Upload folder using huggingface_hub (part 2)
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-550/optimizer.pt +3 -0
- checkpoint-550/rng_state.pth +3 -0
- checkpoint-550/scheduler.pt +3 -0
- checkpoint-550/tokenizer.json +3 -0
- checkpoint-550/tokenizer_config.json +30 -0
- checkpoint-550/trainer_state.json +705 -0
- checkpoint-550/training_args.bin +3 -0
- checkpoint-600/README.md +209 -0
- checkpoint-600/adapter_config.json +48 -0
- checkpoint-600/adapter_model.safetensors +3 -0
- checkpoint-600/chat_template.jinja +54 -0
- checkpoint-600/optimizer.pt +3 -0
- checkpoint-600/rng_state.pth +3 -0
- checkpoint-600/scheduler.pt +3 -0
- checkpoint-600/tokenizer.json +3 -0
- checkpoint-600/tokenizer_config.json +30 -0
- checkpoint-600/trainer_state.json +766 -0
- checkpoint-600/training_args.bin +3 -0
- checkpoint-650/README.md +209 -0
- checkpoint-650/adapter_config.json +48 -0
- checkpoint-650/adapter_model.safetensors +3 -0
- checkpoint-650/chat_template.jinja +54 -0
- checkpoint-650/optimizer.pt +3 -0
- checkpoint-650/rng_state.pth +3 -0
- checkpoint-650/scheduler.pt +3 -0
- checkpoint-650/tokenizer.json +3 -0
- checkpoint-650/tokenizer_config.json +30 -0
- checkpoint-650/trainer_state.json +827 -0
- checkpoint-650/training_args.bin +3 -0
- checkpoint-700/README.md +209 -0
- checkpoint-700/adapter_config.json +48 -0
- checkpoint-700/adapter_model.safetensors +3 -0
- checkpoint-700/chat_template.jinja +54 -0
- checkpoint-700/optimizer.pt +3 -0
- checkpoint-700/rng_state.pth +3 -0
- checkpoint-700/scheduler.pt +3 -0
- checkpoint-700/tokenizer.json +3 -0
- checkpoint-700/tokenizer_config.json +30 -0
- checkpoint-700/trainer_state.json +888 -0
- checkpoint-700/training_args.bin +3 -0
- checkpoint-750/README.md +209 -0
- checkpoint-750/adapter_config.json +48 -0
- checkpoint-750/adapter_model.safetensors +3 -0
- checkpoint-750/chat_template.jinja +54 -0
- checkpoint-750/optimizer.pt +3 -0
- checkpoint-750/rng_state.pth +3 -0
- checkpoint-750/scheduler.pt +3 -0
- checkpoint-750/tokenizer.json +3 -0
- checkpoint-750/tokenizer_config.json +30 -0
- checkpoint-750/trainer_state.json +949 -0
checkpoint-550/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d89fda31c67881f3f8097f34f17aa9b52cff98fdf1d89131f03d0b1f147a85d
|
| 3 |
+
size 75481221
|
checkpoint-550/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bc1f7dd96bb37ca8b6ef47f50c911ab8ba33816e5a0dfa0f8a45e76f5e274c9
|
| 3 |
+
size 14581
|
checkpoint-550/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:509b079b874ac3328530b24e6b0bc36418eecbbcf6d1362a5e5e1e0a21f5e700
|
| 3 |
+
size 1465
|
checkpoint-550/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
checkpoint-550/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|fim_pad|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
checkpoint-550/trainer_state.json
ADDED
|
@@ -0,0 +1,705 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0826771653543308,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 550,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.4378354728221894,
|
| 14 |
+
"epoch": 0.01968503937007874,
|
| 15 |
+
"grad_norm": 0.62109375,
|
| 16 |
+
"learning_rate": 3.91304347826087e-05,
|
| 17 |
+
"loss": 1.657682228088379,
|
| 18 |
+
"mean_token_accuracy": 0.6598833322525024,
|
| 19 |
+
"num_tokens": 115439.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5141301095485686,
|
| 24 |
+
"epoch": 0.03937007874015748,
|
| 25 |
+
"grad_norm": 0.44140625,
|
| 26 |
+
"learning_rate": 8.260869565217392e-05,
|
| 27 |
+
"loss": 1.4646138191223144,
|
| 28 |
+
"mean_token_accuracy": 0.6834615051746369,
|
| 29 |
+
"num_tokens": 225264.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.2295305937528611,
|
| 34 |
+
"epoch": 0.05905511811023622,
|
| 35 |
+
"grad_norm": 0.6796875,
|
| 36 |
+
"learning_rate": 0.00012608695652173915,
|
| 37 |
+
"loss": 1.1134957313537597,
|
| 38 |
+
"mean_token_accuracy": 0.7453642427921295,
|
| 39 |
+
"num_tokens": 330923.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.0573274463415145,
|
| 44 |
+
"epoch": 0.07874015748031496,
|
| 45 |
+
"grad_norm": 0.474609375,
|
| 46 |
+
"learning_rate": 0.00016956521739130436,
|
| 47 |
+
"loss": 1.077296829223633,
|
| 48 |
+
"mean_token_accuracy": 0.7446383863687516,
|
| 49 |
+
"num_tokens": 437622.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.952904561161995,
|
| 54 |
+
"epoch": 0.0984251968503937,
|
| 55 |
+
"grad_norm": 0.50390625,
|
| 56 |
+
"learning_rate": 0.00019999796688511753,
|
| 57 |
+
"loss": 0.9590332984924317,
|
| 58 |
+
"mean_token_accuracy": 0.768164387345314,
|
| 59 |
+
"num_tokens": 551175.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0984251968503937,
|
| 64 |
+
"eval_entropy": 1.0900797645250957,
|
| 65 |
+
"eval_loss": 1.0484484434127808,
|
| 66 |
+
"eval_mean_token_accuracy": 0.7461776600943671,
|
| 67 |
+
"eval_num_tokens": 551175.0,
|
| 68 |
+
"eval_runtime": 15.9866,
|
| 69 |
+
"eval_samples_per_second": 26.71,
|
| 70 |
+
"eval_steps_per_second": 3.378,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"entropy": 0.9487997680902481,
|
| 75 |
+
"epoch": 0.11811023622047244,
|
| 76 |
+
"grad_norm": 0.59375,
|
| 77 |
+
"learning_rate": 0.0001999618249203163,
|
| 78 |
+
"loss": 0.9577752113342285,
|
| 79 |
+
"mean_token_accuracy": 0.7689193069934845,
|
| 80 |
+
"num_tokens": 658006.0,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"entropy": 1.0506175458431244,
|
| 85 |
+
"epoch": 0.1377952755905512,
|
| 86 |
+
"grad_norm": 0.5390625,
|
| 87 |
+
"learning_rate": 0.00019988052141977201,
|
| 88 |
+
"loss": 0.9976933479309082,
|
| 89 |
+
"mean_token_accuracy": 0.756487911939621,
|
| 90 |
+
"num_tokens": 771278.0,
|
| 91 |
+
"step": 70
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.8528705358505249,
|
| 95 |
+
"epoch": 0.15748031496062992,
|
| 96 |
+
"grad_norm": 0.5078125,
|
| 97 |
+
"learning_rate": 0.0001997540931154166,
|
| 98 |
+
"loss": 0.8407608032226562,
|
| 99 |
+
"mean_token_accuracy": 0.7868376106023789,
|
| 100 |
+
"num_tokens": 886071.0,
|
| 101 |
+
"step": 80
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.9220433413982392,
|
| 105 |
+
"epoch": 0.17716535433070865,
|
| 106 |
+
"grad_norm": 0.484375,
|
| 107 |
+
"learning_rate": 0.00019958259712601903,
|
| 108 |
+
"loss": 0.8958203315734863,
|
| 109 |
+
"mean_token_accuracy": 0.7736223608255386,
|
| 110 |
+
"num_tokens": 996361.0,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.8399994730949402,
|
| 115 |
+
"epoch": 0.1968503937007874,
|
| 116 |
+
"grad_norm": 0.51953125,
|
| 117 |
+
"learning_rate": 0.00019936611093137983,
|
| 118 |
+
"loss": 0.8394058227539063,
|
| 119 |
+
"mean_token_accuracy": 0.7876519203186035,
|
| 120 |
+
"num_tokens": 1103999.0,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1968503937007874,
|
| 125 |
+
"eval_entropy": 0.9908565746413337,
|
| 126 |
+
"eval_loss": 0.949418842792511,
|
| 127 |
+
"eval_mean_token_accuracy": 0.7609190278583102,
|
| 128 |
+
"eval_num_tokens": 1103999.0,
|
| 129 |
+
"eval_runtime": 15.9475,
|
| 130 |
+
"eval_samples_per_second": 26.775,
|
| 131 |
+
"eval_steps_per_second": 3.386,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"entropy": 0.8772778362035751,
|
| 136 |
+
"epoch": 0.21653543307086615,
|
| 137 |
+
"grad_norm": 0.40625,
|
| 138 |
+
"learning_rate": 0.00019910473233732668,
|
| 139 |
+
"loss": 0.8347702026367188,
|
| 140 |
+
"mean_token_accuracy": 0.7877911299467086,
|
| 141 |
+
"num_tokens": 1216586.0,
|
| 142 |
+
"step": 110
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"entropy": 0.8745568007230758,
|
| 146 |
+
"epoch": 0.23622047244094488,
|
| 147 |
+
"grad_norm": 0.609375,
|
| 148 |
+
"learning_rate": 0.00019879857943152674,
|
| 149 |
+
"loss": 0.8359953880310058,
|
| 150 |
+
"mean_token_accuracy": 0.7790884494781494,
|
| 151 |
+
"num_tokens": 1324767.0,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"entropy": 0.878146781027317,
|
| 156 |
+
"epoch": 0.2559055118110236,
|
| 157 |
+
"grad_norm": 0.5390625,
|
| 158 |
+
"learning_rate": 0.00019844779053013637,
|
| 159 |
+
"loss": 0.8335110664367675,
|
| 160 |
+
"mean_token_accuracy": 0.7791220843791962,
|
| 161 |
+
"num_tokens": 1432356.0,
|
| 162 |
+
"step": 130
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"entropy": 0.788033875823021,
|
| 166 |
+
"epoch": 0.2755905511811024,
|
| 167 |
+
"grad_norm": 0.546875,
|
| 168 |
+
"learning_rate": 0.00019805252411531126,
|
| 169 |
+
"loss": 0.7967269420623779,
|
| 170 |
+
"mean_token_accuracy": 0.7931749552488327,
|
| 171 |
+
"num_tokens": 1542545.0,
|
| 172 |
+
"step": 140
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"entropy": 0.8667207360267639,
|
| 176 |
+
"epoch": 0.2952755905511811,
|
| 177 |
+
"grad_norm": 0.5546875,
|
| 178 |
+
"learning_rate": 0.0001976129587636064,
|
| 179 |
+
"loss": 0.8101954460144043,
|
| 180 |
+
"mean_token_accuracy": 0.7908060193061829,
|
| 181 |
+
"num_tokens": 1654462.0,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2952755905511811,
|
| 186 |
+
"eval_entropy": 0.9391163366812246,
|
| 187 |
+
"eval_loss": 0.9146928191184998,
|
| 188 |
+
"eval_mean_token_accuracy": 0.7670937886944523,
|
| 189 |
+
"eval_num_tokens": 1654462.0,
|
| 190 |
+
"eval_runtime": 15.956,
|
| 191 |
+
"eval_samples_per_second": 26.761,
|
| 192 |
+
"eval_steps_per_second": 3.384,
|
| 193 |
+
"step": 150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"entropy": 0.769407157599926,
|
| 197 |
+
"epoch": 0.31496062992125984,
|
| 198 |
+
"grad_norm": 0.470703125,
|
| 199 |
+
"learning_rate": 0.00019712929306529723,
|
| 200 |
+
"loss": 0.7655523777008056,
|
| 201 |
+
"mean_token_accuracy": 0.8053037762641907,
|
| 202 |
+
"num_tokens": 1760181.0,
|
| 203 |
+
"step": 160
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"entropy": 0.8818381905555726,
|
| 207 |
+
"epoch": 0.3346456692913386,
|
| 208 |
+
"grad_norm": 0.625,
|
| 209 |
+
"learning_rate": 0.000196601745534659,
|
| 210 |
+
"loss": 0.8408863067626953,
|
| 211 |
+
"mean_token_accuracy": 0.7815578579902649,
|
| 212 |
+
"num_tokens": 1864683.0,
|
| 213 |
+
"step": 170
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"entropy": 0.8344995141029358,
|
| 217 |
+
"epoch": 0.3543307086614173,
|
| 218 |
+
"grad_norm": 0.4765625,
|
| 219 |
+
"learning_rate": 0.0001960305545112445,
|
| 220 |
+
"loss": 0.8205550193786622,
|
| 221 |
+
"mean_token_accuracy": 0.7871369570493698,
|
| 222 |
+
"num_tokens": 1978641.0,
|
| 223 |
+
"step": 180
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"entropy": 0.8058241099119187,
|
| 227 |
+
"epoch": 0.37401574803149606,
|
| 228 |
+
"grad_norm": 0.494140625,
|
| 229 |
+
"learning_rate": 0.0001954159780522056,
|
| 230 |
+
"loss": 0.8002825736999511,
|
| 231 |
+
"mean_token_accuracy": 0.7913093209266663,
|
| 232 |
+
"num_tokens": 2087989.0,
|
| 233 |
+
"step": 190
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"entropy": 0.8938606142997741,
|
| 237 |
+
"epoch": 0.3937007874015748,
|
| 238 |
+
"grad_norm": 0.61328125,
|
| 239 |
+
"learning_rate": 0.00019475829381570566,
|
| 240 |
+
"loss": 0.8305434226989746,
|
| 241 |
+
"mean_token_accuracy": 0.7836446255445481,
|
| 242 |
+
"num_tokens": 2195494.0,
|
| 243 |
+
"step": 200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.3937007874015748,
|
| 247 |
+
"eval_entropy": 0.9502577009024443,
|
| 248 |
+
"eval_loss": 0.8978050351142883,
|
| 249 |
+
"eval_mean_token_accuracy": 0.7696934717672842,
|
| 250 |
+
"eval_num_tokens": 2195494.0,
|
| 251 |
+
"eval_runtime": 15.9419,
|
| 252 |
+
"eval_samples_per_second": 26.785,
|
| 253 |
+
"eval_steps_per_second": 3.387,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"entropy": 0.7890492826700211,
|
| 258 |
+
"epoch": 0.41338582677165353,
|
| 259 |
+
"grad_norm": 0.40625,
|
| 260 |
+
"learning_rate": 0.0001940577989354773,
|
| 261 |
+
"loss": 0.7953387260437011,
|
| 262 |
+
"mean_token_accuracy": 0.7982505321502685,
|
| 263 |
+
"num_tokens": 2314228.0,
|
| 264 |
+
"step": 210
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"entropy": 0.8576261162757873,
|
| 268 |
+
"epoch": 0.4330708661417323,
|
| 269 |
+
"grad_norm": 0.66015625,
|
| 270 |
+
"learning_rate": 0.00019331480988658083,
|
| 271 |
+
"loss": 0.8120486259460449,
|
| 272 |
+
"mean_token_accuracy": 0.7829198718070984,
|
| 273 |
+
"num_tokens": 2419122.0,
|
| 274 |
+
"step": 220
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"entropy": 0.8514308303594589,
|
| 278 |
+
"epoch": 0.452755905511811,
|
| 279 |
+
"grad_norm": 0.470703125,
|
| 280 |
+
"learning_rate": 0.00019252966234242468,
|
| 281 |
+
"loss": 0.8203784942626953,
|
| 282 |
+
"mean_token_accuracy": 0.7819343030452728,
|
| 283 |
+
"num_tokens": 2524623.0,
|
| 284 |
+
"step": 230
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"entropy": 0.8994888842105866,
|
| 288 |
+
"epoch": 0.47244094488188976,
|
| 289 |
+
"grad_norm": 0.59765625,
|
| 290 |
+
"learning_rate": 0.00019170271102311238,
|
| 291 |
+
"loss": 0.9019557952880859,
|
| 292 |
+
"mean_token_accuracy": 0.7712395042181015,
|
| 293 |
+
"num_tokens": 2631031.0,
|
| 294 |
+
"step": 240
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"entropy": 0.7910601049661636,
|
| 298 |
+
"epoch": 0.4921259842519685,
|
| 299 |
+
"grad_norm": 0.494140625,
|
| 300 |
+
"learning_rate": 0.00019083432953518418,
|
| 301 |
+
"loss": 0.8107678413391113,
|
| 302 |
+
"mean_token_accuracy": 0.7996705889701843,
|
| 303 |
+
"num_tokens": 2741031.0,
|
| 304 |
+
"step": 250
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4921259842519685,
|
| 308 |
+
"eval_entropy": 0.9037868281205496,
|
| 309 |
+
"eval_loss": 0.8843846917152405,
|
| 310 |
+
"eval_mean_token_accuracy": 0.7717091352851303,
|
| 311 |
+
"eval_num_tokens": 2741031.0,
|
| 312 |
+
"eval_runtime": 15.93,
|
| 313 |
+
"eval_samples_per_second": 26.805,
|
| 314 |
+
"eval_steps_per_second": 3.39,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"entropy": 0.7740790158510208,
|
| 319 |
+
"epoch": 0.5118110236220472,
|
| 320 |
+
"grad_norm": 0.57421875,
|
| 321 |
+
"learning_rate": 0.00018992491020282618,
|
| 322 |
+
"loss": 0.7579652309417725,
|
| 323 |
+
"mean_token_accuracy": 0.7955388814210892,
|
| 324 |
+
"num_tokens": 2853547.0,
|
| 325 |
+
"step": 260
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"entropy": 0.8572690159082412,
|
| 329 |
+
"epoch": 0.531496062992126,
|
| 330 |
+
"grad_norm": 1.171875,
|
| 331 |
+
"learning_rate": 0.0001889748638906231,
|
| 332 |
+
"loss": 0.8072081565856933,
|
| 333 |
+
"mean_token_accuracy": 0.7910655379295349,
|
| 334 |
+
"num_tokens": 2968367.0,
|
| 335 |
+
"step": 270
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"entropy": 0.8885004252195359,
|
| 339 |
+
"epoch": 0.5511811023622047,
|
| 340 |
+
"grad_norm": 0.451171875,
|
| 341 |
+
"learning_rate": 0.00018798461981793462,
|
| 342 |
+
"loss": 0.8460770606994629,
|
| 343 |
+
"mean_token_accuracy": 0.7776093751192092,
|
| 344 |
+
"num_tokens": 3075963.0,
|
| 345 |
+
"step": 280
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"entropy": 0.829613895714283,
|
| 349 |
+
"epoch": 0.5708661417322834,
|
| 350 |
+
"grad_norm": 0.4453125,
|
| 351 |
+
"learning_rate": 0.00018695462536497934,
|
| 352 |
+
"loss": 0.823792839050293,
|
| 353 |
+
"mean_token_accuracy": 0.7848509013652801,
|
| 354 |
+
"num_tokens": 3185899.0,
|
| 355 |
+
"step": 290
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"entropy": 0.8341330245137215,
|
| 359 |
+
"epoch": 0.5905511811023622,
|
| 360 |
+
"grad_norm": 0.490234375,
|
| 361 |
+
"learning_rate": 0.00018588534587071385,
|
| 362 |
+
"loss": 0.810818099975586,
|
| 363 |
+
"mean_token_accuracy": 0.7906568497419357,
|
| 364 |
+
"num_tokens": 3297319.0,
|
| 365 |
+
"step": 300
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.5905511811023622,
|
| 369 |
+
"eval_entropy": 0.8445847459413387,
|
| 370 |
+
"eval_loss": 0.8718247413635254,
|
| 371 |
+
"eval_mean_token_accuracy": 0.774838043583764,
|
| 372 |
+
"eval_num_tokens": 3297319.0,
|
| 373 |
+
"eval_runtime": 15.9561,
|
| 374 |
+
"eval_samples_per_second": 26.761,
|
| 375 |
+
"eval_steps_per_second": 3.384,
|
| 376 |
+
"step": 300
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"entropy": 0.8317201763391495,
|
| 380 |
+
"epoch": 0.610236220472441,
|
| 381 |
+
"grad_norm": 0.396484375,
|
| 382 |
+
"learning_rate": 0.00018477726442259806,
|
| 383 |
+
"loss": 0.80075101852417,
|
| 384 |
+
"mean_token_accuracy": 0.7886052161455155,
|
| 385 |
+
"num_tokens": 3415477.0,
|
| 386 |
+
"step": 310
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"entropy": 0.8597566410899162,
|
| 390 |
+
"epoch": 0.6299212598425197,
|
| 391 |
+
"grad_norm": 0.404296875,
|
| 392 |
+
"learning_rate": 0.00018363088163834252,
|
| 393 |
+
"loss": 0.8123328208923339,
|
| 394 |
+
"mean_token_accuracy": 0.7854531407356262,
|
| 395 |
+
"num_tokens": 3524759.0,
|
| 396 |
+
"step": 320
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"entropy": 0.8519140958786011,
|
| 400 |
+
"epoch": 0.6496062992125984,
|
| 401 |
+
"grad_norm": 0.458984375,
|
| 402 |
+
"learning_rate": 0.00018244671543973513,
|
| 403 |
+
"loss": 0.8214571952819825,
|
| 404 |
+
"mean_token_accuracy": 0.7828344345092774,
|
| 405 |
+
"num_tokens": 3640838.0,
|
| 406 |
+
"step": 330
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"entropy": 0.7781533747911453,
|
| 410 |
+
"epoch": 0.6692913385826772,
|
| 411 |
+
"grad_norm": 0.51953125,
|
| 412 |
+
"learning_rate": 0.0001812253008186505,
|
| 413 |
+
"loss": 0.753899097442627,
|
| 414 |
+
"mean_token_accuracy": 0.8011120349168778,
|
| 415 |
+
"num_tokens": 3756735.0,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"entropy": 0.8384901583194733,
|
| 420 |
+
"epoch": 0.6889763779527559,
|
| 421 |
+
"grad_norm": 0.51171875,
|
| 422 |
+
"learning_rate": 0.0001799671895953471,
|
| 423 |
+
"loss": 0.8112489700317382,
|
| 424 |
+
"mean_token_accuracy": 0.7898134678602219,
|
| 425 |
+
"num_tokens": 3870377.0,
|
| 426 |
+
"step": 350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6889763779527559,
|
| 430 |
+
"eval_entropy": 0.8795759567507991,
|
| 431 |
+
"eval_loss": 0.8568941354751587,
|
| 432 |
+
"eval_mean_token_accuracy": 0.7754804182935644,
|
| 433 |
+
"eval_num_tokens": 3870377.0,
|
| 434 |
+
"eval_runtime": 15.9337,
|
| 435 |
+
"eval_samples_per_second": 26.798,
|
| 436 |
+
"eval_steps_per_second": 3.389,
|
| 437 |
+
"step": 350
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"entropy": 0.8008699864149094,
|
| 441 |
+
"epoch": 0.7086614173228346,
|
| 442 |
+
"grad_norm": 0.498046875,
|
| 443 |
+
"learning_rate": 0.00017867295016916167,
|
| 444 |
+
"loss": 0.7585730075836181,
|
| 445 |
+
"mean_token_accuracy": 0.7942175149917603,
|
| 446 |
+
"num_tokens": 3975692.0,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"entropy": 0.9035080641508102,
|
| 451 |
+
"epoch": 0.7283464566929134,
|
| 452 |
+
"grad_norm": 0.48046875,
|
| 453 |
+
"learning_rate": 0.0001773431672617132,
|
| 454 |
+
"loss": 0.8653995513916015,
|
| 455 |
+
"mean_token_accuracy": 0.7730168104171753,
|
| 456 |
+
"num_tokens": 4087256.0,
|
| 457 |
+
"step": 370
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"entropy": 0.760843014717102,
|
| 461 |
+
"epoch": 0.7480314960629921,
|
| 462 |
+
"grad_norm": 0.49609375,
|
| 463 |
+
"learning_rate": 0.00017597844165273286,
|
| 464 |
+
"loss": 0.7377382278442383,
|
| 465 |
+
"mean_token_accuracy": 0.7972156703472137,
|
| 466 |
+
"num_tokens": 4192629.0,
|
| 467 |
+
"step": 380
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"entropy": 0.8075762838125229,
|
| 471 |
+
"epoch": 0.7677165354330708,
|
| 472 |
+
"grad_norm": 0.447265625,
|
| 473 |
+
"learning_rate": 0.00017457938990863908,
|
| 474 |
+
"loss": 0.7615089893341065,
|
| 475 |
+
"mean_token_accuracy": 0.8005614727735519,
|
| 476 |
+
"num_tokens": 4303838.0,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"entropy": 0.8942124575376511,
|
| 481 |
+
"epoch": 0.7874015748031497,
|
| 482 |
+
"grad_norm": 0.48828125,
|
| 483 |
+
"learning_rate": 0.00017314664410398033,
|
| 484 |
+
"loss": 0.8365015983581543,
|
| 485 |
+
"mean_token_accuracy": 0.7790710270404816,
|
| 486 |
+
"num_tokens": 4414002.0,
|
| 487 |
+
"step": 400
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.7874015748031497,
|
| 491 |
+
"eval_entropy": 0.8613758815659417,
|
| 492 |
+
"eval_loss": 0.8455358743667603,
|
| 493 |
+
"eval_mean_token_accuracy": 0.7789811304321995,
|
| 494 |
+
"eval_num_tokens": 4414002.0,
|
| 495 |
+
"eval_runtime": 16.2401,
|
| 496 |
+
"eval_samples_per_second": 26.293,
|
| 497 |
+
"eval_steps_per_second": 3.325,
|
| 498 |
+
"step": 400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"entropy": 0.7841676041483879,
|
| 502 |
+
"epoch": 0.8070866141732284,
|
| 503 |
+
"grad_norm": 0.57421875,
|
| 504 |
+
"learning_rate": 0.0001716808515358714,
|
| 505 |
+
"loss": 0.8027224540710449,
|
| 506 |
+
"mean_token_accuracy": 0.79732064306736,
|
| 507 |
+
"num_tokens": 4525758.0,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"entropy": 0.7710117936134339,
|
| 512 |
+
"epoch": 0.8267716535433071,
|
| 513 |
+
"grad_norm": 0.4453125,
|
| 514 |
+
"learning_rate": 0.00017018267443155268,
|
| 515 |
+
"loss": 0.7185665130615234,
|
| 516 |
+
"mean_token_accuracy": 0.807221668958664,
|
| 517 |
+
"num_tokens": 4640742.0,
|
| 518 |
+
"step": 420
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"entropy": 0.8494665056467057,
|
| 522 |
+
"epoch": 0.8464566929133859,
|
| 523 |
+
"grad_norm": 0.453125,
|
| 524 |
+
"learning_rate": 0.00016865278964920378,
|
| 525 |
+
"loss": 0.8273701667785645,
|
| 526 |
+
"mean_token_accuracy": 0.7870708376169204,
|
| 527 |
+
"num_tokens": 4754244.0,
|
| 528 |
+
"step": 430
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"entropy": 0.7938957527279854,
|
| 532 |
+
"epoch": 0.8661417322834646,
|
| 533 |
+
"grad_norm": 0.345703125,
|
| 534 |
+
"learning_rate": 0.00016709188837214732,
|
| 535 |
+
"loss": 0.7776453971862793,
|
| 536 |
+
"mean_token_accuracy": 0.7911081612110138,
|
| 537 |
+
"num_tokens": 4862576.0,
|
| 538 |
+
"step": 440
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"entropy": 0.7948901996016502,
|
| 542 |
+
"epoch": 0.8858267716535433,
|
| 543 |
+
"grad_norm": 0.376953125,
|
| 544 |
+
"learning_rate": 0.0001655006757965806,
|
| 545 |
+
"loss": 0.7554664611816406,
|
| 546 |
+
"mean_token_accuracy": 0.7939331024885178,
|
| 547 |
+
"num_tokens": 4984410.0,
|
| 548 |
+
"step": 450
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8858267716535433,
|
| 552 |
+
"eval_entropy": 0.8405309479545664,
|
| 553 |
+
"eval_loss": 0.8371886610984802,
|
| 554 |
+
"eval_mean_token_accuracy": 0.7799682672376986,
|
| 555 |
+
"eval_num_tokens": 4984410.0,
|
| 556 |
+
"eval_runtime": 15.9419,
|
| 557 |
+
"eval_samples_per_second": 26.785,
|
| 558 |
+
"eval_steps_per_second": 3.387,
|
| 559 |
+
"step": 450
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"entropy": 0.8764406844973565,
|
| 563 |
+
"epoch": 0.905511811023622,
|
| 564 |
+
"grad_norm": 0.5625,
|
| 565 |
+
"learning_rate": 0.0001638798708129768,
|
| 566 |
+
"loss": 0.8325652122497559,
|
| 567 |
+
"mean_token_accuracy": 0.7821455717086792,
|
| 568 |
+
"num_tokens": 5094029.0,
|
| 569 |
+
"step": 460
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"entropy": 0.8582975655794144,
|
| 573 |
+
"epoch": 0.9251968503937008,
|
| 574 |
+
"grad_norm": 0.3828125,
|
| 575 |
+
"learning_rate": 0.00016223020568129854,
|
| 576 |
+
"loss": 0.8309861183166504,
|
| 577 |
+
"mean_token_accuracy": 0.7791573971509933,
|
| 578 |
+
"num_tokens": 5210613.0,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"entropy": 0.8273941457271576,
|
| 583 |
+
"epoch": 0.9448818897637795,
|
| 584 |
+
"grad_norm": 0.59375,
|
| 585 |
+
"learning_rate": 0.00016055242570017244,
|
| 586 |
+
"loss": 0.7878972053527832,
|
| 587 |
+
"mean_token_accuracy": 0.7900911033153534,
|
| 588 |
+
"num_tokens": 5322546.0,
|
| 589 |
+
"step": 480
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"entropy": 0.8146103203296662,
|
| 593 |
+
"epoch": 0.9645669291338582,
|
| 594 |
+
"grad_norm": 0.42578125,
|
| 595 |
+
"learning_rate": 0.00015884728887017162,
|
| 596 |
+
"loss": 0.7865399837493896,
|
| 597 |
+
"mean_token_accuracy": 0.7947310745716095,
|
| 598 |
+
"num_tokens": 5434008.0,
|
| 599 |
+
"step": 490
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"entropy": 0.6613125756382943,
|
| 603 |
+
"epoch": 0.984251968503937,
|
| 604 |
+
"grad_norm": 0.41796875,
|
| 605 |
+
"learning_rate": 0.0001571155655513606,
|
| 606 |
+
"loss": 0.6725417137145996,
|
| 607 |
+
"mean_token_accuracy": 0.816859421133995,
|
| 608 |
+
"num_tokens": 5544086.0,
|
| 609 |
+
"step": 500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.984251968503937,
|
| 613 |
+
"eval_entropy": 0.8118620448642306,
|
| 614 |
+
"eval_loss": 0.8308539986610413,
|
| 615 |
+
"eval_mean_token_accuracy": 0.781522473803273,
|
| 616 |
+
"eval_num_tokens": 5544086.0,
|
| 617 |
+
"eval_runtime": 15.9383,
|
| 618 |
+
"eval_samples_per_second": 26.791,
|
| 619 |
+
"eval_steps_per_second": 3.388,
|
| 620 |
+
"step": 500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.7347942754626274,
|
| 624 |
+
"epoch": 1.0039370078740157,
|
| 625 |
+
"grad_norm": 0.39453125,
|
| 626 |
+
"learning_rate": 0.0001553580381152559,
|
| 627 |
+
"loss": 0.6915054798126221,
|
| 628 |
+
"mean_token_accuracy": 0.8176700383424759,
|
| 629 |
+
"num_tokens": 5657246.0,
|
| 630 |
+
"step": 510
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.7550317242741584,
|
| 634 |
+
"epoch": 1.0236220472440944,
|
| 635 |
+
"grad_norm": 0.4921875,
|
| 636 |
+
"learning_rate": 0.0001535755005913602,
|
| 637 |
+
"loss": 0.6865068912506104,
|
| 638 |
+
"mean_token_accuracy": 0.8140248268842697,
|
| 639 |
+
"num_tokens": 5768184.0,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.7479684263467788,
|
| 644 |
+
"epoch": 1.0433070866141732,
|
| 645 |
+
"grad_norm": 0.60546875,
|
| 646 |
+
"learning_rate": 0.00015176875830842938,
|
| 647 |
+
"loss": 0.7037695407867431,
|
| 648 |
+
"mean_token_accuracy": 0.8133333414793015,
|
| 649 |
+
"num_tokens": 5885598.0,
|
| 650 |
+
"step": 530
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.6792907789349556,
|
| 654 |
+
"epoch": 1.0629921259842519,
|
| 655 |
+
"grad_norm": 0.439453125,
|
| 656 |
+
"learning_rate": 0.0001499386275306348,
|
| 657 |
+
"loss": 0.640275239944458,
|
| 658 |
+
"mean_token_accuracy": 0.8249545454978943,
|
| 659 |
+
"num_tokens": 6002120.0,
|
| 660 |
+
"step": 540
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.6819084867835045,
|
| 664 |
+
"epoch": 1.0826771653543308,
|
| 665 |
+
"grad_norm": 0.41015625,
|
| 666 |
+
"learning_rate": 0.0001480859350887852,
|
| 667 |
+
"loss": 0.6469451904296875,
|
| 668 |
+
"mean_token_accuracy": 0.8235166579484939,
|
| 669 |
+
"num_tokens": 6112085.0,
|
| 670 |
+
"step": 550
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.0826771653543308,
|
| 674 |
+
"eval_entropy": 0.8042021377219094,
|
| 675 |
+
"eval_loss": 0.8352769017219543,
|
| 676 |
+
"eval_mean_token_accuracy": 0.7806271998970596,
|
| 677 |
+
"eval_num_tokens": 6112085.0,
|
| 678 |
+
"eval_runtime": 15.9298,
|
| 679 |
+
"eval_samples_per_second": 26.805,
|
| 680 |
+
"eval_steps_per_second": 3.39,
|
| 681 |
+
"step": 550
|
| 682 |
+
}
|
| 683 |
+
],
|
| 684 |
+
"logging_steps": 10,
|
| 685 |
+
"max_steps": 1524,
|
| 686 |
+
"num_input_tokens_seen": 0,
|
| 687 |
+
"num_train_epochs": 3,
|
| 688 |
+
"save_steps": 50,
|
| 689 |
+
"stateful_callbacks": {
|
| 690 |
+
"TrainerControl": {
|
| 691 |
+
"args": {
|
| 692 |
+
"should_epoch_stop": false,
|
| 693 |
+
"should_evaluate": false,
|
| 694 |
+
"should_log": false,
|
| 695 |
+
"should_save": true,
|
| 696 |
+
"should_training_stop": false
|
| 697 |
+
},
|
| 698 |
+
"attributes": {}
|
| 699 |
+
}
|
| 700 |
+
},
|
| 701 |
+
"total_flos": 8.598251652513178e+16,
|
| 702 |
+
"train_batch_size": 8,
|
| 703 |
+
"trial_name": null,
|
| 704 |
+
"trial_params": null
|
| 705 |
+
}
|
checkpoint-550/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
|
| 3 |
+
size 5713
|
checkpoint-600/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
checkpoint-600/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-Instruct",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"down_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"gate_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-600/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b51e5573c493f818dc73cf3468f5fd8b40614ceec0b2595b62e02c1d65b105
|
| 3 |
+
size 73911504
|
checkpoint-600/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a702e7a36a3e74d0e9239fd2dda090f740bb2415cafc716336d190d6cfcd1a38
|
| 3 |
+
size 75481221
|
checkpoint-600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef3cfb08afe8fe6f587678c754bf877ca761995aa2f1f008e5e322392042a6e1
|
| 3 |
+
size 14581
|
checkpoint-600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a08359fd27c8e1b752cdcfc00f0b7c9a81938cb9e5d29e74ae46561213445c50
|
| 3 |
+
size 1465
|
checkpoint-600/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
checkpoint-600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|fim_pad|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
checkpoint-600/trainer_state.json
ADDED
|
@@ -0,0 +1,766 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.1811023622047245,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 600,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.4378354728221894,
|
| 14 |
+
"epoch": 0.01968503937007874,
|
| 15 |
+
"grad_norm": 0.62109375,
|
| 16 |
+
"learning_rate": 3.91304347826087e-05,
|
| 17 |
+
"loss": 1.657682228088379,
|
| 18 |
+
"mean_token_accuracy": 0.6598833322525024,
|
| 19 |
+
"num_tokens": 115439.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5141301095485686,
|
| 24 |
+
"epoch": 0.03937007874015748,
|
| 25 |
+
"grad_norm": 0.44140625,
|
| 26 |
+
"learning_rate": 8.260869565217392e-05,
|
| 27 |
+
"loss": 1.4646138191223144,
|
| 28 |
+
"mean_token_accuracy": 0.6834615051746369,
|
| 29 |
+
"num_tokens": 225264.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.2295305937528611,
|
| 34 |
+
"epoch": 0.05905511811023622,
|
| 35 |
+
"grad_norm": 0.6796875,
|
| 36 |
+
"learning_rate": 0.00012608695652173915,
|
| 37 |
+
"loss": 1.1134957313537597,
|
| 38 |
+
"mean_token_accuracy": 0.7453642427921295,
|
| 39 |
+
"num_tokens": 330923.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.0573274463415145,
|
| 44 |
+
"epoch": 0.07874015748031496,
|
| 45 |
+
"grad_norm": 0.474609375,
|
| 46 |
+
"learning_rate": 0.00016956521739130436,
|
| 47 |
+
"loss": 1.077296829223633,
|
| 48 |
+
"mean_token_accuracy": 0.7446383863687516,
|
| 49 |
+
"num_tokens": 437622.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.952904561161995,
|
| 54 |
+
"epoch": 0.0984251968503937,
|
| 55 |
+
"grad_norm": 0.50390625,
|
| 56 |
+
"learning_rate": 0.00019999796688511753,
|
| 57 |
+
"loss": 0.9590332984924317,
|
| 58 |
+
"mean_token_accuracy": 0.768164387345314,
|
| 59 |
+
"num_tokens": 551175.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0984251968503937,
|
| 64 |
+
"eval_entropy": 1.0900797645250957,
|
| 65 |
+
"eval_loss": 1.0484484434127808,
|
| 66 |
+
"eval_mean_token_accuracy": 0.7461776600943671,
|
| 67 |
+
"eval_num_tokens": 551175.0,
|
| 68 |
+
"eval_runtime": 15.9866,
|
| 69 |
+
"eval_samples_per_second": 26.71,
|
| 70 |
+
"eval_steps_per_second": 3.378,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"entropy": 0.9487997680902481,
|
| 75 |
+
"epoch": 0.11811023622047244,
|
| 76 |
+
"grad_norm": 0.59375,
|
| 77 |
+
"learning_rate": 0.0001999618249203163,
|
| 78 |
+
"loss": 0.9577752113342285,
|
| 79 |
+
"mean_token_accuracy": 0.7689193069934845,
|
| 80 |
+
"num_tokens": 658006.0,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"entropy": 1.0506175458431244,
|
| 85 |
+
"epoch": 0.1377952755905512,
|
| 86 |
+
"grad_norm": 0.5390625,
|
| 87 |
+
"learning_rate": 0.00019988052141977201,
|
| 88 |
+
"loss": 0.9976933479309082,
|
| 89 |
+
"mean_token_accuracy": 0.756487911939621,
|
| 90 |
+
"num_tokens": 771278.0,
|
| 91 |
+
"step": 70
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.8528705358505249,
|
| 95 |
+
"epoch": 0.15748031496062992,
|
| 96 |
+
"grad_norm": 0.5078125,
|
| 97 |
+
"learning_rate": 0.0001997540931154166,
|
| 98 |
+
"loss": 0.8407608032226562,
|
| 99 |
+
"mean_token_accuracy": 0.7868376106023789,
|
| 100 |
+
"num_tokens": 886071.0,
|
| 101 |
+
"step": 80
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.9220433413982392,
|
| 105 |
+
"epoch": 0.17716535433070865,
|
| 106 |
+
"grad_norm": 0.484375,
|
| 107 |
+
"learning_rate": 0.00019958259712601903,
|
| 108 |
+
"loss": 0.8958203315734863,
|
| 109 |
+
"mean_token_accuracy": 0.7736223608255386,
|
| 110 |
+
"num_tokens": 996361.0,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.8399994730949402,
|
| 115 |
+
"epoch": 0.1968503937007874,
|
| 116 |
+
"grad_norm": 0.51953125,
|
| 117 |
+
"learning_rate": 0.00019936611093137983,
|
| 118 |
+
"loss": 0.8394058227539063,
|
| 119 |
+
"mean_token_accuracy": 0.7876519203186035,
|
| 120 |
+
"num_tokens": 1103999.0,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1968503937007874,
|
| 125 |
+
"eval_entropy": 0.9908565746413337,
|
| 126 |
+
"eval_loss": 0.949418842792511,
|
| 127 |
+
"eval_mean_token_accuracy": 0.7609190278583102,
|
| 128 |
+
"eval_num_tokens": 1103999.0,
|
| 129 |
+
"eval_runtime": 15.9475,
|
| 130 |
+
"eval_samples_per_second": 26.775,
|
| 131 |
+
"eval_steps_per_second": 3.386,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"entropy": 0.8772778362035751,
|
| 136 |
+
"epoch": 0.21653543307086615,
|
| 137 |
+
"grad_norm": 0.40625,
|
| 138 |
+
"learning_rate": 0.00019910473233732668,
|
| 139 |
+
"loss": 0.8347702026367188,
|
| 140 |
+
"mean_token_accuracy": 0.7877911299467086,
|
| 141 |
+
"num_tokens": 1216586.0,
|
| 142 |
+
"step": 110
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"entropy": 0.8745568007230758,
|
| 146 |
+
"epoch": 0.23622047244094488,
|
| 147 |
+
"grad_norm": 0.609375,
|
| 148 |
+
"learning_rate": 0.00019879857943152674,
|
| 149 |
+
"loss": 0.8359953880310058,
|
| 150 |
+
"mean_token_accuracy": 0.7790884494781494,
|
| 151 |
+
"num_tokens": 1324767.0,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"entropy": 0.878146781027317,
|
| 156 |
+
"epoch": 0.2559055118110236,
|
| 157 |
+
"grad_norm": 0.5390625,
|
| 158 |
+
"learning_rate": 0.00019844779053013637,
|
| 159 |
+
"loss": 0.8335110664367675,
|
| 160 |
+
"mean_token_accuracy": 0.7791220843791962,
|
| 161 |
+
"num_tokens": 1432356.0,
|
| 162 |
+
"step": 130
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"entropy": 0.788033875823021,
|
| 166 |
+
"epoch": 0.2755905511811024,
|
| 167 |
+
"grad_norm": 0.546875,
|
| 168 |
+
"learning_rate": 0.00019805252411531126,
|
| 169 |
+
"loss": 0.7967269420623779,
|
| 170 |
+
"mean_token_accuracy": 0.7931749552488327,
|
| 171 |
+
"num_tokens": 1542545.0,
|
| 172 |
+
"step": 140
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"entropy": 0.8667207360267639,
|
| 176 |
+
"epoch": 0.2952755905511811,
|
| 177 |
+
"grad_norm": 0.5546875,
|
| 178 |
+
"learning_rate": 0.0001976129587636064,
|
| 179 |
+
"loss": 0.8101954460144043,
|
| 180 |
+
"mean_token_accuracy": 0.7908060193061829,
|
| 181 |
+
"num_tokens": 1654462.0,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2952755905511811,
|
| 186 |
+
"eval_entropy": 0.9391163366812246,
|
| 187 |
+
"eval_loss": 0.9146928191184998,
|
| 188 |
+
"eval_mean_token_accuracy": 0.7670937886944523,
|
| 189 |
+
"eval_num_tokens": 1654462.0,
|
| 190 |
+
"eval_runtime": 15.956,
|
| 191 |
+
"eval_samples_per_second": 26.761,
|
| 192 |
+
"eval_steps_per_second": 3.384,
|
| 193 |
+
"step": 150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"entropy": 0.769407157599926,
|
| 197 |
+
"epoch": 0.31496062992125984,
|
| 198 |
+
"grad_norm": 0.470703125,
|
| 199 |
+
"learning_rate": 0.00019712929306529723,
|
| 200 |
+
"loss": 0.7655523777008056,
|
| 201 |
+
"mean_token_accuracy": 0.8053037762641907,
|
| 202 |
+
"num_tokens": 1760181.0,
|
| 203 |
+
"step": 160
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"entropy": 0.8818381905555726,
|
| 207 |
+
"epoch": 0.3346456692913386,
|
| 208 |
+
"grad_norm": 0.625,
|
| 209 |
+
"learning_rate": 0.000196601745534659,
|
| 210 |
+
"loss": 0.8408863067626953,
|
| 211 |
+
"mean_token_accuracy": 0.7815578579902649,
|
| 212 |
+
"num_tokens": 1864683.0,
|
| 213 |
+
"step": 170
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"entropy": 0.8344995141029358,
|
| 217 |
+
"epoch": 0.3543307086614173,
|
| 218 |
+
"grad_norm": 0.4765625,
|
| 219 |
+
"learning_rate": 0.0001960305545112445,
|
| 220 |
+
"loss": 0.8205550193786622,
|
| 221 |
+
"mean_token_accuracy": 0.7871369570493698,
|
| 222 |
+
"num_tokens": 1978641.0,
|
| 223 |
+
"step": 180
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"entropy": 0.8058241099119187,
|
| 227 |
+
"epoch": 0.37401574803149606,
|
| 228 |
+
"grad_norm": 0.494140625,
|
| 229 |
+
"learning_rate": 0.0001954159780522056,
|
| 230 |
+
"loss": 0.8002825736999511,
|
| 231 |
+
"mean_token_accuracy": 0.7913093209266663,
|
| 232 |
+
"num_tokens": 2087989.0,
|
| 233 |
+
"step": 190
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"entropy": 0.8938606142997741,
|
| 237 |
+
"epoch": 0.3937007874015748,
|
| 238 |
+
"grad_norm": 0.61328125,
|
| 239 |
+
"learning_rate": 0.00019475829381570566,
|
| 240 |
+
"loss": 0.8305434226989746,
|
| 241 |
+
"mean_token_accuracy": 0.7836446255445481,
|
| 242 |
+
"num_tokens": 2195494.0,
|
| 243 |
+
"step": 200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.3937007874015748,
|
| 247 |
+
"eval_entropy": 0.9502577009024443,
|
| 248 |
+
"eval_loss": 0.8978050351142883,
|
| 249 |
+
"eval_mean_token_accuracy": 0.7696934717672842,
|
| 250 |
+
"eval_num_tokens": 2195494.0,
|
| 251 |
+
"eval_runtime": 15.9419,
|
| 252 |
+
"eval_samples_per_second": 26.785,
|
| 253 |
+
"eval_steps_per_second": 3.387,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"entropy": 0.7890492826700211,
|
| 258 |
+
"epoch": 0.41338582677165353,
|
| 259 |
+
"grad_norm": 0.40625,
|
| 260 |
+
"learning_rate": 0.0001940577989354773,
|
| 261 |
+
"loss": 0.7953387260437011,
|
| 262 |
+
"mean_token_accuracy": 0.7982505321502685,
|
| 263 |
+
"num_tokens": 2314228.0,
|
| 264 |
+
"step": 210
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"entropy": 0.8576261162757873,
|
| 268 |
+
"epoch": 0.4330708661417323,
|
| 269 |
+
"grad_norm": 0.66015625,
|
| 270 |
+
"learning_rate": 0.00019331480988658083,
|
| 271 |
+
"loss": 0.8120486259460449,
|
| 272 |
+
"mean_token_accuracy": 0.7829198718070984,
|
| 273 |
+
"num_tokens": 2419122.0,
|
| 274 |
+
"step": 220
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"entropy": 0.8514308303594589,
|
| 278 |
+
"epoch": 0.452755905511811,
|
| 279 |
+
"grad_norm": 0.470703125,
|
| 280 |
+
"learning_rate": 0.00019252966234242468,
|
| 281 |
+
"loss": 0.8203784942626953,
|
| 282 |
+
"mean_token_accuracy": 0.7819343030452728,
|
| 283 |
+
"num_tokens": 2524623.0,
|
| 284 |
+
"step": 230
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"entropy": 0.8994888842105866,
|
| 288 |
+
"epoch": 0.47244094488188976,
|
| 289 |
+
"grad_norm": 0.59765625,
|
| 290 |
+
"learning_rate": 0.00019170271102311238,
|
| 291 |
+
"loss": 0.9019557952880859,
|
| 292 |
+
"mean_token_accuracy": 0.7712395042181015,
|
| 293 |
+
"num_tokens": 2631031.0,
|
| 294 |
+
"step": 240
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"entropy": 0.7910601049661636,
|
| 298 |
+
"epoch": 0.4921259842519685,
|
| 299 |
+
"grad_norm": 0.494140625,
|
| 300 |
+
"learning_rate": 0.00019083432953518418,
|
| 301 |
+
"loss": 0.8107678413391113,
|
| 302 |
+
"mean_token_accuracy": 0.7996705889701843,
|
| 303 |
+
"num_tokens": 2741031.0,
|
| 304 |
+
"step": 250
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4921259842519685,
|
| 308 |
+
"eval_entropy": 0.9037868281205496,
|
| 309 |
+
"eval_loss": 0.8843846917152405,
|
| 310 |
+
"eval_mean_token_accuracy": 0.7717091352851303,
|
| 311 |
+
"eval_num_tokens": 2741031.0,
|
| 312 |
+
"eval_runtime": 15.93,
|
| 313 |
+
"eval_samples_per_second": 26.805,
|
| 314 |
+
"eval_steps_per_second": 3.39,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"entropy": 0.7740790158510208,
|
| 319 |
+
"epoch": 0.5118110236220472,
|
| 320 |
+
"grad_norm": 0.57421875,
|
| 321 |
+
"learning_rate": 0.00018992491020282618,
|
| 322 |
+
"loss": 0.7579652309417725,
|
| 323 |
+
"mean_token_accuracy": 0.7955388814210892,
|
| 324 |
+
"num_tokens": 2853547.0,
|
| 325 |
+
"step": 260
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"entropy": 0.8572690159082412,
|
| 329 |
+
"epoch": 0.531496062992126,
|
| 330 |
+
"grad_norm": 1.171875,
|
| 331 |
+
"learning_rate": 0.0001889748638906231,
|
| 332 |
+
"loss": 0.8072081565856933,
|
| 333 |
+
"mean_token_accuracy": 0.7910655379295349,
|
| 334 |
+
"num_tokens": 2968367.0,
|
| 335 |
+
"step": 270
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"entropy": 0.8885004252195359,
|
| 339 |
+
"epoch": 0.5511811023622047,
|
| 340 |
+
"grad_norm": 0.451171875,
|
| 341 |
+
"learning_rate": 0.00018798461981793462,
|
| 342 |
+
"loss": 0.8460770606994629,
|
| 343 |
+
"mean_token_accuracy": 0.7776093751192092,
|
| 344 |
+
"num_tokens": 3075963.0,
|
| 345 |
+
"step": 280
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"entropy": 0.829613895714283,
|
| 349 |
+
"epoch": 0.5708661417322834,
|
| 350 |
+
"grad_norm": 0.4453125,
|
| 351 |
+
"learning_rate": 0.00018695462536497934,
|
| 352 |
+
"loss": 0.823792839050293,
|
| 353 |
+
"mean_token_accuracy": 0.7848509013652801,
|
| 354 |
+
"num_tokens": 3185899.0,
|
| 355 |
+
"step": 290
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"entropy": 0.8341330245137215,
|
| 359 |
+
"epoch": 0.5905511811023622,
|
| 360 |
+
"grad_norm": 0.490234375,
|
| 361 |
+
"learning_rate": 0.00018588534587071385,
|
| 362 |
+
"loss": 0.810818099975586,
|
| 363 |
+
"mean_token_accuracy": 0.7906568497419357,
|
| 364 |
+
"num_tokens": 3297319.0,
|
| 365 |
+
"step": 300
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.5905511811023622,
|
| 369 |
+
"eval_entropy": 0.8445847459413387,
|
| 370 |
+
"eval_loss": 0.8718247413635254,
|
| 371 |
+
"eval_mean_token_accuracy": 0.774838043583764,
|
| 372 |
+
"eval_num_tokens": 3297319.0,
|
| 373 |
+
"eval_runtime": 15.9561,
|
| 374 |
+
"eval_samples_per_second": 26.761,
|
| 375 |
+
"eval_steps_per_second": 3.384,
|
| 376 |
+
"step": 300
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"entropy": 0.8317201763391495,
|
| 380 |
+
"epoch": 0.610236220472441,
|
| 381 |
+
"grad_norm": 0.396484375,
|
| 382 |
+
"learning_rate": 0.00018477726442259806,
|
| 383 |
+
"loss": 0.80075101852417,
|
| 384 |
+
"mean_token_accuracy": 0.7886052161455155,
|
| 385 |
+
"num_tokens": 3415477.0,
|
| 386 |
+
"step": 310
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"entropy": 0.8597566410899162,
|
| 390 |
+
"epoch": 0.6299212598425197,
|
| 391 |
+
"grad_norm": 0.404296875,
|
| 392 |
+
"learning_rate": 0.00018363088163834252,
|
| 393 |
+
"loss": 0.8123328208923339,
|
| 394 |
+
"mean_token_accuracy": 0.7854531407356262,
|
| 395 |
+
"num_tokens": 3524759.0,
|
| 396 |
+
"step": 320
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"entropy": 0.8519140958786011,
|
| 400 |
+
"epoch": 0.6496062992125984,
|
| 401 |
+
"grad_norm": 0.458984375,
|
| 402 |
+
"learning_rate": 0.00018244671543973513,
|
| 403 |
+
"loss": 0.8214571952819825,
|
| 404 |
+
"mean_token_accuracy": 0.7828344345092774,
|
| 405 |
+
"num_tokens": 3640838.0,
|
| 406 |
+
"step": 330
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"entropy": 0.7781533747911453,
|
| 410 |
+
"epoch": 0.6692913385826772,
|
| 411 |
+
"grad_norm": 0.51953125,
|
| 412 |
+
"learning_rate": 0.0001812253008186505,
|
| 413 |
+
"loss": 0.753899097442627,
|
| 414 |
+
"mean_token_accuracy": 0.8011120349168778,
|
| 415 |
+
"num_tokens": 3756735.0,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"entropy": 0.8384901583194733,
|
| 420 |
+
"epoch": 0.6889763779527559,
|
| 421 |
+
"grad_norm": 0.51171875,
|
| 422 |
+
"learning_rate": 0.0001799671895953471,
|
| 423 |
+
"loss": 0.8112489700317382,
|
| 424 |
+
"mean_token_accuracy": 0.7898134678602219,
|
| 425 |
+
"num_tokens": 3870377.0,
|
| 426 |
+
"step": 350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6889763779527559,
|
| 430 |
+
"eval_entropy": 0.8795759567507991,
|
| 431 |
+
"eval_loss": 0.8568941354751587,
|
| 432 |
+
"eval_mean_token_accuracy": 0.7754804182935644,
|
| 433 |
+
"eval_num_tokens": 3870377.0,
|
| 434 |
+
"eval_runtime": 15.9337,
|
| 435 |
+
"eval_samples_per_second": 26.798,
|
| 436 |
+
"eval_steps_per_second": 3.389,
|
| 437 |
+
"step": 350
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"entropy": 0.8008699864149094,
|
| 441 |
+
"epoch": 0.7086614173228346,
|
| 442 |
+
"grad_norm": 0.498046875,
|
| 443 |
+
"learning_rate": 0.00017867295016916167,
|
| 444 |
+
"loss": 0.7585730075836181,
|
| 445 |
+
"mean_token_accuracy": 0.7942175149917603,
|
| 446 |
+
"num_tokens": 3975692.0,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"entropy": 0.9035080641508102,
|
| 451 |
+
"epoch": 0.7283464566929134,
|
| 452 |
+
"grad_norm": 0.48046875,
|
| 453 |
+
"learning_rate": 0.0001773431672617132,
|
| 454 |
+
"loss": 0.8653995513916015,
|
| 455 |
+
"mean_token_accuracy": 0.7730168104171753,
|
| 456 |
+
"num_tokens": 4087256.0,
|
| 457 |
+
"step": 370
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"entropy": 0.760843014717102,
|
| 461 |
+
"epoch": 0.7480314960629921,
|
| 462 |
+
"grad_norm": 0.49609375,
|
| 463 |
+
"learning_rate": 0.00017597844165273286,
|
| 464 |
+
"loss": 0.7377382278442383,
|
| 465 |
+
"mean_token_accuracy": 0.7972156703472137,
|
| 466 |
+
"num_tokens": 4192629.0,
|
| 467 |
+
"step": 380
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"entropy": 0.8075762838125229,
|
| 471 |
+
"epoch": 0.7677165354330708,
|
| 472 |
+
"grad_norm": 0.447265625,
|
| 473 |
+
"learning_rate": 0.00017457938990863908,
|
| 474 |
+
"loss": 0.7615089893341065,
|
| 475 |
+
"mean_token_accuracy": 0.8005614727735519,
|
| 476 |
+
"num_tokens": 4303838.0,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"entropy": 0.8942124575376511,
|
| 481 |
+
"epoch": 0.7874015748031497,
|
| 482 |
+
"grad_norm": 0.48828125,
|
| 483 |
+
"learning_rate": 0.00017314664410398033,
|
| 484 |
+
"loss": 0.8365015983581543,
|
| 485 |
+
"mean_token_accuracy": 0.7790710270404816,
|
| 486 |
+
"num_tokens": 4414002.0,
|
| 487 |
+
"step": 400
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.7874015748031497,
|
| 491 |
+
"eval_entropy": 0.8613758815659417,
|
| 492 |
+
"eval_loss": 0.8455358743667603,
|
| 493 |
+
"eval_mean_token_accuracy": 0.7789811304321995,
|
| 494 |
+
"eval_num_tokens": 4414002.0,
|
| 495 |
+
"eval_runtime": 16.2401,
|
| 496 |
+
"eval_samples_per_second": 26.293,
|
| 497 |
+
"eval_steps_per_second": 3.325,
|
| 498 |
+
"step": 400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"entropy": 0.7841676041483879,
|
| 502 |
+
"epoch": 0.8070866141732284,
|
| 503 |
+
"grad_norm": 0.57421875,
|
| 504 |
+
"learning_rate": 0.0001716808515358714,
|
| 505 |
+
"loss": 0.8027224540710449,
|
| 506 |
+
"mean_token_accuracy": 0.79732064306736,
|
| 507 |
+
"num_tokens": 4525758.0,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"entropy": 0.7710117936134339,
|
| 512 |
+
"epoch": 0.8267716535433071,
|
| 513 |
+
"grad_norm": 0.4453125,
|
| 514 |
+
"learning_rate": 0.00017018267443155268,
|
| 515 |
+
"loss": 0.7185665130615234,
|
| 516 |
+
"mean_token_accuracy": 0.807221668958664,
|
| 517 |
+
"num_tokens": 4640742.0,
|
| 518 |
+
"step": 420
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"entropy": 0.8494665056467057,
|
| 522 |
+
"epoch": 0.8464566929133859,
|
| 523 |
+
"grad_norm": 0.453125,
|
| 524 |
+
"learning_rate": 0.00016865278964920378,
|
| 525 |
+
"loss": 0.8273701667785645,
|
| 526 |
+
"mean_token_accuracy": 0.7870708376169204,
|
| 527 |
+
"num_tokens": 4754244.0,
|
| 528 |
+
"step": 430
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"entropy": 0.7938957527279854,
|
| 532 |
+
"epoch": 0.8661417322834646,
|
| 533 |
+
"grad_norm": 0.345703125,
|
| 534 |
+
"learning_rate": 0.00016709188837214732,
|
| 535 |
+
"loss": 0.7776453971862793,
|
| 536 |
+
"mean_token_accuracy": 0.7911081612110138,
|
| 537 |
+
"num_tokens": 4862576.0,
|
| 538 |
+
"step": 440
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"entropy": 0.7948901996016502,
|
| 542 |
+
"epoch": 0.8858267716535433,
|
| 543 |
+
"grad_norm": 0.376953125,
|
| 544 |
+
"learning_rate": 0.0001655006757965806,
|
| 545 |
+
"loss": 0.7554664611816406,
|
| 546 |
+
"mean_token_accuracy": 0.7939331024885178,
|
| 547 |
+
"num_tokens": 4984410.0,
|
| 548 |
+
"step": 450
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8858267716535433,
|
| 552 |
+
"eval_entropy": 0.8405309479545664,
|
| 553 |
+
"eval_loss": 0.8371886610984802,
|
| 554 |
+
"eval_mean_token_accuracy": 0.7799682672376986,
|
| 555 |
+
"eval_num_tokens": 4984410.0,
|
| 556 |
+
"eval_runtime": 15.9419,
|
| 557 |
+
"eval_samples_per_second": 26.785,
|
| 558 |
+
"eval_steps_per_second": 3.387,
|
| 559 |
+
"step": 450
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"entropy": 0.8764406844973565,
|
| 563 |
+
"epoch": 0.905511811023622,
|
| 564 |
+
"grad_norm": 0.5625,
|
| 565 |
+
"learning_rate": 0.0001638798708129768,
|
| 566 |
+
"loss": 0.8325652122497559,
|
| 567 |
+
"mean_token_accuracy": 0.7821455717086792,
|
| 568 |
+
"num_tokens": 5094029.0,
|
| 569 |
+
"step": 460
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"entropy": 0.8582975655794144,
|
| 573 |
+
"epoch": 0.9251968503937008,
|
| 574 |
+
"grad_norm": 0.3828125,
|
| 575 |
+
"learning_rate": 0.00016223020568129854,
|
| 576 |
+
"loss": 0.8309861183166504,
|
| 577 |
+
"mean_token_accuracy": 0.7791573971509933,
|
| 578 |
+
"num_tokens": 5210613.0,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"entropy": 0.8273941457271576,
|
| 583 |
+
"epoch": 0.9448818897637795,
|
| 584 |
+
"grad_norm": 0.59375,
|
| 585 |
+
"learning_rate": 0.00016055242570017244,
|
| 586 |
+
"loss": 0.7878972053527832,
|
| 587 |
+
"mean_token_accuracy": 0.7900911033153534,
|
| 588 |
+
"num_tokens": 5322546.0,
|
| 589 |
+
"step": 480
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"entropy": 0.8146103203296662,
|
| 593 |
+
"epoch": 0.9645669291338582,
|
| 594 |
+
"grad_norm": 0.42578125,
|
| 595 |
+
"learning_rate": 0.00015884728887017162,
|
| 596 |
+
"loss": 0.7865399837493896,
|
| 597 |
+
"mean_token_accuracy": 0.7947310745716095,
|
| 598 |
+
"num_tokens": 5434008.0,
|
| 599 |
+
"step": 490
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"entropy": 0.6613125756382943,
|
| 603 |
+
"epoch": 0.984251968503937,
|
| 604 |
+
"grad_norm": 0.41796875,
|
| 605 |
+
"learning_rate": 0.0001571155655513606,
|
| 606 |
+
"loss": 0.6725417137145996,
|
| 607 |
+
"mean_token_accuracy": 0.816859421133995,
|
| 608 |
+
"num_tokens": 5544086.0,
|
| 609 |
+
"step": 500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.984251968503937,
|
| 613 |
+
"eval_entropy": 0.8118620448642306,
|
| 614 |
+
"eval_loss": 0.8308539986610413,
|
| 615 |
+
"eval_mean_token_accuracy": 0.781522473803273,
|
| 616 |
+
"eval_num_tokens": 5544086.0,
|
| 617 |
+
"eval_runtime": 15.9383,
|
| 618 |
+
"eval_samples_per_second": 26.791,
|
| 619 |
+
"eval_steps_per_second": 3.388,
|
| 620 |
+
"step": 500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.7347942754626274,
|
| 624 |
+
"epoch": 1.0039370078740157,
|
| 625 |
+
"grad_norm": 0.39453125,
|
| 626 |
+
"learning_rate": 0.0001553580381152559,
|
| 627 |
+
"loss": 0.6915054798126221,
|
| 628 |
+
"mean_token_accuracy": 0.8176700383424759,
|
| 629 |
+
"num_tokens": 5657246.0,
|
| 630 |
+
"step": 510
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.7550317242741584,
|
| 634 |
+
"epoch": 1.0236220472440944,
|
| 635 |
+
"grad_norm": 0.4921875,
|
| 636 |
+
"learning_rate": 0.0001535755005913602,
|
| 637 |
+
"loss": 0.6865068912506104,
|
| 638 |
+
"mean_token_accuracy": 0.8140248268842697,
|
| 639 |
+
"num_tokens": 5768184.0,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.7479684263467788,
|
| 644 |
+
"epoch": 1.0433070866141732,
|
| 645 |
+
"grad_norm": 0.60546875,
|
| 646 |
+
"learning_rate": 0.00015176875830842938,
|
| 647 |
+
"loss": 0.7037695407867431,
|
| 648 |
+
"mean_token_accuracy": 0.8133333414793015,
|
| 649 |
+
"num_tokens": 5885598.0,
|
| 650 |
+
"step": 530
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.6792907789349556,
|
| 654 |
+
"epoch": 1.0629921259842519,
|
| 655 |
+
"grad_norm": 0.439453125,
|
| 656 |
+
"learning_rate": 0.0001499386275306348,
|
| 657 |
+
"loss": 0.640275239944458,
|
| 658 |
+
"mean_token_accuracy": 0.8249545454978943,
|
| 659 |
+
"num_tokens": 6002120.0,
|
| 660 |
+
"step": 540
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.6819084867835045,
|
| 664 |
+
"epoch": 1.0826771653543308,
|
| 665 |
+
"grad_norm": 0.41015625,
|
| 666 |
+
"learning_rate": 0.0001480859350887852,
|
| 667 |
+
"loss": 0.6469451904296875,
|
| 668 |
+
"mean_token_accuracy": 0.8235166579484939,
|
| 669 |
+
"num_tokens": 6112085.0,
|
| 670 |
+
"step": 550
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.0826771653543308,
|
| 674 |
+
"eval_entropy": 0.8042021377219094,
|
| 675 |
+
"eval_loss": 0.8352769017219543,
|
| 676 |
+
"eval_mean_token_accuracy": 0.7806271998970596,
|
| 677 |
+
"eval_num_tokens": 6112085.0,
|
| 678 |
+
"eval_runtime": 15.9298,
|
| 679 |
+
"eval_samples_per_second": 26.805,
|
| 680 |
+
"eval_steps_per_second": 3.39,
|
| 681 |
+
"step": 550
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"entropy": 0.7026952266693115,
|
| 685 |
+
"epoch": 1.1023622047244095,
|
| 686 |
+
"grad_norm": 0.47265625,
|
| 687 |
+
"learning_rate": 0.00014621151800677434,
|
| 688 |
+
"loss": 0.667764139175415,
|
| 689 |
+
"mean_token_accuracy": 0.8164290696382522,
|
| 690 |
+
"num_tokens": 6224645.0,
|
| 691 |
+
"step": 560
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"entropy": 0.6083555489778518,
|
| 695 |
+
"epoch": 1.1220472440944882,
|
| 696 |
+
"grad_norm": 0.37890625,
|
| 697 |
+
"learning_rate": 0.0001443162231234242,
|
| 698 |
+
"loss": 0.5703843116760254,
|
| 699 |
+
"mean_token_accuracy": 0.8396952480077744,
|
| 700 |
+
"num_tokens": 6336790.0,
|
| 701 |
+
"step": 570
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"entropy": 0.6823922500014306,
|
| 705 |
+
"epoch": 1.141732283464567,
|
| 706 |
+
"grad_norm": 0.55078125,
|
| 707 |
+
"learning_rate": 0.0001424009067098931,
|
| 708 |
+
"loss": 0.6488718032836914,
|
| 709 |
+
"mean_token_accuracy": 0.8208951652050018,
|
| 710 |
+
"num_tokens": 6450761.0,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"entropy": 0.6331134095788002,
|
| 715 |
+
"epoch": 1.1614173228346456,
|
| 716 |
+
"grad_norm": 0.482421875,
|
| 717 |
+
"learning_rate": 0.00014046643408282305,
|
| 718 |
+
"loss": 0.5916334629058838,
|
| 719 |
+
"mean_token_accuracy": 0.8340157747268677,
|
| 720 |
+
"num_tokens": 6562060.0,
|
| 721 |
+
"step": 590
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"entropy": 0.6203767985105515,
|
| 725 |
+
"epoch": 1.1811023622047245,
|
| 726 |
+
"grad_norm": 0.45703125,
|
| 727 |
+
"learning_rate": 0.00013851367921340017,
|
| 728 |
+
"loss": 0.5833216667175293,
|
| 729 |
+
"mean_token_accuracy": 0.8345949351787567,
|
| 730 |
+
"num_tokens": 6676922.0,
|
| 731 |
+
"step": 600
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1811023622047245,
|
| 735 |
+
"eval_entropy": 0.7756788493306549,
|
| 736 |
+
"eval_loss": 0.8351659178733826,
|
| 737 |
+
"eval_mean_token_accuracy": 0.7810865651678156,
|
| 738 |
+
"eval_num_tokens": 6676922.0,
|
| 739 |
+
"eval_runtime": 15.9481,
|
| 740 |
+
"eval_samples_per_second": 26.774,
|
| 741 |
+
"eval_steps_per_second": 3.386,
|
| 742 |
+
"step": 600
|
| 743 |
+
}
|
| 744 |
+
],
|
| 745 |
+
"logging_steps": 10,
|
| 746 |
+
"max_steps": 1524,
|
| 747 |
+
"num_input_tokens_seen": 0,
|
| 748 |
+
"num_train_epochs": 3,
|
| 749 |
+
"save_steps": 50,
|
| 750 |
+
"stateful_callbacks": {
|
| 751 |
+
"TrainerControl": {
|
| 752 |
+
"args": {
|
| 753 |
+
"should_epoch_stop": false,
|
| 754 |
+
"should_evaluate": false,
|
| 755 |
+
"should_log": false,
|
| 756 |
+
"should_save": true,
|
| 757 |
+
"should_training_stop": false
|
| 758 |
+
},
|
| 759 |
+
"attributes": {}
|
| 760 |
+
}
|
| 761 |
+
},
|
| 762 |
+
"total_flos": 9.400722396027494e+16,
|
| 763 |
+
"train_batch_size": 8,
|
| 764 |
+
"trial_name": null,
|
| 765 |
+
"trial_params": null
|
| 766 |
+
}
|
checkpoint-600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
|
| 3 |
+
size 5713
|
checkpoint-650/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
checkpoint-650/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-Instruct",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"down_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"gate_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-650/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f759bf644828d9e51633b3ea127c358b1b23f79c77e7a04b941816692e4a1cbd
|
| 3 |
+
size 73911504
|
checkpoint-650/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-650/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a9dd46887bb831d66685198acdc49ddc06693cf7e3ceec9b405580c94116516
|
| 3 |
+
size 75481221
|
checkpoint-650/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aae49d4babe0d2ef11b87d851f402d2b5d9dbd130ee3f946783ffbffd0757c07
|
| 3 |
+
size 14581
|
checkpoint-650/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35526100ec3c89217e290a7634c922438dcc7d5b3a0107e39f6fad9615cfb5a1
|
| 3 |
+
size 1465
|
checkpoint-650/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
checkpoint-650/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|fim_pad|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
checkpoint-650/trainer_state.json
ADDED
|
@@ -0,0 +1,827 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.279527559055118,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 650,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.4378354728221894,
|
| 14 |
+
"epoch": 0.01968503937007874,
|
| 15 |
+
"grad_norm": 0.62109375,
|
| 16 |
+
"learning_rate": 3.91304347826087e-05,
|
| 17 |
+
"loss": 1.657682228088379,
|
| 18 |
+
"mean_token_accuracy": 0.6598833322525024,
|
| 19 |
+
"num_tokens": 115439.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5141301095485686,
|
| 24 |
+
"epoch": 0.03937007874015748,
|
| 25 |
+
"grad_norm": 0.44140625,
|
| 26 |
+
"learning_rate": 8.260869565217392e-05,
|
| 27 |
+
"loss": 1.4646138191223144,
|
| 28 |
+
"mean_token_accuracy": 0.6834615051746369,
|
| 29 |
+
"num_tokens": 225264.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.2295305937528611,
|
| 34 |
+
"epoch": 0.05905511811023622,
|
| 35 |
+
"grad_norm": 0.6796875,
|
| 36 |
+
"learning_rate": 0.00012608695652173915,
|
| 37 |
+
"loss": 1.1134957313537597,
|
| 38 |
+
"mean_token_accuracy": 0.7453642427921295,
|
| 39 |
+
"num_tokens": 330923.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.0573274463415145,
|
| 44 |
+
"epoch": 0.07874015748031496,
|
| 45 |
+
"grad_norm": 0.474609375,
|
| 46 |
+
"learning_rate": 0.00016956521739130436,
|
| 47 |
+
"loss": 1.077296829223633,
|
| 48 |
+
"mean_token_accuracy": 0.7446383863687516,
|
| 49 |
+
"num_tokens": 437622.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.952904561161995,
|
| 54 |
+
"epoch": 0.0984251968503937,
|
| 55 |
+
"grad_norm": 0.50390625,
|
| 56 |
+
"learning_rate": 0.00019999796688511753,
|
| 57 |
+
"loss": 0.9590332984924317,
|
| 58 |
+
"mean_token_accuracy": 0.768164387345314,
|
| 59 |
+
"num_tokens": 551175.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0984251968503937,
|
| 64 |
+
"eval_entropy": 1.0900797645250957,
|
| 65 |
+
"eval_loss": 1.0484484434127808,
|
| 66 |
+
"eval_mean_token_accuracy": 0.7461776600943671,
|
| 67 |
+
"eval_num_tokens": 551175.0,
|
| 68 |
+
"eval_runtime": 15.9866,
|
| 69 |
+
"eval_samples_per_second": 26.71,
|
| 70 |
+
"eval_steps_per_second": 3.378,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"entropy": 0.9487997680902481,
|
| 75 |
+
"epoch": 0.11811023622047244,
|
| 76 |
+
"grad_norm": 0.59375,
|
| 77 |
+
"learning_rate": 0.0001999618249203163,
|
| 78 |
+
"loss": 0.9577752113342285,
|
| 79 |
+
"mean_token_accuracy": 0.7689193069934845,
|
| 80 |
+
"num_tokens": 658006.0,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"entropy": 1.0506175458431244,
|
| 85 |
+
"epoch": 0.1377952755905512,
|
| 86 |
+
"grad_norm": 0.5390625,
|
| 87 |
+
"learning_rate": 0.00019988052141977201,
|
| 88 |
+
"loss": 0.9976933479309082,
|
| 89 |
+
"mean_token_accuracy": 0.756487911939621,
|
| 90 |
+
"num_tokens": 771278.0,
|
| 91 |
+
"step": 70
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.8528705358505249,
|
| 95 |
+
"epoch": 0.15748031496062992,
|
| 96 |
+
"grad_norm": 0.5078125,
|
| 97 |
+
"learning_rate": 0.0001997540931154166,
|
| 98 |
+
"loss": 0.8407608032226562,
|
| 99 |
+
"mean_token_accuracy": 0.7868376106023789,
|
| 100 |
+
"num_tokens": 886071.0,
|
| 101 |
+
"step": 80
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.9220433413982392,
|
| 105 |
+
"epoch": 0.17716535433070865,
|
| 106 |
+
"grad_norm": 0.484375,
|
| 107 |
+
"learning_rate": 0.00019958259712601903,
|
| 108 |
+
"loss": 0.8958203315734863,
|
| 109 |
+
"mean_token_accuracy": 0.7736223608255386,
|
| 110 |
+
"num_tokens": 996361.0,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.8399994730949402,
|
| 115 |
+
"epoch": 0.1968503937007874,
|
| 116 |
+
"grad_norm": 0.51953125,
|
| 117 |
+
"learning_rate": 0.00019936611093137983,
|
| 118 |
+
"loss": 0.8394058227539063,
|
| 119 |
+
"mean_token_accuracy": 0.7876519203186035,
|
| 120 |
+
"num_tokens": 1103999.0,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1968503937007874,
|
| 125 |
+
"eval_entropy": 0.9908565746413337,
|
| 126 |
+
"eval_loss": 0.949418842792511,
|
| 127 |
+
"eval_mean_token_accuracy": 0.7609190278583102,
|
| 128 |
+
"eval_num_tokens": 1103999.0,
|
| 129 |
+
"eval_runtime": 15.9475,
|
| 130 |
+
"eval_samples_per_second": 26.775,
|
| 131 |
+
"eval_steps_per_second": 3.386,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"entropy": 0.8772778362035751,
|
| 136 |
+
"epoch": 0.21653543307086615,
|
| 137 |
+
"grad_norm": 0.40625,
|
| 138 |
+
"learning_rate": 0.00019910473233732668,
|
| 139 |
+
"loss": 0.8347702026367188,
|
| 140 |
+
"mean_token_accuracy": 0.7877911299467086,
|
| 141 |
+
"num_tokens": 1216586.0,
|
| 142 |
+
"step": 110
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"entropy": 0.8745568007230758,
|
| 146 |
+
"epoch": 0.23622047244094488,
|
| 147 |
+
"grad_norm": 0.609375,
|
| 148 |
+
"learning_rate": 0.00019879857943152674,
|
| 149 |
+
"loss": 0.8359953880310058,
|
| 150 |
+
"mean_token_accuracy": 0.7790884494781494,
|
| 151 |
+
"num_tokens": 1324767.0,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"entropy": 0.878146781027317,
|
| 156 |
+
"epoch": 0.2559055118110236,
|
| 157 |
+
"grad_norm": 0.5390625,
|
| 158 |
+
"learning_rate": 0.00019844779053013637,
|
| 159 |
+
"loss": 0.8335110664367675,
|
| 160 |
+
"mean_token_accuracy": 0.7791220843791962,
|
| 161 |
+
"num_tokens": 1432356.0,
|
| 162 |
+
"step": 130
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"entropy": 0.788033875823021,
|
| 166 |
+
"epoch": 0.2755905511811024,
|
| 167 |
+
"grad_norm": 0.546875,
|
| 168 |
+
"learning_rate": 0.00019805252411531126,
|
| 169 |
+
"loss": 0.7967269420623779,
|
| 170 |
+
"mean_token_accuracy": 0.7931749552488327,
|
| 171 |
+
"num_tokens": 1542545.0,
|
| 172 |
+
"step": 140
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"entropy": 0.8667207360267639,
|
| 176 |
+
"epoch": 0.2952755905511811,
|
| 177 |
+
"grad_norm": 0.5546875,
|
| 178 |
+
"learning_rate": 0.0001976129587636064,
|
| 179 |
+
"loss": 0.8101954460144043,
|
| 180 |
+
"mean_token_accuracy": 0.7908060193061829,
|
| 181 |
+
"num_tokens": 1654462.0,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2952755905511811,
|
| 186 |
+
"eval_entropy": 0.9391163366812246,
|
| 187 |
+
"eval_loss": 0.9146928191184998,
|
| 188 |
+
"eval_mean_token_accuracy": 0.7670937886944523,
|
| 189 |
+
"eval_num_tokens": 1654462.0,
|
| 190 |
+
"eval_runtime": 15.956,
|
| 191 |
+
"eval_samples_per_second": 26.761,
|
| 192 |
+
"eval_steps_per_second": 3.384,
|
| 193 |
+
"step": 150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"entropy": 0.769407157599926,
|
| 197 |
+
"epoch": 0.31496062992125984,
|
| 198 |
+
"grad_norm": 0.470703125,
|
| 199 |
+
"learning_rate": 0.00019712929306529723,
|
| 200 |
+
"loss": 0.7655523777008056,
|
| 201 |
+
"mean_token_accuracy": 0.8053037762641907,
|
| 202 |
+
"num_tokens": 1760181.0,
|
| 203 |
+
"step": 160
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"entropy": 0.8818381905555726,
|
| 207 |
+
"epoch": 0.3346456692913386,
|
| 208 |
+
"grad_norm": 0.625,
|
| 209 |
+
"learning_rate": 0.000196601745534659,
|
| 210 |
+
"loss": 0.8408863067626953,
|
| 211 |
+
"mean_token_accuracy": 0.7815578579902649,
|
| 212 |
+
"num_tokens": 1864683.0,
|
| 213 |
+
"step": 170
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"entropy": 0.8344995141029358,
|
| 217 |
+
"epoch": 0.3543307086614173,
|
| 218 |
+
"grad_norm": 0.4765625,
|
| 219 |
+
"learning_rate": 0.0001960305545112445,
|
| 220 |
+
"loss": 0.8205550193786622,
|
| 221 |
+
"mean_token_accuracy": 0.7871369570493698,
|
| 222 |
+
"num_tokens": 1978641.0,
|
| 223 |
+
"step": 180
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"entropy": 0.8058241099119187,
|
| 227 |
+
"epoch": 0.37401574803149606,
|
| 228 |
+
"grad_norm": 0.494140625,
|
| 229 |
+
"learning_rate": 0.0001954159780522056,
|
| 230 |
+
"loss": 0.8002825736999511,
|
| 231 |
+
"mean_token_accuracy": 0.7913093209266663,
|
| 232 |
+
"num_tokens": 2087989.0,
|
| 233 |
+
"step": 190
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"entropy": 0.8938606142997741,
|
| 237 |
+
"epoch": 0.3937007874015748,
|
| 238 |
+
"grad_norm": 0.61328125,
|
| 239 |
+
"learning_rate": 0.00019475829381570566,
|
| 240 |
+
"loss": 0.8305434226989746,
|
| 241 |
+
"mean_token_accuracy": 0.7836446255445481,
|
| 242 |
+
"num_tokens": 2195494.0,
|
| 243 |
+
"step": 200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.3937007874015748,
|
| 247 |
+
"eval_entropy": 0.9502577009024443,
|
| 248 |
+
"eval_loss": 0.8978050351142883,
|
| 249 |
+
"eval_mean_token_accuracy": 0.7696934717672842,
|
| 250 |
+
"eval_num_tokens": 2195494.0,
|
| 251 |
+
"eval_runtime": 15.9419,
|
| 252 |
+
"eval_samples_per_second": 26.785,
|
| 253 |
+
"eval_steps_per_second": 3.387,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"entropy": 0.7890492826700211,
|
| 258 |
+
"epoch": 0.41338582677165353,
|
| 259 |
+
"grad_norm": 0.40625,
|
| 260 |
+
"learning_rate": 0.0001940577989354773,
|
| 261 |
+
"loss": 0.7953387260437011,
|
| 262 |
+
"mean_token_accuracy": 0.7982505321502685,
|
| 263 |
+
"num_tokens": 2314228.0,
|
| 264 |
+
"step": 210
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"entropy": 0.8576261162757873,
|
| 268 |
+
"epoch": 0.4330708661417323,
|
| 269 |
+
"grad_norm": 0.66015625,
|
| 270 |
+
"learning_rate": 0.00019331480988658083,
|
| 271 |
+
"loss": 0.8120486259460449,
|
| 272 |
+
"mean_token_accuracy": 0.7829198718070984,
|
| 273 |
+
"num_tokens": 2419122.0,
|
| 274 |
+
"step": 220
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"entropy": 0.8514308303594589,
|
| 278 |
+
"epoch": 0.452755905511811,
|
| 279 |
+
"grad_norm": 0.470703125,
|
| 280 |
+
"learning_rate": 0.00019252966234242468,
|
| 281 |
+
"loss": 0.8203784942626953,
|
| 282 |
+
"mean_token_accuracy": 0.7819343030452728,
|
| 283 |
+
"num_tokens": 2524623.0,
|
| 284 |
+
"step": 230
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"entropy": 0.8994888842105866,
|
| 288 |
+
"epoch": 0.47244094488188976,
|
| 289 |
+
"grad_norm": 0.59765625,
|
| 290 |
+
"learning_rate": 0.00019170271102311238,
|
| 291 |
+
"loss": 0.9019557952880859,
|
| 292 |
+
"mean_token_accuracy": 0.7712395042181015,
|
| 293 |
+
"num_tokens": 2631031.0,
|
| 294 |
+
"step": 240
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"entropy": 0.7910601049661636,
|
| 298 |
+
"epoch": 0.4921259842519685,
|
| 299 |
+
"grad_norm": 0.494140625,
|
| 300 |
+
"learning_rate": 0.00019083432953518418,
|
| 301 |
+
"loss": 0.8107678413391113,
|
| 302 |
+
"mean_token_accuracy": 0.7996705889701843,
|
| 303 |
+
"num_tokens": 2741031.0,
|
| 304 |
+
"step": 250
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4921259842519685,
|
| 308 |
+
"eval_entropy": 0.9037868281205496,
|
| 309 |
+
"eval_loss": 0.8843846917152405,
|
| 310 |
+
"eval_mean_token_accuracy": 0.7717091352851303,
|
| 311 |
+
"eval_num_tokens": 2741031.0,
|
| 312 |
+
"eval_runtime": 15.93,
|
| 313 |
+
"eval_samples_per_second": 26.805,
|
| 314 |
+
"eval_steps_per_second": 3.39,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"entropy": 0.7740790158510208,
|
| 319 |
+
"epoch": 0.5118110236220472,
|
| 320 |
+
"grad_norm": 0.57421875,
|
| 321 |
+
"learning_rate": 0.00018992491020282618,
|
| 322 |
+
"loss": 0.7579652309417725,
|
| 323 |
+
"mean_token_accuracy": 0.7955388814210892,
|
| 324 |
+
"num_tokens": 2853547.0,
|
| 325 |
+
"step": 260
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"entropy": 0.8572690159082412,
|
| 329 |
+
"epoch": 0.531496062992126,
|
| 330 |
+
"grad_norm": 1.171875,
|
| 331 |
+
"learning_rate": 0.0001889748638906231,
|
| 332 |
+
"loss": 0.8072081565856933,
|
| 333 |
+
"mean_token_accuracy": 0.7910655379295349,
|
| 334 |
+
"num_tokens": 2968367.0,
|
| 335 |
+
"step": 270
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"entropy": 0.8885004252195359,
|
| 339 |
+
"epoch": 0.5511811023622047,
|
| 340 |
+
"grad_norm": 0.451171875,
|
| 341 |
+
"learning_rate": 0.00018798461981793462,
|
| 342 |
+
"loss": 0.8460770606994629,
|
| 343 |
+
"mean_token_accuracy": 0.7776093751192092,
|
| 344 |
+
"num_tokens": 3075963.0,
|
| 345 |
+
"step": 280
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"entropy": 0.829613895714283,
|
| 349 |
+
"epoch": 0.5708661417322834,
|
| 350 |
+
"grad_norm": 0.4453125,
|
| 351 |
+
"learning_rate": 0.00018695462536497934,
|
| 352 |
+
"loss": 0.823792839050293,
|
| 353 |
+
"mean_token_accuracy": 0.7848509013652801,
|
| 354 |
+
"num_tokens": 3185899.0,
|
| 355 |
+
"step": 290
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"entropy": 0.8341330245137215,
|
| 359 |
+
"epoch": 0.5905511811023622,
|
| 360 |
+
"grad_norm": 0.490234375,
|
| 361 |
+
"learning_rate": 0.00018588534587071385,
|
| 362 |
+
"loss": 0.810818099975586,
|
| 363 |
+
"mean_token_accuracy": 0.7906568497419357,
|
| 364 |
+
"num_tokens": 3297319.0,
|
| 365 |
+
"step": 300
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.5905511811023622,
|
| 369 |
+
"eval_entropy": 0.8445847459413387,
|
| 370 |
+
"eval_loss": 0.8718247413635254,
|
| 371 |
+
"eval_mean_token_accuracy": 0.774838043583764,
|
| 372 |
+
"eval_num_tokens": 3297319.0,
|
| 373 |
+
"eval_runtime": 15.9561,
|
| 374 |
+
"eval_samples_per_second": 26.761,
|
| 375 |
+
"eval_steps_per_second": 3.384,
|
| 376 |
+
"step": 300
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"entropy": 0.8317201763391495,
|
| 380 |
+
"epoch": 0.610236220472441,
|
| 381 |
+
"grad_norm": 0.396484375,
|
| 382 |
+
"learning_rate": 0.00018477726442259806,
|
| 383 |
+
"loss": 0.80075101852417,
|
| 384 |
+
"mean_token_accuracy": 0.7886052161455155,
|
| 385 |
+
"num_tokens": 3415477.0,
|
| 386 |
+
"step": 310
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"entropy": 0.8597566410899162,
|
| 390 |
+
"epoch": 0.6299212598425197,
|
| 391 |
+
"grad_norm": 0.404296875,
|
| 392 |
+
"learning_rate": 0.00018363088163834252,
|
| 393 |
+
"loss": 0.8123328208923339,
|
| 394 |
+
"mean_token_accuracy": 0.7854531407356262,
|
| 395 |
+
"num_tokens": 3524759.0,
|
| 396 |
+
"step": 320
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"entropy": 0.8519140958786011,
|
| 400 |
+
"epoch": 0.6496062992125984,
|
| 401 |
+
"grad_norm": 0.458984375,
|
| 402 |
+
"learning_rate": 0.00018244671543973513,
|
| 403 |
+
"loss": 0.8214571952819825,
|
| 404 |
+
"mean_token_accuracy": 0.7828344345092774,
|
| 405 |
+
"num_tokens": 3640838.0,
|
| 406 |
+
"step": 330
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"entropy": 0.7781533747911453,
|
| 410 |
+
"epoch": 0.6692913385826772,
|
| 411 |
+
"grad_norm": 0.51953125,
|
| 412 |
+
"learning_rate": 0.0001812253008186505,
|
| 413 |
+
"loss": 0.753899097442627,
|
| 414 |
+
"mean_token_accuracy": 0.8011120349168778,
|
| 415 |
+
"num_tokens": 3756735.0,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"entropy": 0.8384901583194733,
|
| 420 |
+
"epoch": 0.6889763779527559,
|
| 421 |
+
"grad_norm": 0.51171875,
|
| 422 |
+
"learning_rate": 0.0001799671895953471,
|
| 423 |
+
"loss": 0.8112489700317382,
|
| 424 |
+
"mean_token_accuracy": 0.7898134678602219,
|
| 425 |
+
"num_tokens": 3870377.0,
|
| 426 |
+
"step": 350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6889763779527559,
|
| 430 |
+
"eval_entropy": 0.8795759567507991,
|
| 431 |
+
"eval_loss": 0.8568941354751587,
|
| 432 |
+
"eval_mean_token_accuracy": 0.7754804182935644,
|
| 433 |
+
"eval_num_tokens": 3870377.0,
|
| 434 |
+
"eval_runtime": 15.9337,
|
| 435 |
+
"eval_samples_per_second": 26.798,
|
| 436 |
+
"eval_steps_per_second": 3.389,
|
| 437 |
+
"step": 350
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"entropy": 0.8008699864149094,
|
| 441 |
+
"epoch": 0.7086614173228346,
|
| 442 |
+
"grad_norm": 0.498046875,
|
| 443 |
+
"learning_rate": 0.00017867295016916167,
|
| 444 |
+
"loss": 0.7585730075836181,
|
| 445 |
+
"mean_token_accuracy": 0.7942175149917603,
|
| 446 |
+
"num_tokens": 3975692.0,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"entropy": 0.9035080641508102,
|
| 451 |
+
"epoch": 0.7283464566929134,
|
| 452 |
+
"grad_norm": 0.48046875,
|
| 453 |
+
"learning_rate": 0.0001773431672617132,
|
| 454 |
+
"loss": 0.8653995513916015,
|
| 455 |
+
"mean_token_accuracy": 0.7730168104171753,
|
| 456 |
+
"num_tokens": 4087256.0,
|
| 457 |
+
"step": 370
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"entropy": 0.760843014717102,
|
| 461 |
+
"epoch": 0.7480314960629921,
|
| 462 |
+
"grad_norm": 0.49609375,
|
| 463 |
+
"learning_rate": 0.00017597844165273286,
|
| 464 |
+
"loss": 0.7377382278442383,
|
| 465 |
+
"mean_token_accuracy": 0.7972156703472137,
|
| 466 |
+
"num_tokens": 4192629.0,
|
| 467 |
+
"step": 380
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"entropy": 0.8075762838125229,
|
| 471 |
+
"epoch": 0.7677165354330708,
|
| 472 |
+
"grad_norm": 0.447265625,
|
| 473 |
+
"learning_rate": 0.00017457938990863908,
|
| 474 |
+
"loss": 0.7615089893341065,
|
| 475 |
+
"mean_token_accuracy": 0.8005614727735519,
|
| 476 |
+
"num_tokens": 4303838.0,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"entropy": 0.8942124575376511,
|
| 481 |
+
"epoch": 0.7874015748031497,
|
| 482 |
+
"grad_norm": 0.48828125,
|
| 483 |
+
"learning_rate": 0.00017314664410398033,
|
| 484 |
+
"loss": 0.8365015983581543,
|
| 485 |
+
"mean_token_accuracy": 0.7790710270404816,
|
| 486 |
+
"num_tokens": 4414002.0,
|
| 487 |
+
"step": 400
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.7874015748031497,
|
| 491 |
+
"eval_entropy": 0.8613758815659417,
|
| 492 |
+
"eval_loss": 0.8455358743667603,
|
| 493 |
+
"eval_mean_token_accuracy": 0.7789811304321995,
|
| 494 |
+
"eval_num_tokens": 4414002.0,
|
| 495 |
+
"eval_runtime": 16.2401,
|
| 496 |
+
"eval_samples_per_second": 26.293,
|
| 497 |
+
"eval_steps_per_second": 3.325,
|
| 498 |
+
"step": 400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"entropy": 0.7841676041483879,
|
| 502 |
+
"epoch": 0.8070866141732284,
|
| 503 |
+
"grad_norm": 0.57421875,
|
| 504 |
+
"learning_rate": 0.0001716808515358714,
|
| 505 |
+
"loss": 0.8027224540710449,
|
| 506 |
+
"mean_token_accuracy": 0.79732064306736,
|
| 507 |
+
"num_tokens": 4525758.0,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"entropy": 0.7710117936134339,
|
| 512 |
+
"epoch": 0.8267716535433071,
|
| 513 |
+
"grad_norm": 0.4453125,
|
| 514 |
+
"learning_rate": 0.00017018267443155268,
|
| 515 |
+
"loss": 0.7185665130615234,
|
| 516 |
+
"mean_token_accuracy": 0.807221668958664,
|
| 517 |
+
"num_tokens": 4640742.0,
|
| 518 |
+
"step": 420
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"entropy": 0.8494665056467057,
|
| 522 |
+
"epoch": 0.8464566929133859,
|
| 523 |
+
"grad_norm": 0.453125,
|
| 524 |
+
"learning_rate": 0.00016865278964920378,
|
| 525 |
+
"loss": 0.8273701667785645,
|
| 526 |
+
"mean_token_accuracy": 0.7870708376169204,
|
| 527 |
+
"num_tokens": 4754244.0,
|
| 528 |
+
"step": 430
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"entropy": 0.7938957527279854,
|
| 532 |
+
"epoch": 0.8661417322834646,
|
| 533 |
+
"grad_norm": 0.345703125,
|
| 534 |
+
"learning_rate": 0.00016709188837214732,
|
| 535 |
+
"loss": 0.7776453971862793,
|
| 536 |
+
"mean_token_accuracy": 0.7911081612110138,
|
| 537 |
+
"num_tokens": 4862576.0,
|
| 538 |
+
"step": 440
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"entropy": 0.7948901996016502,
|
| 542 |
+
"epoch": 0.8858267716535433,
|
| 543 |
+
"grad_norm": 0.376953125,
|
| 544 |
+
"learning_rate": 0.0001655006757965806,
|
| 545 |
+
"loss": 0.7554664611816406,
|
| 546 |
+
"mean_token_accuracy": 0.7939331024885178,
|
| 547 |
+
"num_tokens": 4984410.0,
|
| 548 |
+
"step": 450
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8858267716535433,
|
| 552 |
+
"eval_entropy": 0.8405309479545664,
|
| 553 |
+
"eval_loss": 0.8371886610984802,
|
| 554 |
+
"eval_mean_token_accuracy": 0.7799682672376986,
|
| 555 |
+
"eval_num_tokens": 4984410.0,
|
| 556 |
+
"eval_runtime": 15.9419,
|
| 557 |
+
"eval_samples_per_second": 26.785,
|
| 558 |
+
"eval_steps_per_second": 3.387,
|
| 559 |
+
"step": 450
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"entropy": 0.8764406844973565,
|
| 563 |
+
"epoch": 0.905511811023622,
|
| 564 |
+
"grad_norm": 0.5625,
|
| 565 |
+
"learning_rate": 0.0001638798708129768,
|
| 566 |
+
"loss": 0.8325652122497559,
|
| 567 |
+
"mean_token_accuracy": 0.7821455717086792,
|
| 568 |
+
"num_tokens": 5094029.0,
|
| 569 |
+
"step": 460
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"entropy": 0.8582975655794144,
|
| 573 |
+
"epoch": 0.9251968503937008,
|
| 574 |
+
"grad_norm": 0.3828125,
|
| 575 |
+
"learning_rate": 0.00016223020568129854,
|
| 576 |
+
"loss": 0.8309861183166504,
|
| 577 |
+
"mean_token_accuracy": 0.7791573971509933,
|
| 578 |
+
"num_tokens": 5210613.0,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"entropy": 0.8273941457271576,
|
| 583 |
+
"epoch": 0.9448818897637795,
|
| 584 |
+
"grad_norm": 0.59375,
|
| 585 |
+
"learning_rate": 0.00016055242570017244,
|
| 586 |
+
"loss": 0.7878972053527832,
|
| 587 |
+
"mean_token_accuracy": 0.7900911033153534,
|
| 588 |
+
"num_tokens": 5322546.0,
|
| 589 |
+
"step": 480
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"entropy": 0.8146103203296662,
|
| 593 |
+
"epoch": 0.9645669291338582,
|
| 594 |
+
"grad_norm": 0.42578125,
|
| 595 |
+
"learning_rate": 0.00015884728887017162,
|
| 596 |
+
"loss": 0.7865399837493896,
|
| 597 |
+
"mean_token_accuracy": 0.7947310745716095,
|
| 598 |
+
"num_tokens": 5434008.0,
|
| 599 |
+
"step": 490
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"entropy": 0.6613125756382943,
|
| 603 |
+
"epoch": 0.984251968503937,
|
| 604 |
+
"grad_norm": 0.41796875,
|
| 605 |
+
"learning_rate": 0.0001571155655513606,
|
| 606 |
+
"loss": 0.6725417137145996,
|
| 607 |
+
"mean_token_accuracy": 0.816859421133995,
|
| 608 |
+
"num_tokens": 5544086.0,
|
| 609 |
+
"step": 500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.984251968503937,
|
| 613 |
+
"eval_entropy": 0.8118620448642306,
|
| 614 |
+
"eval_loss": 0.8308539986610413,
|
| 615 |
+
"eval_mean_token_accuracy": 0.781522473803273,
|
| 616 |
+
"eval_num_tokens": 5544086.0,
|
| 617 |
+
"eval_runtime": 15.9383,
|
| 618 |
+
"eval_samples_per_second": 26.791,
|
| 619 |
+
"eval_steps_per_second": 3.388,
|
| 620 |
+
"step": 500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.7347942754626274,
|
| 624 |
+
"epoch": 1.0039370078740157,
|
| 625 |
+
"grad_norm": 0.39453125,
|
| 626 |
+
"learning_rate": 0.0001553580381152559,
|
| 627 |
+
"loss": 0.6915054798126221,
|
| 628 |
+
"mean_token_accuracy": 0.8176700383424759,
|
| 629 |
+
"num_tokens": 5657246.0,
|
| 630 |
+
"step": 510
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.7550317242741584,
|
| 634 |
+
"epoch": 1.0236220472440944,
|
| 635 |
+
"grad_norm": 0.4921875,
|
| 636 |
+
"learning_rate": 0.0001535755005913602,
|
| 637 |
+
"loss": 0.6865068912506104,
|
| 638 |
+
"mean_token_accuracy": 0.8140248268842697,
|
| 639 |
+
"num_tokens": 5768184.0,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.7479684263467788,
|
| 644 |
+
"epoch": 1.0433070866141732,
|
| 645 |
+
"grad_norm": 0.60546875,
|
| 646 |
+
"learning_rate": 0.00015176875830842938,
|
| 647 |
+
"loss": 0.7037695407867431,
|
| 648 |
+
"mean_token_accuracy": 0.8133333414793015,
|
| 649 |
+
"num_tokens": 5885598.0,
|
| 650 |
+
"step": 530
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.6792907789349556,
|
| 654 |
+
"epoch": 1.0629921259842519,
|
| 655 |
+
"grad_norm": 0.439453125,
|
| 656 |
+
"learning_rate": 0.0001499386275306348,
|
| 657 |
+
"loss": 0.640275239944458,
|
| 658 |
+
"mean_token_accuracy": 0.8249545454978943,
|
| 659 |
+
"num_tokens": 6002120.0,
|
| 660 |
+
"step": 540
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.6819084867835045,
|
| 664 |
+
"epoch": 1.0826771653543308,
|
| 665 |
+
"grad_norm": 0.41015625,
|
| 666 |
+
"learning_rate": 0.0001480859350887852,
|
| 667 |
+
"loss": 0.6469451904296875,
|
| 668 |
+
"mean_token_accuracy": 0.8235166579484939,
|
| 669 |
+
"num_tokens": 6112085.0,
|
| 670 |
+
"step": 550
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.0826771653543308,
|
| 674 |
+
"eval_entropy": 0.8042021377219094,
|
| 675 |
+
"eval_loss": 0.8352769017219543,
|
| 676 |
+
"eval_mean_token_accuracy": 0.7806271998970596,
|
| 677 |
+
"eval_num_tokens": 6112085.0,
|
| 678 |
+
"eval_runtime": 15.9298,
|
| 679 |
+
"eval_samples_per_second": 26.805,
|
| 680 |
+
"eval_steps_per_second": 3.39,
|
| 681 |
+
"step": 550
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"entropy": 0.7026952266693115,
|
| 685 |
+
"epoch": 1.1023622047244095,
|
| 686 |
+
"grad_norm": 0.47265625,
|
| 687 |
+
"learning_rate": 0.00014621151800677434,
|
| 688 |
+
"loss": 0.667764139175415,
|
| 689 |
+
"mean_token_accuracy": 0.8164290696382522,
|
| 690 |
+
"num_tokens": 6224645.0,
|
| 691 |
+
"step": 560
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"entropy": 0.6083555489778518,
|
| 695 |
+
"epoch": 1.1220472440944882,
|
| 696 |
+
"grad_norm": 0.37890625,
|
| 697 |
+
"learning_rate": 0.0001443162231234242,
|
| 698 |
+
"loss": 0.5703843116760254,
|
| 699 |
+
"mean_token_accuracy": 0.8396952480077744,
|
| 700 |
+
"num_tokens": 6336790.0,
|
| 701 |
+
"step": 570
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"entropy": 0.6823922500014306,
|
| 705 |
+
"epoch": 1.141732283464567,
|
| 706 |
+
"grad_norm": 0.55078125,
|
| 707 |
+
"learning_rate": 0.0001424009067098931,
|
| 708 |
+
"loss": 0.6488718032836914,
|
| 709 |
+
"mean_token_accuracy": 0.8208951652050018,
|
| 710 |
+
"num_tokens": 6450761.0,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"entropy": 0.6331134095788002,
|
| 715 |
+
"epoch": 1.1614173228346456,
|
| 716 |
+
"grad_norm": 0.482421875,
|
| 717 |
+
"learning_rate": 0.00014046643408282305,
|
| 718 |
+
"loss": 0.5916334629058838,
|
| 719 |
+
"mean_token_accuracy": 0.8340157747268677,
|
| 720 |
+
"num_tokens": 6562060.0,
|
| 721 |
+
"step": 590
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"entropy": 0.6203767985105515,
|
| 725 |
+
"epoch": 1.1811023622047245,
|
| 726 |
+
"grad_norm": 0.45703125,
|
| 727 |
+
"learning_rate": 0.00013851367921340017,
|
| 728 |
+
"loss": 0.5833216667175293,
|
| 729 |
+
"mean_token_accuracy": 0.8345949351787567,
|
| 730 |
+
"num_tokens": 6676922.0,
|
| 731 |
+
"step": 600
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1811023622047245,
|
| 735 |
+
"eval_entropy": 0.7756788493306549,
|
| 736 |
+
"eval_loss": 0.8351659178733826,
|
| 737 |
+
"eval_mean_token_accuracy": 0.7810865651678156,
|
| 738 |
+
"eval_num_tokens": 6676922.0,
|
| 739 |
+
"eval_runtime": 15.9481,
|
| 740 |
+
"eval_samples_per_second": 26.774,
|
| 741 |
+
"eval_steps_per_second": 3.386,
|
| 742 |
+
"step": 600
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"entropy": 0.645186324417591,
|
| 746 |
+
"epoch": 1.2007874015748032,
|
| 747 |
+
"grad_norm": 0.498046875,
|
| 748 |
+
"learning_rate": 0.0001365435243325051,
|
| 749 |
+
"loss": 0.6237170219421386,
|
| 750 |
+
"mean_token_accuracy": 0.8277532249689102,
|
| 751 |
+
"num_tokens": 6783497.0,
|
| 752 |
+
"step": 610
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"entropy": 0.6759833052754403,
|
| 756 |
+
"epoch": 1.220472440944882,
|
| 757 |
+
"grad_norm": 0.546875,
|
| 758 |
+
"learning_rate": 0.00013455685953213194,
|
| 759 |
+
"loss": 0.6462036609649658,
|
| 760 |
+
"mean_token_accuracy": 0.8247299671173096,
|
| 761 |
+
"num_tokens": 6894014.0,
|
| 762 |
+
"step": 620
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"entropy": 0.6737162366509437,
|
| 766 |
+
"epoch": 1.2401574803149606,
|
| 767 |
+
"grad_norm": 0.48828125,
|
| 768 |
+
"learning_rate": 0.0001325545823632554,
|
| 769 |
+
"loss": 0.6107028484344482,
|
| 770 |
+
"mean_token_accuracy": 0.8260864973068237,
|
| 771 |
+
"num_tokens": 6997350.0,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"entropy": 0.6702337503433228,
|
| 776 |
+
"epoch": 1.2598425196850394,
|
| 777 |
+
"grad_norm": 0.451171875,
|
| 778 |
+
"learning_rate": 0.00013053759743032823,
|
| 779 |
+
"loss": 0.6504123210906982,
|
| 780 |
+
"mean_token_accuracy": 0.818900191783905,
|
| 781 |
+
"num_tokens": 7109067.0,
|
| 782 |
+
"step": 640
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"entropy": 0.7739008516073227,
|
| 786 |
+
"epoch": 1.279527559055118,
|
| 787 |
+
"grad_norm": 0.56640625,
|
| 788 |
+
"learning_rate": 0.00012850681598259195,
|
| 789 |
+
"loss": 0.7173595905303956,
|
| 790 |
+
"mean_token_accuracy": 0.7997365325689316,
|
| 791 |
+
"num_tokens": 7218739.0,
|
| 792 |
+
"step": 650
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.279527559055118,
|
| 796 |
+
"eval_entropy": 0.7500080190323017,
|
| 797 |
+
"eval_loss": 0.8297256231307983,
|
| 798 |
+
"eval_mean_token_accuracy": 0.7822851461392862,
|
| 799 |
+
"eval_num_tokens": 7218739.0,
|
| 800 |
+
"eval_runtime": 15.9417,
|
| 801 |
+
"eval_samples_per_second": 26.785,
|
| 802 |
+
"eval_steps_per_second": 3.387,
|
| 803 |
+
"step": 650
|
| 804 |
+
}
|
| 805 |
+
],
|
| 806 |
+
"logging_steps": 10,
|
| 807 |
+
"max_steps": 1524,
|
| 808 |
+
"num_input_tokens_seen": 0,
|
| 809 |
+
"num_train_epochs": 3,
|
| 810 |
+
"save_steps": 50,
|
| 811 |
+
"stateful_callbacks": {
|
| 812 |
+
"TrainerControl": {
|
| 813 |
+
"args": {
|
| 814 |
+
"should_epoch_stop": false,
|
| 815 |
+
"should_evaluate": false,
|
| 816 |
+
"should_log": false,
|
| 817 |
+
"should_save": true,
|
| 818 |
+
"should_training_stop": false
|
| 819 |
+
},
|
| 820 |
+
"attributes": {}
|
| 821 |
+
}
|
| 822 |
+
},
|
| 823 |
+
"total_flos": 1.016977221744169e+17,
|
| 824 |
+
"train_batch_size": 8,
|
| 825 |
+
"trial_name": null,
|
| 826 |
+
"trial_params": null
|
| 827 |
+
}
|
checkpoint-650/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
|
| 3 |
+
size 5713
|
checkpoint-700/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
checkpoint-700/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-Instruct",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"down_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"gate_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-700/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a8d0b3374f5e27bb367f0a86eaf1d5a0f17b9f9b4796b0f6872314b1bd58976
|
| 3 |
+
size 73911504
|
checkpoint-700/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-700/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc99afc7a51ab43448e591a49c3fb5d1d84e621b6a9fb64abb95859b083e262a
|
| 3 |
+
size 75481221
|
checkpoint-700/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1180b03427666428e4a88c789e81019f38c9165bb61b890b53bc24258bc62e6
|
| 3 |
+
size 14581
|
checkpoint-700/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9848117dca48c208b83a2167cae0f73acef8b67252c4201901bc4bfa1bf14001
|
| 3 |
+
size 1465
|
checkpoint-700/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
checkpoint-700/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|fim_pad|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
checkpoint-700/trainer_state.json
ADDED
|
@@ -0,0 +1,888 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.3779527559055118,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 700,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.4378354728221894,
|
| 14 |
+
"epoch": 0.01968503937007874,
|
| 15 |
+
"grad_norm": 0.62109375,
|
| 16 |
+
"learning_rate": 3.91304347826087e-05,
|
| 17 |
+
"loss": 1.657682228088379,
|
| 18 |
+
"mean_token_accuracy": 0.6598833322525024,
|
| 19 |
+
"num_tokens": 115439.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5141301095485686,
|
| 24 |
+
"epoch": 0.03937007874015748,
|
| 25 |
+
"grad_norm": 0.44140625,
|
| 26 |
+
"learning_rate": 8.260869565217392e-05,
|
| 27 |
+
"loss": 1.4646138191223144,
|
| 28 |
+
"mean_token_accuracy": 0.6834615051746369,
|
| 29 |
+
"num_tokens": 225264.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.2295305937528611,
|
| 34 |
+
"epoch": 0.05905511811023622,
|
| 35 |
+
"grad_norm": 0.6796875,
|
| 36 |
+
"learning_rate": 0.00012608695652173915,
|
| 37 |
+
"loss": 1.1134957313537597,
|
| 38 |
+
"mean_token_accuracy": 0.7453642427921295,
|
| 39 |
+
"num_tokens": 330923.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.0573274463415145,
|
| 44 |
+
"epoch": 0.07874015748031496,
|
| 45 |
+
"grad_norm": 0.474609375,
|
| 46 |
+
"learning_rate": 0.00016956521739130436,
|
| 47 |
+
"loss": 1.077296829223633,
|
| 48 |
+
"mean_token_accuracy": 0.7446383863687516,
|
| 49 |
+
"num_tokens": 437622.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.952904561161995,
|
| 54 |
+
"epoch": 0.0984251968503937,
|
| 55 |
+
"grad_norm": 0.50390625,
|
| 56 |
+
"learning_rate": 0.00019999796688511753,
|
| 57 |
+
"loss": 0.9590332984924317,
|
| 58 |
+
"mean_token_accuracy": 0.768164387345314,
|
| 59 |
+
"num_tokens": 551175.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0984251968503937,
|
| 64 |
+
"eval_entropy": 1.0900797645250957,
|
| 65 |
+
"eval_loss": 1.0484484434127808,
|
| 66 |
+
"eval_mean_token_accuracy": 0.7461776600943671,
|
| 67 |
+
"eval_num_tokens": 551175.0,
|
| 68 |
+
"eval_runtime": 15.9866,
|
| 69 |
+
"eval_samples_per_second": 26.71,
|
| 70 |
+
"eval_steps_per_second": 3.378,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"entropy": 0.9487997680902481,
|
| 75 |
+
"epoch": 0.11811023622047244,
|
| 76 |
+
"grad_norm": 0.59375,
|
| 77 |
+
"learning_rate": 0.0001999618249203163,
|
| 78 |
+
"loss": 0.9577752113342285,
|
| 79 |
+
"mean_token_accuracy": 0.7689193069934845,
|
| 80 |
+
"num_tokens": 658006.0,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"entropy": 1.0506175458431244,
|
| 85 |
+
"epoch": 0.1377952755905512,
|
| 86 |
+
"grad_norm": 0.5390625,
|
| 87 |
+
"learning_rate": 0.00019988052141977201,
|
| 88 |
+
"loss": 0.9976933479309082,
|
| 89 |
+
"mean_token_accuracy": 0.756487911939621,
|
| 90 |
+
"num_tokens": 771278.0,
|
| 91 |
+
"step": 70
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.8528705358505249,
|
| 95 |
+
"epoch": 0.15748031496062992,
|
| 96 |
+
"grad_norm": 0.5078125,
|
| 97 |
+
"learning_rate": 0.0001997540931154166,
|
| 98 |
+
"loss": 0.8407608032226562,
|
| 99 |
+
"mean_token_accuracy": 0.7868376106023789,
|
| 100 |
+
"num_tokens": 886071.0,
|
| 101 |
+
"step": 80
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.9220433413982392,
|
| 105 |
+
"epoch": 0.17716535433070865,
|
| 106 |
+
"grad_norm": 0.484375,
|
| 107 |
+
"learning_rate": 0.00019958259712601903,
|
| 108 |
+
"loss": 0.8958203315734863,
|
| 109 |
+
"mean_token_accuracy": 0.7736223608255386,
|
| 110 |
+
"num_tokens": 996361.0,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.8399994730949402,
|
| 115 |
+
"epoch": 0.1968503937007874,
|
| 116 |
+
"grad_norm": 0.51953125,
|
| 117 |
+
"learning_rate": 0.00019936611093137983,
|
| 118 |
+
"loss": 0.8394058227539063,
|
| 119 |
+
"mean_token_accuracy": 0.7876519203186035,
|
| 120 |
+
"num_tokens": 1103999.0,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1968503937007874,
|
| 125 |
+
"eval_entropy": 0.9908565746413337,
|
| 126 |
+
"eval_loss": 0.949418842792511,
|
| 127 |
+
"eval_mean_token_accuracy": 0.7609190278583102,
|
| 128 |
+
"eval_num_tokens": 1103999.0,
|
| 129 |
+
"eval_runtime": 15.9475,
|
| 130 |
+
"eval_samples_per_second": 26.775,
|
| 131 |
+
"eval_steps_per_second": 3.386,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"entropy": 0.8772778362035751,
|
| 136 |
+
"epoch": 0.21653543307086615,
|
| 137 |
+
"grad_norm": 0.40625,
|
| 138 |
+
"learning_rate": 0.00019910473233732668,
|
| 139 |
+
"loss": 0.8347702026367188,
|
| 140 |
+
"mean_token_accuracy": 0.7877911299467086,
|
| 141 |
+
"num_tokens": 1216586.0,
|
| 142 |
+
"step": 110
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"entropy": 0.8745568007230758,
|
| 146 |
+
"epoch": 0.23622047244094488,
|
| 147 |
+
"grad_norm": 0.609375,
|
| 148 |
+
"learning_rate": 0.00019879857943152674,
|
| 149 |
+
"loss": 0.8359953880310058,
|
| 150 |
+
"mean_token_accuracy": 0.7790884494781494,
|
| 151 |
+
"num_tokens": 1324767.0,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"entropy": 0.878146781027317,
|
| 156 |
+
"epoch": 0.2559055118110236,
|
| 157 |
+
"grad_norm": 0.5390625,
|
| 158 |
+
"learning_rate": 0.00019844779053013637,
|
| 159 |
+
"loss": 0.8335110664367675,
|
| 160 |
+
"mean_token_accuracy": 0.7791220843791962,
|
| 161 |
+
"num_tokens": 1432356.0,
|
| 162 |
+
"step": 130
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"entropy": 0.788033875823021,
|
| 166 |
+
"epoch": 0.2755905511811024,
|
| 167 |
+
"grad_norm": 0.546875,
|
| 168 |
+
"learning_rate": 0.00019805252411531126,
|
| 169 |
+
"loss": 0.7967269420623779,
|
| 170 |
+
"mean_token_accuracy": 0.7931749552488327,
|
| 171 |
+
"num_tokens": 1542545.0,
|
| 172 |
+
"step": 140
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"entropy": 0.8667207360267639,
|
| 176 |
+
"epoch": 0.2952755905511811,
|
| 177 |
+
"grad_norm": 0.5546875,
|
| 178 |
+
"learning_rate": 0.0001976129587636064,
|
| 179 |
+
"loss": 0.8101954460144043,
|
| 180 |
+
"mean_token_accuracy": 0.7908060193061829,
|
| 181 |
+
"num_tokens": 1654462.0,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2952755905511811,
|
| 186 |
+
"eval_entropy": 0.9391163366812246,
|
| 187 |
+
"eval_loss": 0.9146928191184998,
|
| 188 |
+
"eval_mean_token_accuracy": 0.7670937886944523,
|
| 189 |
+
"eval_num_tokens": 1654462.0,
|
| 190 |
+
"eval_runtime": 15.956,
|
| 191 |
+
"eval_samples_per_second": 26.761,
|
| 192 |
+
"eval_steps_per_second": 3.384,
|
| 193 |
+
"step": 150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"entropy": 0.769407157599926,
|
| 197 |
+
"epoch": 0.31496062992125984,
|
| 198 |
+
"grad_norm": 0.470703125,
|
| 199 |
+
"learning_rate": 0.00019712929306529723,
|
| 200 |
+
"loss": 0.7655523777008056,
|
| 201 |
+
"mean_token_accuracy": 0.8053037762641907,
|
| 202 |
+
"num_tokens": 1760181.0,
|
| 203 |
+
"step": 160
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"entropy": 0.8818381905555726,
|
| 207 |
+
"epoch": 0.3346456692913386,
|
| 208 |
+
"grad_norm": 0.625,
|
| 209 |
+
"learning_rate": 0.000196601745534659,
|
| 210 |
+
"loss": 0.8408863067626953,
|
| 211 |
+
"mean_token_accuracy": 0.7815578579902649,
|
| 212 |
+
"num_tokens": 1864683.0,
|
| 213 |
+
"step": 170
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"entropy": 0.8344995141029358,
|
| 217 |
+
"epoch": 0.3543307086614173,
|
| 218 |
+
"grad_norm": 0.4765625,
|
| 219 |
+
"learning_rate": 0.0001960305545112445,
|
| 220 |
+
"loss": 0.8205550193786622,
|
| 221 |
+
"mean_token_accuracy": 0.7871369570493698,
|
| 222 |
+
"num_tokens": 1978641.0,
|
| 223 |
+
"step": 180
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"entropy": 0.8058241099119187,
|
| 227 |
+
"epoch": 0.37401574803149606,
|
| 228 |
+
"grad_norm": 0.494140625,
|
| 229 |
+
"learning_rate": 0.0001954159780522056,
|
| 230 |
+
"loss": 0.8002825736999511,
|
| 231 |
+
"mean_token_accuracy": 0.7913093209266663,
|
| 232 |
+
"num_tokens": 2087989.0,
|
| 233 |
+
"step": 190
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"entropy": 0.8938606142997741,
|
| 237 |
+
"epoch": 0.3937007874015748,
|
| 238 |
+
"grad_norm": 0.61328125,
|
| 239 |
+
"learning_rate": 0.00019475829381570566,
|
| 240 |
+
"loss": 0.8305434226989746,
|
| 241 |
+
"mean_token_accuracy": 0.7836446255445481,
|
| 242 |
+
"num_tokens": 2195494.0,
|
| 243 |
+
"step": 200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.3937007874015748,
|
| 247 |
+
"eval_entropy": 0.9502577009024443,
|
| 248 |
+
"eval_loss": 0.8978050351142883,
|
| 249 |
+
"eval_mean_token_accuracy": 0.7696934717672842,
|
| 250 |
+
"eval_num_tokens": 2195494.0,
|
| 251 |
+
"eval_runtime": 15.9419,
|
| 252 |
+
"eval_samples_per_second": 26.785,
|
| 253 |
+
"eval_steps_per_second": 3.387,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"entropy": 0.7890492826700211,
|
| 258 |
+
"epoch": 0.41338582677165353,
|
| 259 |
+
"grad_norm": 0.40625,
|
| 260 |
+
"learning_rate": 0.0001940577989354773,
|
| 261 |
+
"loss": 0.7953387260437011,
|
| 262 |
+
"mean_token_accuracy": 0.7982505321502685,
|
| 263 |
+
"num_tokens": 2314228.0,
|
| 264 |
+
"step": 210
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"entropy": 0.8576261162757873,
|
| 268 |
+
"epoch": 0.4330708661417323,
|
| 269 |
+
"grad_norm": 0.66015625,
|
| 270 |
+
"learning_rate": 0.00019331480988658083,
|
| 271 |
+
"loss": 0.8120486259460449,
|
| 272 |
+
"mean_token_accuracy": 0.7829198718070984,
|
| 273 |
+
"num_tokens": 2419122.0,
|
| 274 |
+
"step": 220
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"entropy": 0.8514308303594589,
|
| 278 |
+
"epoch": 0.452755905511811,
|
| 279 |
+
"grad_norm": 0.470703125,
|
| 280 |
+
"learning_rate": 0.00019252966234242468,
|
| 281 |
+
"loss": 0.8203784942626953,
|
| 282 |
+
"mean_token_accuracy": 0.7819343030452728,
|
| 283 |
+
"num_tokens": 2524623.0,
|
| 284 |
+
"step": 230
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"entropy": 0.8994888842105866,
|
| 288 |
+
"epoch": 0.47244094488188976,
|
| 289 |
+
"grad_norm": 0.59765625,
|
| 290 |
+
"learning_rate": 0.00019170271102311238,
|
| 291 |
+
"loss": 0.9019557952880859,
|
| 292 |
+
"mean_token_accuracy": 0.7712395042181015,
|
| 293 |
+
"num_tokens": 2631031.0,
|
| 294 |
+
"step": 240
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"entropy": 0.7910601049661636,
|
| 298 |
+
"epoch": 0.4921259842519685,
|
| 299 |
+
"grad_norm": 0.494140625,
|
| 300 |
+
"learning_rate": 0.00019083432953518418,
|
| 301 |
+
"loss": 0.8107678413391113,
|
| 302 |
+
"mean_token_accuracy": 0.7996705889701843,
|
| 303 |
+
"num_tokens": 2741031.0,
|
| 304 |
+
"step": 250
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4921259842519685,
|
| 308 |
+
"eval_entropy": 0.9037868281205496,
|
| 309 |
+
"eval_loss": 0.8843846917152405,
|
| 310 |
+
"eval_mean_token_accuracy": 0.7717091352851303,
|
| 311 |
+
"eval_num_tokens": 2741031.0,
|
| 312 |
+
"eval_runtime": 15.93,
|
| 313 |
+
"eval_samples_per_second": 26.805,
|
| 314 |
+
"eval_steps_per_second": 3.39,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"entropy": 0.7740790158510208,
|
| 319 |
+
"epoch": 0.5118110236220472,
|
| 320 |
+
"grad_norm": 0.57421875,
|
| 321 |
+
"learning_rate": 0.00018992491020282618,
|
| 322 |
+
"loss": 0.7579652309417725,
|
| 323 |
+
"mean_token_accuracy": 0.7955388814210892,
|
| 324 |
+
"num_tokens": 2853547.0,
|
| 325 |
+
"step": 260
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"entropy": 0.8572690159082412,
|
| 329 |
+
"epoch": 0.531496062992126,
|
| 330 |
+
"grad_norm": 1.171875,
|
| 331 |
+
"learning_rate": 0.0001889748638906231,
|
| 332 |
+
"loss": 0.8072081565856933,
|
| 333 |
+
"mean_token_accuracy": 0.7910655379295349,
|
| 334 |
+
"num_tokens": 2968367.0,
|
| 335 |
+
"step": 270
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"entropy": 0.8885004252195359,
|
| 339 |
+
"epoch": 0.5511811023622047,
|
| 340 |
+
"grad_norm": 0.451171875,
|
| 341 |
+
"learning_rate": 0.00018798461981793462,
|
| 342 |
+
"loss": 0.8460770606994629,
|
| 343 |
+
"mean_token_accuracy": 0.7776093751192092,
|
| 344 |
+
"num_tokens": 3075963.0,
|
| 345 |
+
"step": 280
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"entropy": 0.829613895714283,
|
| 349 |
+
"epoch": 0.5708661417322834,
|
| 350 |
+
"grad_norm": 0.4453125,
|
| 351 |
+
"learning_rate": 0.00018695462536497934,
|
| 352 |
+
"loss": 0.823792839050293,
|
| 353 |
+
"mean_token_accuracy": 0.7848509013652801,
|
| 354 |
+
"num_tokens": 3185899.0,
|
| 355 |
+
"step": 290
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"entropy": 0.8341330245137215,
|
| 359 |
+
"epoch": 0.5905511811023622,
|
| 360 |
+
"grad_norm": 0.490234375,
|
| 361 |
+
"learning_rate": 0.00018588534587071385,
|
| 362 |
+
"loss": 0.810818099975586,
|
| 363 |
+
"mean_token_accuracy": 0.7906568497419357,
|
| 364 |
+
"num_tokens": 3297319.0,
|
| 365 |
+
"step": 300
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.5905511811023622,
|
| 369 |
+
"eval_entropy": 0.8445847459413387,
|
| 370 |
+
"eval_loss": 0.8718247413635254,
|
| 371 |
+
"eval_mean_token_accuracy": 0.774838043583764,
|
| 372 |
+
"eval_num_tokens": 3297319.0,
|
| 373 |
+
"eval_runtime": 15.9561,
|
| 374 |
+
"eval_samples_per_second": 26.761,
|
| 375 |
+
"eval_steps_per_second": 3.384,
|
| 376 |
+
"step": 300
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"entropy": 0.8317201763391495,
|
| 380 |
+
"epoch": 0.610236220472441,
|
| 381 |
+
"grad_norm": 0.396484375,
|
| 382 |
+
"learning_rate": 0.00018477726442259806,
|
| 383 |
+
"loss": 0.80075101852417,
|
| 384 |
+
"mean_token_accuracy": 0.7886052161455155,
|
| 385 |
+
"num_tokens": 3415477.0,
|
| 386 |
+
"step": 310
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"entropy": 0.8597566410899162,
|
| 390 |
+
"epoch": 0.6299212598425197,
|
| 391 |
+
"grad_norm": 0.404296875,
|
| 392 |
+
"learning_rate": 0.00018363088163834252,
|
| 393 |
+
"loss": 0.8123328208923339,
|
| 394 |
+
"mean_token_accuracy": 0.7854531407356262,
|
| 395 |
+
"num_tokens": 3524759.0,
|
| 396 |
+
"step": 320
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"entropy": 0.8519140958786011,
|
| 400 |
+
"epoch": 0.6496062992125984,
|
| 401 |
+
"grad_norm": 0.458984375,
|
| 402 |
+
"learning_rate": 0.00018244671543973513,
|
| 403 |
+
"loss": 0.8214571952819825,
|
| 404 |
+
"mean_token_accuracy": 0.7828344345092774,
|
| 405 |
+
"num_tokens": 3640838.0,
|
| 406 |
+
"step": 330
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"entropy": 0.7781533747911453,
|
| 410 |
+
"epoch": 0.6692913385826772,
|
| 411 |
+
"grad_norm": 0.51953125,
|
| 412 |
+
"learning_rate": 0.0001812253008186505,
|
| 413 |
+
"loss": 0.753899097442627,
|
| 414 |
+
"mean_token_accuracy": 0.8011120349168778,
|
| 415 |
+
"num_tokens": 3756735.0,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"entropy": 0.8384901583194733,
|
| 420 |
+
"epoch": 0.6889763779527559,
|
| 421 |
+
"grad_norm": 0.51171875,
|
| 422 |
+
"learning_rate": 0.0001799671895953471,
|
| 423 |
+
"loss": 0.8112489700317382,
|
| 424 |
+
"mean_token_accuracy": 0.7898134678602219,
|
| 425 |
+
"num_tokens": 3870377.0,
|
| 426 |
+
"step": 350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6889763779527559,
|
| 430 |
+
"eval_entropy": 0.8795759567507991,
|
| 431 |
+
"eval_loss": 0.8568941354751587,
|
| 432 |
+
"eval_mean_token_accuracy": 0.7754804182935644,
|
| 433 |
+
"eval_num_tokens": 3870377.0,
|
| 434 |
+
"eval_runtime": 15.9337,
|
| 435 |
+
"eval_samples_per_second": 26.798,
|
| 436 |
+
"eval_steps_per_second": 3.389,
|
| 437 |
+
"step": 350
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"entropy": 0.8008699864149094,
|
| 441 |
+
"epoch": 0.7086614173228346,
|
| 442 |
+
"grad_norm": 0.498046875,
|
| 443 |
+
"learning_rate": 0.00017867295016916167,
|
| 444 |
+
"loss": 0.7585730075836181,
|
| 445 |
+
"mean_token_accuracy": 0.7942175149917603,
|
| 446 |
+
"num_tokens": 3975692.0,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"entropy": 0.9035080641508102,
|
| 451 |
+
"epoch": 0.7283464566929134,
|
| 452 |
+
"grad_norm": 0.48046875,
|
| 453 |
+
"learning_rate": 0.0001773431672617132,
|
| 454 |
+
"loss": 0.8653995513916015,
|
| 455 |
+
"mean_token_accuracy": 0.7730168104171753,
|
| 456 |
+
"num_tokens": 4087256.0,
|
| 457 |
+
"step": 370
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"entropy": 0.760843014717102,
|
| 461 |
+
"epoch": 0.7480314960629921,
|
| 462 |
+
"grad_norm": 0.49609375,
|
| 463 |
+
"learning_rate": 0.00017597844165273286,
|
| 464 |
+
"loss": 0.7377382278442383,
|
| 465 |
+
"mean_token_accuracy": 0.7972156703472137,
|
| 466 |
+
"num_tokens": 4192629.0,
|
| 467 |
+
"step": 380
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"entropy": 0.8075762838125229,
|
| 471 |
+
"epoch": 0.7677165354330708,
|
| 472 |
+
"grad_norm": 0.447265625,
|
| 473 |
+
"learning_rate": 0.00017457938990863908,
|
| 474 |
+
"loss": 0.7615089893341065,
|
| 475 |
+
"mean_token_accuracy": 0.8005614727735519,
|
| 476 |
+
"num_tokens": 4303838.0,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"entropy": 0.8942124575376511,
|
| 481 |
+
"epoch": 0.7874015748031497,
|
| 482 |
+
"grad_norm": 0.48828125,
|
| 483 |
+
"learning_rate": 0.00017314664410398033,
|
| 484 |
+
"loss": 0.8365015983581543,
|
| 485 |
+
"mean_token_accuracy": 0.7790710270404816,
|
| 486 |
+
"num_tokens": 4414002.0,
|
| 487 |
+
"step": 400
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.7874015748031497,
|
| 491 |
+
"eval_entropy": 0.8613758815659417,
|
| 492 |
+
"eval_loss": 0.8455358743667603,
|
| 493 |
+
"eval_mean_token_accuracy": 0.7789811304321995,
|
| 494 |
+
"eval_num_tokens": 4414002.0,
|
| 495 |
+
"eval_runtime": 16.2401,
|
| 496 |
+
"eval_samples_per_second": 26.293,
|
| 497 |
+
"eval_steps_per_second": 3.325,
|
| 498 |
+
"step": 400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"entropy": 0.7841676041483879,
|
| 502 |
+
"epoch": 0.8070866141732284,
|
| 503 |
+
"grad_norm": 0.57421875,
|
| 504 |
+
"learning_rate": 0.0001716808515358714,
|
| 505 |
+
"loss": 0.8027224540710449,
|
| 506 |
+
"mean_token_accuracy": 0.79732064306736,
|
| 507 |
+
"num_tokens": 4525758.0,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"entropy": 0.7710117936134339,
|
| 512 |
+
"epoch": 0.8267716535433071,
|
| 513 |
+
"grad_norm": 0.4453125,
|
| 514 |
+
"learning_rate": 0.00017018267443155268,
|
| 515 |
+
"loss": 0.7185665130615234,
|
| 516 |
+
"mean_token_accuracy": 0.807221668958664,
|
| 517 |
+
"num_tokens": 4640742.0,
|
| 518 |
+
"step": 420
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"entropy": 0.8494665056467057,
|
| 522 |
+
"epoch": 0.8464566929133859,
|
| 523 |
+
"grad_norm": 0.453125,
|
| 524 |
+
"learning_rate": 0.00016865278964920378,
|
| 525 |
+
"loss": 0.8273701667785645,
|
| 526 |
+
"mean_token_accuracy": 0.7870708376169204,
|
| 527 |
+
"num_tokens": 4754244.0,
|
| 528 |
+
"step": 430
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"entropy": 0.7938957527279854,
|
| 532 |
+
"epoch": 0.8661417322834646,
|
| 533 |
+
"grad_norm": 0.345703125,
|
| 534 |
+
"learning_rate": 0.00016709188837214732,
|
| 535 |
+
"loss": 0.7776453971862793,
|
| 536 |
+
"mean_token_accuracy": 0.7911081612110138,
|
| 537 |
+
"num_tokens": 4862576.0,
|
| 538 |
+
"step": 440
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"entropy": 0.7948901996016502,
|
| 542 |
+
"epoch": 0.8858267716535433,
|
| 543 |
+
"grad_norm": 0.376953125,
|
| 544 |
+
"learning_rate": 0.0001655006757965806,
|
| 545 |
+
"loss": 0.7554664611816406,
|
| 546 |
+
"mean_token_accuracy": 0.7939331024885178,
|
| 547 |
+
"num_tokens": 4984410.0,
|
| 548 |
+
"step": 450
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8858267716535433,
|
| 552 |
+
"eval_entropy": 0.8405309479545664,
|
| 553 |
+
"eval_loss": 0.8371886610984802,
|
| 554 |
+
"eval_mean_token_accuracy": 0.7799682672376986,
|
| 555 |
+
"eval_num_tokens": 4984410.0,
|
| 556 |
+
"eval_runtime": 15.9419,
|
| 557 |
+
"eval_samples_per_second": 26.785,
|
| 558 |
+
"eval_steps_per_second": 3.387,
|
| 559 |
+
"step": 450
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"entropy": 0.8764406844973565,
|
| 563 |
+
"epoch": 0.905511811023622,
|
| 564 |
+
"grad_norm": 0.5625,
|
| 565 |
+
"learning_rate": 0.0001638798708129768,
|
| 566 |
+
"loss": 0.8325652122497559,
|
| 567 |
+
"mean_token_accuracy": 0.7821455717086792,
|
| 568 |
+
"num_tokens": 5094029.0,
|
| 569 |
+
"step": 460
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"entropy": 0.8582975655794144,
|
| 573 |
+
"epoch": 0.9251968503937008,
|
| 574 |
+
"grad_norm": 0.3828125,
|
| 575 |
+
"learning_rate": 0.00016223020568129854,
|
| 576 |
+
"loss": 0.8309861183166504,
|
| 577 |
+
"mean_token_accuracy": 0.7791573971509933,
|
| 578 |
+
"num_tokens": 5210613.0,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"entropy": 0.8273941457271576,
|
| 583 |
+
"epoch": 0.9448818897637795,
|
| 584 |
+
"grad_norm": 0.59375,
|
| 585 |
+
"learning_rate": 0.00016055242570017244,
|
| 586 |
+
"loss": 0.7878972053527832,
|
| 587 |
+
"mean_token_accuracy": 0.7900911033153534,
|
| 588 |
+
"num_tokens": 5322546.0,
|
| 589 |
+
"step": 480
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"entropy": 0.8146103203296662,
|
| 593 |
+
"epoch": 0.9645669291338582,
|
| 594 |
+
"grad_norm": 0.42578125,
|
| 595 |
+
"learning_rate": 0.00015884728887017162,
|
| 596 |
+
"loss": 0.7865399837493896,
|
| 597 |
+
"mean_token_accuracy": 0.7947310745716095,
|
| 598 |
+
"num_tokens": 5434008.0,
|
| 599 |
+
"step": 490
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"entropy": 0.6613125756382943,
|
| 603 |
+
"epoch": 0.984251968503937,
|
| 604 |
+
"grad_norm": 0.41796875,
|
| 605 |
+
"learning_rate": 0.0001571155655513606,
|
| 606 |
+
"loss": 0.6725417137145996,
|
| 607 |
+
"mean_token_accuracy": 0.816859421133995,
|
| 608 |
+
"num_tokens": 5544086.0,
|
| 609 |
+
"step": 500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.984251968503937,
|
| 613 |
+
"eval_entropy": 0.8118620448642306,
|
| 614 |
+
"eval_loss": 0.8308539986610413,
|
| 615 |
+
"eval_mean_token_accuracy": 0.781522473803273,
|
| 616 |
+
"eval_num_tokens": 5544086.0,
|
| 617 |
+
"eval_runtime": 15.9383,
|
| 618 |
+
"eval_samples_per_second": 26.791,
|
| 619 |
+
"eval_steps_per_second": 3.388,
|
| 620 |
+
"step": 500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.7347942754626274,
|
| 624 |
+
"epoch": 1.0039370078740157,
|
| 625 |
+
"grad_norm": 0.39453125,
|
| 626 |
+
"learning_rate": 0.0001553580381152559,
|
| 627 |
+
"loss": 0.6915054798126221,
|
| 628 |
+
"mean_token_accuracy": 0.8176700383424759,
|
| 629 |
+
"num_tokens": 5657246.0,
|
| 630 |
+
"step": 510
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.7550317242741584,
|
| 634 |
+
"epoch": 1.0236220472440944,
|
| 635 |
+
"grad_norm": 0.4921875,
|
| 636 |
+
"learning_rate": 0.0001535755005913602,
|
| 637 |
+
"loss": 0.6865068912506104,
|
| 638 |
+
"mean_token_accuracy": 0.8140248268842697,
|
| 639 |
+
"num_tokens": 5768184.0,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.7479684263467788,
|
| 644 |
+
"epoch": 1.0433070866141732,
|
| 645 |
+
"grad_norm": 0.60546875,
|
| 646 |
+
"learning_rate": 0.00015176875830842938,
|
| 647 |
+
"loss": 0.7037695407867431,
|
| 648 |
+
"mean_token_accuracy": 0.8133333414793015,
|
| 649 |
+
"num_tokens": 5885598.0,
|
| 650 |
+
"step": 530
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.6792907789349556,
|
| 654 |
+
"epoch": 1.0629921259842519,
|
| 655 |
+
"grad_norm": 0.439453125,
|
| 656 |
+
"learning_rate": 0.0001499386275306348,
|
| 657 |
+
"loss": 0.640275239944458,
|
| 658 |
+
"mean_token_accuracy": 0.8249545454978943,
|
| 659 |
+
"num_tokens": 6002120.0,
|
| 660 |
+
"step": 540
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.6819084867835045,
|
| 664 |
+
"epoch": 1.0826771653543308,
|
| 665 |
+
"grad_norm": 0.41015625,
|
| 666 |
+
"learning_rate": 0.0001480859350887852,
|
| 667 |
+
"loss": 0.6469451904296875,
|
| 668 |
+
"mean_token_accuracy": 0.8235166579484939,
|
| 669 |
+
"num_tokens": 6112085.0,
|
| 670 |
+
"step": 550
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.0826771653543308,
|
| 674 |
+
"eval_entropy": 0.8042021377219094,
|
| 675 |
+
"eval_loss": 0.8352769017219543,
|
| 676 |
+
"eval_mean_token_accuracy": 0.7806271998970596,
|
| 677 |
+
"eval_num_tokens": 6112085.0,
|
| 678 |
+
"eval_runtime": 15.9298,
|
| 679 |
+
"eval_samples_per_second": 26.805,
|
| 680 |
+
"eval_steps_per_second": 3.39,
|
| 681 |
+
"step": 550
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"entropy": 0.7026952266693115,
|
| 685 |
+
"epoch": 1.1023622047244095,
|
| 686 |
+
"grad_norm": 0.47265625,
|
| 687 |
+
"learning_rate": 0.00014621151800677434,
|
| 688 |
+
"loss": 0.667764139175415,
|
| 689 |
+
"mean_token_accuracy": 0.8164290696382522,
|
| 690 |
+
"num_tokens": 6224645.0,
|
| 691 |
+
"step": 560
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"entropy": 0.6083555489778518,
|
| 695 |
+
"epoch": 1.1220472440944882,
|
| 696 |
+
"grad_norm": 0.37890625,
|
| 697 |
+
"learning_rate": 0.0001443162231234242,
|
| 698 |
+
"loss": 0.5703843116760254,
|
| 699 |
+
"mean_token_accuracy": 0.8396952480077744,
|
| 700 |
+
"num_tokens": 6336790.0,
|
| 701 |
+
"step": 570
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"entropy": 0.6823922500014306,
|
| 705 |
+
"epoch": 1.141732283464567,
|
| 706 |
+
"grad_norm": 0.55078125,
|
| 707 |
+
"learning_rate": 0.0001424009067098931,
|
| 708 |
+
"loss": 0.6488718032836914,
|
| 709 |
+
"mean_token_accuracy": 0.8208951652050018,
|
| 710 |
+
"num_tokens": 6450761.0,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"entropy": 0.6331134095788002,
|
| 715 |
+
"epoch": 1.1614173228346456,
|
| 716 |
+
"grad_norm": 0.482421875,
|
| 717 |
+
"learning_rate": 0.00014046643408282305,
|
| 718 |
+
"loss": 0.5916334629058838,
|
| 719 |
+
"mean_token_accuracy": 0.8340157747268677,
|
| 720 |
+
"num_tokens": 6562060.0,
|
| 721 |
+
"step": 590
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"entropy": 0.6203767985105515,
|
| 725 |
+
"epoch": 1.1811023622047245,
|
| 726 |
+
"grad_norm": 0.45703125,
|
| 727 |
+
"learning_rate": 0.00013851367921340017,
|
| 728 |
+
"loss": 0.5833216667175293,
|
| 729 |
+
"mean_token_accuracy": 0.8345949351787567,
|
| 730 |
+
"num_tokens": 6676922.0,
|
| 731 |
+
"step": 600
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1811023622047245,
|
| 735 |
+
"eval_entropy": 0.7756788493306549,
|
| 736 |
+
"eval_loss": 0.8351659178733826,
|
| 737 |
+
"eval_mean_token_accuracy": 0.7810865651678156,
|
| 738 |
+
"eval_num_tokens": 6676922.0,
|
| 739 |
+
"eval_runtime": 15.9481,
|
| 740 |
+
"eval_samples_per_second": 26.774,
|
| 741 |
+
"eval_steps_per_second": 3.386,
|
| 742 |
+
"step": 600
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"entropy": 0.645186324417591,
|
| 746 |
+
"epoch": 1.2007874015748032,
|
| 747 |
+
"grad_norm": 0.498046875,
|
| 748 |
+
"learning_rate": 0.0001365435243325051,
|
| 749 |
+
"loss": 0.6237170219421386,
|
| 750 |
+
"mean_token_accuracy": 0.8277532249689102,
|
| 751 |
+
"num_tokens": 6783497.0,
|
| 752 |
+
"step": 610
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"entropy": 0.6759833052754403,
|
| 756 |
+
"epoch": 1.220472440944882,
|
| 757 |
+
"grad_norm": 0.546875,
|
| 758 |
+
"learning_rate": 0.00013455685953213194,
|
| 759 |
+
"loss": 0.6462036609649658,
|
| 760 |
+
"mean_token_accuracy": 0.8247299671173096,
|
| 761 |
+
"num_tokens": 6894014.0,
|
| 762 |
+
"step": 620
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"entropy": 0.6737162366509437,
|
| 766 |
+
"epoch": 1.2401574803149606,
|
| 767 |
+
"grad_norm": 0.48828125,
|
| 768 |
+
"learning_rate": 0.0001325545823632554,
|
| 769 |
+
"loss": 0.6107028484344482,
|
| 770 |
+
"mean_token_accuracy": 0.8260864973068237,
|
| 771 |
+
"num_tokens": 6997350.0,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"entropy": 0.6702337503433228,
|
| 776 |
+
"epoch": 1.2598425196850394,
|
| 777 |
+
"grad_norm": 0.451171875,
|
| 778 |
+
"learning_rate": 0.00013053759743032823,
|
| 779 |
+
"loss": 0.6504123210906982,
|
| 780 |
+
"mean_token_accuracy": 0.818900191783905,
|
| 781 |
+
"num_tokens": 7109067.0,
|
| 782 |
+
"step": 640
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"entropy": 0.7739008516073227,
|
| 786 |
+
"epoch": 1.279527559055118,
|
| 787 |
+
"grad_norm": 0.56640625,
|
| 788 |
+
"learning_rate": 0.00012850681598259195,
|
| 789 |
+
"loss": 0.7173595905303956,
|
| 790 |
+
"mean_token_accuracy": 0.7997365325689316,
|
| 791 |
+
"num_tokens": 7218739.0,
|
| 792 |
+
"step": 650
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.279527559055118,
|
| 796 |
+
"eval_entropy": 0.7500080190323017,
|
| 797 |
+
"eval_loss": 0.8297256231307983,
|
| 798 |
+
"eval_mean_token_accuracy": 0.7822851461392862,
|
| 799 |
+
"eval_num_tokens": 7218739.0,
|
| 800 |
+
"eval_runtime": 15.9417,
|
| 801 |
+
"eval_samples_per_second": 26.785,
|
| 802 |
+
"eval_steps_per_second": 3.387,
|
| 803 |
+
"step": 650
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"entropy": 0.7080179423093795,
|
| 807 |
+
"epoch": 1.2992125984251968,
|
| 808 |
+
"grad_norm": 0.53125,
|
| 809 |
+
"learning_rate": 0.0001264631555023856,
|
| 810 |
+
"loss": 0.661363172531128,
|
| 811 |
+
"mean_token_accuracy": 0.8172380715608597,
|
| 812 |
+
"num_tokens": 7334561.0,
|
| 813 |
+
"step": 660
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"entropy": 0.6184108316898346,
|
| 817 |
+
"epoch": 1.3188976377952755,
|
| 818 |
+
"grad_norm": 0.78515625,
|
| 819 |
+
"learning_rate": 0.00012440753929063826,
|
| 820 |
+
"loss": 0.6013145923614502,
|
| 821 |
+
"mean_token_accuracy": 0.8273262619972229,
|
| 822 |
+
"num_tokens": 7443871.0,
|
| 823 |
+
"step": 670
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"entropy": 0.71297377794981,
|
| 827 |
+
"epoch": 1.3385826771653544,
|
| 828 |
+
"grad_norm": 0.5078125,
|
| 829 |
+
"learning_rate": 0.00012234089604973303,
|
| 830 |
+
"loss": 0.6702734470367432,
|
| 831 |
+
"mean_token_accuracy": 0.8151450455188751,
|
| 832 |
+
"num_tokens": 7555559.0,
|
| 833 |
+
"step": 680
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"entropy": 0.6389088705182076,
|
| 837 |
+
"epoch": 1.358267716535433,
|
| 838 |
+
"grad_norm": 0.50390625,
|
| 839 |
+
"learning_rate": 0.0001202641594639305,
|
| 840 |
+
"loss": 0.6133567810058593,
|
| 841 |
+
"mean_token_accuracy": 0.8298202604055405,
|
| 842 |
+
"num_tokens": 7669861.0,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"entropy": 0.7520714432001114,
|
| 847 |
+
"epoch": 1.3779527559055118,
|
| 848 |
+
"grad_norm": 0.5390625,
|
| 849 |
+
"learning_rate": 0.00011817826777754171,
|
| 850 |
+
"loss": 0.6847642421722412,
|
| 851 |
+
"mean_token_accuracy": 0.8055585384368896,
|
| 852 |
+
"num_tokens": 7782831.0,
|
| 853 |
+
"step": 700
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.3779527559055118,
|
| 857 |
+
"eval_entropy": 0.7791200037355777,
|
| 858 |
+
"eval_loss": 0.8222253322601318,
|
| 859 |
+
"eval_mean_token_accuracy": 0.7843283326537521,
|
| 860 |
+
"eval_num_tokens": 7782831.0,
|
| 861 |
+
"eval_runtime": 15.9494,
|
| 862 |
+
"eval_samples_per_second": 26.772,
|
| 863 |
+
"eval_steps_per_second": 3.386,
|
| 864 |
+
"step": 700
|
| 865 |
+
}
|
| 866 |
+
],
|
| 867 |
+
"logging_steps": 10,
|
| 868 |
+
"max_steps": 1524,
|
| 869 |
+
"num_input_tokens_seen": 0,
|
| 870 |
+
"num_train_epochs": 3,
|
| 871 |
+
"save_steps": 50,
|
| 872 |
+
"stateful_callbacks": {
|
| 873 |
+
"TrainerControl": {
|
| 874 |
+
"args": {
|
| 875 |
+
"should_epoch_stop": false,
|
| 876 |
+
"should_evaluate": false,
|
| 877 |
+
"should_log": false,
|
| 878 |
+
"should_save": true,
|
| 879 |
+
"should_training_stop": false
|
| 880 |
+
},
|
| 881 |
+
"attributes": {}
|
| 882 |
+
}
|
| 883 |
+
},
|
| 884 |
+
"total_flos": 1.0962523215229133e+17,
|
| 885 |
+
"train_batch_size": 8,
|
| 886 |
+
"trial_name": null,
|
| 887 |
+
"trial_params": null
|
| 888 |
+
}
|
checkpoint-700/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
|
| 3 |
+
size 5713
|
checkpoint-750/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
checkpoint-750/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-Instruct",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 32,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"down_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"gate_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-750/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af0491ec58ad03820e66ac4abf78e7f17c7993a1f506e8279d8e4ce100317bcd
|
| 3 |
+
size 73911504
|
checkpoint-750/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:330fd1771cc26450c97f464fa33bbb1849256512502a7affd103516d55094709
|
| 3 |
+
size 75481221
|
checkpoint-750/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d318cd4ea9e9c6b783386b2e856aee90a42129153b6eeed98e937da5f5431f9
|
| 3 |
+
size 14581
|
checkpoint-750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aca170ed76417e6b2df97df374cbac1a5d9133d796b9d1f1cd529129ae172624
|
| 3 |
+
size 1465
|
checkpoint-750/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
| 3 |
+
size 11421892
|
checkpoint-750/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|fim_pad|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
checkpoint-750/trainer_state.json
ADDED
|
@@ -0,0 +1,949 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4763779527559056,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 750,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.4378354728221894,
|
| 14 |
+
"epoch": 0.01968503937007874,
|
| 15 |
+
"grad_norm": 0.62109375,
|
| 16 |
+
"learning_rate": 3.91304347826087e-05,
|
| 17 |
+
"loss": 1.657682228088379,
|
| 18 |
+
"mean_token_accuracy": 0.6598833322525024,
|
| 19 |
+
"num_tokens": 115439.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5141301095485686,
|
| 24 |
+
"epoch": 0.03937007874015748,
|
| 25 |
+
"grad_norm": 0.44140625,
|
| 26 |
+
"learning_rate": 8.260869565217392e-05,
|
| 27 |
+
"loss": 1.4646138191223144,
|
| 28 |
+
"mean_token_accuracy": 0.6834615051746369,
|
| 29 |
+
"num_tokens": 225264.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.2295305937528611,
|
| 34 |
+
"epoch": 0.05905511811023622,
|
| 35 |
+
"grad_norm": 0.6796875,
|
| 36 |
+
"learning_rate": 0.00012608695652173915,
|
| 37 |
+
"loss": 1.1134957313537597,
|
| 38 |
+
"mean_token_accuracy": 0.7453642427921295,
|
| 39 |
+
"num_tokens": 330923.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.0573274463415145,
|
| 44 |
+
"epoch": 0.07874015748031496,
|
| 45 |
+
"grad_norm": 0.474609375,
|
| 46 |
+
"learning_rate": 0.00016956521739130436,
|
| 47 |
+
"loss": 1.077296829223633,
|
| 48 |
+
"mean_token_accuracy": 0.7446383863687516,
|
| 49 |
+
"num_tokens": 437622.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.952904561161995,
|
| 54 |
+
"epoch": 0.0984251968503937,
|
| 55 |
+
"grad_norm": 0.50390625,
|
| 56 |
+
"learning_rate": 0.00019999796688511753,
|
| 57 |
+
"loss": 0.9590332984924317,
|
| 58 |
+
"mean_token_accuracy": 0.768164387345314,
|
| 59 |
+
"num_tokens": 551175.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0984251968503937,
|
| 64 |
+
"eval_entropy": 1.0900797645250957,
|
| 65 |
+
"eval_loss": 1.0484484434127808,
|
| 66 |
+
"eval_mean_token_accuracy": 0.7461776600943671,
|
| 67 |
+
"eval_num_tokens": 551175.0,
|
| 68 |
+
"eval_runtime": 15.9866,
|
| 69 |
+
"eval_samples_per_second": 26.71,
|
| 70 |
+
"eval_steps_per_second": 3.378,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"entropy": 0.9487997680902481,
|
| 75 |
+
"epoch": 0.11811023622047244,
|
| 76 |
+
"grad_norm": 0.59375,
|
| 77 |
+
"learning_rate": 0.0001999618249203163,
|
| 78 |
+
"loss": 0.9577752113342285,
|
| 79 |
+
"mean_token_accuracy": 0.7689193069934845,
|
| 80 |
+
"num_tokens": 658006.0,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"entropy": 1.0506175458431244,
|
| 85 |
+
"epoch": 0.1377952755905512,
|
| 86 |
+
"grad_norm": 0.5390625,
|
| 87 |
+
"learning_rate": 0.00019988052141977201,
|
| 88 |
+
"loss": 0.9976933479309082,
|
| 89 |
+
"mean_token_accuracy": 0.756487911939621,
|
| 90 |
+
"num_tokens": 771278.0,
|
| 91 |
+
"step": 70
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.8528705358505249,
|
| 95 |
+
"epoch": 0.15748031496062992,
|
| 96 |
+
"grad_norm": 0.5078125,
|
| 97 |
+
"learning_rate": 0.0001997540931154166,
|
| 98 |
+
"loss": 0.8407608032226562,
|
| 99 |
+
"mean_token_accuracy": 0.7868376106023789,
|
| 100 |
+
"num_tokens": 886071.0,
|
| 101 |
+
"step": 80
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.9220433413982392,
|
| 105 |
+
"epoch": 0.17716535433070865,
|
| 106 |
+
"grad_norm": 0.484375,
|
| 107 |
+
"learning_rate": 0.00019958259712601903,
|
| 108 |
+
"loss": 0.8958203315734863,
|
| 109 |
+
"mean_token_accuracy": 0.7736223608255386,
|
| 110 |
+
"num_tokens": 996361.0,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.8399994730949402,
|
| 115 |
+
"epoch": 0.1968503937007874,
|
| 116 |
+
"grad_norm": 0.51953125,
|
| 117 |
+
"learning_rate": 0.00019936611093137983,
|
| 118 |
+
"loss": 0.8394058227539063,
|
| 119 |
+
"mean_token_accuracy": 0.7876519203186035,
|
| 120 |
+
"num_tokens": 1103999.0,
|
| 121 |
+
"step": 100
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1968503937007874,
|
| 125 |
+
"eval_entropy": 0.9908565746413337,
|
| 126 |
+
"eval_loss": 0.949418842792511,
|
| 127 |
+
"eval_mean_token_accuracy": 0.7609190278583102,
|
| 128 |
+
"eval_num_tokens": 1103999.0,
|
| 129 |
+
"eval_runtime": 15.9475,
|
| 130 |
+
"eval_samples_per_second": 26.775,
|
| 131 |
+
"eval_steps_per_second": 3.386,
|
| 132 |
+
"step": 100
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"entropy": 0.8772778362035751,
|
| 136 |
+
"epoch": 0.21653543307086615,
|
| 137 |
+
"grad_norm": 0.40625,
|
| 138 |
+
"learning_rate": 0.00019910473233732668,
|
| 139 |
+
"loss": 0.8347702026367188,
|
| 140 |
+
"mean_token_accuracy": 0.7877911299467086,
|
| 141 |
+
"num_tokens": 1216586.0,
|
| 142 |
+
"step": 110
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"entropy": 0.8745568007230758,
|
| 146 |
+
"epoch": 0.23622047244094488,
|
| 147 |
+
"grad_norm": 0.609375,
|
| 148 |
+
"learning_rate": 0.00019879857943152674,
|
| 149 |
+
"loss": 0.8359953880310058,
|
| 150 |
+
"mean_token_accuracy": 0.7790884494781494,
|
| 151 |
+
"num_tokens": 1324767.0,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"entropy": 0.878146781027317,
|
| 156 |
+
"epoch": 0.2559055118110236,
|
| 157 |
+
"grad_norm": 0.5390625,
|
| 158 |
+
"learning_rate": 0.00019844779053013637,
|
| 159 |
+
"loss": 0.8335110664367675,
|
| 160 |
+
"mean_token_accuracy": 0.7791220843791962,
|
| 161 |
+
"num_tokens": 1432356.0,
|
| 162 |
+
"step": 130
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"entropy": 0.788033875823021,
|
| 166 |
+
"epoch": 0.2755905511811024,
|
| 167 |
+
"grad_norm": 0.546875,
|
| 168 |
+
"learning_rate": 0.00019805252411531126,
|
| 169 |
+
"loss": 0.7967269420623779,
|
| 170 |
+
"mean_token_accuracy": 0.7931749552488327,
|
| 171 |
+
"num_tokens": 1542545.0,
|
| 172 |
+
"step": 140
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"entropy": 0.8667207360267639,
|
| 176 |
+
"epoch": 0.2952755905511811,
|
| 177 |
+
"grad_norm": 0.5546875,
|
| 178 |
+
"learning_rate": 0.0001976129587636064,
|
| 179 |
+
"loss": 0.8101954460144043,
|
| 180 |
+
"mean_token_accuracy": 0.7908060193061829,
|
| 181 |
+
"num_tokens": 1654462.0,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2952755905511811,
|
| 186 |
+
"eval_entropy": 0.9391163366812246,
|
| 187 |
+
"eval_loss": 0.9146928191184998,
|
| 188 |
+
"eval_mean_token_accuracy": 0.7670937886944523,
|
| 189 |
+
"eval_num_tokens": 1654462.0,
|
| 190 |
+
"eval_runtime": 15.956,
|
| 191 |
+
"eval_samples_per_second": 26.761,
|
| 192 |
+
"eval_steps_per_second": 3.384,
|
| 193 |
+
"step": 150
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"entropy": 0.769407157599926,
|
| 197 |
+
"epoch": 0.31496062992125984,
|
| 198 |
+
"grad_norm": 0.470703125,
|
| 199 |
+
"learning_rate": 0.00019712929306529723,
|
| 200 |
+
"loss": 0.7655523777008056,
|
| 201 |
+
"mean_token_accuracy": 0.8053037762641907,
|
| 202 |
+
"num_tokens": 1760181.0,
|
| 203 |
+
"step": 160
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"entropy": 0.8818381905555726,
|
| 207 |
+
"epoch": 0.3346456692913386,
|
| 208 |
+
"grad_norm": 0.625,
|
| 209 |
+
"learning_rate": 0.000196601745534659,
|
| 210 |
+
"loss": 0.8408863067626953,
|
| 211 |
+
"mean_token_accuracy": 0.7815578579902649,
|
| 212 |
+
"num_tokens": 1864683.0,
|
| 213 |
+
"step": 170
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"entropy": 0.8344995141029358,
|
| 217 |
+
"epoch": 0.3543307086614173,
|
| 218 |
+
"grad_norm": 0.4765625,
|
| 219 |
+
"learning_rate": 0.0001960305545112445,
|
| 220 |
+
"loss": 0.8205550193786622,
|
| 221 |
+
"mean_token_accuracy": 0.7871369570493698,
|
| 222 |
+
"num_tokens": 1978641.0,
|
| 223 |
+
"step": 180
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"entropy": 0.8058241099119187,
|
| 227 |
+
"epoch": 0.37401574803149606,
|
| 228 |
+
"grad_norm": 0.494140625,
|
| 229 |
+
"learning_rate": 0.0001954159780522056,
|
| 230 |
+
"loss": 0.8002825736999511,
|
| 231 |
+
"mean_token_accuracy": 0.7913093209266663,
|
| 232 |
+
"num_tokens": 2087989.0,
|
| 233 |
+
"step": 190
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"entropy": 0.8938606142997741,
|
| 237 |
+
"epoch": 0.3937007874015748,
|
| 238 |
+
"grad_norm": 0.61328125,
|
| 239 |
+
"learning_rate": 0.00019475829381570566,
|
| 240 |
+
"loss": 0.8305434226989746,
|
| 241 |
+
"mean_token_accuracy": 0.7836446255445481,
|
| 242 |
+
"num_tokens": 2195494.0,
|
| 243 |
+
"step": 200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.3937007874015748,
|
| 247 |
+
"eval_entropy": 0.9502577009024443,
|
| 248 |
+
"eval_loss": 0.8978050351142883,
|
| 249 |
+
"eval_mean_token_accuracy": 0.7696934717672842,
|
| 250 |
+
"eval_num_tokens": 2195494.0,
|
| 251 |
+
"eval_runtime": 15.9419,
|
| 252 |
+
"eval_samples_per_second": 26.785,
|
| 253 |
+
"eval_steps_per_second": 3.387,
|
| 254 |
+
"step": 200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"entropy": 0.7890492826700211,
|
| 258 |
+
"epoch": 0.41338582677165353,
|
| 259 |
+
"grad_norm": 0.40625,
|
| 260 |
+
"learning_rate": 0.0001940577989354773,
|
| 261 |
+
"loss": 0.7953387260437011,
|
| 262 |
+
"mean_token_accuracy": 0.7982505321502685,
|
| 263 |
+
"num_tokens": 2314228.0,
|
| 264 |
+
"step": 210
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"entropy": 0.8576261162757873,
|
| 268 |
+
"epoch": 0.4330708661417323,
|
| 269 |
+
"grad_norm": 0.66015625,
|
| 270 |
+
"learning_rate": 0.00019331480988658083,
|
| 271 |
+
"loss": 0.8120486259460449,
|
| 272 |
+
"mean_token_accuracy": 0.7829198718070984,
|
| 273 |
+
"num_tokens": 2419122.0,
|
| 274 |
+
"step": 220
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"entropy": 0.8514308303594589,
|
| 278 |
+
"epoch": 0.452755905511811,
|
| 279 |
+
"grad_norm": 0.470703125,
|
| 280 |
+
"learning_rate": 0.00019252966234242468,
|
| 281 |
+
"loss": 0.8203784942626953,
|
| 282 |
+
"mean_token_accuracy": 0.7819343030452728,
|
| 283 |
+
"num_tokens": 2524623.0,
|
| 284 |
+
"step": 230
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"entropy": 0.8994888842105866,
|
| 288 |
+
"epoch": 0.47244094488188976,
|
| 289 |
+
"grad_norm": 0.59765625,
|
| 290 |
+
"learning_rate": 0.00019170271102311238,
|
| 291 |
+
"loss": 0.9019557952880859,
|
| 292 |
+
"mean_token_accuracy": 0.7712395042181015,
|
| 293 |
+
"num_tokens": 2631031.0,
|
| 294 |
+
"step": 240
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"entropy": 0.7910601049661636,
|
| 298 |
+
"epoch": 0.4921259842519685,
|
| 299 |
+
"grad_norm": 0.494140625,
|
| 300 |
+
"learning_rate": 0.00019083432953518418,
|
| 301 |
+
"loss": 0.8107678413391113,
|
| 302 |
+
"mean_token_accuracy": 0.7996705889701843,
|
| 303 |
+
"num_tokens": 2741031.0,
|
| 304 |
+
"step": 250
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4921259842519685,
|
| 308 |
+
"eval_entropy": 0.9037868281205496,
|
| 309 |
+
"eval_loss": 0.8843846917152405,
|
| 310 |
+
"eval_mean_token_accuracy": 0.7717091352851303,
|
| 311 |
+
"eval_num_tokens": 2741031.0,
|
| 312 |
+
"eval_runtime": 15.93,
|
| 313 |
+
"eval_samples_per_second": 26.805,
|
| 314 |
+
"eval_steps_per_second": 3.39,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"entropy": 0.7740790158510208,
|
| 319 |
+
"epoch": 0.5118110236220472,
|
| 320 |
+
"grad_norm": 0.57421875,
|
| 321 |
+
"learning_rate": 0.00018992491020282618,
|
| 322 |
+
"loss": 0.7579652309417725,
|
| 323 |
+
"mean_token_accuracy": 0.7955388814210892,
|
| 324 |
+
"num_tokens": 2853547.0,
|
| 325 |
+
"step": 260
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"entropy": 0.8572690159082412,
|
| 329 |
+
"epoch": 0.531496062992126,
|
| 330 |
+
"grad_norm": 1.171875,
|
| 331 |
+
"learning_rate": 0.0001889748638906231,
|
| 332 |
+
"loss": 0.8072081565856933,
|
| 333 |
+
"mean_token_accuracy": 0.7910655379295349,
|
| 334 |
+
"num_tokens": 2968367.0,
|
| 335 |
+
"step": 270
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"entropy": 0.8885004252195359,
|
| 339 |
+
"epoch": 0.5511811023622047,
|
| 340 |
+
"grad_norm": 0.451171875,
|
| 341 |
+
"learning_rate": 0.00018798461981793462,
|
| 342 |
+
"loss": 0.8460770606994629,
|
| 343 |
+
"mean_token_accuracy": 0.7776093751192092,
|
| 344 |
+
"num_tokens": 3075963.0,
|
| 345 |
+
"step": 280
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"entropy": 0.829613895714283,
|
| 349 |
+
"epoch": 0.5708661417322834,
|
| 350 |
+
"grad_norm": 0.4453125,
|
| 351 |
+
"learning_rate": 0.00018695462536497934,
|
| 352 |
+
"loss": 0.823792839050293,
|
| 353 |
+
"mean_token_accuracy": 0.7848509013652801,
|
| 354 |
+
"num_tokens": 3185899.0,
|
| 355 |
+
"step": 290
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"entropy": 0.8341330245137215,
|
| 359 |
+
"epoch": 0.5905511811023622,
|
| 360 |
+
"grad_norm": 0.490234375,
|
| 361 |
+
"learning_rate": 0.00018588534587071385,
|
| 362 |
+
"loss": 0.810818099975586,
|
| 363 |
+
"mean_token_accuracy": 0.7906568497419357,
|
| 364 |
+
"num_tokens": 3297319.0,
|
| 365 |
+
"step": 300
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.5905511811023622,
|
| 369 |
+
"eval_entropy": 0.8445847459413387,
|
| 370 |
+
"eval_loss": 0.8718247413635254,
|
| 371 |
+
"eval_mean_token_accuracy": 0.774838043583764,
|
| 372 |
+
"eval_num_tokens": 3297319.0,
|
| 373 |
+
"eval_runtime": 15.9561,
|
| 374 |
+
"eval_samples_per_second": 26.761,
|
| 375 |
+
"eval_steps_per_second": 3.384,
|
| 376 |
+
"step": 300
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"entropy": 0.8317201763391495,
|
| 380 |
+
"epoch": 0.610236220472441,
|
| 381 |
+
"grad_norm": 0.396484375,
|
| 382 |
+
"learning_rate": 0.00018477726442259806,
|
| 383 |
+
"loss": 0.80075101852417,
|
| 384 |
+
"mean_token_accuracy": 0.7886052161455155,
|
| 385 |
+
"num_tokens": 3415477.0,
|
| 386 |
+
"step": 310
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"entropy": 0.8597566410899162,
|
| 390 |
+
"epoch": 0.6299212598425197,
|
| 391 |
+
"grad_norm": 0.404296875,
|
| 392 |
+
"learning_rate": 0.00018363088163834252,
|
| 393 |
+
"loss": 0.8123328208923339,
|
| 394 |
+
"mean_token_accuracy": 0.7854531407356262,
|
| 395 |
+
"num_tokens": 3524759.0,
|
| 396 |
+
"step": 320
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"entropy": 0.8519140958786011,
|
| 400 |
+
"epoch": 0.6496062992125984,
|
| 401 |
+
"grad_norm": 0.458984375,
|
| 402 |
+
"learning_rate": 0.00018244671543973513,
|
| 403 |
+
"loss": 0.8214571952819825,
|
| 404 |
+
"mean_token_accuracy": 0.7828344345092774,
|
| 405 |
+
"num_tokens": 3640838.0,
|
| 406 |
+
"step": 330
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"entropy": 0.7781533747911453,
|
| 410 |
+
"epoch": 0.6692913385826772,
|
| 411 |
+
"grad_norm": 0.51953125,
|
| 412 |
+
"learning_rate": 0.0001812253008186505,
|
| 413 |
+
"loss": 0.753899097442627,
|
| 414 |
+
"mean_token_accuracy": 0.8011120349168778,
|
| 415 |
+
"num_tokens": 3756735.0,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"entropy": 0.8384901583194733,
|
| 420 |
+
"epoch": 0.6889763779527559,
|
| 421 |
+
"grad_norm": 0.51171875,
|
| 422 |
+
"learning_rate": 0.0001799671895953471,
|
| 423 |
+
"loss": 0.8112489700317382,
|
| 424 |
+
"mean_token_accuracy": 0.7898134678602219,
|
| 425 |
+
"num_tokens": 3870377.0,
|
| 426 |
+
"step": 350
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6889763779527559,
|
| 430 |
+
"eval_entropy": 0.8795759567507991,
|
| 431 |
+
"eval_loss": 0.8568941354751587,
|
| 432 |
+
"eval_mean_token_accuracy": 0.7754804182935644,
|
| 433 |
+
"eval_num_tokens": 3870377.0,
|
| 434 |
+
"eval_runtime": 15.9337,
|
| 435 |
+
"eval_samples_per_second": 26.798,
|
| 436 |
+
"eval_steps_per_second": 3.389,
|
| 437 |
+
"step": 350
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"entropy": 0.8008699864149094,
|
| 441 |
+
"epoch": 0.7086614173228346,
|
| 442 |
+
"grad_norm": 0.498046875,
|
| 443 |
+
"learning_rate": 0.00017867295016916167,
|
| 444 |
+
"loss": 0.7585730075836181,
|
| 445 |
+
"mean_token_accuracy": 0.7942175149917603,
|
| 446 |
+
"num_tokens": 3975692.0,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"entropy": 0.9035080641508102,
|
| 451 |
+
"epoch": 0.7283464566929134,
|
| 452 |
+
"grad_norm": 0.48046875,
|
| 453 |
+
"learning_rate": 0.0001773431672617132,
|
| 454 |
+
"loss": 0.8653995513916015,
|
| 455 |
+
"mean_token_accuracy": 0.7730168104171753,
|
| 456 |
+
"num_tokens": 4087256.0,
|
| 457 |
+
"step": 370
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"entropy": 0.760843014717102,
|
| 461 |
+
"epoch": 0.7480314960629921,
|
| 462 |
+
"grad_norm": 0.49609375,
|
| 463 |
+
"learning_rate": 0.00017597844165273286,
|
| 464 |
+
"loss": 0.7377382278442383,
|
| 465 |
+
"mean_token_accuracy": 0.7972156703472137,
|
| 466 |
+
"num_tokens": 4192629.0,
|
| 467 |
+
"step": 380
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"entropy": 0.8075762838125229,
|
| 471 |
+
"epoch": 0.7677165354330708,
|
| 472 |
+
"grad_norm": 0.447265625,
|
| 473 |
+
"learning_rate": 0.00017457938990863908,
|
| 474 |
+
"loss": 0.7615089893341065,
|
| 475 |
+
"mean_token_accuracy": 0.8005614727735519,
|
| 476 |
+
"num_tokens": 4303838.0,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"entropy": 0.8942124575376511,
|
| 481 |
+
"epoch": 0.7874015748031497,
|
| 482 |
+
"grad_norm": 0.48828125,
|
| 483 |
+
"learning_rate": 0.00017314664410398033,
|
| 484 |
+
"loss": 0.8365015983581543,
|
| 485 |
+
"mean_token_accuracy": 0.7790710270404816,
|
| 486 |
+
"num_tokens": 4414002.0,
|
| 487 |
+
"step": 400
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.7874015748031497,
|
| 491 |
+
"eval_entropy": 0.8613758815659417,
|
| 492 |
+
"eval_loss": 0.8455358743667603,
|
| 493 |
+
"eval_mean_token_accuracy": 0.7789811304321995,
|
| 494 |
+
"eval_num_tokens": 4414002.0,
|
| 495 |
+
"eval_runtime": 16.2401,
|
| 496 |
+
"eval_samples_per_second": 26.293,
|
| 497 |
+
"eval_steps_per_second": 3.325,
|
| 498 |
+
"step": 400
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"entropy": 0.7841676041483879,
|
| 502 |
+
"epoch": 0.8070866141732284,
|
| 503 |
+
"grad_norm": 0.57421875,
|
| 504 |
+
"learning_rate": 0.0001716808515358714,
|
| 505 |
+
"loss": 0.8027224540710449,
|
| 506 |
+
"mean_token_accuracy": 0.79732064306736,
|
| 507 |
+
"num_tokens": 4525758.0,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"entropy": 0.7710117936134339,
|
| 512 |
+
"epoch": 0.8267716535433071,
|
| 513 |
+
"grad_norm": 0.4453125,
|
| 514 |
+
"learning_rate": 0.00017018267443155268,
|
| 515 |
+
"loss": 0.7185665130615234,
|
| 516 |
+
"mean_token_accuracy": 0.807221668958664,
|
| 517 |
+
"num_tokens": 4640742.0,
|
| 518 |
+
"step": 420
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"entropy": 0.8494665056467057,
|
| 522 |
+
"epoch": 0.8464566929133859,
|
| 523 |
+
"grad_norm": 0.453125,
|
| 524 |
+
"learning_rate": 0.00016865278964920378,
|
| 525 |
+
"loss": 0.8273701667785645,
|
| 526 |
+
"mean_token_accuracy": 0.7870708376169204,
|
| 527 |
+
"num_tokens": 4754244.0,
|
| 528 |
+
"step": 430
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"entropy": 0.7938957527279854,
|
| 532 |
+
"epoch": 0.8661417322834646,
|
| 533 |
+
"grad_norm": 0.345703125,
|
| 534 |
+
"learning_rate": 0.00016709188837214732,
|
| 535 |
+
"loss": 0.7776453971862793,
|
| 536 |
+
"mean_token_accuracy": 0.7911081612110138,
|
| 537 |
+
"num_tokens": 4862576.0,
|
| 538 |
+
"step": 440
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"entropy": 0.7948901996016502,
|
| 542 |
+
"epoch": 0.8858267716535433,
|
| 543 |
+
"grad_norm": 0.376953125,
|
| 544 |
+
"learning_rate": 0.0001655006757965806,
|
| 545 |
+
"loss": 0.7554664611816406,
|
| 546 |
+
"mean_token_accuracy": 0.7939331024885178,
|
| 547 |
+
"num_tokens": 4984410.0,
|
| 548 |
+
"step": 450
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8858267716535433,
|
| 552 |
+
"eval_entropy": 0.8405309479545664,
|
| 553 |
+
"eval_loss": 0.8371886610984802,
|
| 554 |
+
"eval_mean_token_accuracy": 0.7799682672376986,
|
| 555 |
+
"eval_num_tokens": 4984410.0,
|
| 556 |
+
"eval_runtime": 15.9419,
|
| 557 |
+
"eval_samples_per_second": 26.785,
|
| 558 |
+
"eval_steps_per_second": 3.387,
|
| 559 |
+
"step": 450
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"entropy": 0.8764406844973565,
|
| 563 |
+
"epoch": 0.905511811023622,
|
| 564 |
+
"grad_norm": 0.5625,
|
| 565 |
+
"learning_rate": 0.0001638798708129768,
|
| 566 |
+
"loss": 0.8325652122497559,
|
| 567 |
+
"mean_token_accuracy": 0.7821455717086792,
|
| 568 |
+
"num_tokens": 5094029.0,
|
| 569 |
+
"step": 460
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"entropy": 0.8582975655794144,
|
| 573 |
+
"epoch": 0.9251968503937008,
|
| 574 |
+
"grad_norm": 0.3828125,
|
| 575 |
+
"learning_rate": 0.00016223020568129854,
|
| 576 |
+
"loss": 0.8309861183166504,
|
| 577 |
+
"mean_token_accuracy": 0.7791573971509933,
|
| 578 |
+
"num_tokens": 5210613.0,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"entropy": 0.8273941457271576,
|
| 583 |
+
"epoch": 0.9448818897637795,
|
| 584 |
+
"grad_norm": 0.59375,
|
| 585 |
+
"learning_rate": 0.00016055242570017244,
|
| 586 |
+
"loss": 0.7878972053527832,
|
| 587 |
+
"mean_token_accuracy": 0.7900911033153534,
|
| 588 |
+
"num_tokens": 5322546.0,
|
| 589 |
+
"step": 480
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"entropy": 0.8146103203296662,
|
| 593 |
+
"epoch": 0.9645669291338582,
|
| 594 |
+
"grad_norm": 0.42578125,
|
| 595 |
+
"learning_rate": 0.00015884728887017162,
|
| 596 |
+
"loss": 0.7865399837493896,
|
| 597 |
+
"mean_token_accuracy": 0.7947310745716095,
|
| 598 |
+
"num_tokens": 5434008.0,
|
| 599 |
+
"step": 490
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"entropy": 0.6613125756382943,
|
| 603 |
+
"epoch": 0.984251968503937,
|
| 604 |
+
"grad_norm": 0.41796875,
|
| 605 |
+
"learning_rate": 0.0001571155655513606,
|
| 606 |
+
"loss": 0.6725417137145996,
|
| 607 |
+
"mean_token_accuracy": 0.816859421133995,
|
| 608 |
+
"num_tokens": 5544086.0,
|
| 609 |
+
"step": 500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.984251968503937,
|
| 613 |
+
"eval_entropy": 0.8118620448642306,
|
| 614 |
+
"eval_loss": 0.8308539986610413,
|
| 615 |
+
"eval_mean_token_accuracy": 0.781522473803273,
|
| 616 |
+
"eval_num_tokens": 5544086.0,
|
| 617 |
+
"eval_runtime": 15.9383,
|
| 618 |
+
"eval_samples_per_second": 26.791,
|
| 619 |
+
"eval_steps_per_second": 3.388,
|
| 620 |
+
"step": 500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.7347942754626274,
|
| 624 |
+
"epoch": 1.0039370078740157,
|
| 625 |
+
"grad_norm": 0.39453125,
|
| 626 |
+
"learning_rate": 0.0001553580381152559,
|
| 627 |
+
"loss": 0.6915054798126221,
|
| 628 |
+
"mean_token_accuracy": 0.8176700383424759,
|
| 629 |
+
"num_tokens": 5657246.0,
|
| 630 |
+
"step": 510
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.7550317242741584,
|
| 634 |
+
"epoch": 1.0236220472440944,
|
| 635 |
+
"grad_norm": 0.4921875,
|
| 636 |
+
"learning_rate": 0.0001535755005913602,
|
| 637 |
+
"loss": 0.6865068912506104,
|
| 638 |
+
"mean_token_accuracy": 0.8140248268842697,
|
| 639 |
+
"num_tokens": 5768184.0,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.7479684263467788,
|
| 644 |
+
"epoch": 1.0433070866141732,
|
| 645 |
+
"grad_norm": 0.60546875,
|
| 646 |
+
"learning_rate": 0.00015176875830842938,
|
| 647 |
+
"loss": 0.7037695407867431,
|
| 648 |
+
"mean_token_accuracy": 0.8133333414793015,
|
| 649 |
+
"num_tokens": 5885598.0,
|
| 650 |
+
"step": 530
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.6792907789349556,
|
| 654 |
+
"epoch": 1.0629921259842519,
|
| 655 |
+
"grad_norm": 0.439453125,
|
| 656 |
+
"learning_rate": 0.0001499386275306348,
|
| 657 |
+
"loss": 0.640275239944458,
|
| 658 |
+
"mean_token_accuracy": 0.8249545454978943,
|
| 659 |
+
"num_tokens": 6002120.0,
|
| 660 |
+
"step": 540
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.6819084867835045,
|
| 664 |
+
"epoch": 1.0826771653543308,
|
| 665 |
+
"grad_norm": 0.41015625,
|
| 666 |
+
"learning_rate": 0.0001480859350887852,
|
| 667 |
+
"loss": 0.6469451904296875,
|
| 668 |
+
"mean_token_accuracy": 0.8235166579484939,
|
| 669 |
+
"num_tokens": 6112085.0,
|
| 670 |
+
"step": 550
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.0826771653543308,
|
| 674 |
+
"eval_entropy": 0.8042021377219094,
|
| 675 |
+
"eval_loss": 0.8352769017219543,
|
| 676 |
+
"eval_mean_token_accuracy": 0.7806271998970596,
|
| 677 |
+
"eval_num_tokens": 6112085.0,
|
| 678 |
+
"eval_runtime": 15.9298,
|
| 679 |
+
"eval_samples_per_second": 26.805,
|
| 680 |
+
"eval_steps_per_second": 3.39,
|
| 681 |
+
"step": 550
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"entropy": 0.7026952266693115,
|
| 685 |
+
"epoch": 1.1023622047244095,
|
| 686 |
+
"grad_norm": 0.47265625,
|
| 687 |
+
"learning_rate": 0.00014621151800677434,
|
| 688 |
+
"loss": 0.667764139175415,
|
| 689 |
+
"mean_token_accuracy": 0.8164290696382522,
|
| 690 |
+
"num_tokens": 6224645.0,
|
| 691 |
+
"step": 560
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"entropy": 0.6083555489778518,
|
| 695 |
+
"epoch": 1.1220472440944882,
|
| 696 |
+
"grad_norm": 0.37890625,
|
| 697 |
+
"learning_rate": 0.0001443162231234242,
|
| 698 |
+
"loss": 0.5703843116760254,
|
| 699 |
+
"mean_token_accuracy": 0.8396952480077744,
|
| 700 |
+
"num_tokens": 6336790.0,
|
| 701 |
+
"step": 570
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"entropy": 0.6823922500014306,
|
| 705 |
+
"epoch": 1.141732283464567,
|
| 706 |
+
"grad_norm": 0.55078125,
|
| 707 |
+
"learning_rate": 0.0001424009067098931,
|
| 708 |
+
"loss": 0.6488718032836914,
|
| 709 |
+
"mean_token_accuracy": 0.8208951652050018,
|
| 710 |
+
"num_tokens": 6450761.0,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"entropy": 0.6331134095788002,
|
| 715 |
+
"epoch": 1.1614173228346456,
|
| 716 |
+
"grad_norm": 0.482421875,
|
| 717 |
+
"learning_rate": 0.00014046643408282305,
|
| 718 |
+
"loss": 0.5916334629058838,
|
| 719 |
+
"mean_token_accuracy": 0.8340157747268677,
|
| 720 |
+
"num_tokens": 6562060.0,
|
| 721 |
+
"step": 590
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"entropy": 0.6203767985105515,
|
| 725 |
+
"epoch": 1.1811023622047245,
|
| 726 |
+
"grad_norm": 0.45703125,
|
| 727 |
+
"learning_rate": 0.00013851367921340017,
|
| 728 |
+
"loss": 0.5833216667175293,
|
| 729 |
+
"mean_token_accuracy": 0.8345949351787567,
|
| 730 |
+
"num_tokens": 6676922.0,
|
| 731 |
+
"step": 600
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1811023622047245,
|
| 735 |
+
"eval_entropy": 0.7756788493306549,
|
| 736 |
+
"eval_loss": 0.8351659178733826,
|
| 737 |
+
"eval_mean_token_accuracy": 0.7810865651678156,
|
| 738 |
+
"eval_num_tokens": 6676922.0,
|
| 739 |
+
"eval_runtime": 15.9481,
|
| 740 |
+
"eval_samples_per_second": 26.774,
|
| 741 |
+
"eval_steps_per_second": 3.386,
|
| 742 |
+
"step": 600
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"entropy": 0.645186324417591,
|
| 746 |
+
"epoch": 1.2007874015748032,
|
| 747 |
+
"grad_norm": 0.498046875,
|
| 748 |
+
"learning_rate": 0.0001365435243325051,
|
| 749 |
+
"loss": 0.6237170219421386,
|
| 750 |
+
"mean_token_accuracy": 0.8277532249689102,
|
| 751 |
+
"num_tokens": 6783497.0,
|
| 752 |
+
"step": 610
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"entropy": 0.6759833052754403,
|
| 756 |
+
"epoch": 1.220472440944882,
|
| 757 |
+
"grad_norm": 0.546875,
|
| 758 |
+
"learning_rate": 0.00013455685953213194,
|
| 759 |
+
"loss": 0.6462036609649658,
|
| 760 |
+
"mean_token_accuracy": 0.8247299671173096,
|
| 761 |
+
"num_tokens": 6894014.0,
|
| 762 |
+
"step": 620
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"entropy": 0.6737162366509437,
|
| 766 |
+
"epoch": 1.2401574803149606,
|
| 767 |
+
"grad_norm": 0.48828125,
|
| 768 |
+
"learning_rate": 0.0001325545823632554,
|
| 769 |
+
"loss": 0.6107028484344482,
|
| 770 |
+
"mean_token_accuracy": 0.8260864973068237,
|
| 771 |
+
"num_tokens": 6997350.0,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"entropy": 0.6702337503433228,
|
| 776 |
+
"epoch": 1.2598425196850394,
|
| 777 |
+
"grad_norm": 0.451171875,
|
| 778 |
+
"learning_rate": 0.00013053759743032823,
|
| 779 |
+
"loss": 0.6504123210906982,
|
| 780 |
+
"mean_token_accuracy": 0.818900191783905,
|
| 781 |
+
"num_tokens": 7109067.0,
|
| 782 |
+
"step": 640
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"entropy": 0.7739008516073227,
|
| 786 |
+
"epoch": 1.279527559055118,
|
| 787 |
+
"grad_norm": 0.56640625,
|
| 788 |
+
"learning_rate": 0.00012850681598259195,
|
| 789 |
+
"loss": 0.7173595905303956,
|
| 790 |
+
"mean_token_accuracy": 0.7997365325689316,
|
| 791 |
+
"num_tokens": 7218739.0,
|
| 792 |
+
"step": 650
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.279527559055118,
|
| 796 |
+
"eval_entropy": 0.7500080190323017,
|
| 797 |
+
"eval_loss": 0.8297256231307983,
|
| 798 |
+
"eval_mean_token_accuracy": 0.7822851461392862,
|
| 799 |
+
"eval_num_tokens": 7218739.0,
|
| 800 |
+
"eval_runtime": 15.9417,
|
| 801 |
+
"eval_samples_per_second": 26.785,
|
| 802 |
+
"eval_steps_per_second": 3.387,
|
| 803 |
+
"step": 650
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"entropy": 0.7080179423093795,
|
| 807 |
+
"epoch": 1.2992125984251968,
|
| 808 |
+
"grad_norm": 0.53125,
|
| 809 |
+
"learning_rate": 0.0001264631555023856,
|
| 810 |
+
"loss": 0.661363172531128,
|
| 811 |
+
"mean_token_accuracy": 0.8172380715608597,
|
| 812 |
+
"num_tokens": 7334561.0,
|
| 813 |
+
"step": 660
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"entropy": 0.6184108316898346,
|
| 817 |
+
"epoch": 1.3188976377952755,
|
| 818 |
+
"grad_norm": 0.78515625,
|
| 819 |
+
"learning_rate": 0.00012440753929063826,
|
| 820 |
+
"loss": 0.6013145923614502,
|
| 821 |
+
"mean_token_accuracy": 0.8273262619972229,
|
| 822 |
+
"num_tokens": 7443871.0,
|
| 823 |
+
"step": 670
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"entropy": 0.71297377794981,
|
| 827 |
+
"epoch": 1.3385826771653544,
|
| 828 |
+
"grad_norm": 0.5078125,
|
| 829 |
+
"learning_rate": 0.00012234089604973303,
|
| 830 |
+
"loss": 0.6702734470367432,
|
| 831 |
+
"mean_token_accuracy": 0.8151450455188751,
|
| 832 |
+
"num_tokens": 7555559.0,
|
| 833 |
+
"step": 680
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"entropy": 0.6389088705182076,
|
| 837 |
+
"epoch": 1.358267716535433,
|
| 838 |
+
"grad_norm": 0.50390625,
|
| 839 |
+
"learning_rate": 0.0001202641594639305,
|
| 840 |
+
"loss": 0.6133567810058593,
|
| 841 |
+
"mean_token_accuracy": 0.8298202604055405,
|
| 842 |
+
"num_tokens": 7669861.0,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"entropy": 0.7520714432001114,
|
| 847 |
+
"epoch": 1.3779527559055118,
|
| 848 |
+
"grad_norm": 0.5390625,
|
| 849 |
+
"learning_rate": 0.00011817826777754171,
|
| 850 |
+
"loss": 0.6847642421722412,
|
| 851 |
+
"mean_token_accuracy": 0.8055585384368896,
|
| 852 |
+
"num_tokens": 7782831.0,
|
| 853 |
+
"step": 700
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.3779527559055118,
|
| 857 |
+
"eval_entropy": 0.7791200037355777,
|
| 858 |
+
"eval_loss": 0.8222253322601318,
|
| 859 |
+
"eval_mean_token_accuracy": 0.7843283326537521,
|
| 860 |
+
"eval_num_tokens": 7782831.0,
|
| 861 |
+
"eval_runtime": 15.9494,
|
| 862 |
+
"eval_samples_per_second": 26.772,
|
| 863 |
+
"eval_steps_per_second": 3.386,
|
| 864 |
+
"step": 700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"entropy": 0.7161616936326027,
|
| 868 |
+
"epoch": 1.3976377952755905,
|
| 869 |
+
"grad_norm": 0.421875,
|
| 870 |
+
"learning_rate": 0.00011608416337104065,
|
| 871 |
+
"loss": 0.6723262786865234,
|
| 872 |
+
"mean_token_accuracy": 0.8196182817220687,
|
| 873 |
+
"num_tokens": 7895511.0,
|
| 874 |
+
"step": 710
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"entropy": 0.6407245740294456,
|
| 878 |
+
"epoch": 1.4173228346456692,
|
| 879 |
+
"grad_norm": 0.443359375,
|
| 880 |
+
"learning_rate": 0.00011398279233530829,
|
| 881 |
+
"loss": 0.6370048522949219,
|
| 882 |
+
"mean_token_accuracy": 0.8265632688999176,
|
| 883 |
+
"num_tokens": 8006186.0,
|
| 884 |
+
"step": 720
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"entropy": 0.704089181125164,
|
| 888 |
+
"epoch": 1.4370078740157481,
|
| 889 |
+
"grad_norm": 0.51953125,
|
| 890 |
+
"learning_rate": 0.00011187510404420028,
|
| 891 |
+
"loss": 0.645330286026001,
|
| 892 |
+
"mean_token_accuracy": 0.8142861813306809,
|
| 893 |
+
"num_tokens": 8110444.0,
|
| 894 |
+
"step": 730
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"entropy": 0.7673430755734444,
|
| 898 |
+
"epoch": 1.4566929133858268,
|
| 899 |
+
"grad_norm": 0.7109375,
|
| 900 |
+
"learning_rate": 0.00010976205072563132,
|
| 901 |
+
"loss": 0.7298968315124512,
|
| 902 |
+
"mean_token_accuracy": 0.8080587953329086,
|
| 903 |
+
"num_tokens": 8220128.0,
|
| 904 |
+
"step": 740
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"entropy": 0.6395664170384407,
|
| 908 |
+
"epoch": 1.4763779527559056,
|
| 909 |
+
"grad_norm": 0.5078125,
|
| 910 |
+
"learning_rate": 0.00010764458703137024,
|
| 911 |
+
"loss": 0.6174263477325439,
|
| 912 |
+
"mean_token_accuracy": 0.8285290688276291,
|
| 913 |
+
"num_tokens": 8327961.0,
|
| 914 |
+
"step": 750
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.4763779527559056,
|
| 918 |
+
"eval_entropy": 0.7358508281133793,
|
| 919 |
+
"eval_loss": 0.8263605833053589,
|
| 920 |
+
"eval_mean_token_accuracy": 0.7838875507866895,
|
| 921 |
+
"eval_num_tokens": 8327961.0,
|
| 922 |
+
"eval_runtime": 15.9403,
|
| 923 |
+
"eval_samples_per_second": 26.787,
|
| 924 |
+
"eval_steps_per_second": 3.388,
|
| 925 |
+
"step": 750
|
| 926 |
+
}
|
| 927 |
+
],
|
| 928 |
+
"logging_steps": 10,
|
| 929 |
+
"max_steps": 1524,
|
| 930 |
+
"num_input_tokens_seen": 0,
|
| 931 |
+
"num_train_epochs": 3,
|
| 932 |
+
"save_steps": 50,
|
| 933 |
+
"stateful_callbacks": {
|
| 934 |
+
"TrainerControl": {
|
| 935 |
+
"args": {
|
| 936 |
+
"should_epoch_stop": false,
|
| 937 |
+
"should_evaluate": false,
|
| 938 |
+
"should_log": false,
|
| 939 |
+
"should_save": true,
|
| 940 |
+
"should_training_stop": false
|
| 941 |
+
},
|
| 942 |
+
"attributes": {}
|
| 943 |
+
}
|
| 944 |
+
},
|
| 945 |
+
"total_flos": 1.1723056133701018e+17,
|
| 946 |
+
"train_batch_size": 8,
|
| 947 |
+
"trial_name": null,
|
| 948 |
+
"trial_params": null
|
| 949 |
+
}
|