Cisco1963/llmplasticity-en_zh_linear_0.125_1-seed42
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Cisco1963/llmplasticity-en_zh_linear_0.125_1-seed42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 06:20:27 +08:00
commit ee5e46d8ff
158 changed files with 4508267 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

18
all_results.json Normal file
View File

@@ -0,0 +1,18 @@
{
"epoch": 1.0,
"eval_accuracy": 0.3301316985740435,
"eval_en_loss": 5.919877803414801,
"eval_loss": 3.4310219287872314,
"eval_runtime": 139.0203,
"eval_samples": 7894,
"eval_samples_per_second": 56.783,
"eval_steps_per_second": 7.1,
"eval_zh_loss": 2.5322090978390035,
"perplexity": 30.908212608082085,
"total_flos": 3.56955225587712e+17,
"train_loss": 57.429637563704375,
"train_runtime": 52919.1561,
"train_samples": 683058,
"train_samples_per_second": 12.908,
"train_steps_per_second": 0.101
}

39
checkpoint-1/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-1/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-1/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1a1b47498e07ededbf11fbf7b8d9092733a3d1e65f546d80f2cba033a7e86ce
size 497774208

6
checkpoint-1/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-1/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-1/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

50
checkpoint-1/trainer_state.json Normal file
View File

@@ -0,0 +1,50 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0001873909326212478,
"eval_steps": 99999999,
"global_step": 1,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 66890760192000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-1/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-1/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-1024/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-1024/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-1024/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-1024/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca7a2217721d4237ccef0edeae1babf7077ed188970c50fd0d1068fb98f55af6
size 497774208

6
checkpoint-1024/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-1024/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-1024/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

210
checkpoint-1024/trainer_state.json Normal file
View File

@@ -0,0 +1,210 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.19188831500415773,
"eval_steps": 99999999,
"global_step": 1024,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
},
{
"epoch": 0.005996509843879929,
"grad_norm": 33.14303207397461,
"learning_rate": 4.970957466741615e-05,
"loss": 141.2197,
"step": 32
},
{
"epoch": 0.005996509843879929,
"eval_accuracy": 0.02386372614066984,
"eval_loss": 10.312174797058105,
"eval_runtime": 201.4605,
"eval_samples_per_second": 39.184,
"eval_steps_per_second": 4.899,
"step": 32
},
{
"epoch": 0.011993019687759858,
"grad_norm": 17.63327407836914,
"learning_rate": 4.94097807757167e-05,
"loss": 128.0666,
"step": 64
},
{
"epoch": 0.011993019687759858,
"eval_accuracy": 0.0342046782626398,
"eval_loss": 9.543290138244629,
"eval_runtime": 210.7504,
"eval_samples_per_second": 37.457,
"eval_steps_per_second": 4.683,
"step": 64
},
{
"epoch": 0.023986039375519717,
"grad_norm": 22.085046768188477,
"learning_rate": 4.881019299231778e-05,
"loss": 118.9934,
"step": 128
},
{
"epoch": 0.023986039375519717,
"eval_accuracy": 0.03304265387350131,
"eval_loss": 7.98660945892334,
"eval_runtime": 227.9954,
"eval_samples_per_second": 34.624,
"eval_steps_per_second": 4.329,
"step": 128
},
{
"epoch": 0.04797207875103943,
"grad_norm": 17.06017303466797,
"learning_rate": 4.761101742551995e-05,
"loss": 102.9587,
"step": 256
},
{
"epoch": 0.04797207875103943,
"eval_accuracy": 0.055030721081703045,
"eval_loss": 5.9021315574646,
"eval_runtime": 240.335,
"eval_samples_per_second": 32.846,
"eval_steps_per_second": 4.107,
"step": 256
},
{
"epoch": 0.09594415750207887,
"grad_norm": 68.73705291748047,
"learning_rate": 4.52126662919243e-05,
"loss": 93.4498,
"step": 512
},
{
"epoch": 0.09594415750207887,
"eval_accuracy": 0.18273613650666046,
"eval_loss": 4.6600799560546875,
"eval_runtime": 236.8236,
"eval_samples_per_second": 33.333,
"eval_steps_per_second": 4.168,
"step": 512
},
{
"epoch": 0.19188831500415773,
"grad_norm": 16.876415252685547,
"learning_rate": 4.0415964024733e-05,
"loss": 74.4021,
"step": 1024
},
{
"epoch": 0.19188831500415773,
"eval_accuracy": 0.1382732248232383,
"eval_loss": 4.865310192108154,
"eval_runtime": 268.5345,
"eval_samples_per_second": 29.397,
"eval_steps_per_second": 3.676,
"step": 1024
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.8496138436608e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-1024/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-1024/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-128/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-128/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-128/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-128/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de36eb5e1bc167b001f55c586b043fdf7ffd589ec5aae8ff628ec2849c137baf
size 497774208

6
checkpoint-128/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-128/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-128/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

162
checkpoint-128/trainer_state.json Normal file
View File

@@ -0,0 +1,162 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.023986039375519717,
"eval_steps": 99999999,
"global_step": 128,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
},
{
"epoch": 0.005996509843879929,
"grad_norm": 33.14303207397461,
"learning_rate": 4.970957466741615e-05,
"loss": 141.2197,
"step": 32
},
{
"epoch": 0.005996509843879929,
"eval_accuracy": 0.02386372614066984,
"eval_loss": 10.312174797058105,
"eval_runtime": 201.4605,
"eval_samples_per_second": 39.184,
"eval_steps_per_second": 4.899,
"step": 32
},
{
"epoch": 0.011993019687759858,
"grad_norm": 17.63327407836914,
"learning_rate": 4.94097807757167e-05,
"loss": 128.0666,
"step": 64
},
{
"epoch": 0.011993019687759858,
"eval_accuracy": 0.0342046782626398,
"eval_loss": 9.543290138244629,
"eval_runtime": 210.7504,
"eval_samples_per_second": 37.457,
"eval_steps_per_second": 4.683,
"step": 64
},
{
"epoch": 0.023986039375519717,
"grad_norm": 22.085046768188477,
"learning_rate": 4.881019299231778e-05,
"loss": 118.9934,
"step": 128
},
{
"epoch": 0.023986039375519717,
"eval_accuracy": 0.03304265387350131,
"eval_loss": 7.98660945892334,
"eval_runtime": 227.9954,
"eval_samples_per_second": 34.624,
"eval_steps_per_second": 4.329,
"step": 128
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8562017304576000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-128/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-128/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-16/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-16/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-16/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-16/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10a2d213c58a8b14c9e1d0d9988576914845167d9e797bf48c9d1606d577c3fa
size 497774208

6
checkpoint-16/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-16/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-16/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

114
checkpoint-16/trainer_state.json Normal file
View File

@@ -0,0 +1,114 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0029982549219399646,
"eval_steps": 99999999,
"global_step": 16,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1070252163072000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-16/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-16/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-2/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-2/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-2/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-2/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:890dc4b52db7c5132de7c35a48094dc352d57d07df1ef24b34cef70506fa5ec9
size 497774208

6
checkpoint-2/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-2/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-2/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

66
checkpoint-2/trainer_state.json Normal file
View File

@@ -0,0 +1,66 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0003747818652424956,
"eval_steps": 99999999,
"global_step": 2,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 133781520384000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-2/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-2/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-2048/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-2048/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-2048/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-2048/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfd886f43fff62b82bead5be3b3391b8f63b4f6a8fc63984f19668f7bc729049
size 497774208

6
checkpoint-2048/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-2048/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-2048/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

226
checkpoint-2048/trainer_state.json Normal file
View File

@@ -0,0 +1,226 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.38377663000831547,
"eval_steps": 99999999,
"global_step": 2048,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
},
{
"epoch": 0.005996509843879929,
"grad_norm": 33.14303207397461,
"learning_rate": 4.970957466741615e-05,
"loss": 141.2197,
"step": 32
},
{
"epoch": 0.005996509843879929,
"eval_accuracy": 0.02386372614066984,
"eval_loss": 10.312174797058105,
"eval_runtime": 201.4605,
"eval_samples_per_second": 39.184,
"eval_steps_per_second": 4.899,
"step": 32
},
{
"epoch": 0.011993019687759858,
"grad_norm": 17.63327407836914,
"learning_rate": 4.94097807757167e-05,
"loss": 128.0666,
"step": 64
},
{
"epoch": 0.011993019687759858,
"eval_accuracy": 0.0342046782626398,
"eval_loss": 9.543290138244629,
"eval_runtime": 210.7504,
"eval_samples_per_second": 37.457,
"eval_steps_per_second": 4.683,
"step": 64
},
{
"epoch": 0.023986039375519717,
"grad_norm": 22.085046768188477,
"learning_rate": 4.881019299231778e-05,
"loss": 118.9934,
"step": 128
},
{
"epoch": 0.023986039375519717,
"eval_accuracy": 0.03304265387350131,
"eval_loss": 7.98660945892334,
"eval_runtime": 227.9954,
"eval_samples_per_second": 34.624,
"eval_steps_per_second": 4.329,
"step": 128
},
{
"epoch": 0.04797207875103943,
"grad_norm": 17.06017303466797,
"learning_rate": 4.761101742551995e-05,
"loss": 102.9587,
"step": 256
},
{
"epoch": 0.04797207875103943,
"eval_accuracy": 0.055030721081703045,
"eval_loss": 5.9021315574646,
"eval_runtime": 240.335,
"eval_samples_per_second": 32.846,
"eval_steps_per_second": 4.107,
"step": 256
},
{
"epoch": 0.09594415750207887,
"grad_norm": 68.73705291748047,
"learning_rate": 4.52126662919243e-05,
"loss": 93.4498,
"step": 512
},
{
"epoch": 0.09594415750207887,
"eval_accuracy": 0.18273613650666046,
"eval_loss": 4.6600799560546875,
"eval_runtime": 236.8236,
"eval_samples_per_second": 33.333,
"eval_steps_per_second": 4.168,
"step": 512
},
{
"epoch": 0.19188831500415773,
"grad_norm": 16.876415252685547,
"learning_rate": 4.0415964024733e-05,
"loss": 74.4021,
"step": 1024
},
{
"epoch": 0.19188831500415773,
"eval_accuracy": 0.1382732248232383,
"eval_loss": 4.865310192108154,
"eval_runtime": 268.5345,
"eval_samples_per_second": 29.397,
"eval_steps_per_second": 3.676,
"step": 1024
},
{
"epoch": 0.38377663000831547,
"grad_norm": 7.590776443481445,
"learning_rate": 3.082255949035038e-05,
"loss": 63.2125,
"step": 2048
},
{
"epoch": 0.38377663000831547,
"eval_accuracy": 0.22398527805247487,
"eval_loss": 4.008070468902588,
"eval_runtime": 233.7103,
"eval_samples_per_second": 33.777,
"eval_steps_per_second": 4.223,
"step": 2048
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.36992276873216e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-2048/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-2048/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-256/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-256/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-256/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-256/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b1f75cea831fbb529ecf75b905e6024e57083efe37c01f3fac3083a3b3dc31e3
size 497774208

6
checkpoint-256/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-256/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-256/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

178
checkpoint-256/trainer_state.json Normal file
View File

@@ -0,0 +1,178 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.04797207875103943,
"eval_steps": 99999999,
"global_step": 256,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
},
{
"epoch": 0.005996509843879929,
"grad_norm": 33.14303207397461,
"learning_rate": 4.970957466741615e-05,
"loss": 141.2197,
"step": 32
},
{
"epoch": 0.005996509843879929,
"eval_accuracy": 0.02386372614066984,
"eval_loss": 10.312174797058105,
"eval_runtime": 201.4605,
"eval_samples_per_second": 39.184,
"eval_steps_per_second": 4.899,
"step": 32
},
{
"epoch": 0.011993019687759858,
"grad_norm": 17.63327407836914,
"learning_rate": 4.94097807757167e-05,
"loss": 128.0666,
"step": 64
},
{
"epoch": 0.011993019687759858,
"eval_accuracy": 0.0342046782626398,
"eval_loss": 9.543290138244629,
"eval_runtime": 210.7504,
"eval_samples_per_second": 37.457,
"eval_steps_per_second": 4.683,
"step": 64
},
{
"epoch": 0.023986039375519717,
"grad_norm": 22.085046768188477,
"learning_rate": 4.881019299231778e-05,
"loss": 118.9934,
"step": 128
},
{
"epoch": 0.023986039375519717,
"eval_accuracy": 0.03304265387350131,
"eval_loss": 7.98660945892334,
"eval_runtime": 227.9954,
"eval_samples_per_second": 34.624,
"eval_steps_per_second": 4.329,
"step": 128
},
{
"epoch": 0.04797207875103943,
"grad_norm": 17.06017303466797,
"learning_rate": 4.761101742551995e-05,
"loss": 102.9587,
"step": 256
},
{
"epoch": 0.04797207875103943,
"eval_accuracy": 0.055030721081703045,
"eval_loss": 5.9021315574646,
"eval_runtime": 240.335,
"eval_samples_per_second": 32.846,
"eval_steps_per_second": 4.107,
"step": 256
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.7124034609152e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-256/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-256/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-32/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-32/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-32/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-32/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1cbcfac53e0bece5be9008a7617550b56610904093152a71b659f4c518828e8
size 497774208

6
checkpoint-32/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-32/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-32/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

130
checkpoint-32/trainer_state.json Normal file
View File

@@ -0,0 +1,130 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.005996509843879929,
"eval_steps": 99999999,
"global_step": 32,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
},
{
"epoch": 0.005996509843879929,
"grad_norm": 33.14303207397461,
"learning_rate": 4.970957466741615e-05,
"loss": 141.2197,
"step": 32
},
{
"epoch": 0.005996509843879929,
"eval_accuracy": 0.02386372614066984,
"eval_loss": 10.312174797058105,
"eval_runtime": 201.4605,
"eval_samples_per_second": 39.184,
"eval_steps_per_second": 4.899,
"step": 32
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2140504326144000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-32/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-32/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-4/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-4/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-4/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-4/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43508a14973a0e8abc1aad06f0cec0ce8dfe55464f2c889633022ac6e6d89524
size 497774208

6
checkpoint-4/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-4/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-4/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

82
checkpoint-4/trainer_state.json Normal file
View File

@@ -0,0 +1,82 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0007495637304849911,
"eval_steps": 99999999,
"global_step": 4,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 267563040768000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-4/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
size 6033

1
checkpoint-4/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

39
checkpoint-4096/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-4096/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-4096/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-4096/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:36ef91266d83cd14ccc7d0326a5ad712c23c7a2582cf28442e7b07243ff864fa
size 497774208

6
checkpoint-4096/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-4096/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-4096/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

242
checkpoint-4096/trainer_state.json Normal file
View File

@@ -0,0 +1,242 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7675532600166309,
"eval_steps": 99999999,
"global_step": 4096,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001873909326212478,
"grad_norm": 245.6398468017578,
"learning_rate": 5e-05,
"loss": 175.7636,
"step": 1
},
{
"epoch": 0.0001873909326212478,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.732580184936523,
"eval_runtime": 219.7551,
"eval_samples_per_second": 35.922,
"eval_steps_per_second": 4.491,
"step": 1
},
{
"epoch": 0.0003747818652424956,
"grad_norm": 113.21331024169922,
"learning_rate": 4.9990631440884397e-05,
"loss": 161.0339,
"step": 2
},
{
"epoch": 0.0003747818652424956,
"eval_accuracy": 0.015452299171252725,
"eval_loss": 10.66187572479248,
"eval_runtime": 137.4523,
"eval_samples_per_second": 57.431,
"eval_steps_per_second": 7.181,
"step": 2
},
{
"epoch": 0.0007495637304849911,
"grad_norm": 65.50191497802734,
"learning_rate": 4.997189432265318e-05,
"loss": 156.102,
"step": 4
},
{
"epoch": 0.0007495637304849911,
"eval_accuracy": 0.015464063058397669,
"eval_loss": 10.59908676147461,
"eval_runtime": 188.7788,
"eval_samples_per_second": 41.816,
"eval_steps_per_second": 5.228,
"step": 4
},
{
"epoch": 0.0014991274609699823,
"grad_norm": 38.306678771972656,
"learning_rate": 4.993442008619075e-05,
"loss": 152.2921,
"step": 8
},
{
"epoch": 0.0014991274609699823,
"eval_accuracy": 0.015459481333930691,
"eval_loss": 10.50749397277832,
"eval_runtime": 140.9589,
"eval_samples_per_second": 56.002,
"eval_steps_per_second": 7.002,
"step": 8
},
{
"epoch": 0.0029982549219399646,
"grad_norm": 33.0531005859375,
"learning_rate": 4.985947161326589e-05,
"loss": 148.7237,
"step": 16
},
{
"epoch": 0.0029982549219399646,
"eval_accuracy": 0.018715353804478252,
"eval_loss": 10.448219299316406,
"eval_runtime": 215.51,
"eval_samples_per_second": 36.629,
"eval_steps_per_second": 4.58,
"step": 16
},
{
"epoch": 0.005996509843879929,
"grad_norm": 33.14303207397461,
"learning_rate": 4.970957466741615e-05,
"loss": 141.2197,
"step": 32
},
{
"epoch": 0.005996509843879929,
"eval_accuracy": 0.02386372614066984,
"eval_loss": 10.312174797058105,
"eval_runtime": 201.4605,
"eval_samples_per_second": 39.184,
"eval_steps_per_second": 4.899,
"step": 32
},
{
"epoch": 0.011993019687759858,
"grad_norm": 17.63327407836914,
"learning_rate": 4.94097807757167e-05,
"loss": 128.0666,
"step": 64
},
{
"epoch": 0.011993019687759858,
"eval_accuracy": 0.0342046782626398,
"eval_loss": 9.543290138244629,
"eval_runtime": 210.7504,
"eval_samples_per_second": 37.457,
"eval_steps_per_second": 4.683,
"step": 64
},
{
"epoch": 0.023986039375519717,
"grad_norm": 22.085046768188477,
"learning_rate": 4.881019299231778e-05,
"loss": 118.9934,
"step": 128
},
{
"epoch": 0.023986039375519717,
"eval_accuracy": 0.03304265387350131,
"eval_loss": 7.98660945892334,
"eval_runtime": 227.9954,
"eval_samples_per_second": 34.624,
"eval_steps_per_second": 4.329,
"step": 128
},
{
"epoch": 0.04797207875103943,
"grad_norm": 17.06017303466797,
"learning_rate": 4.761101742551995e-05,
"loss": 102.9587,
"step": 256
},
{
"epoch": 0.04797207875103943,
"eval_accuracy": 0.055030721081703045,
"eval_loss": 5.9021315574646,
"eval_runtime": 240.335,
"eval_samples_per_second": 32.846,
"eval_steps_per_second": 4.107,
"step": 256
},
{
"epoch": 0.09594415750207887,
"grad_norm": 68.73705291748047,
"learning_rate": 4.52126662919243e-05,
"loss": 93.4498,
"step": 512
},
{
"epoch": 0.09594415750207887,
"eval_accuracy": 0.18273613650666046,
"eval_loss": 4.6600799560546875,
"eval_runtime": 236.8236,
"eval_samples_per_second": 33.333,
"eval_steps_per_second": 4.168,
"step": 512
},
{
"epoch": 0.19188831500415773,
"grad_norm": 16.876415252685547,
"learning_rate": 4.0415964024733e-05,
"loss": 74.4021,
"step": 1024
},
{
"epoch": 0.19188831500415773,
"eval_accuracy": 0.1382732248232383,
"eval_loss": 4.865310192108154,
"eval_runtime": 268.5345,
"eval_samples_per_second": 29.397,
"eval_steps_per_second": 3.676,
"step": 1024
},
{
"epoch": 0.38377663000831547,
"grad_norm": 7.590776443481445,
"learning_rate": 3.082255949035038e-05,
"loss": 63.2125,
"step": 2048
},
{
"epoch": 0.38377663000831547,
"eval_accuracy": 0.22398527805247487,
"eval_loss": 4.008070468902588,
"eval_runtime": 233.7103,
"eval_samples_per_second": 33.777,
"eval_steps_per_second": 4.223,
"step": 2048
},
{
"epoch": 0.7675532600166309,
"grad_norm": 9.217267990112305,
"learning_rate": 1.163575042158516e-05,
"loss": 46.9282,
"step": 4096
},
{
"epoch": 0.7675532600166309,
"eval_accuracy": 0.31996237537399874,
"eval_loss": 3.480340003967285,
"eval_runtime": 277.8889,
"eval_samples_per_second": 28.407,
"eval_steps_per_second": 3.552,
"step": 4096
}
],
"logging_steps": 99999999,
"max_steps": 5337,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.73984553746432e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

Some files were not shown because too many files have changed in this diff Show More