Cisco1963/llmplasticity-zh_fi_instant_0.5_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_fi_instant_0.5_1-seed42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 05:01:28 +08:00
commit 7d960cd321
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": 0.2829077390777954,
"eval_fi_loss": 2.756577809673876,
"eval_loss": 4.162175178527832,
"eval_runtime": 168.4961,
"eval_samples": 10002,
"eval_samples_per_second": 59.36,
"eval_steps_per_second": 7.425,
"eval_zh_loss": 5.180693438180575,
"perplexity": 64.21104128415467,
"total_flos": 3.75465675718656e+17,
"train_loss": 52.505090124376906,
"train_runtime": 26736.2295,
"train_samples": 718479,
"train_samples_per_second": 26.873,
"train_steps_per_second": 0.21
}

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:ba0213166dc844d97e9e20c97ec1bc6af85946509543033a9d997336e117fa4e
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": 0.00017815388041420778,
"eval_steps": 99999999,
"global_step": 1,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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:a861fdd5161c1f551d0634a1e6f5d9cf83a940b8659b6c8d23ea9a4b430a7f42
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": 0.18242957354414877,
"eval_steps": 99999999,
"global_step": 1024,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
},
{
"epoch": 0.005700924173254649,
"grad_norm": 48.63093566894531,
"learning_rate": 4.972390452440328e-05,
"loss": 113.2903,
"step": 32
},
{
"epoch": 0.005700924173254649,
"eval_accuracy": 0.12488157305000389,
"eval_loss": 8.238554954528809,
"eval_runtime": 159.9917,
"eval_samples_per_second": 62.516,
"eval_steps_per_second": 7.819,
"step": 32
},
{
"epoch": 0.011401848346509298,
"grad_norm": 30.36475372314453,
"learning_rate": 4.9438902743142145e-05,
"loss": 92.4312,
"step": 64
},
{
"epoch": 0.011401848346509298,
"eval_accuracy": 0.13147976465313,
"eval_loss": 7.147886276245117,
"eval_runtime": 166.5905,
"eval_samples_per_second": 60.039,
"eval_steps_per_second": 7.509,
"step": 64
},
{
"epoch": 0.022803696693018596,
"grad_norm": 53.339027404785156,
"learning_rate": 4.886889918061988e-05,
"loss": 63.2434,
"step": 128
},
{
"epoch": 0.022803696693018596,
"eval_accuracy": 0.16450072644317668,
"eval_loss": 6.494359493255615,
"eval_runtime": 168.6415,
"eval_samples_per_second": 59.309,
"eval_steps_per_second": 7.418,
"step": 128
},
{
"epoch": 0.04560739338603719,
"grad_norm": 12.019591331481934,
"learning_rate": 4.7728892055575344e-05,
"loss": 57.3288,
"step": 256
},
{
"epoch": 0.04560739338603719,
"eval_accuracy": 0.14192156681078252,
"eval_loss": 6.2028303146362305,
"eval_runtime": 180.9015,
"eval_samples_per_second": 55.29,
"eval_steps_per_second": 6.915,
"step": 256
},
{
"epoch": 0.09121478677207438,
"grad_norm": 14.86228084564209,
"learning_rate": 4.544887780548628e-05,
"loss": 55.0041,
"step": 512
},
{
"epoch": 0.09121478677207438,
"eval_accuracy": 0.16740767193579856,
"eval_loss": 5.706745147705078,
"eval_runtime": 182.3289,
"eval_samples_per_second": 54.857,
"eval_steps_per_second": 6.861,
"step": 512
},
{
"epoch": 0.18242957354414877,
"grad_norm": 13.710566520690918,
"learning_rate": 4.0888849305308155e-05,
"loss": 50.6182,
"step": 1024
},
{
"epoch": 0.18242957354414877,
"eval_accuracy": 0.19536239379690046,
"eval_loss": 5.437285423278809,
"eval_runtime": 159.2749,
"eval_samples_per_second": 62.797,
"eval_steps_per_second": 7.854,
"step": 1024
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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:e711a1e2b20250caf3324f86456cb668a9b9af1497d558292c3dba8fe3b8e0dd
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": 0.022803696693018596,
"eval_steps": 99999999,
"global_step": 128,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
},
{
"epoch": 0.005700924173254649,
"grad_norm": 48.63093566894531,
"learning_rate": 4.972390452440328e-05,
"loss": 113.2903,
"step": 32
},
{
"epoch": 0.005700924173254649,
"eval_accuracy": 0.12488157305000389,
"eval_loss": 8.238554954528809,
"eval_runtime": 159.9917,
"eval_samples_per_second": 62.516,
"eval_steps_per_second": 7.819,
"step": 32
},
{
"epoch": 0.011401848346509298,
"grad_norm": 30.36475372314453,
"learning_rate": 4.9438902743142145e-05,
"loss": 92.4312,
"step": 64
},
{
"epoch": 0.011401848346509298,
"eval_accuracy": 0.13147976465313,
"eval_loss": 7.147886276245117,
"eval_runtime": 166.5905,
"eval_samples_per_second": 60.039,
"eval_steps_per_second": 7.509,
"step": 64
},
{
"epoch": 0.022803696693018596,
"grad_norm": 53.339027404785156,
"learning_rate": 4.886889918061988e-05,
"loss": 63.2434,
"step": 128
},
{
"epoch": 0.022803696693018596,
"eval_accuracy": 0.16450072644317668,
"eval_loss": 6.494359493255615,
"eval_runtime": 168.6415,
"eval_samples_per_second": 59.309,
"eval_steps_per_second": 7.418,
"step": 128
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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 sha256:41881e9e86636df3dc854607f9499fd06f6be3572bf8e2251e60e4e34c60e9f5
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": 0.0028504620866273245,
"eval_steps": 99999999,
"global_step": 16,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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:f91cfed4bf7ae5cf6535fbd7ba8cb2affa09534dce7e621ea7dfeaaef9300292
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": 0.00035630776082841556,
"eval_steps": 99999999,
"global_step": 2,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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 sha256:2353f0e46a20c9f48dac2c3c9c637e940987bc217c96f9d1e6e146b3c609ea12
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": 0.36485914708829753,
"eval_steps": 99999999,
"global_step": 2048,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
},
{
"epoch": 0.005700924173254649,
"grad_norm": 48.63093566894531,
"learning_rate": 4.972390452440328e-05,
"loss": 113.2903,
"step": 32
},
{
"epoch": 0.005700924173254649,
"eval_accuracy": 0.12488157305000389,
"eval_loss": 8.238554954528809,
"eval_runtime": 159.9917,
"eval_samples_per_second": 62.516,
"eval_steps_per_second": 7.819,
"step": 32
},
{
"epoch": 0.011401848346509298,
"grad_norm": 30.36475372314453,
"learning_rate": 4.9438902743142145e-05,
"loss": 92.4312,
"step": 64
},
{
"epoch": 0.011401848346509298,
"eval_accuracy": 0.13147976465313,
"eval_loss": 7.147886276245117,
"eval_runtime": 166.5905,
"eval_samples_per_second": 60.039,
"eval_steps_per_second": 7.509,
"step": 64
},
{
"epoch": 0.022803696693018596,
"grad_norm": 53.339027404785156,
"learning_rate": 4.886889918061988e-05,
"loss": 63.2434,
"step": 128
},
{
"epoch": 0.022803696693018596,
"eval_accuracy": 0.16450072644317668,
"eval_loss": 6.494359493255615,
"eval_runtime": 168.6415,
"eval_samples_per_second": 59.309,
"eval_steps_per_second": 7.418,
"step": 128
},
{
"epoch": 0.04560739338603719,
"grad_norm": 12.019591331481934,
"learning_rate": 4.7728892055575344e-05,
"loss": 57.3288,
"step": 256
},
{
"epoch": 0.04560739338603719,
"eval_accuracy": 0.14192156681078252,
"eval_loss": 6.2028303146362305,
"eval_runtime": 180.9015,
"eval_samples_per_second": 55.29,
"eval_steps_per_second": 6.915,
"step": 256
},
{
"epoch": 0.09121478677207438,
"grad_norm": 14.86228084564209,
"learning_rate": 4.544887780548628e-05,
"loss": 55.0041,
"step": 512
},
{
"epoch": 0.09121478677207438,
"eval_accuracy": 0.16740767193579856,
"eval_loss": 5.706745147705078,
"eval_runtime": 182.3289,
"eval_samples_per_second": 54.857,
"eval_steps_per_second": 6.861,
"step": 512
},
{
"epoch": 0.18242957354414877,
"grad_norm": 13.710566520690918,
"learning_rate": 4.0888849305308155e-05,
"loss": 50.6182,
"step": 1024
},
{
"epoch": 0.18242957354414877,
"eval_accuracy": 0.19536239379690046,
"eval_loss": 5.437285423278809,
"eval_runtime": 159.2749,
"eval_samples_per_second": 62.797,
"eval_steps_per_second": 7.854,
"step": 1024
},
{
"epoch": 0.36485914708829753,
"grad_norm": 23.54279327392578,
"learning_rate": 3.17687923049519e-05,
"loss": 46.5895,
"step": 2048
},
{
"epoch": 0.36485914708829753,
"eval_accuracy": 0.12475931011256204,
"eval_loss": 6.226956844329834,
"eval_runtime": 165.8237,
"eval_samples_per_second": 60.317,
"eval_steps_per_second": 7.544,
"step": 2048
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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 sha256:9a3aa40946b5ede20e1aedefed212eda7ea801fa24bfc76a0de100c3757713a9
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": 0.04560739338603719,
"eval_steps": 99999999,
"global_step": 256,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
},
{
"epoch": 0.005700924173254649,
"grad_norm": 48.63093566894531,
"learning_rate": 4.972390452440328e-05,
"loss": 113.2903,
"step": 32
},
{
"epoch": 0.005700924173254649,
"eval_accuracy": 0.12488157305000389,
"eval_loss": 8.238554954528809,
"eval_runtime": 159.9917,
"eval_samples_per_second": 62.516,
"eval_steps_per_second": 7.819,
"step": 32
},
{
"epoch": 0.011401848346509298,
"grad_norm": 30.36475372314453,
"learning_rate": 4.9438902743142145e-05,
"loss": 92.4312,
"step": 64
},
{
"epoch": 0.011401848346509298,
"eval_accuracy": 0.13147976465313,
"eval_loss": 7.147886276245117,
"eval_runtime": 166.5905,
"eval_samples_per_second": 60.039,
"eval_steps_per_second": 7.509,
"step": 64
},
{
"epoch": 0.022803696693018596,
"grad_norm": 53.339027404785156,
"learning_rate": 4.886889918061988e-05,
"loss": 63.2434,
"step": 128
},
{
"epoch": 0.022803696693018596,
"eval_accuracy": 0.16450072644317668,
"eval_loss": 6.494359493255615,
"eval_runtime": 168.6415,
"eval_samples_per_second": 59.309,
"eval_steps_per_second": 7.418,
"step": 128
},
{
"epoch": 0.04560739338603719,
"grad_norm": 12.019591331481934,
"learning_rate": 4.7728892055575344e-05,
"loss": 57.3288,
"step": 256
},
{
"epoch": 0.04560739338603719,
"eval_accuracy": 0.14192156681078252,
"eval_loss": 6.2028303146362305,
"eval_runtime": 180.9015,
"eval_samples_per_second": 55.29,
"eval_steps_per_second": 6.915,
"step": 256
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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 sha256:53fad45b68a0583668950d9c5f83c969df05e5852358624db8586d1ec293b4e1
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": 0.005700924173254649,
"eval_steps": 99999999,
"global_step": 32,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
},
{
"epoch": 0.005700924173254649,
"grad_norm": 48.63093566894531,
"learning_rate": 4.972390452440328e-05,
"loss": 113.2903,
"step": 32
},
{
"epoch": 0.005700924173254649,
"eval_accuracy": 0.12488157305000389,
"eval_loss": 8.238554954528809,
"eval_runtime": 159.9917,
"eval_samples_per_second": 62.516,
"eval_steps_per_second": 7.819,
"step": 32
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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 sha256:68a6670558ea4fe200a1902cba9e25b41735ead609ff7e117fa9b556a6a1b212
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": 0.0007126155216568311,
"eval_steps": 99999999,
"global_step": 4,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
size 5969

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 sha256:8ca276aa8e196b5c2ca11ef61532aec2bec2a4058ae38d266e2d3eafd4b05e50
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": 0.7297182941765951,
"eval_steps": 99999999,
"global_step": 4096,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00017815388041420778,
"grad_norm": 232.1993865966797,
"learning_rate": 5e-05,
"loss": 175.5579,
"step": 1
},
{
"epoch": 0.00017815388041420778,
"eval_accuracy": 0.018891725076294615,
"eval_loss": 10.400674819946289,
"eval_runtime": 157.3868,
"eval_samples_per_second": 63.55,
"eval_steps_per_second": 7.949,
"step": 1
},
{
"epoch": 0.00035630776082841556,
"grad_norm": 114.17350769042969,
"learning_rate": 4.99910936943356e-05,
"loss": 160.0191,
"step": 2
},
{
"epoch": 0.00035630776082841556,
"eval_accuracy": 0.01293475420262966,
"eval_loss": 10.170297622680664,
"eval_runtime": 161.9764,
"eval_samples_per_second": 61.75,
"eval_steps_per_second": 7.723,
"step": 2
},
{
"epoch": 0.0007126155216568311,
"grad_norm": 51.90617370605469,
"learning_rate": 4.9973281083006775e-05,
"loss": 152.5677,
"step": 4
},
{
"epoch": 0.0007126155216568311,
"eval_accuracy": 0.022687935531173334,
"eval_loss": 9.972246170043945,
"eval_runtime": 181.1968,
"eval_samples_per_second": 55.2,
"eval_steps_per_second": 6.904,
"step": 4
},
{
"epoch": 0.0014252310433136622,
"grad_norm": 79.16446685791016,
"learning_rate": 4.993765586034913e-05,
"loss": 145.6416,
"step": 8
},
{
"epoch": 0.0014252310433136622,
"eval_accuracy": 0.08070331192803473,
"eval_loss": 10.352470397949219,
"eval_runtime": 167.7318,
"eval_samples_per_second": 59.631,
"eval_steps_per_second": 7.458,
"step": 8
},
{
"epoch": 0.0028504620866273245,
"grad_norm": 62.1901969909668,
"learning_rate": 4.9866405415033846e-05,
"loss": 139.5395,
"step": 16
},
{
"epoch": 0.0028504620866273245,
"eval_accuracy": 0.09230773591127327,
"eval_loss": 9.133565902709961,
"eval_runtime": 167.1804,
"eval_samples_per_second": 59.828,
"eval_steps_per_second": 7.483,
"step": 16
},
{
"epoch": 0.005700924173254649,
"grad_norm": 48.63093566894531,
"learning_rate": 4.972390452440328e-05,
"loss": 113.2903,
"step": 32
},
{
"epoch": 0.005700924173254649,
"eval_accuracy": 0.12488157305000389,
"eval_loss": 8.238554954528809,
"eval_runtime": 159.9917,
"eval_samples_per_second": 62.516,
"eval_steps_per_second": 7.819,
"step": 32
},
{
"epoch": 0.011401848346509298,
"grad_norm": 30.36475372314453,
"learning_rate": 4.9438902743142145e-05,
"loss": 92.4312,
"step": 64
},
{
"epoch": 0.011401848346509298,
"eval_accuracy": 0.13147976465313,
"eval_loss": 7.147886276245117,
"eval_runtime": 166.5905,
"eval_samples_per_second": 60.039,
"eval_steps_per_second": 7.509,
"step": 64
},
{
"epoch": 0.022803696693018596,
"grad_norm": 53.339027404785156,
"learning_rate": 4.886889918061988e-05,
"loss": 63.2434,
"step": 128
},
{
"epoch": 0.022803696693018596,
"eval_accuracy": 0.16450072644317668,
"eval_loss": 6.494359493255615,
"eval_runtime": 168.6415,
"eval_samples_per_second": 59.309,
"eval_steps_per_second": 7.418,
"step": 128
},
{
"epoch": 0.04560739338603719,
"grad_norm": 12.019591331481934,
"learning_rate": 4.7728892055575344e-05,
"loss": 57.3288,
"step": 256
},
{
"epoch": 0.04560739338603719,
"eval_accuracy": 0.14192156681078252,
"eval_loss": 6.2028303146362305,
"eval_runtime": 180.9015,
"eval_samples_per_second": 55.29,
"eval_steps_per_second": 6.915,
"step": 256
},
{
"epoch": 0.09121478677207438,
"grad_norm": 14.86228084564209,
"learning_rate": 4.544887780548628e-05,
"loss": 55.0041,
"step": 512
},
{
"epoch": 0.09121478677207438,
"eval_accuracy": 0.16740767193579856,
"eval_loss": 5.706745147705078,
"eval_runtime": 182.3289,
"eval_samples_per_second": 54.857,
"eval_steps_per_second": 6.861,
"step": 512
},
{
"epoch": 0.18242957354414877,
"grad_norm": 13.710566520690918,
"learning_rate": 4.0888849305308155e-05,
"loss": 50.6182,
"step": 1024
},
{
"epoch": 0.18242957354414877,
"eval_accuracy": 0.19536239379690046,
"eval_loss": 5.437285423278809,
"eval_runtime": 159.2749,
"eval_samples_per_second": 62.797,
"eval_steps_per_second": 7.854,
"step": 1024
},
{
"epoch": 0.36485914708829753,
"grad_norm": 23.54279327392578,
"learning_rate": 3.17687923049519e-05,
"loss": 46.5895,
"step": 2048
},
{
"epoch": 0.36485914708829753,
"eval_accuracy": 0.12475931011256204,
"eval_loss": 6.226956844329834,
"eval_runtime": 165.8237,
"eval_samples_per_second": 60.317,
"eval_steps_per_second": 7.544,
"step": 2048
},
{
"epoch": 0.7297182941765951,
"grad_norm": 26.13650894165039,
"learning_rate": 1.3528678304239403e-05,
"loss": 55.4762,
"step": 4096
},
{
"epoch": 0.7297182941765951,
"eval_accuracy": 0.2658144812875157,
"eval_loss": 4.172967433929443,
"eval_runtime": 161.3436,
"eval_samples_per_second": 61.992,
"eval_steps_per_second": 7.754,
"step": 4096
}
],
"logging_steps": 99999999,
"max_steps": 5614,
"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