Commit
•
540e23b
1
Parent(s):
71f7c6a
Upload folder using huggingface_hub
Browse files- checkpoint-1454/config.json +43 -0
- checkpoint-1454/merges.txt +0 -0
- checkpoint-1454/model.safetensors +3 -0
- checkpoint-1454/optimizer.pt +3 -0
- checkpoint-1454/rng_state.pth +3 -0
- checkpoint-1454/scheduler.pt +3 -0
- checkpoint-1454/special_tokens_map.json +6 -0
- checkpoint-1454/tokenizer.json +0 -0
- checkpoint-1454/tokenizer_config.json +20 -0
- checkpoint-1454/trainer_state.json +81 -0
- checkpoint-1454/training_args.bin +3 -0
- checkpoint-1454/vocab.json +0 -0
- checkpoint-727/config.json +43 -0
- checkpoint-727/merges.txt +0 -0
- checkpoint-727/model.safetensors +3 -0
- checkpoint-727/optimizer.pt +3 -0
- checkpoint-727/rng_state.pth +3 -0
- checkpoint-727/scheduler.pt +3 -0
- checkpoint-727/special_tokens_map.json +6 -0
- checkpoint-727/tokenizer.json +0 -0
- checkpoint-727/tokenizer_config.json +20 -0
- checkpoint-727/trainer_state.json +57 -0
- checkpoint-727/training_args.bin +3 -0
- checkpoint-727/vocab.json +0 -0
checkpoint-1454/config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-community/gpt2-medium",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"pad_token_id": 50256,
|
22 |
+
"predict_special_tokens": true,
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"reorder_and_upcast_attn": false,
|
25 |
+
"resid_pdrop": 0.1,
|
26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
27 |
+
"scale_attn_weights": true,
|
28 |
+
"summary_activation": null,
|
29 |
+
"summary_first_dropout": 0.1,
|
30 |
+
"summary_proj_to_labels": true,
|
31 |
+
"summary_type": "cls_index",
|
32 |
+
"summary_use_proj": true,
|
33 |
+
"task_specific_params": {
|
34 |
+
"text-generation": {
|
35 |
+
"do_sample": true,
|
36 |
+
"max_length": 50
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.44.0",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 50257
|
43 |
+
}
|
checkpoint-1454/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1454/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebfacb98fb57e9d940f2d25e7760f3e267f41b8b675da9d2dcd01952c9002aa2
|
3 |
+
size 1419331144
|
checkpoint-1454/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a725303fd96a57378ff422f3ba47aad30bf039ac16810a7b4f4685765194d9
|
3 |
+
size 2838846522
|
checkpoint-1454/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8340c9e6afd93664b1c1fe6e017e934daed48a33f08b5d03dca8f0711f59d3a8
|
3 |
+
size 14244
|
checkpoint-1454/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ca3ce1b58628a6183122df4c1a51864c74c6cc6e89cb30a9a04f163482fc8f2
|
3 |
+
size 1064
|
checkpoint-1454/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-1454/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1454/tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
+
}
|
checkpoint-1454/trainer_state.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1454,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.687757909215956,
|
13 |
+
"grad_norm": 8.139726638793945,
|
14 |
+
"learning_rate": 1.3122420907840441e-05,
|
15 |
+
"loss": 0.6433,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7663230240549829,
|
21 |
+
"eval_auc": 0.8559733108955907,
|
22 |
+
"eval_balanced_accuracy": 0.7664585270802888,
|
23 |
+
"eval_f1_macro": 0.7662063771026864,
|
24 |
+
"eval_f1_micro": 0.7663230240549829,
|
25 |
+
"eval_loss": 0.4740949869155884,
|
26 |
+
"eval_precision_macro": 0.7671146521133054,
|
27 |
+
"eval_precision_micro": 0.7663230240549829,
|
28 |
+
"eval_recall_macro": 0.7664585270802888,
|
29 |
+
"eval_recall_micro": 0.7663230240549829,
|
30 |
+
"eval_runtime": 3.136,
|
31 |
+
"eval_samples_per_second": 371.174,
|
32 |
+
"eval_steps_per_second": 6.059,
|
33 |
+
"step": 727
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.375515818431912,
|
37 |
+
"grad_norm": 10.305329322814941,
|
38 |
+
"learning_rate": 6.244841815680881e-06,
|
39 |
+
"loss": 0.4554,
|
40 |
+
"step": 1000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 2.0,
|
44 |
+
"eval_accuracy": 0.7783505154639175,
|
45 |
+
"eval_auc": 0.876533368761348,
|
46 |
+
"eval_balanced_accuracy": 0.7785483370975599,
|
47 |
+
"eval_f1_macro": 0.7780884595831217,
|
48 |
+
"eval_f1_micro": 0.7783505154639175,
|
49 |
+
"eval_loss": 0.457742840051651,
|
50 |
+
"eval_precision_macro": 0.780069758812616,
|
51 |
+
"eval_precision_micro": 0.7783505154639175,
|
52 |
+
"eval_recall_macro": 0.7785483370975599,
|
53 |
+
"eval_recall_micro": 0.7783505154639175,
|
54 |
+
"eval_runtime": 3.1343,
|
55 |
+
"eval_samples_per_second": 371.379,
|
56 |
+
"eval_steps_per_second": 6.062,
|
57 |
+
"step": 1454
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 500,
|
61 |
+
"max_steps": 1454,
|
62 |
+
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 2,
|
64 |
+
"save_steps": 500,
|
65 |
+
"stateful_callbacks": {
|
66 |
+
"TrainerControl": {
|
67 |
+
"args": {
|
68 |
+
"should_epoch_stop": false,
|
69 |
+
"should_evaluate": false,
|
70 |
+
"should_log": false,
|
71 |
+
"should_save": true,
|
72 |
+
"should_training_stop": true
|
73 |
+
},
|
74 |
+
"attributes": {}
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"total_flos": 4558235369914368.0,
|
78 |
+
"train_batch_size": 16,
|
79 |
+
"trial_name": null,
|
80 |
+
"trial_params": null
|
81 |
+
}
|
checkpoint-1454/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02d7b85704d74b4ccc22f2b729a44eb627e7b3a8fd3e9dfb612b9071fd616311
|
3 |
+
size 5304
|
checkpoint-1454/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-727/config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-community/gpt2-medium",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"pad_token_id": 50256,
|
22 |
+
"predict_special_tokens": true,
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"reorder_and_upcast_attn": false,
|
25 |
+
"resid_pdrop": 0.1,
|
26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
27 |
+
"scale_attn_weights": true,
|
28 |
+
"summary_activation": null,
|
29 |
+
"summary_first_dropout": 0.1,
|
30 |
+
"summary_proj_to_labels": true,
|
31 |
+
"summary_type": "cls_index",
|
32 |
+
"summary_use_proj": true,
|
33 |
+
"task_specific_params": {
|
34 |
+
"text-generation": {
|
35 |
+
"do_sample": true,
|
36 |
+
"max_length": 50
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.44.0",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 50257
|
43 |
+
}
|
checkpoint-727/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-727/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4001cabf4d9de4f3b32f1485351966596dcfd2e2dda7b41357b63d6c27a703f
|
3 |
+
size 1419331144
|
checkpoint-727/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a839c496f538afb6bf126daaeaaf694e1e24105c12b80f7324cbb148cc4150ea
|
3 |
+
size 2838846522
|
checkpoint-727/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43ded77a23dd8adc2bd59b56c64e169aaad9295dbb826a083c6404621a434fb6
|
3 |
+
size 14244
|
checkpoint-727/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6494f32da2fcb57933cf55aae07f5d58791d06b4a9922d1931ad95e1904a9af9
|
3 |
+
size 1064
|
checkpoint-727/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-727/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-727/tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
+
}
|
checkpoint-727/trainer_state.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 727,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.687757909215956,
|
13 |
+
"grad_norm": 8.139726638793945,
|
14 |
+
"learning_rate": 1.3122420907840441e-05,
|
15 |
+
"loss": 0.6433,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7663230240549829,
|
21 |
+
"eval_auc": 0.8559733108955907,
|
22 |
+
"eval_balanced_accuracy": 0.7664585270802888,
|
23 |
+
"eval_f1_macro": 0.7662063771026864,
|
24 |
+
"eval_f1_micro": 0.7663230240549829,
|
25 |
+
"eval_loss": 0.4740949869155884,
|
26 |
+
"eval_precision_macro": 0.7671146521133054,
|
27 |
+
"eval_precision_micro": 0.7663230240549829,
|
28 |
+
"eval_recall_macro": 0.7664585270802888,
|
29 |
+
"eval_recall_micro": 0.7663230240549829,
|
30 |
+
"eval_runtime": 3.136,
|
31 |
+
"eval_samples_per_second": 371.174,
|
32 |
+
"eval_steps_per_second": 6.059,
|
33 |
+
"step": 727
|
34 |
+
}
|
35 |
+
],
|
36 |
+
"logging_steps": 500,
|
37 |
+
"max_steps": 1454,
|
38 |
+
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 2,
|
40 |
+
"save_steps": 500,
|
41 |
+
"stateful_callbacks": {
|
42 |
+
"TrainerControl": {
|
43 |
+
"args": {
|
44 |
+
"should_epoch_stop": false,
|
45 |
+
"should_evaluate": false,
|
46 |
+
"should_log": false,
|
47 |
+
"should_save": true,
|
48 |
+
"should_training_stop": false
|
49 |
+
},
|
50 |
+
"attributes": {}
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"total_flos": 2284755226583040.0,
|
54 |
+
"train_batch_size": 16,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": null
|
57 |
+
}
|
checkpoint-727/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02d7b85704d74b4ccc22f2b729a44eb627e7b3a8fd3e9dfb612b9071fd616311
|
3 |
+
size 5304
|
checkpoint-727/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|