Upload folder using huggingface_hub
Browse files- fisher_dict_fp32/llama-2-7b.fisher_dict.c4.length-1024.nsamples-10000.pth +3 -0
- ilp_data_bf16/llama-2-70b-1024.ilp.ranks-64.data-False.pth +3 -0
- ilp_data_bf16/llama-2-70b-1024.ilp.ranks-64.data-True.pth +3 -0
- ilp_data_bf16/llama-2-70b-1024.ilp.ranks-None.data-False.pth +3 -0
- ilp_data_bf16/llama-2-70b-1024.ilp.ranks-None.data-True.pth +3 -0
- ilp_data_fp32/llama-2-7b-1024.ilp.ranks-64.data-False.pth +3 -0
- ilp_data_fp32/llama-2-7b-1024.ilp.ranks-64.data-True.pth +3 -0
- ilp_data_fp32/llama-2-7b-1024.ilp.ranks-None.data-False.pth +3 -0
- ilp_data_fp32/llama-2-7b-1024.ilp.ranks-None.data-True.pth +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/README.md +59 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/adapter_config.json +26 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/adapter_model.bin +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/all_results.json +22 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/eval_results.json +17 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/full_model.pth +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/runs/Oct24_22-25-51_4ce0df614d10/events.out.tfevents.1698200561.4ce0df614d10 +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/runs/Oct24_22-25-51_4ce0df614d10/events.out.tfevents.1698629160.4ce0df614d10 +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/runs/Oct24_22-25-51_4ce0df614d10/events.out.tfevents.1698636783.4ce0df614d10 +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/special_tokens_map.json +23 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/tokenizer.model +3 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/tokenizer_config.json +42 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/train_results.json +8 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/trainer_state.json +2284 -0
- output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/training_args.bin +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/README.md +59 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/adapter_config.json +26 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/adapter_model.bin +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/all_results.json +22 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/eval_results.json +17 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/full_model.pth +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/runs/Oct23_19-16-28_f39a6c538c5a/events.out.tfevents.1698095130.f39a6c538c5a +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/runs/Oct23_19-16-28_f39a6c538c5a/events.out.tfevents.1698215269.f39a6c538c5a +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/runs/Oct23_19-16-28_f39a6c538c5a/events.out.tfevents.1698217298.f39a6c538c5a +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/special_tokens_map.json +23 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/tokenizer.model +3 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/tokenizer_config.json +42 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/train_results.json +8 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/trainer_state.json +2284 -0
- output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/training_args.bin +3 -0
fisher_dict_fp32/llama-2-7b.fisher_dict.c4.length-1024.nsamples-10000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f54767e95f67a57b8cc356ec6ed2934ba9af380252c3155ed38273f7fee060c5
|
| 3 |
+
size 25904117267
|
ilp_data_bf16/llama-2-70b-1024.ilp.ranks-64.data-False.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec8881efb1f0e8a4d210c21a54b9ddc1b2cac582597dc661c57340a4d14443e1
|
| 3 |
+
size 2093977
|
ilp_data_bf16/llama-2-70b-1024.ilp.ranks-64.data-True.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c62ce515c7e71667af391072df5f78a8bd9e26527e5e96afde95651093ba9de
|
| 3 |
+
size 2094479
|
ilp_data_bf16/llama-2-70b-1024.ilp.ranks-None.data-False.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:291c34fcffe111515c455da5a98f296fa98527fd63c0b46379f48873f3b2e755
|
| 3 |
+
size 2093997
|
ilp_data_bf16/llama-2-70b-1024.ilp.ranks-None.data-True.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c74dcf7a37e6ee5897ba1684aa519470c85c03706bc26df8ff16bd198cd1dd14
|
| 3 |
+
size 2094499
|
ilp_data_fp32/llama-2-7b-1024.ilp.ranks-64.data-False.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefe2c7469e79f7eb77fc3fa2f09fe30f7bc102e2c8e5d51b5006eec54f9bf8d
|
| 3 |
+
size 844815
|
ilp_data_fp32/llama-2-7b-1024.ilp.ranks-64.data-True.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b05a81dea32e6b8e1da5d0e3dfd8eec9168dfedeb1fc1bfa1c840fabb3877aed
|
| 3 |
+
size 845253
|
ilp_data_fp32/llama-2-7b-1024.ilp.ranks-None.data-False.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a334437b6e41f5c485276f68e50e1fa27b3f250d6943fc1a43b5d04285811fe7
|
| 3 |
+
size 844835
|
ilp_data_fp32/llama-2-7b-1024.ilp.ranks-None.data-True.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eff4c09c314ecbb8e29ed6bbcf76401f4a944775c71aaadd24cce7c8a8ef5b99
|
| 3 |
+
size 845273
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: /export/share3/experiments/20230731/llama-2/Llama-2-70b-hf
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- c4-wiki-large
|
| 7 |
+
model-index:
|
| 8 |
+
- name: output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [/export/share3/experiments/20230731/llama-2/Llama-2-70b-hf](https://huggingface.co//export/share3/experiments/20230731/llama-2/Llama-2-70b-hf) on the c4-wiki-large dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 2
|
| 38 |
+
- eval_batch_size: 2
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- num_devices: 4
|
| 42 |
+
- gradient_accumulation_steps: 64
|
| 43 |
+
- total_train_batch_size: 512
|
| 44 |
+
- total_eval_batch_size: 8
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
+
- num_epochs: 1.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 4.34.1
|
| 57 |
+
- Pytorch 2.0.0
|
| 58 |
+
- Datasets 2.14.6
|
| 59 |
+
- Tokenizers 0.14.1
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "/export/share3/experiments/20230731/llama-2/Llama-2-70b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"v_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"gate_proj",
|
| 22 |
+
"down_proj",
|
| 23 |
+
"up_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bed66381c13ac7ab8d0c2213256c5ba740332eedce00181c22f5efcb60f3381
|
| 3 |
+
size 3313905157
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"c4_perplexity": 6.112377705965592,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"eval_c4_accuracy": 0.5845445807378373,
|
| 5 |
+
"eval_c4_loss": 1.8103158473968506,
|
| 6 |
+
"eval_c4_runtime": 8526.3486,
|
| 7 |
+
"eval_c4_samples": 11927,
|
| 8 |
+
"eval_c4_samples_per_second": 1.399,
|
| 9 |
+
"eval_c4_steps_per_second": 0.175,
|
| 10 |
+
"eval_wikitext_accuracy": 0.67864226814439,
|
| 11 |
+
"eval_wikitext_loss": 1.2958391904830933,
|
| 12 |
+
"eval_wikitext_runtime": 120.5752,
|
| 13 |
+
"eval_wikitext_samples": 166,
|
| 14 |
+
"eval_wikitext_samples_per_second": 1.377,
|
| 15 |
+
"eval_wikitext_steps_per_second": 0.174,
|
| 16 |
+
"train_loss": 1.7981542252205513,
|
| 17 |
+
"train_runtime": 419993.6461,
|
| 18 |
+
"train_samples": 189709,
|
| 19 |
+
"train_samples_per_second": 0.452,
|
| 20 |
+
"train_steps_per_second": 0.001,
|
| 21 |
+
"wikitext_perplexity": 3.6540611411661965
|
| 22 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/eval_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"c4_perplexity": 6.112377705965592,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"eval_c4_accuracy": 0.5845445807378373,
|
| 5 |
+
"eval_c4_loss": 1.8103158473968506,
|
| 6 |
+
"eval_c4_runtime": 8526.3486,
|
| 7 |
+
"eval_c4_samples": 11927,
|
| 8 |
+
"eval_c4_samples_per_second": 1.399,
|
| 9 |
+
"eval_c4_steps_per_second": 0.175,
|
| 10 |
+
"eval_wikitext_accuracy": 0.67864226814439,
|
| 11 |
+
"eval_wikitext_loss": 1.2958391904830933,
|
| 12 |
+
"eval_wikitext_runtime": 120.5752,
|
| 13 |
+
"eval_wikitext_samples": 166,
|
| 14 |
+
"eval_wikitext_samples_per_second": 1.377,
|
| 15 |
+
"eval_wikitext_steps_per_second": 0.174,
|
| 16 |
+
"wikitext_perplexity": 3.6540611411661965
|
| 17 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/full_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:829afa280c2d458ffc225df41187f65a4d6f876a86e4435a564fe025263a4c60
|
| 3 |
+
size 28948121889
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/runs/Oct24_22-25-51_4ce0df614d10/events.out.tfevents.1698200561.4ce0df614d10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda0aec0ee23339a659ab81073eeb357a32f260d2916ea8502e255df33923cef
|
| 3 |
+
size 63696
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/runs/Oct24_22-25-51_4ce0df614d10/events.out.tfevents.1698629160.4ce0df614d10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:677a4e74be39d7b0762651d4630eb33119504862b38ffd1db7ea7b756cf4b644
|
| 3 |
+
size 5543
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/runs/Oct24_22-25-51_4ce0df614d10/events.out.tfevents.1698636783.4ce0df614d10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1330e7e6b0ca0019f74f93f2bcdc0c9aef0acda17ac61d647d3028878d9c412
|
| 3 |
+
size 4610
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": null,
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": true
|
| 42 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.7981542252205513,
|
| 4 |
+
"train_runtime": 419993.6461,
|
| 5 |
+
"train_samples": 189709,
|
| 6 |
+
"train_samples_per_second": 0.452,
|
| 7 |
+
"train_steps_per_second": 0.001
|
| 8 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/trainer_state.json
ADDED
|
@@ -0,0 +1,2284 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9985662477861179,
|
| 5 |
+
"eval_steps": 126,
|
| 6 |
+
"global_step": 370,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 14 |
+
"loss": 1.8654,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 20 |
+
"loss": 1.9132,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 5e-06,
|
| 26 |
+
"loss": 1.8729,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 6.666666666666667e-06,
|
| 32 |
+
"loss": 1.8985,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 8.333333333333334e-06,
|
| 38 |
+
"loss": 1.8958,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 1e-05,
|
| 44 |
+
"loss": 1.8868,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 50 |
+
"loss": 1.8814,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 56 |
+
"loss": 1.888,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02,
|
| 61 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 62 |
+
"loss": 1.8957,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 68 |
+
"loss": 1.8941,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 74 |
+
"loss": 1.8741,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 2e-05,
|
| 80 |
+
"loss": 1.8596,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 1.9999614964379037e-05,
|
| 86 |
+
"loss": 1.8766,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 1.9998459887166635e-05,
|
| 92 |
+
"loss": 1.8753,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 1.9996534857311967e-05,
|
| 98 |
+
"loss": 1.8185,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.04,
|
| 103 |
+
"learning_rate": 1.9993840023056045e-05,
|
| 104 |
+
"loss": 1.8419,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 1.9990375591920304e-05,
|
| 110 |
+
"loss": 1.8245,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.05,
|
| 115 |
+
"learning_rate": 1.9986141830690626e-05,
|
| 116 |
+
"loss": 1.8624,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"learning_rate": 1.9981139065396786e-05,
|
| 122 |
+
"loss": 1.8329,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05,
|
| 127 |
+
"learning_rate": 1.9975367681287358e-05,
|
| 128 |
+
"loss": 1.8462,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 1.9968828122800022e-05,
|
| 134 |
+
"loss": 1.813,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 1.9961520893527385e-05,
|
| 140 |
+
"loss": 1.8092,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.06,
|
| 145 |
+
"learning_rate": 1.995344655617815e-05,
|
| 146 |
+
"loss": 1.8213,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.06,
|
| 151 |
+
"learning_rate": 1.994460573253382e-05,
|
| 152 |
+
"loss": 1.8437,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 1.9934999103400797e-05,
|
| 158 |
+
"loss": 1.8192,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07,
|
| 163 |
+
"learning_rate": 1.9924627408557963e-05,
|
| 164 |
+
"loss": 1.8045,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.07,
|
| 169 |
+
"learning_rate": 1.9913491446699715e-05,
|
| 170 |
+
"loss": 1.8152,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 1.9901592075374447e-05,
|
| 176 |
+
"loss": 1.8075,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 1.988893021091853e-05,
|
| 182 |
+
"loss": 1.8075,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.08,
|
| 187 |
+
"learning_rate": 1.9875506828385723e-05,
|
| 188 |
+
"loss": 1.7901,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.08,
|
| 193 |
+
"learning_rate": 1.986132296147212e-05,
|
| 194 |
+
"loss": 1.8193,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.09,
|
| 199 |
+
"learning_rate": 1.9846379702436518e-05,
|
| 200 |
+
"loss": 1.7977,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.09,
|
| 205 |
+
"learning_rate": 1.9830678202016324e-05,
|
| 206 |
+
"loss": 1.8116,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.09,
|
| 211 |
+
"learning_rate": 1.981421966933893e-05,
|
| 212 |
+
"loss": 1.8342,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.09,
|
| 217 |
+
"learning_rate": 1.9797005371828603e-05,
|
| 218 |
+
"loss": 1.828,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 1.9779036635108892e-05,
|
| 224 |
+
"loss": 1.7899,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.1,
|
| 229 |
+
"learning_rate": 1.9760314842900537e-05,
|
| 230 |
+
"loss": 1.7773,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.1,
|
| 235 |
+
"learning_rate": 1.9740841436914917e-05,
|
| 236 |
+
"loss": 1.8178,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.11,
|
| 241 |
+
"learning_rate": 1.9720617916743022e-05,
|
| 242 |
+
"loss": 1.7967,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.11,
|
| 247 |
+
"learning_rate": 1.9699645839739987e-05,
|
| 248 |
+
"loss": 1.793,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.11,
|
| 253 |
+
"learning_rate": 1.9677926820905143e-05,
|
| 254 |
+
"loss": 1.8071,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.11,
|
| 259 |
+
"learning_rate": 1.9655462532757677e-05,
|
| 260 |
+
"loss": 1.8246,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 1.9632254705207813e-05,
|
| 266 |
+
"loss": 1.8121,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12,
|
| 271 |
+
"learning_rate": 1.9608305125423608e-05,
|
| 272 |
+
"loss": 1.8068,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.12,
|
| 277 |
+
"learning_rate": 1.958361563769333e-05,
|
| 278 |
+
"loss": 1.7871,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.12,
|
| 283 |
+
"learning_rate": 1.9558188143283425e-05,
|
| 284 |
+
"loss": 1.8013,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.13,
|
| 289 |
+
"learning_rate": 1.9532024600292115e-05,
|
| 290 |
+
"loss": 1.8208,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.13,
|
| 295 |
+
"learning_rate": 1.9505127023498603e-05,
|
| 296 |
+
"loss": 1.7894,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.13,
|
| 301 |
+
"learning_rate": 1.9477497484207922e-05,
|
| 302 |
+
"loss": 1.7994,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.13,
|
| 307 |
+
"learning_rate": 1.9449138110091444e-05,
|
| 308 |
+
"loss": 1.801,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.14,
|
| 313 |
+
"learning_rate": 1.9420051085023006e-05,
|
| 314 |
+
"loss": 1.8141,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.14,
|
| 319 |
+
"learning_rate": 1.9390238648910765e-05,
|
| 320 |
+
"loss": 1.789,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.14,
|
| 325 |
+
"learning_rate": 1.935970309752469e-05,
|
| 326 |
+
"loss": 1.7982,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.15,
|
| 331 |
+
"learning_rate": 1.932844678231977e-05,
|
| 332 |
+
"loss": 1.7779,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.15,
|
| 337 |
+
"learning_rate": 1.929647211025497e-05,
|
| 338 |
+
"loss": 1.7966,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.15,
|
| 343 |
+
"learning_rate": 1.9263781543607817e-05,
|
| 344 |
+
"loss": 1.805,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15,
|
| 349 |
+
"learning_rate": 1.923037759978484e-05,
|
| 350 |
+
"loss": 1.7965,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.16,
|
| 355 |
+
"learning_rate": 1.9196262851127695e-05,
|
| 356 |
+
"loss": 1.7868,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.16,
|
| 361 |
+
"learning_rate": 1.9161439924715063e-05,
|
| 362 |
+
"loss": 1.8089,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.16,
|
| 367 |
+
"learning_rate": 1.9125911502160365e-05,
|
| 368 |
+
"loss": 1.8203,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.16,
|
| 373 |
+
"learning_rate": 1.9089680319405252e-05,
|
| 374 |
+
"loss": 1.811,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.17,
|
| 379 |
+
"learning_rate": 1.905274916650891e-05,
|
| 380 |
+
"loss": 1.7755,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.17,
|
| 385 |
+
"learning_rate": 1.9015120887433215e-05,
|
| 386 |
+
"loss": 1.7942,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.17,
|
| 391 |
+
"learning_rate": 1.897679837982373e-05,
|
| 392 |
+
"loss": 1.8063,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.18,
|
| 397 |
+
"learning_rate": 1.8937784594786562e-05,
|
| 398 |
+
"loss": 1.7874,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.18,
|
| 403 |
+
"learning_rate": 1.8898082536661097e-05,
|
| 404 |
+
"loss": 1.8095,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.18,
|
| 409 |
+
"learning_rate": 1.885769526278865e-05,
|
| 410 |
+
"loss": 1.8095,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.18,
|
| 415 |
+
"learning_rate": 1.8816625883277044e-05,
|
| 416 |
+
"loss": 1.7955,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.19,
|
| 421 |
+
"learning_rate": 1.8774877560761082e-05,
|
| 422 |
+
"loss": 1.7961,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.19,
|
| 427 |
+
"learning_rate": 1.8732453510159025e-05,
|
| 428 |
+
"loss": 1.7876,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"learning_rate": 1.8689356998425007e-05,
|
| 434 |
+
"loss": 1.7957,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.19,
|
| 439 |
+
"learning_rate": 1.864559134429745e-05,
|
| 440 |
+
"loss": 1.7832,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.2,
|
| 445 |
+
"learning_rate": 1.8601159918043533e-05,
|
| 446 |
+
"loss": 1.814,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.2,
|
| 451 |
+
"learning_rate": 1.85560661411996e-05,
|
| 452 |
+
"loss": 1.8333,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.2,
|
| 457 |
+
"learning_rate": 1.8510313486307734e-05,
|
| 458 |
+
"loss": 1.8052,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.21,
|
| 463 |
+
"learning_rate": 1.846390547664831e-05,
|
| 464 |
+
"loss": 1.8252,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.21,
|
| 469 |
+
"learning_rate": 1.841684568596869e-05,
|
| 470 |
+
"loss": 1.8317,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"learning_rate": 1.836913773820802e-05,
|
| 476 |
+
"loss": 1.7911,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.21,
|
| 481 |
+
"learning_rate": 1.832078530721816e-05,
|
| 482 |
+
"loss": 1.8356,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.22,
|
| 487 |
+
"learning_rate": 1.8271792116480767e-05,
|
| 488 |
+
"loss": 1.8064,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.22,
|
| 493 |
+
"learning_rate": 1.8222161938820564e-05,
|
| 494 |
+
"loss": 1.7887,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.22,
|
| 499 |
+
"learning_rate": 1.8171898596114804e-05,
|
| 500 |
+
"loss": 1.8028,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.22,
|
| 505 |
+
"learning_rate": 1.8121005958998968e-05,
|
| 506 |
+
"loss": 1.8005,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.23,
|
| 511 |
+
"learning_rate": 1.8069487946568675e-05,
|
| 512 |
+
"loss": 1.8272,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"learning_rate": 1.801734852607791e-05,
|
| 518 |
+
"loss": 1.8085,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.23,
|
| 523 |
+
"learning_rate": 1.79645917126335e-05,
|
| 524 |
+
"loss": 1.7779,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.23,
|
| 529 |
+
"learning_rate": 1.7911221568885935e-05,
|
| 530 |
+
"loss": 1.7704,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.24,
|
| 535 |
+
"learning_rate": 1.7857242204716497e-05,
|
| 536 |
+
"loss": 1.7738,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.24,
|
| 541 |
+
"learning_rate": 1.780265777692079e-05,
|
| 542 |
+
"loss": 1.8085,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.24,
|
| 547 |
+
"learning_rate": 1.7747472488888622e-05,
|
| 548 |
+
"loss": 1.7766,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.25,
|
| 553 |
+
"learning_rate": 1.7691690590280325e-05,
|
| 554 |
+
"loss": 1.7903,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25,
|
| 559 |
+
"learning_rate": 1.763531637669949e-05,
|
| 560 |
+
"loss": 1.7867,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.25,
|
| 565 |
+
"learning_rate": 1.7578354189362183e-05,
|
| 566 |
+
"loss": 1.7898,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.25,
|
| 571 |
+
"learning_rate": 1.752080841476264e-05,
|
| 572 |
+
"loss": 1.8045,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.26,
|
| 577 |
+
"learning_rate": 1.7462683484335477e-05,
|
| 578 |
+
"loss": 1.8086,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.26,
|
| 583 |
+
"learning_rate": 1.7403983874114422e-05,
|
| 584 |
+
"loss": 1.7845,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.26,
|
| 589 |
+
"learning_rate": 1.734471410438765e-05,
|
| 590 |
+
"loss": 1.814,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.26,
|
| 595 |
+
"learning_rate": 1.728487873934969e-05,
|
| 596 |
+
"loss": 1.8026,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27,
|
| 601 |
+
"learning_rate": 1.7224482386749916e-05,
|
| 602 |
+
"loss": 1.7853,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.27,
|
| 607 |
+
"learning_rate": 1.7163529697537756e-05,
|
| 608 |
+
"loss": 1.7907,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.27,
|
| 613 |
+
"learning_rate": 1.7102025365504524e-05,
|
| 614 |
+
"loss": 1.7671,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.28,
|
| 619 |
+
"learning_rate": 1.7039974126921946e-05,
|
| 620 |
+
"loss": 1.809,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.28,
|
| 625 |
+
"learning_rate": 1.6977380760177467e-05,
|
| 626 |
+
"loss": 1.8166,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.28,
|
| 631 |
+
"learning_rate": 1.691425008540625e-05,
|
| 632 |
+
"loss": 1.816,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.28,
|
| 637 |
+
"learning_rate": 1.6850586964120005e-05,
|
| 638 |
+
"loss": 1.8057,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.29,
|
| 643 |
+
"learning_rate": 1.6786396298832622e-05,
|
| 644 |
+
"loss": 1.7852,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.29,
|
| 649 |
+
"learning_rate": 1.6721683032682637e-05,
|
| 650 |
+
"loss": 1.8114,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.29,
|
| 655 |
+
"learning_rate": 1.6656452149052568e-05,
|
| 656 |
+
"loss": 1.8076,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.29,
|
| 661 |
+
"learning_rate": 1.6590708671185176e-05,
|
| 662 |
+
"loss": 1.7977,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.3,
|
| 667 |
+
"learning_rate": 1.6524457661796626e-05,
|
| 668 |
+
"loss": 1.7939,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.3,
|
| 673 |
+
"learning_rate": 1.645770422268662e-05,
|
| 674 |
+
"loss": 1.7988,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3,
|
| 679 |
+
"learning_rate": 1.639045349434554e-05,
|
| 680 |
+
"loss": 1.8102,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3,
|
| 685 |
+
"learning_rate": 1.6322710655558577e-05,
|
| 686 |
+
"loss": 1.8057,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.31,
|
| 691 |
+
"learning_rate": 1.6254480923006924e-05,
|
| 692 |
+
"loss": 1.7842,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.31,
|
| 697 |
+
"learning_rate": 1.6185769550866073e-05,
|
| 698 |
+
"loss": 1.794,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.31,
|
| 703 |
+
"learning_rate": 1.6116581830401193e-05,
|
| 704 |
+
"loss": 1.7781,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.32,
|
| 709 |
+
"learning_rate": 1.6046923089559667e-05,
|
| 710 |
+
"loss": 1.8077,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.32,
|
| 715 |
+
"learning_rate": 1.5976798692560796e-05,
|
| 716 |
+
"loss": 1.7659,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.32,
|
| 721 |
+
"learning_rate": 1.5906214039482732e-05,
|
| 722 |
+
"loss": 1.7894,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.32,
|
| 727 |
+
"learning_rate": 1.5835174565846624e-05,
|
| 728 |
+
"loss": 1.7907,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.33,
|
| 733 |
+
"learning_rate": 1.576368574219804e-05,
|
| 734 |
+
"loss": 1.809,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.33,
|
| 739 |
+
"learning_rate": 1.5691753073685692e-05,
|
| 740 |
+
"loss": 1.7769,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.33,
|
| 745 |
+
"learning_rate": 1.561938209963753e-05,
|
| 746 |
+
"loss": 1.8067,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.33,
|
| 751 |
+
"learning_rate": 1.554657839313413e-05,
|
| 752 |
+
"loss": 1.7765,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.34,
|
| 757 |
+
"learning_rate": 1.5473347560579576e-05,
|
| 758 |
+
"loss": 1.7997,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.34,
|
| 763 |
+
"learning_rate": 1.539969524126967e-05,
|
| 764 |
+
"loss": 1.8253,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.34,
|
| 769 |
+
"eval_c4_accuracy": 0.5840351717861577,
|
| 770 |
+
"eval_c4_loss": 1.8130102157592773,
|
| 771 |
+
"eval_c4_runtime": 8541.4862,
|
| 772 |
+
"eval_c4_samples_per_second": 1.396,
|
| 773 |
+
"eval_c4_steps_per_second": 0.175,
|
| 774 |
+
"step": 126
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.34,
|
| 778 |
+
"eval_wikitext_accuracy": 0.675964237997422,
|
| 779 |
+
"eval_wikitext_loss": 1.3107627630233765,
|
| 780 |
+
"eval_wikitext_runtime": 119.5535,
|
| 781 |
+
"eval_wikitext_samples_per_second": 1.388,
|
| 782 |
+
"eval_wikitext_steps_per_second": 0.176,
|
| 783 |
+
"step": 126
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.34,
|
| 787 |
+
"learning_rate": 1.5325627106957715e-05,
|
| 788 |
+
"loss": 1.8007,
|
| 789 |
+
"step": 127
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.35,
|
| 793 |
+
"learning_rate": 1.5251148861417733e-05,
|
| 794 |
+
"loss": 1.7984,
|
| 795 |
+
"step": 128
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.35,
|
| 799 |
+
"learning_rate": 1.5176266240005225e-05,
|
| 800 |
+
"loss": 1.8106,
|
| 801 |
+
"step": 129
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.35,
|
| 805 |
+
"learning_rate": 1.5100985009215519e-05,
|
| 806 |
+
"loss": 1.769,
|
| 807 |
+
"step": 130
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.35,
|
| 811 |
+
"learning_rate": 1.5025310966239701e-05,
|
| 812 |
+
"loss": 1.7869,
|
| 813 |
+
"step": 131
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.36,
|
| 817 |
+
"learning_rate": 1.4949249938518203e-05,
|
| 818 |
+
"loss": 1.7928,
|
| 819 |
+
"step": 132
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.36,
|
| 823 |
+
"learning_rate": 1.4872807783292027e-05,
|
| 824 |
+
"loss": 1.7894,
|
| 825 |
+
"step": 133
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.36,
|
| 829 |
+
"learning_rate": 1.4795990387151719e-05,
|
| 830 |
+
"loss": 1.7933,
|
| 831 |
+
"step": 134
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.36,
|
| 835 |
+
"learning_rate": 1.4718803665584038e-05,
|
| 836 |
+
"loss": 1.7935,
|
| 837 |
+
"step": 135
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.37,
|
| 841 |
+
"learning_rate": 1.464125356251644e-05,
|
| 842 |
+
"loss": 1.8007,
|
| 843 |
+
"step": 136
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.37,
|
| 847 |
+
"learning_rate": 1.4563346049859348e-05,
|
| 848 |
+
"loss": 1.7724,
|
| 849 |
+
"step": 137
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.37,
|
| 853 |
+
"learning_rate": 1.4485087127046256e-05,
|
| 854 |
+
"loss": 1.7791,
|
| 855 |
+
"step": 138
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.38,
|
| 859 |
+
"learning_rate": 1.4406482820571759e-05,
|
| 860 |
+
"loss": 1.8006,
|
| 861 |
+
"step": 139
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.38,
|
| 865 |
+
"learning_rate": 1.4327539183527447e-05,
|
| 866 |
+
"loss": 1.8027,
|
| 867 |
+
"step": 140
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.38,
|
| 871 |
+
"learning_rate": 1.4248262295135779e-05,
|
| 872 |
+
"loss": 1.7959,
|
| 873 |
+
"step": 141
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.38,
|
| 877 |
+
"learning_rate": 1.4168658260281944e-05,
|
| 878 |
+
"loss": 1.7582,
|
| 879 |
+
"step": 142
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.39,
|
| 883 |
+
"learning_rate": 1.4088733209043748e-05,
|
| 884 |
+
"loss": 1.7951,
|
| 885 |
+
"step": 143
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.39,
|
| 889 |
+
"learning_rate": 1.400849329621953e-05,
|
| 890 |
+
"loss": 1.8226,
|
| 891 |
+
"step": 144
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.39,
|
| 895 |
+
"learning_rate": 1.3927944700854223e-05,
|
| 896 |
+
"loss": 1.8077,
|
| 897 |
+
"step": 145
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.39,
|
| 901 |
+
"learning_rate": 1.3847093625763517e-05,
|
| 902 |
+
"loss": 1.7879,
|
| 903 |
+
"step": 146
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.4,
|
| 907 |
+
"learning_rate": 1.3765946297056192e-05,
|
| 908 |
+
"loss": 1.7708,
|
| 909 |
+
"step": 147
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.4,
|
| 913 |
+
"learning_rate": 1.3684508963654667e-05,
|
| 914 |
+
"loss": 1.8,
|
| 915 |
+
"step": 148
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.4,
|
| 919 |
+
"learning_rate": 1.3602787896813787e-05,
|
| 920 |
+
"loss": 1.818,
|
| 921 |
+
"step": 149
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.4,
|
| 925 |
+
"learning_rate": 1.3520789389637898e-05,
|
| 926 |
+
"loss": 1.7789,
|
| 927 |
+
"step": 150
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.41,
|
| 931 |
+
"learning_rate": 1.3438519756596226e-05,
|
| 932 |
+
"loss": 1.8044,
|
| 933 |
+
"step": 151
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.41,
|
| 937 |
+
"learning_rate": 1.335598533303662e-05,
|
| 938 |
+
"loss": 1.7782,
|
| 939 |
+
"step": 152
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.41,
|
| 943 |
+
"learning_rate": 1.327319247469768e-05,
|
| 944 |
+
"loss": 1.7842,
|
| 945 |
+
"step": 153
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.42,
|
| 949 |
+
"learning_rate": 1.319014755721934e-05,
|
| 950 |
+
"loss": 1.7948,
|
| 951 |
+
"step": 154
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.42,
|
| 955 |
+
"learning_rate": 1.3106856975651866e-05,
|
| 956 |
+
"loss": 1.8157,
|
| 957 |
+
"step": 155
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.42,
|
| 961 |
+
"learning_rate": 1.3023327143963415e-05,
|
| 962 |
+
"loss": 1.7737,
|
| 963 |
+
"step": 156
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.42,
|
| 967 |
+
"learning_rate": 1.293956449454612e-05,
|
| 968 |
+
"loss": 1.7827,
|
| 969 |
+
"step": 157
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.43,
|
| 973 |
+
"learning_rate": 1.285557547772072e-05,
|
| 974 |
+
"loss": 1.7996,
|
| 975 |
+
"step": 158
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.43,
|
| 979 |
+
"learning_rate": 1.2771366561239865e-05,
|
| 980 |
+
"loss": 1.7801,
|
| 981 |
+
"step": 159
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.43,
|
| 985 |
+
"learning_rate": 1.2686944229790044e-05,
|
| 986 |
+
"loss": 1.7973,
|
| 987 |
+
"step": 160
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.43,
|
| 991 |
+
"learning_rate": 1.2602314984492222e-05,
|
| 992 |
+
"loss": 1.8013,
|
| 993 |
+
"step": 161
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.44,
|
| 997 |
+
"learning_rate": 1.2517485342401201e-05,
|
| 998 |
+
"loss": 1.7746,
|
| 999 |
+
"step": 162
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.44,
|
| 1003 |
+
"learning_rate": 1.2432461836003762e-05,
|
| 1004 |
+
"loss": 1.83,
|
| 1005 |
+
"step": 163
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.44,
|
| 1009 |
+
"learning_rate": 1.2347251012715629e-05,
|
| 1010 |
+
"loss": 1.8006,
|
| 1011 |
+
"step": 164
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.45,
|
| 1015 |
+
"learning_rate": 1.2261859434377245e-05,
|
| 1016 |
+
"loss": 1.7835,
|
| 1017 |
+
"step": 165
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.45,
|
| 1021 |
+
"learning_rate": 1.2176293676748494e-05,
|
| 1022 |
+
"loss": 1.78,
|
| 1023 |
+
"step": 166
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.45,
|
| 1027 |
+
"learning_rate": 1.2090560329002294e-05,
|
| 1028 |
+
"loss": 1.7982,
|
| 1029 |
+
"step": 167
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.45,
|
| 1033 |
+
"learning_rate": 1.200466599321721e-05,
|
| 1034 |
+
"loss": 1.7792,
|
| 1035 |
+
"step": 168
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.46,
|
| 1039 |
+
"learning_rate": 1.1918617283869021e-05,
|
| 1040 |
+
"loss": 1.7995,
|
| 1041 |
+
"step": 169
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.46,
|
| 1045 |
+
"learning_rate": 1.1832420827321374e-05,
|
| 1046 |
+
"loss": 1.7971,
|
| 1047 |
+
"step": 170
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.46,
|
| 1051 |
+
"learning_rate": 1.1746083261315505e-05,
|
| 1052 |
+
"loss": 1.7896,
|
| 1053 |
+
"step": 171
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.46,
|
| 1057 |
+
"learning_rate": 1.165961123445908e-05,
|
| 1058 |
+
"loss": 1.7769,
|
| 1059 |
+
"step": 172
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.47,
|
| 1063 |
+
"learning_rate": 1.1573011405714214e-05,
|
| 1064 |
+
"loss": 1.8266,
|
| 1065 |
+
"step": 173
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.47,
|
| 1069 |
+
"learning_rate": 1.1486290443884666e-05,
|
| 1070 |
+
"loss": 1.7984,
|
| 1071 |
+
"step": 174
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.47,
|
| 1075 |
+
"learning_rate": 1.1399455027102327e-05,
|
| 1076 |
+
"loss": 1.795,
|
| 1077 |
+
"step": 175
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.47,
|
| 1081 |
+
"learning_rate": 1.131251184231291e-05,
|
| 1082 |
+
"loss": 1.748,
|
| 1083 |
+
"step": 176
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.48,
|
| 1087 |
+
"learning_rate": 1.122546758476105e-05,
|
| 1088 |
+
"loss": 1.7626,
|
| 1089 |
+
"step": 177
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.48,
|
| 1093 |
+
"learning_rate": 1.1138328957474691e-05,
|
| 1094 |
+
"loss": 1.7735,
|
| 1095 |
+
"step": 178
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.48,
|
| 1099 |
+
"learning_rate": 1.1051102670748939e-05,
|
| 1100 |
+
"loss": 1.8027,
|
| 1101 |
+
"step": 179
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.49,
|
| 1105 |
+
"learning_rate": 1.0963795441629275e-05,
|
| 1106 |
+
"loss": 1.772,
|
| 1107 |
+
"step": 180
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.49,
|
| 1111 |
+
"learning_rate": 1.0876413993394346e-05,
|
| 1112 |
+
"loss": 1.789,
|
| 1113 |
+
"step": 181
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.49,
|
| 1117 |
+
"learning_rate": 1.0788965055038179e-05,
|
| 1118 |
+
"loss": 1.7798,
|
| 1119 |
+
"step": 182
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.49,
|
| 1123 |
+
"learning_rate": 1.0701455360752038e-05,
|
| 1124 |
+
"loss": 1.7897,
|
| 1125 |
+
"step": 183
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.5,
|
| 1129 |
+
"learning_rate": 1.0613891649405816e-05,
|
| 1130 |
+
"loss": 1.7981,
|
| 1131 |
+
"step": 184
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.5,
|
| 1135 |
+
"learning_rate": 1.0526280664029105e-05,
|
| 1136 |
+
"loss": 1.767,
|
| 1137 |
+
"step": 185
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.5,
|
| 1141 |
+
"learning_rate": 1.0438629151291944e-05,
|
| 1142 |
+
"loss": 1.8001,
|
| 1143 |
+
"step": 186
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.5,
|
| 1147 |
+
"learning_rate": 1.0350943860985249e-05,
|
| 1148 |
+
"loss": 1.805,
|
| 1149 |
+
"step": 187
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.51,
|
| 1153 |
+
"learning_rate": 1.0263231545501068e-05,
|
| 1154 |
+
"loss": 1.7844,
|
| 1155 |
+
"step": 188
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.51,
|
| 1159 |
+
"learning_rate": 1.0175498959312572e-05,
|
| 1160 |
+
"loss": 1.7983,
|
| 1161 |
+
"step": 189
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.51,
|
| 1165 |
+
"learning_rate": 1.0087752858453923e-05,
|
| 1166 |
+
"loss": 1.7666,
|
| 1167 |
+
"step": 190
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.52,
|
| 1171 |
+
"learning_rate": 1e-05,
|
| 1172 |
+
"loss": 1.7811,
|
| 1173 |
+
"step": 191
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.52,
|
| 1177 |
+
"learning_rate": 9.91224714154608e-06,
|
| 1178 |
+
"loss": 1.7976,
|
| 1179 |
+
"step": 192
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.52,
|
| 1183 |
+
"learning_rate": 9.82450104068743e-06,
|
| 1184 |
+
"loss": 1.7886,
|
| 1185 |
+
"step": 193
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.52,
|
| 1189 |
+
"learning_rate": 9.736768454498935e-06,
|
| 1190 |
+
"loss": 1.8027,
|
| 1191 |
+
"step": 194
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.53,
|
| 1195 |
+
"learning_rate": 9.649056139014754e-06,
|
| 1196 |
+
"loss": 1.8216,
|
| 1197 |
+
"step": 195
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.53,
|
| 1201 |
+
"learning_rate": 9.561370848708061e-06,
|
| 1202 |
+
"loss": 1.7914,
|
| 1203 |
+
"step": 196
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.53,
|
| 1207 |
+
"learning_rate": 9.473719335970896e-06,
|
| 1208 |
+
"loss": 1.8065,
|
| 1209 |
+
"step": 197
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.53,
|
| 1213 |
+
"learning_rate": 9.38610835059419e-06,
|
| 1214 |
+
"loss": 1.8193,
|
| 1215 |
+
"step": 198
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.54,
|
| 1219 |
+
"learning_rate": 9.298544639247965e-06,
|
| 1220 |
+
"loss": 1.7909,
|
| 1221 |
+
"step": 199
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.54,
|
| 1225 |
+
"learning_rate": 9.211034944961825e-06,
|
| 1226 |
+
"loss": 1.7953,
|
| 1227 |
+
"step": 200
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.54,
|
| 1231 |
+
"learning_rate": 9.123586006605658e-06,
|
| 1232 |
+
"loss": 1.7697,
|
| 1233 |
+
"step": 201
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.55,
|
| 1237 |
+
"learning_rate": 9.036204558370725e-06,
|
| 1238 |
+
"loss": 1.7838,
|
| 1239 |
+
"step": 202
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.55,
|
| 1243 |
+
"learning_rate": 8.948897329251066e-06,
|
| 1244 |
+
"loss": 1.7709,
|
| 1245 |
+
"step": 203
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.55,
|
| 1249 |
+
"learning_rate": 8.861671042525312e-06,
|
| 1250 |
+
"loss": 1.7724,
|
| 1251 |
+
"step": 204
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.55,
|
| 1255 |
+
"learning_rate": 8.774532415238954e-06,
|
| 1256 |
+
"loss": 1.7831,
|
| 1257 |
+
"step": 205
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.56,
|
| 1261 |
+
"learning_rate": 8.68748815768709e-06,
|
| 1262 |
+
"loss": 1.8078,
|
| 1263 |
+
"step": 206
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.56,
|
| 1267 |
+
"learning_rate": 8.600544972897678e-06,
|
| 1268 |
+
"loss": 1.8062,
|
| 1269 |
+
"step": 207
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.56,
|
| 1273 |
+
"learning_rate": 8.513709556115335e-06,
|
| 1274 |
+
"loss": 1.7619,
|
| 1275 |
+
"step": 208
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.56,
|
| 1279 |
+
"learning_rate": 8.42698859428579e-06,
|
| 1280 |
+
"loss": 1.8102,
|
| 1281 |
+
"step": 209
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.57,
|
| 1285 |
+
"learning_rate": 8.340388765540923e-06,
|
| 1286 |
+
"loss": 1.7684,
|
| 1287 |
+
"step": 210
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.57,
|
| 1291 |
+
"learning_rate": 8.253916738684497e-06,
|
| 1292 |
+
"loss": 1.7914,
|
| 1293 |
+
"step": 211
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.57,
|
| 1297 |
+
"learning_rate": 8.16757917267863e-06,
|
| 1298 |
+
"loss": 1.8082,
|
| 1299 |
+
"step": 212
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.57,
|
| 1303 |
+
"learning_rate": 8.081382716130982e-06,
|
| 1304 |
+
"loss": 1.8128,
|
| 1305 |
+
"step": 213
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.58,
|
| 1309 |
+
"learning_rate": 7.995334006782793e-06,
|
| 1310 |
+
"loss": 1.7836,
|
| 1311 |
+
"step": 214
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.58,
|
| 1315 |
+
"learning_rate": 7.909439670997706e-06,
|
| 1316 |
+
"loss": 1.796,
|
| 1317 |
+
"step": 215
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.58,
|
| 1321 |
+
"learning_rate": 7.823706323251512e-06,
|
| 1322 |
+
"loss": 1.7882,
|
| 1323 |
+
"step": 216
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.59,
|
| 1327 |
+
"learning_rate": 7.738140565622758e-06,
|
| 1328 |
+
"loss": 1.7991,
|
| 1329 |
+
"step": 217
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.59,
|
| 1333 |
+
"learning_rate": 7.652748987284375e-06,
|
| 1334 |
+
"loss": 1.7882,
|
| 1335 |
+
"step": 218
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.59,
|
| 1339 |
+
"learning_rate": 7.567538163996237e-06,
|
| 1340 |
+
"loss": 1.7659,
|
| 1341 |
+
"step": 219
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.59,
|
| 1345 |
+
"learning_rate": 7.4825146575988e-06,
|
| 1346 |
+
"loss": 1.8046,
|
| 1347 |
+
"step": 220
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.6,
|
| 1351 |
+
"learning_rate": 7.397685015507781e-06,
|
| 1352 |
+
"loss": 1.785,
|
| 1353 |
+
"step": 221
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.6,
|
| 1357 |
+
"learning_rate": 7.313055770209961e-06,
|
| 1358 |
+
"loss": 1.7957,
|
| 1359 |
+
"step": 222
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.6,
|
| 1363 |
+
"learning_rate": 7.228633438760138e-06,
|
| 1364 |
+
"loss": 1.8203,
|
| 1365 |
+
"step": 223
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.6,
|
| 1369 |
+
"learning_rate": 7.144424522279283e-06,
|
| 1370 |
+
"loss": 1.7776,
|
| 1371 |
+
"step": 224
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.61,
|
| 1375 |
+
"learning_rate": 7.060435505453884e-06,
|
| 1376 |
+
"loss": 1.7941,
|
| 1377 |
+
"step": 225
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.61,
|
| 1381 |
+
"learning_rate": 6.976672856036586e-06,
|
| 1382 |
+
"loss": 1.8055,
|
| 1383 |
+
"step": 226
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.61,
|
| 1387 |
+
"learning_rate": 6.893143024348137e-06,
|
| 1388 |
+
"loss": 1.7899,
|
| 1389 |
+
"step": 227
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.62,
|
| 1393 |
+
"learning_rate": 6.809852442780664e-06,
|
| 1394 |
+
"loss": 1.7568,
|
| 1395 |
+
"step": 228
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.62,
|
| 1399 |
+
"learning_rate": 6.726807525302319e-06,
|
| 1400 |
+
"loss": 1.8206,
|
| 1401 |
+
"step": 229
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.62,
|
| 1405 |
+
"learning_rate": 6.6440146669633855e-06,
|
| 1406 |
+
"loss": 1.7995,
|
| 1407 |
+
"step": 230
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.62,
|
| 1411 |
+
"learning_rate": 6.561480243403776e-06,
|
| 1412 |
+
"loss": 1.8216,
|
| 1413 |
+
"step": 231
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.63,
|
| 1417 |
+
"learning_rate": 6.479210610362103e-06,
|
| 1418 |
+
"loss": 1.7776,
|
| 1419 |
+
"step": 232
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.63,
|
| 1423 |
+
"learning_rate": 6.397212103186214e-06,
|
| 1424 |
+
"loss": 1.8053,
|
| 1425 |
+
"step": 233
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.63,
|
| 1429 |
+
"learning_rate": 6.315491036345338e-06,
|
| 1430 |
+
"loss": 1.7891,
|
| 1431 |
+
"step": 234
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.63,
|
| 1435 |
+
"learning_rate": 6.23405370294381e-06,
|
| 1436 |
+
"loss": 1.7957,
|
| 1437 |
+
"step": 235
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.64,
|
| 1441 |
+
"learning_rate": 6.1529063742364844e-06,
|
| 1442 |
+
"loss": 1.7877,
|
| 1443 |
+
"step": 236
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.64,
|
| 1447 |
+
"learning_rate": 6.072055299145778e-06,
|
| 1448 |
+
"loss": 1.8022,
|
| 1449 |
+
"step": 237
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.64,
|
| 1453 |
+
"learning_rate": 5.991506703780475e-06,
|
| 1454 |
+
"loss": 1.7964,
|
| 1455 |
+
"step": 238
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.65,
|
| 1459 |
+
"learning_rate": 5.911266790956258e-06,
|
| 1460 |
+
"loss": 1.7626,
|
| 1461 |
+
"step": 239
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.65,
|
| 1465 |
+
"learning_rate": 5.831341739718055e-06,
|
| 1466 |
+
"loss": 1.7919,
|
| 1467 |
+
"step": 240
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.65,
|
| 1471 |
+
"learning_rate": 5.751737704864224e-06,
|
| 1472 |
+
"loss": 1.814,
|
| 1473 |
+
"step": 241
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.65,
|
| 1477 |
+
"learning_rate": 5.672460816472556e-06,
|
| 1478 |
+
"loss": 1.7844,
|
| 1479 |
+
"step": 242
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.66,
|
| 1483 |
+
"learning_rate": 5.5935171794282426e-06,
|
| 1484 |
+
"loss": 1.7852,
|
| 1485 |
+
"step": 243
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.66,
|
| 1489 |
+
"learning_rate": 5.514912872953746e-06,
|
| 1490 |
+
"loss": 1.8017,
|
| 1491 |
+
"step": 244
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.66,
|
| 1495 |
+
"learning_rate": 5.436653950140657e-06,
|
| 1496 |
+
"loss": 1.7905,
|
| 1497 |
+
"step": 245
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.66,
|
| 1501 |
+
"learning_rate": 5.35874643748356e-06,
|
| 1502 |
+
"loss": 1.8164,
|
| 1503 |
+
"step": 246
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.67,
|
| 1507 |
+
"learning_rate": 5.281196334415968e-06,
|
| 1508 |
+
"loss": 1.7747,
|
| 1509 |
+
"step": 247
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.67,
|
| 1513 |
+
"learning_rate": 5.204009612848288e-06,
|
| 1514 |
+
"loss": 1.7776,
|
| 1515 |
+
"step": 248
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.67,
|
| 1519 |
+
"learning_rate": 5.127192216707974e-06,
|
| 1520 |
+
"loss": 1.7653,
|
| 1521 |
+
"step": 249
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.67,
|
| 1525 |
+
"learning_rate": 5.050750061481799e-06,
|
| 1526 |
+
"loss": 1.7963,
|
| 1527 |
+
"step": 250
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.68,
|
| 1531 |
+
"learning_rate": 4.9746890337603005e-06,
|
| 1532 |
+
"loss": 1.793,
|
| 1533 |
+
"step": 251
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.68,
|
| 1537 |
+
"learning_rate": 4.899014990784485e-06,
|
| 1538 |
+
"loss": 1.7931,
|
| 1539 |
+
"step": 252
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.68,
|
| 1543 |
+
"eval_c4_accuracy": 0.5844665535566079,
|
| 1544 |
+
"eval_c4_loss": 1.8106247186660767,
|
| 1545 |
+
"eval_c4_runtime": 8592.9839,
|
| 1546 |
+
"eval_c4_samples_per_second": 1.388,
|
| 1547 |
+
"eval_c4_steps_per_second": 0.174,
|
| 1548 |
+
"step": 252
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.68,
|
| 1552 |
+
"eval_wikitext_accuracy": 0.6783450362269793,
|
| 1553 |
+
"eval_wikitext_loss": 1.2974998950958252,
|
| 1554 |
+
"eval_wikitext_runtime": 121.0983,
|
| 1555 |
+
"eval_wikitext_samples_per_second": 1.371,
|
| 1556 |
+
"eval_wikitext_steps_per_second": 0.173,
|
| 1557 |
+
"step": 252
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.68,
|
| 1561 |
+
"learning_rate": 4.8237337599947795e-06,
|
| 1562 |
+
"loss": 1.7742,
|
| 1563 |
+
"step": 253
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.69,
|
| 1567 |
+
"learning_rate": 4.748851138582269e-06,
|
| 1568 |
+
"loss": 1.7644,
|
| 1569 |
+
"step": 254
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.69,
|
| 1573 |
+
"learning_rate": 4.674372893042287e-06,
|
| 1574 |
+
"loss": 1.7826,
|
| 1575 |
+
"step": 255
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.69,
|
| 1579 |
+
"learning_rate": 4.6003047587303376e-06,
|
| 1580 |
+
"loss": 1.7793,
|
| 1581 |
+
"step": 256
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.69,
|
| 1585 |
+
"learning_rate": 4.526652439420427e-06,
|
| 1586 |
+
"loss": 1.7911,
|
| 1587 |
+
"step": 257
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.7,
|
| 1591 |
+
"learning_rate": 4.453421606865869e-06,
|
| 1592 |
+
"loss": 1.7704,
|
| 1593 |
+
"step": 258
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.7,
|
| 1597 |
+
"learning_rate": 4.380617900362473e-06,
|
| 1598 |
+
"loss": 1.8114,
|
| 1599 |
+
"step": 259
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.7,
|
| 1603 |
+
"learning_rate": 4.308246926314307e-06,
|
| 1604 |
+
"loss": 1.7993,
|
| 1605 |
+
"step": 260
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.7,
|
| 1609 |
+
"learning_rate": 4.236314257801968e-06,
|
| 1610 |
+
"loss": 1.7608,
|
| 1611 |
+
"step": 261
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.71,
|
| 1615 |
+
"learning_rate": 4.164825434153381e-06,
|
| 1616 |
+
"loss": 1.7883,
|
| 1617 |
+
"step": 262
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.71,
|
| 1621 |
+
"learning_rate": 4.093785960517269e-06,
|
| 1622 |
+
"loss": 1.7874,
|
| 1623 |
+
"step": 263
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.71,
|
| 1627 |
+
"learning_rate": 4.0232013074392065e-06,
|
| 1628 |
+
"loss": 1.7954,
|
| 1629 |
+
"step": 264
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.72,
|
| 1633 |
+
"learning_rate": 3.953076910440337e-06,
|
| 1634 |
+
"loss": 1.7897,
|
| 1635 |
+
"step": 265
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.72,
|
| 1639 |
+
"learning_rate": 3.883418169598808e-06,
|
| 1640 |
+
"loss": 1.8162,
|
| 1641 |
+
"step": 266
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.72,
|
| 1645 |
+
"learning_rate": 3.814230449133928e-06,
|
| 1646 |
+
"loss": 1.788,
|
| 1647 |
+
"step": 267
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.72,
|
| 1651 |
+
"learning_rate": 3.745519076993078e-06,
|
| 1652 |
+
"loss": 1.8065,
|
| 1653 |
+
"step": 268
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.73,
|
| 1657 |
+
"learning_rate": 3.6772893444414226e-06,
|
| 1658 |
+
"loss": 1.8212,
|
| 1659 |
+
"step": 269
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.73,
|
| 1663 |
+
"learning_rate": 3.609546505654462e-06,
|
| 1664 |
+
"loss": 1.8017,
|
| 1665 |
+
"step": 270
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.73,
|
| 1669 |
+
"learning_rate": 3.5422957773133804e-06,
|
| 1670 |
+
"loss": 1.769,
|
| 1671 |
+
"step": 271
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.73,
|
| 1675 |
+
"learning_rate": 3.475542338203377e-06,
|
| 1676 |
+
"loss": 1.7917,
|
| 1677 |
+
"step": 272
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.74,
|
| 1681 |
+
"learning_rate": 3.4092913288148254e-06,
|
| 1682 |
+
"loss": 1.7923,
|
| 1683 |
+
"step": 273
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.74,
|
| 1687 |
+
"learning_rate": 3.343547850947434e-06,
|
| 1688 |
+
"loss": 1.7956,
|
| 1689 |
+
"step": 274
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.74,
|
| 1693 |
+
"learning_rate": 3.2783169673173666e-06,
|
| 1694 |
+
"loss": 1.7955,
|
| 1695 |
+
"step": 275
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.74,
|
| 1699 |
+
"learning_rate": 3.2136037011673803e-06,
|
| 1700 |
+
"loss": 1.8008,
|
| 1701 |
+
"step": 276
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.75,
|
| 1705 |
+
"learning_rate": 3.149413035879996e-06,
|
| 1706 |
+
"loss": 1.7913,
|
| 1707 |
+
"step": 277
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.75,
|
| 1711 |
+
"learning_rate": 3.085749914593752e-06,
|
| 1712 |
+
"loss": 1.7677,
|
| 1713 |
+
"step": 278
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.75,
|
| 1717 |
+
"learning_rate": 3.022619239822535e-06,
|
| 1718 |
+
"loss": 1.7912,
|
| 1719 |
+
"step": 279
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.76,
|
| 1723 |
+
"learning_rate": 2.9600258730780564e-06,
|
| 1724 |
+
"loss": 1.7785,
|
| 1725 |
+
"step": 280
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.76,
|
| 1729 |
+
"learning_rate": 2.897974634495482e-06,
|
| 1730 |
+
"loss": 1.7682,
|
| 1731 |
+
"step": 281
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.76,
|
| 1735 |
+
"learning_rate": 2.8364703024622474e-06,
|
| 1736 |
+
"loss": 1.7867,
|
| 1737 |
+
"step": 282
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.76,
|
| 1741 |
+
"learning_rate": 2.7755176132500905e-06,
|
| 1742 |
+
"loss": 1.7874,
|
| 1743 |
+
"step": 283
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.77,
|
| 1747 |
+
"learning_rate": 2.7151212606503164e-06,
|
| 1748 |
+
"loss": 1.756,
|
| 1749 |
+
"step": 284
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.77,
|
| 1753 |
+
"learning_rate": 2.6552858956123485e-06,
|
| 1754 |
+
"loss": 1.8193,
|
| 1755 |
+
"step": 285
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.77,
|
| 1759 |
+
"learning_rate": 2.5960161258855807e-06,
|
| 1760 |
+
"loss": 1.8098,
|
| 1761 |
+
"step": 286
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.77,
|
| 1765 |
+
"learning_rate": 2.5373165156645263e-06,
|
| 1766 |
+
"loss": 1.8032,
|
| 1767 |
+
"step": 287
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.78,
|
| 1771 |
+
"learning_rate": 2.4791915852373604e-06,
|
| 1772 |
+
"loss": 1.7975,
|
| 1773 |
+
"step": 288
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.78,
|
| 1777 |
+
"learning_rate": 2.4216458106378194e-06,
|
| 1778 |
+
"loss": 1.7855,
|
| 1779 |
+
"step": 289
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.78,
|
| 1783 |
+
"learning_rate": 2.3646836233005133e-06,
|
| 1784 |
+
"loss": 1.7994,
|
| 1785 |
+
"step": 290
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.79,
|
| 1789 |
+
"learning_rate": 2.3083094097196766e-06,
|
| 1790 |
+
"loss": 1.8054,
|
| 1791 |
+
"step": 291
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.79,
|
| 1795 |
+
"learning_rate": 2.252527511111381e-06,
|
| 1796 |
+
"loss": 1.7835,
|
| 1797 |
+
"step": 292
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 0.79,
|
| 1801 |
+
"learning_rate": 2.197342223079212e-06,
|
| 1802 |
+
"loss": 1.8004,
|
| 1803 |
+
"step": 293
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.79,
|
| 1807 |
+
"learning_rate": 2.1427577952835044e-06,
|
| 1808 |
+
"loss": 1.785,
|
| 1809 |
+
"step": 294
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.8,
|
| 1813 |
+
"learning_rate": 2.088778431114068e-06,
|
| 1814 |
+
"loss": 1.7895,
|
| 1815 |
+
"step": 295
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.8,
|
| 1819 |
+
"learning_rate": 2.0354082873665015e-06,
|
| 1820 |
+
"loss": 1.7666,
|
| 1821 |
+
"step": 296
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.8,
|
| 1825 |
+
"learning_rate": 1.9826514739220946e-06,
|
| 1826 |
+
"loss": 1.8161,
|
| 1827 |
+
"step": 297
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.8,
|
| 1831 |
+
"learning_rate": 1.9305120534313295e-06,
|
| 1832 |
+
"loss": 1.792,
|
| 1833 |
+
"step": 298
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.81,
|
| 1837 |
+
"learning_rate": 1.8789940410010355e-06,
|
| 1838 |
+
"loss": 1.8002,
|
| 1839 |
+
"step": 299
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.81,
|
| 1843 |
+
"learning_rate": 1.8281014038851963e-06,
|
| 1844 |
+
"loss": 1.7925,
|
| 1845 |
+
"step": 300
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.81,
|
| 1849 |
+
"learning_rate": 1.777838061179442e-06,
|
| 1850 |
+
"loss": 1.7925,
|
| 1851 |
+
"step": 301
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.82,
|
| 1855 |
+
"learning_rate": 1.7282078835192362e-06,
|
| 1856 |
+
"loss": 1.7995,
|
| 1857 |
+
"step": 302
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.82,
|
| 1861 |
+
"learning_rate": 1.679214692781842e-06,
|
| 1862 |
+
"loss": 1.7686,
|
| 1863 |
+
"step": 303
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.82,
|
| 1867 |
+
"learning_rate": 1.6308622617919823e-06,
|
| 1868 |
+
"loss": 1.7806,
|
| 1869 |
+
"step": 304
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.82,
|
| 1873 |
+
"learning_rate": 1.583154314031311e-06,
|
| 1874 |
+
"loss": 1.7792,
|
| 1875 |
+
"step": 305
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.83,
|
| 1879 |
+
"learning_rate": 1.5360945233516933e-06,
|
| 1880 |
+
"loss": 1.8009,
|
| 1881 |
+
"step": 306
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.83,
|
| 1885 |
+
"learning_rate": 1.489686513692269e-06,
|
| 1886 |
+
"loss": 1.7839,
|
| 1887 |
+
"step": 307
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.83,
|
| 1891 |
+
"learning_rate": 1.4439338588004005e-06,
|
| 1892 |
+
"loss": 1.8043,
|
| 1893 |
+
"step": 308
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.83,
|
| 1897 |
+
"learning_rate": 1.3988400819564707e-06,
|
| 1898 |
+
"loss": 1.7892,
|
| 1899 |
+
"step": 309
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.84,
|
| 1903 |
+
"learning_rate": 1.3544086557025493e-06,
|
| 1904 |
+
"loss": 1.7776,
|
| 1905 |
+
"step": 310
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.84,
|
| 1909 |
+
"learning_rate": 1.3106430015749971e-06,
|
| 1910 |
+
"loss": 1.7758,
|
| 1911 |
+
"step": 311
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.84,
|
| 1915 |
+
"learning_rate": 1.2675464898409772e-06,
|
| 1916 |
+
"loss": 1.8103,
|
| 1917 |
+
"step": 312
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.84,
|
| 1921 |
+
"learning_rate": 1.2251224392389183e-06,
|
| 1922 |
+
"loss": 1.7743,
|
| 1923 |
+
"step": 313
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 0.85,
|
| 1927 |
+
"learning_rate": 1.1833741167229584e-06,
|
| 1928 |
+
"loss": 1.7756,
|
| 1929 |
+
"step": 314
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.85,
|
| 1933 |
+
"learning_rate": 1.1423047372113538e-06,
|
| 1934 |
+
"loss": 1.7774,
|
| 1935 |
+
"step": 315
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.85,
|
| 1939 |
+
"learning_rate": 1.1019174633389073e-06,
|
| 1940 |
+
"loss": 1.7967,
|
| 1941 |
+
"step": 316
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.86,
|
| 1945 |
+
"learning_rate": 1.0622154052134392e-06,
|
| 1946 |
+
"loss": 1.8046,
|
| 1947 |
+
"step": 317
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.86,
|
| 1951 |
+
"learning_rate": 1.0232016201762696e-06,
|
| 1952 |
+
"loss": 1.8023,
|
| 1953 |
+
"step": 318
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.86,
|
| 1957 |
+
"learning_rate": 9.848791125667867e-07,
|
| 1958 |
+
"loss": 1.7924,
|
| 1959 |
+
"step": 319
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.86,
|
| 1963 |
+
"learning_rate": 9.472508334910946e-07,
|
| 1964 |
+
"loss": 1.7979,
|
| 1965 |
+
"step": 320
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 0.87,
|
| 1969 |
+
"learning_rate": 9.103196805947522e-07,
|
| 1970 |
+
"loss": 1.7993,
|
| 1971 |
+
"step": 321
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.87,
|
| 1975 |
+
"learning_rate": 8.740884978396358e-07,
|
| 1976 |
+
"loss": 1.7997,
|
| 1977 |
+
"step": 322
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.87,
|
| 1981 |
+
"learning_rate": 8.385600752849387e-07,
|
| 1982 |
+
"loss": 1.79,
|
| 1983 |
+
"step": 323
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.87,
|
| 1987 |
+
"learning_rate": 8.037371488723078e-07,
|
| 1988 |
+
"loss": 1.7934,
|
| 1989 |
+
"step": 324
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.88,
|
| 1993 |
+
"learning_rate": 7.69622400215162e-07,
|
| 1994 |
+
"loss": 1.7691,
|
| 1995 |
+
"step": 325
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.88,
|
| 1999 |
+
"learning_rate": 7.36218456392187e-07,
|
| 2000 |
+
"loss": 1.7877,
|
| 2001 |
+
"step": 326
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.88,
|
| 2005 |
+
"learning_rate": 7.035278897450326e-07,
|
| 2006 |
+
"loss": 1.8122,
|
| 2007 |
+
"step": 327
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 0.89,
|
| 2011 |
+
"learning_rate": 6.715532176802298e-07,
|
| 2012 |
+
"loss": 1.7833,
|
| 2013 |
+
"step": 328
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 0.89,
|
| 2017 |
+
"learning_rate": 6.402969024753147e-07,
|
| 2018 |
+
"loss": 1.7859,
|
| 2019 |
+
"step": 329
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.89,
|
| 2023 |
+
"learning_rate": 6.097613510892364e-07,
|
| 2024 |
+
"loss": 1.7659,
|
| 2025 |
+
"step": 330
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.89,
|
| 2029 |
+
"learning_rate": 5.799489149769943e-07,
|
| 2030 |
+
"loss": 1.7988,
|
| 2031 |
+
"step": 331
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.9,
|
| 2035 |
+
"learning_rate": 5.508618899085583e-07,
|
| 2036 |
+
"loss": 1.7779,
|
| 2037 |
+
"step": 332
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.9,
|
| 2041 |
+
"learning_rate": 5.225025157920782e-07,
|
| 2042 |
+
"loss": 1.7841,
|
| 2043 |
+
"step": 333
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 0.9,
|
| 2047 |
+
"learning_rate": 4.948729765014004e-07,
|
| 2048 |
+
"loss": 1.8028,
|
| 2049 |
+
"step": 334
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 0.9,
|
| 2053 |
+
"learning_rate": 4.6797539970788843e-07,
|
| 2054 |
+
"loss": 1.7522,
|
| 2055 |
+
"step": 335
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.91,
|
| 2059 |
+
"learning_rate": 4.4181185671657634e-07,
|
| 2060 |
+
"loss": 1.8075,
|
| 2061 |
+
"step": 336
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.91,
|
| 2065 |
+
"learning_rate": 4.163843623066732e-07,
|
| 2066 |
+
"loss": 1.8198,
|
| 2067 |
+
"step": 337
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.91,
|
| 2071 |
+
"learning_rate": 3.916948745763938e-07,
|
| 2072 |
+
"loss": 1.7857,
|
| 2073 |
+
"step": 338
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.91,
|
| 2077 |
+
"learning_rate": 3.6774529479219e-07,
|
| 2078 |
+
"loss": 1.8055,
|
| 2079 |
+
"step": 339
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.92,
|
| 2083 |
+
"learning_rate": 3.445374672423252e-07,
|
| 2084 |
+
"loss": 1.7971,
|
| 2085 |
+
"step": 340
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 0.92,
|
| 2089 |
+
"learning_rate": 3.2207317909485834e-07,
|
| 2090 |
+
"loss": 1.7771,
|
| 2091 |
+
"step": 341
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.92,
|
| 2095 |
+
"learning_rate": 3.0035416026001573e-07,
|
| 2096 |
+
"loss": 1.7949,
|
| 2097 |
+
"step": 342
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.93,
|
| 2101 |
+
"learning_rate": 2.7938208325697825e-07,
|
| 2102 |
+
"loss": 1.8005,
|
| 2103 |
+
"step": 343
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.93,
|
| 2107 |
+
"learning_rate": 2.591585630850835e-07,
|
| 2108 |
+
"loss": 1.7762,
|
| 2109 |
+
"step": 344
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.93,
|
| 2113 |
+
"learning_rate": 2.3968515709946296e-07,
|
| 2114 |
+
"loss": 1.8102,
|
| 2115 |
+
"step": 345
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.93,
|
| 2119 |
+
"learning_rate": 2.2096336489111025e-07,
|
| 2120 |
+
"loss": 1.7736,
|
| 2121 |
+
"step": 346
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.94,
|
| 2125 |
+
"learning_rate": 2.0299462817139902e-07,
|
| 2126 |
+
"loss": 1.7758,
|
| 2127 |
+
"step": 347
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 0.94,
|
| 2131 |
+
"learning_rate": 1.8578033066107392e-07,
|
| 2132 |
+
"loss": 1.8026,
|
| 2133 |
+
"step": 348
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.94,
|
| 2137 |
+
"learning_rate": 1.693217979836792e-07,
|
| 2138 |
+
"loss": 1.8195,
|
| 2139 |
+
"step": 349
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.94,
|
| 2143 |
+
"learning_rate": 1.5362029756348373e-07,
|
| 2144 |
+
"loss": 1.7964,
|
| 2145 |
+
"step": 350
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.95,
|
| 2149 |
+
"learning_rate": 1.386770385278835e-07,
|
| 2150 |
+
"loss": 1.7938,
|
| 2151 |
+
"step": 351
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.95,
|
| 2155 |
+
"learning_rate": 1.2449317161427942e-07,
|
| 2156 |
+
"loss": 1.7922,
|
| 2157 |
+
"step": 352
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.95,
|
| 2161 |
+
"learning_rate": 1.1106978908147381e-07,
|
| 2162 |
+
"loss": 1.7837,
|
| 2163 |
+
"step": 353
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.96,
|
| 2167 |
+
"learning_rate": 9.840792462555426e-08,
|
| 2168 |
+
"loss": 1.7903,
|
| 2169 |
+
"step": 354
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.96,
|
| 2173 |
+
"learning_rate": 8.650855330028629e-08,
|
| 2174 |
+
"loss": 1.7613,
|
| 2175 |
+
"step": 355
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 0.96,
|
| 2179 |
+
"learning_rate": 7.53725914420378e-08,
|
| 2180 |
+
"loss": 1.7834,
|
| 2181 |
+
"step": 356
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 0.96,
|
| 2185 |
+
"learning_rate": 6.500089659920661e-08,
|
| 2186 |
+
"loss": 1.7906,
|
| 2187 |
+
"step": 357
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.97,
|
| 2191 |
+
"learning_rate": 5.539426746618337e-08,
|
| 2192 |
+
"loss": 1.8067,
|
| 2193 |
+
"step": 358
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.97,
|
| 2197 |
+
"learning_rate": 4.6553443821852893e-08,
|
| 2198 |
+
"loss": 1.7883,
|
| 2199 |
+
"step": 359
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.97,
|
| 2203 |
+
"learning_rate": 3.847910647261754e-08,
|
| 2204 |
+
"loss": 1.8194,
|
| 2205 |
+
"step": 360
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.97,
|
| 2209 |
+
"learning_rate": 3.117187719997805e-08,
|
| 2210 |
+
"loss": 1.7865,
|
| 2211 |
+
"step": 361
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 0.98,
|
| 2215 |
+
"learning_rate": 2.4632318712646264e-08,
|
| 2216 |
+
"loss": 1.7726,
|
| 2217 |
+
"step": 362
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 0.98,
|
| 2221 |
+
"learning_rate": 1.8860934603215365e-08,
|
| 2222 |
+
"loss": 1.8037,
|
| 2223 |
+
"step": 363
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.98,
|
| 2227 |
+
"learning_rate": 1.3858169309376446e-08,
|
| 2228 |
+
"loss": 1.7788,
|
| 2229 |
+
"step": 364
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.99,
|
| 2233 |
+
"learning_rate": 9.624408079699221e-09,
|
| 2234 |
+
"loss": 1.8099,
|
| 2235 |
+
"step": 365
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.99,
|
| 2239 |
+
"learning_rate": 6.1599769439590896e-09,
|
| 2240 |
+
"loss": 1.7654,
|
| 2241 |
+
"step": 366
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.99,
|
| 2245 |
+
"learning_rate": 3.465142688036105e-09,
|
| 2246 |
+
"loss": 1.8014,
|
| 2247 |
+
"step": 367
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 0.99,
|
| 2251 |
+
"learning_rate": 1.540112833366969e-09,
|
| 2252 |
+
"loss": 1.7673,
|
| 2253 |
+
"step": 368
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 1.0,
|
| 2257 |
+
"learning_rate": 3.850356209633699e-10,
|
| 2258 |
+
"loss": 1.7883,
|
| 2259 |
+
"step": 369
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.0,
|
| 2263 |
+
"learning_rate": 0.0,
|
| 2264 |
+
"loss": 1.764,
|
| 2265 |
+
"step": 370
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 1.0,
|
| 2269 |
+
"step": 370,
|
| 2270 |
+
"total_flos": 1.6188461333308506e+20,
|
| 2271 |
+
"train_loss": 1.7981542252205513,
|
| 2272 |
+
"train_runtime": 419993.6461,
|
| 2273 |
+
"train_samples_per_second": 0.452,
|
| 2274 |
+
"train_steps_per_second": 0.001
|
| 2275 |
+
}
|
| 2276 |
+
],
|
| 2277 |
+
"logging_steps": 1.0,
|
| 2278 |
+
"max_steps": 370,
|
| 2279 |
+
"num_train_epochs": 1,
|
| 2280 |
+
"save_steps": 126,
|
| 2281 |
+
"total_flos": 1.6188461333308506e+20,
|
| 2282 |
+
"trial_name": null,
|
| 2283 |
+
"trial_params": null
|
| 2284 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_70b_c4_2.75/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f542ee8c3d01ab01613504c4721c2eac3698f51b7166227b44a02ab7a488b383
|
| 3 |
+
size 4155
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: /export/share3/experiments/20230731/llama-2/Llama-2-7b-hf
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- c4-wiki-large
|
| 7 |
+
model-index:
|
| 8 |
+
- name: output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [/export/share3/experiments/20230731/llama-2/Llama-2-7b-hf](https://huggingface.co//export/share3/experiments/20230731/llama-2/Llama-2-7b-hf) on the c4-wiki-large dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 2
|
| 38 |
+
- eval_batch_size: 2
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- num_devices: 4
|
| 42 |
+
- gradient_accumulation_steps: 64
|
| 43 |
+
- total_train_batch_size: 512
|
| 44 |
+
- total_eval_batch_size: 8
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
+
- num_epochs: 1.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 4.34.1
|
| 57 |
+
- Pytorch 2.0.0
|
| 58 |
+
- Datasets 2.14.6
|
| 59 |
+
- Tokenizers 0.14.1
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "/export/share3/experiments/20230731/llama-2/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"v_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"gate_proj",
|
| 22 |
+
"down_proj",
|
| 23 |
+
"up_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6c8fce98c5ba940840333b7d35f162f251d84e92619b2af91ff09d278518b0
|
| 3 |
+
size 639792909
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"c4_perplexity": 7.9382072288370855,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"eval_c4_accuracy": 0.5418060421218167,
|
| 5 |
+
"eval_c4_loss": 2.0716874599456787,
|
| 6 |
+
"eval_c4_runtime": 2321.6134,
|
| 7 |
+
"eval_c4_samples": 11927,
|
| 8 |
+
"eval_c4_samples_per_second": 5.137,
|
| 9 |
+
"eval_c4_steps_per_second": 0.642,
|
| 10 |
+
"eval_wikitext_accuracy": 0.6015679719365984,
|
| 11 |
+
"eval_wikitext_loss": 1.735874056816101,
|
| 12 |
+
"eval_wikitext_runtime": 35.4325,
|
| 13 |
+
"eval_wikitext_samples": 166,
|
| 14 |
+
"eval_wikitext_samples_per_second": 4.685,
|
| 15 |
+
"eval_wikitext_steps_per_second": 0.593,
|
| 16 |
+
"train_loss": 2.0780758393777385,
|
| 17 |
+
"train_runtime": 117810.8799,
|
| 18 |
+
"train_samples": 189709,
|
| 19 |
+
"train_samples_per_second": 1.61,
|
| 20 |
+
"train_steps_per_second": 0.003,
|
| 21 |
+
"wikitext_perplexity": 5.67388493488339
|
| 22 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/eval_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"c4_perplexity": 7.9382072288370855,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"eval_c4_accuracy": 0.5418060421218167,
|
| 5 |
+
"eval_c4_loss": 2.0716874599456787,
|
| 6 |
+
"eval_c4_runtime": 2321.6134,
|
| 7 |
+
"eval_c4_samples": 11927,
|
| 8 |
+
"eval_c4_samples_per_second": 5.137,
|
| 9 |
+
"eval_c4_steps_per_second": 0.642,
|
| 10 |
+
"eval_wikitext_accuracy": 0.6015679719365984,
|
| 11 |
+
"eval_wikitext_loss": 1.735874056816101,
|
| 12 |
+
"eval_wikitext_runtime": 35.4325,
|
| 13 |
+
"eval_wikitext_samples": 166,
|
| 14 |
+
"eval_wikitext_samples_per_second": 4.685,
|
| 15 |
+
"eval_wikitext_steps_per_second": 0.593,
|
| 16 |
+
"wikitext_perplexity": 5.67388493488339
|
| 17 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/full_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55d2787e38fb00e061584f846aabdbb0fdf9234701de0842155ef51d26bfb641
|
| 3 |
+
size 3916235237
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/runs/Oct23_19-16-28_f39a6c538c5a/events.out.tfevents.1698095130.f39a6c538c5a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8d5b1bd997260c5e4e17d3236f9d826d482020ed44851d7fdc17a3ad4f6079a
|
| 3 |
+
size 63693
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/runs/Oct23_19-16-28_f39a6c538c5a/events.out.tfevents.1698215269.f39a6c538c5a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9773f3864800c14a5de06788328f23a533d27f5f9653de930199f3cbbdff351
|
| 3 |
+
size 5543
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/runs/Oct23_19-16-28_f39a6c538c5a/events.out.tfevents.1698217298.f39a6c538c5a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ec8fbce87f3d850ed58d3968f6825280dbf9ce93e687590bc7d3ff0ff6f041
|
| 3 |
+
size 4610
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": null,
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": true
|
| 42 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.0780758393777385,
|
| 4 |
+
"train_runtime": 117810.8799,
|
| 5 |
+
"train_samples": 189709,
|
| 6 |
+
"train_samples_per_second": 1.61,
|
| 7 |
+
"train_steps_per_second": 0.003
|
| 8 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/trainer_state.json
ADDED
|
@@ -0,0 +1,2284 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9985662477861179,
|
| 5 |
+
"eval_steps": 126,
|
| 6 |
+
"global_step": 370,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 14 |
+
"loss": 2.21,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 20 |
+
"loss": 2.2098,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 5e-06,
|
| 26 |
+
"loss": 2.2183,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 6.666666666666667e-06,
|
| 32 |
+
"loss": 2.2003,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 8.333333333333334e-06,
|
| 38 |
+
"loss": 2.2081,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 1e-05,
|
| 44 |
+
"loss": 2.1861,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 50 |
+
"loss": 2.2021,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 56 |
+
"loss": 2.1958,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02,
|
| 61 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 62 |
+
"loss": 2.1541,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 68 |
+
"loss": 2.1845,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 74 |
+
"loss": 2.1596,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 2e-05,
|
| 80 |
+
"loss": 2.1891,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 1.9999614964379037e-05,
|
| 86 |
+
"loss": 2.1535,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 1.9998459887166635e-05,
|
| 92 |
+
"loss": 2.1483,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 1.9996534857311967e-05,
|
| 98 |
+
"loss": 2.1163,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.04,
|
| 103 |
+
"learning_rate": 1.9993840023056045e-05,
|
| 104 |
+
"loss": 2.1489,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 1.9990375591920304e-05,
|
| 110 |
+
"loss": 2.1474,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.05,
|
| 115 |
+
"learning_rate": 1.9986141830690626e-05,
|
| 116 |
+
"loss": 2.1534,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"learning_rate": 1.9981139065396786e-05,
|
| 122 |
+
"loss": 2.1407,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05,
|
| 127 |
+
"learning_rate": 1.9975367681287358e-05,
|
| 128 |
+
"loss": 2.1295,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 1.9968828122800022e-05,
|
| 134 |
+
"loss": 2.1063,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 1.9961520893527385e-05,
|
| 140 |
+
"loss": 2.1448,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.06,
|
| 145 |
+
"learning_rate": 1.995344655617815e-05,
|
| 146 |
+
"loss": 2.0936,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.06,
|
| 151 |
+
"learning_rate": 1.994460573253382e-05,
|
| 152 |
+
"loss": 2.1192,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 1.9934999103400797e-05,
|
| 158 |
+
"loss": 2.1278,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07,
|
| 163 |
+
"learning_rate": 1.9924627408557963e-05,
|
| 164 |
+
"loss": 2.1043,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.07,
|
| 169 |
+
"learning_rate": 1.9913491446699715e-05,
|
| 170 |
+
"loss": 2.1304,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 1.9901592075374447e-05,
|
| 176 |
+
"loss": 2.1273,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 1.988893021091853e-05,
|
| 182 |
+
"loss": 2.1117,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.08,
|
| 187 |
+
"learning_rate": 1.9875506828385723e-05,
|
| 188 |
+
"loss": 2.1223,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.08,
|
| 193 |
+
"learning_rate": 1.986132296147212e-05,
|
| 194 |
+
"loss": 2.1073,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.09,
|
| 199 |
+
"learning_rate": 1.9846379702436518e-05,
|
| 200 |
+
"loss": 2.1039,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.09,
|
| 205 |
+
"learning_rate": 1.9830678202016324e-05,
|
| 206 |
+
"loss": 2.125,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.09,
|
| 211 |
+
"learning_rate": 1.981421966933893e-05,
|
| 212 |
+
"loss": 2.1125,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.09,
|
| 217 |
+
"learning_rate": 1.9797005371828603e-05,
|
| 218 |
+
"loss": 2.087,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 1.9779036635108892e-05,
|
| 224 |
+
"loss": 2.1073,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.1,
|
| 229 |
+
"learning_rate": 1.9760314842900537e-05,
|
| 230 |
+
"loss": 2.124,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.1,
|
| 235 |
+
"learning_rate": 1.9740841436914917e-05,
|
| 236 |
+
"loss": 2.1016,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.11,
|
| 241 |
+
"learning_rate": 1.9720617916743022e-05,
|
| 242 |
+
"loss": 2.0938,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.11,
|
| 247 |
+
"learning_rate": 1.9699645839739987e-05,
|
| 248 |
+
"loss": 2.0955,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.11,
|
| 253 |
+
"learning_rate": 1.9677926820905143e-05,
|
| 254 |
+
"loss": 2.1009,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.11,
|
| 259 |
+
"learning_rate": 1.9655462532757677e-05,
|
| 260 |
+
"loss": 2.1044,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 1.9632254705207813e-05,
|
| 266 |
+
"loss": 2.1375,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12,
|
| 271 |
+
"learning_rate": 1.9608305125423608e-05,
|
| 272 |
+
"loss": 2.0873,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.12,
|
| 277 |
+
"learning_rate": 1.958361563769333e-05,
|
| 278 |
+
"loss": 2.0819,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.12,
|
| 283 |
+
"learning_rate": 1.9558188143283425e-05,
|
| 284 |
+
"loss": 2.1338,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.13,
|
| 289 |
+
"learning_rate": 1.9532024600292115e-05,
|
| 290 |
+
"loss": 2.1094,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.13,
|
| 295 |
+
"learning_rate": 1.9505127023498603e-05,
|
| 296 |
+
"loss": 2.1009,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.13,
|
| 301 |
+
"learning_rate": 1.9477497484207922e-05,
|
| 302 |
+
"loss": 2.1171,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.13,
|
| 307 |
+
"learning_rate": 1.9449138110091444e-05,
|
| 308 |
+
"loss": 2.1043,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.14,
|
| 313 |
+
"learning_rate": 1.9420051085023006e-05,
|
| 314 |
+
"loss": 2.0786,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.14,
|
| 319 |
+
"learning_rate": 1.9390238648910765e-05,
|
| 320 |
+
"loss": 2.0651,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.14,
|
| 325 |
+
"learning_rate": 1.935970309752469e-05,
|
| 326 |
+
"loss": 2.0847,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.15,
|
| 331 |
+
"learning_rate": 1.932844678231977e-05,
|
| 332 |
+
"loss": 2.0917,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.15,
|
| 337 |
+
"learning_rate": 1.929647211025497e-05,
|
| 338 |
+
"loss": 2.0831,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.15,
|
| 343 |
+
"learning_rate": 1.9263781543607817e-05,
|
| 344 |
+
"loss": 2.1077,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15,
|
| 349 |
+
"learning_rate": 1.923037759978484e-05,
|
| 350 |
+
"loss": 2.0894,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.16,
|
| 355 |
+
"learning_rate": 1.9196262851127695e-05,
|
| 356 |
+
"loss": 2.1217,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.16,
|
| 361 |
+
"learning_rate": 1.9161439924715063e-05,
|
| 362 |
+
"loss": 2.1162,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.16,
|
| 367 |
+
"learning_rate": 1.9125911502160365e-05,
|
| 368 |
+
"loss": 2.0804,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.16,
|
| 373 |
+
"learning_rate": 1.9089680319405252e-05,
|
| 374 |
+
"loss": 2.088,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.17,
|
| 379 |
+
"learning_rate": 1.905274916650891e-05,
|
| 380 |
+
"loss": 2.0784,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.17,
|
| 385 |
+
"learning_rate": 1.9015120887433215e-05,
|
| 386 |
+
"loss": 2.1028,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.17,
|
| 391 |
+
"learning_rate": 1.897679837982373e-05,
|
| 392 |
+
"loss": 2.097,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.18,
|
| 397 |
+
"learning_rate": 1.8937784594786562e-05,
|
| 398 |
+
"loss": 2.0901,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.18,
|
| 403 |
+
"learning_rate": 1.8898082536661097e-05,
|
| 404 |
+
"loss": 2.082,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.18,
|
| 409 |
+
"learning_rate": 1.885769526278865e-05,
|
| 410 |
+
"loss": 2.0889,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.18,
|
| 415 |
+
"learning_rate": 1.8816625883277044e-05,
|
| 416 |
+
"loss": 2.1066,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.19,
|
| 421 |
+
"learning_rate": 1.8774877560761082e-05,
|
| 422 |
+
"loss": 2.0974,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.19,
|
| 427 |
+
"learning_rate": 1.8732453510159025e-05,
|
| 428 |
+
"loss": 2.0805,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"learning_rate": 1.8689356998425007e-05,
|
| 434 |
+
"loss": 2.1094,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.19,
|
| 439 |
+
"learning_rate": 1.864559134429745e-05,
|
| 440 |
+
"loss": 2.069,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.2,
|
| 445 |
+
"learning_rate": 1.8601159918043533e-05,
|
| 446 |
+
"loss": 2.0891,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.2,
|
| 451 |
+
"learning_rate": 1.85560661411996e-05,
|
| 452 |
+
"loss": 2.0874,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.2,
|
| 457 |
+
"learning_rate": 1.8510313486307734e-05,
|
| 458 |
+
"loss": 2.0652,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.21,
|
| 463 |
+
"learning_rate": 1.846390547664831e-05,
|
| 464 |
+
"loss": 2.1123,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.21,
|
| 469 |
+
"learning_rate": 1.841684568596869e-05,
|
| 470 |
+
"loss": 2.061,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"learning_rate": 1.836913773820802e-05,
|
| 476 |
+
"loss": 2.0906,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.21,
|
| 481 |
+
"learning_rate": 1.832078530721816e-05,
|
| 482 |
+
"loss": 2.0882,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.22,
|
| 487 |
+
"learning_rate": 1.8271792116480767e-05,
|
| 488 |
+
"loss": 2.0843,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.22,
|
| 493 |
+
"learning_rate": 1.8222161938820564e-05,
|
| 494 |
+
"loss": 2.0985,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.22,
|
| 499 |
+
"learning_rate": 1.8171898596114804e-05,
|
| 500 |
+
"loss": 2.0684,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.22,
|
| 505 |
+
"learning_rate": 1.8121005958998968e-05,
|
| 506 |
+
"loss": 2.0736,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.23,
|
| 511 |
+
"learning_rate": 1.8069487946568675e-05,
|
| 512 |
+
"loss": 2.079,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"learning_rate": 1.801734852607791e-05,
|
| 518 |
+
"loss": 2.1056,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.23,
|
| 523 |
+
"learning_rate": 1.79645917126335e-05,
|
| 524 |
+
"loss": 2.058,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.23,
|
| 529 |
+
"learning_rate": 1.7911221568885935e-05,
|
| 530 |
+
"loss": 2.0838,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.24,
|
| 535 |
+
"learning_rate": 1.7857242204716497e-05,
|
| 536 |
+
"loss": 2.0812,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.24,
|
| 541 |
+
"learning_rate": 1.780265777692079e-05,
|
| 542 |
+
"loss": 2.0915,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.24,
|
| 547 |
+
"learning_rate": 1.7747472488888622e-05,
|
| 548 |
+
"loss": 2.0966,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.25,
|
| 553 |
+
"learning_rate": 1.7691690590280325e-05,
|
| 554 |
+
"loss": 2.0744,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.25,
|
| 559 |
+
"learning_rate": 1.763531637669949e-05,
|
| 560 |
+
"loss": 2.0937,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.25,
|
| 565 |
+
"learning_rate": 1.7578354189362183e-05,
|
| 566 |
+
"loss": 2.0686,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.25,
|
| 571 |
+
"learning_rate": 1.752080841476264e-05,
|
| 572 |
+
"loss": 2.0861,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.26,
|
| 577 |
+
"learning_rate": 1.7462683484335477e-05,
|
| 578 |
+
"loss": 2.0828,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.26,
|
| 583 |
+
"learning_rate": 1.7403983874114422e-05,
|
| 584 |
+
"loss": 2.047,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.26,
|
| 589 |
+
"learning_rate": 1.734471410438765e-05,
|
| 590 |
+
"loss": 2.0738,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.26,
|
| 595 |
+
"learning_rate": 1.728487873934969e-05,
|
| 596 |
+
"loss": 2.075,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.27,
|
| 601 |
+
"learning_rate": 1.7224482386749916e-05,
|
| 602 |
+
"loss": 2.0851,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.27,
|
| 607 |
+
"learning_rate": 1.7163529697537756e-05,
|
| 608 |
+
"loss": 2.094,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.27,
|
| 613 |
+
"learning_rate": 1.7102025365504524e-05,
|
| 614 |
+
"loss": 2.097,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.28,
|
| 619 |
+
"learning_rate": 1.7039974126921946e-05,
|
| 620 |
+
"loss": 2.099,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.28,
|
| 625 |
+
"learning_rate": 1.6977380760177467e-05,
|
| 626 |
+
"loss": 2.0643,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.28,
|
| 631 |
+
"learning_rate": 1.691425008540625e-05,
|
| 632 |
+
"loss": 2.0612,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.28,
|
| 637 |
+
"learning_rate": 1.6850586964120005e-05,
|
| 638 |
+
"loss": 2.0789,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.29,
|
| 643 |
+
"learning_rate": 1.6786396298832622e-05,
|
| 644 |
+
"loss": 2.0637,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.29,
|
| 649 |
+
"learning_rate": 1.6721683032682637e-05,
|
| 650 |
+
"loss": 2.0617,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.29,
|
| 655 |
+
"learning_rate": 1.6656452149052568e-05,
|
| 656 |
+
"loss": 2.0452,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.29,
|
| 661 |
+
"learning_rate": 1.6590708671185176e-05,
|
| 662 |
+
"loss": 2.0909,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.3,
|
| 667 |
+
"learning_rate": 1.6524457661796626e-05,
|
| 668 |
+
"loss": 2.0807,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.3,
|
| 673 |
+
"learning_rate": 1.645770422268662e-05,
|
| 674 |
+
"loss": 2.0926,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3,
|
| 679 |
+
"learning_rate": 1.639045349434554e-05,
|
| 680 |
+
"loss": 2.0827,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3,
|
| 685 |
+
"learning_rate": 1.6322710655558577e-05,
|
| 686 |
+
"loss": 2.0636,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.31,
|
| 691 |
+
"learning_rate": 1.6254480923006924e-05,
|
| 692 |
+
"loss": 2.0594,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.31,
|
| 697 |
+
"learning_rate": 1.6185769550866073e-05,
|
| 698 |
+
"loss": 2.0684,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.31,
|
| 703 |
+
"learning_rate": 1.6116581830401193e-05,
|
| 704 |
+
"loss": 2.0152,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.32,
|
| 709 |
+
"learning_rate": 1.6046923089559667e-05,
|
| 710 |
+
"loss": 2.0642,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.32,
|
| 715 |
+
"learning_rate": 1.5976798692560796e-05,
|
| 716 |
+
"loss": 2.0832,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.32,
|
| 721 |
+
"learning_rate": 1.5906214039482732e-05,
|
| 722 |
+
"loss": 2.0637,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.32,
|
| 727 |
+
"learning_rate": 1.5835174565846624e-05,
|
| 728 |
+
"loss": 2.0457,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.33,
|
| 733 |
+
"learning_rate": 1.576368574219804e-05,
|
| 734 |
+
"loss": 2.07,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.33,
|
| 739 |
+
"learning_rate": 1.5691753073685692e-05,
|
| 740 |
+
"loss": 2.0799,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.33,
|
| 745 |
+
"learning_rate": 1.561938209963753e-05,
|
| 746 |
+
"loss": 2.0817,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.33,
|
| 751 |
+
"learning_rate": 1.554657839313413e-05,
|
| 752 |
+
"loss": 2.0782,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.34,
|
| 757 |
+
"learning_rate": 1.5473347560579576e-05,
|
| 758 |
+
"loss": 2.0516,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.34,
|
| 763 |
+
"learning_rate": 1.539969524126967e-05,
|
| 764 |
+
"loss": 2.0801,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.34,
|
| 769 |
+
"eval_c4_accuracy": 0.5405555183054839,
|
| 770 |
+
"eval_c4_loss": 2.0783538818359375,
|
| 771 |
+
"eval_c4_runtime": 2322.9595,
|
| 772 |
+
"eval_c4_samples_per_second": 5.134,
|
| 773 |
+
"eval_c4_steps_per_second": 0.642,
|
| 774 |
+
"step": 126
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.34,
|
| 778 |
+
"eval_wikitext_accuracy": 0.5984131935656647,
|
| 779 |
+
"eval_wikitext_loss": 1.7553809881210327,
|
| 780 |
+
"eval_wikitext_runtime": 35.2285,
|
| 781 |
+
"eval_wikitext_samples_per_second": 4.712,
|
| 782 |
+
"eval_wikitext_steps_per_second": 0.596,
|
| 783 |
+
"step": 126
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.34,
|
| 787 |
+
"learning_rate": 1.5325627106957715e-05,
|
| 788 |
+
"loss": 2.05,
|
| 789 |
+
"step": 127
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.35,
|
| 793 |
+
"learning_rate": 1.5251148861417733e-05,
|
| 794 |
+
"loss": 2.0605,
|
| 795 |
+
"step": 128
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.35,
|
| 799 |
+
"learning_rate": 1.5176266240005225e-05,
|
| 800 |
+
"loss": 2.0831,
|
| 801 |
+
"step": 129
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.35,
|
| 805 |
+
"learning_rate": 1.5100985009215519e-05,
|
| 806 |
+
"loss": 2.0585,
|
| 807 |
+
"step": 130
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.35,
|
| 811 |
+
"learning_rate": 1.5025310966239701e-05,
|
| 812 |
+
"loss": 2.1019,
|
| 813 |
+
"step": 131
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.36,
|
| 817 |
+
"learning_rate": 1.4949249938518203e-05,
|
| 818 |
+
"loss": 2.067,
|
| 819 |
+
"step": 132
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.36,
|
| 823 |
+
"learning_rate": 1.4872807783292027e-05,
|
| 824 |
+
"loss": 2.0905,
|
| 825 |
+
"step": 133
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.36,
|
| 829 |
+
"learning_rate": 1.4795990387151719e-05,
|
| 830 |
+
"loss": 2.0819,
|
| 831 |
+
"step": 134
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.36,
|
| 835 |
+
"learning_rate": 1.4718803665584038e-05,
|
| 836 |
+
"loss": 2.0574,
|
| 837 |
+
"step": 135
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.37,
|
| 841 |
+
"learning_rate": 1.464125356251644e-05,
|
| 842 |
+
"loss": 2.0445,
|
| 843 |
+
"step": 136
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.37,
|
| 847 |
+
"learning_rate": 1.4563346049859348e-05,
|
| 848 |
+
"loss": 2.0537,
|
| 849 |
+
"step": 137
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.37,
|
| 853 |
+
"learning_rate": 1.4485087127046256e-05,
|
| 854 |
+
"loss": 2.0638,
|
| 855 |
+
"step": 138
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.38,
|
| 859 |
+
"learning_rate": 1.4406482820571759e-05,
|
| 860 |
+
"loss": 2.0888,
|
| 861 |
+
"step": 139
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.38,
|
| 865 |
+
"learning_rate": 1.4327539183527447e-05,
|
| 866 |
+
"loss": 2.0713,
|
| 867 |
+
"step": 140
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.38,
|
| 871 |
+
"learning_rate": 1.4248262295135779e-05,
|
| 872 |
+
"loss": 2.0515,
|
| 873 |
+
"step": 141
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.38,
|
| 877 |
+
"learning_rate": 1.4168658260281944e-05,
|
| 878 |
+
"loss": 2.0645,
|
| 879 |
+
"step": 142
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.39,
|
| 883 |
+
"learning_rate": 1.4088733209043748e-05,
|
| 884 |
+
"loss": 2.0624,
|
| 885 |
+
"step": 143
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.39,
|
| 889 |
+
"learning_rate": 1.400849329621953e-05,
|
| 890 |
+
"loss": 2.0571,
|
| 891 |
+
"step": 144
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.39,
|
| 895 |
+
"learning_rate": 1.3927944700854223e-05,
|
| 896 |
+
"loss": 2.0781,
|
| 897 |
+
"step": 145
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.39,
|
| 901 |
+
"learning_rate": 1.3847093625763517e-05,
|
| 902 |
+
"loss": 2.0888,
|
| 903 |
+
"step": 146
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.4,
|
| 907 |
+
"learning_rate": 1.3765946297056192e-05,
|
| 908 |
+
"loss": 2.0507,
|
| 909 |
+
"step": 147
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.4,
|
| 913 |
+
"learning_rate": 1.3684508963654667e-05,
|
| 914 |
+
"loss": 2.0506,
|
| 915 |
+
"step": 148
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.4,
|
| 919 |
+
"learning_rate": 1.3602787896813787e-05,
|
| 920 |
+
"loss": 2.0678,
|
| 921 |
+
"step": 149
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.4,
|
| 925 |
+
"learning_rate": 1.3520789389637898e-05,
|
| 926 |
+
"loss": 2.0657,
|
| 927 |
+
"step": 150
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.41,
|
| 931 |
+
"learning_rate": 1.3438519756596226e-05,
|
| 932 |
+
"loss": 2.0569,
|
| 933 |
+
"step": 151
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.41,
|
| 937 |
+
"learning_rate": 1.335598533303662e-05,
|
| 938 |
+
"loss": 2.095,
|
| 939 |
+
"step": 152
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.41,
|
| 943 |
+
"learning_rate": 1.327319247469768e-05,
|
| 944 |
+
"loss": 2.0473,
|
| 945 |
+
"step": 153
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.42,
|
| 949 |
+
"learning_rate": 1.319014755721934e-05,
|
| 950 |
+
"loss": 2.0439,
|
| 951 |
+
"step": 154
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.42,
|
| 955 |
+
"learning_rate": 1.3106856975651866e-05,
|
| 956 |
+
"loss": 2.0655,
|
| 957 |
+
"step": 155
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.42,
|
| 961 |
+
"learning_rate": 1.3023327143963415e-05,
|
| 962 |
+
"loss": 2.0757,
|
| 963 |
+
"step": 156
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.42,
|
| 967 |
+
"learning_rate": 1.293956449454612e-05,
|
| 968 |
+
"loss": 2.0899,
|
| 969 |
+
"step": 157
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.43,
|
| 973 |
+
"learning_rate": 1.285557547772072e-05,
|
| 974 |
+
"loss": 2.0625,
|
| 975 |
+
"step": 158
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.43,
|
| 979 |
+
"learning_rate": 1.2771366561239865e-05,
|
| 980 |
+
"loss": 2.0753,
|
| 981 |
+
"step": 159
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.43,
|
| 985 |
+
"learning_rate": 1.2686944229790044e-05,
|
| 986 |
+
"loss": 2.081,
|
| 987 |
+
"step": 160
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.43,
|
| 991 |
+
"learning_rate": 1.2602314984492222e-05,
|
| 992 |
+
"loss": 2.0547,
|
| 993 |
+
"step": 161
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.44,
|
| 997 |
+
"learning_rate": 1.2517485342401201e-05,
|
| 998 |
+
"loss": 2.0403,
|
| 999 |
+
"step": 162
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.44,
|
| 1003 |
+
"learning_rate": 1.2432461836003762e-05,
|
| 1004 |
+
"loss": 2.0726,
|
| 1005 |
+
"step": 163
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.44,
|
| 1009 |
+
"learning_rate": 1.2347251012715629e-05,
|
| 1010 |
+
"loss": 2.0646,
|
| 1011 |
+
"step": 164
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.45,
|
| 1015 |
+
"learning_rate": 1.2261859434377245e-05,
|
| 1016 |
+
"loss": 2.0735,
|
| 1017 |
+
"step": 165
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.45,
|
| 1021 |
+
"learning_rate": 1.2176293676748494e-05,
|
| 1022 |
+
"loss": 2.0947,
|
| 1023 |
+
"step": 166
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.45,
|
| 1027 |
+
"learning_rate": 1.2090560329002294e-05,
|
| 1028 |
+
"loss": 2.0613,
|
| 1029 |
+
"step": 167
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.45,
|
| 1033 |
+
"learning_rate": 1.200466599321721e-05,
|
| 1034 |
+
"loss": 2.0824,
|
| 1035 |
+
"step": 168
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.46,
|
| 1039 |
+
"learning_rate": 1.1918617283869021e-05,
|
| 1040 |
+
"loss": 2.0698,
|
| 1041 |
+
"step": 169
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.46,
|
| 1045 |
+
"learning_rate": 1.1832420827321374e-05,
|
| 1046 |
+
"loss": 2.0509,
|
| 1047 |
+
"step": 170
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.46,
|
| 1051 |
+
"learning_rate": 1.1746083261315505e-05,
|
| 1052 |
+
"loss": 2.0406,
|
| 1053 |
+
"step": 171
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.46,
|
| 1057 |
+
"learning_rate": 1.165961123445908e-05,
|
| 1058 |
+
"loss": 2.094,
|
| 1059 |
+
"step": 172
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.47,
|
| 1063 |
+
"learning_rate": 1.1573011405714214e-05,
|
| 1064 |
+
"loss": 2.0593,
|
| 1065 |
+
"step": 173
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.47,
|
| 1069 |
+
"learning_rate": 1.1486290443884666e-05,
|
| 1070 |
+
"loss": 2.0695,
|
| 1071 |
+
"step": 174
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.47,
|
| 1075 |
+
"learning_rate": 1.1399455027102327e-05,
|
| 1076 |
+
"loss": 2.0659,
|
| 1077 |
+
"step": 175
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.47,
|
| 1081 |
+
"learning_rate": 1.131251184231291e-05,
|
| 1082 |
+
"loss": 2.0941,
|
| 1083 |
+
"step": 176
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.48,
|
| 1087 |
+
"learning_rate": 1.122546758476105e-05,
|
| 1088 |
+
"loss": 2.0684,
|
| 1089 |
+
"step": 177
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.48,
|
| 1093 |
+
"learning_rate": 1.1138328957474691e-05,
|
| 1094 |
+
"loss": 2.0828,
|
| 1095 |
+
"step": 178
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.48,
|
| 1099 |
+
"learning_rate": 1.1051102670748939e-05,
|
| 1100 |
+
"loss": 2.0742,
|
| 1101 |
+
"step": 179
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.49,
|
| 1105 |
+
"learning_rate": 1.0963795441629275e-05,
|
| 1106 |
+
"loss": 2.0707,
|
| 1107 |
+
"step": 180
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.49,
|
| 1111 |
+
"learning_rate": 1.0876413993394346e-05,
|
| 1112 |
+
"loss": 2.0698,
|
| 1113 |
+
"step": 181
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.49,
|
| 1117 |
+
"learning_rate": 1.0788965055038179e-05,
|
| 1118 |
+
"loss": 2.0768,
|
| 1119 |
+
"step": 182
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.49,
|
| 1123 |
+
"learning_rate": 1.0701455360752038e-05,
|
| 1124 |
+
"loss": 2.0579,
|
| 1125 |
+
"step": 183
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.5,
|
| 1129 |
+
"learning_rate": 1.0613891649405816e-05,
|
| 1130 |
+
"loss": 2.0304,
|
| 1131 |
+
"step": 184
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.5,
|
| 1135 |
+
"learning_rate": 1.0526280664029105e-05,
|
| 1136 |
+
"loss": 2.0834,
|
| 1137 |
+
"step": 185
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.5,
|
| 1141 |
+
"learning_rate": 1.0438629151291944e-05,
|
| 1142 |
+
"loss": 2.0879,
|
| 1143 |
+
"step": 186
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.5,
|
| 1147 |
+
"learning_rate": 1.0350943860985249e-05,
|
| 1148 |
+
"loss": 2.0658,
|
| 1149 |
+
"step": 187
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.51,
|
| 1153 |
+
"learning_rate": 1.0263231545501068e-05,
|
| 1154 |
+
"loss": 2.0484,
|
| 1155 |
+
"step": 188
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.51,
|
| 1159 |
+
"learning_rate": 1.0175498959312572e-05,
|
| 1160 |
+
"loss": 2.0518,
|
| 1161 |
+
"step": 189
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.51,
|
| 1165 |
+
"learning_rate": 1.0087752858453923e-05,
|
| 1166 |
+
"loss": 2.0609,
|
| 1167 |
+
"step": 190
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.52,
|
| 1171 |
+
"learning_rate": 1e-05,
|
| 1172 |
+
"loss": 2.0516,
|
| 1173 |
+
"step": 191
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.52,
|
| 1177 |
+
"learning_rate": 9.91224714154608e-06,
|
| 1178 |
+
"loss": 2.0543,
|
| 1179 |
+
"step": 192
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.52,
|
| 1183 |
+
"learning_rate": 9.82450104068743e-06,
|
| 1184 |
+
"loss": 2.0704,
|
| 1185 |
+
"step": 193
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.52,
|
| 1189 |
+
"learning_rate": 9.736768454498935e-06,
|
| 1190 |
+
"loss": 2.0526,
|
| 1191 |
+
"step": 194
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.53,
|
| 1195 |
+
"learning_rate": 9.649056139014754e-06,
|
| 1196 |
+
"loss": 2.1021,
|
| 1197 |
+
"step": 195
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.53,
|
| 1201 |
+
"learning_rate": 9.561370848708061e-06,
|
| 1202 |
+
"loss": 2.0613,
|
| 1203 |
+
"step": 196
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.53,
|
| 1207 |
+
"learning_rate": 9.473719335970896e-06,
|
| 1208 |
+
"loss": 2.0704,
|
| 1209 |
+
"step": 197
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.53,
|
| 1213 |
+
"learning_rate": 9.38610835059419e-06,
|
| 1214 |
+
"loss": 2.0769,
|
| 1215 |
+
"step": 198
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.54,
|
| 1219 |
+
"learning_rate": 9.298544639247965e-06,
|
| 1220 |
+
"loss": 2.0484,
|
| 1221 |
+
"step": 199
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.54,
|
| 1225 |
+
"learning_rate": 9.211034944961825e-06,
|
| 1226 |
+
"loss": 2.0687,
|
| 1227 |
+
"step": 200
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.54,
|
| 1231 |
+
"learning_rate": 9.123586006605658e-06,
|
| 1232 |
+
"loss": 2.0724,
|
| 1233 |
+
"step": 201
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.55,
|
| 1237 |
+
"learning_rate": 9.036204558370725e-06,
|
| 1238 |
+
"loss": 2.0468,
|
| 1239 |
+
"step": 202
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.55,
|
| 1243 |
+
"learning_rate": 8.948897329251066e-06,
|
| 1244 |
+
"loss": 2.0676,
|
| 1245 |
+
"step": 203
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.55,
|
| 1249 |
+
"learning_rate": 8.861671042525312e-06,
|
| 1250 |
+
"loss": 2.0606,
|
| 1251 |
+
"step": 204
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.55,
|
| 1255 |
+
"learning_rate": 8.774532415238954e-06,
|
| 1256 |
+
"loss": 2.0504,
|
| 1257 |
+
"step": 205
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.56,
|
| 1261 |
+
"learning_rate": 8.68748815768709e-06,
|
| 1262 |
+
"loss": 2.0577,
|
| 1263 |
+
"step": 206
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.56,
|
| 1267 |
+
"learning_rate": 8.600544972897678e-06,
|
| 1268 |
+
"loss": 2.0958,
|
| 1269 |
+
"step": 207
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.56,
|
| 1273 |
+
"learning_rate": 8.513709556115335e-06,
|
| 1274 |
+
"loss": 2.071,
|
| 1275 |
+
"step": 208
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.56,
|
| 1279 |
+
"learning_rate": 8.42698859428579e-06,
|
| 1280 |
+
"loss": 2.0418,
|
| 1281 |
+
"step": 209
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.57,
|
| 1285 |
+
"learning_rate": 8.340388765540923e-06,
|
| 1286 |
+
"loss": 2.078,
|
| 1287 |
+
"step": 210
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.57,
|
| 1291 |
+
"learning_rate": 8.253916738684497e-06,
|
| 1292 |
+
"loss": 2.0766,
|
| 1293 |
+
"step": 211
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.57,
|
| 1297 |
+
"learning_rate": 8.16757917267863e-06,
|
| 1298 |
+
"loss": 2.0798,
|
| 1299 |
+
"step": 212
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.57,
|
| 1303 |
+
"learning_rate": 8.081382716130982e-06,
|
| 1304 |
+
"loss": 2.0689,
|
| 1305 |
+
"step": 213
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.58,
|
| 1309 |
+
"learning_rate": 7.995334006782793e-06,
|
| 1310 |
+
"loss": 2.0657,
|
| 1311 |
+
"step": 214
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.58,
|
| 1315 |
+
"learning_rate": 7.909439670997706e-06,
|
| 1316 |
+
"loss": 2.0827,
|
| 1317 |
+
"step": 215
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.58,
|
| 1321 |
+
"learning_rate": 7.823706323251512e-06,
|
| 1322 |
+
"loss": 2.0831,
|
| 1323 |
+
"step": 216
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.59,
|
| 1327 |
+
"learning_rate": 7.738140565622758e-06,
|
| 1328 |
+
"loss": 2.063,
|
| 1329 |
+
"step": 217
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.59,
|
| 1333 |
+
"learning_rate": 7.652748987284375e-06,
|
| 1334 |
+
"loss": 2.0697,
|
| 1335 |
+
"step": 218
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.59,
|
| 1339 |
+
"learning_rate": 7.567538163996237e-06,
|
| 1340 |
+
"loss": 2.0534,
|
| 1341 |
+
"step": 219
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.59,
|
| 1345 |
+
"learning_rate": 7.4825146575988e-06,
|
| 1346 |
+
"loss": 2.0394,
|
| 1347 |
+
"step": 220
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.6,
|
| 1351 |
+
"learning_rate": 7.397685015507781e-06,
|
| 1352 |
+
"loss": 2.0585,
|
| 1353 |
+
"step": 221
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.6,
|
| 1357 |
+
"learning_rate": 7.313055770209961e-06,
|
| 1358 |
+
"loss": 2.0597,
|
| 1359 |
+
"step": 222
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.6,
|
| 1363 |
+
"learning_rate": 7.228633438760138e-06,
|
| 1364 |
+
"loss": 2.0787,
|
| 1365 |
+
"step": 223
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.6,
|
| 1369 |
+
"learning_rate": 7.144424522279283e-06,
|
| 1370 |
+
"loss": 2.0706,
|
| 1371 |
+
"step": 224
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.61,
|
| 1375 |
+
"learning_rate": 7.060435505453884e-06,
|
| 1376 |
+
"loss": 2.0599,
|
| 1377 |
+
"step": 225
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.61,
|
| 1381 |
+
"learning_rate": 6.976672856036586e-06,
|
| 1382 |
+
"loss": 2.0483,
|
| 1383 |
+
"step": 226
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.61,
|
| 1387 |
+
"learning_rate": 6.893143024348137e-06,
|
| 1388 |
+
"loss": 2.0337,
|
| 1389 |
+
"step": 227
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.62,
|
| 1393 |
+
"learning_rate": 6.809852442780664e-06,
|
| 1394 |
+
"loss": 2.0651,
|
| 1395 |
+
"step": 228
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.62,
|
| 1399 |
+
"learning_rate": 6.726807525302319e-06,
|
| 1400 |
+
"loss": 2.0769,
|
| 1401 |
+
"step": 229
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.62,
|
| 1405 |
+
"learning_rate": 6.6440146669633855e-06,
|
| 1406 |
+
"loss": 2.0566,
|
| 1407 |
+
"step": 230
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.62,
|
| 1411 |
+
"learning_rate": 6.561480243403776e-06,
|
| 1412 |
+
"loss": 2.0782,
|
| 1413 |
+
"step": 231
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.63,
|
| 1417 |
+
"learning_rate": 6.479210610362103e-06,
|
| 1418 |
+
"loss": 2.0427,
|
| 1419 |
+
"step": 232
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.63,
|
| 1423 |
+
"learning_rate": 6.397212103186214e-06,
|
| 1424 |
+
"loss": 2.0986,
|
| 1425 |
+
"step": 233
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.63,
|
| 1429 |
+
"learning_rate": 6.315491036345338e-06,
|
| 1430 |
+
"loss": 2.0712,
|
| 1431 |
+
"step": 234
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.63,
|
| 1435 |
+
"learning_rate": 6.23405370294381e-06,
|
| 1436 |
+
"loss": 2.0469,
|
| 1437 |
+
"step": 235
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.64,
|
| 1441 |
+
"learning_rate": 6.1529063742364844e-06,
|
| 1442 |
+
"loss": 2.0808,
|
| 1443 |
+
"step": 236
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.64,
|
| 1447 |
+
"learning_rate": 6.072055299145778e-06,
|
| 1448 |
+
"loss": 2.0919,
|
| 1449 |
+
"step": 237
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.64,
|
| 1453 |
+
"learning_rate": 5.991506703780475e-06,
|
| 1454 |
+
"loss": 2.0725,
|
| 1455 |
+
"step": 238
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.65,
|
| 1459 |
+
"learning_rate": 5.911266790956258e-06,
|
| 1460 |
+
"loss": 2.0708,
|
| 1461 |
+
"step": 239
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.65,
|
| 1465 |
+
"learning_rate": 5.831341739718055e-06,
|
| 1466 |
+
"loss": 2.0768,
|
| 1467 |
+
"step": 240
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.65,
|
| 1471 |
+
"learning_rate": 5.751737704864224e-06,
|
| 1472 |
+
"loss": 2.0435,
|
| 1473 |
+
"step": 241
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.65,
|
| 1477 |
+
"learning_rate": 5.672460816472556e-06,
|
| 1478 |
+
"loss": 2.0493,
|
| 1479 |
+
"step": 242
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.66,
|
| 1483 |
+
"learning_rate": 5.5935171794282426e-06,
|
| 1484 |
+
"loss": 2.0927,
|
| 1485 |
+
"step": 243
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.66,
|
| 1489 |
+
"learning_rate": 5.514912872953746e-06,
|
| 1490 |
+
"loss": 2.0303,
|
| 1491 |
+
"step": 244
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.66,
|
| 1495 |
+
"learning_rate": 5.436653950140657e-06,
|
| 1496 |
+
"loss": 2.064,
|
| 1497 |
+
"step": 245
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.66,
|
| 1501 |
+
"learning_rate": 5.35874643748356e-06,
|
| 1502 |
+
"loss": 2.087,
|
| 1503 |
+
"step": 246
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.67,
|
| 1507 |
+
"learning_rate": 5.281196334415968e-06,
|
| 1508 |
+
"loss": 2.0528,
|
| 1509 |
+
"step": 247
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.67,
|
| 1513 |
+
"learning_rate": 5.204009612848288e-06,
|
| 1514 |
+
"loss": 2.0827,
|
| 1515 |
+
"step": 248
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.67,
|
| 1519 |
+
"learning_rate": 5.127192216707974e-06,
|
| 1520 |
+
"loss": 2.064,
|
| 1521 |
+
"step": 249
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.67,
|
| 1525 |
+
"learning_rate": 5.050750061481799e-06,
|
| 1526 |
+
"loss": 2.0818,
|
| 1527 |
+
"step": 250
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.68,
|
| 1531 |
+
"learning_rate": 4.9746890337603005e-06,
|
| 1532 |
+
"loss": 2.0553,
|
| 1533 |
+
"step": 251
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.68,
|
| 1537 |
+
"learning_rate": 4.899014990784485e-06,
|
| 1538 |
+
"loss": 2.0617,
|
| 1539 |
+
"step": 252
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.68,
|
| 1543 |
+
"eval_c4_accuracy": 0.541675054759312,
|
| 1544 |
+
"eval_c4_loss": 2.0723888874053955,
|
| 1545 |
+
"eval_c4_runtime": 2327.2601,
|
| 1546 |
+
"eval_c4_samples_per_second": 5.125,
|
| 1547 |
+
"eval_c4_steps_per_second": 0.641,
|
| 1548 |
+
"step": 252
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.68,
|
| 1552 |
+
"eval_wikitext_accuracy": 0.6012766257997304,
|
| 1553 |
+
"eval_wikitext_loss": 1.7378333806991577,
|
| 1554 |
+
"eval_wikitext_runtime": 41.621,
|
| 1555 |
+
"eval_wikitext_samples_per_second": 3.988,
|
| 1556 |
+
"eval_wikitext_steps_per_second": 0.505,
|
| 1557 |
+
"step": 252
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.68,
|
| 1561 |
+
"learning_rate": 4.8237337599947795e-06,
|
| 1562 |
+
"loss": 2.0933,
|
| 1563 |
+
"step": 253
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.69,
|
| 1567 |
+
"learning_rate": 4.748851138582269e-06,
|
| 1568 |
+
"loss": 2.0743,
|
| 1569 |
+
"step": 254
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.69,
|
| 1573 |
+
"learning_rate": 4.674372893042287e-06,
|
| 1574 |
+
"loss": 2.0574,
|
| 1575 |
+
"step": 255
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.69,
|
| 1579 |
+
"learning_rate": 4.6003047587303376e-06,
|
| 1580 |
+
"loss": 2.0618,
|
| 1581 |
+
"step": 256
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.69,
|
| 1585 |
+
"learning_rate": 4.526652439420427e-06,
|
| 1586 |
+
"loss": 2.0684,
|
| 1587 |
+
"step": 257
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.7,
|
| 1591 |
+
"learning_rate": 4.453421606865869e-06,
|
| 1592 |
+
"loss": 2.0546,
|
| 1593 |
+
"step": 258
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.7,
|
| 1597 |
+
"learning_rate": 4.380617900362473e-06,
|
| 1598 |
+
"loss": 2.0577,
|
| 1599 |
+
"step": 259
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.7,
|
| 1603 |
+
"learning_rate": 4.308246926314307e-06,
|
| 1604 |
+
"loss": 2.0599,
|
| 1605 |
+
"step": 260
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.7,
|
| 1609 |
+
"learning_rate": 4.236314257801968e-06,
|
| 1610 |
+
"loss": 2.0758,
|
| 1611 |
+
"step": 261
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.71,
|
| 1615 |
+
"learning_rate": 4.164825434153381e-06,
|
| 1616 |
+
"loss": 2.0402,
|
| 1617 |
+
"step": 262
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.71,
|
| 1621 |
+
"learning_rate": 4.093785960517269e-06,
|
| 1622 |
+
"loss": 2.0518,
|
| 1623 |
+
"step": 263
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.71,
|
| 1627 |
+
"learning_rate": 4.0232013074392065e-06,
|
| 1628 |
+
"loss": 2.0771,
|
| 1629 |
+
"step": 264
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.72,
|
| 1633 |
+
"learning_rate": 3.953076910440337e-06,
|
| 1634 |
+
"loss": 2.0716,
|
| 1635 |
+
"step": 265
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.72,
|
| 1639 |
+
"learning_rate": 3.883418169598808e-06,
|
| 1640 |
+
"loss": 2.0648,
|
| 1641 |
+
"step": 266
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.72,
|
| 1645 |
+
"learning_rate": 3.814230449133928e-06,
|
| 1646 |
+
"loss": 2.0562,
|
| 1647 |
+
"step": 267
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.72,
|
| 1651 |
+
"learning_rate": 3.745519076993078e-06,
|
| 1652 |
+
"loss": 2.0442,
|
| 1653 |
+
"step": 268
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.73,
|
| 1657 |
+
"learning_rate": 3.6772893444414226e-06,
|
| 1658 |
+
"loss": 2.0825,
|
| 1659 |
+
"step": 269
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.73,
|
| 1663 |
+
"learning_rate": 3.609546505654462e-06,
|
| 1664 |
+
"loss": 2.0489,
|
| 1665 |
+
"step": 270
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.73,
|
| 1669 |
+
"learning_rate": 3.5422957773133804e-06,
|
| 1670 |
+
"loss": 2.0646,
|
| 1671 |
+
"step": 271
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.73,
|
| 1675 |
+
"learning_rate": 3.475542338203377e-06,
|
| 1676 |
+
"loss": 2.0631,
|
| 1677 |
+
"step": 272
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.74,
|
| 1681 |
+
"learning_rate": 3.4092913288148254e-06,
|
| 1682 |
+
"loss": 2.0707,
|
| 1683 |
+
"step": 273
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.74,
|
| 1687 |
+
"learning_rate": 3.343547850947434e-06,
|
| 1688 |
+
"loss": 2.0643,
|
| 1689 |
+
"step": 274
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.74,
|
| 1693 |
+
"learning_rate": 3.2783169673173666e-06,
|
| 1694 |
+
"loss": 2.0674,
|
| 1695 |
+
"step": 275
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.74,
|
| 1699 |
+
"learning_rate": 3.2136037011673803e-06,
|
| 1700 |
+
"loss": 2.0907,
|
| 1701 |
+
"step": 276
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.75,
|
| 1705 |
+
"learning_rate": 3.149413035879996e-06,
|
| 1706 |
+
"loss": 2.068,
|
| 1707 |
+
"step": 277
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.75,
|
| 1711 |
+
"learning_rate": 3.085749914593752e-06,
|
| 1712 |
+
"loss": 2.0612,
|
| 1713 |
+
"step": 278
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.75,
|
| 1717 |
+
"learning_rate": 3.022619239822535e-06,
|
| 1718 |
+
"loss": 2.0647,
|
| 1719 |
+
"step": 279
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.76,
|
| 1723 |
+
"learning_rate": 2.9600258730780564e-06,
|
| 1724 |
+
"loss": 2.0515,
|
| 1725 |
+
"step": 280
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.76,
|
| 1729 |
+
"learning_rate": 2.897974634495482e-06,
|
| 1730 |
+
"loss": 2.0856,
|
| 1731 |
+
"step": 281
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.76,
|
| 1735 |
+
"learning_rate": 2.8364703024622474e-06,
|
| 1736 |
+
"loss": 2.0409,
|
| 1737 |
+
"step": 282
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.76,
|
| 1741 |
+
"learning_rate": 2.7755176132500905e-06,
|
| 1742 |
+
"loss": 2.0506,
|
| 1743 |
+
"step": 283
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.77,
|
| 1747 |
+
"learning_rate": 2.7151212606503164e-06,
|
| 1748 |
+
"loss": 2.0866,
|
| 1749 |
+
"step": 284
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.77,
|
| 1753 |
+
"learning_rate": 2.6552858956123485e-06,
|
| 1754 |
+
"loss": 2.0581,
|
| 1755 |
+
"step": 285
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.77,
|
| 1759 |
+
"learning_rate": 2.5960161258855807e-06,
|
| 1760 |
+
"loss": 2.0731,
|
| 1761 |
+
"step": 286
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.77,
|
| 1765 |
+
"learning_rate": 2.5373165156645263e-06,
|
| 1766 |
+
"loss": 2.0724,
|
| 1767 |
+
"step": 287
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.78,
|
| 1771 |
+
"learning_rate": 2.4791915852373604e-06,
|
| 1772 |
+
"loss": 2.0688,
|
| 1773 |
+
"step": 288
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.78,
|
| 1777 |
+
"learning_rate": 2.4216458106378194e-06,
|
| 1778 |
+
"loss": 2.0679,
|
| 1779 |
+
"step": 289
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.78,
|
| 1783 |
+
"learning_rate": 2.3646836233005133e-06,
|
| 1784 |
+
"loss": 2.0544,
|
| 1785 |
+
"step": 290
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.79,
|
| 1789 |
+
"learning_rate": 2.3083094097196766e-06,
|
| 1790 |
+
"loss": 2.0885,
|
| 1791 |
+
"step": 291
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.79,
|
| 1795 |
+
"learning_rate": 2.252527511111381e-06,
|
| 1796 |
+
"loss": 2.0437,
|
| 1797 |
+
"step": 292
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 0.79,
|
| 1801 |
+
"learning_rate": 2.197342223079212e-06,
|
| 1802 |
+
"loss": 2.0826,
|
| 1803 |
+
"step": 293
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.79,
|
| 1807 |
+
"learning_rate": 2.1427577952835044e-06,
|
| 1808 |
+
"loss": 2.0471,
|
| 1809 |
+
"step": 294
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.8,
|
| 1813 |
+
"learning_rate": 2.088778431114068e-06,
|
| 1814 |
+
"loss": 2.0519,
|
| 1815 |
+
"step": 295
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.8,
|
| 1819 |
+
"learning_rate": 2.0354082873665015e-06,
|
| 1820 |
+
"loss": 2.0688,
|
| 1821 |
+
"step": 296
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.8,
|
| 1825 |
+
"learning_rate": 1.9826514739220946e-06,
|
| 1826 |
+
"loss": 2.0527,
|
| 1827 |
+
"step": 297
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.8,
|
| 1831 |
+
"learning_rate": 1.9305120534313295e-06,
|
| 1832 |
+
"loss": 2.0402,
|
| 1833 |
+
"step": 298
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.81,
|
| 1837 |
+
"learning_rate": 1.8789940410010355e-06,
|
| 1838 |
+
"loss": 2.0666,
|
| 1839 |
+
"step": 299
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.81,
|
| 1843 |
+
"learning_rate": 1.8281014038851963e-06,
|
| 1844 |
+
"loss": 2.0738,
|
| 1845 |
+
"step": 300
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.81,
|
| 1849 |
+
"learning_rate": 1.777838061179442e-06,
|
| 1850 |
+
"loss": 2.0603,
|
| 1851 |
+
"step": 301
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.82,
|
| 1855 |
+
"learning_rate": 1.7282078835192362e-06,
|
| 1856 |
+
"loss": 2.0726,
|
| 1857 |
+
"step": 302
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.82,
|
| 1861 |
+
"learning_rate": 1.679214692781842e-06,
|
| 1862 |
+
"loss": 2.06,
|
| 1863 |
+
"step": 303
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.82,
|
| 1867 |
+
"learning_rate": 1.6308622617919823e-06,
|
| 1868 |
+
"loss": 2.0862,
|
| 1869 |
+
"step": 304
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.82,
|
| 1873 |
+
"learning_rate": 1.583154314031311e-06,
|
| 1874 |
+
"loss": 2.0769,
|
| 1875 |
+
"step": 305
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.83,
|
| 1879 |
+
"learning_rate": 1.5360945233516933e-06,
|
| 1880 |
+
"loss": 2.0977,
|
| 1881 |
+
"step": 306
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.83,
|
| 1885 |
+
"learning_rate": 1.489686513692269e-06,
|
| 1886 |
+
"loss": 2.0798,
|
| 1887 |
+
"step": 307
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.83,
|
| 1891 |
+
"learning_rate": 1.4439338588004005e-06,
|
| 1892 |
+
"loss": 2.081,
|
| 1893 |
+
"step": 308
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.83,
|
| 1897 |
+
"learning_rate": 1.3988400819564707e-06,
|
| 1898 |
+
"loss": 2.0765,
|
| 1899 |
+
"step": 309
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.84,
|
| 1903 |
+
"learning_rate": 1.3544086557025493e-06,
|
| 1904 |
+
"loss": 2.0597,
|
| 1905 |
+
"step": 310
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.84,
|
| 1909 |
+
"learning_rate": 1.3106430015749971e-06,
|
| 1910 |
+
"loss": 2.058,
|
| 1911 |
+
"step": 311
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.84,
|
| 1915 |
+
"learning_rate": 1.2675464898409772e-06,
|
| 1916 |
+
"loss": 2.0869,
|
| 1917 |
+
"step": 312
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.84,
|
| 1921 |
+
"learning_rate": 1.2251224392389183e-06,
|
| 1922 |
+
"loss": 2.0762,
|
| 1923 |
+
"step": 313
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 0.85,
|
| 1927 |
+
"learning_rate": 1.1833741167229584e-06,
|
| 1928 |
+
"loss": 2.0694,
|
| 1929 |
+
"step": 314
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.85,
|
| 1933 |
+
"learning_rate": 1.1423047372113538e-06,
|
| 1934 |
+
"loss": 2.0476,
|
| 1935 |
+
"step": 315
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.85,
|
| 1939 |
+
"learning_rate": 1.1019174633389073e-06,
|
| 1940 |
+
"loss": 2.0607,
|
| 1941 |
+
"step": 316
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.86,
|
| 1945 |
+
"learning_rate": 1.0622154052134392e-06,
|
| 1946 |
+
"loss": 2.0502,
|
| 1947 |
+
"step": 317
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.86,
|
| 1951 |
+
"learning_rate": 1.0232016201762696e-06,
|
| 1952 |
+
"loss": 2.0695,
|
| 1953 |
+
"step": 318
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.86,
|
| 1957 |
+
"learning_rate": 9.848791125667867e-07,
|
| 1958 |
+
"loss": 2.0384,
|
| 1959 |
+
"step": 319
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.86,
|
| 1963 |
+
"learning_rate": 9.472508334910946e-07,
|
| 1964 |
+
"loss": 2.0513,
|
| 1965 |
+
"step": 320
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 0.87,
|
| 1969 |
+
"learning_rate": 9.103196805947522e-07,
|
| 1970 |
+
"loss": 2.0551,
|
| 1971 |
+
"step": 321
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.87,
|
| 1975 |
+
"learning_rate": 8.740884978396358e-07,
|
| 1976 |
+
"loss": 2.068,
|
| 1977 |
+
"step": 322
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.87,
|
| 1981 |
+
"learning_rate": 8.385600752849387e-07,
|
| 1982 |
+
"loss": 2.0505,
|
| 1983 |
+
"step": 323
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.87,
|
| 1987 |
+
"learning_rate": 8.037371488723078e-07,
|
| 1988 |
+
"loss": 2.0547,
|
| 1989 |
+
"step": 324
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.88,
|
| 1993 |
+
"learning_rate": 7.69622400215162e-07,
|
| 1994 |
+
"loss": 2.0674,
|
| 1995 |
+
"step": 325
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.88,
|
| 1999 |
+
"learning_rate": 7.36218456392187e-07,
|
| 2000 |
+
"loss": 2.0632,
|
| 2001 |
+
"step": 326
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.88,
|
| 2005 |
+
"learning_rate": 7.035278897450326e-07,
|
| 2006 |
+
"loss": 2.0607,
|
| 2007 |
+
"step": 327
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 0.89,
|
| 2011 |
+
"learning_rate": 6.715532176802298e-07,
|
| 2012 |
+
"loss": 2.1007,
|
| 2013 |
+
"step": 328
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 0.89,
|
| 2017 |
+
"learning_rate": 6.402969024753147e-07,
|
| 2018 |
+
"loss": 2.0334,
|
| 2019 |
+
"step": 329
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.89,
|
| 2023 |
+
"learning_rate": 6.097613510892364e-07,
|
| 2024 |
+
"loss": 2.0429,
|
| 2025 |
+
"step": 330
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.89,
|
| 2029 |
+
"learning_rate": 5.799489149769943e-07,
|
| 2030 |
+
"loss": 2.0659,
|
| 2031 |
+
"step": 331
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.9,
|
| 2035 |
+
"learning_rate": 5.508618899085583e-07,
|
| 2036 |
+
"loss": 2.06,
|
| 2037 |
+
"step": 332
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.9,
|
| 2041 |
+
"learning_rate": 5.225025157920782e-07,
|
| 2042 |
+
"loss": 2.063,
|
| 2043 |
+
"step": 333
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 0.9,
|
| 2047 |
+
"learning_rate": 4.948729765014004e-07,
|
| 2048 |
+
"loss": 2.0655,
|
| 2049 |
+
"step": 334
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 0.9,
|
| 2053 |
+
"learning_rate": 4.6797539970788843e-07,
|
| 2054 |
+
"loss": 2.0857,
|
| 2055 |
+
"step": 335
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.91,
|
| 2059 |
+
"learning_rate": 4.4181185671657634e-07,
|
| 2060 |
+
"loss": 2.0507,
|
| 2061 |
+
"step": 336
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.91,
|
| 2065 |
+
"learning_rate": 4.163843623066732e-07,
|
| 2066 |
+
"loss": 2.0683,
|
| 2067 |
+
"step": 337
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.91,
|
| 2071 |
+
"learning_rate": 3.916948745763938e-07,
|
| 2072 |
+
"loss": 2.0658,
|
| 2073 |
+
"step": 338
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.91,
|
| 2077 |
+
"learning_rate": 3.6774529479219e-07,
|
| 2078 |
+
"loss": 2.08,
|
| 2079 |
+
"step": 339
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.92,
|
| 2083 |
+
"learning_rate": 3.445374672423252e-07,
|
| 2084 |
+
"loss": 2.0667,
|
| 2085 |
+
"step": 340
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 0.92,
|
| 2089 |
+
"learning_rate": 3.2207317909485834e-07,
|
| 2090 |
+
"loss": 2.0456,
|
| 2091 |
+
"step": 341
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.92,
|
| 2095 |
+
"learning_rate": 3.0035416026001573e-07,
|
| 2096 |
+
"loss": 2.0586,
|
| 2097 |
+
"step": 342
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.93,
|
| 2101 |
+
"learning_rate": 2.7938208325697825e-07,
|
| 2102 |
+
"loss": 2.0443,
|
| 2103 |
+
"step": 343
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.93,
|
| 2107 |
+
"learning_rate": 2.591585630850835e-07,
|
| 2108 |
+
"loss": 2.0677,
|
| 2109 |
+
"step": 344
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.93,
|
| 2113 |
+
"learning_rate": 2.3968515709946296e-07,
|
| 2114 |
+
"loss": 2.0628,
|
| 2115 |
+
"step": 345
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.93,
|
| 2119 |
+
"learning_rate": 2.2096336489111025e-07,
|
| 2120 |
+
"loss": 2.0533,
|
| 2121 |
+
"step": 346
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.94,
|
| 2125 |
+
"learning_rate": 2.0299462817139902e-07,
|
| 2126 |
+
"loss": 2.0549,
|
| 2127 |
+
"step": 347
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 0.94,
|
| 2131 |
+
"learning_rate": 1.8578033066107392e-07,
|
| 2132 |
+
"loss": 2.0865,
|
| 2133 |
+
"step": 348
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.94,
|
| 2137 |
+
"learning_rate": 1.693217979836792e-07,
|
| 2138 |
+
"loss": 2.065,
|
| 2139 |
+
"step": 349
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.94,
|
| 2143 |
+
"learning_rate": 1.5362029756348373e-07,
|
| 2144 |
+
"loss": 2.0509,
|
| 2145 |
+
"step": 350
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.95,
|
| 2149 |
+
"learning_rate": 1.386770385278835e-07,
|
| 2150 |
+
"loss": 2.0459,
|
| 2151 |
+
"step": 351
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.95,
|
| 2155 |
+
"learning_rate": 1.2449317161427942e-07,
|
| 2156 |
+
"loss": 2.0744,
|
| 2157 |
+
"step": 352
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.95,
|
| 2161 |
+
"learning_rate": 1.1106978908147381e-07,
|
| 2162 |
+
"loss": 2.06,
|
| 2163 |
+
"step": 353
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.96,
|
| 2167 |
+
"learning_rate": 9.840792462555426e-08,
|
| 2168 |
+
"loss": 2.0549,
|
| 2169 |
+
"step": 354
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.96,
|
| 2173 |
+
"learning_rate": 8.650855330028629e-08,
|
| 2174 |
+
"loss": 2.0808,
|
| 2175 |
+
"step": 355
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 0.96,
|
| 2179 |
+
"learning_rate": 7.53725914420378e-08,
|
| 2180 |
+
"loss": 2.0698,
|
| 2181 |
+
"step": 356
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 0.96,
|
| 2185 |
+
"learning_rate": 6.500089659920661e-08,
|
| 2186 |
+
"loss": 2.0546,
|
| 2187 |
+
"step": 357
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.97,
|
| 2191 |
+
"learning_rate": 5.539426746618337e-08,
|
| 2192 |
+
"loss": 2.0416,
|
| 2193 |
+
"step": 358
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.97,
|
| 2197 |
+
"learning_rate": 4.6553443821852893e-08,
|
| 2198 |
+
"loss": 2.0574,
|
| 2199 |
+
"step": 359
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.97,
|
| 2203 |
+
"learning_rate": 3.847910647261754e-08,
|
| 2204 |
+
"loss": 2.0699,
|
| 2205 |
+
"step": 360
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.97,
|
| 2209 |
+
"learning_rate": 3.117187719997805e-08,
|
| 2210 |
+
"loss": 2.0733,
|
| 2211 |
+
"step": 361
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 0.98,
|
| 2215 |
+
"learning_rate": 2.4632318712646264e-08,
|
| 2216 |
+
"loss": 2.0532,
|
| 2217 |
+
"step": 362
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 0.98,
|
| 2221 |
+
"learning_rate": 1.8860934603215365e-08,
|
| 2222 |
+
"loss": 2.0679,
|
| 2223 |
+
"step": 363
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.98,
|
| 2227 |
+
"learning_rate": 1.3858169309376446e-08,
|
| 2228 |
+
"loss": 2.0442,
|
| 2229 |
+
"step": 364
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.99,
|
| 2233 |
+
"learning_rate": 9.624408079699221e-09,
|
| 2234 |
+
"loss": 2.0586,
|
| 2235 |
+
"step": 365
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.99,
|
| 2239 |
+
"learning_rate": 6.1599769439590896e-09,
|
| 2240 |
+
"loss": 2.0724,
|
| 2241 |
+
"step": 366
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.99,
|
| 2245 |
+
"learning_rate": 3.465142688036105e-09,
|
| 2246 |
+
"loss": 2.0801,
|
| 2247 |
+
"step": 367
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 0.99,
|
| 2251 |
+
"learning_rate": 1.540112833366969e-09,
|
| 2252 |
+
"loss": 2.0749,
|
| 2253 |
+
"step": 368
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 1.0,
|
| 2257 |
+
"learning_rate": 3.850356209633699e-10,
|
| 2258 |
+
"loss": 2.0702,
|
| 2259 |
+
"step": 369
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.0,
|
| 2263 |
+
"learning_rate": 0.0,
|
| 2264 |
+
"loss": 2.0757,
|
| 2265 |
+
"step": 370
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 1.0,
|
| 2269 |
+
"step": 370,
|
| 2270 |
+
"total_flos": 1.5753069967253176e+19,
|
| 2271 |
+
"train_loss": 2.0780758393777385,
|
| 2272 |
+
"train_runtime": 117810.8799,
|
| 2273 |
+
"train_samples_per_second": 1.61,
|
| 2274 |
+
"train_steps_per_second": 0.003
|
| 2275 |
+
}
|
| 2276 |
+
],
|
| 2277 |
+
"logging_steps": 1.0,
|
| 2278 |
+
"max_steps": 370,
|
| 2279 |
+
"num_train_epochs": 1,
|
| 2280 |
+
"save_steps": 126,
|
| 2281 |
+
"total_flos": 1.5753069967253176e+19,
|
| 2282 |
+
"trial_name": null,
|
| 2283 |
+
"trial_params": null
|
| 2284 |
+
}
|
output_c4wiki_lpq_20231022_ranks64_7b_c4_2.75/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fee3022d77dc8dd6bc3e709d5bc89eeef225eecbe5c74b3cecc8fe5cd1b875f3
|
| 3 |
+
size 4155
|