diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..d0f5b168a289c13ecd8f40990b389a735afc651e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,14 @@ 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 +sft_worldsplit_1_5b/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-160/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-378/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text +sft_worldsplit_1_5b/final/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/sft_worldsplit_1_5b/README.md b/sft_worldsplit_1_5b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..719863362c6105ea819195d17efdf3b8d5219336 --- /dev/null +++ b/sft_worldsplit_1_5b/README.md @@ -0,0 +1,60 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: transformers +model_name: sft_worldsplit_1_5b +tags: +- generated_from_trainer +- unsloth +- hf_jobs +- trl +- sft +licence: license +--- + +# Model Card for sft_worldsplit_1_5b + +This model is a fine-tuned version of [unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + +This model was trained with SFT. + +### Framework versions + +- TRL: 0.24.0 +- Transformers: 5.5.0 +- Pytorch: 2.10.0 +- Datasets: 4.3.0 +- Tokenizers: 0.22.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@misc{vonwerra2022trl, + title = {{TRL: Transformer Reinforcement Learning}}, + author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, + year = 2020, + journal = {GitHub repository}, + publisher = {GitHub}, + howpublished = {\url{https://github.com/huggingface/trl}} +} +``` \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-120/README.md b/sft_worldsplit_1_5b/checkpoint-120/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-120/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-120/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-120/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-120/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7212450f3018d571295aad7e61b7f0c50e666ad7 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080d2fbacd4048cd6dd8e7846b2829afb32705383ca19a4398ed9c385bafaca7 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-120/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-120/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-120/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-120/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f69d925c695bdf68e9baf0b777a8bfd198c4331e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d261c9ffca9066c16e9a4ed5c20acb627e2dcb4789c59197d467b6f5c2fa492b +size 37969669 diff --git a/sft_worldsplit_1_5b/checkpoint-120/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-120/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-120/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-120/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..48deffcaa76e667f37e993070f650b1ec616964d --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e7b373c59277136abd02a07580dbf88116614ccc7f063a8e58725457a42c56 +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-120/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-120/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-120/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-120/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-120/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-120/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..06cf60d7a5b1b9c52556d804eefbde6d2f20c678 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/trainer_state.json @@ -0,0 +1,874 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.31746031746031744, + "eval_steps": 500, + "global_step": 120, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4638466241224704.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-120/training_args.bin b/sft_worldsplit_1_5b/checkpoint-120/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-120/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-160/README.md b/sft_worldsplit_1_5b/checkpoint-160/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-160/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-160/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-160/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-160/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16165b3ad704d72897d86cea7c44d42d2219c20c --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5faca62be383035cd046d6ac7fec84a0d459001a73295075b053a9108b409f5 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-160/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-160/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-160/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-160/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a41b8c5731fa8976d6145d557d95202a88f6e847 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3f1cd74334940078bba2b1140fad77936c3cc62dcdb7cd08dc274ba5e6e9988 +size 37969669 diff --git a/sft_worldsplit_1_5b/checkpoint-160/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-160/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-160/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-160/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8417285fc9077ffd299c3dc5d2b23c1f7b9e7149 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97edbd54771e05bd6b0b4f8cace6ea41f902d4ba2ed428bd6feff8823b3ba2fc +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-160/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-160/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-160/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-160/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-160/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-160/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1364feb22637f20b1a27a3e4bff985acd5c45c84 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/trainer_state.json @@ -0,0 +1,1154 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.42328042328042326, + "eval_steps": 500, + "global_step": 160, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6228687498845184.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-160/training_args.bin b/sft_worldsplit_1_5b/checkpoint-160/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-160/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-200/README.md b/sft_worldsplit_1_5b/checkpoint-200/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-200/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-200/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-200/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-200/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93333864d1c6e479a099b54f161a8c85901ea774 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adbd4be524ce325824b0938a980ccc2b1880bb855da22b23d1c988f5690414f +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-200/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-200/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-200/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..9201db32a42d0615340ac6ee5028d5c39943db50 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefcb95410804f18adeccfdfa9d78df683b94b083f25ac23c8fea229abc8d267 +size 37969669 diff --git a/sft_worldsplit_1_5b/checkpoint-200/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-200/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea518779bc1c2fd1f59ad0fdc0ad08ef9fc77031 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bda535de5ddf5d4f48adf28841b25dcd101db71afacb38d952ac9d56622170b +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-200/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-200/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-200/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-200/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-200/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b4278404ac992e5ddb108fe1167819b7733c1519 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/trainer_state.json @@ -0,0 +1,1434 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5291005291005291, + "eval_steps": 500, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + }, + { + "epoch": 0.42592592592592593, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "loss": 0.03136860206723213, + "step": 161 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "loss": 0.02894529700279236, + "step": 162 + }, + { + "epoch": 0.4312169312169312, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "loss": 0.033732134848833084, + "step": 163 + }, + { + "epoch": 0.43386243386243384, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "loss": 0.026288658380508423, + "step": 164 + }, + { + "epoch": 0.4365079365079365, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "loss": 0.03067208267748356, + "step": 165 + }, + { + "epoch": 0.43915343915343913, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "loss": 0.027257606387138367, + "step": 166 + }, + { + "epoch": 0.4417989417989418, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "loss": 0.020257430151104927, + "step": 167 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "loss": 0.025873055681586266, + "step": 168 + }, + { + "epoch": 0.4470899470899471, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "loss": 0.02722345106303692, + "step": 169 + }, + { + "epoch": 0.4497354497354497, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "loss": 0.0284090805798769, + "step": 170 + }, + { + "epoch": 0.4523809523809524, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "loss": 0.0273237656801939, + "step": 171 + }, + { + "epoch": 0.455026455026455, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "loss": 0.03370822221040726, + "step": 172 + }, + { + "epoch": 0.4576719576719577, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "loss": 0.018664535135030746, + "step": 173 + }, + { + "epoch": 0.4603174603174603, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "loss": 0.029450563713908195, + "step": 174 + }, + { + "epoch": 0.46296296296296297, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "loss": 0.02172383852303028, + "step": 175 + }, + { + "epoch": 0.4656084656084656, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "loss": 0.029448989778757095, + "step": 176 + }, + { + "epoch": 0.46825396825396826, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "loss": 0.023345600813627243, + "step": 177 + }, + { + "epoch": 0.4708994708994709, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "loss": 0.026639586314558983, + "step": 178 + }, + { + "epoch": 0.47354497354497355, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "loss": 0.021892163902521133, + "step": 179 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "loss": 0.022277187556028366, + "step": 180 + }, + { + "epoch": 0.47883597883597884, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "loss": 0.03035702183842659, + "step": 181 + }, + { + "epoch": 0.48148148148148145, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "loss": 0.03421338275074959, + "step": 182 + }, + { + "epoch": 0.48412698412698413, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "loss": 0.029597604647278786, + "step": 183 + }, + { + "epoch": 0.48677248677248675, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "loss": 0.027550101280212402, + "step": 184 + }, + { + "epoch": 0.4894179894179894, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "loss": 0.03323390707373619, + "step": 185 + }, + { + "epoch": 0.49206349206349204, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "loss": 0.02156604826450348, + "step": 186 + }, + { + "epoch": 0.4947089947089947, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "loss": 0.024817658588290215, + "step": 187 + }, + { + "epoch": 0.4973544973544973, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "loss": 0.02846340462565422, + "step": 188 + }, + { + "epoch": 0.5, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "loss": 0.016268836334347725, + "step": 189 + }, + { + "epoch": 0.5026455026455027, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "loss": 0.02841845154762268, + "step": 190 + }, + { + "epoch": 0.5052910052910053, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "loss": 0.0306367389857769, + "step": 191 + }, + { + "epoch": 0.5079365079365079, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "loss": 0.031015485525131226, + "step": 192 + }, + { + "epoch": 0.5105820105820106, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "loss": 0.03242127224802971, + "step": 193 + }, + { + "epoch": 0.5132275132275133, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "loss": 0.03684879094362259, + "step": 194 + }, + { + "epoch": 0.5158730158730159, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "loss": 0.0260506309568882, + "step": 195 + }, + { + "epoch": 0.5185185185185185, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "loss": 0.02128693461418152, + "step": 196 + }, + { + "epoch": 0.5211640211640212, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "loss": 0.03452152758836746, + "step": 197 + }, + { + "epoch": 0.5238095238095238, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "loss": 0.028310813009738922, + "step": 198 + }, + { + "epoch": 0.5264550264550265, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "loss": 0.029575366526842117, + "step": 199 + }, + { + "epoch": 0.5291005291005291, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "loss": 0.029606211930513382, + "step": 200 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7830333825088512.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-200/training_args.bin b/sft_worldsplit_1_5b/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-240/README.md b/sft_worldsplit_1_5b/checkpoint-240/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-240/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-240/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-240/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-240/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a09e545e80bf6554e7addd98d785a7ff0127fa19 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632441508debaaf01514acddb4c8eea89ccf062ff0630b13013451ea774f46cf +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-240/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-240/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-240/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-240/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f05dba4ad03bfaba9d9c7b5c5442d5fa2a9ef32 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70baaef5d3a74e84e038887af5564c17b3a4e4748a4195126ca00b27854de76 +size 37969669 diff --git a/sft_worldsplit_1_5b/checkpoint-240/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-240/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-240/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-240/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c63b7be26cb336ae80d691204f1896f2448ac127 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b31502269c869f7b15401be3e2c78a1c5c68d03918c847333cdd44a94126e2c +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-240/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-240/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-240/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-240/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-240/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-240/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6019d2e5ca0d6aa23c207ccd8a2610d90e61864a --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/trainer_state.json @@ -0,0 +1,1714 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6349206349206349, + "eval_steps": 500, + "global_step": 240, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + }, + { + "epoch": 0.42592592592592593, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "loss": 0.03136860206723213, + "step": 161 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "loss": 0.02894529700279236, + "step": 162 + }, + { + "epoch": 0.4312169312169312, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "loss": 0.033732134848833084, + "step": 163 + }, + { + "epoch": 0.43386243386243384, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "loss": 0.026288658380508423, + "step": 164 + }, + { + "epoch": 0.4365079365079365, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "loss": 0.03067208267748356, + "step": 165 + }, + { + "epoch": 0.43915343915343913, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "loss": 0.027257606387138367, + "step": 166 + }, + { + "epoch": 0.4417989417989418, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "loss": 0.020257430151104927, + "step": 167 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "loss": 0.025873055681586266, + "step": 168 + }, + { + "epoch": 0.4470899470899471, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "loss": 0.02722345106303692, + "step": 169 + }, + { + "epoch": 0.4497354497354497, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "loss": 0.0284090805798769, + "step": 170 + }, + { + "epoch": 0.4523809523809524, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "loss": 0.0273237656801939, + "step": 171 + }, + { + "epoch": 0.455026455026455, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "loss": 0.03370822221040726, + "step": 172 + }, + { + "epoch": 0.4576719576719577, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "loss": 0.018664535135030746, + "step": 173 + }, + { + "epoch": 0.4603174603174603, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "loss": 0.029450563713908195, + "step": 174 + }, + { + "epoch": 0.46296296296296297, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "loss": 0.02172383852303028, + "step": 175 + }, + { + "epoch": 0.4656084656084656, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "loss": 0.029448989778757095, + "step": 176 + }, + { + "epoch": 0.46825396825396826, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "loss": 0.023345600813627243, + "step": 177 + }, + { + "epoch": 0.4708994708994709, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "loss": 0.026639586314558983, + "step": 178 + }, + { + "epoch": 0.47354497354497355, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "loss": 0.021892163902521133, + "step": 179 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "loss": 0.022277187556028366, + "step": 180 + }, + { + "epoch": 0.47883597883597884, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "loss": 0.03035702183842659, + "step": 181 + }, + { + "epoch": 0.48148148148148145, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "loss": 0.03421338275074959, + "step": 182 + }, + { + "epoch": 0.48412698412698413, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "loss": 0.029597604647278786, + "step": 183 + }, + { + "epoch": 0.48677248677248675, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "loss": 0.027550101280212402, + "step": 184 + }, + { + "epoch": 0.4894179894179894, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "loss": 0.03323390707373619, + "step": 185 + }, + { + "epoch": 0.49206349206349204, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "loss": 0.02156604826450348, + "step": 186 + }, + { + "epoch": 0.4947089947089947, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "loss": 0.024817658588290215, + "step": 187 + }, + { + "epoch": 0.4973544973544973, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "loss": 0.02846340462565422, + "step": 188 + }, + { + "epoch": 0.5, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "loss": 0.016268836334347725, + "step": 189 + }, + { + "epoch": 0.5026455026455027, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "loss": 0.02841845154762268, + "step": 190 + }, + { + "epoch": 0.5052910052910053, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "loss": 0.0306367389857769, + "step": 191 + }, + { + "epoch": 0.5079365079365079, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "loss": 0.031015485525131226, + "step": 192 + }, + { + "epoch": 0.5105820105820106, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "loss": 0.03242127224802971, + "step": 193 + }, + { + "epoch": 0.5132275132275133, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "loss": 0.03684879094362259, + "step": 194 + }, + { + "epoch": 0.5158730158730159, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "loss": 0.0260506309568882, + "step": 195 + }, + { + "epoch": 0.5185185185185185, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "loss": 0.02128693461418152, + "step": 196 + }, + { + "epoch": 0.5211640211640212, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "loss": 0.03452152758836746, + "step": 197 + }, + { + "epoch": 0.5238095238095238, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "loss": 0.028310813009738922, + "step": 198 + }, + { + "epoch": 0.5264550264550265, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "loss": 0.029575366526842117, + "step": 199 + }, + { + "epoch": 0.5291005291005291, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "loss": 0.029606211930513382, + "step": 200 + }, + { + "epoch": 0.5317460317460317, + "grad_norm": 0.09481994062662125, + "learning_rate": 0.00010470588235294118, + "loss": 0.02741779386997223, + "step": 201 + }, + { + "epoch": 0.5343915343915344, + "grad_norm": 0.06643011420965195, + "learning_rate": 0.00010411764705882355, + "loss": 0.02750249207019806, + "step": 202 + }, + { + "epoch": 0.5370370370370371, + "grad_norm": 0.08693543821573257, + "learning_rate": 0.0001035294117647059, + "loss": 0.025049429386854172, + "step": 203 + }, + { + "epoch": 0.5396825396825397, + "grad_norm": 0.08780419826507568, + "learning_rate": 0.00010294117647058823, + "loss": 0.0188161451369524, + "step": 204 + }, + { + "epoch": 0.5423280423280423, + "grad_norm": 0.08089763671159744, + "learning_rate": 0.00010235294117647058, + "loss": 0.025752779096364975, + "step": 205 + }, + { + "epoch": 0.544973544973545, + "grad_norm": 0.11511234939098358, + "learning_rate": 0.00010176470588235295, + "loss": 0.03086625598371029, + "step": 206 + }, + { + "epoch": 0.5476190476190477, + "grad_norm": 0.10907749086618423, + "learning_rate": 0.0001011764705882353, + "loss": 0.0273880697786808, + "step": 207 + }, + { + "epoch": 0.5502645502645502, + "grad_norm": 0.08107511699199677, + "learning_rate": 0.00010058823529411765, + "loss": 0.026370292529463768, + "step": 208 + }, + { + "epoch": 0.5529100529100529, + "grad_norm": 0.0737859457731247, + "learning_rate": 0.0001, + "loss": 0.025786038488149643, + "step": 209 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.09232968837022781, + "learning_rate": 9.941176470588236e-05, + "loss": 0.030016383156180382, + "step": 210 + }, + { + "epoch": 0.5582010582010583, + "grad_norm": 0.0948951318860054, + "learning_rate": 9.882352941176471e-05, + "loss": 0.021605785936117172, + "step": 211 + }, + { + "epoch": 0.5608465608465608, + "grad_norm": 0.09735886752605438, + "learning_rate": 9.823529411764706e-05, + "loss": 0.031091010197997093, + "step": 212 + }, + { + "epoch": 0.5634920634920635, + "grad_norm": 0.10056869685649872, + "learning_rate": 9.764705882352942e-05, + "loss": 0.030390700325369835, + "step": 213 + }, + { + "epoch": 0.5661375661375662, + "grad_norm": 0.0720759853720665, + "learning_rate": 9.705882352941177e-05, + "loss": 0.02216975763440132, + "step": 214 + }, + { + "epoch": 0.5687830687830688, + "grad_norm": 0.09141097962856293, + "learning_rate": 9.647058823529412e-05, + "loss": 0.02660333178937435, + "step": 215 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.09253139793872833, + "learning_rate": 9.588235294117648e-05, + "loss": 0.02590668946504593, + "step": 216 + }, + { + "epoch": 0.5740740740740741, + "grad_norm": 0.08869278430938721, + "learning_rate": 9.529411764705883e-05, + "loss": 0.02776462584733963, + "step": 217 + }, + { + "epoch": 0.5767195767195767, + "grad_norm": 0.10566668212413788, + "learning_rate": 9.470588235294118e-05, + "loss": 0.015304268337786198, + "step": 218 + }, + { + "epoch": 0.5793650793650794, + "grad_norm": 0.08862630277872086, + "learning_rate": 9.411764705882353e-05, + "loss": 0.027874145656824112, + "step": 219 + }, + { + "epoch": 0.582010582010582, + "grad_norm": 0.0958574190735817, + "learning_rate": 9.352941176470589e-05, + "loss": 0.030754802748560905, + "step": 220 + }, + { + "epoch": 0.5846560846560847, + "grad_norm": 0.09204437583684921, + "learning_rate": 9.294117647058824e-05, + "loss": 0.023360423743724823, + "step": 221 + }, + { + "epoch": 0.5873015873015873, + "grad_norm": 0.12147050350904465, + "learning_rate": 9.23529411764706e-05, + "loss": 0.031416505575180054, + "step": 222 + }, + { + "epoch": 0.58994708994709, + "grad_norm": 0.08076925575733185, + "learning_rate": 9.176470588235295e-05, + "loss": 0.023884786292910576, + "step": 223 + }, + { + "epoch": 0.5925925925925926, + "grad_norm": 0.08516595512628555, + "learning_rate": 9.11764705882353e-05, + "loss": 0.025108790025115013, + "step": 224 + }, + { + "epoch": 0.5952380952380952, + "grad_norm": 0.09453090280294418, + "learning_rate": 9.058823529411765e-05, + "loss": 0.0236780047416687, + "step": 225 + }, + { + "epoch": 0.5978835978835979, + "grad_norm": 0.08398544788360596, + "learning_rate": 9e-05, + "loss": 0.02253679558634758, + "step": 226 + }, + { + "epoch": 0.6005291005291006, + "grad_norm": 0.08214128762483597, + "learning_rate": 8.941176470588236e-05, + "loss": 0.027625620365142822, + "step": 227 + }, + { + "epoch": 0.6031746031746031, + "grad_norm": 0.07763852924108505, + "learning_rate": 8.882352941176471e-05, + "loss": 0.018679391592741013, + "step": 228 + }, + { + "epoch": 0.6058201058201058, + "grad_norm": 0.0663997232913971, + "learning_rate": 8.823529411764706e-05, + "loss": 0.018782157450914383, + "step": 229 + }, + { + "epoch": 0.6084656084656085, + "grad_norm": 0.07828967273235321, + "learning_rate": 8.764705882352942e-05, + "loss": 0.027178611606359482, + "step": 230 + }, + { + "epoch": 0.6111111111111112, + "grad_norm": 0.08604388684034348, + "learning_rate": 8.705882352941177e-05, + "loss": 0.023709267377853394, + "step": 231 + }, + { + "epoch": 0.6137566137566137, + "grad_norm": 0.07984922081232071, + "learning_rate": 8.647058823529412e-05, + "loss": 0.02602708712220192, + "step": 232 + }, + { + "epoch": 0.6164021164021164, + "grad_norm": 0.07321182638406754, + "learning_rate": 8.588235294117646e-05, + "loss": 0.02468765154480934, + "step": 233 + }, + { + "epoch": 0.6190476190476191, + "grad_norm": 0.07817960530519485, + "learning_rate": 8.529411764705883e-05, + "loss": 0.03028242662549019, + "step": 234 + }, + { + "epoch": 0.6216931216931217, + "grad_norm": 0.06251050531864166, + "learning_rate": 8.470588235294118e-05, + "loss": 0.02902349643409252, + "step": 235 + }, + { + "epoch": 0.6243386243386243, + "grad_norm": 0.09529170393943787, + "learning_rate": 8.411764705882354e-05, + "loss": 0.024306783452630043, + "step": 236 + }, + { + "epoch": 0.626984126984127, + "grad_norm": 0.1267942190170288, + "learning_rate": 8.352941176470589e-05, + "loss": 0.03521513566374779, + "step": 237 + }, + { + "epoch": 0.6296296296296297, + "grad_norm": 0.08621630817651749, + "learning_rate": 8.294117647058824e-05, + "loss": 0.020196501165628433, + "step": 238 + }, + { + "epoch": 0.6322751322751323, + "grad_norm": 0.07552770525217056, + "learning_rate": 8.23529411764706e-05, + "loss": 0.029385194182395935, + "step": 239 + }, + { + "epoch": 0.6349206349206349, + "grad_norm": 0.09521529078483582, + "learning_rate": 8.176470588235295e-05, + "loss": 0.01693333312869072, + "step": 240 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9354284900997120.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-240/training_args.bin b/sft_worldsplit_1_5b/checkpoint-240/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-240/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-280/README.md b/sft_worldsplit_1_5b/checkpoint-280/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-280/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-280/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-280/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-280/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60b48f2b20c5a7aa383c61a176603164af5a9872 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ddd8a604b43eee8bc5e2608b5988671ff3a0932fde6a21e3928da076c7b7b6 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-280/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-280/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-280/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-280/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e71bd4d2ac2ba1e7ed74ec4e565573e6cb755062 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12aeaadf15682ca166043961a8f6b14d315ba11331d6ec28a2ab741061eca6fc +size 37970053 diff --git a/sft_worldsplit_1_5b/checkpoint-280/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-280/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-280/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-280/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bde730cfaa8b04b02b49218b9413f9d3878e1797 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0266909355a3050dead71bead98e1eea2f49994f9e94a7489e48fe75b0c35d69 +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-280/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-280/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-280/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-280/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-280/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-280/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f63f53030a85d2e5c5a5a5b3f69955903cbf3045 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/trainer_state.json @@ -0,0 +1,1994 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.7407407407407407, + "eval_steps": 500, + "global_step": 280, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + }, + { + "epoch": 0.42592592592592593, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "loss": 0.03136860206723213, + "step": 161 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "loss": 0.02894529700279236, + "step": 162 + }, + { + "epoch": 0.4312169312169312, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "loss": 0.033732134848833084, + "step": 163 + }, + { + "epoch": 0.43386243386243384, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "loss": 0.026288658380508423, + "step": 164 + }, + { + "epoch": 0.4365079365079365, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "loss": 0.03067208267748356, + "step": 165 + }, + { + "epoch": 0.43915343915343913, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "loss": 0.027257606387138367, + "step": 166 + }, + { + "epoch": 0.4417989417989418, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "loss": 0.020257430151104927, + "step": 167 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "loss": 0.025873055681586266, + "step": 168 + }, + { + "epoch": 0.4470899470899471, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "loss": 0.02722345106303692, + "step": 169 + }, + { + "epoch": 0.4497354497354497, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "loss": 0.0284090805798769, + "step": 170 + }, + { + "epoch": 0.4523809523809524, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "loss": 0.0273237656801939, + "step": 171 + }, + { + "epoch": 0.455026455026455, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "loss": 0.03370822221040726, + "step": 172 + }, + { + "epoch": 0.4576719576719577, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "loss": 0.018664535135030746, + "step": 173 + }, + { + "epoch": 0.4603174603174603, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "loss": 0.029450563713908195, + "step": 174 + }, + { + "epoch": 0.46296296296296297, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "loss": 0.02172383852303028, + "step": 175 + }, + { + "epoch": 0.4656084656084656, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "loss": 0.029448989778757095, + "step": 176 + }, + { + "epoch": 0.46825396825396826, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "loss": 0.023345600813627243, + "step": 177 + }, + { + "epoch": 0.4708994708994709, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "loss": 0.026639586314558983, + "step": 178 + }, + { + "epoch": 0.47354497354497355, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "loss": 0.021892163902521133, + "step": 179 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "loss": 0.022277187556028366, + "step": 180 + }, + { + "epoch": 0.47883597883597884, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "loss": 0.03035702183842659, + "step": 181 + }, + { + "epoch": 0.48148148148148145, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "loss": 0.03421338275074959, + "step": 182 + }, + { + "epoch": 0.48412698412698413, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "loss": 0.029597604647278786, + "step": 183 + }, + { + "epoch": 0.48677248677248675, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "loss": 0.027550101280212402, + "step": 184 + }, + { + "epoch": 0.4894179894179894, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "loss": 0.03323390707373619, + "step": 185 + }, + { + "epoch": 0.49206349206349204, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "loss": 0.02156604826450348, + "step": 186 + }, + { + "epoch": 0.4947089947089947, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "loss": 0.024817658588290215, + "step": 187 + }, + { + "epoch": 0.4973544973544973, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "loss": 0.02846340462565422, + "step": 188 + }, + { + "epoch": 0.5, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "loss": 0.016268836334347725, + "step": 189 + }, + { + "epoch": 0.5026455026455027, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "loss": 0.02841845154762268, + "step": 190 + }, + { + "epoch": 0.5052910052910053, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "loss": 0.0306367389857769, + "step": 191 + }, + { + "epoch": 0.5079365079365079, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "loss": 0.031015485525131226, + "step": 192 + }, + { + "epoch": 0.5105820105820106, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "loss": 0.03242127224802971, + "step": 193 + }, + { + "epoch": 0.5132275132275133, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "loss": 0.03684879094362259, + "step": 194 + }, + { + "epoch": 0.5158730158730159, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "loss": 0.0260506309568882, + "step": 195 + }, + { + "epoch": 0.5185185185185185, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "loss": 0.02128693461418152, + "step": 196 + }, + { + "epoch": 0.5211640211640212, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "loss": 0.03452152758836746, + "step": 197 + }, + { + "epoch": 0.5238095238095238, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "loss": 0.028310813009738922, + "step": 198 + }, + { + "epoch": 0.5264550264550265, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "loss": 0.029575366526842117, + "step": 199 + }, + { + "epoch": 0.5291005291005291, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "loss": 0.029606211930513382, + "step": 200 + }, + { + "epoch": 0.5317460317460317, + "grad_norm": 0.09481994062662125, + "learning_rate": 0.00010470588235294118, + "loss": 0.02741779386997223, + "step": 201 + }, + { + "epoch": 0.5343915343915344, + "grad_norm": 0.06643011420965195, + "learning_rate": 0.00010411764705882355, + "loss": 0.02750249207019806, + "step": 202 + }, + { + "epoch": 0.5370370370370371, + "grad_norm": 0.08693543821573257, + "learning_rate": 0.0001035294117647059, + "loss": 0.025049429386854172, + "step": 203 + }, + { + "epoch": 0.5396825396825397, + "grad_norm": 0.08780419826507568, + "learning_rate": 0.00010294117647058823, + "loss": 0.0188161451369524, + "step": 204 + }, + { + "epoch": 0.5423280423280423, + "grad_norm": 0.08089763671159744, + "learning_rate": 0.00010235294117647058, + "loss": 0.025752779096364975, + "step": 205 + }, + { + "epoch": 0.544973544973545, + "grad_norm": 0.11511234939098358, + "learning_rate": 0.00010176470588235295, + "loss": 0.03086625598371029, + "step": 206 + }, + { + "epoch": 0.5476190476190477, + "grad_norm": 0.10907749086618423, + "learning_rate": 0.0001011764705882353, + "loss": 0.0273880697786808, + "step": 207 + }, + { + "epoch": 0.5502645502645502, + "grad_norm": 0.08107511699199677, + "learning_rate": 0.00010058823529411765, + "loss": 0.026370292529463768, + "step": 208 + }, + { + "epoch": 0.5529100529100529, + "grad_norm": 0.0737859457731247, + "learning_rate": 0.0001, + "loss": 0.025786038488149643, + "step": 209 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.09232968837022781, + "learning_rate": 9.941176470588236e-05, + "loss": 0.030016383156180382, + "step": 210 + }, + { + "epoch": 0.5582010582010583, + "grad_norm": 0.0948951318860054, + "learning_rate": 9.882352941176471e-05, + "loss": 0.021605785936117172, + "step": 211 + }, + { + "epoch": 0.5608465608465608, + "grad_norm": 0.09735886752605438, + "learning_rate": 9.823529411764706e-05, + "loss": 0.031091010197997093, + "step": 212 + }, + { + "epoch": 0.5634920634920635, + "grad_norm": 0.10056869685649872, + "learning_rate": 9.764705882352942e-05, + "loss": 0.030390700325369835, + "step": 213 + }, + { + "epoch": 0.5661375661375662, + "grad_norm": 0.0720759853720665, + "learning_rate": 9.705882352941177e-05, + "loss": 0.02216975763440132, + "step": 214 + }, + { + "epoch": 0.5687830687830688, + "grad_norm": 0.09141097962856293, + "learning_rate": 9.647058823529412e-05, + "loss": 0.02660333178937435, + "step": 215 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.09253139793872833, + "learning_rate": 9.588235294117648e-05, + "loss": 0.02590668946504593, + "step": 216 + }, + { + "epoch": 0.5740740740740741, + "grad_norm": 0.08869278430938721, + "learning_rate": 9.529411764705883e-05, + "loss": 0.02776462584733963, + "step": 217 + }, + { + "epoch": 0.5767195767195767, + "grad_norm": 0.10566668212413788, + "learning_rate": 9.470588235294118e-05, + "loss": 0.015304268337786198, + "step": 218 + }, + { + "epoch": 0.5793650793650794, + "grad_norm": 0.08862630277872086, + "learning_rate": 9.411764705882353e-05, + "loss": 0.027874145656824112, + "step": 219 + }, + { + "epoch": 0.582010582010582, + "grad_norm": 0.0958574190735817, + "learning_rate": 9.352941176470589e-05, + "loss": 0.030754802748560905, + "step": 220 + }, + { + "epoch": 0.5846560846560847, + "grad_norm": 0.09204437583684921, + "learning_rate": 9.294117647058824e-05, + "loss": 0.023360423743724823, + "step": 221 + }, + { + "epoch": 0.5873015873015873, + "grad_norm": 0.12147050350904465, + "learning_rate": 9.23529411764706e-05, + "loss": 0.031416505575180054, + "step": 222 + }, + { + "epoch": 0.58994708994709, + "grad_norm": 0.08076925575733185, + "learning_rate": 9.176470588235295e-05, + "loss": 0.023884786292910576, + "step": 223 + }, + { + "epoch": 0.5925925925925926, + "grad_norm": 0.08516595512628555, + "learning_rate": 9.11764705882353e-05, + "loss": 0.025108790025115013, + "step": 224 + }, + { + "epoch": 0.5952380952380952, + "grad_norm": 0.09453090280294418, + "learning_rate": 9.058823529411765e-05, + "loss": 0.0236780047416687, + "step": 225 + }, + { + "epoch": 0.5978835978835979, + "grad_norm": 0.08398544788360596, + "learning_rate": 9e-05, + "loss": 0.02253679558634758, + "step": 226 + }, + { + "epoch": 0.6005291005291006, + "grad_norm": 0.08214128762483597, + "learning_rate": 8.941176470588236e-05, + "loss": 0.027625620365142822, + "step": 227 + }, + { + "epoch": 0.6031746031746031, + "grad_norm": 0.07763852924108505, + "learning_rate": 8.882352941176471e-05, + "loss": 0.018679391592741013, + "step": 228 + }, + { + "epoch": 0.6058201058201058, + "grad_norm": 0.0663997232913971, + "learning_rate": 8.823529411764706e-05, + "loss": 0.018782157450914383, + "step": 229 + }, + { + "epoch": 0.6084656084656085, + "grad_norm": 0.07828967273235321, + "learning_rate": 8.764705882352942e-05, + "loss": 0.027178611606359482, + "step": 230 + }, + { + "epoch": 0.6111111111111112, + "grad_norm": 0.08604388684034348, + "learning_rate": 8.705882352941177e-05, + "loss": 0.023709267377853394, + "step": 231 + }, + { + "epoch": 0.6137566137566137, + "grad_norm": 0.07984922081232071, + "learning_rate": 8.647058823529412e-05, + "loss": 0.02602708712220192, + "step": 232 + }, + { + "epoch": 0.6164021164021164, + "grad_norm": 0.07321182638406754, + "learning_rate": 8.588235294117646e-05, + "loss": 0.02468765154480934, + "step": 233 + }, + { + "epoch": 0.6190476190476191, + "grad_norm": 0.07817960530519485, + "learning_rate": 8.529411764705883e-05, + "loss": 0.03028242662549019, + "step": 234 + }, + { + "epoch": 0.6216931216931217, + "grad_norm": 0.06251050531864166, + "learning_rate": 8.470588235294118e-05, + "loss": 0.02902349643409252, + "step": 235 + }, + { + "epoch": 0.6243386243386243, + "grad_norm": 0.09529170393943787, + "learning_rate": 8.411764705882354e-05, + "loss": 0.024306783452630043, + "step": 236 + }, + { + "epoch": 0.626984126984127, + "grad_norm": 0.1267942190170288, + "learning_rate": 8.352941176470589e-05, + "loss": 0.03521513566374779, + "step": 237 + }, + { + "epoch": 0.6296296296296297, + "grad_norm": 0.08621630817651749, + "learning_rate": 8.294117647058824e-05, + "loss": 0.020196501165628433, + "step": 238 + }, + { + "epoch": 0.6322751322751323, + "grad_norm": 0.07552770525217056, + "learning_rate": 8.23529411764706e-05, + "loss": 0.029385194182395935, + "step": 239 + }, + { + "epoch": 0.6349206349206349, + "grad_norm": 0.09521529078483582, + "learning_rate": 8.176470588235295e-05, + "loss": 0.01693333312869072, + "step": 240 + }, + { + "epoch": 0.6375661375661376, + "grad_norm": 0.09436187893152237, + "learning_rate": 8.11764705882353e-05, + "loss": 0.025097660720348358, + "step": 241 + }, + { + "epoch": 0.6402116402116402, + "grad_norm": 0.07002269476652145, + "learning_rate": 8.058823529411765e-05, + "loss": 0.027106281369924545, + "step": 242 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.08871318399906158, + "learning_rate": 8e-05, + "loss": 0.027904586866497993, + "step": 243 + }, + { + "epoch": 0.6455026455026455, + "grad_norm": 0.0833863765001297, + "learning_rate": 7.941176470588235e-05, + "loss": 0.030118469148874283, + "step": 244 + }, + { + "epoch": 0.6481481481481481, + "grad_norm": 0.0630115196108818, + "learning_rate": 7.882352941176471e-05, + "loss": 0.015584684908390045, + "step": 245 + }, + { + "epoch": 0.6507936507936508, + "grad_norm": 0.0754900649189949, + "learning_rate": 7.823529411764707e-05, + "loss": 0.024866245687007904, + "step": 246 + }, + { + "epoch": 0.6534391534391535, + "grad_norm": 0.09214677661657333, + "learning_rate": 7.764705882352942e-05, + "loss": 0.02521335333585739, + "step": 247 + }, + { + "epoch": 0.656084656084656, + "grad_norm": 0.07616355270147324, + "learning_rate": 7.705882352941177e-05, + "loss": 0.02567514404654503, + "step": 248 + }, + { + "epoch": 0.6587301587301587, + "grad_norm": 0.10812173038721085, + "learning_rate": 7.647058823529411e-05, + "loss": 0.03087168186903, + "step": 249 + }, + { + "epoch": 0.6613756613756614, + "grad_norm": 0.07225628942251205, + "learning_rate": 7.588235294117648e-05, + "loss": 0.02886301279067993, + "step": 250 + }, + { + "epoch": 0.6640211640211641, + "grad_norm": 0.08968020230531693, + "learning_rate": 7.529411764705883e-05, + "loss": 0.02838725596666336, + "step": 251 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.1066119521856308, + "learning_rate": 7.470588235294118e-05, + "loss": 0.0240425243973732, + "step": 252 + }, + { + "epoch": 0.6693121693121693, + "grad_norm": 0.07908853143453598, + "learning_rate": 7.411764705882354e-05, + "loss": 0.020799003541469574, + "step": 253 + }, + { + "epoch": 0.671957671957672, + "grad_norm": 0.08067328482866287, + "learning_rate": 7.352941176470589e-05, + "loss": 0.03212092071771622, + "step": 254 + }, + { + "epoch": 0.6746031746031746, + "grad_norm": 0.09752342849969864, + "learning_rate": 7.294117647058823e-05, + "loss": 0.02562413364648819, + "step": 255 + }, + { + "epoch": 0.6772486772486772, + "grad_norm": 0.07102340459823608, + "learning_rate": 7.23529411764706e-05, + "loss": 0.01694977842271328, + "step": 256 + }, + { + "epoch": 0.6798941798941799, + "grad_norm": 0.07671815156936646, + "learning_rate": 7.176470588235295e-05, + "loss": 0.02575928345322609, + "step": 257 + }, + { + "epoch": 0.6825396825396826, + "grad_norm": 0.1419815868139267, + "learning_rate": 7.11764705882353e-05, + "loss": 0.021748626604676247, + "step": 258 + }, + { + "epoch": 0.6851851851851852, + "grad_norm": 0.10793975740671158, + "learning_rate": 7.058823529411765e-05, + "loss": 0.02359670028090477, + "step": 259 + }, + { + "epoch": 0.6878306878306878, + "grad_norm": 0.10104779154062271, + "learning_rate": 7e-05, + "loss": 0.020240038633346558, + "step": 260 + }, + { + "epoch": 0.6904761904761905, + "grad_norm": 0.09232339262962341, + "learning_rate": 6.941176470588236e-05, + "loss": 0.03007177822291851, + "step": 261 + }, + { + "epoch": 0.6931216931216931, + "grad_norm": 0.060809917747974396, + "learning_rate": 6.882352941176471e-05, + "loss": 0.02441459335386753, + "step": 262 + }, + { + "epoch": 0.6957671957671958, + "grad_norm": 0.07218184322118759, + "learning_rate": 6.823529411764707e-05, + "loss": 0.02289595827460289, + "step": 263 + }, + { + "epoch": 0.6984126984126984, + "grad_norm": 0.09035782516002655, + "learning_rate": 6.764705882352942e-05, + "loss": 0.02958938293159008, + "step": 264 + }, + { + "epoch": 0.701058201058201, + "grad_norm": 0.08335528522729874, + "learning_rate": 6.705882352941176e-05, + "loss": 0.028876766562461853, + "step": 265 + }, + { + "epoch": 0.7037037037037037, + "grad_norm": 0.06112835556268692, + "learning_rate": 6.647058823529411e-05, + "loss": 0.022992007434368134, + "step": 266 + }, + { + "epoch": 0.7063492063492064, + "grad_norm": 0.09583422541618347, + "learning_rate": 6.588235294117648e-05, + "loss": 0.027839267626404762, + "step": 267 + }, + { + "epoch": 0.708994708994709, + "grad_norm": 0.10437622666358948, + "learning_rate": 6.529411764705883e-05, + "loss": 0.03310278058052063, + "step": 268 + }, + { + "epoch": 0.7116402116402116, + "grad_norm": 0.05979550629854202, + "learning_rate": 6.470588235294118e-05, + "loss": 0.02412830851972103, + "step": 269 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.057857904583215714, + "learning_rate": 6.411764705882354e-05, + "loss": 0.026769282296299934, + "step": 270 + }, + { + "epoch": 0.716931216931217, + "grad_norm": 0.0795726403594017, + "learning_rate": 6.352941176470588e-05, + "loss": 0.01822183094918728, + "step": 271 + }, + { + "epoch": 0.7195767195767195, + "grad_norm": 0.11597180366516113, + "learning_rate": 6.294117647058824e-05, + "loss": 0.03175610303878784, + "step": 272 + }, + { + "epoch": 0.7222222222222222, + "grad_norm": 0.12822823226451874, + "learning_rate": 6.23529411764706e-05, + "loss": 0.02406914159655571, + "step": 273 + }, + { + "epoch": 0.7248677248677249, + "grad_norm": 0.11681342869997025, + "learning_rate": 6.176470588235295e-05, + "loss": 0.017685284838080406, + "step": 274 + }, + { + "epoch": 0.7275132275132276, + "grad_norm": 0.06948421150445938, + "learning_rate": 6.11764705882353e-05, + "loss": 0.02279685251414776, + "step": 275 + }, + { + "epoch": 0.7301587301587301, + "grad_norm": 0.10276354104280472, + "learning_rate": 6.058823529411765e-05, + "loss": 0.032588277012109756, + "step": 276 + }, + { + "epoch": 0.7328042328042328, + "grad_norm": 0.10721025615930557, + "learning_rate": 6e-05, + "loss": 0.02961578778922558, + "step": 277 + }, + { + "epoch": 0.7354497354497355, + "grad_norm": 0.08410617709159851, + "learning_rate": 5.9411764705882355e-05, + "loss": 0.02747366949915886, + "step": 278 + }, + { + "epoch": 0.7380952380952381, + "grad_norm": 0.0806620791554451, + "learning_rate": 5.882352941176471e-05, + "loss": 0.02593173459172249, + "step": 279 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.06915932148694992, + "learning_rate": 5.823529411764707e-05, + "loss": 0.02764303609728813, + "step": 280 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.0889836447838208e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-280/training_args.bin b/sft_worldsplit_1_5b/checkpoint-280/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-280/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-320/README.md b/sft_worldsplit_1_5b/checkpoint-320/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-320/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-320/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-320/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-320/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51056343939e0eeff97c3c32a08c6c040019ffa0 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1735c2824d8d93e7605b3d34087cd1e7ec345a483c7d3a1143166f7972a3c3 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-320/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-320/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-320/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-320/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b1b3108384ae520f965a511c7164f68c7028e90 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7af3ddbf8eb079e3bb5693853d634ecd721cdc80c439e37af6f830e188ccc04 +size 37970053 diff --git a/sft_worldsplit_1_5b/checkpoint-320/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-320/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-320/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-320/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa1229a3640690e51a2cbcf5d66eb16ac8766c6f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890e942e87ac3559e6ef537481397465578889ec71d023d0d9ac068d694fbbdc +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-320/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-320/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-320/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-320/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-320/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-320/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..53c2fb59b6d52afa066042ef5e8faec8d8c688ac --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/trainer_state.json @@ -0,0 +1,2274 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.8465608465608465, + "eval_steps": 500, + "global_step": 320, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + }, + { + "epoch": 0.42592592592592593, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "loss": 0.03136860206723213, + "step": 161 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "loss": 0.02894529700279236, + "step": 162 + }, + { + "epoch": 0.4312169312169312, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "loss": 0.033732134848833084, + "step": 163 + }, + { + "epoch": 0.43386243386243384, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "loss": 0.026288658380508423, + "step": 164 + }, + { + "epoch": 0.4365079365079365, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "loss": 0.03067208267748356, + "step": 165 + }, + { + "epoch": 0.43915343915343913, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "loss": 0.027257606387138367, + "step": 166 + }, + { + "epoch": 0.4417989417989418, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "loss": 0.020257430151104927, + "step": 167 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "loss": 0.025873055681586266, + "step": 168 + }, + { + "epoch": 0.4470899470899471, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "loss": 0.02722345106303692, + "step": 169 + }, + { + "epoch": 0.4497354497354497, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "loss": 0.0284090805798769, + "step": 170 + }, + { + "epoch": 0.4523809523809524, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "loss": 0.0273237656801939, + "step": 171 + }, + { + "epoch": 0.455026455026455, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "loss": 0.03370822221040726, + "step": 172 + }, + { + "epoch": 0.4576719576719577, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "loss": 0.018664535135030746, + "step": 173 + }, + { + "epoch": 0.4603174603174603, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "loss": 0.029450563713908195, + "step": 174 + }, + { + "epoch": 0.46296296296296297, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "loss": 0.02172383852303028, + "step": 175 + }, + { + "epoch": 0.4656084656084656, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "loss": 0.029448989778757095, + "step": 176 + }, + { + "epoch": 0.46825396825396826, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "loss": 0.023345600813627243, + "step": 177 + }, + { + "epoch": 0.4708994708994709, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "loss": 0.026639586314558983, + "step": 178 + }, + { + "epoch": 0.47354497354497355, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "loss": 0.021892163902521133, + "step": 179 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "loss": 0.022277187556028366, + "step": 180 + }, + { + "epoch": 0.47883597883597884, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "loss": 0.03035702183842659, + "step": 181 + }, + { + "epoch": 0.48148148148148145, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "loss": 0.03421338275074959, + "step": 182 + }, + { + "epoch": 0.48412698412698413, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "loss": 0.029597604647278786, + "step": 183 + }, + { + "epoch": 0.48677248677248675, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "loss": 0.027550101280212402, + "step": 184 + }, + { + "epoch": 0.4894179894179894, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "loss": 0.03323390707373619, + "step": 185 + }, + { + "epoch": 0.49206349206349204, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "loss": 0.02156604826450348, + "step": 186 + }, + { + "epoch": 0.4947089947089947, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "loss": 0.024817658588290215, + "step": 187 + }, + { + "epoch": 0.4973544973544973, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "loss": 0.02846340462565422, + "step": 188 + }, + { + "epoch": 0.5, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "loss": 0.016268836334347725, + "step": 189 + }, + { + "epoch": 0.5026455026455027, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "loss": 0.02841845154762268, + "step": 190 + }, + { + "epoch": 0.5052910052910053, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "loss": 0.0306367389857769, + "step": 191 + }, + { + "epoch": 0.5079365079365079, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "loss": 0.031015485525131226, + "step": 192 + }, + { + "epoch": 0.5105820105820106, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "loss": 0.03242127224802971, + "step": 193 + }, + { + "epoch": 0.5132275132275133, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "loss": 0.03684879094362259, + "step": 194 + }, + { + "epoch": 0.5158730158730159, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "loss": 0.0260506309568882, + "step": 195 + }, + { + "epoch": 0.5185185185185185, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "loss": 0.02128693461418152, + "step": 196 + }, + { + "epoch": 0.5211640211640212, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "loss": 0.03452152758836746, + "step": 197 + }, + { + "epoch": 0.5238095238095238, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "loss": 0.028310813009738922, + "step": 198 + }, + { + "epoch": 0.5264550264550265, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "loss": 0.029575366526842117, + "step": 199 + }, + { + "epoch": 0.5291005291005291, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "loss": 0.029606211930513382, + "step": 200 + }, + { + "epoch": 0.5317460317460317, + "grad_norm": 0.09481994062662125, + "learning_rate": 0.00010470588235294118, + "loss": 0.02741779386997223, + "step": 201 + }, + { + "epoch": 0.5343915343915344, + "grad_norm": 0.06643011420965195, + "learning_rate": 0.00010411764705882355, + "loss": 0.02750249207019806, + "step": 202 + }, + { + "epoch": 0.5370370370370371, + "grad_norm": 0.08693543821573257, + "learning_rate": 0.0001035294117647059, + "loss": 0.025049429386854172, + "step": 203 + }, + { + "epoch": 0.5396825396825397, + "grad_norm": 0.08780419826507568, + "learning_rate": 0.00010294117647058823, + "loss": 0.0188161451369524, + "step": 204 + }, + { + "epoch": 0.5423280423280423, + "grad_norm": 0.08089763671159744, + "learning_rate": 0.00010235294117647058, + "loss": 0.025752779096364975, + "step": 205 + }, + { + "epoch": 0.544973544973545, + "grad_norm": 0.11511234939098358, + "learning_rate": 0.00010176470588235295, + "loss": 0.03086625598371029, + "step": 206 + }, + { + "epoch": 0.5476190476190477, + "grad_norm": 0.10907749086618423, + "learning_rate": 0.0001011764705882353, + "loss": 0.0273880697786808, + "step": 207 + }, + { + "epoch": 0.5502645502645502, + "grad_norm": 0.08107511699199677, + "learning_rate": 0.00010058823529411765, + "loss": 0.026370292529463768, + "step": 208 + }, + { + "epoch": 0.5529100529100529, + "grad_norm": 0.0737859457731247, + "learning_rate": 0.0001, + "loss": 0.025786038488149643, + "step": 209 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.09232968837022781, + "learning_rate": 9.941176470588236e-05, + "loss": 0.030016383156180382, + "step": 210 + }, + { + "epoch": 0.5582010582010583, + "grad_norm": 0.0948951318860054, + "learning_rate": 9.882352941176471e-05, + "loss": 0.021605785936117172, + "step": 211 + }, + { + "epoch": 0.5608465608465608, + "grad_norm": 0.09735886752605438, + "learning_rate": 9.823529411764706e-05, + "loss": 0.031091010197997093, + "step": 212 + }, + { + "epoch": 0.5634920634920635, + "grad_norm": 0.10056869685649872, + "learning_rate": 9.764705882352942e-05, + "loss": 0.030390700325369835, + "step": 213 + }, + { + "epoch": 0.5661375661375662, + "grad_norm": 0.0720759853720665, + "learning_rate": 9.705882352941177e-05, + "loss": 0.02216975763440132, + "step": 214 + }, + { + "epoch": 0.5687830687830688, + "grad_norm": 0.09141097962856293, + "learning_rate": 9.647058823529412e-05, + "loss": 0.02660333178937435, + "step": 215 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.09253139793872833, + "learning_rate": 9.588235294117648e-05, + "loss": 0.02590668946504593, + "step": 216 + }, + { + "epoch": 0.5740740740740741, + "grad_norm": 0.08869278430938721, + "learning_rate": 9.529411764705883e-05, + "loss": 0.02776462584733963, + "step": 217 + }, + { + "epoch": 0.5767195767195767, + "grad_norm": 0.10566668212413788, + "learning_rate": 9.470588235294118e-05, + "loss": 0.015304268337786198, + "step": 218 + }, + { + "epoch": 0.5793650793650794, + "grad_norm": 0.08862630277872086, + "learning_rate": 9.411764705882353e-05, + "loss": 0.027874145656824112, + "step": 219 + }, + { + "epoch": 0.582010582010582, + "grad_norm": 0.0958574190735817, + "learning_rate": 9.352941176470589e-05, + "loss": 0.030754802748560905, + "step": 220 + }, + { + "epoch": 0.5846560846560847, + "grad_norm": 0.09204437583684921, + "learning_rate": 9.294117647058824e-05, + "loss": 0.023360423743724823, + "step": 221 + }, + { + "epoch": 0.5873015873015873, + "grad_norm": 0.12147050350904465, + "learning_rate": 9.23529411764706e-05, + "loss": 0.031416505575180054, + "step": 222 + }, + { + "epoch": 0.58994708994709, + "grad_norm": 0.08076925575733185, + "learning_rate": 9.176470588235295e-05, + "loss": 0.023884786292910576, + "step": 223 + }, + { + "epoch": 0.5925925925925926, + "grad_norm": 0.08516595512628555, + "learning_rate": 9.11764705882353e-05, + "loss": 0.025108790025115013, + "step": 224 + }, + { + "epoch": 0.5952380952380952, + "grad_norm": 0.09453090280294418, + "learning_rate": 9.058823529411765e-05, + "loss": 0.0236780047416687, + "step": 225 + }, + { + "epoch": 0.5978835978835979, + "grad_norm": 0.08398544788360596, + "learning_rate": 9e-05, + "loss": 0.02253679558634758, + "step": 226 + }, + { + "epoch": 0.6005291005291006, + "grad_norm": 0.08214128762483597, + "learning_rate": 8.941176470588236e-05, + "loss": 0.027625620365142822, + "step": 227 + }, + { + "epoch": 0.6031746031746031, + "grad_norm": 0.07763852924108505, + "learning_rate": 8.882352941176471e-05, + "loss": 0.018679391592741013, + "step": 228 + }, + { + "epoch": 0.6058201058201058, + "grad_norm": 0.0663997232913971, + "learning_rate": 8.823529411764706e-05, + "loss": 0.018782157450914383, + "step": 229 + }, + { + "epoch": 0.6084656084656085, + "grad_norm": 0.07828967273235321, + "learning_rate": 8.764705882352942e-05, + "loss": 0.027178611606359482, + "step": 230 + }, + { + "epoch": 0.6111111111111112, + "grad_norm": 0.08604388684034348, + "learning_rate": 8.705882352941177e-05, + "loss": 0.023709267377853394, + "step": 231 + }, + { + "epoch": 0.6137566137566137, + "grad_norm": 0.07984922081232071, + "learning_rate": 8.647058823529412e-05, + "loss": 0.02602708712220192, + "step": 232 + }, + { + "epoch": 0.6164021164021164, + "grad_norm": 0.07321182638406754, + "learning_rate": 8.588235294117646e-05, + "loss": 0.02468765154480934, + "step": 233 + }, + { + "epoch": 0.6190476190476191, + "grad_norm": 0.07817960530519485, + "learning_rate": 8.529411764705883e-05, + "loss": 0.03028242662549019, + "step": 234 + }, + { + "epoch": 0.6216931216931217, + "grad_norm": 0.06251050531864166, + "learning_rate": 8.470588235294118e-05, + "loss": 0.02902349643409252, + "step": 235 + }, + { + "epoch": 0.6243386243386243, + "grad_norm": 0.09529170393943787, + "learning_rate": 8.411764705882354e-05, + "loss": 0.024306783452630043, + "step": 236 + }, + { + "epoch": 0.626984126984127, + "grad_norm": 0.1267942190170288, + "learning_rate": 8.352941176470589e-05, + "loss": 0.03521513566374779, + "step": 237 + }, + { + "epoch": 0.6296296296296297, + "grad_norm": 0.08621630817651749, + "learning_rate": 8.294117647058824e-05, + "loss": 0.020196501165628433, + "step": 238 + }, + { + "epoch": 0.6322751322751323, + "grad_norm": 0.07552770525217056, + "learning_rate": 8.23529411764706e-05, + "loss": 0.029385194182395935, + "step": 239 + }, + { + "epoch": 0.6349206349206349, + "grad_norm": 0.09521529078483582, + "learning_rate": 8.176470588235295e-05, + "loss": 0.01693333312869072, + "step": 240 + }, + { + "epoch": 0.6375661375661376, + "grad_norm": 0.09436187893152237, + "learning_rate": 8.11764705882353e-05, + "loss": 0.025097660720348358, + "step": 241 + }, + { + "epoch": 0.6402116402116402, + "grad_norm": 0.07002269476652145, + "learning_rate": 8.058823529411765e-05, + "loss": 0.027106281369924545, + "step": 242 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.08871318399906158, + "learning_rate": 8e-05, + "loss": 0.027904586866497993, + "step": 243 + }, + { + "epoch": 0.6455026455026455, + "grad_norm": 0.0833863765001297, + "learning_rate": 7.941176470588235e-05, + "loss": 0.030118469148874283, + "step": 244 + }, + { + "epoch": 0.6481481481481481, + "grad_norm": 0.0630115196108818, + "learning_rate": 7.882352941176471e-05, + "loss": 0.015584684908390045, + "step": 245 + }, + { + "epoch": 0.6507936507936508, + "grad_norm": 0.0754900649189949, + "learning_rate": 7.823529411764707e-05, + "loss": 0.024866245687007904, + "step": 246 + }, + { + "epoch": 0.6534391534391535, + "grad_norm": 0.09214677661657333, + "learning_rate": 7.764705882352942e-05, + "loss": 0.02521335333585739, + "step": 247 + }, + { + "epoch": 0.656084656084656, + "grad_norm": 0.07616355270147324, + "learning_rate": 7.705882352941177e-05, + "loss": 0.02567514404654503, + "step": 248 + }, + { + "epoch": 0.6587301587301587, + "grad_norm": 0.10812173038721085, + "learning_rate": 7.647058823529411e-05, + "loss": 0.03087168186903, + "step": 249 + }, + { + "epoch": 0.6613756613756614, + "grad_norm": 0.07225628942251205, + "learning_rate": 7.588235294117648e-05, + "loss": 0.02886301279067993, + "step": 250 + }, + { + "epoch": 0.6640211640211641, + "grad_norm": 0.08968020230531693, + "learning_rate": 7.529411764705883e-05, + "loss": 0.02838725596666336, + "step": 251 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.1066119521856308, + "learning_rate": 7.470588235294118e-05, + "loss": 0.0240425243973732, + "step": 252 + }, + { + "epoch": 0.6693121693121693, + "grad_norm": 0.07908853143453598, + "learning_rate": 7.411764705882354e-05, + "loss": 0.020799003541469574, + "step": 253 + }, + { + "epoch": 0.671957671957672, + "grad_norm": 0.08067328482866287, + "learning_rate": 7.352941176470589e-05, + "loss": 0.03212092071771622, + "step": 254 + }, + { + "epoch": 0.6746031746031746, + "grad_norm": 0.09752342849969864, + "learning_rate": 7.294117647058823e-05, + "loss": 0.02562413364648819, + "step": 255 + }, + { + "epoch": 0.6772486772486772, + "grad_norm": 0.07102340459823608, + "learning_rate": 7.23529411764706e-05, + "loss": 0.01694977842271328, + "step": 256 + }, + { + "epoch": 0.6798941798941799, + "grad_norm": 0.07671815156936646, + "learning_rate": 7.176470588235295e-05, + "loss": 0.02575928345322609, + "step": 257 + }, + { + "epoch": 0.6825396825396826, + "grad_norm": 0.1419815868139267, + "learning_rate": 7.11764705882353e-05, + "loss": 0.021748626604676247, + "step": 258 + }, + { + "epoch": 0.6851851851851852, + "grad_norm": 0.10793975740671158, + "learning_rate": 7.058823529411765e-05, + "loss": 0.02359670028090477, + "step": 259 + }, + { + "epoch": 0.6878306878306878, + "grad_norm": 0.10104779154062271, + "learning_rate": 7e-05, + "loss": 0.020240038633346558, + "step": 260 + }, + { + "epoch": 0.6904761904761905, + "grad_norm": 0.09232339262962341, + "learning_rate": 6.941176470588236e-05, + "loss": 0.03007177822291851, + "step": 261 + }, + { + "epoch": 0.6931216931216931, + "grad_norm": 0.060809917747974396, + "learning_rate": 6.882352941176471e-05, + "loss": 0.02441459335386753, + "step": 262 + }, + { + "epoch": 0.6957671957671958, + "grad_norm": 0.07218184322118759, + "learning_rate": 6.823529411764707e-05, + "loss": 0.02289595827460289, + "step": 263 + }, + { + "epoch": 0.6984126984126984, + "grad_norm": 0.09035782516002655, + "learning_rate": 6.764705882352942e-05, + "loss": 0.02958938293159008, + "step": 264 + }, + { + "epoch": 0.701058201058201, + "grad_norm": 0.08335528522729874, + "learning_rate": 6.705882352941176e-05, + "loss": 0.028876766562461853, + "step": 265 + }, + { + "epoch": 0.7037037037037037, + "grad_norm": 0.06112835556268692, + "learning_rate": 6.647058823529411e-05, + "loss": 0.022992007434368134, + "step": 266 + }, + { + "epoch": 0.7063492063492064, + "grad_norm": 0.09583422541618347, + "learning_rate": 6.588235294117648e-05, + "loss": 0.027839267626404762, + "step": 267 + }, + { + "epoch": 0.708994708994709, + "grad_norm": 0.10437622666358948, + "learning_rate": 6.529411764705883e-05, + "loss": 0.03310278058052063, + "step": 268 + }, + { + "epoch": 0.7116402116402116, + "grad_norm": 0.05979550629854202, + "learning_rate": 6.470588235294118e-05, + "loss": 0.02412830851972103, + "step": 269 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.057857904583215714, + "learning_rate": 6.411764705882354e-05, + "loss": 0.026769282296299934, + "step": 270 + }, + { + "epoch": 0.716931216931217, + "grad_norm": 0.0795726403594017, + "learning_rate": 6.352941176470588e-05, + "loss": 0.01822183094918728, + "step": 271 + }, + { + "epoch": 0.7195767195767195, + "grad_norm": 0.11597180366516113, + "learning_rate": 6.294117647058824e-05, + "loss": 0.03175610303878784, + "step": 272 + }, + { + "epoch": 0.7222222222222222, + "grad_norm": 0.12822823226451874, + "learning_rate": 6.23529411764706e-05, + "loss": 0.02406914159655571, + "step": 273 + }, + { + "epoch": 0.7248677248677249, + "grad_norm": 0.11681342869997025, + "learning_rate": 6.176470588235295e-05, + "loss": 0.017685284838080406, + "step": 274 + }, + { + "epoch": 0.7275132275132276, + "grad_norm": 0.06948421150445938, + "learning_rate": 6.11764705882353e-05, + "loss": 0.02279685251414776, + "step": 275 + }, + { + "epoch": 0.7301587301587301, + "grad_norm": 0.10276354104280472, + "learning_rate": 6.058823529411765e-05, + "loss": 0.032588277012109756, + "step": 276 + }, + { + "epoch": 0.7328042328042328, + "grad_norm": 0.10721025615930557, + "learning_rate": 6e-05, + "loss": 0.02961578778922558, + "step": 277 + }, + { + "epoch": 0.7354497354497355, + "grad_norm": 0.08410617709159851, + "learning_rate": 5.9411764705882355e-05, + "loss": 0.02747366949915886, + "step": 278 + }, + { + "epoch": 0.7380952380952381, + "grad_norm": 0.0806620791554451, + "learning_rate": 5.882352941176471e-05, + "loss": 0.02593173459172249, + "step": 279 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.06915932148694992, + "learning_rate": 5.823529411764707e-05, + "loss": 0.02764303609728813, + "step": 280 + }, + { + "epoch": 0.7433862433862434, + "grad_norm": 0.06709478050470352, + "learning_rate": 5.764705882352941e-05, + "loss": 0.024347776547074318, + "step": 281 + }, + { + "epoch": 0.746031746031746, + "grad_norm": 0.053211960941553116, + "learning_rate": 5.7058823529411766e-05, + "loss": 0.02141982689499855, + "step": 282 + }, + { + "epoch": 0.7486772486772487, + "grad_norm": 0.06790946424007416, + "learning_rate": 5.647058823529412e-05, + "loss": 0.02252194657921791, + "step": 283 + }, + { + "epoch": 0.7513227513227513, + "grad_norm": 0.08224959671497345, + "learning_rate": 5.588235294117647e-05, + "loss": 0.01945466734468937, + "step": 284 + }, + { + "epoch": 0.753968253968254, + "grad_norm": 0.09265672415494919, + "learning_rate": 5.529411764705883e-05, + "loss": 0.032275885343551636, + "step": 285 + }, + { + "epoch": 0.7566137566137566, + "grad_norm": 0.07285762578248978, + "learning_rate": 5.4705882352941185e-05, + "loss": 0.027079608291387558, + "step": 286 + }, + { + "epoch": 0.7592592592592593, + "grad_norm": 0.05742108076810837, + "learning_rate": 5.411764705882353e-05, + "loss": 0.02384945936501026, + "step": 287 + }, + { + "epoch": 0.7619047619047619, + "grad_norm": 0.11136175692081451, + "learning_rate": 5.3529411764705884e-05, + "loss": 0.02898704633116722, + "step": 288 + }, + { + "epoch": 0.7645502645502645, + "grad_norm": 0.09560064971446991, + "learning_rate": 5.294117647058824e-05, + "loss": 0.03049132414162159, + "step": 289 + }, + { + "epoch": 0.7671957671957672, + "grad_norm": 0.062173303216695786, + "learning_rate": 5.235294117647059e-05, + "loss": 0.024453597143292427, + "step": 290 + }, + { + "epoch": 0.7698412698412699, + "grad_norm": 0.0988180935382843, + "learning_rate": 5.176470588235295e-05, + "loss": 0.0318286158144474, + "step": 291 + }, + { + "epoch": 0.7724867724867724, + "grad_norm": 0.0626835897564888, + "learning_rate": 5.117647058823529e-05, + "loss": 0.02699001133441925, + "step": 292 + }, + { + "epoch": 0.7751322751322751, + "grad_norm": 0.07981280982494354, + "learning_rate": 5.058823529411765e-05, + "loss": 0.023896772414445877, + "step": 293 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.07893257588148117, + "learning_rate": 5e-05, + "loss": 0.024391846731305122, + "step": 294 + }, + { + "epoch": 0.7804232804232805, + "grad_norm": 0.06932593882083893, + "learning_rate": 4.9411764705882355e-05, + "loss": 0.025584066286683083, + "step": 295 + }, + { + "epoch": 0.783068783068783, + "grad_norm": 0.07785957306623459, + "learning_rate": 4.882352941176471e-05, + "loss": 0.0220668762922287, + "step": 296 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 0.06624335050582886, + "learning_rate": 4.823529411764706e-05, + "loss": 0.020017938688397408, + "step": 297 + }, + { + "epoch": 0.7883597883597884, + "grad_norm": 0.0832471251487732, + "learning_rate": 4.7647058823529414e-05, + "loss": 0.02506105974316597, + "step": 298 + }, + { + "epoch": 0.791005291005291, + "grad_norm": 0.06540657579898834, + "learning_rate": 4.705882352941177e-05, + "loss": 0.017597489058971405, + "step": 299 + }, + { + "epoch": 0.7936507936507936, + "grad_norm": 0.15526005625724792, + "learning_rate": 4.647058823529412e-05, + "loss": 0.0298212431371212, + "step": 300 + }, + { + "epoch": 0.7962962962962963, + "grad_norm": 0.10094427317380905, + "learning_rate": 4.588235294117647e-05, + "loss": 0.023575644940137863, + "step": 301 + }, + { + "epoch": 0.798941798941799, + "grad_norm": 0.08192069083452225, + "learning_rate": 4.5294117647058826e-05, + "loss": 0.02380991168320179, + "step": 302 + }, + { + "epoch": 0.8015873015873016, + "grad_norm": 0.0720907524228096, + "learning_rate": 4.470588235294118e-05, + "loss": 0.01674514263868332, + "step": 303 + }, + { + "epoch": 0.8042328042328042, + "grad_norm": 0.058165185153484344, + "learning_rate": 4.411764705882353e-05, + "loss": 0.018333733081817627, + "step": 304 + }, + { + "epoch": 0.8068783068783069, + "grad_norm": 0.09807229042053223, + "learning_rate": 4.3529411764705885e-05, + "loss": 0.026520205661654472, + "step": 305 + }, + { + "epoch": 0.8095238095238095, + "grad_norm": 0.08209870010614395, + "learning_rate": 4.294117647058823e-05, + "loss": 0.028179757297039032, + "step": 306 + }, + { + "epoch": 0.8121693121693122, + "grad_norm": 0.08082698285579681, + "learning_rate": 4.235294117647059e-05, + "loss": 0.020067555829882622, + "step": 307 + }, + { + "epoch": 0.8148148148148148, + "grad_norm": 0.0704454705119133, + "learning_rate": 4.1764705882352944e-05, + "loss": 0.02571108378469944, + "step": 308 + }, + { + "epoch": 0.8174603174603174, + "grad_norm": 0.12649419903755188, + "learning_rate": 4.11764705882353e-05, + "loss": 0.030464062467217445, + "step": 309 + }, + { + "epoch": 0.8201058201058201, + "grad_norm": 0.0701553225517273, + "learning_rate": 4.058823529411765e-05, + "loss": 0.029247839003801346, + "step": 310 + }, + { + "epoch": 0.8227513227513228, + "grad_norm": 0.061975978314876556, + "learning_rate": 4e-05, + "loss": 0.019865376874804497, + "step": 311 + }, + { + "epoch": 0.8253968253968254, + "grad_norm": 0.07122108340263367, + "learning_rate": 3.9411764705882356e-05, + "loss": 0.025799460709095, + "step": 312 + }, + { + "epoch": 0.828042328042328, + "grad_norm": 0.0794585570693016, + "learning_rate": 3.882352941176471e-05, + "loss": 0.02584882080554962, + "step": 313 + }, + { + "epoch": 0.8306878306878307, + "grad_norm": 0.07829529792070389, + "learning_rate": 3.8235294117647055e-05, + "loss": 0.016808034852147102, + "step": 314 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 0.10015936195850372, + "learning_rate": 3.7647058823529415e-05, + "loss": 0.029843248426914215, + "step": 315 + }, + { + "epoch": 0.8359788359788359, + "grad_norm": 0.08752724528312683, + "learning_rate": 3.705882352941177e-05, + "loss": 0.0207672156393528, + "step": 316 + }, + { + "epoch": 0.8386243386243386, + "grad_norm": 0.07568460702896118, + "learning_rate": 3.6470588235294114e-05, + "loss": 0.025986317545175552, + "step": 317 + }, + { + "epoch": 0.8412698412698413, + "grad_norm": 0.10557642579078674, + "learning_rate": 3.5882352941176474e-05, + "loss": 0.03166591376066208, + "step": 318 + }, + { + "epoch": 0.843915343915344, + "grad_norm": 0.0882193073630333, + "learning_rate": 3.529411764705883e-05, + "loss": 0.027180485427379608, + "step": 319 + }, + { + "epoch": 0.8465608465608465, + "grad_norm": 0.10279812663793564, + "learning_rate": 3.470588235294118e-05, + "loss": 0.025324862450361252, + "step": 320 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.2450287149814784e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-320/training_args.bin b/sft_worldsplit_1_5b/checkpoint-320/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-320/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-360/README.md b/sft_worldsplit_1_5b/checkpoint-360/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-360/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-360/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-360/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-360/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01532f9eb531b83bb22175c77f44b2ce12bab80e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db7b9f146c2397e5472092719c9381db6a578ebc9188a23a2f6a8d1816c0d74 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-360/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-360/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-360/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-360/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..550801ee72266859a6c57777e1b7cde1183cf7d7 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80ac64d0bf03fb5fb78ef33c0ca14673a7da21bc4ba63239d23f8869e97bb82 +size 37970053 diff --git a/sft_worldsplit_1_5b/checkpoint-360/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-360/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-360/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-360/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..92256af6088456f08381c79161f6a49d1138bde2 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3d4b69719d334316ab79e4d09fa93ed2bbca983eae52f7da098f6a10493805 +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-360/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-360/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-360/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-360/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-360/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-360/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f07f5536bd35541346ff312889f7e30131fc33b5 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/trainer_state.json @@ -0,0 +1,2554 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9523809523809523, + "eval_steps": 500, + "global_step": 360, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + }, + { + "epoch": 0.42592592592592593, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "loss": 0.03136860206723213, + "step": 161 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "loss": 0.02894529700279236, + "step": 162 + }, + { + "epoch": 0.4312169312169312, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "loss": 0.033732134848833084, + "step": 163 + }, + { + "epoch": 0.43386243386243384, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "loss": 0.026288658380508423, + "step": 164 + }, + { + "epoch": 0.4365079365079365, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "loss": 0.03067208267748356, + "step": 165 + }, + { + "epoch": 0.43915343915343913, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "loss": 0.027257606387138367, + "step": 166 + }, + { + "epoch": 0.4417989417989418, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "loss": 0.020257430151104927, + "step": 167 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "loss": 0.025873055681586266, + "step": 168 + }, + { + "epoch": 0.4470899470899471, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "loss": 0.02722345106303692, + "step": 169 + }, + { + "epoch": 0.4497354497354497, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "loss": 0.0284090805798769, + "step": 170 + }, + { + "epoch": 0.4523809523809524, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "loss": 0.0273237656801939, + "step": 171 + }, + { + "epoch": 0.455026455026455, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "loss": 0.03370822221040726, + "step": 172 + }, + { + "epoch": 0.4576719576719577, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "loss": 0.018664535135030746, + "step": 173 + }, + { + "epoch": 0.4603174603174603, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "loss": 0.029450563713908195, + "step": 174 + }, + { + "epoch": 0.46296296296296297, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "loss": 0.02172383852303028, + "step": 175 + }, + { + "epoch": 0.4656084656084656, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "loss": 0.029448989778757095, + "step": 176 + }, + { + "epoch": 0.46825396825396826, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "loss": 0.023345600813627243, + "step": 177 + }, + { + "epoch": 0.4708994708994709, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "loss": 0.026639586314558983, + "step": 178 + }, + { + "epoch": 0.47354497354497355, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "loss": 0.021892163902521133, + "step": 179 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "loss": 0.022277187556028366, + "step": 180 + }, + { + "epoch": 0.47883597883597884, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "loss": 0.03035702183842659, + "step": 181 + }, + { + "epoch": 0.48148148148148145, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "loss": 0.03421338275074959, + "step": 182 + }, + { + "epoch": 0.48412698412698413, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "loss": 0.029597604647278786, + "step": 183 + }, + { + "epoch": 0.48677248677248675, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "loss": 0.027550101280212402, + "step": 184 + }, + { + "epoch": 0.4894179894179894, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "loss": 0.03323390707373619, + "step": 185 + }, + { + "epoch": 0.49206349206349204, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "loss": 0.02156604826450348, + "step": 186 + }, + { + "epoch": 0.4947089947089947, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "loss": 0.024817658588290215, + "step": 187 + }, + { + "epoch": 0.4973544973544973, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "loss": 0.02846340462565422, + "step": 188 + }, + { + "epoch": 0.5, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "loss": 0.016268836334347725, + "step": 189 + }, + { + "epoch": 0.5026455026455027, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "loss": 0.02841845154762268, + "step": 190 + }, + { + "epoch": 0.5052910052910053, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "loss": 0.0306367389857769, + "step": 191 + }, + { + "epoch": 0.5079365079365079, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "loss": 0.031015485525131226, + "step": 192 + }, + { + "epoch": 0.5105820105820106, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "loss": 0.03242127224802971, + "step": 193 + }, + { + "epoch": 0.5132275132275133, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "loss": 0.03684879094362259, + "step": 194 + }, + { + "epoch": 0.5158730158730159, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "loss": 0.0260506309568882, + "step": 195 + }, + { + "epoch": 0.5185185185185185, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "loss": 0.02128693461418152, + "step": 196 + }, + { + "epoch": 0.5211640211640212, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "loss": 0.03452152758836746, + "step": 197 + }, + { + "epoch": 0.5238095238095238, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "loss": 0.028310813009738922, + "step": 198 + }, + { + "epoch": 0.5264550264550265, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "loss": 0.029575366526842117, + "step": 199 + }, + { + "epoch": 0.5291005291005291, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "loss": 0.029606211930513382, + "step": 200 + }, + { + "epoch": 0.5317460317460317, + "grad_norm": 0.09481994062662125, + "learning_rate": 0.00010470588235294118, + "loss": 0.02741779386997223, + "step": 201 + }, + { + "epoch": 0.5343915343915344, + "grad_norm": 0.06643011420965195, + "learning_rate": 0.00010411764705882355, + "loss": 0.02750249207019806, + "step": 202 + }, + { + "epoch": 0.5370370370370371, + "grad_norm": 0.08693543821573257, + "learning_rate": 0.0001035294117647059, + "loss": 0.025049429386854172, + "step": 203 + }, + { + "epoch": 0.5396825396825397, + "grad_norm": 0.08780419826507568, + "learning_rate": 0.00010294117647058823, + "loss": 0.0188161451369524, + "step": 204 + }, + { + "epoch": 0.5423280423280423, + "grad_norm": 0.08089763671159744, + "learning_rate": 0.00010235294117647058, + "loss": 0.025752779096364975, + "step": 205 + }, + { + "epoch": 0.544973544973545, + "grad_norm": 0.11511234939098358, + "learning_rate": 0.00010176470588235295, + "loss": 0.03086625598371029, + "step": 206 + }, + { + "epoch": 0.5476190476190477, + "grad_norm": 0.10907749086618423, + "learning_rate": 0.0001011764705882353, + "loss": 0.0273880697786808, + "step": 207 + }, + { + "epoch": 0.5502645502645502, + "grad_norm": 0.08107511699199677, + "learning_rate": 0.00010058823529411765, + "loss": 0.026370292529463768, + "step": 208 + }, + { + "epoch": 0.5529100529100529, + "grad_norm": 0.0737859457731247, + "learning_rate": 0.0001, + "loss": 0.025786038488149643, + "step": 209 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.09232968837022781, + "learning_rate": 9.941176470588236e-05, + "loss": 0.030016383156180382, + "step": 210 + }, + { + "epoch": 0.5582010582010583, + "grad_norm": 0.0948951318860054, + "learning_rate": 9.882352941176471e-05, + "loss": 0.021605785936117172, + "step": 211 + }, + { + "epoch": 0.5608465608465608, + "grad_norm": 0.09735886752605438, + "learning_rate": 9.823529411764706e-05, + "loss": 0.031091010197997093, + "step": 212 + }, + { + "epoch": 0.5634920634920635, + "grad_norm": 0.10056869685649872, + "learning_rate": 9.764705882352942e-05, + "loss": 0.030390700325369835, + "step": 213 + }, + { + "epoch": 0.5661375661375662, + "grad_norm": 0.0720759853720665, + "learning_rate": 9.705882352941177e-05, + "loss": 0.02216975763440132, + "step": 214 + }, + { + "epoch": 0.5687830687830688, + "grad_norm": 0.09141097962856293, + "learning_rate": 9.647058823529412e-05, + "loss": 0.02660333178937435, + "step": 215 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.09253139793872833, + "learning_rate": 9.588235294117648e-05, + "loss": 0.02590668946504593, + "step": 216 + }, + { + "epoch": 0.5740740740740741, + "grad_norm": 0.08869278430938721, + "learning_rate": 9.529411764705883e-05, + "loss": 0.02776462584733963, + "step": 217 + }, + { + "epoch": 0.5767195767195767, + "grad_norm": 0.10566668212413788, + "learning_rate": 9.470588235294118e-05, + "loss": 0.015304268337786198, + "step": 218 + }, + { + "epoch": 0.5793650793650794, + "grad_norm": 0.08862630277872086, + "learning_rate": 9.411764705882353e-05, + "loss": 0.027874145656824112, + "step": 219 + }, + { + "epoch": 0.582010582010582, + "grad_norm": 0.0958574190735817, + "learning_rate": 9.352941176470589e-05, + "loss": 0.030754802748560905, + "step": 220 + }, + { + "epoch": 0.5846560846560847, + "grad_norm": 0.09204437583684921, + "learning_rate": 9.294117647058824e-05, + "loss": 0.023360423743724823, + "step": 221 + }, + { + "epoch": 0.5873015873015873, + "grad_norm": 0.12147050350904465, + "learning_rate": 9.23529411764706e-05, + "loss": 0.031416505575180054, + "step": 222 + }, + { + "epoch": 0.58994708994709, + "grad_norm": 0.08076925575733185, + "learning_rate": 9.176470588235295e-05, + "loss": 0.023884786292910576, + "step": 223 + }, + { + "epoch": 0.5925925925925926, + "grad_norm": 0.08516595512628555, + "learning_rate": 9.11764705882353e-05, + "loss": 0.025108790025115013, + "step": 224 + }, + { + "epoch": 0.5952380952380952, + "grad_norm": 0.09453090280294418, + "learning_rate": 9.058823529411765e-05, + "loss": 0.0236780047416687, + "step": 225 + }, + { + "epoch": 0.5978835978835979, + "grad_norm": 0.08398544788360596, + "learning_rate": 9e-05, + "loss": 0.02253679558634758, + "step": 226 + }, + { + "epoch": 0.6005291005291006, + "grad_norm": 0.08214128762483597, + "learning_rate": 8.941176470588236e-05, + "loss": 0.027625620365142822, + "step": 227 + }, + { + "epoch": 0.6031746031746031, + "grad_norm": 0.07763852924108505, + "learning_rate": 8.882352941176471e-05, + "loss": 0.018679391592741013, + "step": 228 + }, + { + "epoch": 0.6058201058201058, + "grad_norm": 0.0663997232913971, + "learning_rate": 8.823529411764706e-05, + "loss": 0.018782157450914383, + "step": 229 + }, + { + "epoch": 0.6084656084656085, + "grad_norm": 0.07828967273235321, + "learning_rate": 8.764705882352942e-05, + "loss": 0.027178611606359482, + "step": 230 + }, + { + "epoch": 0.6111111111111112, + "grad_norm": 0.08604388684034348, + "learning_rate": 8.705882352941177e-05, + "loss": 0.023709267377853394, + "step": 231 + }, + { + "epoch": 0.6137566137566137, + "grad_norm": 0.07984922081232071, + "learning_rate": 8.647058823529412e-05, + "loss": 0.02602708712220192, + "step": 232 + }, + { + "epoch": 0.6164021164021164, + "grad_norm": 0.07321182638406754, + "learning_rate": 8.588235294117646e-05, + "loss": 0.02468765154480934, + "step": 233 + }, + { + "epoch": 0.6190476190476191, + "grad_norm": 0.07817960530519485, + "learning_rate": 8.529411764705883e-05, + "loss": 0.03028242662549019, + "step": 234 + }, + { + "epoch": 0.6216931216931217, + "grad_norm": 0.06251050531864166, + "learning_rate": 8.470588235294118e-05, + "loss": 0.02902349643409252, + "step": 235 + }, + { + "epoch": 0.6243386243386243, + "grad_norm": 0.09529170393943787, + "learning_rate": 8.411764705882354e-05, + "loss": 0.024306783452630043, + "step": 236 + }, + { + "epoch": 0.626984126984127, + "grad_norm": 0.1267942190170288, + "learning_rate": 8.352941176470589e-05, + "loss": 0.03521513566374779, + "step": 237 + }, + { + "epoch": 0.6296296296296297, + "grad_norm": 0.08621630817651749, + "learning_rate": 8.294117647058824e-05, + "loss": 0.020196501165628433, + "step": 238 + }, + { + "epoch": 0.6322751322751323, + "grad_norm": 0.07552770525217056, + "learning_rate": 8.23529411764706e-05, + "loss": 0.029385194182395935, + "step": 239 + }, + { + "epoch": 0.6349206349206349, + "grad_norm": 0.09521529078483582, + "learning_rate": 8.176470588235295e-05, + "loss": 0.01693333312869072, + "step": 240 + }, + { + "epoch": 0.6375661375661376, + "grad_norm": 0.09436187893152237, + "learning_rate": 8.11764705882353e-05, + "loss": 0.025097660720348358, + "step": 241 + }, + { + "epoch": 0.6402116402116402, + "grad_norm": 0.07002269476652145, + "learning_rate": 8.058823529411765e-05, + "loss": 0.027106281369924545, + "step": 242 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.08871318399906158, + "learning_rate": 8e-05, + "loss": 0.027904586866497993, + "step": 243 + }, + { + "epoch": 0.6455026455026455, + "grad_norm": 0.0833863765001297, + "learning_rate": 7.941176470588235e-05, + "loss": 0.030118469148874283, + "step": 244 + }, + { + "epoch": 0.6481481481481481, + "grad_norm": 0.0630115196108818, + "learning_rate": 7.882352941176471e-05, + "loss": 0.015584684908390045, + "step": 245 + }, + { + "epoch": 0.6507936507936508, + "grad_norm": 0.0754900649189949, + "learning_rate": 7.823529411764707e-05, + "loss": 0.024866245687007904, + "step": 246 + }, + { + "epoch": 0.6534391534391535, + "grad_norm": 0.09214677661657333, + "learning_rate": 7.764705882352942e-05, + "loss": 0.02521335333585739, + "step": 247 + }, + { + "epoch": 0.656084656084656, + "grad_norm": 0.07616355270147324, + "learning_rate": 7.705882352941177e-05, + "loss": 0.02567514404654503, + "step": 248 + }, + { + "epoch": 0.6587301587301587, + "grad_norm": 0.10812173038721085, + "learning_rate": 7.647058823529411e-05, + "loss": 0.03087168186903, + "step": 249 + }, + { + "epoch": 0.6613756613756614, + "grad_norm": 0.07225628942251205, + "learning_rate": 7.588235294117648e-05, + "loss": 0.02886301279067993, + "step": 250 + }, + { + "epoch": 0.6640211640211641, + "grad_norm": 0.08968020230531693, + "learning_rate": 7.529411764705883e-05, + "loss": 0.02838725596666336, + "step": 251 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.1066119521856308, + "learning_rate": 7.470588235294118e-05, + "loss": 0.0240425243973732, + "step": 252 + }, + { + "epoch": 0.6693121693121693, + "grad_norm": 0.07908853143453598, + "learning_rate": 7.411764705882354e-05, + "loss": 0.020799003541469574, + "step": 253 + }, + { + "epoch": 0.671957671957672, + "grad_norm": 0.08067328482866287, + "learning_rate": 7.352941176470589e-05, + "loss": 0.03212092071771622, + "step": 254 + }, + { + "epoch": 0.6746031746031746, + "grad_norm": 0.09752342849969864, + "learning_rate": 7.294117647058823e-05, + "loss": 0.02562413364648819, + "step": 255 + }, + { + "epoch": 0.6772486772486772, + "grad_norm": 0.07102340459823608, + "learning_rate": 7.23529411764706e-05, + "loss": 0.01694977842271328, + "step": 256 + }, + { + "epoch": 0.6798941798941799, + "grad_norm": 0.07671815156936646, + "learning_rate": 7.176470588235295e-05, + "loss": 0.02575928345322609, + "step": 257 + }, + { + "epoch": 0.6825396825396826, + "grad_norm": 0.1419815868139267, + "learning_rate": 7.11764705882353e-05, + "loss": 0.021748626604676247, + "step": 258 + }, + { + "epoch": 0.6851851851851852, + "grad_norm": 0.10793975740671158, + "learning_rate": 7.058823529411765e-05, + "loss": 0.02359670028090477, + "step": 259 + }, + { + "epoch": 0.6878306878306878, + "grad_norm": 0.10104779154062271, + "learning_rate": 7e-05, + "loss": 0.020240038633346558, + "step": 260 + }, + { + "epoch": 0.6904761904761905, + "grad_norm": 0.09232339262962341, + "learning_rate": 6.941176470588236e-05, + "loss": 0.03007177822291851, + "step": 261 + }, + { + "epoch": 0.6931216931216931, + "grad_norm": 0.060809917747974396, + "learning_rate": 6.882352941176471e-05, + "loss": 0.02441459335386753, + "step": 262 + }, + { + "epoch": 0.6957671957671958, + "grad_norm": 0.07218184322118759, + "learning_rate": 6.823529411764707e-05, + "loss": 0.02289595827460289, + "step": 263 + }, + { + "epoch": 0.6984126984126984, + "grad_norm": 0.09035782516002655, + "learning_rate": 6.764705882352942e-05, + "loss": 0.02958938293159008, + "step": 264 + }, + { + "epoch": 0.701058201058201, + "grad_norm": 0.08335528522729874, + "learning_rate": 6.705882352941176e-05, + "loss": 0.028876766562461853, + "step": 265 + }, + { + "epoch": 0.7037037037037037, + "grad_norm": 0.06112835556268692, + "learning_rate": 6.647058823529411e-05, + "loss": 0.022992007434368134, + "step": 266 + }, + { + "epoch": 0.7063492063492064, + "grad_norm": 0.09583422541618347, + "learning_rate": 6.588235294117648e-05, + "loss": 0.027839267626404762, + "step": 267 + }, + { + "epoch": 0.708994708994709, + "grad_norm": 0.10437622666358948, + "learning_rate": 6.529411764705883e-05, + "loss": 0.03310278058052063, + "step": 268 + }, + { + "epoch": 0.7116402116402116, + "grad_norm": 0.05979550629854202, + "learning_rate": 6.470588235294118e-05, + "loss": 0.02412830851972103, + "step": 269 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.057857904583215714, + "learning_rate": 6.411764705882354e-05, + "loss": 0.026769282296299934, + "step": 270 + }, + { + "epoch": 0.716931216931217, + "grad_norm": 0.0795726403594017, + "learning_rate": 6.352941176470588e-05, + "loss": 0.01822183094918728, + "step": 271 + }, + { + "epoch": 0.7195767195767195, + "grad_norm": 0.11597180366516113, + "learning_rate": 6.294117647058824e-05, + "loss": 0.03175610303878784, + "step": 272 + }, + { + "epoch": 0.7222222222222222, + "grad_norm": 0.12822823226451874, + "learning_rate": 6.23529411764706e-05, + "loss": 0.02406914159655571, + "step": 273 + }, + { + "epoch": 0.7248677248677249, + "grad_norm": 0.11681342869997025, + "learning_rate": 6.176470588235295e-05, + "loss": 0.017685284838080406, + "step": 274 + }, + { + "epoch": 0.7275132275132276, + "grad_norm": 0.06948421150445938, + "learning_rate": 6.11764705882353e-05, + "loss": 0.02279685251414776, + "step": 275 + }, + { + "epoch": 0.7301587301587301, + "grad_norm": 0.10276354104280472, + "learning_rate": 6.058823529411765e-05, + "loss": 0.032588277012109756, + "step": 276 + }, + { + "epoch": 0.7328042328042328, + "grad_norm": 0.10721025615930557, + "learning_rate": 6e-05, + "loss": 0.02961578778922558, + "step": 277 + }, + { + "epoch": 0.7354497354497355, + "grad_norm": 0.08410617709159851, + "learning_rate": 5.9411764705882355e-05, + "loss": 0.02747366949915886, + "step": 278 + }, + { + "epoch": 0.7380952380952381, + "grad_norm": 0.0806620791554451, + "learning_rate": 5.882352941176471e-05, + "loss": 0.02593173459172249, + "step": 279 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.06915932148694992, + "learning_rate": 5.823529411764707e-05, + "loss": 0.02764303609728813, + "step": 280 + }, + { + "epoch": 0.7433862433862434, + "grad_norm": 0.06709478050470352, + "learning_rate": 5.764705882352941e-05, + "loss": 0.024347776547074318, + "step": 281 + }, + { + "epoch": 0.746031746031746, + "grad_norm": 0.053211960941553116, + "learning_rate": 5.7058823529411766e-05, + "loss": 0.02141982689499855, + "step": 282 + }, + { + "epoch": 0.7486772486772487, + "grad_norm": 0.06790946424007416, + "learning_rate": 5.647058823529412e-05, + "loss": 0.02252194657921791, + "step": 283 + }, + { + "epoch": 0.7513227513227513, + "grad_norm": 0.08224959671497345, + "learning_rate": 5.588235294117647e-05, + "loss": 0.01945466734468937, + "step": 284 + }, + { + "epoch": 0.753968253968254, + "grad_norm": 0.09265672415494919, + "learning_rate": 5.529411764705883e-05, + "loss": 0.032275885343551636, + "step": 285 + }, + { + "epoch": 0.7566137566137566, + "grad_norm": 0.07285762578248978, + "learning_rate": 5.4705882352941185e-05, + "loss": 0.027079608291387558, + "step": 286 + }, + { + "epoch": 0.7592592592592593, + "grad_norm": 0.05742108076810837, + "learning_rate": 5.411764705882353e-05, + "loss": 0.02384945936501026, + "step": 287 + }, + { + "epoch": 0.7619047619047619, + "grad_norm": 0.11136175692081451, + "learning_rate": 5.3529411764705884e-05, + "loss": 0.02898704633116722, + "step": 288 + }, + { + "epoch": 0.7645502645502645, + "grad_norm": 0.09560064971446991, + "learning_rate": 5.294117647058824e-05, + "loss": 0.03049132414162159, + "step": 289 + }, + { + "epoch": 0.7671957671957672, + "grad_norm": 0.062173303216695786, + "learning_rate": 5.235294117647059e-05, + "loss": 0.024453597143292427, + "step": 290 + }, + { + "epoch": 0.7698412698412699, + "grad_norm": 0.0988180935382843, + "learning_rate": 5.176470588235295e-05, + "loss": 0.0318286158144474, + "step": 291 + }, + { + "epoch": 0.7724867724867724, + "grad_norm": 0.0626835897564888, + "learning_rate": 5.117647058823529e-05, + "loss": 0.02699001133441925, + "step": 292 + }, + { + "epoch": 0.7751322751322751, + "grad_norm": 0.07981280982494354, + "learning_rate": 5.058823529411765e-05, + "loss": 0.023896772414445877, + "step": 293 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.07893257588148117, + "learning_rate": 5e-05, + "loss": 0.024391846731305122, + "step": 294 + }, + { + "epoch": 0.7804232804232805, + "grad_norm": 0.06932593882083893, + "learning_rate": 4.9411764705882355e-05, + "loss": 0.025584066286683083, + "step": 295 + }, + { + "epoch": 0.783068783068783, + "grad_norm": 0.07785957306623459, + "learning_rate": 4.882352941176471e-05, + "loss": 0.0220668762922287, + "step": 296 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 0.06624335050582886, + "learning_rate": 4.823529411764706e-05, + "loss": 0.020017938688397408, + "step": 297 + }, + { + "epoch": 0.7883597883597884, + "grad_norm": 0.0832471251487732, + "learning_rate": 4.7647058823529414e-05, + "loss": 0.02506105974316597, + "step": 298 + }, + { + "epoch": 0.791005291005291, + "grad_norm": 0.06540657579898834, + "learning_rate": 4.705882352941177e-05, + "loss": 0.017597489058971405, + "step": 299 + }, + { + "epoch": 0.7936507936507936, + "grad_norm": 0.15526005625724792, + "learning_rate": 4.647058823529412e-05, + "loss": 0.0298212431371212, + "step": 300 + }, + { + "epoch": 0.7962962962962963, + "grad_norm": 0.10094427317380905, + "learning_rate": 4.588235294117647e-05, + "loss": 0.023575644940137863, + "step": 301 + }, + { + "epoch": 0.798941798941799, + "grad_norm": 0.08192069083452225, + "learning_rate": 4.5294117647058826e-05, + "loss": 0.02380991168320179, + "step": 302 + }, + { + "epoch": 0.8015873015873016, + "grad_norm": 0.0720907524228096, + "learning_rate": 4.470588235294118e-05, + "loss": 0.01674514263868332, + "step": 303 + }, + { + "epoch": 0.8042328042328042, + "grad_norm": 0.058165185153484344, + "learning_rate": 4.411764705882353e-05, + "loss": 0.018333733081817627, + "step": 304 + }, + { + "epoch": 0.8068783068783069, + "grad_norm": 0.09807229042053223, + "learning_rate": 4.3529411764705885e-05, + "loss": 0.026520205661654472, + "step": 305 + }, + { + "epoch": 0.8095238095238095, + "grad_norm": 0.08209870010614395, + "learning_rate": 4.294117647058823e-05, + "loss": 0.028179757297039032, + "step": 306 + }, + { + "epoch": 0.8121693121693122, + "grad_norm": 0.08082698285579681, + "learning_rate": 4.235294117647059e-05, + "loss": 0.020067555829882622, + "step": 307 + }, + { + "epoch": 0.8148148148148148, + "grad_norm": 0.0704454705119133, + "learning_rate": 4.1764705882352944e-05, + "loss": 0.02571108378469944, + "step": 308 + }, + { + "epoch": 0.8174603174603174, + "grad_norm": 0.12649419903755188, + "learning_rate": 4.11764705882353e-05, + "loss": 0.030464062467217445, + "step": 309 + }, + { + "epoch": 0.8201058201058201, + "grad_norm": 0.0701553225517273, + "learning_rate": 4.058823529411765e-05, + "loss": 0.029247839003801346, + "step": 310 + }, + { + "epoch": 0.8227513227513228, + "grad_norm": 0.061975978314876556, + "learning_rate": 4e-05, + "loss": 0.019865376874804497, + "step": 311 + }, + { + "epoch": 0.8253968253968254, + "grad_norm": 0.07122108340263367, + "learning_rate": 3.9411764705882356e-05, + "loss": 0.025799460709095, + "step": 312 + }, + { + "epoch": 0.828042328042328, + "grad_norm": 0.0794585570693016, + "learning_rate": 3.882352941176471e-05, + "loss": 0.02584882080554962, + "step": 313 + }, + { + "epoch": 0.8306878306878307, + "grad_norm": 0.07829529792070389, + "learning_rate": 3.8235294117647055e-05, + "loss": 0.016808034852147102, + "step": 314 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 0.10015936195850372, + "learning_rate": 3.7647058823529415e-05, + "loss": 0.029843248426914215, + "step": 315 + }, + { + "epoch": 0.8359788359788359, + "grad_norm": 0.08752724528312683, + "learning_rate": 3.705882352941177e-05, + "loss": 0.0207672156393528, + "step": 316 + }, + { + "epoch": 0.8386243386243386, + "grad_norm": 0.07568460702896118, + "learning_rate": 3.6470588235294114e-05, + "loss": 0.025986317545175552, + "step": 317 + }, + { + "epoch": 0.8412698412698413, + "grad_norm": 0.10557642579078674, + "learning_rate": 3.5882352941176474e-05, + "loss": 0.03166591376066208, + "step": 318 + }, + { + "epoch": 0.843915343915344, + "grad_norm": 0.0882193073630333, + "learning_rate": 3.529411764705883e-05, + "loss": 0.027180485427379608, + "step": 319 + }, + { + "epoch": 0.8465608465608465, + "grad_norm": 0.10279812663793564, + "learning_rate": 3.470588235294118e-05, + "loss": 0.025324862450361252, + "step": 320 + }, + { + "epoch": 0.8492063492063492, + "grad_norm": 0.08359183371067047, + "learning_rate": 3.411764705882353e-05, + "loss": 0.031235653907060623, + "step": 321 + }, + { + "epoch": 0.8518518518518519, + "grad_norm": 0.06786882132291794, + "learning_rate": 3.352941176470588e-05, + "loss": 0.028402645140886307, + "step": 322 + }, + { + "epoch": 0.8544973544973545, + "grad_norm": 0.09749054163694382, + "learning_rate": 3.294117647058824e-05, + "loss": 0.024368081241846085, + "step": 323 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 0.06912931054830551, + "learning_rate": 3.235294117647059e-05, + "loss": 0.029769334942102432, + "step": 324 + }, + { + "epoch": 0.8597883597883598, + "grad_norm": 0.07546117901802063, + "learning_rate": 3.176470588235294e-05, + "loss": 0.027555279433727264, + "step": 325 + }, + { + "epoch": 0.8624338624338624, + "grad_norm": 0.08951126784086227, + "learning_rate": 3.11764705882353e-05, + "loss": 0.03135411813855171, + "step": 326 + }, + { + "epoch": 0.8650793650793651, + "grad_norm": 0.08512236922979355, + "learning_rate": 3.058823529411765e-05, + "loss": 0.018115023151040077, + "step": 327 + }, + { + "epoch": 0.8677248677248677, + "grad_norm": 0.08400000631809235, + "learning_rate": 3e-05, + "loss": 0.024688314646482468, + "step": 328 + }, + { + "epoch": 0.8703703703703703, + "grad_norm": 0.06805701553821564, + "learning_rate": 2.9411764705882354e-05, + "loss": 0.025533631443977356, + "step": 329 + }, + { + "epoch": 0.873015873015873, + "grad_norm": 0.08600405603647232, + "learning_rate": 2.8823529411764703e-05, + "loss": 0.02600039541721344, + "step": 330 + }, + { + "epoch": 0.8756613756613757, + "grad_norm": 0.07160481810569763, + "learning_rate": 2.823529411764706e-05, + "loss": 0.0179967749863863, + "step": 331 + }, + { + "epoch": 0.8783068783068783, + "grad_norm": 0.07811455428600311, + "learning_rate": 2.7647058823529416e-05, + "loss": 0.025588110089302063, + "step": 332 + }, + { + "epoch": 0.8809523809523809, + "grad_norm": 0.07041554898023605, + "learning_rate": 2.7058823529411766e-05, + "loss": 0.024966120719909668, + "step": 333 + }, + { + "epoch": 0.8835978835978836, + "grad_norm": 0.07744963467121124, + "learning_rate": 2.647058823529412e-05, + "loss": 0.02608634904026985, + "step": 334 + }, + { + "epoch": 0.8862433862433863, + "grad_norm": 0.07343604415655136, + "learning_rate": 2.5882352941176475e-05, + "loss": 0.024391014128923416, + "step": 335 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 0.10205741226673126, + "learning_rate": 2.5294117647058825e-05, + "loss": 0.015595385804772377, + "step": 336 + }, + { + "epoch": 0.8915343915343915, + "grad_norm": 0.08257130533456802, + "learning_rate": 2.4705882352941178e-05, + "loss": 0.025536613538861275, + "step": 337 + }, + { + "epoch": 0.8941798941798942, + "grad_norm": 0.1315038800239563, + "learning_rate": 2.411764705882353e-05, + "loss": 0.031951554119586945, + "step": 338 + }, + { + "epoch": 0.8968253968253969, + "grad_norm": 0.08411096036434174, + "learning_rate": 2.3529411764705884e-05, + "loss": 0.023610807955265045, + "step": 339 + }, + { + "epoch": 0.8994708994708994, + "grad_norm": 0.07679664343595505, + "learning_rate": 2.2941176470588237e-05, + "loss": 0.030541151762008667, + "step": 340 + }, + { + "epoch": 0.9021164021164021, + "grad_norm": 0.07304323464632034, + "learning_rate": 2.235294117647059e-05, + "loss": 0.02696535736322403, + "step": 341 + }, + { + "epoch": 0.9047619047619048, + "grad_norm": 0.061864130198955536, + "learning_rate": 2.1764705882352943e-05, + "loss": 0.02784024551510811, + "step": 342 + }, + { + "epoch": 0.9074074074074074, + "grad_norm": 0.06673755496740341, + "learning_rate": 2.1176470588235296e-05, + "loss": 0.025248851627111435, + "step": 343 + }, + { + "epoch": 0.91005291005291, + "grad_norm": 0.07668192684650421, + "learning_rate": 2.058823529411765e-05, + "loss": 0.029280394315719604, + "step": 344 + }, + { + "epoch": 0.9126984126984127, + "grad_norm": 0.07531134784221649, + "learning_rate": 2e-05, + "loss": 0.02605779841542244, + "step": 345 + }, + { + "epoch": 0.9153439153439153, + "grad_norm": 0.08565571904182434, + "learning_rate": 1.9411764705882355e-05, + "loss": 0.028157757595181465, + "step": 346 + }, + { + "epoch": 0.917989417989418, + "grad_norm": 0.07180029898881912, + "learning_rate": 1.8823529411764708e-05, + "loss": 0.025131918489933014, + "step": 347 + }, + { + "epoch": 0.9206349206349206, + "grad_norm": 0.07056324183940887, + "learning_rate": 1.8235294117647057e-05, + "loss": 0.02796267159283161, + "step": 348 + }, + { + "epoch": 0.9232804232804233, + "grad_norm": 0.08292558044195175, + "learning_rate": 1.7647058823529414e-05, + "loss": 0.025395592674613, + "step": 349 + }, + { + "epoch": 0.9259259259259259, + "grad_norm": 0.07555428147315979, + "learning_rate": 1.7058823529411767e-05, + "loss": 0.028561469167470932, + "step": 350 + }, + { + "epoch": 0.9285714285714286, + "grad_norm": 0.06799963861703873, + "learning_rate": 1.647058823529412e-05, + "loss": 0.020762892439961433, + "step": 351 + }, + { + "epoch": 0.9312169312169312, + "grad_norm": 0.09109848737716675, + "learning_rate": 1.588235294117647e-05, + "loss": 0.014401258900761604, + "step": 352 + }, + { + "epoch": 0.9338624338624338, + "grad_norm": 0.07757920771837234, + "learning_rate": 1.5294117647058826e-05, + "loss": 0.02667010948061943, + "step": 353 + }, + { + "epoch": 0.9365079365079365, + "grad_norm": 0.07955507934093475, + "learning_rate": 1.4705882352941177e-05, + "loss": 0.023868650197982788, + "step": 354 + }, + { + "epoch": 0.9391534391534392, + "grad_norm": 0.07310300320386887, + "learning_rate": 1.411764705882353e-05, + "loss": 0.017540596425533295, + "step": 355 + }, + { + "epoch": 0.9417989417989417, + "grad_norm": 0.06979277729988098, + "learning_rate": 1.3529411764705883e-05, + "loss": 0.026370886713266373, + "step": 356 + }, + { + "epoch": 0.9444444444444444, + "grad_norm": 0.07074704021215439, + "learning_rate": 1.2941176470588238e-05, + "loss": 0.018387794494628906, + "step": 357 + }, + { + "epoch": 0.9470899470899471, + "grad_norm": 0.07400532811880112, + "learning_rate": 1.2352941176470589e-05, + "loss": 0.022234005853533745, + "step": 358 + }, + { + "epoch": 0.9497354497354498, + "grad_norm": 0.06865154951810837, + "learning_rate": 1.1764705882352942e-05, + "loss": 0.022929485887289047, + "step": 359 + }, + { + "epoch": 0.9523809523809523, + "grad_norm": 0.07323960214853287, + "learning_rate": 1.1176470588235295e-05, + "loss": 0.014135655015707016, + "step": 360 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.3971934077201408e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-360/training_args.bin b/sft_worldsplit_1_5b/checkpoint-360/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-360/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-378/README.md b/sft_worldsplit_1_5b/checkpoint-378/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-378/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-378/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-378/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-378/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72db56363eb36ce9dbcb28c8adc455eb44ba2c5d --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a51a8e5505d70bde4e3c3878cd165c69001836a56f37a89ffff8d66ac02408 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-378/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-378/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-378/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-378/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..81953b04e1dae960875fe8f52752d4a201e8c921 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8536c19dbdcde5d47947a3a03626fe6060ef80d42a7893e0af1754d63b9a390 +size 37970053 diff --git a/sft_worldsplit_1_5b/checkpoint-378/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-378/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-378/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-378/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f986b4c07f57c9b369a875ce5c0b5b7fd1b1da3 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60eaed8b3d4c75d45885d5c484983900aa1d4f5f8048d1d8c4ea07b25c93636 +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-378/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-378/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-378/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-378/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-378/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-378/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e44606feca721b7f13a7f3c5bea8f3003a540515 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/trainer_state.json @@ -0,0 +1,2680 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 378, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "loss": 0.05233598127961159, + "step": 81 + }, + { + "epoch": 0.21693121693121692, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "loss": 0.03420679643750191, + "step": 82 + }, + { + "epoch": 0.21957671957671956, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "loss": 0.031814150512218475, + "step": 83 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "loss": 0.033638425171375275, + "step": 84 + }, + { + "epoch": 0.22486772486772486, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "loss": 0.03216666728258133, + "step": 85 + }, + { + "epoch": 0.2275132275132275, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "loss": 0.04404332861304283, + "step": 86 + }, + { + "epoch": 0.23015873015873015, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "loss": 0.03520449623465538, + "step": 87 + }, + { + "epoch": 0.2328042328042328, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "loss": 0.033416785299777985, + "step": 88 + }, + { + "epoch": 0.23544973544973544, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "loss": 0.02910282462835312, + "step": 89 + }, + { + "epoch": 0.23809523809523808, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "loss": 0.04076948016881943, + "step": 90 + }, + { + "epoch": 0.24074074074074073, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "loss": 0.03425406664609909, + "step": 91 + }, + { + "epoch": 0.24338624338624337, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "loss": 0.031353384256362915, + "step": 92 + }, + { + "epoch": 0.24603174603174602, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "loss": 0.0268703605979681, + "step": 93 + }, + { + "epoch": 0.24867724867724866, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "loss": 0.03515759855508804, + "step": 94 + }, + { + "epoch": 0.25132275132275134, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "loss": 0.02797013334929943, + "step": 95 + }, + { + "epoch": 0.25396825396825395, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "loss": 0.04394323751330376, + "step": 96 + }, + { + "epoch": 0.2566137566137566, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "loss": 0.037255994975566864, + "step": 97 + }, + { + "epoch": 0.25925925925925924, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "loss": 0.03898382931947708, + "step": 98 + }, + { + "epoch": 0.2619047619047619, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "loss": 0.039507556706666946, + "step": 99 + }, + { + "epoch": 0.26455026455026454, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "loss": 0.02951202541589737, + "step": 100 + }, + { + "epoch": 0.2671957671957672, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "loss": 0.026405351236462593, + "step": 101 + }, + { + "epoch": 0.2698412698412698, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "loss": 0.033975858241319656, + "step": 102 + }, + { + "epoch": 0.2724867724867725, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "loss": 0.04301761835813522, + "step": 103 + }, + { + "epoch": 0.2751322751322751, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "loss": 0.03340883180499077, + "step": 104 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "loss": 0.023269247263669968, + "step": 105 + }, + { + "epoch": 0.2804232804232804, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "loss": 0.03297317028045654, + "step": 106 + }, + { + "epoch": 0.2830687830687831, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "loss": 0.02670835703611374, + "step": 107 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "loss": 0.03365064039826393, + "step": 108 + }, + { + "epoch": 0.28835978835978837, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "loss": 0.03272430971264839, + "step": 109 + }, + { + "epoch": 0.291005291005291, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "loss": 0.030736371874809265, + "step": 110 + }, + { + "epoch": 0.29365079365079366, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "loss": 0.03765019774436951, + "step": 111 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "loss": 0.027364399284124374, + "step": 112 + }, + { + "epoch": 0.29894179894179895, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "loss": 0.03020496666431427, + "step": 113 + }, + { + "epoch": 0.30158730158730157, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "loss": 0.024272479116916656, + "step": 114 + }, + { + "epoch": 0.30423280423280424, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "loss": 0.030500095337629318, + "step": 115 + }, + { + "epoch": 0.30687830687830686, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "loss": 0.024758869782090187, + "step": 116 + }, + { + "epoch": 0.30952380952380953, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "loss": 0.029552360996603966, + "step": 117 + }, + { + "epoch": 0.31216931216931215, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "loss": 0.030012380331754684, + "step": 118 + }, + { + "epoch": 0.3148148148148148, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "loss": 0.02706737630069256, + "step": 119 + }, + { + "epoch": 0.31746031746031744, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "loss": 0.0400836318731308, + "step": 120 + }, + { + "epoch": 0.3201058201058201, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "loss": 0.03125084191560745, + "step": 121 + }, + { + "epoch": 0.32275132275132273, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "loss": 0.035637352615594864, + "step": 122 + }, + { + "epoch": 0.3253968253968254, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "loss": 0.02989823743700981, + "step": 123 + }, + { + "epoch": 0.328042328042328, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "loss": 0.029374703764915466, + "step": 124 + }, + { + "epoch": 0.3306878306878307, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "loss": 0.02627715840935707, + "step": 125 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "loss": 0.03121405467391014, + "step": 126 + }, + { + "epoch": 0.335978835978836, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "loss": 0.032626084983348846, + "step": 127 + }, + { + "epoch": 0.3386243386243386, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "loss": 0.028939921408891678, + "step": 128 + }, + { + "epoch": 0.3412698412698413, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "loss": 0.021900050342082977, + "step": 129 + }, + { + "epoch": 0.3439153439153439, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "loss": 0.023994363844394684, + "step": 130 + }, + { + "epoch": 0.34656084656084657, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "loss": 0.031131461262702942, + "step": 131 + }, + { + "epoch": 0.3492063492063492, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "loss": 0.02585621550679207, + "step": 132 + }, + { + "epoch": 0.35185185185185186, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "loss": 0.03250286355614662, + "step": 133 + }, + { + "epoch": 0.3544973544973545, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "loss": 0.020486077293753624, + "step": 134 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "loss": 0.036177776753902435, + "step": 135 + }, + { + "epoch": 0.35978835978835977, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "loss": 0.012204527854919434, + "step": 136 + }, + { + "epoch": 0.36243386243386244, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "loss": 0.03306424245238304, + "step": 137 + }, + { + "epoch": 0.36507936507936506, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "loss": 0.015852898359298706, + "step": 138 + }, + { + "epoch": 0.36772486772486773, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "loss": 0.0280722938477993, + "step": 139 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "loss": 0.02845999225974083, + "step": 140 + }, + { + "epoch": 0.373015873015873, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "loss": 0.028397955000400543, + "step": 141 + }, + { + "epoch": 0.37566137566137564, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "loss": 0.03037174791097641, + "step": 142 + }, + { + "epoch": 0.3783068783068783, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "loss": 0.031476639211177826, + "step": 143 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "loss": 0.02341204509139061, + "step": 144 + }, + { + "epoch": 0.3835978835978836, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "loss": 0.029298145323991776, + "step": 145 + }, + { + "epoch": 0.3862433862433862, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "loss": 0.026255691424012184, + "step": 146 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "loss": 0.03272281587123871, + "step": 147 + }, + { + "epoch": 0.3915343915343915, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "loss": 0.028953030705451965, + "step": 148 + }, + { + "epoch": 0.3941798941798942, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "loss": 0.03124978020787239, + "step": 149 + }, + { + "epoch": 0.3968253968253968, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "loss": 0.032467320561409, + "step": 150 + }, + { + "epoch": 0.3994708994708995, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "loss": 0.026149973273277283, + "step": 151 + }, + { + "epoch": 0.4021164021164021, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "loss": 0.03004319593310356, + "step": 152 + }, + { + "epoch": 0.40476190476190477, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "loss": 0.029231414198875427, + "step": 153 + }, + { + "epoch": 0.4074074074074074, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "loss": 0.03578457981348038, + "step": 154 + }, + { + "epoch": 0.41005291005291006, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "loss": 0.02078537829220295, + "step": 155 + }, + { + "epoch": 0.4126984126984127, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "loss": 0.03142306208610535, + "step": 156 + }, + { + "epoch": 0.41534391534391535, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "loss": 0.02688862755894661, + "step": 157 + }, + { + "epoch": 0.41798941798941797, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "loss": 0.027476545423269272, + "step": 158 + }, + { + "epoch": 0.42063492063492064, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "loss": 0.029973959550261497, + "step": 159 + }, + { + "epoch": 0.42328042328042326, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "loss": 0.022143110632896423, + "step": 160 + }, + { + "epoch": 0.42592592592592593, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "loss": 0.03136860206723213, + "step": 161 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "loss": 0.02894529700279236, + "step": 162 + }, + { + "epoch": 0.4312169312169312, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "loss": 0.033732134848833084, + "step": 163 + }, + { + "epoch": 0.43386243386243384, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "loss": 0.026288658380508423, + "step": 164 + }, + { + "epoch": 0.4365079365079365, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "loss": 0.03067208267748356, + "step": 165 + }, + { + "epoch": 0.43915343915343913, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "loss": 0.027257606387138367, + "step": 166 + }, + { + "epoch": 0.4417989417989418, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "loss": 0.020257430151104927, + "step": 167 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "loss": 0.025873055681586266, + "step": 168 + }, + { + "epoch": 0.4470899470899471, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "loss": 0.02722345106303692, + "step": 169 + }, + { + "epoch": 0.4497354497354497, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "loss": 0.0284090805798769, + "step": 170 + }, + { + "epoch": 0.4523809523809524, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "loss": 0.0273237656801939, + "step": 171 + }, + { + "epoch": 0.455026455026455, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "loss": 0.03370822221040726, + "step": 172 + }, + { + "epoch": 0.4576719576719577, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "loss": 0.018664535135030746, + "step": 173 + }, + { + "epoch": 0.4603174603174603, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "loss": 0.029450563713908195, + "step": 174 + }, + { + "epoch": 0.46296296296296297, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "loss": 0.02172383852303028, + "step": 175 + }, + { + "epoch": 0.4656084656084656, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "loss": 0.029448989778757095, + "step": 176 + }, + { + "epoch": 0.46825396825396826, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "loss": 0.023345600813627243, + "step": 177 + }, + { + "epoch": 0.4708994708994709, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "loss": 0.026639586314558983, + "step": 178 + }, + { + "epoch": 0.47354497354497355, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "loss": 0.021892163902521133, + "step": 179 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "loss": 0.022277187556028366, + "step": 180 + }, + { + "epoch": 0.47883597883597884, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "loss": 0.03035702183842659, + "step": 181 + }, + { + "epoch": 0.48148148148148145, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "loss": 0.03421338275074959, + "step": 182 + }, + { + "epoch": 0.48412698412698413, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "loss": 0.029597604647278786, + "step": 183 + }, + { + "epoch": 0.48677248677248675, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "loss": 0.027550101280212402, + "step": 184 + }, + { + "epoch": 0.4894179894179894, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "loss": 0.03323390707373619, + "step": 185 + }, + { + "epoch": 0.49206349206349204, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "loss": 0.02156604826450348, + "step": 186 + }, + { + "epoch": 0.4947089947089947, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "loss": 0.024817658588290215, + "step": 187 + }, + { + "epoch": 0.4973544973544973, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "loss": 0.02846340462565422, + "step": 188 + }, + { + "epoch": 0.5, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "loss": 0.016268836334347725, + "step": 189 + }, + { + "epoch": 0.5026455026455027, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "loss": 0.02841845154762268, + "step": 190 + }, + { + "epoch": 0.5052910052910053, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "loss": 0.0306367389857769, + "step": 191 + }, + { + "epoch": 0.5079365079365079, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "loss": 0.031015485525131226, + "step": 192 + }, + { + "epoch": 0.5105820105820106, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "loss": 0.03242127224802971, + "step": 193 + }, + { + "epoch": 0.5132275132275133, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "loss": 0.03684879094362259, + "step": 194 + }, + { + "epoch": 0.5158730158730159, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "loss": 0.0260506309568882, + "step": 195 + }, + { + "epoch": 0.5185185185185185, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "loss": 0.02128693461418152, + "step": 196 + }, + { + "epoch": 0.5211640211640212, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "loss": 0.03452152758836746, + "step": 197 + }, + { + "epoch": 0.5238095238095238, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "loss": 0.028310813009738922, + "step": 198 + }, + { + "epoch": 0.5264550264550265, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "loss": 0.029575366526842117, + "step": 199 + }, + { + "epoch": 0.5291005291005291, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "loss": 0.029606211930513382, + "step": 200 + }, + { + "epoch": 0.5317460317460317, + "grad_norm": 0.09481994062662125, + "learning_rate": 0.00010470588235294118, + "loss": 0.02741779386997223, + "step": 201 + }, + { + "epoch": 0.5343915343915344, + "grad_norm": 0.06643011420965195, + "learning_rate": 0.00010411764705882355, + "loss": 0.02750249207019806, + "step": 202 + }, + { + "epoch": 0.5370370370370371, + "grad_norm": 0.08693543821573257, + "learning_rate": 0.0001035294117647059, + "loss": 0.025049429386854172, + "step": 203 + }, + { + "epoch": 0.5396825396825397, + "grad_norm": 0.08780419826507568, + "learning_rate": 0.00010294117647058823, + "loss": 0.0188161451369524, + "step": 204 + }, + { + "epoch": 0.5423280423280423, + "grad_norm": 0.08089763671159744, + "learning_rate": 0.00010235294117647058, + "loss": 0.025752779096364975, + "step": 205 + }, + { + "epoch": 0.544973544973545, + "grad_norm": 0.11511234939098358, + "learning_rate": 0.00010176470588235295, + "loss": 0.03086625598371029, + "step": 206 + }, + { + "epoch": 0.5476190476190477, + "grad_norm": 0.10907749086618423, + "learning_rate": 0.0001011764705882353, + "loss": 0.0273880697786808, + "step": 207 + }, + { + "epoch": 0.5502645502645502, + "grad_norm": 0.08107511699199677, + "learning_rate": 0.00010058823529411765, + "loss": 0.026370292529463768, + "step": 208 + }, + { + "epoch": 0.5529100529100529, + "grad_norm": 0.0737859457731247, + "learning_rate": 0.0001, + "loss": 0.025786038488149643, + "step": 209 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.09232968837022781, + "learning_rate": 9.941176470588236e-05, + "loss": 0.030016383156180382, + "step": 210 + }, + { + "epoch": 0.5582010582010583, + "grad_norm": 0.0948951318860054, + "learning_rate": 9.882352941176471e-05, + "loss": 0.021605785936117172, + "step": 211 + }, + { + "epoch": 0.5608465608465608, + "grad_norm": 0.09735886752605438, + "learning_rate": 9.823529411764706e-05, + "loss": 0.031091010197997093, + "step": 212 + }, + { + "epoch": 0.5634920634920635, + "grad_norm": 0.10056869685649872, + "learning_rate": 9.764705882352942e-05, + "loss": 0.030390700325369835, + "step": 213 + }, + { + "epoch": 0.5661375661375662, + "grad_norm": 0.0720759853720665, + "learning_rate": 9.705882352941177e-05, + "loss": 0.02216975763440132, + "step": 214 + }, + { + "epoch": 0.5687830687830688, + "grad_norm": 0.09141097962856293, + "learning_rate": 9.647058823529412e-05, + "loss": 0.02660333178937435, + "step": 215 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.09253139793872833, + "learning_rate": 9.588235294117648e-05, + "loss": 0.02590668946504593, + "step": 216 + }, + { + "epoch": 0.5740740740740741, + "grad_norm": 0.08869278430938721, + "learning_rate": 9.529411764705883e-05, + "loss": 0.02776462584733963, + "step": 217 + }, + { + "epoch": 0.5767195767195767, + "grad_norm": 0.10566668212413788, + "learning_rate": 9.470588235294118e-05, + "loss": 0.015304268337786198, + "step": 218 + }, + { + "epoch": 0.5793650793650794, + "grad_norm": 0.08862630277872086, + "learning_rate": 9.411764705882353e-05, + "loss": 0.027874145656824112, + "step": 219 + }, + { + "epoch": 0.582010582010582, + "grad_norm": 0.0958574190735817, + "learning_rate": 9.352941176470589e-05, + "loss": 0.030754802748560905, + "step": 220 + }, + { + "epoch": 0.5846560846560847, + "grad_norm": 0.09204437583684921, + "learning_rate": 9.294117647058824e-05, + "loss": 0.023360423743724823, + "step": 221 + }, + { + "epoch": 0.5873015873015873, + "grad_norm": 0.12147050350904465, + "learning_rate": 9.23529411764706e-05, + "loss": 0.031416505575180054, + "step": 222 + }, + { + "epoch": 0.58994708994709, + "grad_norm": 0.08076925575733185, + "learning_rate": 9.176470588235295e-05, + "loss": 0.023884786292910576, + "step": 223 + }, + { + "epoch": 0.5925925925925926, + "grad_norm": 0.08516595512628555, + "learning_rate": 9.11764705882353e-05, + "loss": 0.025108790025115013, + "step": 224 + }, + { + "epoch": 0.5952380952380952, + "grad_norm": 0.09453090280294418, + "learning_rate": 9.058823529411765e-05, + "loss": 0.0236780047416687, + "step": 225 + }, + { + "epoch": 0.5978835978835979, + "grad_norm": 0.08398544788360596, + "learning_rate": 9e-05, + "loss": 0.02253679558634758, + "step": 226 + }, + { + "epoch": 0.6005291005291006, + "grad_norm": 0.08214128762483597, + "learning_rate": 8.941176470588236e-05, + "loss": 0.027625620365142822, + "step": 227 + }, + { + "epoch": 0.6031746031746031, + "grad_norm": 0.07763852924108505, + "learning_rate": 8.882352941176471e-05, + "loss": 0.018679391592741013, + "step": 228 + }, + { + "epoch": 0.6058201058201058, + "grad_norm": 0.0663997232913971, + "learning_rate": 8.823529411764706e-05, + "loss": 0.018782157450914383, + "step": 229 + }, + { + "epoch": 0.6084656084656085, + "grad_norm": 0.07828967273235321, + "learning_rate": 8.764705882352942e-05, + "loss": 0.027178611606359482, + "step": 230 + }, + { + "epoch": 0.6111111111111112, + "grad_norm": 0.08604388684034348, + "learning_rate": 8.705882352941177e-05, + "loss": 0.023709267377853394, + "step": 231 + }, + { + "epoch": 0.6137566137566137, + "grad_norm": 0.07984922081232071, + "learning_rate": 8.647058823529412e-05, + "loss": 0.02602708712220192, + "step": 232 + }, + { + "epoch": 0.6164021164021164, + "grad_norm": 0.07321182638406754, + "learning_rate": 8.588235294117646e-05, + "loss": 0.02468765154480934, + "step": 233 + }, + { + "epoch": 0.6190476190476191, + "grad_norm": 0.07817960530519485, + "learning_rate": 8.529411764705883e-05, + "loss": 0.03028242662549019, + "step": 234 + }, + { + "epoch": 0.6216931216931217, + "grad_norm": 0.06251050531864166, + "learning_rate": 8.470588235294118e-05, + "loss": 0.02902349643409252, + "step": 235 + }, + { + "epoch": 0.6243386243386243, + "grad_norm": 0.09529170393943787, + "learning_rate": 8.411764705882354e-05, + "loss": 0.024306783452630043, + "step": 236 + }, + { + "epoch": 0.626984126984127, + "grad_norm": 0.1267942190170288, + "learning_rate": 8.352941176470589e-05, + "loss": 0.03521513566374779, + "step": 237 + }, + { + "epoch": 0.6296296296296297, + "grad_norm": 0.08621630817651749, + "learning_rate": 8.294117647058824e-05, + "loss": 0.020196501165628433, + "step": 238 + }, + { + "epoch": 0.6322751322751323, + "grad_norm": 0.07552770525217056, + "learning_rate": 8.23529411764706e-05, + "loss": 0.029385194182395935, + "step": 239 + }, + { + "epoch": 0.6349206349206349, + "grad_norm": 0.09521529078483582, + "learning_rate": 8.176470588235295e-05, + "loss": 0.01693333312869072, + "step": 240 + }, + { + "epoch": 0.6375661375661376, + "grad_norm": 0.09436187893152237, + "learning_rate": 8.11764705882353e-05, + "loss": 0.025097660720348358, + "step": 241 + }, + { + "epoch": 0.6402116402116402, + "grad_norm": 0.07002269476652145, + "learning_rate": 8.058823529411765e-05, + "loss": 0.027106281369924545, + "step": 242 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.08871318399906158, + "learning_rate": 8e-05, + "loss": 0.027904586866497993, + "step": 243 + }, + { + "epoch": 0.6455026455026455, + "grad_norm": 0.0833863765001297, + "learning_rate": 7.941176470588235e-05, + "loss": 0.030118469148874283, + "step": 244 + }, + { + "epoch": 0.6481481481481481, + "grad_norm": 0.0630115196108818, + "learning_rate": 7.882352941176471e-05, + "loss": 0.015584684908390045, + "step": 245 + }, + { + "epoch": 0.6507936507936508, + "grad_norm": 0.0754900649189949, + "learning_rate": 7.823529411764707e-05, + "loss": 0.024866245687007904, + "step": 246 + }, + { + "epoch": 0.6534391534391535, + "grad_norm": 0.09214677661657333, + "learning_rate": 7.764705882352942e-05, + "loss": 0.02521335333585739, + "step": 247 + }, + { + "epoch": 0.656084656084656, + "grad_norm": 0.07616355270147324, + "learning_rate": 7.705882352941177e-05, + "loss": 0.02567514404654503, + "step": 248 + }, + { + "epoch": 0.6587301587301587, + "grad_norm": 0.10812173038721085, + "learning_rate": 7.647058823529411e-05, + "loss": 0.03087168186903, + "step": 249 + }, + { + "epoch": 0.6613756613756614, + "grad_norm": 0.07225628942251205, + "learning_rate": 7.588235294117648e-05, + "loss": 0.02886301279067993, + "step": 250 + }, + { + "epoch": 0.6640211640211641, + "grad_norm": 0.08968020230531693, + "learning_rate": 7.529411764705883e-05, + "loss": 0.02838725596666336, + "step": 251 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.1066119521856308, + "learning_rate": 7.470588235294118e-05, + "loss": 0.0240425243973732, + "step": 252 + }, + { + "epoch": 0.6693121693121693, + "grad_norm": 0.07908853143453598, + "learning_rate": 7.411764705882354e-05, + "loss": 0.020799003541469574, + "step": 253 + }, + { + "epoch": 0.671957671957672, + "grad_norm": 0.08067328482866287, + "learning_rate": 7.352941176470589e-05, + "loss": 0.03212092071771622, + "step": 254 + }, + { + "epoch": 0.6746031746031746, + "grad_norm": 0.09752342849969864, + "learning_rate": 7.294117647058823e-05, + "loss": 0.02562413364648819, + "step": 255 + }, + { + "epoch": 0.6772486772486772, + "grad_norm": 0.07102340459823608, + "learning_rate": 7.23529411764706e-05, + "loss": 0.01694977842271328, + "step": 256 + }, + { + "epoch": 0.6798941798941799, + "grad_norm": 0.07671815156936646, + "learning_rate": 7.176470588235295e-05, + "loss": 0.02575928345322609, + "step": 257 + }, + { + "epoch": 0.6825396825396826, + "grad_norm": 0.1419815868139267, + "learning_rate": 7.11764705882353e-05, + "loss": 0.021748626604676247, + "step": 258 + }, + { + "epoch": 0.6851851851851852, + "grad_norm": 0.10793975740671158, + "learning_rate": 7.058823529411765e-05, + "loss": 0.02359670028090477, + "step": 259 + }, + { + "epoch": 0.6878306878306878, + "grad_norm": 0.10104779154062271, + "learning_rate": 7e-05, + "loss": 0.020240038633346558, + "step": 260 + }, + { + "epoch": 0.6904761904761905, + "grad_norm": 0.09232339262962341, + "learning_rate": 6.941176470588236e-05, + "loss": 0.03007177822291851, + "step": 261 + }, + { + "epoch": 0.6931216931216931, + "grad_norm": 0.060809917747974396, + "learning_rate": 6.882352941176471e-05, + "loss": 0.02441459335386753, + "step": 262 + }, + { + "epoch": 0.6957671957671958, + "grad_norm": 0.07218184322118759, + "learning_rate": 6.823529411764707e-05, + "loss": 0.02289595827460289, + "step": 263 + }, + { + "epoch": 0.6984126984126984, + "grad_norm": 0.09035782516002655, + "learning_rate": 6.764705882352942e-05, + "loss": 0.02958938293159008, + "step": 264 + }, + { + "epoch": 0.701058201058201, + "grad_norm": 0.08335528522729874, + "learning_rate": 6.705882352941176e-05, + "loss": 0.028876766562461853, + "step": 265 + }, + { + "epoch": 0.7037037037037037, + "grad_norm": 0.06112835556268692, + "learning_rate": 6.647058823529411e-05, + "loss": 0.022992007434368134, + "step": 266 + }, + { + "epoch": 0.7063492063492064, + "grad_norm": 0.09583422541618347, + "learning_rate": 6.588235294117648e-05, + "loss": 0.027839267626404762, + "step": 267 + }, + { + "epoch": 0.708994708994709, + "grad_norm": 0.10437622666358948, + "learning_rate": 6.529411764705883e-05, + "loss": 0.03310278058052063, + "step": 268 + }, + { + "epoch": 0.7116402116402116, + "grad_norm": 0.05979550629854202, + "learning_rate": 6.470588235294118e-05, + "loss": 0.02412830851972103, + "step": 269 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.057857904583215714, + "learning_rate": 6.411764705882354e-05, + "loss": 0.026769282296299934, + "step": 270 + }, + { + "epoch": 0.716931216931217, + "grad_norm": 0.0795726403594017, + "learning_rate": 6.352941176470588e-05, + "loss": 0.01822183094918728, + "step": 271 + }, + { + "epoch": 0.7195767195767195, + "grad_norm": 0.11597180366516113, + "learning_rate": 6.294117647058824e-05, + "loss": 0.03175610303878784, + "step": 272 + }, + { + "epoch": 0.7222222222222222, + "grad_norm": 0.12822823226451874, + "learning_rate": 6.23529411764706e-05, + "loss": 0.02406914159655571, + "step": 273 + }, + { + "epoch": 0.7248677248677249, + "grad_norm": 0.11681342869997025, + "learning_rate": 6.176470588235295e-05, + "loss": 0.017685284838080406, + "step": 274 + }, + { + "epoch": 0.7275132275132276, + "grad_norm": 0.06948421150445938, + "learning_rate": 6.11764705882353e-05, + "loss": 0.02279685251414776, + "step": 275 + }, + { + "epoch": 0.7301587301587301, + "grad_norm": 0.10276354104280472, + "learning_rate": 6.058823529411765e-05, + "loss": 0.032588277012109756, + "step": 276 + }, + { + "epoch": 0.7328042328042328, + "grad_norm": 0.10721025615930557, + "learning_rate": 6e-05, + "loss": 0.02961578778922558, + "step": 277 + }, + { + "epoch": 0.7354497354497355, + "grad_norm": 0.08410617709159851, + "learning_rate": 5.9411764705882355e-05, + "loss": 0.02747366949915886, + "step": 278 + }, + { + "epoch": 0.7380952380952381, + "grad_norm": 0.0806620791554451, + "learning_rate": 5.882352941176471e-05, + "loss": 0.02593173459172249, + "step": 279 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.06915932148694992, + "learning_rate": 5.823529411764707e-05, + "loss": 0.02764303609728813, + "step": 280 + }, + { + "epoch": 0.7433862433862434, + "grad_norm": 0.06709478050470352, + "learning_rate": 5.764705882352941e-05, + "loss": 0.024347776547074318, + "step": 281 + }, + { + "epoch": 0.746031746031746, + "grad_norm": 0.053211960941553116, + "learning_rate": 5.7058823529411766e-05, + "loss": 0.02141982689499855, + "step": 282 + }, + { + "epoch": 0.7486772486772487, + "grad_norm": 0.06790946424007416, + "learning_rate": 5.647058823529412e-05, + "loss": 0.02252194657921791, + "step": 283 + }, + { + "epoch": 0.7513227513227513, + "grad_norm": 0.08224959671497345, + "learning_rate": 5.588235294117647e-05, + "loss": 0.01945466734468937, + "step": 284 + }, + { + "epoch": 0.753968253968254, + "grad_norm": 0.09265672415494919, + "learning_rate": 5.529411764705883e-05, + "loss": 0.032275885343551636, + "step": 285 + }, + { + "epoch": 0.7566137566137566, + "grad_norm": 0.07285762578248978, + "learning_rate": 5.4705882352941185e-05, + "loss": 0.027079608291387558, + "step": 286 + }, + { + "epoch": 0.7592592592592593, + "grad_norm": 0.05742108076810837, + "learning_rate": 5.411764705882353e-05, + "loss": 0.02384945936501026, + "step": 287 + }, + { + "epoch": 0.7619047619047619, + "grad_norm": 0.11136175692081451, + "learning_rate": 5.3529411764705884e-05, + "loss": 0.02898704633116722, + "step": 288 + }, + { + "epoch": 0.7645502645502645, + "grad_norm": 0.09560064971446991, + "learning_rate": 5.294117647058824e-05, + "loss": 0.03049132414162159, + "step": 289 + }, + { + "epoch": 0.7671957671957672, + "grad_norm": 0.062173303216695786, + "learning_rate": 5.235294117647059e-05, + "loss": 0.024453597143292427, + "step": 290 + }, + { + "epoch": 0.7698412698412699, + "grad_norm": 0.0988180935382843, + "learning_rate": 5.176470588235295e-05, + "loss": 0.0318286158144474, + "step": 291 + }, + { + "epoch": 0.7724867724867724, + "grad_norm": 0.0626835897564888, + "learning_rate": 5.117647058823529e-05, + "loss": 0.02699001133441925, + "step": 292 + }, + { + "epoch": 0.7751322751322751, + "grad_norm": 0.07981280982494354, + "learning_rate": 5.058823529411765e-05, + "loss": 0.023896772414445877, + "step": 293 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.07893257588148117, + "learning_rate": 5e-05, + "loss": 0.024391846731305122, + "step": 294 + }, + { + "epoch": 0.7804232804232805, + "grad_norm": 0.06932593882083893, + "learning_rate": 4.9411764705882355e-05, + "loss": 0.025584066286683083, + "step": 295 + }, + { + "epoch": 0.783068783068783, + "grad_norm": 0.07785957306623459, + "learning_rate": 4.882352941176471e-05, + "loss": 0.0220668762922287, + "step": 296 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 0.06624335050582886, + "learning_rate": 4.823529411764706e-05, + "loss": 0.020017938688397408, + "step": 297 + }, + { + "epoch": 0.7883597883597884, + "grad_norm": 0.0832471251487732, + "learning_rate": 4.7647058823529414e-05, + "loss": 0.02506105974316597, + "step": 298 + }, + { + "epoch": 0.791005291005291, + "grad_norm": 0.06540657579898834, + "learning_rate": 4.705882352941177e-05, + "loss": 0.017597489058971405, + "step": 299 + }, + { + "epoch": 0.7936507936507936, + "grad_norm": 0.15526005625724792, + "learning_rate": 4.647058823529412e-05, + "loss": 0.0298212431371212, + "step": 300 + }, + { + "epoch": 0.7962962962962963, + "grad_norm": 0.10094427317380905, + "learning_rate": 4.588235294117647e-05, + "loss": 0.023575644940137863, + "step": 301 + }, + { + "epoch": 0.798941798941799, + "grad_norm": 0.08192069083452225, + "learning_rate": 4.5294117647058826e-05, + "loss": 0.02380991168320179, + "step": 302 + }, + { + "epoch": 0.8015873015873016, + "grad_norm": 0.0720907524228096, + "learning_rate": 4.470588235294118e-05, + "loss": 0.01674514263868332, + "step": 303 + }, + { + "epoch": 0.8042328042328042, + "grad_norm": 0.058165185153484344, + "learning_rate": 4.411764705882353e-05, + "loss": 0.018333733081817627, + "step": 304 + }, + { + "epoch": 0.8068783068783069, + "grad_norm": 0.09807229042053223, + "learning_rate": 4.3529411764705885e-05, + "loss": 0.026520205661654472, + "step": 305 + }, + { + "epoch": 0.8095238095238095, + "grad_norm": 0.08209870010614395, + "learning_rate": 4.294117647058823e-05, + "loss": 0.028179757297039032, + "step": 306 + }, + { + "epoch": 0.8121693121693122, + "grad_norm": 0.08082698285579681, + "learning_rate": 4.235294117647059e-05, + "loss": 0.020067555829882622, + "step": 307 + }, + { + "epoch": 0.8148148148148148, + "grad_norm": 0.0704454705119133, + "learning_rate": 4.1764705882352944e-05, + "loss": 0.02571108378469944, + "step": 308 + }, + { + "epoch": 0.8174603174603174, + "grad_norm": 0.12649419903755188, + "learning_rate": 4.11764705882353e-05, + "loss": 0.030464062467217445, + "step": 309 + }, + { + "epoch": 0.8201058201058201, + "grad_norm": 0.0701553225517273, + "learning_rate": 4.058823529411765e-05, + "loss": 0.029247839003801346, + "step": 310 + }, + { + "epoch": 0.8227513227513228, + "grad_norm": 0.061975978314876556, + "learning_rate": 4e-05, + "loss": 0.019865376874804497, + "step": 311 + }, + { + "epoch": 0.8253968253968254, + "grad_norm": 0.07122108340263367, + "learning_rate": 3.9411764705882356e-05, + "loss": 0.025799460709095, + "step": 312 + }, + { + "epoch": 0.828042328042328, + "grad_norm": 0.0794585570693016, + "learning_rate": 3.882352941176471e-05, + "loss": 0.02584882080554962, + "step": 313 + }, + { + "epoch": 0.8306878306878307, + "grad_norm": 0.07829529792070389, + "learning_rate": 3.8235294117647055e-05, + "loss": 0.016808034852147102, + "step": 314 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 0.10015936195850372, + "learning_rate": 3.7647058823529415e-05, + "loss": 0.029843248426914215, + "step": 315 + }, + { + "epoch": 0.8359788359788359, + "grad_norm": 0.08752724528312683, + "learning_rate": 3.705882352941177e-05, + "loss": 0.0207672156393528, + "step": 316 + }, + { + "epoch": 0.8386243386243386, + "grad_norm": 0.07568460702896118, + "learning_rate": 3.6470588235294114e-05, + "loss": 0.025986317545175552, + "step": 317 + }, + { + "epoch": 0.8412698412698413, + "grad_norm": 0.10557642579078674, + "learning_rate": 3.5882352941176474e-05, + "loss": 0.03166591376066208, + "step": 318 + }, + { + "epoch": 0.843915343915344, + "grad_norm": 0.0882193073630333, + "learning_rate": 3.529411764705883e-05, + "loss": 0.027180485427379608, + "step": 319 + }, + { + "epoch": 0.8465608465608465, + "grad_norm": 0.10279812663793564, + "learning_rate": 3.470588235294118e-05, + "loss": 0.025324862450361252, + "step": 320 + }, + { + "epoch": 0.8492063492063492, + "grad_norm": 0.08359183371067047, + "learning_rate": 3.411764705882353e-05, + "loss": 0.031235653907060623, + "step": 321 + }, + { + "epoch": 0.8518518518518519, + "grad_norm": 0.06786882132291794, + "learning_rate": 3.352941176470588e-05, + "loss": 0.028402645140886307, + "step": 322 + }, + { + "epoch": 0.8544973544973545, + "grad_norm": 0.09749054163694382, + "learning_rate": 3.294117647058824e-05, + "loss": 0.024368081241846085, + "step": 323 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 0.06912931054830551, + "learning_rate": 3.235294117647059e-05, + "loss": 0.029769334942102432, + "step": 324 + }, + { + "epoch": 0.8597883597883598, + "grad_norm": 0.07546117901802063, + "learning_rate": 3.176470588235294e-05, + "loss": 0.027555279433727264, + "step": 325 + }, + { + "epoch": 0.8624338624338624, + "grad_norm": 0.08951126784086227, + "learning_rate": 3.11764705882353e-05, + "loss": 0.03135411813855171, + "step": 326 + }, + { + "epoch": 0.8650793650793651, + "grad_norm": 0.08512236922979355, + "learning_rate": 3.058823529411765e-05, + "loss": 0.018115023151040077, + "step": 327 + }, + { + "epoch": 0.8677248677248677, + "grad_norm": 0.08400000631809235, + "learning_rate": 3e-05, + "loss": 0.024688314646482468, + "step": 328 + }, + { + "epoch": 0.8703703703703703, + "grad_norm": 0.06805701553821564, + "learning_rate": 2.9411764705882354e-05, + "loss": 0.025533631443977356, + "step": 329 + }, + { + "epoch": 0.873015873015873, + "grad_norm": 0.08600405603647232, + "learning_rate": 2.8823529411764703e-05, + "loss": 0.02600039541721344, + "step": 330 + }, + { + "epoch": 0.8756613756613757, + "grad_norm": 0.07160481810569763, + "learning_rate": 2.823529411764706e-05, + "loss": 0.0179967749863863, + "step": 331 + }, + { + "epoch": 0.8783068783068783, + "grad_norm": 0.07811455428600311, + "learning_rate": 2.7647058823529416e-05, + "loss": 0.025588110089302063, + "step": 332 + }, + { + "epoch": 0.8809523809523809, + "grad_norm": 0.07041554898023605, + "learning_rate": 2.7058823529411766e-05, + "loss": 0.024966120719909668, + "step": 333 + }, + { + "epoch": 0.8835978835978836, + "grad_norm": 0.07744963467121124, + "learning_rate": 2.647058823529412e-05, + "loss": 0.02608634904026985, + "step": 334 + }, + { + "epoch": 0.8862433862433863, + "grad_norm": 0.07343604415655136, + "learning_rate": 2.5882352941176475e-05, + "loss": 0.024391014128923416, + "step": 335 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 0.10205741226673126, + "learning_rate": 2.5294117647058825e-05, + "loss": 0.015595385804772377, + "step": 336 + }, + { + "epoch": 0.8915343915343915, + "grad_norm": 0.08257130533456802, + "learning_rate": 2.4705882352941178e-05, + "loss": 0.025536613538861275, + "step": 337 + }, + { + "epoch": 0.8941798941798942, + "grad_norm": 0.1315038800239563, + "learning_rate": 2.411764705882353e-05, + "loss": 0.031951554119586945, + "step": 338 + }, + { + "epoch": 0.8968253968253969, + "grad_norm": 0.08411096036434174, + "learning_rate": 2.3529411764705884e-05, + "loss": 0.023610807955265045, + "step": 339 + }, + { + "epoch": 0.8994708994708994, + "grad_norm": 0.07679664343595505, + "learning_rate": 2.2941176470588237e-05, + "loss": 0.030541151762008667, + "step": 340 + }, + { + "epoch": 0.9021164021164021, + "grad_norm": 0.07304323464632034, + "learning_rate": 2.235294117647059e-05, + "loss": 0.02696535736322403, + "step": 341 + }, + { + "epoch": 0.9047619047619048, + "grad_norm": 0.061864130198955536, + "learning_rate": 2.1764705882352943e-05, + "loss": 0.02784024551510811, + "step": 342 + }, + { + "epoch": 0.9074074074074074, + "grad_norm": 0.06673755496740341, + "learning_rate": 2.1176470588235296e-05, + "loss": 0.025248851627111435, + "step": 343 + }, + { + "epoch": 0.91005291005291, + "grad_norm": 0.07668192684650421, + "learning_rate": 2.058823529411765e-05, + "loss": 0.029280394315719604, + "step": 344 + }, + { + "epoch": 0.9126984126984127, + "grad_norm": 0.07531134784221649, + "learning_rate": 2e-05, + "loss": 0.02605779841542244, + "step": 345 + }, + { + "epoch": 0.9153439153439153, + "grad_norm": 0.08565571904182434, + "learning_rate": 1.9411764705882355e-05, + "loss": 0.028157757595181465, + "step": 346 + }, + { + "epoch": 0.917989417989418, + "grad_norm": 0.07180029898881912, + "learning_rate": 1.8823529411764708e-05, + "loss": 0.025131918489933014, + "step": 347 + }, + { + "epoch": 0.9206349206349206, + "grad_norm": 0.07056324183940887, + "learning_rate": 1.8235294117647057e-05, + "loss": 0.02796267159283161, + "step": 348 + }, + { + "epoch": 0.9232804232804233, + "grad_norm": 0.08292558044195175, + "learning_rate": 1.7647058823529414e-05, + "loss": 0.025395592674613, + "step": 349 + }, + { + "epoch": 0.9259259259259259, + "grad_norm": 0.07555428147315979, + "learning_rate": 1.7058823529411767e-05, + "loss": 0.028561469167470932, + "step": 350 + }, + { + "epoch": 0.9285714285714286, + "grad_norm": 0.06799963861703873, + "learning_rate": 1.647058823529412e-05, + "loss": 0.020762892439961433, + "step": 351 + }, + { + "epoch": 0.9312169312169312, + "grad_norm": 0.09109848737716675, + "learning_rate": 1.588235294117647e-05, + "loss": 0.014401258900761604, + "step": 352 + }, + { + "epoch": 0.9338624338624338, + "grad_norm": 0.07757920771837234, + "learning_rate": 1.5294117647058826e-05, + "loss": 0.02667010948061943, + "step": 353 + }, + { + "epoch": 0.9365079365079365, + "grad_norm": 0.07955507934093475, + "learning_rate": 1.4705882352941177e-05, + "loss": 0.023868650197982788, + "step": 354 + }, + { + "epoch": 0.9391534391534392, + "grad_norm": 0.07310300320386887, + "learning_rate": 1.411764705882353e-05, + "loss": 0.017540596425533295, + "step": 355 + }, + { + "epoch": 0.9417989417989417, + "grad_norm": 0.06979277729988098, + "learning_rate": 1.3529411764705883e-05, + "loss": 0.026370886713266373, + "step": 356 + }, + { + "epoch": 0.9444444444444444, + "grad_norm": 0.07074704021215439, + "learning_rate": 1.2941176470588238e-05, + "loss": 0.018387794494628906, + "step": 357 + }, + { + "epoch": 0.9470899470899471, + "grad_norm": 0.07400532811880112, + "learning_rate": 1.2352941176470589e-05, + "loss": 0.022234005853533745, + "step": 358 + }, + { + "epoch": 0.9497354497354498, + "grad_norm": 0.06865154951810837, + "learning_rate": 1.1764705882352942e-05, + "loss": 0.022929485887289047, + "step": 359 + }, + { + "epoch": 0.9523809523809523, + "grad_norm": 0.07323960214853287, + "learning_rate": 1.1176470588235295e-05, + "loss": 0.014135655015707016, + "step": 360 + }, + { + "epoch": 0.955026455026455, + "grad_norm": 0.07920295000076294, + "learning_rate": 1.0588235294117648e-05, + "loss": 0.022620154544711113, + "step": 361 + }, + { + "epoch": 0.9576719576719577, + "grad_norm": 0.07833685725927353, + "learning_rate": 1e-05, + "loss": 0.02163829654455185, + "step": 362 + }, + { + "epoch": 0.9603174603174603, + "grad_norm": 0.07127346098423004, + "learning_rate": 9.411764705882354e-06, + "loss": 0.024631310254335403, + "step": 363 + }, + { + "epoch": 0.9629629629629629, + "grad_norm": 0.08091171830892563, + "learning_rate": 8.823529411764707e-06, + "loss": 0.02476324699819088, + "step": 364 + }, + { + "epoch": 0.9656084656084656, + "grad_norm": 0.07320816069841385, + "learning_rate": 8.23529411764706e-06, + "loss": 0.028194960206747055, + "step": 365 + }, + { + "epoch": 0.9682539682539683, + "grad_norm": 0.05777011066675186, + "learning_rate": 7.647058823529413e-06, + "loss": 0.021045658737421036, + "step": 366 + }, + { + "epoch": 0.9708994708994709, + "grad_norm": 0.05877400189638138, + "learning_rate": 7.058823529411765e-06, + "loss": 0.01954471692442894, + "step": 367 + }, + { + "epoch": 0.9735449735449735, + "grad_norm": 0.08140099048614502, + "learning_rate": 6.470588235294119e-06, + "loss": 0.022302869707345963, + "step": 368 + }, + { + "epoch": 0.9761904761904762, + "grad_norm": 0.07870705425739288, + "learning_rate": 5.882352941176471e-06, + "loss": 0.028763171285390854, + "step": 369 + }, + { + "epoch": 0.9788359788359788, + "grad_norm": 0.07137063145637512, + "learning_rate": 5.294117647058824e-06, + "loss": 0.02230384200811386, + "step": 370 + }, + { + "epoch": 0.9814814814814815, + "grad_norm": 0.08352145552635193, + "learning_rate": 4.705882352941177e-06, + "loss": 0.029754120856523514, + "step": 371 + }, + { + "epoch": 0.9841269841269841, + "grad_norm": 0.11225514113903046, + "learning_rate": 4.11764705882353e-06, + "loss": 0.02422209642827511, + "step": 372 + }, + { + "epoch": 0.9867724867724867, + "grad_norm": 0.06159619614481926, + "learning_rate": 3.5294117647058825e-06, + "loss": 0.02646939642727375, + "step": 373 + }, + { + "epoch": 0.9894179894179894, + "grad_norm": 0.07783936709165573, + "learning_rate": 2.9411764705882355e-06, + "loss": 0.025930095463991165, + "step": 374 + }, + { + "epoch": 0.9920634920634921, + "grad_norm": 0.07969409227371216, + "learning_rate": 2.3529411764705885e-06, + "loss": 0.02609175071120262, + "step": 375 + }, + { + "epoch": 0.9947089947089947, + "grad_norm": 0.07719960063695908, + "learning_rate": 1.7647058823529412e-06, + "loss": 0.029602840542793274, + "step": 376 + }, + { + "epoch": 0.9973544973544973, + "grad_norm": 0.08469251543283463, + "learning_rate": 1.1764705882352942e-06, + "loss": 0.02769250050187111, + "step": 377 + }, + { + "epoch": 1.0, + "grad_norm": 0.08339664340019226, + "learning_rate": 5.882352941176471e-07, + "loss": 0.01469414122402668, + "step": 378 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.466247702455808e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-378/training_args.bin b/sft_worldsplit_1_5b/checkpoint-378/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-378/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-40/README.md b/sft_worldsplit_1_5b/checkpoint-40/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-40/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-40/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-40/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-40/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..231ad96258419d774a3db28f0fb8479c7035dd69 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301cb158ca4f0ecdc713856787bcb0c4cee71cdc76ba710ae8167b1213405527 +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-40/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-40/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-40/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-40/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7723d77e63b2f1f25c0ca713ab6979c43808f7d --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1068ca0119d1b3c8d2662a02c5be6e4da05764a5fb4c62f6cd7ea3cffbac113 +size 37969669 diff --git a/sft_worldsplit_1_5b/checkpoint-40/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-40/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-40/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-40/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..57335e7958eb5eaf73d4ecde1521be6da483bb69 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196266f899abbd6892e59c0e2dc1b143e77cc77911bc885b2980da7bb3748221 +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-40/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-40/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-40/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-40/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-40/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-40/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b0a20110fe33d58279b94d8086b994426874584d --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/trainer_state.json @@ -0,0 +1,314 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.10582010582010581, + "eval_steps": 500, + "global_step": 40, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1540550512665600.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-40/training_args.bin b/sft_worldsplit_1_5b/checkpoint-40/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-40/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/checkpoint-80/README.md b/sft_worldsplit_1_5b/checkpoint-80/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-80/adapter_config.json b/sft_worldsplit_1_5b/checkpoint-80/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/checkpoint-80/adapter_model.safetensors b/sft_worldsplit_1_5b/checkpoint-80/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ff0135cb71b078bcab2c18cb2ae0bf9eb2929c2 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd7a3c546ba99647a643c8f1bb4b076d6339e4f5862646fd452b0e3628987ce +size 73911112 diff --git a/sft_worldsplit_1_5b/checkpoint-80/chat_template.jinja b/sft_worldsplit_1_5b/checkpoint-80/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/checkpoint-80/optimizer.pt b/sft_worldsplit_1_5b/checkpoint-80/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c019ce30840d1915d3206d29fb69e2f4a9bd9fd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6658a7be8c5bc547d2d717fc24e0375fe808e1c87e76ddb0785296cbcadb69ac +size 37969669 diff --git a/sft_worldsplit_1_5b/checkpoint-80/rng_state.pth b/sft_worldsplit_1_5b/checkpoint-80/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a8f17addf8aaee350625e9847751582bc9f86dd --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4 +size 14645 diff --git a/sft_worldsplit_1_5b/checkpoint-80/scheduler.pt b/sft_worldsplit_1_5b/checkpoint-80/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..63b60667de672ca024353e3576335a9fc3a486d7 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e239a212ec5062a827251271fcd08b5b0f1e909ef8edb95cd21bfb3c7afc91 +size 1465 diff --git a/sft_worldsplit_1_5b/checkpoint-80/tokenizer.json b/sft_worldsplit_1_5b/checkpoint-80/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/checkpoint-80/tokenizer_config.json b/sft_worldsplit_1_5b/checkpoint-80/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d3dac539765625f7e736bb2cdacac98bfa616b1f --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/checkpoint-80/trainer_state.json b/sft_worldsplit_1_5b/checkpoint-80/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d0b2134187a0cb1d4ec2a392283502b2fa4d6215 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/trainer_state.json @@ -0,0 +1,594 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.21164021164021163, + "eval_steps": 500, + "global_step": 80, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0026455026455026454, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "loss": 2.1897194385528564, + "step": 1 + }, + { + "epoch": 0.005291005291005291, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "loss": 2.023362159729004, + "step": 2 + }, + { + "epoch": 0.007936507936507936, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "loss": 2.1094398498535156, + "step": 3 + }, + { + "epoch": 0.010582010582010581, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "loss": 2.0047714710235596, + "step": 4 + }, + { + "epoch": 0.013227513227513227, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "loss": 2.121164560317993, + "step": 5 + }, + { + "epoch": 0.015873015873015872, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "loss": 2.1543028354644775, + "step": 6 + }, + { + "epoch": 0.018518518518518517, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "loss": 1.98488187789917, + "step": 7 + }, + { + "epoch": 0.021164021164021163, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "loss": 1.990682601928711, + "step": 8 + }, + { + "epoch": 0.023809523809523808, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "loss": 2.113189697265625, + "step": 9 + }, + { + "epoch": 0.026455026455026454, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "loss": 1.9175727367401123, + "step": 10 + }, + { + "epoch": 0.0291005291005291, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "loss": 2.070034980773926, + "step": 11 + }, + { + "epoch": 0.031746031746031744, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "loss": 1.849581003189087, + "step": 12 + }, + { + "epoch": 0.03439153439153439, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "loss": 1.6639738082885742, + "step": 13 + }, + { + "epoch": 0.037037037037037035, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "loss": 1.7406408786773682, + "step": 14 + }, + { + "epoch": 0.03968253968253968, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "loss": 1.6576179265975952, + "step": 15 + }, + { + "epoch": 0.042328042328042326, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "loss": 1.761307954788208, + "step": 16 + }, + { + "epoch": 0.04497354497354497, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "loss": 1.728525161743164, + "step": 17 + }, + { + "epoch": 0.047619047619047616, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "loss": 1.6631115674972534, + "step": 18 + }, + { + "epoch": 0.05026455026455026, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "loss": 1.566865086555481, + "step": 19 + }, + { + "epoch": 0.05291005291005291, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "loss": 1.386806607246399, + "step": 20 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "loss": 1.3766692876815796, + "step": 21 + }, + { + "epoch": 0.0582010582010582, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "loss": 1.2881217002868652, + "step": 22 + }, + { + "epoch": 0.06084656084656084, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "loss": 1.3662283420562744, + "step": 23 + }, + { + "epoch": 0.06349206349206349, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "loss": 1.1722878217697144, + "step": 24 + }, + { + "epoch": 0.06613756613756613, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "loss": 1.0199048519134521, + "step": 25 + }, + { + "epoch": 0.06878306878306878, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "loss": 0.8610183000564575, + "step": 26 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "loss": 0.8983635306358337, + "step": 27 + }, + { + "epoch": 0.07407407407407407, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "loss": 0.883075475692749, + "step": 28 + }, + { + "epoch": 0.07671957671957672, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "loss": 0.6960610151290894, + "step": 29 + }, + { + "epoch": 0.07936507936507936, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "loss": 0.4915878176689148, + "step": 30 + }, + { + "epoch": 0.082010582010582, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "loss": 0.48479601740837097, + "step": 31 + }, + { + "epoch": 0.08465608465608465, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "loss": 0.45518991351127625, + "step": 32 + }, + { + "epoch": 0.0873015873015873, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "loss": 0.5127372145652771, + "step": 33 + }, + { + "epoch": 0.08994708994708994, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "loss": 0.24351520836353302, + "step": 34 + }, + { + "epoch": 0.09259259259259259, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "loss": 0.43377262353897095, + "step": 35 + }, + { + "epoch": 0.09523809523809523, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "loss": 0.419627845287323, + "step": 36 + }, + { + "epoch": 0.09788359788359788, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "loss": 0.28788167238235474, + "step": 37 + }, + { + "epoch": 0.10052910052910052, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "loss": 0.345514714717865, + "step": 38 + }, + { + "epoch": 0.10317460317460317, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "loss": 0.2702908217906952, + "step": 39 + }, + { + "epoch": 0.10582010582010581, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "loss": 0.138988196849823, + "step": 40 + }, + { + "epoch": 0.10846560846560846, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "loss": 0.2215503752231598, + "step": 41 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "loss": 0.1795579493045807, + "step": 42 + }, + { + "epoch": 0.11375661375661375, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "loss": 0.2540356516838074, + "step": 43 + }, + { + "epoch": 0.1164021164021164, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "loss": 0.1952768862247467, + "step": 44 + }, + { + "epoch": 0.11904761904761904, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "loss": 0.09109751880168915, + "step": 45 + }, + { + "epoch": 0.12169312169312169, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "loss": 0.05925009772181511, + "step": 46 + }, + { + "epoch": 0.12433862433862433, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "loss": 0.20134183764457703, + "step": 47 + }, + { + "epoch": 0.12698412698412698, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "loss": 0.06878196448087692, + "step": 48 + }, + { + "epoch": 0.12962962962962962, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "loss": 0.08819292485713959, + "step": 49 + }, + { + "epoch": 0.13227513227513227, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "loss": 0.06745278090238571, + "step": 50 + }, + { + "epoch": 0.1349206349206349, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "loss": 0.08112215995788574, + "step": 51 + }, + { + "epoch": 0.13756613756613756, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "loss": 0.05829603970050812, + "step": 52 + }, + { + "epoch": 0.1402116402116402, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "loss": 0.06131816282868385, + "step": 53 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "loss": 0.06756111979484558, + "step": 54 + }, + { + "epoch": 0.1455026455026455, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "loss": 0.06646526604890823, + "step": 55 + }, + { + "epoch": 0.14814814814814814, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "loss": 0.0654621571302414, + "step": 56 + }, + { + "epoch": 0.15079365079365079, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "loss": 0.04999839514493942, + "step": 57 + }, + { + "epoch": 0.15343915343915343, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "loss": 0.06149204075336456, + "step": 58 + }, + { + "epoch": 0.15608465608465608, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "loss": 0.05500664934515953, + "step": 59 + }, + { + "epoch": 0.15873015873015872, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "loss": 0.06044406071305275, + "step": 60 + }, + { + "epoch": 0.16137566137566137, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "loss": 0.09898850321769714, + "step": 61 + }, + { + "epoch": 0.164021164021164, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "loss": 0.03585953637957573, + "step": 62 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "loss": 0.04662243276834488, + "step": 63 + }, + { + "epoch": 0.1693121693121693, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "loss": 0.03733272850513458, + "step": 64 + }, + { + "epoch": 0.17195767195767195, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "loss": 0.053247880190610886, + "step": 65 + }, + { + "epoch": 0.1746031746031746, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "loss": 0.032761458307504654, + "step": 66 + }, + { + "epoch": 0.17724867724867724, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "loss": 0.03275494650006294, + "step": 67 + }, + { + "epoch": 0.17989417989417988, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "loss": 0.048416756093502045, + "step": 68 + }, + { + "epoch": 0.18253968253968253, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "loss": 0.05309575796127319, + "step": 69 + }, + { + "epoch": 0.18518518518518517, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "loss": 0.034724876284599304, + "step": 70 + }, + { + "epoch": 0.18783068783068782, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "loss": 0.03913448005914688, + "step": 71 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "loss": 0.039260510355234146, + "step": 72 + }, + { + "epoch": 0.1931216931216931, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "loss": 0.04198860377073288, + "step": 73 + }, + { + "epoch": 0.19576719576719576, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "loss": 0.04677252471446991, + "step": 74 + }, + { + "epoch": 0.1984126984126984, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "loss": 0.028377845883369446, + "step": 75 + }, + { + "epoch": 0.20105820105820105, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "loss": 0.03226421773433685, + "step": 76 + }, + { + "epoch": 0.2037037037037037, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "loss": 0.029218731448054314, + "step": 77 + }, + { + "epoch": 0.20634920634920634, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "loss": 0.046170152723789215, + "step": 78 + }, + { + "epoch": 0.20899470899470898, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "loss": 0.02912411093711853, + "step": 79 + }, + { + "epoch": 0.21164021164021163, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "loss": 0.030748452991247177, + "step": 80 + } + ], + "logging_steps": 1, + "max_steps": 378, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 40, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3095786982346752.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/sft_worldsplit_1_5b/checkpoint-80/training_args.bin b/sft_worldsplit_1_5b/checkpoint-80/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..690efd63c6277167a89f6b9405cd4edc58db6927 --- /dev/null +++ b/sft_worldsplit_1_5b/checkpoint-80/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8592cab6c58b1adfee898260ecea909e7edb820af276385de44a0704c7b160 +size 5713 diff --git a/sft_worldsplit_1_5b/final/README.md b/sft_worldsplit_1_5b/final/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a4c765daa313599df95244ce58b96c8b42a30694 --- /dev/null +++ b/sft_worldsplit_1_5b/final/README.md @@ -0,0 +1,210 @@ +--- +base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit +- lora +- sft +- transformers +- trl +- unsloth +--- + +# 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 0.19.1 \ No newline at end of file diff --git a/sft_worldsplit_1_5b/final/adapter_config.json b/sft_worldsplit_1_5b/final/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d086915708aef917d92a660d1468ac3d106000c8 --- /dev/null +++ b/sft_worldsplit_1_5b/final/adapter_config.json @@ -0,0 +1,52 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": { + "base_model_class": "Qwen2ForCausalLM", + "parent_library": "transformers.models.qwen2.modeling_qwen2", + "unsloth_fixed": true + }, + "base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "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": 32, + "lora_bias": false, + "lora_dropout": 0.0, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "up_proj", + "o_proj", + "q_proj", + "v_proj", + "down_proj", + "gate_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/sft_worldsplit_1_5b/final/adapter_model.safetensors b/sft_worldsplit_1_5b/final/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72db56363eb36ce9dbcb28c8adc455eb44ba2c5d --- /dev/null +++ b/sft_worldsplit_1_5b/final/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a51a8e5505d70bde4e3c3878cd165c69001836a56f37a89ffff8d66ac02408 +size 73911112 diff --git a/sft_worldsplit_1_5b/final/chat_template.jinja b/sft_worldsplit_1_5b/final/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e --- /dev/null +++ b/sft_worldsplit_1_5b/final/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/sft_worldsplit_1_5b/final/tokenizer.json b/sft_worldsplit_1_5b/final/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924 --- /dev/null +++ b/sft_worldsplit_1_5b/final/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/sft_worldsplit_1_5b/final/tokenizer_config.json b/sft_worldsplit_1_5b/final/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c0a143788515485bf14c4f1cb8cca0378ec5e78a --- /dev/null +++ b/sft_worldsplit_1_5b/final/tokenizer_config.json @@ -0,0 +1,201 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + } +} diff --git a/sft_worldsplit_1_5b/loss_curve.png b/sft_worldsplit_1_5b/loss_curve.png new file mode 100644 index 0000000000000000000000000000000000000000..052dc8b80c9b75c8c435a091fb93d4c347d1adfc Binary files /dev/null and b/sft_worldsplit_1_5b/loss_curve.png differ diff --git a/sft_worldsplit_1_5b/reward_curve.png b/sft_worldsplit_1_5b/reward_curve.png new file mode 100644 index 0000000000000000000000000000000000000000..57df5d0ce79d254da97f8f8030e20228d3e4e51a Binary files /dev/null and b/sft_worldsplit_1_5b/reward_curve.png differ diff --git a/sft_worldsplit_1_5b/sft_metrics.json b/sft_worldsplit_1_5b/sft_metrics.json new file mode 100644 index 0000000000000000000000000000000000000000..73fa12cbc648e952fda8e89ceed554813580f65a --- /dev/null +++ b/sft_worldsplit_1_5b/sft_metrics.json @@ -0,0 +1,3493 @@ +{ + "trainer": "sft", + "model": "unsloth/Qwen2.5-1.5B-Instruct", + "dataset": "/workspace/adaptshield/data/adaptshield_sft_worldsplit.jsonl", + "rows": 3024, + "epochs": 1.0, + "learning_rate": 0.0002, + "evaluation_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.96, + "steps": 16.0, + "tool_calls": 54.5, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_evaluation_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.93, + "steps": 16.0, + "tool_calls": 54.5, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "eval", + "world_family": "auto" + } + ], + "heldout_seed": 314, + "train_world_split": "train", + "heldout_world_split": "eval", + "reward_curve_rows": [ + { + "checkpoint": "checkpoint-40", + "in_distribution_score": 0.78, + "heldout_score": 0.837, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.78, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.83, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.73, + "steps": 16.0, + "tool_calls": 54.5, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.87, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.97, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.67, + "steps": 16.0, + "tool_calls": 54.5, + "eval_episodes": 2, + "seed_start": 314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-80", + "in_distribution_score": 0.952, + "heldout_score": 0.898, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 1314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.965, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 1314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.9, + "steps": 16.0, + "tool_calls": 51.5, + "eval_episodes": 2, + "seed_start": 1314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 1314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.88, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 1314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.825, + "steps": 16.0, + "tool_calls": 51.5, + "eval_episodes": 2, + "seed_start": 1314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-120", + "in_distribution_score": 0.913, + "heldout_score": 0.877, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 2314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.95, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 2314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.8, + "steps": 16.0, + "tool_calls": 47.0, + "eval_episodes": 2, + "seed_start": 2314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 2314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.885, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 2314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.755, + "steps": 16.0, + "tool_calls": 47.0, + "eval_episodes": 2, + "seed_start": 2314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-160", + "in_distribution_score": 0.823, + "heldout_score": 0.823, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 3314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.68, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 3314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.8, + "steps": 16.0, + "tool_calls": 48.5, + "eval_episodes": 2, + "seed_start": 3314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 3314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.68, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 3314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.8, + "steps": 16.0, + "tool_calls": 48.5, + "eval_episodes": 2, + "seed_start": 3314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-200", + "in_distribution_score": 0.843, + "heldout_score": 0.875, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 4314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 4314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.715, + "steps": 16.0, + "tool_calls": 54.5, + "eval_episodes": 2, + "seed_start": 4314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 4314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 4314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.81, + "steps": 16.0, + "tool_calls": 54.5, + "eval_episodes": 2, + "seed_start": 4314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-240", + "in_distribution_score": 0.863, + "heldout_score": 0.915, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 5314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.815, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 5314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.785, + "steps": 16.0, + "tool_calls": 48.5, + "eval_episodes": 2, + "seed_start": 5314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 5314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.935, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 5314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.82, + "steps": 16.0, + "tool_calls": 48.5, + "eval_episodes": 2, + "seed_start": 5314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-280", + "in_distribution_score": 0.895, + "heldout_score": 0.947, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 6314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.815, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 6314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.88, + "steps": 16.0, + "tool_calls": 50.0, + "eval_episodes": 2, + "seed_start": 6314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 6314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.97, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 6314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.88, + "steps": 16.0, + "tool_calls": 50.0, + "eval_episodes": 2, + "seed_start": 6314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-320", + "in_distribution_score": 0.898, + "heldout_score": 0.908, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 7314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 7314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.88, + "steps": 16.0, + "tool_calls": 53.0, + "eval_episodes": 2, + "seed_start": 7314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 7314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 7314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.91, + "steps": 16.0, + "tool_calls": 53.0, + "eval_episodes": 2, + "seed_start": 7314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-360", + "in_distribution_score": 0.942, + "heldout_score": 0.918, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 8314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.97, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 8314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.865, + "steps": 16.0, + "tool_calls": 48.5, + "eval_episodes": 2, + "seed_start": 8314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 8314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.97, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 8314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.795, + "steps": 16.0, + "tool_calls": 48.5, + "eval_episodes": 2, + "seed_start": 8314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "checkpoint-378", + "in_distribution_score": 0.892, + "heldout_score": 0.89, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 9314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 9314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.86, + "steps": 16.0, + "tool_calls": 53.0, + "eval_episodes": 2, + "seed_start": 9314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 9314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.825, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 9314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.855, + "steps": 16.0, + "tool_calls": 53.0, + "eval_episodes": 2, + "seed_start": 9314, + "world_split": "eval", + "world_family": "auto" + } + ] + }, + { + "checkpoint": "final", + "in_distribution_score": 0.94, + "heldout_score": 0.952, + "in_distribution_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 10314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.97, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 10314, + "world_split": "train", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.86, + "steps": 16.0, + "tool_calls": 51.5, + "eval_episodes": 2, + "seed_start": 10314, + "world_split": "train", + "world_family": "auto" + } + ], + "heldout_rows": [ + { + "task": "direct-triage", + "score": 0.99, + "steps": 10.0, + "tool_calls": 5.0, + "eval_episodes": 2, + "seed_start": 10314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "dual-pivot", + "score": 0.97, + "steps": 12.0, + "tool_calls": 10.0, + "eval_episodes": 2, + "seed_start": 10314, + "world_split": "eval", + "world_family": "auto" + }, + { + "task": "polymorphic-zero-day", + "score": 0.895, + "steps": 16.0, + "tool_calls": 51.5, + "eval_episodes": 2, + "seed_start": 10314, + "world_split": "eval", + "world_family": "auto" + } + ] + } + ], + "log_history": [ + { + "loss": 2.1897194385528564, + "grad_norm": 2.179722309112549, + "learning_rate": 0.0, + "epoch": 0.0026455026455026454, + "step": 1 + }, + { + "loss": 2.023362159729004, + "grad_norm": 1.4213849306106567, + "learning_rate": 5.263157894736842e-06, + "epoch": 0.005291005291005291, + "step": 2 + }, + { + "loss": 2.1094398498535156, + "grad_norm": 1.4651298522949219, + "learning_rate": 1.0526315789473684e-05, + "epoch": 0.007936507936507936, + "step": 3 + }, + { + "loss": 2.0047714710235596, + "grad_norm": 1.3533823490142822, + "learning_rate": 1.5789473684210526e-05, + "epoch": 0.010582010582010581, + "step": 4 + }, + { + "loss": 2.121164560317993, + "grad_norm": 1.6160931587219238, + "learning_rate": 2.105263157894737e-05, + "epoch": 0.013227513227513227, + "step": 5 + }, + { + "loss": 2.1543028354644775, + "grad_norm": 1.7538481950759888, + "learning_rate": 2.6315789473684212e-05, + "epoch": 0.015873015873015872, + "step": 6 + }, + { + "loss": 1.98488187789917, + "grad_norm": 1.4564684629440308, + "learning_rate": 3.157894736842105e-05, + "epoch": 0.018518518518518517, + "step": 7 + }, + { + "loss": 1.990682601928711, + "grad_norm": 1.106909155845642, + "learning_rate": 3.6842105263157895e-05, + "epoch": 0.021164021164021163, + "step": 8 + }, + { + "loss": 2.113189697265625, + "grad_norm": 1.23565673828125, + "learning_rate": 4.210526315789474e-05, + "epoch": 0.023809523809523808, + "step": 9 + }, + { + "loss": 1.9175727367401123, + "grad_norm": 0.8749648332595825, + "learning_rate": 4.736842105263158e-05, + "epoch": 0.026455026455026454, + "step": 10 + }, + { + "loss": 2.070034980773926, + "grad_norm": 0.9515067934989929, + "learning_rate": 5.2631578947368424e-05, + "epoch": 0.0291005291005291, + "step": 11 + }, + { + "loss": 1.849581003189087, + "grad_norm": 0.6469148397445679, + "learning_rate": 5.789473684210527e-05, + "epoch": 0.031746031746031744, + "step": 12 + }, + { + "loss": 1.6639738082885742, + "grad_norm": 0.6476016044616699, + "learning_rate": 6.31578947368421e-05, + "epoch": 0.03439153439153439, + "step": 13 + }, + { + "loss": 1.7406408786773682, + "grad_norm": 0.7043063640594482, + "learning_rate": 6.842105263157895e-05, + "epoch": 0.037037037037037035, + "step": 14 + }, + { + "loss": 1.6576179265975952, + "grad_norm": 0.5968908071517944, + "learning_rate": 7.368421052631579e-05, + "epoch": 0.03968253968253968, + "step": 15 + }, + { + "loss": 1.761307954788208, + "grad_norm": 0.679215669631958, + "learning_rate": 7.894736842105263e-05, + "epoch": 0.042328042328042326, + "step": 16 + }, + { + "loss": 1.728525161743164, + "grad_norm": 0.6668431758880615, + "learning_rate": 8.421052631578948e-05, + "epoch": 0.04497354497354497, + "step": 17 + }, + { + "loss": 1.6631115674972534, + "grad_norm": 0.6382503509521484, + "learning_rate": 8.947368421052632e-05, + "epoch": 0.047619047619047616, + "step": 18 + }, + { + "loss": 1.566865086555481, + "grad_norm": 0.699229896068573, + "learning_rate": 9.473684210526316e-05, + "epoch": 0.05026455026455026, + "step": 19 + }, + { + "loss": 1.386806607246399, + "grad_norm": 0.6102572679519653, + "learning_rate": 0.0001, + "epoch": 0.05291005291005291, + "step": 20 + }, + { + "loss": 1.3766692876815796, + "grad_norm": 0.7419372797012329, + "learning_rate": 0.00010526315789473685, + "epoch": 0.05555555555555555, + "step": 21 + }, + { + "loss": 1.2881217002868652, + "grad_norm": 0.7205930948257446, + "learning_rate": 0.0001105263157894737, + "epoch": 0.0582010582010582, + "step": 22 + }, + { + "loss": 1.3662283420562744, + "grad_norm": 0.7660960555076599, + "learning_rate": 0.00011578947368421053, + "epoch": 0.06084656084656084, + "step": 23 + }, + { + "loss": 1.1722878217697144, + "grad_norm": 0.8346042037010193, + "learning_rate": 0.00012105263157894738, + "epoch": 0.06349206349206349, + "step": 24 + }, + { + "loss": 1.0199048519134521, + "grad_norm": 0.8875777721405029, + "learning_rate": 0.0001263157894736842, + "epoch": 0.06613756613756613, + "step": 25 + }, + { + "loss": 0.8610183000564575, + "grad_norm": 0.908794105052948, + "learning_rate": 0.00013157894736842108, + "epoch": 0.06878306878306878, + "step": 26 + }, + { + "loss": 0.8983635306358337, + "grad_norm": 1.1685150861740112, + "learning_rate": 0.0001368421052631579, + "epoch": 0.07142857142857142, + "step": 27 + }, + { + "loss": 0.883075475692749, + "grad_norm": 1.1241850852966309, + "learning_rate": 0.00014210526315789474, + "epoch": 0.07407407407407407, + "step": 28 + }, + { + "loss": 0.6960610151290894, + "grad_norm": 0.899897038936615, + "learning_rate": 0.00014736842105263158, + "epoch": 0.07671957671957672, + "step": 29 + }, + { + "loss": 0.4915878176689148, + "grad_norm": 1.270443081855774, + "learning_rate": 0.00015263157894736845, + "epoch": 0.07936507936507936, + "step": 30 + }, + { + "loss": 0.48479601740837097, + "grad_norm": 0.8855540156364441, + "learning_rate": 0.00015789473684210527, + "epoch": 0.082010582010582, + "step": 31 + }, + { + "loss": 0.45518991351127625, + "grad_norm": 0.6610377430915833, + "learning_rate": 0.0001631578947368421, + "epoch": 0.08465608465608465, + "step": 32 + }, + { + "loss": 0.5127372145652771, + "grad_norm": 0.8044703602790833, + "learning_rate": 0.00016842105263157895, + "epoch": 0.0873015873015873, + "step": 33 + }, + { + "loss": 0.24351520836353302, + "grad_norm": 0.6767902374267578, + "learning_rate": 0.0001736842105263158, + "epoch": 0.08994708994708994, + "step": 34 + }, + { + "loss": 0.43377262353897095, + "grad_norm": 0.8144934773445129, + "learning_rate": 0.00017894736842105264, + "epoch": 0.09259259259259259, + "step": 35 + }, + { + "loss": 0.419627845287323, + "grad_norm": 0.7722636461257935, + "learning_rate": 0.00018421052631578948, + "epoch": 0.09523809523809523, + "step": 36 + }, + { + "loss": 0.28788167238235474, + "grad_norm": 0.6482549905776978, + "learning_rate": 0.00018947368421052632, + "epoch": 0.09788359788359788, + "step": 37 + }, + { + "loss": 0.345514714717865, + "grad_norm": 0.86399906873703, + "learning_rate": 0.00019473684210526317, + "epoch": 0.10052910052910052, + "step": 38 + }, + { + "loss": 0.2702908217906952, + "grad_norm": 0.5985870957374573, + "learning_rate": 0.0002, + "epoch": 0.10317460317460317, + "step": 39 + }, + { + "loss": 0.138988196849823, + "grad_norm": 0.9768778681755066, + "learning_rate": 0.00019941176470588236, + "epoch": 0.10582010582010581, + "step": 40 + }, + { + "loss": 0.2215503752231598, + "grad_norm": 0.5112291574478149, + "learning_rate": 0.00019882352941176472, + "epoch": 0.10846560846560846, + "step": 41 + }, + { + "loss": 0.1795579493045807, + "grad_norm": 0.6100095510482788, + "learning_rate": 0.00019823529411764707, + "epoch": 0.1111111111111111, + "step": 42 + }, + { + "loss": 0.2540356516838074, + "grad_norm": 0.6007102131843567, + "learning_rate": 0.00019764705882352942, + "epoch": 0.11375661375661375, + "step": 43 + }, + { + "loss": 0.1952768862247467, + "grad_norm": 0.8506730198860168, + "learning_rate": 0.00019705882352941177, + "epoch": 0.1164021164021164, + "step": 44 + }, + { + "loss": 0.09109751880168915, + "grad_norm": 0.539446234703064, + "learning_rate": 0.00019647058823529413, + "epoch": 0.11904761904761904, + "step": 45 + }, + { + "loss": 0.05925009772181511, + "grad_norm": 0.6698726415634155, + "learning_rate": 0.00019588235294117648, + "epoch": 0.12169312169312169, + "step": 46 + }, + { + "loss": 0.20134183764457703, + "grad_norm": 0.7804432511329651, + "learning_rate": 0.00019529411764705883, + "epoch": 0.12433862433862433, + "step": 47 + }, + { + "loss": 0.06878196448087692, + "grad_norm": 0.4411237835884094, + "learning_rate": 0.0001947058823529412, + "epoch": 0.12698412698412698, + "step": 48 + }, + { + "loss": 0.08819292485713959, + "grad_norm": 0.44216546416282654, + "learning_rate": 0.00019411764705882354, + "epoch": 0.12962962962962962, + "step": 49 + }, + { + "loss": 0.06745278090238571, + "grad_norm": 0.3976341485977173, + "learning_rate": 0.0001935294117647059, + "epoch": 0.13227513227513227, + "step": 50 + }, + { + "loss": 0.08112215995788574, + "grad_norm": 0.3720063269138336, + "learning_rate": 0.00019294117647058825, + "epoch": 0.1349206349206349, + "step": 51 + }, + { + "loss": 0.05829603970050812, + "grad_norm": 0.3113236129283905, + "learning_rate": 0.0001923529411764706, + "epoch": 0.13756613756613756, + "step": 52 + }, + { + "loss": 0.06131816282868385, + "grad_norm": 0.32390567660331726, + "learning_rate": 0.00019176470588235295, + "epoch": 0.1402116402116402, + "step": 53 + }, + { + "loss": 0.06756111979484558, + "grad_norm": 0.32028791308403015, + "learning_rate": 0.0001911764705882353, + "epoch": 0.14285714285714285, + "step": 54 + }, + { + "loss": 0.06646526604890823, + "grad_norm": 0.37312281131744385, + "learning_rate": 0.00019058823529411766, + "epoch": 0.1455026455026455, + "step": 55 + }, + { + "loss": 0.0654621571302414, + "grad_norm": 0.31677088141441345, + "learning_rate": 0.00019, + "epoch": 0.14814814814814814, + "step": 56 + }, + { + "loss": 0.04999839514493942, + "grad_norm": 0.3041898012161255, + "learning_rate": 0.00018941176470588236, + "epoch": 0.15079365079365079, + "step": 57 + }, + { + "loss": 0.06149204075336456, + "grad_norm": 0.3311505913734436, + "learning_rate": 0.00018882352941176472, + "epoch": 0.15343915343915343, + "step": 58 + }, + { + "loss": 0.05500664934515953, + "grad_norm": 0.37871378660202026, + "learning_rate": 0.00018823529411764707, + "epoch": 0.15608465608465608, + "step": 59 + }, + { + "loss": 0.06044406071305275, + "grad_norm": 0.39543280005455017, + "learning_rate": 0.00018764705882352942, + "epoch": 0.15873015873015872, + "step": 60 + }, + { + "loss": 0.09898850321769714, + "grad_norm": 0.4568597078323364, + "learning_rate": 0.00018705882352941178, + "epoch": 0.16137566137566137, + "step": 61 + }, + { + "loss": 0.03585953637957573, + "grad_norm": 0.22915291786193848, + "learning_rate": 0.00018647058823529413, + "epoch": 0.164021164021164, + "step": 62 + }, + { + "loss": 0.04662243276834488, + "grad_norm": 0.24822668731212616, + "learning_rate": 0.00018588235294117648, + "epoch": 0.16666666666666666, + "step": 63 + }, + { + "loss": 0.03733272850513458, + "grad_norm": 0.21082530915737152, + "learning_rate": 0.00018529411764705883, + "epoch": 0.1693121693121693, + "step": 64 + }, + { + "loss": 0.053247880190610886, + "grad_norm": 0.24000464379787445, + "learning_rate": 0.0001847058823529412, + "epoch": 0.17195767195767195, + "step": 65 + }, + { + "loss": 0.032761458307504654, + "grad_norm": 0.2516216039657593, + "learning_rate": 0.00018411764705882354, + "epoch": 0.1746031746031746, + "step": 66 + }, + { + "loss": 0.03275494650006294, + "grad_norm": 0.18968793749809265, + "learning_rate": 0.0001835294117647059, + "epoch": 0.17724867724867724, + "step": 67 + }, + { + "loss": 0.048416756093502045, + "grad_norm": 0.276112824678421, + "learning_rate": 0.00018294117647058825, + "epoch": 0.17989417989417988, + "step": 68 + }, + { + "loss": 0.05309575796127319, + "grad_norm": 0.26847490668296814, + "learning_rate": 0.0001823529411764706, + "epoch": 0.18253968253968253, + "step": 69 + }, + { + "loss": 0.034724876284599304, + "grad_norm": 0.1752200871706009, + "learning_rate": 0.00018176470588235295, + "epoch": 0.18518518518518517, + "step": 70 + }, + { + "loss": 0.03913448005914688, + "grad_norm": 0.21263518929481506, + "learning_rate": 0.0001811764705882353, + "epoch": 0.18783068783068782, + "step": 71 + }, + { + "loss": 0.039260510355234146, + "grad_norm": 0.2233489453792572, + "learning_rate": 0.00018058823529411766, + "epoch": 0.19047619047619047, + "step": 72 + }, + { + "loss": 0.04198860377073288, + "grad_norm": 0.2861306369304657, + "learning_rate": 0.00018, + "epoch": 0.1931216931216931, + "step": 73 + }, + { + "loss": 0.04677252471446991, + "grad_norm": 0.24997933208942413, + "learning_rate": 0.00017941176470588236, + "epoch": 0.19576719576719576, + "step": 74 + }, + { + "loss": 0.028377845883369446, + "grad_norm": 0.16289812326431274, + "learning_rate": 0.00017882352941176472, + "epoch": 0.1984126984126984, + "step": 75 + }, + { + "loss": 0.03226421773433685, + "grad_norm": 0.16733668744564056, + "learning_rate": 0.00017823529411764707, + "epoch": 0.20105820105820105, + "step": 76 + }, + { + "loss": 0.029218731448054314, + "grad_norm": 0.19138193130493164, + "learning_rate": 0.00017764705882352942, + "epoch": 0.2037037037037037, + "step": 77 + }, + { + "loss": 0.046170152723789215, + "grad_norm": 0.3590056598186493, + "learning_rate": 0.00017705882352941178, + "epoch": 0.20634920634920634, + "step": 78 + }, + { + "loss": 0.02912411093711853, + "grad_norm": 0.11775410175323486, + "learning_rate": 0.00017647058823529413, + "epoch": 0.20899470899470898, + "step": 79 + }, + { + "loss": 0.030748452991247177, + "grad_norm": 0.27214574813842773, + "learning_rate": 0.00017588235294117648, + "epoch": 0.21164021164021163, + "step": 80 + }, + { + "loss": 0.05233598127961159, + "grad_norm": 0.24026575684547424, + "learning_rate": 0.00017529411764705884, + "epoch": 0.21428571428571427, + "step": 81 + }, + { + "loss": 0.03420679643750191, + "grad_norm": 0.1532716304063797, + "learning_rate": 0.0001747058823529412, + "epoch": 0.21693121693121692, + "step": 82 + }, + { + "loss": 0.031814150512218475, + "grad_norm": 0.20529142022132874, + "learning_rate": 0.00017411764705882354, + "epoch": 0.21957671957671956, + "step": 83 + }, + { + "loss": 0.033638425171375275, + "grad_norm": 0.15324054658412933, + "learning_rate": 0.0001735294117647059, + "epoch": 0.2222222222222222, + "step": 84 + }, + { + "loss": 0.03216666728258133, + "grad_norm": 0.12442298233509064, + "learning_rate": 0.00017294117647058825, + "epoch": 0.22486772486772486, + "step": 85 + }, + { + "loss": 0.04404332861304283, + "grad_norm": 0.17220208048820496, + "learning_rate": 0.0001723529411764706, + "epoch": 0.2275132275132275, + "step": 86 + }, + { + "loss": 0.03520449623465538, + "grad_norm": 0.17782780528068542, + "learning_rate": 0.00017176470588235293, + "epoch": 0.23015873015873015, + "step": 87 + }, + { + "loss": 0.033416785299777985, + "grad_norm": 0.1682697832584381, + "learning_rate": 0.0001711764705882353, + "epoch": 0.2328042328042328, + "step": 88 + }, + { + "loss": 0.02910282462835312, + "grad_norm": 0.14391784369945526, + "learning_rate": 0.00017058823529411766, + "epoch": 0.23544973544973544, + "step": 89 + }, + { + "loss": 0.04076948016881943, + "grad_norm": 0.18359090387821198, + "learning_rate": 0.00017, + "epoch": 0.23809523809523808, + "step": 90 + }, + { + "loss": 0.03425406664609909, + "grad_norm": 0.16633570194244385, + "learning_rate": 0.00016941176470588237, + "epoch": 0.24074074074074073, + "step": 91 + }, + { + "loss": 0.031353384256362915, + "grad_norm": 0.19237634539604187, + "learning_rate": 0.00016882352941176472, + "epoch": 0.24338624338624337, + "step": 92 + }, + { + "loss": 0.0268703605979681, + "grad_norm": 0.1461161971092224, + "learning_rate": 0.00016823529411764707, + "epoch": 0.24603174603174602, + "step": 93 + }, + { + "loss": 0.03515759855508804, + "grad_norm": 0.1624964326620102, + "learning_rate": 0.00016764705882352942, + "epoch": 0.24867724867724866, + "step": 94 + }, + { + "loss": 0.02797013334929943, + "grad_norm": 0.166213721036911, + "learning_rate": 0.00016705882352941178, + "epoch": 0.25132275132275134, + "step": 95 + }, + { + "loss": 0.04394323751330376, + "grad_norm": 0.1734573096036911, + "learning_rate": 0.00016647058823529413, + "epoch": 0.25396825396825395, + "step": 96 + }, + { + "loss": 0.037255994975566864, + "grad_norm": 0.13153059780597687, + "learning_rate": 0.00016588235294117648, + "epoch": 0.2566137566137566, + "step": 97 + }, + { + "loss": 0.03898382931947708, + "grad_norm": 0.18587706983089447, + "learning_rate": 0.0001652941176470588, + "epoch": 0.25925925925925924, + "step": 98 + }, + { + "loss": 0.039507556706666946, + "grad_norm": 0.23434405028820038, + "learning_rate": 0.0001647058823529412, + "epoch": 0.2619047619047619, + "step": 99 + }, + { + "loss": 0.02951202541589737, + "grad_norm": 0.155650794506073, + "learning_rate": 0.00016411764705882354, + "epoch": 0.26455026455026454, + "step": 100 + }, + { + "loss": 0.026405351236462593, + "grad_norm": 0.15819966793060303, + "learning_rate": 0.0001635294117647059, + "epoch": 0.2671957671957672, + "step": 101 + }, + { + "loss": 0.033975858241319656, + "grad_norm": 0.17255833745002747, + "learning_rate": 0.00016294117647058825, + "epoch": 0.2698412698412698, + "step": 102 + }, + { + "loss": 0.04301761835813522, + "grad_norm": 0.19272208213806152, + "learning_rate": 0.0001623529411764706, + "epoch": 0.2724867724867725, + "step": 103 + }, + { + "loss": 0.03340883180499077, + "grad_norm": 0.11553694307804108, + "learning_rate": 0.00016176470588235295, + "epoch": 0.2751322751322751, + "step": 104 + }, + { + "loss": 0.023269247263669968, + "grad_norm": 0.14557777345180511, + "learning_rate": 0.0001611764705882353, + "epoch": 0.2777777777777778, + "step": 105 + }, + { + "loss": 0.03297317028045654, + "grad_norm": 0.16001370549201965, + "learning_rate": 0.00016058823529411766, + "epoch": 0.2804232804232804, + "step": 106 + }, + { + "loss": 0.02670835703611374, + "grad_norm": 0.126630961894989, + "learning_rate": 0.00016, + "epoch": 0.2830687830687831, + "step": 107 + }, + { + "loss": 0.03365064039826393, + "grad_norm": 0.1740054488182068, + "learning_rate": 0.00015941176470588237, + "epoch": 0.2857142857142857, + "step": 108 + }, + { + "loss": 0.03272430971264839, + "grad_norm": 0.13207320868968964, + "learning_rate": 0.0001588235294117647, + "epoch": 0.28835978835978837, + "step": 109 + }, + { + "loss": 0.030736371874809265, + "grad_norm": 0.12624885141849518, + "learning_rate": 0.00015823529411764707, + "epoch": 0.291005291005291, + "step": 110 + }, + { + "loss": 0.03765019774436951, + "grad_norm": 0.16265016794204712, + "learning_rate": 0.00015764705882352943, + "epoch": 0.29365079365079366, + "step": 111 + }, + { + "loss": 0.027364399284124374, + "grad_norm": 0.10131661593914032, + "learning_rate": 0.00015705882352941178, + "epoch": 0.2962962962962963, + "step": 112 + }, + { + "loss": 0.03020496666431427, + "grad_norm": 0.11311211436986923, + "learning_rate": 0.00015647058823529413, + "epoch": 0.29894179894179895, + "step": 113 + }, + { + "loss": 0.024272479116916656, + "grad_norm": 0.14199671149253845, + "learning_rate": 0.00015588235294117648, + "epoch": 0.30158730158730157, + "step": 114 + }, + { + "loss": 0.030500095337629318, + "grad_norm": 0.10554862767457962, + "learning_rate": 0.00015529411764705884, + "epoch": 0.30423280423280424, + "step": 115 + }, + { + "loss": 0.024758869782090187, + "grad_norm": 0.1271071583032608, + "learning_rate": 0.0001547058823529412, + "epoch": 0.30687830687830686, + "step": 116 + }, + { + "loss": 0.029552360996603966, + "grad_norm": 0.10222607851028442, + "learning_rate": 0.00015411764705882354, + "epoch": 0.30952380952380953, + "step": 117 + }, + { + "loss": 0.030012380331754684, + "grad_norm": 0.1220894306898117, + "learning_rate": 0.0001535294117647059, + "epoch": 0.31216931216931215, + "step": 118 + }, + { + "loss": 0.02706737630069256, + "grad_norm": 0.09390514343976974, + "learning_rate": 0.00015294117647058822, + "epoch": 0.3148148148148148, + "step": 119 + }, + { + "loss": 0.0400836318731308, + "grad_norm": 0.14255541563034058, + "learning_rate": 0.00015235294117647057, + "epoch": 0.31746031746031744, + "step": 120 + }, + { + "loss": 0.03125084191560745, + "grad_norm": 0.14766481518745422, + "learning_rate": 0.00015176470588235295, + "epoch": 0.3201058201058201, + "step": 121 + }, + { + "loss": 0.035637352615594864, + "grad_norm": 0.13055112957954407, + "learning_rate": 0.0001511764705882353, + "epoch": 0.32275132275132273, + "step": 122 + }, + { + "loss": 0.02989823743700981, + "grad_norm": 0.12400601804256439, + "learning_rate": 0.00015058823529411766, + "epoch": 0.3253968253968254, + "step": 123 + }, + { + "loss": 0.029374703764915466, + "grad_norm": 0.10204735398292542, + "learning_rate": 0.00015000000000000001, + "epoch": 0.328042328042328, + "step": 124 + }, + { + "loss": 0.02627715840935707, + "grad_norm": 0.13396649062633514, + "learning_rate": 0.00014941176470588237, + "epoch": 0.3306878306878307, + "step": 125 + }, + { + "loss": 0.03121405467391014, + "grad_norm": 0.135880708694458, + "learning_rate": 0.00014882352941176472, + "epoch": 0.3333333333333333, + "step": 126 + }, + { + "loss": 0.032626084983348846, + "grad_norm": 0.12243980169296265, + "learning_rate": 0.00014823529411764707, + "epoch": 0.335978835978836, + "step": 127 + }, + { + "loss": 0.028939921408891678, + "grad_norm": 0.12009332329034805, + "learning_rate": 0.00014764705882352943, + "epoch": 0.3386243386243386, + "step": 128 + }, + { + "loss": 0.021900050342082977, + "grad_norm": 0.10653378814458847, + "learning_rate": 0.00014705882352941178, + "epoch": 0.3412698412698413, + "step": 129 + }, + { + "loss": 0.023994363844394684, + "grad_norm": 0.12935952842235565, + "learning_rate": 0.0001464705882352941, + "epoch": 0.3439153439153439, + "step": 130 + }, + { + "loss": 0.031131461262702942, + "grad_norm": 0.11746851354837418, + "learning_rate": 0.00014588235294117646, + "epoch": 0.34656084656084657, + "step": 131 + }, + { + "loss": 0.02585621550679207, + "grad_norm": 0.07750687748193741, + "learning_rate": 0.00014529411764705884, + "epoch": 0.3492063492063492, + "step": 132 + }, + { + "loss": 0.03250286355614662, + "grad_norm": 0.11024343967437744, + "learning_rate": 0.0001447058823529412, + "epoch": 0.35185185185185186, + "step": 133 + }, + { + "loss": 0.020486077293753624, + "grad_norm": 0.06996645033359528, + "learning_rate": 0.00014411764705882354, + "epoch": 0.3544973544973545, + "step": 134 + }, + { + "loss": 0.036177776753902435, + "grad_norm": 0.12662774324417114, + "learning_rate": 0.0001435294117647059, + "epoch": 0.35714285714285715, + "step": 135 + }, + { + "loss": 0.012204527854919434, + "grad_norm": 0.1284666508436203, + "learning_rate": 0.00014294117647058825, + "epoch": 0.35978835978835977, + "step": 136 + }, + { + "loss": 0.03306424245238304, + "grad_norm": 0.13339443504810333, + "learning_rate": 0.0001423529411764706, + "epoch": 0.36243386243386244, + "step": 137 + }, + { + "loss": 0.015852898359298706, + "grad_norm": 0.08559766411781311, + "learning_rate": 0.00014176470588235296, + "epoch": 0.36507936507936506, + "step": 138 + }, + { + "loss": 0.0280722938477993, + "grad_norm": 0.09247807413339615, + "learning_rate": 0.0001411764705882353, + "epoch": 0.36772486772486773, + "step": 139 + }, + { + "loss": 0.02845999225974083, + "grad_norm": 0.07329782098531723, + "learning_rate": 0.00014058823529411763, + "epoch": 0.37037037037037035, + "step": 140 + }, + { + "loss": 0.028397955000400543, + "grad_norm": 0.07966873049736023, + "learning_rate": 0.00014, + "epoch": 0.373015873015873, + "step": 141 + }, + { + "loss": 0.03037174791097641, + "grad_norm": 0.11311368644237518, + "learning_rate": 0.00013941176470588234, + "epoch": 0.37566137566137564, + "step": 142 + }, + { + "loss": 0.031476639211177826, + "grad_norm": 0.09898155182600021, + "learning_rate": 0.00013882352941176472, + "epoch": 0.3783068783068783, + "step": 143 + }, + { + "loss": 0.02341204509139061, + "grad_norm": 0.08948683738708496, + "learning_rate": 0.00013823529411764707, + "epoch": 0.38095238095238093, + "step": 144 + }, + { + "loss": 0.029298145323991776, + "grad_norm": 0.09334739297628403, + "learning_rate": 0.00013764705882352943, + "epoch": 0.3835978835978836, + "step": 145 + }, + { + "loss": 0.026255691424012184, + "grad_norm": 0.08544398099184036, + "learning_rate": 0.00013705882352941178, + "epoch": 0.3862433862433862, + "step": 146 + }, + { + "loss": 0.03272281587123871, + "grad_norm": 0.13078875839710236, + "learning_rate": 0.00013647058823529413, + "epoch": 0.3888888888888889, + "step": 147 + }, + { + "loss": 0.028953030705451965, + "grad_norm": 0.09091654419898987, + "learning_rate": 0.00013588235294117649, + "epoch": 0.3915343915343915, + "step": 148 + }, + { + "loss": 0.03124978020787239, + "grad_norm": 0.10748365521430969, + "learning_rate": 0.00013529411764705884, + "epoch": 0.3941798941798942, + "step": 149 + }, + { + "loss": 0.032467320561409, + "grad_norm": 0.10507789254188538, + "learning_rate": 0.0001347058823529412, + "epoch": 0.3968253968253968, + "step": 150 + }, + { + "loss": 0.026149973273277283, + "grad_norm": 0.12107130140066147, + "learning_rate": 0.00013411764705882352, + "epoch": 0.3994708994708995, + "step": 151 + }, + { + "loss": 0.03004319593310356, + "grad_norm": 0.09358958154916763, + "learning_rate": 0.00013352941176470587, + "epoch": 0.4021164021164021, + "step": 152 + }, + { + "loss": 0.029231414198875427, + "grad_norm": 0.12608052790164948, + "learning_rate": 0.00013294117647058822, + "epoch": 0.40476190476190477, + "step": 153 + }, + { + "loss": 0.03578457981348038, + "grad_norm": 0.13080942630767822, + "learning_rate": 0.0001323529411764706, + "epoch": 0.4074074074074074, + "step": 154 + }, + { + "loss": 0.02078537829220295, + "grad_norm": 0.11083829402923584, + "learning_rate": 0.00013176470588235296, + "epoch": 0.41005291005291006, + "step": 155 + }, + { + "loss": 0.03142306208610535, + "grad_norm": 0.09704726189374924, + "learning_rate": 0.0001311764705882353, + "epoch": 0.4126984126984127, + "step": 156 + }, + { + "loss": 0.02688862755894661, + "grad_norm": 0.09696362167596817, + "learning_rate": 0.00013058823529411766, + "epoch": 0.41534391534391535, + "step": 157 + }, + { + "loss": 0.027476545423269272, + "grad_norm": 0.11424606293439865, + "learning_rate": 0.00013000000000000002, + "epoch": 0.41798941798941797, + "step": 158 + }, + { + "loss": 0.029973959550261497, + "grad_norm": 0.11554589122533798, + "learning_rate": 0.00012941176470588237, + "epoch": 0.42063492063492064, + "step": 159 + }, + { + "loss": 0.022143110632896423, + "grad_norm": 0.08863114565610886, + "learning_rate": 0.00012882352941176472, + "epoch": 0.42328042328042326, + "step": 160 + }, + { + "loss": 0.03136860206723213, + "grad_norm": 0.11660370230674744, + "learning_rate": 0.00012823529411764707, + "epoch": 0.42592592592592593, + "step": 161 + }, + { + "loss": 0.02894529700279236, + "grad_norm": 0.1340770572423935, + "learning_rate": 0.0001276470588235294, + "epoch": 0.42857142857142855, + "step": 162 + }, + { + "loss": 0.033732134848833084, + "grad_norm": 0.12249583750963211, + "learning_rate": 0.00012705882352941175, + "epoch": 0.4312169312169312, + "step": 163 + }, + { + "loss": 0.026288658380508423, + "grad_norm": 0.072428397834301, + "learning_rate": 0.0001264705882352941, + "epoch": 0.43386243386243384, + "step": 164 + }, + { + "loss": 0.03067208267748356, + "grad_norm": 0.09587821364402771, + "learning_rate": 0.0001258823529411765, + "epoch": 0.4365079365079365, + "step": 165 + }, + { + "loss": 0.027257606387138367, + "grad_norm": 0.09238255769014359, + "learning_rate": 0.00012529411764705884, + "epoch": 0.43915343915343913, + "step": 166 + }, + { + "loss": 0.020257430151104927, + "grad_norm": 0.09599533677101135, + "learning_rate": 0.0001247058823529412, + "epoch": 0.4417989417989418, + "step": 167 + }, + { + "loss": 0.025873055681586266, + "grad_norm": 0.08279647678136826, + "learning_rate": 0.00012411764705882355, + "epoch": 0.4444444444444444, + "step": 168 + }, + { + "loss": 0.02722345106303692, + "grad_norm": 0.10330381989479065, + "learning_rate": 0.0001235294117647059, + "epoch": 0.4470899470899471, + "step": 169 + }, + { + "loss": 0.0284090805798769, + "grad_norm": 0.09777422249317169, + "learning_rate": 0.00012294117647058825, + "epoch": 0.4497354497354497, + "step": 170 + }, + { + "loss": 0.0273237656801939, + "grad_norm": 0.10960041731595993, + "learning_rate": 0.0001223529411764706, + "epoch": 0.4523809523809524, + "step": 171 + }, + { + "loss": 0.03370822221040726, + "grad_norm": 0.1169227808713913, + "learning_rate": 0.00012176470588235293, + "epoch": 0.455026455026455, + "step": 172 + }, + { + "loss": 0.018664535135030746, + "grad_norm": 0.08496791124343872, + "learning_rate": 0.0001211764705882353, + "epoch": 0.4576719576719577, + "step": 173 + }, + { + "loss": 0.029450563713908195, + "grad_norm": 0.10068070143461227, + "learning_rate": 0.00012058823529411765, + "epoch": 0.4603174603174603, + "step": 174 + }, + { + "loss": 0.02172383852303028, + "grad_norm": 0.09669794887304306, + "learning_rate": 0.00012, + "epoch": 0.46296296296296297, + "step": 175 + }, + { + "loss": 0.029448989778757095, + "grad_norm": 0.12710849940776825, + "learning_rate": 0.00011941176470588236, + "epoch": 0.4656084656084656, + "step": 176 + }, + { + "loss": 0.023345600813627243, + "grad_norm": 0.09274916350841522, + "learning_rate": 0.00011882352941176471, + "epoch": 0.46825396825396826, + "step": 177 + }, + { + "loss": 0.026639586314558983, + "grad_norm": 0.10277178883552551, + "learning_rate": 0.00011823529411764706, + "epoch": 0.4708994708994709, + "step": 178 + }, + { + "loss": 0.021892163902521133, + "grad_norm": 0.06539881974458694, + "learning_rate": 0.00011764705882352942, + "epoch": 0.47354497354497355, + "step": 179 + }, + { + "loss": 0.022277187556028366, + "grad_norm": 0.10823221504688263, + "learning_rate": 0.00011705882352941178, + "epoch": 0.47619047619047616, + "step": 180 + }, + { + "loss": 0.03035702183842659, + "grad_norm": 0.15443108975887299, + "learning_rate": 0.00011647058823529413, + "epoch": 0.47883597883597884, + "step": 181 + }, + { + "loss": 0.03421338275074959, + "grad_norm": 0.10227533429861069, + "learning_rate": 0.00011588235294117649, + "epoch": 0.48148148148148145, + "step": 182 + }, + { + "loss": 0.029597604647278786, + "grad_norm": 0.0971686840057373, + "learning_rate": 0.00011529411764705881, + "epoch": 0.48412698412698413, + "step": 183 + }, + { + "loss": 0.027550101280212402, + "grad_norm": 0.1261613965034485, + "learning_rate": 0.00011470588235294118, + "epoch": 0.48677248677248675, + "step": 184 + }, + { + "loss": 0.03323390707373619, + "grad_norm": 0.11550288647413254, + "learning_rate": 0.00011411764705882353, + "epoch": 0.4894179894179894, + "step": 185 + }, + { + "loss": 0.02156604826450348, + "grad_norm": 0.08063457161188126, + "learning_rate": 0.00011352941176470589, + "epoch": 0.49206349206349204, + "step": 186 + }, + { + "loss": 0.024817658588290215, + "grad_norm": 0.10156011581420898, + "learning_rate": 0.00011294117647058824, + "epoch": 0.4947089947089947, + "step": 187 + }, + { + "loss": 0.02846340462565422, + "grad_norm": 0.15647770464420319, + "learning_rate": 0.00011235294117647059, + "epoch": 0.4973544973544973, + "step": 188 + }, + { + "loss": 0.016268836334347725, + "grad_norm": 0.07191152125597, + "learning_rate": 0.00011176470588235294, + "epoch": 0.5, + "step": 189 + }, + { + "loss": 0.02841845154762268, + "grad_norm": 0.11040358245372772, + "learning_rate": 0.0001111764705882353, + "epoch": 0.5026455026455027, + "step": 190 + }, + { + "loss": 0.0306367389857769, + "grad_norm": 0.14806240797042847, + "learning_rate": 0.00011058823529411766, + "epoch": 0.5052910052910053, + "step": 191 + }, + { + "loss": 0.031015485525131226, + "grad_norm": 0.10778608918190002, + "learning_rate": 0.00011000000000000002, + "epoch": 0.5079365079365079, + "step": 192 + }, + { + "loss": 0.03242127224802971, + "grad_norm": 0.11341337114572525, + "learning_rate": 0.00010941176470588237, + "epoch": 0.5105820105820106, + "step": 193 + }, + { + "loss": 0.03684879094362259, + "grad_norm": 0.12730282545089722, + "learning_rate": 0.0001088235294117647, + "epoch": 0.5132275132275133, + "step": 194 + }, + { + "loss": 0.0260506309568882, + "grad_norm": 0.09207483381032944, + "learning_rate": 0.00010823529411764706, + "epoch": 0.5158730158730159, + "step": 195 + }, + { + "loss": 0.02128693461418152, + "grad_norm": 0.10040389746427536, + "learning_rate": 0.00010764705882352942, + "epoch": 0.5185185185185185, + "step": 196 + }, + { + "loss": 0.03452152758836746, + "grad_norm": 0.11447006464004517, + "learning_rate": 0.00010705882352941177, + "epoch": 0.5211640211640212, + "step": 197 + }, + { + "loss": 0.028310813009738922, + "grad_norm": 0.1034921407699585, + "learning_rate": 0.00010647058823529412, + "epoch": 0.5238095238095238, + "step": 198 + }, + { + "loss": 0.029575366526842117, + "grad_norm": 0.09908110648393631, + "learning_rate": 0.00010588235294117647, + "epoch": 0.5264550264550265, + "step": 199 + }, + { + "loss": 0.029606211930513382, + "grad_norm": 0.0822087973356247, + "learning_rate": 0.00010529411764705883, + "epoch": 0.5291005291005291, + "step": 200 + }, + { + "loss": 0.02741779386997223, + "grad_norm": 0.09481994062662125, + "learning_rate": 0.00010470588235294118, + "epoch": 0.5317460317460317, + "step": 201 + }, + { + "loss": 0.02750249207019806, + "grad_norm": 0.06643011420965195, + "learning_rate": 0.00010411764705882355, + "epoch": 0.5343915343915344, + "step": 202 + }, + { + "loss": 0.025049429386854172, + "grad_norm": 0.08693543821573257, + "learning_rate": 0.0001035294117647059, + "epoch": 0.5370370370370371, + "step": 203 + }, + { + "loss": 0.0188161451369524, + "grad_norm": 0.08780419826507568, + "learning_rate": 0.00010294117647058823, + "epoch": 0.5396825396825397, + "step": 204 + }, + { + "loss": 0.025752779096364975, + "grad_norm": 0.08089763671159744, + "learning_rate": 0.00010235294117647058, + "epoch": 0.5423280423280423, + "step": 205 + }, + { + "loss": 0.03086625598371029, + "grad_norm": 0.11511234939098358, + "learning_rate": 0.00010176470588235295, + "epoch": 0.544973544973545, + "step": 206 + }, + { + "loss": 0.0273880697786808, + "grad_norm": 0.10907749086618423, + "learning_rate": 0.0001011764705882353, + "epoch": 0.5476190476190477, + "step": 207 + }, + { + "loss": 0.026370292529463768, + "grad_norm": 0.08107511699199677, + "learning_rate": 0.00010058823529411765, + "epoch": 0.5502645502645502, + "step": 208 + }, + { + "loss": 0.025786038488149643, + "grad_norm": 0.0737859457731247, + "learning_rate": 0.0001, + "epoch": 0.5529100529100529, + "step": 209 + }, + { + "loss": 0.030016383156180382, + "grad_norm": 0.09232968837022781, + "learning_rate": 9.941176470588236e-05, + "epoch": 0.5555555555555556, + "step": 210 + }, + { + "loss": 0.021605785936117172, + "grad_norm": 0.0948951318860054, + "learning_rate": 9.882352941176471e-05, + "epoch": 0.5582010582010583, + "step": 211 + }, + { + "loss": 0.031091010197997093, + "grad_norm": 0.09735886752605438, + "learning_rate": 9.823529411764706e-05, + "epoch": 0.5608465608465608, + "step": 212 + }, + { + "loss": 0.030390700325369835, + "grad_norm": 0.10056869685649872, + "learning_rate": 9.764705882352942e-05, + "epoch": 0.5634920634920635, + "step": 213 + }, + { + "loss": 0.02216975763440132, + "grad_norm": 0.0720759853720665, + "learning_rate": 9.705882352941177e-05, + "epoch": 0.5661375661375662, + "step": 214 + }, + { + "loss": 0.02660333178937435, + "grad_norm": 0.09141097962856293, + "learning_rate": 9.647058823529412e-05, + "epoch": 0.5687830687830688, + "step": 215 + }, + { + "loss": 0.02590668946504593, + "grad_norm": 0.09253139793872833, + "learning_rate": 9.588235294117648e-05, + "epoch": 0.5714285714285714, + "step": 216 + }, + { + "loss": 0.02776462584733963, + "grad_norm": 0.08869278430938721, + "learning_rate": 9.529411764705883e-05, + "epoch": 0.5740740740740741, + "step": 217 + }, + { + "loss": 0.015304268337786198, + "grad_norm": 0.10566668212413788, + "learning_rate": 9.470588235294118e-05, + "epoch": 0.5767195767195767, + "step": 218 + }, + { + "loss": 0.027874145656824112, + "grad_norm": 0.08862630277872086, + "learning_rate": 9.411764705882353e-05, + "epoch": 0.5793650793650794, + "step": 219 + }, + { + "loss": 0.030754802748560905, + "grad_norm": 0.0958574190735817, + "learning_rate": 9.352941176470589e-05, + "epoch": 0.582010582010582, + "step": 220 + }, + { + "loss": 0.023360423743724823, + "grad_norm": 0.09204437583684921, + "learning_rate": 9.294117647058824e-05, + "epoch": 0.5846560846560847, + "step": 221 + }, + { + "loss": 0.031416505575180054, + "grad_norm": 0.12147050350904465, + "learning_rate": 9.23529411764706e-05, + "epoch": 0.5873015873015873, + "step": 222 + }, + { + "loss": 0.023884786292910576, + "grad_norm": 0.08076925575733185, + "learning_rate": 9.176470588235295e-05, + "epoch": 0.58994708994709, + "step": 223 + }, + { + "loss": 0.025108790025115013, + "grad_norm": 0.08516595512628555, + "learning_rate": 9.11764705882353e-05, + "epoch": 0.5925925925925926, + "step": 224 + }, + { + "loss": 0.0236780047416687, + "grad_norm": 0.09453090280294418, + "learning_rate": 9.058823529411765e-05, + "epoch": 0.5952380952380952, + "step": 225 + }, + { + "loss": 0.02253679558634758, + "grad_norm": 0.08398544788360596, + "learning_rate": 9e-05, + "epoch": 0.5978835978835979, + "step": 226 + }, + { + "loss": 0.027625620365142822, + "grad_norm": 0.08214128762483597, + "learning_rate": 8.941176470588236e-05, + "epoch": 0.6005291005291006, + "step": 227 + }, + { + "loss": 0.018679391592741013, + "grad_norm": 0.07763852924108505, + "learning_rate": 8.882352941176471e-05, + "epoch": 0.6031746031746031, + "step": 228 + }, + { + "loss": 0.018782157450914383, + "grad_norm": 0.0663997232913971, + "learning_rate": 8.823529411764706e-05, + "epoch": 0.6058201058201058, + "step": 229 + }, + { + "loss": 0.027178611606359482, + "grad_norm": 0.07828967273235321, + "learning_rate": 8.764705882352942e-05, + "epoch": 0.6084656084656085, + "step": 230 + }, + { + "loss": 0.023709267377853394, + "grad_norm": 0.08604388684034348, + "learning_rate": 8.705882352941177e-05, + "epoch": 0.6111111111111112, + "step": 231 + }, + { + "loss": 0.02602708712220192, + "grad_norm": 0.07984922081232071, + "learning_rate": 8.647058823529412e-05, + "epoch": 0.6137566137566137, + "step": 232 + }, + { + "loss": 0.02468765154480934, + "grad_norm": 0.07321182638406754, + "learning_rate": 8.588235294117646e-05, + "epoch": 0.6164021164021164, + "step": 233 + }, + { + "loss": 0.03028242662549019, + "grad_norm": 0.07817960530519485, + "learning_rate": 8.529411764705883e-05, + "epoch": 0.6190476190476191, + "step": 234 + }, + { + "loss": 0.02902349643409252, + "grad_norm": 0.06251050531864166, + "learning_rate": 8.470588235294118e-05, + "epoch": 0.6216931216931217, + "step": 235 + }, + { + "loss": 0.024306783452630043, + "grad_norm": 0.09529170393943787, + "learning_rate": 8.411764705882354e-05, + "epoch": 0.6243386243386243, + "step": 236 + }, + { + "loss": 0.03521513566374779, + "grad_norm": 0.1267942190170288, + "learning_rate": 8.352941176470589e-05, + "epoch": 0.626984126984127, + "step": 237 + }, + { + "loss": 0.020196501165628433, + "grad_norm": 0.08621630817651749, + "learning_rate": 8.294117647058824e-05, + "epoch": 0.6296296296296297, + "step": 238 + }, + { + "loss": 0.029385194182395935, + "grad_norm": 0.07552770525217056, + "learning_rate": 8.23529411764706e-05, + "epoch": 0.6322751322751323, + "step": 239 + }, + { + "loss": 0.01693333312869072, + "grad_norm": 0.09521529078483582, + "learning_rate": 8.176470588235295e-05, + "epoch": 0.6349206349206349, + "step": 240 + }, + { + "loss": 0.025097660720348358, + "grad_norm": 0.09436187893152237, + "learning_rate": 8.11764705882353e-05, + "epoch": 0.6375661375661376, + "step": 241 + }, + { + "loss": 0.027106281369924545, + "grad_norm": 0.07002269476652145, + "learning_rate": 8.058823529411765e-05, + "epoch": 0.6402116402116402, + "step": 242 + }, + { + "loss": 0.027904586866497993, + "grad_norm": 0.08871318399906158, + "learning_rate": 8e-05, + "epoch": 0.6428571428571429, + "step": 243 + }, + { + "loss": 0.030118469148874283, + "grad_norm": 0.0833863765001297, + "learning_rate": 7.941176470588235e-05, + "epoch": 0.6455026455026455, + "step": 244 + }, + { + "loss": 0.015584684908390045, + "grad_norm": 0.0630115196108818, + "learning_rate": 7.882352941176471e-05, + "epoch": 0.6481481481481481, + "step": 245 + }, + { + "loss": 0.024866245687007904, + "grad_norm": 0.0754900649189949, + "learning_rate": 7.823529411764707e-05, + "epoch": 0.6507936507936508, + "step": 246 + }, + { + "loss": 0.02521335333585739, + "grad_norm": 0.09214677661657333, + "learning_rate": 7.764705882352942e-05, + "epoch": 0.6534391534391535, + "step": 247 + }, + { + "loss": 0.02567514404654503, + "grad_norm": 0.07616355270147324, + "learning_rate": 7.705882352941177e-05, + "epoch": 0.656084656084656, + "step": 248 + }, + { + "loss": 0.03087168186903, + "grad_norm": 0.10812173038721085, + "learning_rate": 7.647058823529411e-05, + "epoch": 0.6587301587301587, + "step": 249 + }, + { + "loss": 0.02886301279067993, + "grad_norm": 0.07225628942251205, + "learning_rate": 7.588235294117648e-05, + "epoch": 0.6613756613756614, + "step": 250 + }, + { + "loss": 0.02838725596666336, + "grad_norm": 0.08968020230531693, + "learning_rate": 7.529411764705883e-05, + "epoch": 0.6640211640211641, + "step": 251 + }, + { + "loss": 0.0240425243973732, + "grad_norm": 0.1066119521856308, + "learning_rate": 7.470588235294118e-05, + "epoch": 0.6666666666666666, + "step": 252 + }, + { + "loss": 0.020799003541469574, + "grad_norm": 0.07908853143453598, + "learning_rate": 7.411764705882354e-05, + "epoch": 0.6693121693121693, + "step": 253 + }, + { + "loss": 0.03212092071771622, + "grad_norm": 0.08067328482866287, + "learning_rate": 7.352941176470589e-05, + "epoch": 0.671957671957672, + "step": 254 + }, + { + "loss": 0.02562413364648819, + "grad_norm": 0.09752342849969864, + "learning_rate": 7.294117647058823e-05, + "epoch": 0.6746031746031746, + "step": 255 + }, + { + "loss": 0.01694977842271328, + "grad_norm": 0.07102340459823608, + "learning_rate": 7.23529411764706e-05, + "epoch": 0.6772486772486772, + "step": 256 + }, + { + "loss": 0.02575928345322609, + "grad_norm": 0.07671815156936646, + "learning_rate": 7.176470588235295e-05, + "epoch": 0.6798941798941799, + "step": 257 + }, + { + "loss": 0.021748626604676247, + "grad_norm": 0.1419815868139267, + "learning_rate": 7.11764705882353e-05, + "epoch": 0.6825396825396826, + "step": 258 + }, + { + "loss": 0.02359670028090477, + "grad_norm": 0.10793975740671158, + "learning_rate": 7.058823529411765e-05, + "epoch": 0.6851851851851852, + "step": 259 + }, + { + "loss": 0.020240038633346558, + "grad_norm": 0.10104779154062271, + "learning_rate": 7e-05, + "epoch": 0.6878306878306878, + "step": 260 + }, + { + "loss": 0.03007177822291851, + "grad_norm": 0.09232339262962341, + "learning_rate": 6.941176470588236e-05, + "epoch": 0.6904761904761905, + "step": 261 + }, + { + "loss": 0.02441459335386753, + "grad_norm": 0.060809917747974396, + "learning_rate": 6.882352941176471e-05, + "epoch": 0.6931216931216931, + "step": 262 + }, + { + "loss": 0.02289595827460289, + "grad_norm": 0.07218184322118759, + "learning_rate": 6.823529411764707e-05, + "epoch": 0.6957671957671958, + "step": 263 + }, + { + "loss": 0.02958938293159008, + "grad_norm": 0.09035782516002655, + "learning_rate": 6.764705882352942e-05, + "epoch": 0.6984126984126984, + "step": 264 + }, + { + "loss": 0.028876766562461853, + "grad_norm": 0.08335528522729874, + "learning_rate": 6.705882352941176e-05, + "epoch": 0.701058201058201, + "step": 265 + }, + { + "loss": 0.022992007434368134, + "grad_norm": 0.06112835556268692, + "learning_rate": 6.647058823529411e-05, + "epoch": 0.7037037037037037, + "step": 266 + }, + { + "loss": 0.027839267626404762, + "grad_norm": 0.09583422541618347, + "learning_rate": 6.588235294117648e-05, + "epoch": 0.7063492063492064, + "step": 267 + }, + { + "loss": 0.03310278058052063, + "grad_norm": 0.10437622666358948, + "learning_rate": 6.529411764705883e-05, + "epoch": 0.708994708994709, + "step": 268 + }, + { + "loss": 0.02412830851972103, + "grad_norm": 0.05979550629854202, + "learning_rate": 6.470588235294118e-05, + "epoch": 0.7116402116402116, + "step": 269 + }, + { + "loss": 0.026769282296299934, + "grad_norm": 0.057857904583215714, + "learning_rate": 6.411764705882354e-05, + "epoch": 0.7142857142857143, + "step": 270 + }, + { + "loss": 0.01822183094918728, + "grad_norm": 0.0795726403594017, + "learning_rate": 6.352941176470588e-05, + "epoch": 0.716931216931217, + "step": 271 + }, + { + "loss": 0.03175610303878784, + "grad_norm": 0.11597180366516113, + "learning_rate": 6.294117647058824e-05, + "epoch": 0.7195767195767195, + "step": 272 + }, + { + "loss": 0.02406914159655571, + "grad_norm": 0.12822823226451874, + "learning_rate": 6.23529411764706e-05, + "epoch": 0.7222222222222222, + "step": 273 + }, + { + "loss": 0.017685284838080406, + "grad_norm": 0.11681342869997025, + "learning_rate": 6.176470588235295e-05, + "epoch": 0.7248677248677249, + "step": 274 + }, + { + "loss": 0.02279685251414776, + "grad_norm": 0.06948421150445938, + "learning_rate": 6.11764705882353e-05, + "epoch": 0.7275132275132276, + "step": 275 + }, + { + "loss": 0.032588277012109756, + "grad_norm": 0.10276354104280472, + "learning_rate": 6.058823529411765e-05, + "epoch": 0.7301587301587301, + "step": 276 + }, + { + "loss": 0.02961578778922558, + "grad_norm": 0.10721025615930557, + "learning_rate": 6e-05, + "epoch": 0.7328042328042328, + "step": 277 + }, + { + "loss": 0.02747366949915886, + "grad_norm": 0.08410617709159851, + "learning_rate": 5.9411764705882355e-05, + "epoch": 0.7354497354497355, + "step": 278 + }, + { + "loss": 0.02593173459172249, + "grad_norm": 0.0806620791554451, + "learning_rate": 5.882352941176471e-05, + "epoch": 0.7380952380952381, + "step": 279 + }, + { + "loss": 0.02764303609728813, + "grad_norm": 0.06915932148694992, + "learning_rate": 5.823529411764707e-05, + "epoch": 0.7407407407407407, + "step": 280 + }, + { + "loss": 0.024347776547074318, + "grad_norm": 0.06709478050470352, + "learning_rate": 5.764705882352941e-05, + "epoch": 0.7433862433862434, + "step": 281 + }, + { + "loss": 0.02141982689499855, + "grad_norm": 0.053211960941553116, + "learning_rate": 5.7058823529411766e-05, + "epoch": 0.746031746031746, + "step": 282 + }, + { + "loss": 0.02252194657921791, + "grad_norm": 0.06790946424007416, + "learning_rate": 5.647058823529412e-05, + "epoch": 0.7486772486772487, + "step": 283 + }, + { + "loss": 0.01945466734468937, + "grad_norm": 0.08224959671497345, + "learning_rate": 5.588235294117647e-05, + "epoch": 0.7513227513227513, + "step": 284 + }, + { + "loss": 0.032275885343551636, + "grad_norm": 0.09265672415494919, + "learning_rate": 5.529411764705883e-05, + "epoch": 0.753968253968254, + "step": 285 + }, + { + "loss": 0.027079608291387558, + "grad_norm": 0.07285762578248978, + "learning_rate": 5.4705882352941185e-05, + "epoch": 0.7566137566137566, + "step": 286 + }, + { + "loss": 0.02384945936501026, + "grad_norm": 0.05742108076810837, + "learning_rate": 5.411764705882353e-05, + "epoch": 0.7592592592592593, + "step": 287 + }, + { + "loss": 0.02898704633116722, + "grad_norm": 0.11136175692081451, + "learning_rate": 5.3529411764705884e-05, + "epoch": 0.7619047619047619, + "step": 288 + }, + { + "loss": 0.03049132414162159, + "grad_norm": 0.09560064971446991, + "learning_rate": 5.294117647058824e-05, + "epoch": 0.7645502645502645, + "step": 289 + }, + { + "loss": 0.024453597143292427, + "grad_norm": 0.062173303216695786, + "learning_rate": 5.235294117647059e-05, + "epoch": 0.7671957671957672, + "step": 290 + }, + { + "loss": 0.0318286158144474, + "grad_norm": 0.0988180935382843, + "learning_rate": 5.176470588235295e-05, + "epoch": 0.7698412698412699, + "step": 291 + }, + { + "loss": 0.02699001133441925, + "grad_norm": 0.0626835897564888, + "learning_rate": 5.117647058823529e-05, + "epoch": 0.7724867724867724, + "step": 292 + }, + { + "loss": 0.023896772414445877, + "grad_norm": 0.07981280982494354, + "learning_rate": 5.058823529411765e-05, + "epoch": 0.7751322751322751, + "step": 293 + }, + { + "loss": 0.024391846731305122, + "grad_norm": 0.07893257588148117, + "learning_rate": 5e-05, + "epoch": 0.7777777777777778, + "step": 294 + }, + { + "loss": 0.025584066286683083, + "grad_norm": 0.06932593882083893, + "learning_rate": 4.9411764705882355e-05, + "epoch": 0.7804232804232805, + "step": 295 + }, + { + "loss": 0.0220668762922287, + "grad_norm": 0.07785957306623459, + "learning_rate": 4.882352941176471e-05, + "epoch": 0.783068783068783, + "step": 296 + }, + { + "loss": 0.020017938688397408, + "grad_norm": 0.06624335050582886, + "learning_rate": 4.823529411764706e-05, + "epoch": 0.7857142857142857, + "step": 297 + }, + { + "loss": 0.02506105974316597, + "grad_norm": 0.0832471251487732, + "learning_rate": 4.7647058823529414e-05, + "epoch": 0.7883597883597884, + "step": 298 + }, + { + "loss": 0.017597489058971405, + "grad_norm": 0.06540657579898834, + "learning_rate": 4.705882352941177e-05, + "epoch": 0.791005291005291, + "step": 299 + }, + { + "loss": 0.0298212431371212, + "grad_norm": 0.15526005625724792, + "learning_rate": 4.647058823529412e-05, + "epoch": 0.7936507936507936, + "step": 300 + }, + { + "loss": 0.023575644940137863, + "grad_norm": 0.10094427317380905, + "learning_rate": 4.588235294117647e-05, + "epoch": 0.7962962962962963, + "step": 301 + }, + { + "loss": 0.02380991168320179, + "grad_norm": 0.08192069083452225, + "learning_rate": 4.5294117647058826e-05, + "epoch": 0.798941798941799, + "step": 302 + }, + { + "loss": 0.01674514263868332, + "grad_norm": 0.0720907524228096, + "learning_rate": 4.470588235294118e-05, + "epoch": 0.8015873015873016, + "step": 303 + }, + { + "loss": 0.018333733081817627, + "grad_norm": 0.058165185153484344, + "learning_rate": 4.411764705882353e-05, + "epoch": 0.8042328042328042, + "step": 304 + }, + { + "loss": 0.026520205661654472, + "grad_norm": 0.09807229042053223, + "learning_rate": 4.3529411764705885e-05, + "epoch": 0.8068783068783069, + "step": 305 + }, + { + "loss": 0.028179757297039032, + "grad_norm": 0.08209870010614395, + "learning_rate": 4.294117647058823e-05, + "epoch": 0.8095238095238095, + "step": 306 + }, + { + "loss": 0.020067555829882622, + "grad_norm": 0.08082698285579681, + "learning_rate": 4.235294117647059e-05, + "epoch": 0.8121693121693122, + "step": 307 + }, + { + "loss": 0.02571108378469944, + "grad_norm": 0.0704454705119133, + "learning_rate": 4.1764705882352944e-05, + "epoch": 0.8148148148148148, + "step": 308 + }, + { + "loss": 0.030464062467217445, + "grad_norm": 0.12649419903755188, + "learning_rate": 4.11764705882353e-05, + "epoch": 0.8174603174603174, + "step": 309 + }, + { + "loss": 0.029247839003801346, + "grad_norm": 0.0701553225517273, + "learning_rate": 4.058823529411765e-05, + "epoch": 0.8201058201058201, + "step": 310 + }, + { + "loss": 0.019865376874804497, + "grad_norm": 0.061975978314876556, + "learning_rate": 4e-05, + "epoch": 0.8227513227513228, + "step": 311 + }, + { + "loss": 0.025799460709095, + "grad_norm": 0.07122108340263367, + "learning_rate": 3.9411764705882356e-05, + "epoch": 0.8253968253968254, + "step": 312 + }, + { + "loss": 0.02584882080554962, + "grad_norm": 0.0794585570693016, + "learning_rate": 3.882352941176471e-05, + "epoch": 0.828042328042328, + "step": 313 + }, + { + "loss": 0.016808034852147102, + "grad_norm": 0.07829529792070389, + "learning_rate": 3.8235294117647055e-05, + "epoch": 0.8306878306878307, + "step": 314 + }, + { + "loss": 0.029843248426914215, + "grad_norm": 0.10015936195850372, + "learning_rate": 3.7647058823529415e-05, + "epoch": 0.8333333333333334, + "step": 315 + }, + { + "loss": 0.0207672156393528, + "grad_norm": 0.08752724528312683, + "learning_rate": 3.705882352941177e-05, + "epoch": 0.8359788359788359, + "step": 316 + }, + { + "loss": 0.025986317545175552, + "grad_norm": 0.07568460702896118, + "learning_rate": 3.6470588235294114e-05, + "epoch": 0.8386243386243386, + "step": 317 + }, + { + "loss": 0.03166591376066208, + "grad_norm": 0.10557642579078674, + "learning_rate": 3.5882352941176474e-05, + "epoch": 0.8412698412698413, + "step": 318 + }, + { + "loss": 0.027180485427379608, + "grad_norm": 0.0882193073630333, + "learning_rate": 3.529411764705883e-05, + "epoch": 0.843915343915344, + "step": 319 + }, + { + "loss": 0.025324862450361252, + "grad_norm": 0.10279812663793564, + "learning_rate": 3.470588235294118e-05, + "epoch": 0.8465608465608465, + "step": 320 + }, + { + "loss": 0.031235653907060623, + "grad_norm": 0.08359183371067047, + "learning_rate": 3.411764705882353e-05, + "epoch": 0.8492063492063492, + "step": 321 + }, + { + "loss": 0.028402645140886307, + "grad_norm": 0.06786882132291794, + "learning_rate": 3.352941176470588e-05, + "epoch": 0.8518518518518519, + "step": 322 + }, + { + "loss": 0.024368081241846085, + "grad_norm": 0.09749054163694382, + "learning_rate": 3.294117647058824e-05, + "epoch": 0.8544973544973545, + "step": 323 + }, + { + "loss": 0.029769334942102432, + "grad_norm": 0.06912931054830551, + "learning_rate": 3.235294117647059e-05, + "epoch": 0.8571428571428571, + "step": 324 + }, + { + "loss": 0.027555279433727264, + "grad_norm": 0.07546117901802063, + "learning_rate": 3.176470588235294e-05, + "epoch": 0.8597883597883598, + "step": 325 + }, + { + "loss": 0.03135411813855171, + "grad_norm": 0.08951126784086227, + "learning_rate": 3.11764705882353e-05, + "epoch": 0.8624338624338624, + "step": 326 + }, + { + "loss": 0.018115023151040077, + "grad_norm": 0.08512236922979355, + "learning_rate": 3.058823529411765e-05, + "epoch": 0.8650793650793651, + "step": 327 + }, + { + "loss": 0.024688314646482468, + "grad_norm": 0.08400000631809235, + "learning_rate": 3e-05, + "epoch": 0.8677248677248677, + "step": 328 + }, + { + "loss": 0.025533631443977356, + "grad_norm": 0.06805701553821564, + "learning_rate": 2.9411764705882354e-05, + "epoch": 0.8703703703703703, + "step": 329 + }, + { + "loss": 0.02600039541721344, + "grad_norm": 0.08600405603647232, + "learning_rate": 2.8823529411764703e-05, + "epoch": 0.873015873015873, + "step": 330 + }, + { + "loss": 0.0179967749863863, + "grad_norm": 0.07160481810569763, + "learning_rate": 2.823529411764706e-05, + "epoch": 0.8756613756613757, + "step": 331 + }, + { + "loss": 0.025588110089302063, + "grad_norm": 0.07811455428600311, + "learning_rate": 2.7647058823529416e-05, + "epoch": 0.8783068783068783, + "step": 332 + }, + { + "loss": 0.024966120719909668, + "grad_norm": 0.07041554898023605, + "learning_rate": 2.7058823529411766e-05, + "epoch": 0.8809523809523809, + "step": 333 + }, + { + "loss": 0.02608634904026985, + "grad_norm": 0.07744963467121124, + "learning_rate": 2.647058823529412e-05, + "epoch": 0.8835978835978836, + "step": 334 + }, + { + "loss": 0.024391014128923416, + "grad_norm": 0.07343604415655136, + "learning_rate": 2.5882352941176475e-05, + "epoch": 0.8862433862433863, + "step": 335 + }, + { + "loss": 0.015595385804772377, + "grad_norm": 0.10205741226673126, + "learning_rate": 2.5294117647058825e-05, + "epoch": 0.8888888888888888, + "step": 336 + }, + { + "loss": 0.025536613538861275, + "grad_norm": 0.08257130533456802, + "learning_rate": 2.4705882352941178e-05, + "epoch": 0.8915343915343915, + "step": 337 + }, + { + "loss": 0.031951554119586945, + "grad_norm": 0.1315038800239563, + "learning_rate": 2.411764705882353e-05, + "epoch": 0.8941798941798942, + "step": 338 + }, + { + "loss": 0.023610807955265045, + "grad_norm": 0.08411096036434174, + "learning_rate": 2.3529411764705884e-05, + "epoch": 0.8968253968253969, + "step": 339 + }, + { + "loss": 0.030541151762008667, + "grad_norm": 0.07679664343595505, + "learning_rate": 2.2941176470588237e-05, + "epoch": 0.8994708994708994, + "step": 340 + }, + { + "loss": 0.02696535736322403, + "grad_norm": 0.07304323464632034, + "learning_rate": 2.235294117647059e-05, + "epoch": 0.9021164021164021, + "step": 341 + }, + { + "loss": 0.02784024551510811, + "grad_norm": 0.061864130198955536, + "learning_rate": 2.1764705882352943e-05, + "epoch": 0.9047619047619048, + "step": 342 + }, + { + "loss": 0.025248851627111435, + "grad_norm": 0.06673755496740341, + "learning_rate": 2.1176470588235296e-05, + "epoch": 0.9074074074074074, + "step": 343 + }, + { + "loss": 0.029280394315719604, + "grad_norm": 0.07668192684650421, + "learning_rate": 2.058823529411765e-05, + "epoch": 0.91005291005291, + "step": 344 + }, + { + "loss": 0.02605779841542244, + "grad_norm": 0.07531134784221649, + "learning_rate": 2e-05, + "epoch": 0.9126984126984127, + "step": 345 + }, + { + "loss": 0.028157757595181465, + "grad_norm": 0.08565571904182434, + "learning_rate": 1.9411764705882355e-05, + "epoch": 0.9153439153439153, + "step": 346 + }, + { + "loss": 0.025131918489933014, + "grad_norm": 0.07180029898881912, + "learning_rate": 1.8823529411764708e-05, + "epoch": 0.917989417989418, + "step": 347 + }, + { + "loss": 0.02796267159283161, + "grad_norm": 0.07056324183940887, + "learning_rate": 1.8235294117647057e-05, + "epoch": 0.9206349206349206, + "step": 348 + }, + { + "loss": 0.025395592674613, + "grad_norm": 0.08292558044195175, + "learning_rate": 1.7647058823529414e-05, + "epoch": 0.9232804232804233, + "step": 349 + }, + { + "loss": 0.028561469167470932, + "grad_norm": 0.07555428147315979, + "learning_rate": 1.7058823529411767e-05, + "epoch": 0.9259259259259259, + "step": 350 + }, + { + "loss": 0.020762892439961433, + "grad_norm": 0.06799963861703873, + "learning_rate": 1.647058823529412e-05, + "epoch": 0.9285714285714286, + "step": 351 + }, + { + "loss": 0.014401258900761604, + "grad_norm": 0.09109848737716675, + "learning_rate": 1.588235294117647e-05, + "epoch": 0.9312169312169312, + "step": 352 + }, + { + "loss": 0.02667010948061943, + "grad_norm": 0.07757920771837234, + "learning_rate": 1.5294117647058826e-05, + "epoch": 0.9338624338624338, + "step": 353 + }, + { + "loss": 0.023868650197982788, + "grad_norm": 0.07955507934093475, + "learning_rate": 1.4705882352941177e-05, + "epoch": 0.9365079365079365, + "step": 354 + }, + { + "loss": 0.017540596425533295, + "grad_norm": 0.07310300320386887, + "learning_rate": 1.411764705882353e-05, + "epoch": 0.9391534391534392, + "step": 355 + }, + { + "loss": 0.026370886713266373, + "grad_norm": 0.06979277729988098, + "learning_rate": 1.3529411764705883e-05, + "epoch": 0.9417989417989417, + "step": 356 + }, + { + "loss": 0.018387794494628906, + "grad_norm": 0.07074704021215439, + "learning_rate": 1.2941176470588238e-05, + "epoch": 0.9444444444444444, + "step": 357 + }, + { + "loss": 0.022234005853533745, + "grad_norm": 0.07400532811880112, + "learning_rate": 1.2352941176470589e-05, + "epoch": 0.9470899470899471, + "step": 358 + }, + { + "loss": 0.022929485887289047, + "grad_norm": 0.06865154951810837, + "learning_rate": 1.1764705882352942e-05, + "epoch": 0.9497354497354498, + "step": 359 + }, + { + "loss": 0.014135655015707016, + "grad_norm": 0.07323960214853287, + "learning_rate": 1.1176470588235295e-05, + "epoch": 0.9523809523809523, + "step": 360 + }, + { + "loss": 0.022620154544711113, + "grad_norm": 0.07920295000076294, + "learning_rate": 1.0588235294117648e-05, + "epoch": 0.955026455026455, + "step": 361 + }, + { + "loss": 0.02163829654455185, + "grad_norm": 0.07833685725927353, + "learning_rate": 1e-05, + "epoch": 0.9576719576719577, + "step": 362 + }, + { + "loss": 0.024631310254335403, + "grad_norm": 0.07127346098423004, + "learning_rate": 9.411764705882354e-06, + "epoch": 0.9603174603174603, + "step": 363 + }, + { + "loss": 0.02476324699819088, + "grad_norm": 0.08091171830892563, + "learning_rate": 8.823529411764707e-06, + "epoch": 0.9629629629629629, + "step": 364 + }, + { + "loss": 0.028194960206747055, + "grad_norm": 0.07320816069841385, + "learning_rate": 8.23529411764706e-06, + "epoch": 0.9656084656084656, + "step": 365 + }, + { + "loss": 0.021045658737421036, + "grad_norm": 0.05777011066675186, + "learning_rate": 7.647058823529413e-06, + "epoch": 0.9682539682539683, + "step": 366 + }, + { + "loss": 0.01954471692442894, + "grad_norm": 0.05877400189638138, + "learning_rate": 7.058823529411765e-06, + "epoch": 0.9708994708994709, + "step": 367 + }, + { + "loss": 0.022302869707345963, + "grad_norm": 0.08140099048614502, + "learning_rate": 6.470588235294119e-06, + "epoch": 0.9735449735449735, + "step": 368 + }, + { + "loss": 0.028763171285390854, + "grad_norm": 0.07870705425739288, + "learning_rate": 5.882352941176471e-06, + "epoch": 0.9761904761904762, + "step": 369 + }, + { + "loss": 0.02230384200811386, + "grad_norm": 0.07137063145637512, + "learning_rate": 5.294117647058824e-06, + "epoch": 0.9788359788359788, + "step": 370 + }, + { + "loss": 0.029754120856523514, + "grad_norm": 0.08352145552635193, + "learning_rate": 4.705882352941177e-06, + "epoch": 0.9814814814814815, + "step": 371 + }, + { + "loss": 0.02422209642827511, + "grad_norm": 0.11225514113903046, + "learning_rate": 4.11764705882353e-06, + "epoch": 0.9841269841269841, + "step": 372 + }, + { + "loss": 0.02646939642727375, + "grad_norm": 0.06159619614481926, + "learning_rate": 3.5294117647058825e-06, + "epoch": 0.9867724867724867, + "step": 373 + }, + { + "loss": 0.025930095463991165, + "grad_norm": 0.07783936709165573, + "learning_rate": 2.9411764705882355e-06, + "epoch": 0.9894179894179894, + "step": 374 + }, + { + "loss": 0.02609175071120262, + "grad_norm": 0.07969409227371216, + "learning_rate": 2.3529411764705885e-06, + "epoch": 0.9920634920634921, + "step": 375 + }, + { + "loss": 0.029602840542793274, + "grad_norm": 0.07719960063695908, + "learning_rate": 1.7647058823529412e-06, + "epoch": 0.9947089947089947, + "step": 376 + }, + { + "loss": 0.02769250050187111, + "grad_norm": 0.08469251543283463, + "learning_rate": 1.1764705882352942e-06, + "epoch": 0.9973544973544973, + "step": 377 + }, + { + "loss": 0.01469414122402668, + "grad_norm": 0.08339664340019226, + "learning_rate": 5.882352941176471e-07, + "epoch": 1.0, + "step": 378 + }, + { + "train_runtime": 588.9025, + "train_samples_per_second": 5.135, + "train_steps_per_second": 0.642, + "total_flos": 1.466247702455808e+16, + "train_loss": 0.16477010999535205, + "epoch": 1.0, + "step": 378 + } + ] +} \ No newline at end of file