Cisco1963/llmplasticity-zh_en_instant_0.25_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-zh_en_instant_0.25_1-seed42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 05:00:32 +08:00
commit 41952bb0b6
148 changed files with 4207607 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": 0.18123281108255684,
"eval_en_loss": 5.584699970175632,
"eval_loss": 4.9185099601745605,
"eval_runtime": 127.4354,
"eval_samples": 7892,
"eval_samples_per_second": 61.929,
"eval_steps_per_second": 7.745,
"eval_zh_loss": 4.67808330153985,
"perplexity": 136.7986258490016,
"total_flos": 1.9156102742016e+17,
"train_loss": 78.13838508009245,
"train_runtime": 14662.1363,
"train_samples": 366565,
"train_samples_per_second": 25.001,
"train_steps_per_second": 0.195
}

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:bee572a4b0dda732ae22c3fde94746c5cc4bdd08ef89c73d5e73f66df5dfd35d
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": 0.00034918487156543944,
"eval_steps": 99999999,
"global_step": 1,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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:ab08024e670b830666ac74926def53f6f8e607efeb3819ad2e2420aa880358b1
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": 0.35756530848301,
"eval_steps": 99999999,
"global_step": 1024,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
},
{
"epoch": 0.011173915890094062,
"grad_norm": 48.77768325805664,
"learning_rate": 4.9458798882681565e-05,
"loss": 113.3273,
"step": 32
},
{
"epoch": 0.011173915890094062,
"eval_accuracy": 0.15826276928168595,
"eval_loss": 7.515727519989014,
"eval_runtime": 126.3816,
"eval_samples_per_second": 62.446,
"eval_steps_per_second": 7.81,
"step": 32
},
{
"epoch": 0.022347831780188124,
"grad_norm": 30.68110466003418,
"learning_rate": 4.890013966480447e-05,
"loss": 92.5668,
"step": 64
},
{
"epoch": 0.022347831780188124,
"eval_accuracy": 0.16659792338307128,
"eval_loss": 6.12502384185791,
"eval_runtime": 139.2964,
"eval_samples_per_second": 56.656,
"eval_steps_per_second": 7.086,
"step": 64
},
{
"epoch": 0.04469566356037625,
"grad_norm": 59.65339279174805,
"learning_rate": 4.778282122905028e-05,
"loss": 63.429,
"step": 128
},
{
"epoch": 0.04469566356037625,
"eval_accuracy": 0.18046078065616022,
"eval_loss": 5.348491191864014,
"eval_runtime": 131.9171,
"eval_samples_per_second": 59.825,
"eval_steps_per_second": 7.482,
"step": 128
},
{
"epoch": 0.0893913271207525,
"grad_norm": 11.741301536560059,
"learning_rate": 4.55481843575419e-05,
"loss": 57.462,
"step": 256
},
{
"epoch": 0.0893913271207525,
"eval_accuracy": 0.17872138978853822,
"eval_loss": 5.072287082672119,
"eval_runtime": 129.0224,
"eval_samples_per_second": 61.168,
"eval_steps_per_second": 7.65,
"step": 256
},
{
"epoch": 0.178782654241505,
"grad_norm": 13.833954811096191,
"learning_rate": 4.107891061452514e-05,
"loss": 55.1007,
"step": 512
},
{
"epoch": 0.178782654241505,
"eval_accuracy": 0.1931328308508957,
"eval_loss": 4.581916332244873,
"eval_runtime": 145.9479,
"eval_samples_per_second": 54.074,
"eval_steps_per_second": 6.763,
"step": 512
},
{
"epoch": 0.35756530848301,
"grad_norm": 13.025886535644531,
"learning_rate": 3.2140363128491625e-05,
"loss": 51.226,
"step": 1024
},
{
"epoch": 0.35756530848301,
"eval_accuracy": 0.23887300155223573,
"eval_loss": 4.21856689453125,
"eval_runtime": 132.0572,
"eval_samples_per_second": 59.762,
"eval_steps_per_second": 7.474,
"step": 1024
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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 sha256:7405b3fb55f2d61b88d01c58a17cb03a27bf78f78b36d36f36ef4d10ead68df7
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": 0.04469566356037625,
"eval_steps": 99999999,
"global_step": 128,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
},
{
"epoch": 0.011173915890094062,
"grad_norm": 48.77768325805664,
"learning_rate": 4.9458798882681565e-05,
"loss": 113.3273,
"step": 32
},
{
"epoch": 0.011173915890094062,
"eval_accuracy": 0.15826276928168595,
"eval_loss": 7.515727519989014,
"eval_runtime": 126.3816,
"eval_samples_per_second": 62.446,
"eval_steps_per_second": 7.81,
"step": 32
},
{
"epoch": 0.022347831780188124,
"grad_norm": 30.68110466003418,
"learning_rate": 4.890013966480447e-05,
"loss": 92.5668,
"step": 64
},
{
"epoch": 0.022347831780188124,
"eval_accuracy": 0.16659792338307128,
"eval_loss": 6.12502384185791,
"eval_runtime": 139.2964,
"eval_samples_per_second": 56.656,
"eval_steps_per_second": 7.086,
"step": 64
},
{
"epoch": 0.04469566356037625,
"grad_norm": 59.65339279174805,
"learning_rate": 4.778282122905028e-05,
"loss": 63.429,
"step": 128
},
{
"epoch": 0.04469566356037625,
"eval_accuracy": 0.18046078065616022,
"eval_loss": 5.348491191864014,
"eval_runtime": 131.9171,
"eval_samples_per_second": 59.825,
"eval_steps_per_second": 7.482,
"step": 128
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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:b18bc6bfa566bc320cc2561b8d9ce9f0f7a5e4aff902709fa678982bcbef7204
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": 0.005586957945047031,
"eval_steps": 99999999,
"global_step": 16,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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 sha256:947752050a5b5e1a7c0e4f13cf67bc5f81bc56b1b9e6a81905c1013331f71412
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": 0.0006983697431308789,
"eval_steps": 99999999,
"global_step": 2,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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 sha256:47c5e57b4172fe25498f6bb56c7f26b70680e9f5932c5853f3437dfd3b92e108
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": 0.71513061696602,
"eval_steps": 99999999,
"global_step": 2048,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
},
{
"epoch": 0.011173915890094062,
"grad_norm": 48.77768325805664,
"learning_rate": 4.9458798882681565e-05,
"loss": 113.3273,
"step": 32
},
{
"epoch": 0.011173915890094062,
"eval_accuracy": 0.15826276928168595,
"eval_loss": 7.515727519989014,
"eval_runtime": 126.3816,
"eval_samples_per_second": 62.446,
"eval_steps_per_second": 7.81,
"step": 32
},
{
"epoch": 0.022347831780188124,
"grad_norm": 30.68110466003418,
"learning_rate": 4.890013966480447e-05,
"loss": 92.5668,
"step": 64
},
{
"epoch": 0.022347831780188124,
"eval_accuracy": 0.16659792338307128,
"eval_loss": 6.12502384185791,
"eval_runtime": 139.2964,
"eval_samples_per_second": 56.656,
"eval_steps_per_second": 7.086,
"step": 64
},
{
"epoch": 0.04469566356037625,
"grad_norm": 59.65339279174805,
"learning_rate": 4.778282122905028e-05,
"loss": 63.429,
"step": 128
},
{
"epoch": 0.04469566356037625,
"eval_accuracy": 0.18046078065616022,
"eval_loss": 5.348491191864014,
"eval_runtime": 131.9171,
"eval_samples_per_second": 59.825,
"eval_steps_per_second": 7.482,
"step": 128
},
{
"epoch": 0.0893913271207525,
"grad_norm": 11.741301536560059,
"learning_rate": 4.55481843575419e-05,
"loss": 57.462,
"step": 256
},
{
"epoch": 0.0893913271207525,
"eval_accuracy": 0.17872138978853822,
"eval_loss": 5.072287082672119,
"eval_runtime": 129.0224,
"eval_samples_per_second": 61.168,
"eval_steps_per_second": 7.65,
"step": 256
},
{
"epoch": 0.178782654241505,
"grad_norm": 13.833954811096191,
"learning_rate": 4.107891061452514e-05,
"loss": 55.1007,
"step": 512
},
{
"epoch": 0.178782654241505,
"eval_accuracy": 0.1931328308508957,
"eval_loss": 4.581916332244873,
"eval_runtime": 145.9479,
"eval_samples_per_second": 54.074,
"eval_steps_per_second": 6.763,
"step": 512
},
{
"epoch": 0.35756530848301,
"grad_norm": 13.025886535644531,
"learning_rate": 3.2140363128491625e-05,
"loss": 51.226,
"step": 1024
},
{
"epoch": 0.35756530848301,
"eval_accuracy": 0.23887300155223573,
"eval_loss": 4.21856689453125,
"eval_runtime": 132.0572,
"eval_samples_per_second": 59.762,
"eval_steps_per_second": 7.474,
"step": 1024
},
{
"epoch": 0.71513061696602,
"grad_norm": 20.863210678100586,
"learning_rate": 1.426326815642458e-05,
"loss": 89.1826,
"step": 2048
},
{
"epoch": 0.71513061696602,
"eval_accuracy": 0.17063321606100737,
"eval_loss": 5.058229446411133,
"eval_runtime": 137.3899,
"eval_samples_per_second": 57.442,
"eval_steps_per_second": 7.184,
"step": 2048
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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 sha256:85e75d4d36b842c670b5904598254d2d1843850d7e523dc23fbb3cb062315d75
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": 0.0893913271207525,
"eval_steps": 99999999,
"global_step": 256,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
},
{
"epoch": 0.011173915890094062,
"grad_norm": 48.77768325805664,
"learning_rate": 4.9458798882681565e-05,
"loss": 113.3273,
"step": 32
},
{
"epoch": 0.011173915890094062,
"eval_accuracy": 0.15826276928168595,
"eval_loss": 7.515727519989014,
"eval_runtime": 126.3816,
"eval_samples_per_second": 62.446,
"eval_steps_per_second": 7.81,
"step": 32
},
{
"epoch": 0.022347831780188124,
"grad_norm": 30.68110466003418,
"learning_rate": 4.890013966480447e-05,
"loss": 92.5668,
"step": 64
},
{
"epoch": 0.022347831780188124,
"eval_accuracy": 0.16659792338307128,
"eval_loss": 6.12502384185791,
"eval_runtime": 139.2964,
"eval_samples_per_second": 56.656,
"eval_steps_per_second": 7.086,
"step": 64
},
{
"epoch": 0.04469566356037625,
"grad_norm": 59.65339279174805,
"learning_rate": 4.778282122905028e-05,
"loss": 63.429,
"step": 128
},
{
"epoch": 0.04469566356037625,
"eval_accuracy": 0.18046078065616022,
"eval_loss": 5.348491191864014,
"eval_runtime": 131.9171,
"eval_samples_per_second": 59.825,
"eval_steps_per_second": 7.482,
"step": 128
},
{
"epoch": 0.0893913271207525,
"grad_norm": 11.741301536560059,
"learning_rate": 4.55481843575419e-05,
"loss": 57.462,
"step": 256
},
{
"epoch": 0.0893913271207525,
"eval_accuracy": 0.17872138978853822,
"eval_loss": 5.072287082672119,
"eval_runtime": 129.0224,
"eval_samples_per_second": 61.168,
"eval_steps_per_second": 7.65,
"step": 256
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
size 6033

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

File diff suppressed because one or more lines are too long

39
checkpoint-2864/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-2864/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-2864/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-2864/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6816d578007fa887fff16481b8041e8a3539a7fbf9f10038365b001d3e5189d
size 497774208

3
checkpoint-2864/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e660b80c607bbf9b43fda85da7a570ac00f82eeecfaf76b2514e7afbe47e1855
size 995644811

3
checkpoint-2864/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f2d80ae47326ddf216ecccbe856d1b878c3c6e53f786db78a4999c5e27652d0
size 14645

3
checkpoint-2864/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:416eb83585eabdd94eb9deab54597f1dba9faa2bd8360db62e1ca937aefb060d
size 1383

3
checkpoint-2864/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd4a3fe6165754be06c97126ad059fa98b06650cf662a6f75e5d7970cf9870f5
size 1465

6
checkpoint-2864/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-2864/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-2864/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-2864/trainer_state.json Normal file
View File

@@ -0,0 +1,226 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 99999999,
"global_step": 2864,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
},
{
"epoch": 0.011173915890094062,
"grad_norm": 48.77768325805664,
"learning_rate": 4.9458798882681565e-05,
"loss": 113.3273,
"step": 32
},
{
"epoch": 0.011173915890094062,
"eval_accuracy": 0.15826276928168595,
"eval_loss": 7.515727519989014,
"eval_runtime": 126.3816,
"eval_samples_per_second": 62.446,
"eval_steps_per_second": 7.81,
"step": 32
},
{
"epoch": 0.022347831780188124,
"grad_norm": 30.68110466003418,
"learning_rate": 4.890013966480447e-05,
"loss": 92.5668,
"step": 64
},
{
"epoch": 0.022347831780188124,
"eval_accuracy": 0.16659792338307128,
"eval_loss": 6.12502384185791,
"eval_runtime": 139.2964,
"eval_samples_per_second": 56.656,
"eval_steps_per_second": 7.086,
"step": 64
},
{
"epoch": 0.04469566356037625,
"grad_norm": 59.65339279174805,
"learning_rate": 4.778282122905028e-05,
"loss": 63.429,
"step": 128
},
{
"epoch": 0.04469566356037625,
"eval_accuracy": 0.18046078065616022,
"eval_loss": 5.348491191864014,
"eval_runtime": 131.9171,
"eval_samples_per_second": 59.825,
"eval_steps_per_second": 7.482,
"step": 128
},
{
"epoch": 0.0893913271207525,
"grad_norm": 11.741301536560059,
"learning_rate": 4.55481843575419e-05,
"loss": 57.462,
"step": 256
},
{
"epoch": 0.0893913271207525,
"eval_accuracy": 0.17872138978853822,
"eval_loss": 5.072287082672119,
"eval_runtime": 129.0224,
"eval_samples_per_second": 61.168,
"eval_steps_per_second": 7.65,
"step": 256
},
{
"epoch": 0.178782654241505,
"grad_norm": 13.833954811096191,
"learning_rate": 4.107891061452514e-05,
"loss": 55.1007,
"step": 512
},
{
"epoch": 0.178782654241505,
"eval_accuracy": 0.1931328308508957,
"eval_loss": 4.581916332244873,
"eval_runtime": 145.9479,
"eval_samples_per_second": 54.074,
"eval_steps_per_second": 6.763,
"step": 512
},
{
"epoch": 0.35756530848301,
"grad_norm": 13.025886535644531,
"learning_rate": 3.2140363128491625e-05,
"loss": 51.226,
"step": 1024
},
{
"epoch": 0.35756530848301,
"eval_accuracy": 0.23887300155223573,
"eval_loss": 4.21856689453125,
"eval_runtime": 132.0572,
"eval_samples_per_second": 59.762,
"eval_steps_per_second": 7.474,
"step": 1024
},
{
"epoch": 0.71513061696602,
"grad_norm": 20.863210678100586,
"learning_rate": 1.426326815642458e-05,
"loss": 89.1826,
"step": 2048
},
{
"epoch": 0.71513061696602,
"eval_accuracy": 0.17063321606100737,
"eval_loss": 5.058229446411133,
"eval_runtime": 137.3899,
"eval_samples_per_second": 57.442,
"eval_steps_per_second": 7.184,
"step": 2048
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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": true
},
"attributes": {}
}
},
"total_flos": 1.9156102742016e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-2864/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
size 6033

1
checkpoint-2864/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:c62c4eb29a19d21c6a38d7c67c184c8de8c970ea72fc17e233669bd7a0ef0e53
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": 0.011173915890094062,
"eval_steps": 99999999,
"global_step": 32,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034918487156543944,
"grad_norm": 232.1994171142578,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00034918487156543944,
"eval_accuracy": 0.023954123581349192,
"eval_loss": 10.253963470458984,
"eval_runtime": 128.4941,
"eval_samples_per_second": 61.419,
"eval_steps_per_second": 7.681,
"step": 1
},
{
"epoch": 0.0006983697431308789,
"grad_norm": 114.17286682128906,
"learning_rate": 4.9982541899441346e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.0006983697431308789,
"eval_accuracy": 0.016392362385855185,
"eval_loss": 9.9473237991333,
"eval_runtime": 128.9886,
"eval_samples_per_second": 61.184,
"eval_steps_per_second": 7.652,
"step": 2
},
{
"epoch": 0.0013967394862617578,
"grad_norm": 51.907196044921875,
"learning_rate": 4.9947625698324026e-05,
"loss": 152.5682,
"step": 4
},
{
"epoch": 0.0013967394862617578,
"eval_accuracy": 0.028750051402635483,
"eval_loss": 9.692176818847656,
"eval_runtime": 127.9133,
"eval_samples_per_second": 61.698,
"eval_steps_per_second": 7.716,
"step": 4
},
{
"epoch": 0.0027934789725235156,
"grad_norm": 79.11775970458984,
"learning_rate": 4.9877793296089386e-05,
"loss": 145.6449,
"step": 8
},
{
"epoch": 0.0027934789725235156,
"eval_accuracy": 0.1025968115998036,
"eval_loss": 10.163084030151367,
"eval_runtime": 156.5451,
"eval_samples_per_second": 50.414,
"eval_steps_per_second": 6.305,
"step": 8
},
{
"epoch": 0.005586957945047031,
"grad_norm": 62.22785186767578,
"learning_rate": 4.973812849162011e-05,
"loss": 139.486,
"step": 16
},
{
"epoch": 0.005586957945047031,
"eval_accuracy": 0.11699363697303629,
"eval_loss": 8.626287460327148,
"eval_runtime": 126.9555,
"eval_samples_per_second": 62.164,
"eval_steps_per_second": 7.774,
"step": 16
},
{
"epoch": 0.011173915890094062,
"grad_norm": 48.77768325805664,
"learning_rate": 4.9458798882681565e-05,
"loss": 113.3273,
"step": 32
},
{
"epoch": 0.011173915890094062,
"eval_accuracy": 0.15826276928168595,
"eval_loss": 7.515727519989014,
"eval_runtime": 126.3816,
"eval_samples_per_second": 62.446,
"eval_steps_per_second": 7.81,
"step": 32
}
],
"logging_steps": 99999999,
"max_steps": 2864,
"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 sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
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 sha256:304724c7d8f9a2359d6ae2a416a422546adeb0473c1b0d973d6ed68166623965
size 497774208

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