:14", "remaining_time": "1:19:20"} +{"current_steps": 410, "total_steps": 477, "loss": 0.4606, "lr": 2.9492720416985e-06, "epoch": 2.5786163522012577, "percentage": 85.95, "elapsed_time": "7:58:24", "remaining_time": "1:18:10"} +{"current_steps": 411, "total_steps": 477, "loss": 0.5701, "lr": 2.8635993586697553e-06, "epoch": 2.5849056603773586, "percentage": 86.16, "elapsed_time": "7:59:41", "remaining_time": "1:17:01"} +{"current_steps": 412, "total_steps": 477, "loss": 0.506, "lr": 2.779113783626916e-06, "epoch": 2.591194968553459, "percentage": 86.37, "elapsed_time": "8:00:41", "remaining_time": "1:15:50"} +{"current_steps": 413, "total_steps": 477, "loss": 0.5624, "lr": 2.6958198472749717e-06, "epoch": 2.59748427672956, "percentage": 86.58, "elapsed_time": "8:01:57", "remaining_time": "1:14:41"} +{"current_steps": 414, "total_steps": 477, "loss": 0.5052, "lr": 2.6137220164149435e-06, "epoch": 2.6037735849056602, "percentage": 86.79, "elapsed_time": "8:03:03", "remaining_time": "1:13:30"} +{"current_steps": 415, "total_steps": 477, "loss": 0.5104, "lr": 2.5328246937043526e-06, "epoch": 2.610062893081761, "percentage": 87.0, "elapsed_time": "8:04:13", "remaining_time": "1:12:20"} +{"current_steps": 416, "total_steps": 477, "loss": 0.5077, "lr": 2.4531322174210975e-06, "epoch": 2.6163522012578615, "percentage": 87.21, "elapsed_time": "8:05:27", "remaining_time": "1:11:11"} +{"current_steps": 417, "total_steps": 477, "loss": 0.5086, "lr": 2.37464886123083e-06, "epoch": 2.6226415094339623, "percentage": 87.42, "elapsed_time": "8:06:36", "remaining_time": "1:10:00"} +{"current_steps": 418, "total_steps": 477, "loss": 0.5189, "lr": 2.2973788339577613e-06, "epoch": 2.6289308176100628, "percentage": 87.63, "elapsed_time": "8:07:48", "remaining_time": "1:08:51"} +{"current_steps": 419, "total_steps": 477, "loss": 0.4974, "lr": 2.2213262793589484e-06, "epoch": 2.6352201257861636, "percentage": 87.84, "elapsed_time": "8:08:50", "remaining_time": "1:07:40"} +{"current_steps": 420, "total_steps": 477, "loss": 0.5648, "lr": 2.1464952759020855e-06, "epoch": 2.641509433962264, "percentage": 88.05, "elapsed_time": "8:10:00", "remaining_time": "1:06:30"} +{"current_steps": 421, "total_steps": 477, "loss": 0.5149, "lr": 2.0728898365467903e-06, "epoch": 2.647798742138365, "percentage": 88.26, "elapsed_time": "8:11:14", "remaining_time": "1:05:20"} +{"current_steps": 422, "total_steps": 477, "loss": 0.472, "lr": 2.0005139085293945e-06, "epoch": 2.6540880503144653, "percentage": 88.47, "elapsed_time": "8:12:19", "remaining_time": "1:04:09"} +{"current_steps": 423, "total_steps": 477, "loss": 0.5368, "lr": 1.9293713731512673e-06, "epoch": 2.660377358490566, "percentage": 88.68, "elapsed_time": "8:13:37", "remaining_time": "1:03:01"} +{"current_steps": 424, "total_steps": 477, "loss": 0.4948, "lr": 1.8594660455706763e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "8:14:48", "remaining_time": "1:01:51"} +{"current_steps": 425, "total_steps": 477, "loss": 0.5213, "lr": 1.790801674598186e-06, "epoch": 2.6729559748427674, "percentage": 89.1, "elapsed_time": "8:16:03", "remaining_time": "1:00:41"} +{"current_steps": 426, "total_steps": 477, "loss": 0.6128, "lr": 1.7233819424956248e-06, "epoch": 2.6792452830188678, "percentage": 89.31, "elapsed_time": "8:17:06", "remaining_time": "0:59:30"} +{"current_steps": 427, "total_steps": 477, "loss": 0.5228, "lr": 1.6572104647786247e-06, "epoch": 2.6855345911949686, "percentage": 89.52, "elapsed_time": "8:18:19", "remaining_time": "0:58:21"} +{"current_steps": 428, "total_steps": 477, "loss": 0.4266, "lr": 1.5922907900227018e-06, "epoch": 2.691823899371069, "percentage": 89.73, "elapsed_time": "8:19:31", "remaining_time": "0:57:11"} +{"current_steps": 429, "total_steps": 477, "loss": 0.476, "lr": 1.5286263996730026e-06, "epoch": 2.69811320754717, "percentage": 89.94, "elapsed_time": "8:20:39", "remaining_time": "0:56:01"} +{"current_steps": 430, "total_steps": 477, "loss": 0.5145, "lr": 1.4662207078575684e-06, "epoch": 2.7044025157232703, "percentage": 90.15, "elapsed_time": "8:21:57", "remaining_time": "0:54:51"} +{"current_steps": 431, "total_steps": 477, "loss": 0.5546, "lr": 1.40507706120426e-06, "epoch": 2.710691823899371, "percentage": 90.36, "elapsed_time": "8:23:06", "remaining_time": "0:53:41"} +{"current_steps": 432, "total_steps": 477, "loss": 0.4598, "lr": 1.3451987386612851e-06, "epoch": 2.7169811320754715, "percentage": 90.57, "elapsed_time": "8:24:16", "remaining_time": "0:52:31"} +{"current_steps": 433, "total_steps": 477, "loss": 0.5322, "lr": 1.286588951321363e-06, "epoch": 2.7232704402515724, "percentage": 90.78, "elapsed_time": "8:25:30", "remaining_time": "0:51:22"} +{"current_steps": 434, "total_steps": 477, "loss": 0.5306, "lr": 1.2292508422495158e-06, "epoch": 2.729559748427673, "percentage": 90.99, "elapsed_time": "8:26:39", "remaining_time": "0:50:11"} +{"current_steps": 435, "total_steps": 477, "loss": 0.5109, "lr": 1.1731874863145143e-06, "epoch": 2.7358490566037736, "percentage": 91.19, "elapsed_time": "8:27:59", "remaining_time": "0:49:02"} +{"current_steps": 436, "total_steps": 477, "loss": 0.4579, "lr": 1.1184018900240011e-06, "epoch": 2.742138364779874, "percentage": 91.4, "elapsed_time": "8:29:04", "remaining_time": "0:47:52"} +{"current_steps": 437, "total_steps": 477, "loss": 0.4888, "lr": 1.06489699136324e-06, "epoch": 2.748427672955975, "percentage": 91.61, "elapsed_time": "8:30:14", "remaining_time": "0:46:42"} +{"current_steps": 438, "total_steps": 477, "loss": 0.5225, "lr": 1.0126756596375686e-06, "epoch": 2.7547169811320753, "percentage": 91.82, "elapsed_time": "8:31:22", "remaining_time": "0:45:31"} +{"current_steps": 439, "total_steps": 477, "loss": 0.5241, "lr": 9.617406953185138e-07, "epoch": 2.761006289308176, "percentage": 92.03, "elapsed_time": "8:32:34", "remaining_time": "0:44:22"} +{"current_steps": 440, "total_steps": 477, "loss": 0.4887, "lr": 9.120948298936421e-07, "epoch": 2.767295597484277, "percentage": 92.24, "elapsed_time": "8:33:50", "remaining_time": "0:43:12"} +{"current_steps": 441, "total_steps": 477, "loss": 0.4912, "lr": 8.637407257200497e-07, "epoch": 2.7735849056603774, "percentage": 92.45, "elapsed_time": "8:34:54", "remaining_time": "0:42:02"} +{"current_steps": 442, "total_steps": 477, "loss": 0.5405, "lr": 8.166809758815896e-07, "epoch": 2.779874213836478, "percentage": 92.66, "elapsed_time": "8:36:01", "remaining_time": "0:40:51"} +{"current_steps": 443, "total_steps": 477, "loss": 0.5058, "lr": 7.709181040498254e-07, "epoch": 2.7861635220125787, "percentage": 92.87, "elapsed_time": "8:37:13", "remaining_time": "0:39:41"} +{"current_steps": 444, "total_steps": 477, "loss": 0.5572, "lr": 7.264545643486997e-07, "epoch": 2.7924528301886795, "percentage": 93.08, "elapsed_time": "8:38:20", "remaining_time": "0:38:31"} +{"current_steps": 445, "total_steps": 477, "loss": 0.5118, "lr": 6.832927412229018e-07, "epoch": 2.79874213836478, "percentage": 93.29, "elapsed_time": "8:39:31", "remaining_time": "0:37:21"} +{"current_steps": 446, "total_steps": 477, "loss": 0.536, "lr": 6.41434949310013e-07, "epoch": 2.8050314465408803, "percentage": 93.5, "elapsed_time": "8:40:55", "remaining_time": "0:36:12"} +{"current_steps": 447, "total_steps": 477, "loss": 0.5397, "lr": 6.008834333163876e-07, "epoch": 2.811320754716981, "percentage": 93.71, "elapsed_time": "8:42:11", "remaining_time": "0:35:02"} +{"current_steps": 448, "total_steps": 477, "loss": 0.4516, "lr": 5.616403678967624e-07, "epoch": 2.817610062893082, "percentage": 93.92, "elapsed_time": "8:43:24", "remaining_time": "0:33:52"} +{"current_steps": 449, "total_steps": 477, "loss": 0.5106, "lr": 5.237078575376336e-07, "epoch": 2.8238993710691824, "percentage": 94.13, "elapsed_time": "8:44:36", "remaining_time": "0:32:42"} +{"current_steps": 450, "total_steps": 477, "loss": 0.5153, "lr": 4.870879364444109e-07, "epoch": 2.830188679245283, "percentage": 94.34, "elapsed_time": "8:45:49", "remaining_time": "0:31:32"} +{"current_steps": 451, "total_steps": 477, "loss": 0.5075, "lr": 4.517825684323324e-07, "epoch": 2.8364779874213837, "percentage": 94.55, "elapsed_time": "8:47:00", "remaining_time": "0:30:22"} +{"current_steps": 452, "total_steps": 477, "loss": 0.5354, "lr": 4.1779364682113796e-07, "epoch": 2.8427672955974845, "percentage": 94.76, "elapsed_time": "8:48:11", "remaining_time": "0:29:12"} +{"current_steps": 453, "total_steps": 477, "loss": 0.5468, "lr": 3.851229943335394e-07, "epoch": 2.849056603773585, "percentage": 94.97, "elapsed_time": "8:49:29", "remaining_time": "0:28:03"} +{"current_steps": 454, "total_steps": 477, "loss": 0.4799, "lr": 3.537723629974815e-07, "epoch": 2.8553459119496853, "percentage": 95.18, "elapsed_time": "8:50:30", "remaining_time": "0:26:52"} +{"current_steps": 455, "total_steps": 477, "loss": 0.5604, "lr": 3.237434340521789e-07, "epoch": 2.861635220125786, "percentage": 95.39, "elapsed_time": "8:51:34", "remaining_time": "0:25:42"} +{"current_steps": 456, "total_steps": 477, "loss": 0.4958, "lr": 2.9503781785795713e-07, "epoch": 2.867924528301887, "percentage": 95.6, "elapsed_time": "8:52:46", "remaining_time": "0:24:32"} +{"current_steps": 457, "total_steps": 477, "loss": 0.551, "lr": 2.6765705380989437e-07, "epoch": 2.8742138364779874, "percentage": 95.81, "elapsed_time": "8:53:54", "remaining_time": "0:23:21"} +{"current_steps": 458, "total_steps": 477, "loss": 0.5316, "lr": 2.416026102552732e-07, "epoch": 2.880503144654088, "percentage": 96.02, "elapsed_time": "8:54:58", "remaining_time": "0:22:11"} +{"current_steps": 459, "total_steps": 477, "loss": 0.5416, "lr": 2.168758844148272e-07, "epoch": 2.8867924528301887, "percentage": 96.23, "elapsed_time": "8:56:19", "remaining_time": "0:21:01"} +{"current_steps": 460, "total_steps": 477, "loss": 0.5319, "lr": 1.93478202307823e-07, "epoch": 2.8930817610062896, "percentage": 96.44, "elapsed_time": "8:57:25", "remaining_time": "0:19:51"} +{"current_steps": 461, "total_steps": 477, "loss": 0.5208, "lr": 1.7141081868094212e-07, "epoch": 2.89937106918239, "percentage": 96.65, "elapsed_time": "8:58:31", "remaining_time": "0:18:41"} +{"current_steps": 462, "total_steps": 477, "loss": 0.5133, "lr": 1.5067491694100154e-07, "epoch": 2.9056603773584904, "percentage": 96.86, "elapsed_time": "8:59:42", "remaining_time": "0:17:31"} +{"current_steps": 463, "total_steps": 477, "loss": 0.5107, "lr": 1.3127160909147672e-07, "epoch": 2.911949685534591, "percentage": 97.06, "elapsed_time": "9:00:58", "remaining_time": "0:16:21"} +{"current_steps": 464, "total_steps": 477, "loss": 0.5842, "lr": 1.1320193567288529e-07, "epoch": 2.918238993710692, "percentage": 97.27, "elapsed_time": "9:01:59", "remaining_time": "0:15:11"} +{"current_steps": 465, "total_steps": 477, "loss": 0.5275, "lr": 9.646686570697061e-08, "epoch": 2.9245283018867925, "percentage": 97.48, "elapsed_time": "9:03:07", "remaining_time": "0:14:00"} +{"current_steps": 466, "total_steps": 477, "loss": 0.4815, "lr": 8.106729664475176e-08, "epoch": 2.930817610062893, "percentage": 97.69, "elapsed_time": "9:04:09", "remaining_time": "0:12:50"} +{"current_steps": 467, "total_steps": 477, "loss": 0.4802, "lr": 6.700405431837587e-08, "epoch": 2.9371069182389937, "percentage": 97.9, "elapsed_time": "9:05:19", "remaining_time": "0:11:40"} +{"current_steps": 468, "total_steps": 477, "loss": 0.5044, "lr": 5.4277892896853476e-08, "epoch": 2.9433962264150946, "percentage": 98.11, "elapsed_time": "9:06:28", "remaining_time": "0:10:30"} +{"current_steps": 469, "total_steps": 477, "loss": 0.5601, "lr": 4.2889494845599344e-08, "epoch": 2.949685534591195, "percentage": 98.32, "elapsed_time": "9:07:40", "remaining_time": "0:09:20"} +{"current_steps": 470, "total_steps": 477, "loss": 0.4279, "lr": 3.283947088983663e-08, "epoch": 2.9559748427672954, "percentage": 98.53, "elapsed_time": "9:08:54", "remaining_time": "0:08:10"} +{"current_steps": 471, "total_steps": 477, "loss": 0.483, "lr": 2.4128359981850924e-08, "epoch": 2.9622641509433962, "percentage": 98.74, "elapsed_time": "9:09:56", "remaining_time": "0:07:00"} +{"current_steps": 472, "total_steps": 477, "loss": 0.5921, "lr": 1.6756629272085545e-08, "epoch": 2.968553459119497, "percentage": 98.95, "elapsed_time": "9:11:01", "remaining_time": "0:05:50"} +{"current_steps": 473, "total_steps": 477, "loss": 0.4751, "lr": 1.0724674084083841e-08, "epoch": 2.9748427672955975, "percentage": 99.16, "elapsed_time": "9:12:20", "remaining_time": "0:04:40"} +{"current_steps": 474, "total_steps": 477, "loss": 0.4994, "lr": 6.032817893297793e-09, "epoch": 2.981132075471698, "percentage": 99.37, "elapsed_time": "9:13:37", "remaining_time": "0:03:30"} +{"current_steps": 475, "total_steps": 477, "loss": 0.5308, "lr": 2.681312309735229e-09, "epoch": 2.9874213836477987, "percentage": 99.58, "elapsed_time": "9:14:49", "remaining_time": "0:02:20"} +{"current_steps": 476, "total_steps": 477, "loss": 0.5177, "lr": 6.703370644706164e-10, "epoch": 2.9937106918238996, "percentage": 99.79, "elapsed_time": "9:16:00", "remaining_time": "0:01:10"} +{"current_steps": 477, "total_steps": 477, "loss": 0.4149, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "9:17:00", "remaining_time": "0:00:00"} +{"current_steps": 477, "total_steps": 477, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "9:17:02", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dfde97fed53d5c8042eb91b9d85596834cfa980e --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3381 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 477, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.006289308176100629, + "grad_norm": 4.8737874031066895, + "learning_rate": 1.0416666666666667e-06, + "loss": 3.6915, + "step": 1 + }, + { + "epoch": 0.012578616352201259, + "grad_norm": 4.941007137298584, + "learning_rate": 2.0833333333333334e-06, + "loss": 3.6352, + "step": 2 + }, + { + "epoch": 0.018867924528301886, + "grad_norm": 5.258031368255615, + "learning_rate": 3.125e-06, + "loss": 3.5816, + "step": 3 + }, + { + "epoch": 0.025157232704402517, + "grad_norm": 5.544358253479004, + "learning_rate": 4.166666666666667e-06, + "loss": 3.6233, + "step": 4 + }, + { + "epoch": 0.031446540880503145, + "grad_norm": 5.457708835601807, + "learning_rate": 5.208333333333334e-06, + "loss": 3.6107, + "step": 5 + }, + { + "epoch": 0.03773584905660377, + "grad_norm": 5.185223579406738, + "learning_rate": 6.25e-06, + "loss": 3.6277, + "step": 6 + }, + { + "epoch": 0.0440251572327044, + "grad_norm": 5.433485507965088, + "learning_rate": 7.2916666666666674e-06, + "loss": 3.4974, + "step": 7 + }, + { + "epoch": 0.050314465408805034, + "grad_norm": 5.38355016708374, + "learning_rate": 8.333333333333334e-06, + "loss": 3.5021, + "step": 8 + }, + { + "epoch": 0.05660377358490566, + "grad_norm": 5.851156234741211, + "learning_rate": 9.375000000000001e-06, + "loss": 3.5888, + "step": 9 + }, + { + "epoch": 0.06289308176100629, + "grad_norm": 8.335844993591309, + "learning_rate": 1.0416666666666668e-05, + "loss": 3.3652, + "step": 10 + }, + { + "epoch": 0.06918238993710692, + "grad_norm": 5.598583698272705, + "learning_rate": 1.1458333333333333e-05, + "loss": 3.1476, + "step": 11 + }, + { + "epoch": 0.07547169811320754, + "grad_norm": 6.811880588531494, + "learning_rate": 1.25e-05, + "loss": 3.6846, + "step": 12 + }, + { + "epoch": 0.08176100628930817, + "grad_norm": 5.962316513061523, + "learning_rate": 1.3541666666666666e-05, + "loss": 3.2959, + "step": 13 + }, + { + "epoch": 0.0880503144654088, + "grad_norm": 6.434226989746094, + "learning_rate": 1.4583333333333335e-05, + "loss": 3.3629, + "step": 14 + }, + { + "epoch": 0.09433962264150944, + "grad_norm": 5.959097862243652, + "learning_rate": 1.5625e-05, + "loss": 2.9799, + "step": 15 + }, + { + "epoch": 0.10062893081761007, + "grad_norm": 5.713625907897949, + "learning_rate": 1.6666666666666667e-05, + "loss": 2.8375, + "step": 16 + }, + { + "epoch": 0.1069182389937107, + "grad_norm": 4.679070472717285, + "learning_rate": 1.7708333333333335e-05, + "loss": 2.5298, + "step": 17 + }, + { + "epoch": 0.11320754716981132, + "grad_norm": 4.000007152557373, + "learning_rate": 1.8750000000000002e-05, + "loss": 2.4099, + "step": 18 + }, + { + "epoch": 0.11949685534591195, + "grad_norm": 3.6054141521453857, + "learning_rate": 1.9791666666666665e-05, + "loss": 2.1316, + "step": 19 + }, + { + "epoch": 0.12578616352201258, + "grad_norm": 3.1357152462005615, + "learning_rate": 2.0833333333333336e-05, + "loss": 1.8814, + "step": 20 + }, + { + "epoch": 0.1320754716981132, + "grad_norm": 2.848811149597168, + "learning_rate": 2.1875e-05, + "loss": 1.7786, + "step": 21 + }, + { + "epoch": 0.13836477987421383, + "grad_norm": 2.4006130695343018, + "learning_rate": 2.2916666666666667e-05, + "loss": 1.5133, + "step": 22 + }, + { + "epoch": 0.14465408805031446, + "grad_norm": 2.2537267208099365, + "learning_rate": 2.3958333333333334e-05, + "loss": 1.4229, + "step": 23 + }, + { + "epoch": 0.1509433962264151, + "grad_norm": 2.1117539405822754, + "learning_rate": 2.5e-05, + "loss": 1.3577, + "step": 24 + }, + { + "epoch": 0.15723270440251572, + "grad_norm": 1.5717436075210571, + "learning_rate": 2.604166666666667e-05, + "loss": 1.1501, + "step": 25 + }, + { + "epoch": 0.16352201257861634, + "grad_norm": 1.691366195678711, + "learning_rate": 2.7083333333333332e-05, + "loss": 1.292, + "step": 26 + }, + { + "epoch": 0.16981132075471697, + "grad_norm": 1.4936853647232056, + "learning_rate": 2.8125000000000003e-05, + "loss": 1.1469, + "step": 27 + }, + { + "epoch": 0.1761006289308176, + "grad_norm": 1.2858690023422241, + "learning_rate": 2.916666666666667e-05, + "loss": 1.0433, + "step": 28 + }, + { + "epoch": 0.18238993710691823, + "grad_norm": 1.148773193359375, + "learning_rate": 3.0208333333333334e-05, + "loss": 0.9627, + "step": 29 + }, + { + "epoch": 0.18867924528301888, + "grad_norm": 1.0097932815551758, + "learning_rate": 3.125e-05, + "loss": 0.9103, + "step": 30 + }, + { + "epoch": 0.1949685534591195, + "grad_norm": 0.9332402348518372, + "learning_rate": 3.229166666666667e-05, + "loss": 0.979, + "step": 31 + }, + { + "epoch": 0.20125786163522014, + "grad_norm": 0.8993248343467712, + "learning_rate": 3.3333333333333335e-05, + "loss": 0.9553, + "step": 32 + }, + { + "epoch": 0.20754716981132076, + "grad_norm": 0.7925082445144653, + "learning_rate": 3.4375e-05, + "loss": 0.8379, + "step": 33 + }, + { + "epoch": 0.2138364779874214, + "grad_norm": 0.7847669720649719, + "learning_rate": 3.541666666666667e-05, + "loss": 0.9038, + "step": 34 + }, + { + "epoch": 0.22012578616352202, + "grad_norm": 0.800736665725708, + "learning_rate": 3.6458333333333336e-05, + "loss": 0.8354, + "step": 35 + }, + { + "epoch": 0.22641509433962265, + "grad_norm": 0.6036879420280457, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.8517, + "step": 36 + }, + { + "epoch": 0.23270440251572327, + "grad_norm": 0.6031014919281006, + "learning_rate": 3.854166666666667e-05, + "loss": 0.8702, + "step": 37 + }, + { + "epoch": 0.2389937106918239, + "grad_norm": 0.584917426109314, + "learning_rate": 3.958333333333333e-05, + "loss": 0.8812, + "step": 38 + }, + { + "epoch": 0.24528301886792453, + "grad_norm": 0.5815232396125793, + "learning_rate": 4.0625000000000005e-05, + "loss": 0.8336, + "step": 39 + }, + { + "epoch": 0.25157232704402516, + "grad_norm": 0.5307980179786682, + "learning_rate": 4.166666666666667e-05, + "loss": 0.7162, + "step": 40 + }, + { + "epoch": 0.2578616352201258, + "grad_norm": 0.49309515953063965, + "learning_rate": 4.270833333333333e-05, + "loss": 0.7433, + "step": 41 + }, + { + "epoch": 0.2641509433962264, + "grad_norm": 0.5215100646018982, + "learning_rate": 4.375e-05, + "loss": 0.738, + "step": 42 + }, + { + "epoch": 0.27044025157232704, + "grad_norm": 0.5361147522926331, + "learning_rate": 4.4791666666666673e-05, + "loss": 0.7884, + "step": 43 + }, + { + "epoch": 0.27672955974842767, + "grad_norm": 0.5043961405754089, + "learning_rate": 4.5833333333333334e-05, + "loss": 0.814, + "step": 44 + }, + { + "epoch": 0.2830188679245283, + "grad_norm": 0.476026713848114, + "learning_rate": 4.6875e-05, + "loss": 0.8249, + "step": 45 + }, + { + "epoch": 0.2893081761006289, + "grad_norm": 0.5099363923072815, + "learning_rate": 4.791666666666667e-05, + "loss": 0.7205, + "step": 46 + }, + { + "epoch": 0.29559748427672955, + "grad_norm": 0.4583563208580017, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.7646, + "step": 47 + }, + { + "epoch": 0.3018867924528302, + "grad_norm": 0.5203999876976013, + "learning_rate": 5e-05, + "loss": 0.6697, + "step": 48 + }, + { + "epoch": 0.3081761006289308, + "grad_norm": 0.5025014877319336, + "learning_rate": 4.9999329662935534e-05, + "loss": 0.8134, + "step": 49 + }, + { + "epoch": 0.31446540880503143, + "grad_norm": 0.5326013565063477, + "learning_rate": 4.999731868769027e-05, + "loss": 0.7665, + "step": 50 + }, + { + "epoch": 0.32075471698113206, + "grad_norm": 0.4914862811565399, + "learning_rate": 4.99939671821067e-05, + "loss": 0.7717, + "step": 51 + }, + { + "epoch": 0.3270440251572327, + "grad_norm": 0.567669689655304, + "learning_rate": 4.998927532591592e-05, + "loss": 0.677, + "step": 52 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.44353675842285156, + "learning_rate": 4.9983243370727914e-05, + "loss": 0.6829, + "step": 53 + }, + { + "epoch": 0.33962264150943394, + "grad_norm": 0.48537710309028625, + "learning_rate": 4.9975871640018154e-05, + "loss": 0.7817, + "step": 54 + }, + { + "epoch": 0.34591194968553457, + "grad_norm": 0.6286251544952393, + "learning_rate": 4.996716052911017e-05, + "loss": 0.6835, + "step": 55 + }, + { + "epoch": 0.3522012578616352, + "grad_norm": 0.44308704137802124, + "learning_rate": 4.99571105051544e-05, + "loss": 0.728, + "step": 56 + }, + { + "epoch": 0.3584905660377358, + "grad_norm": 0.4270545542240143, + "learning_rate": 4.994572210710315e-05, + "loss": 0.6448, + "step": 57 + }, + { + "epoch": 0.36477987421383645, + "grad_norm": 0.38012009859085083, + "learning_rate": 4.993299594568163e-05, + "loss": 0.675, + "step": 58 + }, + { + "epoch": 0.3710691823899371, + "grad_norm": 0.46653008460998535, + "learning_rate": 4.9918932703355256e-05, + "loss": 0.6821, + "step": 59 + }, + { + "epoch": 0.37735849056603776, + "grad_norm": 0.3612300753593445, + "learning_rate": 4.990353313429303e-05, + "loss": 0.7063, + "step": 60 + }, + { + "epoch": 0.3836477987421384, + "grad_norm": 0.5769712924957275, + "learning_rate": 4.988679806432712e-05, + "loss": 0.6941, + "step": 61 + }, + { + "epoch": 0.389937106918239, + "grad_norm": 0.431997150182724, + "learning_rate": 4.9868728390908526e-05, + "loss": 0.6544, + "step": 62 + }, + { + "epoch": 0.39622641509433965, + "grad_norm": 0.38126569986343384, + "learning_rate": 4.9849325083059e-05, + "loss": 0.6966, + "step": 63 + }, + { + "epoch": 0.4025157232704403, + "grad_norm": 0.40978091955184937, + "learning_rate": 4.982858918131906e-05, + "loss": 0.6866, + "step": 64 + }, + { + "epoch": 0.4088050314465409, + "grad_norm": 0.5318535566329956, + "learning_rate": 4.980652179769218e-05, + "loss": 0.7029, + "step": 65 + }, + { + "epoch": 0.41509433962264153, + "grad_norm": 0.5288330912590027, + "learning_rate": 4.978312411558518e-05, + "loss": 0.6553, + "step": 66 + }, + { + "epoch": 0.42138364779874216, + "grad_norm": 0.6496341824531555, + "learning_rate": 4.9758397389744734e-05, + "loss": 0.696, + "step": 67 + }, + { + "epoch": 0.4276729559748428, + "grad_norm": 0.5196901559829712, + "learning_rate": 4.973234294619011e-05, + "loss": 0.6676, + "step": 68 + }, + { + "epoch": 0.4339622641509434, + "grad_norm": 0.5431825518608093, + "learning_rate": 4.9704962182142044e-05, + "loss": 0.6337, + "step": 69 + }, + { + "epoch": 0.44025157232704404, + "grad_norm": 0.6981568932533264, + "learning_rate": 4.967625656594782e-05, + "loss": 0.7645, + "step": 70 + }, + { + "epoch": 0.44654088050314467, + "grad_norm": 0.4362429082393646, + "learning_rate": 4.9646227637002515e-05, + "loss": 0.647, + "step": 71 + }, + { + "epoch": 0.4528301886792453, + "grad_norm": 0.41873699426651, + "learning_rate": 4.961487700566646e-05, + "loss": 0.6342, + "step": 72 + }, + { + "epoch": 0.4591194968553459, + "grad_norm": 0.589474081993103, + "learning_rate": 4.958220635317886e-05, + "loss": 0.641, + "step": 73 + }, + { + "epoch": 0.46540880503144655, + "grad_norm": 0.5421208739280701, + "learning_rate": 4.9548217431567665e-05, + "loss": 0.8103, + "step": 74 + }, + { + "epoch": 0.4716981132075472, + "grad_norm": 0.48354727029800415, + "learning_rate": 4.95129120635556e-05, + "loss": 0.6205, + "step": 75 + }, + { + "epoch": 0.4779874213836478, + "grad_norm": 0.6121774911880493, + "learning_rate": 4.9476292142462374e-05, + "loss": 0.6678, + "step": 76 + }, + { + "epoch": 0.48427672955974843, + "grad_norm": 0.5440806150436401, + "learning_rate": 4.943835963210324e-05, + "loss": 0.6668, + "step": 77 + }, + { + "epoch": 0.49056603773584906, + "grad_norm": 0.40740126371383667, + "learning_rate": 4.939911656668361e-05, + "loss": 0.61, + "step": 78 + }, + { + "epoch": 0.4968553459119497, + "grad_norm": 0.5682631731033325, + "learning_rate": 4.9358565050689985e-05, + "loss": 0.6939, + "step": 79 + }, + { + "epoch": 0.5031446540880503, + "grad_norm": 0.43090444803237915, + "learning_rate": 4.93167072587771e-05, + "loss": 0.6698, + "step": 80 + }, + { + "epoch": 0.5094339622641509, + "grad_norm": 0.3859785795211792, + "learning_rate": 4.92735454356513e-05, + "loss": 0.5798, + "step": 81 + }, + { + "epoch": 0.5157232704402516, + "grad_norm": 0.4453634023666382, + "learning_rate": 4.922908189595018e-05, + "loss": 0.7936, + "step": 82 + }, + { + "epoch": 0.5220125786163522, + "grad_norm": 0.4291239380836487, + "learning_rate": 4.9183319024118415e-05, + "loss": 0.667, + "step": 83 + }, + { + "epoch": 0.5283018867924528, + "grad_norm": 0.44029664993286133, + "learning_rate": 4.9136259274279955e-05, + "loss": 0.6518, + "step": 84 + }, + { + "epoch": 0.5345911949685535, + "grad_norm": 0.44975465536117554, + "learning_rate": 4.908790517010636e-05, + "loss": 0.6105, + "step": 85 + }, + { + "epoch": 0.5408805031446541, + "grad_norm": 0.3954753577709198, + "learning_rate": 4.903825930468149e-05, + "loss": 0.6954, + "step": 86 + }, + { + "epoch": 0.5471698113207547, + "grad_norm": 0.3935467302799225, + "learning_rate": 4.898732434036244e-05, + "loss": 0.6614, + "step": 87 + }, + { + "epoch": 0.5534591194968553, + "grad_norm": 0.37667638063430786, + "learning_rate": 4.893510300863676e-05, + "loss": 0.6186, + "step": 88 + }, + { + "epoch": 0.559748427672956, + "grad_norm": 0.5198381543159485, + "learning_rate": 4.8881598109976004e-05, + "loss": 0.6153, + "step": 89 + }, + { + "epoch": 0.5660377358490566, + "grad_norm": 0.4063967764377594, + "learning_rate": 4.8826812513685487e-05, + "loss": 0.6472, + "step": 90 + }, + { + "epoch": 0.5723270440251572, + "grad_norm": 0.4114413857460022, + "learning_rate": 4.877074915775049e-05, + "loss": 0.6404, + "step": 91 + }, + { + "epoch": 0.5786163522012578, + "grad_norm": 0.37414512038230896, + "learning_rate": 4.8713411048678635e-05, + "loss": 0.6353, + "step": 92 + }, + { + "epoch": 0.5849056603773585, + "grad_norm": 0.3818528354167938, + "learning_rate": 4.865480126133872e-05, + "loss": 0.6289, + "step": 93 + }, + { + "epoch": 0.5911949685534591, + "grad_norm": 0.37088677287101746, + "learning_rate": 4.859492293879574e-05, + "loss": 0.6242, + "step": 94 + }, + { + "epoch": 0.5974842767295597, + "grad_norm": 0.43665146827697754, + "learning_rate": 4.853377929214243e-05, + "loss": 0.6055, + "step": 95 + }, + { + "epoch": 0.6037735849056604, + "grad_norm": 0.5932008028030396, + "learning_rate": 4.8471373600326996e-05, + "loss": 0.6354, + "step": 96 + }, + { + "epoch": 0.610062893081761, + "grad_norm": 0.46184536814689636, + "learning_rate": 4.8407709209977305e-05, + "loss": 0.7039, + "step": 97 + }, + { + "epoch": 0.6163522012578616, + "grad_norm": 0.44864600896835327, + "learning_rate": 4.834278953522138e-05, + "loss": 0.6679, + "step": 98 + }, + { + "epoch": 0.6226415094339622, + "grad_norm": 0.4060032069683075, + "learning_rate": 4.8276618057504376e-05, + "loss": 0.7479, + "step": 99 + }, + { + "epoch": 0.6289308176100629, + "grad_norm": 0.5088009834289551, + "learning_rate": 4.8209198325401815e-05, + "loss": 0.5923, + "step": 100 + }, + { + "epoch": 0.6352201257861635, + "grad_norm": 0.4294343590736389, + "learning_rate": 4.8140533954429327e-05, + "loss": 0.6313, + "step": 101 + }, + { + "epoch": 0.6415094339622641, + "grad_norm": 0.5710806846618652, + "learning_rate": 4.8070628626848735e-05, + "loss": 0.6736, + "step": 102 + }, + { + "epoch": 0.6477987421383647, + "grad_norm": 0.40560534596443176, + "learning_rate": 4.799948609147061e-05, + "loss": 0.6173, + "step": 103 + }, + { + "epoch": 0.6540880503144654, + "grad_norm": 0.46361806988716125, + "learning_rate": 4.792711016345321e-05, + "loss": 0.6756, + "step": 104 + }, + { + "epoch": 0.660377358490566, + "grad_norm": 0.5206082463264465, + "learning_rate": 4.785350472409792e-05, + "loss": 0.6413, + "step": 105 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.42583200335502625, + "learning_rate": 4.777867372064105e-05, + "loss": 0.6201, + "step": 106 + }, + { + "epoch": 0.6729559748427673, + "grad_norm": 0.49348241090774536, + "learning_rate": 4.770262116604224e-05, + "loss": 0.5777, + "step": 107 + }, + { + "epoch": 0.6792452830188679, + "grad_norm": 0.43750065565109253, + "learning_rate": 4.762535113876917e-05, + "loss": 0.6326, + "step": 108 + }, + { + "epoch": 0.6855345911949685, + "grad_norm": 0.431643545627594, + "learning_rate": 4.754686778257891e-05, + "loss": 0.5849, + "step": 109 + }, + { + "epoch": 0.6918238993710691, + "grad_norm": 0.41906824707984924, + "learning_rate": 4.7467175306295655e-05, + "loss": 0.6779, + "step": 110 + }, + { + "epoch": 0.6981132075471698, + "grad_norm": 0.4261593222618103, + "learning_rate": 4.738627798358506e-05, + "loss": 0.565, + "step": 111 + }, + { + "epoch": 0.7044025157232704, + "grad_norm": 0.42877814173698425, + "learning_rate": 4.730418015272503e-05, + "loss": 0.6836, + "step": 112 + }, + { + "epoch": 0.710691823899371, + "grad_norm": 0.40995511412620544, + "learning_rate": 4.722088621637309e-05, + "loss": 0.5849, + "step": 113 + }, + { + "epoch": 0.7169811320754716, + "grad_norm": 0.5606467723846436, + "learning_rate": 4.713640064133025e-05, + "loss": 0.644, + "step": 114 + }, + { + "epoch": 0.7232704402515723, + "grad_norm": 0.48454752564430237, + "learning_rate": 4.7050727958301506e-05, + "loss": 0.5418, + "step": 115 + }, + { + "epoch": 0.7295597484276729, + "grad_norm": 0.4099617898464203, + "learning_rate": 4.6963872761652835e-05, + "loss": 0.6524, + "step": 116 + }, + { + "epoch": 0.7358490566037735, + "grad_norm": 0.47192293405532837, + "learning_rate": 4.687583970916487e-05, + "loss": 0.6134, + "step": 117 + }, + { + "epoch": 0.7421383647798742, + "grad_norm": 0.4925817549228668, + "learning_rate": 4.678663352178301e-05, + "loss": 0.6517, + "step": 118 + }, + { + "epoch": 0.7484276729559748, + "grad_norm": 0.41517379879951477, + "learning_rate": 4.6696258983364385e-05, + "loss": 0.5763, + "step": 119 + }, + { + "epoch": 0.7547169811320755, + "grad_norm": 0.6227956414222717, + "learning_rate": 4.660472094042121e-05, + "loss": 0.7349, + "step": 120 + }, + { + "epoch": 0.7610062893081762, + "grad_norm": 0.39108285307884216, + "learning_rate": 4.651202430186092e-05, + "loss": 0.6548, + "step": 121 + }, + { + "epoch": 0.7672955974842768, + "grad_norm": 0.40210628509521484, + "learning_rate": 4.641817403872293e-05, + "loss": 0.6135, + "step": 122 + }, + { + "epoch": 0.7735849056603774, + "grad_norm": 0.42835289239883423, + "learning_rate": 4.6323175183912024e-05, + "loss": 0.5227, + "step": 123 + }, + { + "epoch": 0.779874213836478, + "grad_norm": 0.6215445399284363, + "learning_rate": 4.6227032831928484e-05, + "loss": 0.5265, + "step": 124 + }, + { + "epoch": 0.7861635220125787, + "grad_norm": 0.43423891067504883, + "learning_rate": 4.6129752138594874e-05, + "loss": 0.5972, + "step": 125 + }, + { + "epoch": 0.7924528301886793, + "grad_norm": 0.4693637788295746, + "learning_rate": 4.6031338320779534e-05, + "loss": 0.6758, + "step": 126 + }, + { + "epoch": 0.7987421383647799, + "grad_norm": 0.47571077942848206, + "learning_rate": 4.5931796656116846e-05, + "loss": 0.6419, + "step": 127 + }, + { + "epoch": 0.8050314465408805, + "grad_norm": 0.5828564167022705, + "learning_rate": 4.5831132482724195e-05, + "loss": 0.6952, + "step": 128 + }, + { + "epoch": 0.8113207547169812, + "grad_norm": 0.5325509309768677, + "learning_rate": 4.572935119891571e-05, + "loss": 0.6093, + "step": 129 + }, + { + "epoch": 0.8176100628930818, + "grad_norm": 0.4476761519908905, + "learning_rate": 4.5626458262912745e-05, + "loss": 0.5688, + "step": 130 + }, + { + "epoch": 0.8238993710691824, + "grad_norm": 0.36771783232688904, + "learning_rate": 4.552245919255117e-05, + "loss": 0.5778, + "step": 131 + }, + { + "epoch": 0.8301886792452831, + "grad_norm": 0.3695763647556305, + "learning_rate": 4.541735956498554e-05, + "loss": 0.517, + "step": 132 + }, + { + "epoch": 0.8364779874213837, + "grad_norm": 0.46155717968940735, + "learning_rate": 4.5311165016389916e-05, + "loss": 0.631, + "step": 133 + }, + { + "epoch": 0.8427672955974843, + "grad_norm": 0.5536386966705322, + "learning_rate": 4.5203881241655644e-05, + "loss": 0.6309, + "step": 134 + }, + { + "epoch": 0.8490566037735849, + "grad_norm": 0.42256519198417664, + "learning_rate": 4.509551399408598e-05, + "loss": 0.6754, + "step": 135 + }, + { + "epoch": 0.8553459119496856, + "grad_norm": 0.41634511947631836, + "learning_rate": 4.498606908508754e-05, + "loss": 0.6547, + "step": 136 + }, + { + "epoch": 0.8616352201257862, + "grad_norm": 0.38796696066856384, + "learning_rate": 4.487555238385862e-05, + "loss": 0.5693, + "step": 137 + }, + { + "epoch": 0.8679245283018868, + "grad_norm": 0.43052586913108826, + "learning_rate": 4.476396981707453e-05, + "loss": 0.6655, + "step": 138 + }, + { + "epoch": 0.8742138364779874, + "grad_norm": 0.44500571489334106, + "learning_rate": 4.465132736856969e-05, + "loss": 0.6563, + "step": 139 + }, + { + "epoch": 0.8805031446540881, + "grad_norm": 0.44693946838378906, + "learning_rate": 4.453763107901675e-05, + "loss": 0.5729, + "step": 140 + }, + { + "epoch": 0.8867924528301887, + "grad_norm": 0.3982055187225342, + "learning_rate": 4.442288704560268e-05, + "loss": 0.6425, + "step": 141 + }, + { + "epoch": 0.8930817610062893, + "grad_norm": 0.5706686973571777, + "learning_rate": 4.430710142170176e-05, + "loss": 0.5732, + "step": 142 + }, + { + "epoch": 0.89937106918239, + "grad_norm": 0.4493609070777893, + "learning_rate": 4.419028041654559e-05, + "loss": 0.6507, + "step": 143 + }, + { + "epoch": 0.9056603773584906, + "grad_norm": 0.3834284543991089, + "learning_rate": 4.4072430294890174e-05, + "loss": 0.6883, + "step": 144 + }, + { + "epoch": 0.9119496855345912, + "grad_norm": 0.4243861138820648, + "learning_rate": 4.3953557376679856e-05, + "loss": 0.5818, + "step": 145 + }, + { + "epoch": 0.9182389937106918, + "grad_norm": 0.42064470052719116, + "learning_rate": 4.383366803670849e-05, + "loss": 0.5963, + "step": 146 + }, + { + "epoch": 0.9245283018867925, + "grad_norm": 0.46670740842819214, + "learning_rate": 4.371276870427753e-05, + "loss": 0.65, + "step": 147 + }, + { + "epoch": 0.9308176100628931, + "grad_norm": 0.44945597648620605, + "learning_rate": 4.359086586285127e-05, + "loss": 0.6554, + "step": 148 + }, + { + "epoch": 0.9371069182389937, + "grad_norm": 0.48251762986183167, + "learning_rate": 4.346796604970912e-05, + "loss": 0.6681, + "step": 149 + }, + { + "epoch": 0.9433962264150944, + "grad_norm": 0.4577901065349579, + "learning_rate": 4.3344075855595104e-05, + "loss": 0.6108, + "step": 150 + }, + { + "epoch": 0.949685534591195, + "grad_norm": 0.4710671603679657, + "learning_rate": 4.321920192436433e-05, + "loss": 0.6177, + "step": 151 + }, + { + "epoch": 0.9559748427672956, + "grad_norm": 0.4275747835636139, + "learning_rate": 4.309335095262676e-05, + "loss": 0.5881, + "step": 152 + }, + { + "epoch": 0.9622641509433962, + "grad_norm": 0.4541204571723938, + "learning_rate": 4.296652968938807e-05, + "loss": 0.6142, + "step": 153 + }, + { + "epoch": 0.9685534591194969, + "grad_norm": 0.4179267883300781, + "learning_rate": 4.283874493568772e-05, + "loss": 0.6463, + "step": 154 + }, + { + "epoch": 0.9748427672955975, + "grad_norm": 0.42434728145599365, + "learning_rate": 4.271000354423426e-05, + "loss": 0.5873, + "step": 155 + }, + { + "epoch": 0.9811320754716981, + "grad_norm": 0.44202134013175964, + "learning_rate": 4.258031241903778e-05, + "loss": 0.6046, + "step": 156 + }, + { + "epoch": 0.9874213836477987, + "grad_norm": 0.47817060351371765, + "learning_rate": 4.2449678515039747e-05, + "loss": 0.5989, + "step": 157 + }, + { + "epoch": 0.9937106918238994, + "grad_norm": 0.43847018480300903, + "learning_rate": 4.231810883773999e-05, + "loss": 0.6156, + "step": 158 + }, + { + "epoch": 1.0, + "grad_norm": 0.48976290225982666, + "learning_rate": 4.218561044282099e-05, + "loss": 0.6177, + "step": 159 + }, + { + "epoch": 1.0062893081761006, + "grad_norm": 0.4213927984237671, + "learning_rate": 4.2052190435769554e-05, + "loss": 0.5881, + "step": 160 + }, + { + "epoch": 1.0125786163522013, + "grad_norm": 0.3923173248767853, + "learning_rate": 4.191785597149577e-05, + "loss": 0.5354, + "step": 161 + }, + { + "epoch": 1.0188679245283019, + "grad_norm": 0.41947099566459656, + "learning_rate": 4.178261425394926e-05, + "loss": 0.5745, + "step": 162 + }, + { + "epoch": 1.0251572327044025, + "grad_norm": 0.45812028646469116, + "learning_rate": 4.1646472535732895e-05, + "loss": 0.5836, + "step": 163 + }, + { + "epoch": 1.0314465408805031, + "grad_norm": 0.4519791007041931, + "learning_rate": 4.1509438117713866e-05, + "loss": 0.6118, + "step": 164 + }, + { + "epoch": 1.0377358490566038, + "grad_norm": 0.5628229379653931, + "learning_rate": 4.137151834863213e-05, + "loss": 0.5811, + "step": 165 + }, + { + "epoch": 1.0440251572327044, + "grad_norm": 0.3987003564834595, + "learning_rate": 4.123272062470633e-05, + "loss": 0.5179, + "step": 166 + }, + { + "epoch": 1.050314465408805, + "grad_norm": 0.4499664604663849, + "learning_rate": 4.109305238923718e-05, + "loss": 0.548, + "step": 167 + }, + { + "epoch": 1.0566037735849056, + "grad_norm": 0.4336049556732178, + "learning_rate": 4.095252113220827e-05, + "loss": 0.5659, + "step": 168 + }, + { + "epoch": 1.0628930817610063, + "grad_norm": 0.5409331321716309, + "learning_rate": 4.0811134389884433e-05, + "loss": 0.5522, + "step": 169 + }, + { + "epoch": 1.069182389937107, + "grad_norm": 0.41802865266799927, + "learning_rate": 4.066889974440757e-05, + "loss": 0.542, + "step": 170 + }, + { + "epoch": 1.0754716981132075, + "grad_norm": 0.48149824142456055, + "learning_rate": 4.0525824823390045e-05, + "loss": 0.6131, + "step": 171 + }, + { + "epoch": 1.0817610062893082, + "grad_norm": 0.5059295296669006, + "learning_rate": 4.038191729950569e-05, + "loss": 0.5823, + "step": 172 + }, + { + "epoch": 1.0880503144654088, + "grad_norm": 0.5310669541358948, + "learning_rate": 4.0237184890078245e-05, + "loss": 0.6066, + "step": 173 + }, + { + "epoch": 1.0943396226415094, + "grad_norm": 0.5470696091651917, + "learning_rate": 4.009163535666761e-05, + "loss": 0.6407, + "step": 174 + }, + { + "epoch": 1.10062893081761, + "grad_norm": 0.4407522678375244, + "learning_rate": 3.994527650465352e-05, + "loss": 0.573, + "step": 175 + }, + { + "epoch": 1.1069182389937107, + "grad_norm": 0.4072059094905853, + "learning_rate": 3.979811618281706e-05, + "loss": 0.6349, + "step": 176 + }, + { + "epoch": 1.1132075471698113, + "grad_norm": 0.6410146355628967, + "learning_rate": 3.9650162282919655e-05, + "loss": 0.6036, + "step": 177 + }, + { + "epoch": 1.119496855345912, + "grad_norm": 0.4664185047149658, + "learning_rate": 3.9501422739279956e-05, + "loss": 0.5855, + "step": 178 + }, + { + "epoch": 1.1257861635220126, + "grad_norm": 0.7204552888870239, + "learning_rate": 3.9351905528348285e-05, + "loss": 0.5719, + "step": 179 + }, + { + "epoch": 1.1320754716981132, + "grad_norm": 0.47248926758766174, + "learning_rate": 3.920161866827889e-05, + "loss": 0.5764, + "step": 180 + }, + { + "epoch": 1.1383647798742138, + "grad_norm": 0.64155113697052, + "learning_rate": 3.90505702185e-05, + "loss": 0.644, + "step": 181 + }, + { + "epoch": 1.1446540880503144, + "grad_norm": 0.5559830665588379, + "learning_rate": 3.889876827928156e-05, + "loss": 0.5883, + "step": 182 + }, + { + "epoch": 1.150943396226415, + "grad_norm": 0.46357718110084534, + "learning_rate": 3.874622099130087e-05, + "loss": 0.5942, + "step": 183 + }, + { + "epoch": 1.1572327044025157, + "grad_norm": 0.4527578055858612, + "learning_rate": 3.859293653520604e-05, + "loss": 0.6086, + "step": 184 + }, + { + "epoch": 1.1635220125786163, + "grad_norm": 0.45968765020370483, + "learning_rate": 3.843892313117724e-05, + "loss": 0.6105, + "step": 185 + }, + { + "epoch": 1.169811320754717, + "grad_norm": 0.5293806791305542, + "learning_rate": 3.8284189038485936e-05, + "loss": 0.5622, + "step": 186 + }, + { + "epoch": 1.1761006289308176, + "grad_norm": 0.4499124586582184, + "learning_rate": 3.812874255505191e-05, + "loss": 0.5451, + "step": 187 + }, + { + "epoch": 1.1823899371069182, + "grad_norm": 0.5140619277954102, + "learning_rate": 3.797259201699833e-05, + "loss": 0.5864, + "step": 188 + }, + { + "epoch": 1.1886792452830188, + "grad_norm": 0.40918025374412537, + "learning_rate": 3.781574579820464e-05, + "loss": 0.5602, + "step": 189 + }, + { + "epoch": 1.1949685534591195, + "grad_norm": 0.4417194128036499, + "learning_rate": 3.765821230985758e-05, + "loss": 0.5556, + "step": 190 + }, + { + "epoch": 1.20125786163522, + "grad_norm": 0.4697968363761902, + "learning_rate": 3.7500000000000003e-05, + "loss": 0.6491, + "step": 191 + }, + { + "epoch": 1.2075471698113207, + "grad_norm": 0.40187153220176697, + "learning_rate": 3.7341117353077966e-05, + "loss": 0.5797, + "step": 192 + }, + { + "epoch": 1.2138364779874213, + "grad_norm": 0.456836462020874, + "learning_rate": 3.718157288948563e-05, + "loss": 0.5613, + "step": 193 + }, + { + "epoch": 1.220125786163522, + "grad_norm": 0.45992621779441833, + "learning_rate": 3.702137516510838e-05, + "loss": 0.6301, + "step": 194 + }, + { + "epoch": 1.2264150943396226, + "grad_norm": 0.45000532269477844, + "learning_rate": 3.686053277086401e-05, + "loss": 0.5772, + "step": 195 + }, + { + "epoch": 1.2327044025157232, + "grad_norm": 0.4734075963497162, + "learning_rate": 3.669905433224199e-05, + "loss": 0.5452, + "step": 196 + }, + { + "epoch": 1.2389937106918238, + "grad_norm": 0.41561609506607056, + "learning_rate": 3.653694850884091e-05, + "loss": 0.5365, + "step": 197 + }, + { + "epoch": 1.2452830188679245, + "grad_norm": 0.469097763299942, + "learning_rate": 3.637422399390413e-05, + "loss": 0.5396, + "step": 198 + }, + { + "epoch": 1.251572327044025, + "grad_norm": 0.46705111861228943, + "learning_rate": 3.621088951385353e-05, + "loss": 0.6024, + "step": 199 + }, + { + "epoch": 1.2578616352201257, + "grad_norm": 0.5201407074928284, + "learning_rate": 3.604695382782159e-05, + "loss": 0.6905, + "step": 200 + }, + { + "epoch": 1.2641509433962264, + "grad_norm": 0.4639309346675873, + "learning_rate": 3.588242572718162e-05, + "loss": 0.5909, + "step": 201 + }, + { + "epoch": 1.270440251572327, + "grad_norm": 0.4756741225719452, + "learning_rate": 3.5717314035076355e-05, + "loss": 0.5745, + "step": 202 + }, + { + "epoch": 1.2767295597484276, + "grad_norm": 0.5243765115737915, + "learning_rate": 3.5551627605944745e-05, + "loss": 0.6439, + "step": 203 + }, + { + "epoch": 1.2830188679245282, + "grad_norm": 0.4495748281478882, + "learning_rate": 3.5385375325047166e-05, + "loss": 0.5611, + "step": 204 + }, + { + "epoch": 1.2893081761006289, + "grad_norm": 0.47336816787719727, + "learning_rate": 3.521856610798887e-05, + "loss": 0.5846, + "step": 205 + }, + { + "epoch": 1.2955974842767295, + "grad_norm": 0.4667642116546631, + "learning_rate": 3.505120890024195e-05, + "loss": 0.5982, + "step": 206 + }, + { + "epoch": 1.3018867924528301, + "grad_norm": 0.4477729797363281, + "learning_rate": 3.4883312676665536e-05, + "loss": 0.6265, + "step": 207 + }, + { + "epoch": 1.3081761006289307, + "grad_norm": 0.5078469514846802, + "learning_rate": 3.4714886441024574e-05, + "loss": 0.5161, + "step": 208 + }, + { + "epoch": 1.3144654088050314, + "grad_norm": 0.5072935819625854, + "learning_rate": 3.4545939225506934e-05, + "loss": 0.5408, + "step": 209 + }, + { + "epoch": 1.320754716981132, + "grad_norm": 0.5006597638130188, + "learning_rate": 3.437648009023905e-05, + "loss": 0.5715, + "step": 210 + }, + { + "epoch": 1.3270440251572326, + "grad_norm": 0.44206503033638, + "learning_rate": 3.420651812280006e-05, + "loss": 0.5694, + "step": 211 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.4964762032032013, + "learning_rate": 3.4036062437734484e-05, + "loss": 0.5203, + "step": 212 + }, + { + "epoch": 1.3396226415094339, + "grad_norm": 0.4342876076698303, + "learning_rate": 3.386512217606339e-05, + "loss": 0.5778, + "step": 213 + }, + { + "epoch": 1.3459119496855345, + "grad_norm": 0.46520864963531494, + "learning_rate": 3.369370650479425e-05, + "loss": 0.5757, + "step": 214 + }, + { + "epoch": 1.3522012578616351, + "grad_norm": 0.5179557204246521, + "learning_rate": 3.3521824616429285e-05, + "loss": 0.5348, + "step": 215 + }, + { + "epoch": 1.3584905660377358, + "grad_norm": 0.45922955870628357, + "learning_rate": 3.3349485728472535e-05, + "loss": 0.5982, + "step": 216 + }, + { + "epoch": 1.3647798742138364, + "grad_norm": 0.5132372975349426, + "learning_rate": 3.3176699082935545e-05, + "loss": 0.6131, + "step": 217 + }, + { + "epoch": 1.371069182389937, + "grad_norm": 0.4740884602069855, + "learning_rate": 3.300347394584172e-05, + "loss": 0.6194, + "step": 218 + }, + { + "epoch": 1.3773584905660377, + "grad_norm": 0.45677605271339417, + "learning_rate": 3.282981960672948e-05, + "loss": 0.5938, + "step": 219 + }, + { + "epoch": 1.3836477987421385, + "grad_norm": 0.4545290172100067, + "learning_rate": 3.265574537815398e-05, + "loss": 0.5634, + "step": 220 + }, + { + "epoch": 1.389937106918239, + "grad_norm": 0.4439068138599396, + "learning_rate": 3.248126059518785e-05, + "loss": 0.5543, + "step": 221 + }, + { + "epoch": 1.3962264150943398, + "grad_norm": 0.4973136782646179, + "learning_rate": 3.230637461492043e-05, + "loss": 0.549, + "step": 222 + }, + { + "epoch": 1.4025157232704402, + "grad_norm": 0.5018147826194763, + "learning_rate": 3.213109681595612e-05, + "loss": 0.5799, + "step": 223 + }, + { + "epoch": 1.408805031446541, + "grad_norm": 0.4906245768070221, + "learning_rate": 3.195543659791132e-05, + "loss": 0.5788, + "step": 224 + }, + { + "epoch": 1.4150943396226414, + "grad_norm": 0.5228400826454163, + "learning_rate": 3.177940338091043e-05, + "loss": 0.4883, + "step": 225 + }, + { + "epoch": 1.4213836477987423, + "grad_norm": 0.5177304148674011, + "learning_rate": 3.160300660508064e-05, + "loss": 0.5737, + "step": 226 + }, + { + "epoch": 1.4276729559748427, + "grad_norm": 0.4641788899898529, + "learning_rate": 3.14262557300457e-05, + "loss": 0.5416, + "step": 227 + }, + { + "epoch": 1.4339622641509435, + "grad_norm": 0.49331700801849365, + "learning_rate": 3.124916023441865e-05, + "loss": 0.5747, + "step": 228 + }, + { + "epoch": 1.440251572327044, + "grad_norm": 0.4671120345592499, + "learning_rate": 3.107172961529343e-05, + "loss": 0.508, + "step": 229 + }, + { + "epoch": 1.4465408805031448, + "grad_norm": 0.5811720490455627, + "learning_rate": 3.0893973387735687e-05, + "loss": 0.6929, + "step": 230 + }, + { + "epoch": 1.4528301886792452, + "grad_norm": 0.48253801465034485, + "learning_rate": 3.071590108427244e-05, + "loss": 0.6467, + "step": 231 + }, + { + "epoch": 1.459119496855346, + "grad_norm": 0.5044742226600647, + "learning_rate": 3.0537522254380905e-05, + "loss": 0.5067, + "step": 232 + }, + { + "epoch": 1.4654088050314464, + "grad_norm": 0.5015671849250793, + "learning_rate": 3.0358846463976372e-05, + "loss": 0.6052, + "step": 233 + }, + { + "epoch": 1.4716981132075473, + "grad_norm": 0.5023432374000549, + "learning_rate": 3.017988329489923e-05, + "loss": 0.5961, + "step": 234 + }, + { + "epoch": 1.4779874213836477, + "grad_norm": 0.5157131552696228, + "learning_rate": 3.0000642344401113e-05, + "loss": 0.6285, + "step": 235 + }, + { + "epoch": 1.4842767295597485, + "grad_norm": 0.5081720948219299, + "learning_rate": 2.9821133224630226e-05, + "loss": 0.4634, + "step": 236 + }, + { + "epoch": 1.490566037735849, + "grad_norm": 0.4940662086009979, + "learning_rate": 2.9641365562115887e-05, + "loss": 0.5288, + "step": 237 + }, + { + "epoch": 1.4968553459119498, + "grad_norm": 0.6005929708480835, + "learning_rate": 2.9461348997252265e-05, + "loss": 0.5748, + "step": 238 + }, + { + "epoch": 1.5031446540880502, + "grad_norm": 0.5340356230735779, + "learning_rate": 2.9281093183781403e-05, + "loss": 0.5944, + "step": 239 + }, + { + "epoch": 1.509433962264151, + "grad_norm": 0.5056872367858887, + "learning_rate": 2.9100607788275545e-05, + "loss": 0.5549, + "step": 240 + }, + { + "epoch": 1.5157232704402515, + "grad_norm": 0.5385233759880066, + "learning_rate": 2.891990248961871e-05, + "loss": 0.5345, + "step": 241 + }, + { + "epoch": 1.5220125786163523, + "grad_norm": 0.48144999146461487, + "learning_rate": 2.8738986978487625e-05, + "loss": 0.5839, + "step": 242 + }, + { + "epoch": 1.5283018867924527, + "grad_norm": 0.5069999098777771, + "learning_rate": 2.8557870956832132e-05, + "loss": 0.4931, + "step": 243 + }, + { + "epoch": 1.5345911949685536, + "grad_norm": 0.4660912752151489, + "learning_rate": 2.8376564137354795e-05, + "loss": 0.5598, + "step": 244 + }, + { + "epoch": 1.540880503144654, + "grad_norm": 0.5416334271430969, + "learning_rate": 2.8195076242990122e-05, + "loss": 0.5894, + "step": 245 + }, + { + "epoch": 1.5471698113207548, + "grad_norm": 0.49134501814842224, + "learning_rate": 2.8013417006383076e-05, + "loss": 0.6345, + "step": 246 + }, + { + "epoch": 1.5534591194968552, + "grad_norm": 0.5861812829971313, + "learning_rate": 2.783159616936723e-05, + "loss": 0.6519, + "step": 247 + }, + { + "epoch": 1.559748427672956, + "grad_norm": 0.47188055515289307, + "learning_rate": 2.764962348244228e-05, + "loss": 0.5658, + "step": 248 + }, + { + "epoch": 1.5660377358490565, + "grad_norm": 0.4838746190071106, + "learning_rate": 2.7467508704251137e-05, + "loss": 0.5934, + "step": 249 + }, + { + "epoch": 1.5723270440251573, + "grad_norm": 0.516981840133667, + "learning_rate": 2.7285261601056698e-05, + "loss": 0.5341, + "step": 250 + }, + { + "epoch": 1.5786163522012577, + "grad_norm": 0.4871889352798462, + "learning_rate": 2.7102891946217994e-05, + "loss": 0.5885, + "step": 251 + }, + { + "epoch": 1.5849056603773586, + "grad_norm": 0.47121965885162354, + "learning_rate": 2.6920409519666174e-05, + "loss": 0.5988, + "step": 252 + }, + { + "epoch": 1.591194968553459, + "grad_norm": 0.5421566367149353, + "learning_rate": 2.6737824107379948e-05, + "loss": 0.6635, + "step": 253 + }, + { + "epoch": 1.5974842767295598, + "grad_norm": 0.5449573993682861, + "learning_rate": 2.655514550086086e-05, + "loss": 0.5365, + "step": 254 + }, + { + "epoch": 1.6037735849056602, + "grad_norm": 0.5301252007484436, + "learning_rate": 2.637238349660819e-05, + "loss": 0.6854, + "step": 255 + }, + { + "epoch": 1.610062893081761, + "grad_norm": 0.41109421849250793, + "learning_rate": 2.6189547895593562e-05, + "loss": 0.5234, + "step": 256 + }, + { + "epoch": 1.6163522012578615, + "grad_norm": 0.5346055626869202, + "learning_rate": 2.600664850273538e-05, + "loss": 0.5962, + "step": 257 + }, + { + "epoch": 1.6226415094339623, + "grad_norm": 0.5180861949920654, + "learning_rate": 2.582369512637302e-05, + "loss": 0.5396, + "step": 258 + }, + { + "epoch": 1.6289308176100628, + "grad_norm": 0.49982312321662903, + "learning_rate": 2.564069757774082e-05, + "loss": 0.4889, + "step": 259 + }, + { + "epoch": 1.6352201257861636, + "grad_norm": 0.5226275324821472, + "learning_rate": 2.545766567044194e-05, + "loss": 0.5893, + "step": 260 + }, + { + "epoch": 1.641509433962264, + "grad_norm": 0.47939932346343994, + "learning_rate": 2.527460921992209e-05, + "loss": 0.566, + "step": 261 + }, + { + "epoch": 1.6477987421383649, + "grad_norm": 0.536264955997467, + "learning_rate": 2.509153804294318e-05, + "loss": 0.5598, + "step": 262 + }, + { + "epoch": 1.6540880503144653, + "grad_norm": 0.5297203660011292, + "learning_rate": 2.490846195705683e-05, + "loss": 0.552, + "step": 263 + }, + { + "epoch": 1.6603773584905661, + "grad_norm": 0.5188955664634705, + "learning_rate": 2.4725390780077908e-05, + "loss": 0.6233, + "step": 264 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.4677969217300415, + "learning_rate": 2.4542334329558077e-05, + "loss": 0.4968, + "step": 265 + }, + { + "epoch": 1.6729559748427674, + "grad_norm": 0.5716769099235535, + "learning_rate": 2.435930242225919e-05, + "loss": 0.5315, + "step": 266 + }, + { + "epoch": 1.6792452830188678, + "grad_norm": 0.5071538090705872, + "learning_rate": 2.4176304873626985e-05, + "loss": 0.5622, + "step": 267 + }, + { + "epoch": 1.6855345911949686, + "grad_norm": 0.523229718208313, + "learning_rate": 2.399335149726463e-05, + "loss": 0.5999, + "step": 268 + }, + { + "epoch": 1.691823899371069, + "grad_norm": 0.5254403948783875, + "learning_rate": 2.3810452104406444e-05, + "loss": 0.6351, + "step": 269 + }, + { + "epoch": 1.6981132075471699, + "grad_norm": 0.53160560131073, + "learning_rate": 2.3627616503391814e-05, + "loss": 0.5754, + "step": 270 + }, + { + "epoch": 1.7044025157232703, + "grad_norm": 0.5396912693977356, + "learning_rate": 2.3444854499139142e-05, + "loss": 0.5635, + "step": 271 + }, + { + "epoch": 1.7106918238993711, + "grad_norm": 0.5528764724731445, + "learning_rate": 2.3262175892620065e-05, + "loss": 0.5368, + "step": 272 + }, + { + "epoch": 1.7169811320754715, + "grad_norm": 0.4812920093536377, + "learning_rate": 2.307959048033383e-05, + "loss": 0.5508, + "step": 273 + }, + { + "epoch": 1.7232704402515724, + "grad_norm": 0.5467996001243591, + "learning_rate": 2.2897108053782e-05, + "loss": 0.6073, + "step": 274 + }, + { + "epoch": 1.7295597484276728, + "grad_norm": 0.5203157663345337, + "learning_rate": 2.271473839894331e-05, + "loss": 0.5326, + "step": 275 + }, + { + "epoch": 1.7358490566037736, + "grad_norm": 0.4970155358314514, + "learning_rate": 2.253249129574887e-05, + "loss": 0.5444, + "step": 276 + }, + { + "epoch": 1.742138364779874, + "grad_norm": 0.5279742479324341, + "learning_rate": 2.2350376517557727e-05, + "loss": 0.5778, + "step": 277 + }, + { + "epoch": 1.748427672955975, + "grad_norm": 0.5293897986412048, + "learning_rate": 2.216840383063277e-05, + "loss": 0.5786, + "step": 278 + }, + { + "epoch": 1.7547169811320755, + "grad_norm": 0.565350353717804, + "learning_rate": 2.1986582993616926e-05, + "loss": 0.5877, + "step": 279 + }, + { + "epoch": 1.7610062893081762, + "grad_norm": 0.47762683033943176, + "learning_rate": 2.1804923757009884e-05, + "loss": 0.5419, + "step": 280 + }, + { + "epoch": 1.7672955974842768, + "grad_norm": 0.5171676278114319, + "learning_rate": 2.1623435862645204e-05, + "loss": 0.5418, + "step": 281 + }, + { + "epoch": 1.7735849056603774, + "grad_norm": 0.45764029026031494, + "learning_rate": 2.1442129043167874e-05, + "loss": 0.5487, + "step": 282 + }, + { + "epoch": 1.779874213836478, + "grad_norm": 0.5272729396820068, + "learning_rate": 2.126101302151238e-05, + "loss": 0.5317, + "step": 283 + }, + { + "epoch": 1.7861635220125787, + "grad_norm": 0.49889740347862244, + "learning_rate": 2.1080097510381298e-05, + "loss": 0.6046, + "step": 284 + }, + { + "epoch": 1.7924528301886793, + "grad_norm": 0.5512136220932007, + "learning_rate": 2.089939221172446e-05, + "loss": 0.6541, + "step": 285 + }, + { + "epoch": 1.79874213836478, + "grad_norm": 0.5187536478042603, + "learning_rate": 2.07189068162186e-05, + "loss": 0.5646, + "step": 286 + }, + { + "epoch": 1.8050314465408805, + "grad_norm": 0.4920225143432617, + "learning_rate": 2.0538651002747744e-05, + "loss": 0.5561, + "step": 287 + }, + { + "epoch": 1.8113207547169812, + "grad_norm": 0.5807557702064514, + "learning_rate": 2.0358634437884112e-05, + "loss": 0.6087, + "step": 288 + }, + { + "epoch": 1.8176100628930818, + "grad_norm": 0.48779597878456116, + "learning_rate": 2.0178866775369777e-05, + "loss": 0.5801, + "step": 289 + }, + { + "epoch": 1.8238993710691824, + "grad_norm": 0.47587329149246216, + "learning_rate": 1.9999357655598893e-05, + "loss": 0.6003, + "step": 290 + }, + { + "epoch": 1.830188679245283, + "grad_norm": 0.5073649883270264, + "learning_rate": 1.9820116705100777e-05, + "loss": 0.5838, + "step": 291 + }, + { + "epoch": 1.8364779874213837, + "grad_norm": 0.5661832690238953, + "learning_rate": 1.9641153536023644e-05, + "loss": 0.6054, + "step": 292 + }, + { + "epoch": 1.8427672955974843, + "grad_norm": 0.4822792410850525, + "learning_rate": 1.9462477745619108e-05, + "loss": 0.5515, + "step": 293 + }, + { + "epoch": 1.849056603773585, + "grad_norm": 0.5438389182090759, + "learning_rate": 1.928409891572757e-05, + "loss": 0.6225, + "step": 294 + }, + { + "epoch": 1.8553459119496856, + "grad_norm": 0.4644525647163391, + "learning_rate": 1.9106026612264316e-05, + "loss": 0.6214, + "step": 295 + }, + { + "epoch": 1.8616352201257862, + "grad_norm": 0.477500855922699, + "learning_rate": 1.8928270384706584e-05, + "loss": 0.6164, + "step": 296 + }, + { + "epoch": 1.8679245283018868, + "grad_norm": 0.4944886267185211, + "learning_rate": 1.875083976558136e-05, + "loss": 0.5533, + "step": 297 + }, + { + "epoch": 1.8742138364779874, + "grad_norm": 0.5480766892433167, + "learning_rate": 1.8573744269954298e-05, + "loss": 0.6305, + "step": 298 + }, + { + "epoch": 1.880503144654088, + "grad_norm": 0.5053893327713013, + "learning_rate": 1.8396993394919372e-05, + "loss": 0.574, + "step": 299 + }, + { + "epoch": 1.8867924528301887, + "grad_norm": 0.559573233127594, + "learning_rate": 1.8220596619089576e-05, + "loss": 0.7138, + "step": 300 + }, + { + "epoch": 1.8930817610062893, + "grad_norm": 0.5412449836730957, + "learning_rate": 1.8044563402088684e-05, + "loss": 0.6108, + "step": 301 + }, + { + "epoch": 1.89937106918239, + "grad_norm": 0.49840930104255676, + "learning_rate": 1.7868903184043887e-05, + "loss": 0.546, + "step": 302 + }, + { + "epoch": 1.9056603773584906, + "grad_norm": 0.6073680520057678, + "learning_rate": 1.7693625385079577e-05, + "loss": 0.5597, + "step": 303 + }, + { + "epoch": 1.9119496855345912, + "grad_norm": 0.5452404022216797, + "learning_rate": 1.7518739404812155e-05, + "loss": 0.6107, + "step": 304 + }, + { + "epoch": 1.9182389937106918, + "grad_norm": 0.48530417680740356, + "learning_rate": 1.7344254621846016e-05, + "loss": 0.5671, + "step": 305 + }, + { + "epoch": 1.9245283018867925, + "grad_norm": 0.47276559472084045, + "learning_rate": 1.7170180393270532e-05, + "loss": 0.5503, + "step": 306 + }, + { + "epoch": 1.930817610062893, + "grad_norm": 0.4949149191379547, + "learning_rate": 1.699652605415828e-05, + "loss": 0.4958, + "step": 307 + }, + { + "epoch": 1.9371069182389937, + "grad_norm": 0.5216560363769531, + "learning_rate": 1.682330091706446e-05, + "loss": 0.58, + "step": 308 + }, + { + "epoch": 1.9433962264150944, + "grad_norm": 0.5286461710929871, + "learning_rate": 1.6650514271527468e-05, + "loss": 0.5293, + "step": 309 + }, + { + "epoch": 1.949685534591195, + "grad_norm": 0.4912795424461365, + "learning_rate": 1.647817538357072e-05, + "loss": 0.5666, + "step": 310 + }, + { + "epoch": 1.9559748427672956, + "grad_norm": 0.5797849297523499, + "learning_rate": 1.630629349520576e-05, + "loss": 0.5493, + "step": 311 + }, + { + "epoch": 1.9622641509433962, + "grad_norm": 0.5302536487579346, + "learning_rate": 1.613487782393661e-05, + "loss": 0.5516, + "step": 312 + }, + { + "epoch": 1.9685534591194969, + "grad_norm": 0.5543875694274902, + "learning_rate": 1.5963937562265525e-05, + "loss": 0.5358, + "step": 313 + }, + { + "epoch": 1.9748427672955975, + "grad_norm": 0.5673121809959412, + "learning_rate": 1.5793481877199946e-05, + "loss": 0.5332, + "step": 314 + }, + { + "epoch": 1.9811320754716981, + "grad_norm": 0.508794367313385, + "learning_rate": 1.5623519909760954e-05, + "loss": 0.5968, + "step": 315 + }, + { + "epoch": 1.9874213836477987, + "grad_norm": 0.5409150719642639, + "learning_rate": 1.5454060774493068e-05, + "loss": 0.6077, + "step": 316 + }, + { + "epoch": 1.9937106918238994, + "grad_norm": 0.5045109987258911, + "learning_rate": 1.528511355897543e-05, + "loss": 0.5503, + "step": 317 + }, + { + "epoch": 2.0, + "grad_norm": 0.6411352157592773, + "learning_rate": 1.5116687323334467e-05, + "loss": 0.6122, + "step": 318 + }, + { + "epoch": 2.006289308176101, + "grad_norm": 0.5026600360870361, + "learning_rate": 1.4948791099758052e-05, + "loss": 0.5369, + "step": 319 + }, + { + "epoch": 2.0125786163522013, + "grad_norm": 0.511720597743988, + "learning_rate": 1.4781433892011131e-05, + "loss": 0.5291, + "step": 320 + }, + { + "epoch": 2.018867924528302, + "grad_norm": 0.48618605732917786, + "learning_rate": 1.4614624674952842e-05, + "loss": 0.5378, + "step": 321 + }, + { + "epoch": 2.0251572327044025, + "grad_norm": 0.545242190361023, + "learning_rate": 1.4448372394055249e-05, + "loss": 0.5048, + "step": 322 + }, + { + "epoch": 2.0314465408805034, + "grad_norm": 0.5334264636039734, + "learning_rate": 1.4282685964923642e-05, + "loss": 0.5401, + "step": 323 + }, + { + "epoch": 2.0377358490566038, + "grad_norm": 0.5524183511734009, + "learning_rate": 1.4117574272818388e-05, + "loss": 0.5099, + "step": 324 + }, + { + "epoch": 2.0440251572327046, + "grad_norm": 0.48006343841552734, + "learning_rate": 1.3953046172178414e-05, + "loss": 0.4566, + "step": 325 + }, + { + "epoch": 2.050314465408805, + "grad_norm": 0.45758774876594543, + "learning_rate": 1.378911048614647e-05, + "loss": 0.4861, + "step": 326 + }, + { + "epoch": 2.056603773584906, + "grad_norm": 0.583585262298584, + "learning_rate": 1.3625776006095881e-05, + "loss": 0.5896, + "step": 327 + }, + { + "epoch": 2.0628930817610063, + "grad_norm": 0.5123708844184875, + "learning_rate": 1.3463051491159096e-05, + "loss": 0.5174, + "step": 328 + }, + { + "epoch": 2.069182389937107, + "grad_norm": 0.5508242845535278, + "learning_rate": 1.3300945667758014e-05, + "loss": 0.5042, + "step": 329 + }, + { + "epoch": 2.0754716981132075, + "grad_norm": 0.5526241660118103, + "learning_rate": 1.3139467229135999e-05, + "loss": 0.5457, + "step": 330 + }, + { + "epoch": 2.0817610062893084, + "grad_norm": 0.5903204083442688, + "learning_rate": 1.2978624834891628e-05, + "loss": 0.5299, + "step": 331 + }, + { + "epoch": 2.088050314465409, + "grad_norm": 0.5764947533607483, + "learning_rate": 1.281842711051438e-05, + "loss": 0.512, + "step": 332 + }, + { + "epoch": 2.0943396226415096, + "grad_norm": 0.5653167963027954, + "learning_rate": 1.2658882646922034e-05, + "loss": 0.5131, + "step": 333 + }, + { + "epoch": 2.10062893081761, + "grad_norm": 0.5843393206596375, + "learning_rate": 1.2500000000000006e-05, + "loss": 0.5383, + "step": 334 + }, + { + "epoch": 2.106918238993711, + "grad_norm": 0.6287145614624023, + "learning_rate": 1.2341787690142437e-05, + "loss": 0.5715, + "step": 335 + }, + { + "epoch": 2.1132075471698113, + "grad_norm": 0.5734768509864807, + "learning_rate": 1.2184254201795365e-05, + "loss": 0.548, + "step": 336 + }, + { + "epoch": 2.119496855345912, + "grad_norm": 0.5723345279693604, + "learning_rate": 1.2027407983001681e-05, + "loss": 0.4989, + "step": 337 + }, + { + "epoch": 2.1257861635220126, + "grad_norm": 0.6128413677215576, + "learning_rate": 1.1871257444948098e-05, + "loss": 0.5775, + "step": 338 + }, + { + "epoch": 2.1320754716981134, + "grad_norm": 0.7310327887535095, + "learning_rate": 1.1715810961514073e-05, + "loss": 0.5642, + "step": 339 + }, + { + "epoch": 2.138364779874214, + "grad_norm": 0.6413530707359314, + "learning_rate": 1.1561076868822756e-05, + "loss": 0.571, + "step": 340 + }, + { + "epoch": 2.1446540880503147, + "grad_norm": 0.6232360601425171, + "learning_rate": 1.1407063464793966e-05, + "loss": 0.4891, + "step": 341 + }, + { + "epoch": 2.150943396226415, + "grad_norm": 0.5760077238082886, + "learning_rate": 1.1253779008699131e-05, + "loss": 0.5196, + "step": 342 + }, + { + "epoch": 2.157232704402516, + "grad_norm": 0.5411508083343506, + "learning_rate": 1.1101231720718442e-05, + "loss": 0.479, + "step": 343 + }, + { + "epoch": 2.1635220125786163, + "grad_norm": 0.5932305455207825, + "learning_rate": 1.09494297815e-05, + "loss": 0.4888, + "step": 344 + }, + { + "epoch": 2.169811320754717, + "grad_norm": 0.5784667730331421, + "learning_rate": 1.0798381331721109e-05, + "loss": 0.5119, + "step": 345 + }, + { + "epoch": 2.1761006289308176, + "grad_norm": 0.663508415222168, + "learning_rate": 1.0648094471651724e-05, + "loss": 0.497, + "step": 346 + }, + { + "epoch": 2.1823899371069184, + "grad_norm": 0.5773563981056213, + "learning_rate": 1.049857726072005e-05, + "loss": 0.5013, + "step": 347 + }, + { + "epoch": 2.188679245283019, + "grad_norm": 0.697320282459259, + "learning_rate": 1.034983771708035e-05, + "loss": 0.6453, + "step": 348 + }, + { + "epoch": 2.1949685534591197, + "grad_norm": 0.5786930918693542, + "learning_rate": 1.020188381718295e-05, + "loss": 0.5044, + "step": 349 + }, + { + "epoch": 2.20125786163522, + "grad_norm": 0.6295438408851624, + "learning_rate": 1.0054723495346482e-05, + "loss": 0.594, + "step": 350 + }, + { + "epoch": 2.207547169811321, + "grad_norm": 0.6185433864593506, + "learning_rate": 9.908364643332399e-06, + "loss": 0.5059, + "step": 351 + }, + { + "epoch": 2.2138364779874213, + "grad_norm": 0.6029584407806396, + "learning_rate": 9.762815109921761e-06, + "loss": 0.5069, + "step": 352 + }, + { + "epoch": 2.220125786163522, + "grad_norm": 0.6533452272415161, + "learning_rate": 9.618082700494319e-06, + "loss": 0.5232, + "step": 353 + }, + { + "epoch": 2.2264150943396226, + "grad_norm": 0.6175459027290344, + "learning_rate": 9.474175176609956e-06, + "loss": 0.5466, + "step": 354 + }, + { + "epoch": 2.2327044025157234, + "grad_norm": 0.5657399892807007, + "learning_rate": 9.331100255592437e-06, + "loss": 0.4564, + "step": 355 + }, + { + "epoch": 2.238993710691824, + "grad_norm": 0.6779638528823853, + "learning_rate": 9.18886561011557e-06, + "loss": 0.5621, + "step": 356 + }, + { + "epoch": 2.2452830188679247, + "grad_norm": 0.5873716473579407, + "learning_rate": 9.047478867791732e-06, + "loss": 0.4575, + "step": 357 + }, + { + "epoch": 2.251572327044025, + "grad_norm": 0.5723773837089539, + "learning_rate": 8.906947610762825e-06, + "loss": 0.4867, + "step": 358 + }, + { + "epoch": 2.257861635220126, + "grad_norm": 0.6322399377822876, + "learning_rate": 8.767279375293672e-06, + "loss": 0.5453, + "step": 359 + }, + { + "epoch": 2.2641509433962264, + "grad_norm": 0.6071794033050537, + "learning_rate": 8.628481651367876e-06, + "loss": 0.5465, + "step": 360 + }, + { + "epoch": 2.270440251572327, + "grad_norm": 0.7954049110412598, + "learning_rate": 8.490561882286136e-06, + "loss": 0.5327, + "step": 361 + }, + { + "epoch": 2.2767295597484276, + "grad_norm": 0.5613401532173157, + "learning_rate": 8.353527464267104e-06, + "loss": 0.4759, + "step": 362 + }, + { + "epoch": 2.2830188679245285, + "grad_norm": 0.677384614944458, + "learning_rate": 8.217385746050742e-06, + "loss": 0.5186, + "step": 363 + }, + { + "epoch": 2.289308176100629, + "grad_norm": 0.6257275938987732, + "learning_rate": 8.082144028504233e-06, + "loss": 0.5786, + "step": 364 + }, + { + "epoch": 2.2955974842767297, + "grad_norm": 0.6544857025146484, + "learning_rate": 7.947809564230445e-06, + "loss": 0.4792, + "step": 365 + }, + { + "epoch": 2.30188679245283, + "grad_norm": 0.6507861614227295, + "learning_rate": 7.814389557179017e-06, + "loss": 0.5567, + "step": 366 + }, + { + "epoch": 2.308176100628931, + "grad_norm": 0.6414310336112976, + "learning_rate": 7.681891162260015e-06, + "loss": 0.5227, + "step": 367 + }, + { + "epoch": 2.3144654088050314, + "grad_norm": 0.6640331149101257, + "learning_rate": 7.5503214849602516e-06, + "loss": 0.5339, + "step": 368 + }, + { + "epoch": 2.3207547169811322, + "grad_norm": 0.6685804128646851, + "learning_rate": 7.419687580962223e-06, + "loss": 0.4857, + "step": 369 + }, + { + "epoch": 2.3270440251572326, + "grad_norm": 0.6468353271484375, + "learning_rate": 7.289996455765749e-06, + "loss": 0.4588, + "step": 370 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.5642632842063904, + "learning_rate": 7.161255064312283e-06, + "loss": 0.4676, + "step": 371 + }, + { + "epoch": 2.339622641509434, + "grad_norm": 0.583641529083252, + "learning_rate": 7.033470310611945e-06, + "loss": 0.5441, + "step": 372 + }, + { + "epoch": 2.3459119496855347, + "grad_norm": 0.6600673198699951, + "learning_rate": 6.906649047373246e-06, + "loss": 0.5144, + "step": 373 + }, + { + "epoch": 2.352201257861635, + "grad_norm": 0.6383036971092224, + "learning_rate": 6.780798075635675e-06, + "loss": 0.454, + "step": 374 + }, + { + "epoch": 2.358490566037736, + "grad_norm": 0.5476061105728149, + "learning_rate": 6.655924144404907e-06, + "loss": 0.4471, + "step": 375 + }, + { + "epoch": 2.3647798742138364, + "grad_norm": 0.6322336792945862, + "learning_rate": 6.532033950290886e-06, + "loss": 0.525, + "step": 376 + }, + { + "epoch": 2.3710691823899372, + "grad_norm": 0.6242497563362122, + "learning_rate": 6.409134137148737e-06, + "loss": 0.5181, + "step": 377 + }, + { + "epoch": 2.3773584905660377, + "grad_norm": 0.6529743075370789, + "learning_rate": 6.28723129572247e-06, + "loss": 0.5105, + "step": 378 + }, + { + "epoch": 2.3836477987421385, + "grad_norm": 0.6641661524772644, + "learning_rate": 6.166331963291519e-06, + "loss": 0.4859, + "step": 379 + }, + { + "epoch": 2.389937106918239, + "grad_norm": 0.6310985088348389, + "learning_rate": 6.046442623320145e-06, + "loss": 0.5136, + "step": 380 + }, + { + "epoch": 2.3962264150943398, + "grad_norm": 0.7812454104423523, + "learning_rate": 5.927569705109828e-06, + "loss": 0.4837, + "step": 381 + }, + { + "epoch": 2.40251572327044, + "grad_norm": 0.7382704019546509, + "learning_rate": 5.809719583454415e-06, + "loss": 0.4962, + "step": 382 + }, + { + "epoch": 2.408805031446541, + "grad_norm": 0.6249539256095886, + "learning_rate": 5.692898578298253e-06, + "loss": 0.5138, + "step": 383 + }, + { + "epoch": 2.4150943396226414, + "grad_norm": 0.6593284010887146, + "learning_rate": 5.577112954397321e-06, + "loss": 0.5097, + "step": 384 + }, + { + "epoch": 2.4213836477987423, + "grad_norm": 0.6821117997169495, + "learning_rate": 5.462368920983249e-06, + "loss": 0.5655, + "step": 385 + }, + { + "epoch": 2.4276729559748427, + "grad_norm": 0.7341055274009705, + "learning_rate": 5.348672631430318e-06, + "loss": 0.511, + "step": 386 + }, + { + "epoch": 2.4339622641509435, + "grad_norm": 0.676941454410553, + "learning_rate": 5.236030182925475e-06, + "loss": 0.4494, + "step": 387 + }, + { + "epoch": 2.440251572327044, + "grad_norm": 0.6467084288597107, + "learning_rate": 5.124447616141381e-06, + "loss": 0.4407, + "step": 388 + }, + { + "epoch": 2.4465408805031448, + "grad_norm": 0.6168628931045532, + "learning_rate": 5.013930914912476e-06, + "loss": 0.5424, + "step": 389 + }, + { + "epoch": 2.452830188679245, + "grad_norm": 0.6204650402069092, + "learning_rate": 4.9044860059140275e-06, + "loss": 0.5222, + "step": 390 + }, + { + "epoch": 2.459119496855346, + "grad_norm": 0.6808157563209534, + "learning_rate": 4.796118758344354e-06, + "loss": 0.5181, + "step": 391 + }, + { + "epoch": 2.4654088050314464, + "grad_norm": 0.6607468128204346, + "learning_rate": 4.6888349836100825e-06, + "loss": 0.5849, + "step": 392 + }, + { + "epoch": 2.4716981132075473, + "grad_norm": 0.6367841362953186, + "learning_rate": 4.58264043501446e-06, + "loss": 0.4938, + "step": 393 + }, + { + "epoch": 2.4779874213836477, + "grad_norm": 0.7117082476615906, + "learning_rate": 4.477540807448832e-06, + "loss": 0.4862, + "step": 394 + }, + { + "epoch": 2.4842767295597485, + "grad_norm": 0.662056565284729, + "learning_rate": 4.373541737087264e-06, + "loss": 0.5753, + "step": 395 + }, + { + "epoch": 2.490566037735849, + "grad_norm": 0.6686725616455078, + "learning_rate": 4.270648801084296e-06, + "loss": 0.555, + "step": 396 + }, + { + "epoch": 2.49685534591195, + "grad_norm": 0.7704941034317017, + "learning_rate": 4.1688675172758064e-06, + "loss": 0.6513, + "step": 397 + }, + { + "epoch": 2.50314465408805, + "grad_norm": 0.6105798482894897, + "learning_rate": 4.068203343883159e-06, + "loss": 0.4985, + "step": 398 + }, + { + "epoch": 2.509433962264151, + "grad_norm": 0.6414272785186768, + "learning_rate": 3.968661679220468e-06, + "loss": 0.4736, + "step": 399 + }, + { + "epoch": 2.5157232704402515, + "grad_norm": 0.6939327120780945, + "learning_rate": 3.8702478614051355e-06, + "loss": 0.567, + "step": 400 + }, + { + "epoch": 2.5220125786163523, + "grad_norm": 0.6539825797080994, + "learning_rate": 3.772967168071517e-06, + "loss": 0.4567, + "step": 401 + }, + { + "epoch": 2.5283018867924527, + "grad_norm": 0.6413926482200623, + "learning_rate": 3.6768248160879787e-06, + "loss": 0.5228, + "step": 402 + }, + { + "epoch": 2.5345911949685536, + "grad_norm": 0.6808522939682007, + "learning_rate": 3.5818259612770744e-06, + "loss": 0.5499, + "step": 403 + }, + { + "epoch": 2.540880503144654, + "grad_norm": 0.704112708568573, + "learning_rate": 3.487975698139084e-06, + "loss": 0.4901, + "step": 404 + }, + { + "epoch": 2.547169811320755, + "grad_norm": 0.7583079934120178, + "learning_rate": 3.3952790595787987e-06, + "loss": 0.5253, + "step": 405 + }, + { + "epoch": 2.5534591194968552, + "grad_norm": 0.6490894556045532, + "learning_rate": 3.3037410166356143e-06, + "loss": 0.5036, + "step": 406 + }, + { + "epoch": 2.559748427672956, + "grad_norm": 0.6950412392616272, + "learning_rate": 3.2133664782169948e-06, + "loss": 0.5155, + "step": 407 + }, + { + "epoch": 2.5660377358490565, + "grad_norm": 0.6417565941810608, + "learning_rate": 3.1241602908351404e-06, + "loss": 0.4473, + "step": 408 + }, + { + "epoch": 2.5723270440251573, + "grad_norm": 0.7289451360702515, + "learning_rate": 3.036127238347164e-06, + "loss": 0.5926, + "step": 409 + }, + { + "epoch": 2.5786163522012577, + "grad_norm": 0.6481583118438721, + "learning_rate": 2.9492720416985e-06, + "loss": 0.4606, + "step": 410 + }, + { + "epoch": 2.5849056603773586, + "grad_norm": 0.6715993881225586, + "learning_rate": 2.8635993586697553e-06, + "loss": 0.5701, + "step": 411 + }, + { + "epoch": 2.591194968553459, + "grad_norm": 0.6455919146537781, + "learning_rate": 2.779113783626916e-06, + "loss": 0.506, + "step": 412 + }, + { + "epoch": 2.59748427672956, + "grad_norm": 0.7350935935974121, + "learning_rate": 2.6958198472749717e-06, + "loss": 0.5624, + "step": 413 + }, + { + "epoch": 2.6037735849056602, + "grad_norm": 0.7309563755989075, + "learning_rate": 2.6137220164149435e-06, + "loss": 0.5052, + "step": 414 + }, + { + "epoch": 2.610062893081761, + "grad_norm": 0.6338467597961426, + "learning_rate": 2.5328246937043526e-06, + "loss": 0.5104, + "step": 415 + }, + { + "epoch": 2.6163522012578615, + "grad_norm": 0.6638092398643494, + "learning_rate": 2.4531322174210975e-06, + "loss": 0.5077, + "step": 416 + }, + { + "epoch": 2.6226415094339623, + "grad_norm": 0.6149672269821167, + "learning_rate": 2.37464886123083e-06, + "loss": 0.5086, + "step": 417 + }, + { + "epoch": 2.6289308176100628, + "grad_norm": 0.676372766494751, + "learning_rate": 2.2973788339577613e-06, + "loss": 0.5189, + "step": 418 + }, + { + "epoch": 2.6352201257861636, + "grad_norm": 0.6536609530448914, + "learning_rate": 2.2213262793589484e-06, + "loss": 0.4974, + "step": 419 + }, + { + "epoch": 2.641509433962264, + "grad_norm": 0.6942263245582581, + "learning_rate": 2.1464952759020855e-06, + "loss": 0.5648, + "step": 420 + }, + { + "epoch": 2.647798742138365, + "grad_norm": 0.642825722694397, + "learning_rate": 2.0728898365467903e-06, + "loss": 0.5149, + "step": 421 + }, + { + "epoch": 2.6540880503144653, + "grad_norm": 0.6079385876655579, + "learning_rate": 2.0005139085293945e-06, + "loss": 0.472, + "step": 422 + }, + { + "epoch": 2.660377358490566, + "grad_norm": 0.715664267539978, + "learning_rate": 1.9293713731512673e-06, + "loss": 0.5368, + "step": 423 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.655768871307373, + "learning_rate": 1.8594660455706763e-06, + "loss": 0.4948, + "step": 424 + }, + { + "epoch": 2.6729559748427674, + "grad_norm": 0.6798547506332397, + "learning_rate": 1.790801674598186e-06, + "loss": 0.5213, + "step": 425 + }, + { + "epoch": 2.6792452830188678, + "grad_norm": 0.7034783959388733, + "learning_rate": 1.7233819424956248e-06, + "loss": 0.6128, + "step": 426 + }, + { + "epoch": 2.6855345911949686, + "grad_norm": 0.6610020995140076, + "learning_rate": 1.6572104647786247e-06, + "loss": 0.5228, + "step": 427 + }, + { + "epoch": 2.691823899371069, + "grad_norm": 0.664659857749939, + "learning_rate": 1.5922907900227018e-06, + "loss": 0.4266, + "step": 428 + }, + { + "epoch": 2.69811320754717, + "grad_norm": 0.6232119202613831, + "learning_rate": 1.5286263996730026e-06, + "loss": 0.476, + "step": 429 + }, + { + "epoch": 2.7044025157232703, + "grad_norm": 0.653411328792572, + "learning_rate": 1.4662207078575684e-06, + "loss": 0.5145, + "step": 430 + }, + { + "epoch": 2.710691823899371, + "grad_norm": 0.7129037380218506, + "learning_rate": 1.40507706120426e-06, + "loss": 0.5546, + "step": 431 + }, + { + "epoch": 2.7169811320754715, + "grad_norm": 0.6307116150856018, + "learning_rate": 1.3451987386612851e-06, + "loss": 0.4598, + "step": 432 + }, + { + "epoch": 2.7232704402515724, + "grad_norm": 0.6527603268623352, + "learning_rate": 1.286588951321363e-06, + "loss": 0.5322, + "step": 433 + }, + { + "epoch": 2.729559748427673, + "grad_norm": 0.6609143018722534, + "learning_rate": 1.2292508422495158e-06, + "loss": 0.5306, + "step": 434 + }, + { + "epoch": 2.7358490566037736, + "grad_norm": 0.6827059388160706, + "learning_rate": 1.1731874863145143e-06, + "loss": 0.5109, + "step": 435 + }, + { + "epoch": 2.742138364779874, + "grad_norm": 0.6002165079116821, + "learning_rate": 1.1184018900240011e-06, + "loss": 0.4579, + "step": 436 + }, + { + "epoch": 2.748427672955975, + "grad_norm": 0.6269481182098389, + "learning_rate": 1.06489699136324e-06, + "loss": 0.4888, + "step": 437 + }, + { + "epoch": 2.7547169811320753, + "grad_norm": 0.6706013679504395, + "learning_rate": 1.0126756596375686e-06, + "loss": 0.5225, + "step": 438 + }, + { + "epoch": 2.761006289308176, + "grad_norm": 0.6613484025001526, + "learning_rate": 9.617406953185138e-07, + "loss": 0.5241, + "step": 439 + }, + { + "epoch": 2.767295597484277, + "grad_norm": 0.7121806740760803, + "learning_rate": 9.120948298936421e-07, + "loss": 0.4887, + "step": 440 + }, + { + "epoch": 2.7735849056603774, + "grad_norm": 0.6842261552810669, + "learning_rate": 8.637407257200497e-07, + "loss": 0.4912, + "step": 441 + }, + { + "epoch": 2.779874213836478, + "grad_norm": 0.70417320728302, + "learning_rate": 8.166809758815896e-07, + "loss": 0.5405, + "step": 442 + }, + { + "epoch": 2.7861635220125787, + "grad_norm": 0.6980416178703308, + "learning_rate": 7.709181040498254e-07, + "loss": 0.5058, + "step": 443 + }, + { + "epoch": 2.7924528301886795, + "grad_norm": 0.6587446331977844, + "learning_rate": 7.264545643486997e-07, + "loss": 0.5572, + "step": 444 + }, + { + "epoch": 2.79874213836478, + "grad_norm": 0.6442897319793701, + "learning_rate": 6.832927412229018e-07, + "loss": 0.5118, + "step": 445 + }, + { + "epoch": 2.8050314465408803, + "grad_norm": 0.6052460670471191, + "learning_rate": 6.41434949310013e-07, + "loss": 0.536, + "step": 446 + }, + { + "epoch": 2.811320754716981, + "grad_norm": 0.7546602487564087, + "learning_rate": 6.008834333163876e-07, + "loss": 0.5397, + "step": 447 + }, + { + "epoch": 2.817610062893082, + "grad_norm": 0.6202664375305176, + "learning_rate": 5.616403678967624e-07, + "loss": 0.4516, + "step": 448 + }, + { + "epoch": 2.8238993710691824, + "grad_norm": 0.6362593173980713, + "learning_rate": 5.237078575376336e-07, + "loss": 0.5106, + "step": 449 + }, + { + "epoch": 2.830188679245283, + "grad_norm": 0.6845952272415161, + "learning_rate": 4.870879364444109e-07, + "loss": 0.5153, + "step": 450 + }, + { + "epoch": 2.8364779874213837, + "grad_norm": 0.659001886844635, + "learning_rate": 4.517825684323324e-07, + "loss": 0.5075, + "step": 451 + }, + { + "epoch": 2.8427672955974845, + "grad_norm": 0.6748611927032471, + "learning_rate": 4.1779364682113796e-07, + "loss": 0.5354, + "step": 452 + }, + { + "epoch": 2.849056603773585, + "grad_norm": 0.6511921286582947, + "learning_rate": 3.851229943335394e-07, + "loss": 0.5468, + "step": 453 + }, + { + "epoch": 2.8553459119496853, + "grad_norm": 0.6114699244499207, + "learning_rate": 3.537723629974815e-07, + "loss": 0.4799, + "step": 454 + }, + { + "epoch": 2.861635220125786, + "grad_norm": 0.717573344707489, + "learning_rate": 3.237434340521789e-07, + "loss": 0.5604, + "step": 455 + }, + { + "epoch": 2.867924528301887, + "grad_norm": 0.6609371900558472, + "learning_rate": 2.9503781785795713e-07, + "loss": 0.4958, + "step": 456 + }, + { + "epoch": 2.8742138364779874, + "grad_norm": 0.7015553712844849, + "learning_rate": 2.6765705380989437e-07, + "loss": 0.551, + "step": 457 + }, + { + "epoch": 2.880503144654088, + "grad_norm": 0.6695305109024048, + "learning_rate": 2.416026102552732e-07, + "loss": 0.5316, + "step": 458 + }, + { + "epoch": 2.8867924528301887, + "grad_norm": 0.6004621386528015, + "learning_rate": 2.168758844148272e-07, + "loss": 0.5416, + "step": 459 + }, + { + "epoch": 2.8930817610062896, + "grad_norm": 0.6895103454589844, + "learning_rate": 1.93478202307823e-07, + "loss": 0.5319, + "step": 460 + }, + { + "epoch": 2.89937106918239, + "grad_norm": 0.6955282092094421, + "learning_rate": 1.7141081868094212e-07, + "loss": 0.5208, + "step": 461 + }, + { + "epoch": 2.9056603773584904, + "grad_norm": 0.6640160083770752, + "learning_rate": 1.5067491694100154e-07, + "loss": 0.5133, + "step": 462 + }, + { + "epoch": 2.911949685534591, + "grad_norm": 0.6678076982498169, + "learning_rate": 1.3127160909147672e-07, + "loss": 0.5107, + "step": 463 + }, + { + "epoch": 2.918238993710692, + "grad_norm": 0.7161384224891663, + "learning_rate": 1.1320193567288529e-07, + "loss": 0.5842, + "step": 464 + }, + { + "epoch": 2.9245283018867925, + "grad_norm": 0.712955117225647, + "learning_rate": 9.646686570697061e-08, + "loss": 0.5275, + "step": 465 + }, + { + "epoch": 2.930817610062893, + "grad_norm": 0.711218535900116, + "learning_rate": 8.106729664475176e-08, + "loss": 0.4815, + "step": 466 + }, + { + "epoch": 2.9371069182389937, + "grad_norm": 0.6556484699249268, + "learning_rate": 6.700405431837587e-08, + "loss": 0.4802, + "step": 467 + }, + { + "epoch": 2.9433962264150946, + "grad_norm": 0.6334600448608398, + "learning_rate": 5.4277892896853476e-08, + "loss": 0.5044, + "step": 468 + }, + { + "epoch": 2.949685534591195, + "grad_norm": 0.6841341257095337, + "learning_rate": 4.2889494845599344e-08, + "loss": 0.5601, + "step": 469 + }, + { + "epoch": 2.9559748427672954, + "grad_norm": 0.6439110040664673, + "learning_rate": 3.283947088983663e-08, + "loss": 0.4279, + "step": 470 + }, + { + "epoch": 2.9622641509433962, + "grad_norm": 0.593614935874939, + "learning_rate": 2.4128359981850924e-08, + "loss": 0.483, + "step": 471 + }, + { + "epoch": 2.968553459119497, + "grad_norm": 0.6519297957420349, + "learning_rate": 1.6756629272085545e-08, + "loss": 0.5921, + "step": 472 + }, + { + "epoch": 2.9748427672955975, + "grad_norm": 0.6468663215637207, + "learning_rate": 1.0724674084083841e-08, + "loss": 0.4751, + "step": 473 + }, + { + "epoch": 2.981132075471698, + "grad_norm": 0.6676617860794067, + "learning_rate": 6.032817893297793e-09, + "loss": 0.4994, + "step": 474 + }, + { + "epoch": 2.9874213836477987, + "grad_norm": 0.6803402900695801, + "learning_rate": 2.681312309735229e-09, + "loss": 0.5308, + "step": 475 + }, + { + "epoch": 2.9937106918238996, + "grad_norm": 0.6511867642402649, + "learning_rate": 6.703370644706164e-10, + "loss": 0.5177, + "step": 476 + }, + { + "epoch": 3.0, + "grad_norm": 0.7002833485603333, + "learning_rate": 0.0, + "loss": 0.4149, + "step": 477 + }, + { + "epoch": 3.0, + "step": 477, + "total_flos": 4.746880321608352e+18, + "train_loss": 0.7064950698576633, + "train_runtime": 33423.533, + "train_samples_per_second": 1.825, + "train_steps_per_second": 0.014 + } + ], + "logging_steps": 1, + "max_steps": 477, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 4.746880321608352e+18, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f2a1106da97275ded3721a2b9ad28a19b5c9872 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d245efe4cb1811ec2cffc23b4d3aa9a49d1d65e92b8d678bec9a399e5c1889e +size 5496 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..69c69064a05ad8c297fe2a8748399952e4957524 Binary files /dev/null and b/training_loss.png differ