harishussain12
commited on
Commit
•
69c9f91
1
Parent(s):
63330f3
Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- checkpoint-4500/added_tokens.json +5 -0
- checkpoint-4500/config.json +46 -0
- checkpoint-4500/generation_config.json +6 -0
- checkpoint-4500/merges.txt +0 -0
- checkpoint-4500/model.safetensors +3 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/special_tokens_map.json +34 -0
- checkpoint-4500/tokenizer.json +0 -0
- checkpoint-4500/tokenizer_config.json +52 -0
- checkpoint-4500/trainer_state.json +663 -0
- checkpoint-4500/training_args.bin +3 -0
- checkpoint-4500/vocab.json +0 -0
- checkpoint-4731/added_tokens.json +5 -0
- checkpoint-4731/config.json +46 -0
- checkpoint-4731/generation_config.json +6 -0
- checkpoint-4731/merges.txt +0 -0
- checkpoint-4731/model.safetensors +3 -0
- checkpoint-4731/optimizer.pt +3 -0
- checkpoint-4731/rng_state.pth +3 -0
- checkpoint-4731/scheduler.pt +3 -0
- checkpoint-4731/special_tokens_map.json +34 -0
- checkpoint-4731/tokenizer.json +0 -0
- checkpoint-4731/tokenizer_config.json +52 -0
- checkpoint-4731/trainer_state.json +691 -0
- checkpoint-4731/training_args.bin +3 -0
- checkpoint-4731/vocab.json +0 -0
- config.json +46 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +34 -0
- tokenizer.json +0 -0
- tokenizer_config.json +52 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<C-Plus-Plus>": 50259,
|
3 |
+
"<C>": 50258,
|
4 |
+
"<pad>": 50257
|
5 |
+
}
|
checkpoint-4500/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<C-Plus-Plus>": 50259,
|
3 |
+
"<C>": 50258,
|
4 |
+
"<pad>": 50257
|
5 |
+
}
|
checkpoint-4500/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "abhinema/distillgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.47.1",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50260
|
46 |
+
}
|
checkpoint-4500/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.47.1"
|
6 |
+
}
|
checkpoint-4500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71f4c10d24c5e49a06ccb4a92cd3cd77b7c84023c1b677c8965b5d927c4712fe
|
3 |
+
size 327667144
|
checkpoint-4500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:496f2257e9345f4c24e09dee9e8ca54a2cef2559cc5cdba9f1cb15f96d7569ca
|
3 |
+
size 655382906
|
checkpoint-4500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:308fd07f939fdad591a88b93947c278bb7f25d7964a9179abbaeb8dae0c37056
|
3 |
+
size 14244
|
checkpoint-4500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50bc0d2ae4a3d270d0c6333137e1a6493b1efb235226ac0f1f0d6bb2c6497556
|
3 |
+
size 1064
|
checkpoint-4500/special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<C>",
|
4 |
+
"<C-Plus-Plus>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-4500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4500/tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<pad>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": "<C>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"50259": {
|
30 |
+
"content": "<C-Plus-Plus>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [
|
39 |
+
"<C>",
|
40 |
+
"<C-Plus-Plus>"
|
41 |
+
],
|
42 |
+
"bos_token": "<|endoftext|>",
|
43 |
+
"clean_up_tokenization_spaces": false,
|
44 |
+
"do_lower_case": false,
|
45 |
+
"eos_token": "<|endoftext|>",
|
46 |
+
"errors": "replace",
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"model_max_length": 1024,
|
49 |
+
"pad_token": "<pad>",
|
50 |
+
"tokenizer_class": "GPT2Tokenizer",
|
51 |
+
"unk_token": "<|endoftext|>"
|
52 |
+
}
|
checkpoint-4500/trainer_state.json
ADDED
@@ -0,0 +1,663 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.853519340519975,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03170577045022194,
|
13 |
+
"grad_norm": 1.268200397491455,
|
14 |
+
"learning_rate": 4.94715704924963e-05,
|
15 |
+
"loss": 3.4652,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06341154090044387,
|
20 |
+
"grad_norm": 0.5000430345535278,
|
21 |
+
"learning_rate": 4.8943140984992603e-05,
|
22 |
+
"loss": 0.7541,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09511731135066583,
|
27 |
+
"grad_norm": 0.5261800289154053,
|
28 |
+
"learning_rate": 4.8414711477488904e-05,
|
29 |
+
"loss": 0.644,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.12682308180088775,
|
34 |
+
"grad_norm": 0.4932628571987152,
|
35 |
+
"learning_rate": 4.788628196998521e-05,
|
36 |
+
"loss": 0.6921,
|
37 |
+
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.15852885225110971,
|
41 |
+
"grad_norm": 0.42867496609687805,
|
42 |
+
"learning_rate": 4.7357852462481505e-05,
|
43 |
+
"loss": 0.5897,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19023462270133165,
|
48 |
+
"grad_norm": 0.8850355744361877,
|
49 |
+
"learning_rate": 4.6829422954977806e-05,
|
50 |
+
"loss": 0.6959,
|
51 |
+
"step": 300
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2219403931515536,
|
55 |
+
"grad_norm": 0.5738270878791809,
|
56 |
+
"learning_rate": 4.630099344747411e-05,
|
57 |
+
"loss": 0.754,
|
58 |
+
"step": 350
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2536461636017755,
|
62 |
+
"grad_norm": 0.2961026728153229,
|
63 |
+
"learning_rate": 4.577256393997041e-05,
|
64 |
+
"loss": 0.6201,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2853519340519975,
|
69 |
+
"grad_norm": 0.35886821150779724,
|
70 |
+
"learning_rate": 4.5244134432466714e-05,
|
71 |
+
"loss": 0.5422,
|
72 |
+
"step": 450
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.31705770450221943,
|
76 |
+
"grad_norm": 0.45828256011009216,
|
77 |
+
"learning_rate": 4.4715704924963015e-05,
|
78 |
+
"loss": 0.6895,
|
79 |
+
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.34876347495244137,
|
83 |
+
"grad_norm": 0.40253156423568726,
|
84 |
+
"learning_rate": 4.4187275417459315e-05,
|
85 |
+
"loss": 0.5722,
|
86 |
+
"step": 550
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.3804692454026633,
|
90 |
+
"grad_norm": 0.55234295129776,
|
91 |
+
"learning_rate": 4.3658845909955616e-05,
|
92 |
+
"loss": 0.6205,
|
93 |
+
"step": 600
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.41217501585288524,
|
97 |
+
"grad_norm": 0.38063228130340576,
|
98 |
+
"learning_rate": 4.3130416402451916e-05,
|
99 |
+
"loss": 0.6161,
|
100 |
+
"step": 650
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4438807863031072,
|
104 |
+
"grad_norm": 0.8910940289497375,
|
105 |
+
"learning_rate": 4.260198689494822e-05,
|
106 |
+
"loss": 0.6756,
|
107 |
+
"step": 700
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4755865567533291,
|
111 |
+
"grad_norm": 0.569128692150116,
|
112 |
+
"learning_rate": 4.207355738744452e-05,
|
113 |
+
"loss": 0.5942,
|
114 |
+
"step": 750
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.507292327203551,
|
118 |
+
"grad_norm": 0.713485062122345,
|
119 |
+
"learning_rate": 4.154512787994082e-05,
|
120 |
+
"loss": 0.5872,
|
121 |
+
"step": 800
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5389980976537729,
|
125 |
+
"grad_norm": 0.547140896320343,
|
126 |
+
"learning_rate": 4.101669837243712e-05,
|
127 |
+
"loss": 0.6482,
|
128 |
+
"step": 850
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.570703868103995,
|
132 |
+
"grad_norm": 0.8154194355010986,
|
133 |
+
"learning_rate": 4.048826886493342e-05,
|
134 |
+
"loss": 0.5775,
|
135 |
+
"step": 900
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6024096385542169,
|
139 |
+
"grad_norm": 0.37084701657295227,
|
140 |
+
"learning_rate": 3.995983935742972e-05,
|
141 |
+
"loss": 0.5649,
|
142 |
+
"step": 950
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6341154090044389,
|
146 |
+
"grad_norm": 0.6335868835449219,
|
147 |
+
"learning_rate": 3.943140984992602e-05,
|
148 |
+
"loss": 0.5654,
|
149 |
+
"step": 1000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.6658211794546608,
|
153 |
+
"grad_norm": 0.3464125990867615,
|
154 |
+
"learning_rate": 3.890298034242232e-05,
|
155 |
+
"loss": 0.5236,
|
156 |
+
"step": 1050
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.6975269499048827,
|
160 |
+
"grad_norm": 0.3801315128803253,
|
161 |
+
"learning_rate": 3.837455083491862e-05,
|
162 |
+
"loss": 0.5876,
|
163 |
+
"step": 1100
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7292327203551047,
|
167 |
+
"grad_norm": 0.489006370306015,
|
168 |
+
"learning_rate": 3.784612132741492e-05,
|
169 |
+
"loss": 0.5639,
|
170 |
+
"step": 1150
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7609384908053266,
|
174 |
+
"grad_norm": 0.9908373951911926,
|
175 |
+
"learning_rate": 3.731769181991123e-05,
|
176 |
+
"loss": 0.6626,
|
177 |
+
"step": 1200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.7926442612555485,
|
181 |
+
"grad_norm": 0.39679229259490967,
|
182 |
+
"learning_rate": 3.678926231240752e-05,
|
183 |
+
"loss": 0.6259,
|
184 |
+
"step": 1250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8243500317057705,
|
188 |
+
"grad_norm": 0.3946998715400696,
|
189 |
+
"learning_rate": 3.626083280490383e-05,
|
190 |
+
"loss": 0.573,
|
191 |
+
"step": 1300
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8560558021559924,
|
195 |
+
"grad_norm": 0.41675782203674316,
|
196 |
+
"learning_rate": 3.573240329740013e-05,
|
197 |
+
"loss": 0.6568,
|
198 |
+
"step": 1350
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.8877615726062144,
|
202 |
+
"grad_norm": 0.2899385988712311,
|
203 |
+
"learning_rate": 3.5203973789896424e-05,
|
204 |
+
"loss": 0.5031,
|
205 |
+
"step": 1400
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9194673430564363,
|
209 |
+
"grad_norm": 0.8684162497520447,
|
210 |
+
"learning_rate": 3.467554428239273e-05,
|
211 |
+
"loss": 0.5836,
|
212 |
+
"step": 1450
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.9511731135066582,
|
216 |
+
"grad_norm": 0.9390568137168884,
|
217 |
+
"learning_rate": 3.414711477488903e-05,
|
218 |
+
"loss": 0.5832,
|
219 |
+
"step": 1500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.9828788839568802,
|
223 |
+
"grad_norm": 0.6241053342819214,
|
224 |
+
"learning_rate": 3.361868526738533e-05,
|
225 |
+
"loss": 0.6668,
|
226 |
+
"step": 1550
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.014584654407102,
|
230 |
+
"grad_norm": 0.43029874563217163,
|
231 |
+
"learning_rate": 3.309025575988163e-05,
|
232 |
+
"loss": 0.5516,
|
233 |
+
"step": 1600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.046290424857324,
|
237 |
+
"grad_norm": 0.3394105136394501,
|
238 |
+
"learning_rate": 3.2561826252377934e-05,
|
239 |
+
"loss": 0.5909,
|
240 |
+
"step": 1650
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.0779961953075459,
|
244 |
+
"grad_norm": 0.76275634765625,
|
245 |
+
"learning_rate": 3.2033396744874234e-05,
|
246 |
+
"loss": 0.5535,
|
247 |
+
"step": 1700
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.1097019657577678,
|
251 |
+
"grad_norm": 0.6357107162475586,
|
252 |
+
"learning_rate": 3.1504967237370535e-05,
|
253 |
+
"loss": 0.5632,
|
254 |
+
"step": 1750
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.1414077362079897,
|
258 |
+
"grad_norm": 0.3675929009914398,
|
259 |
+
"learning_rate": 3.097653772986684e-05,
|
260 |
+
"loss": 0.5744,
|
261 |
+
"step": 1800
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.1731135066582117,
|
265 |
+
"grad_norm": 0.3702389895915985,
|
266 |
+
"learning_rate": 3.0448108222363136e-05,
|
267 |
+
"loss": 0.6319,
|
268 |
+
"step": 1850
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.2048192771084336,
|
272 |
+
"grad_norm": 0.43757855892181396,
|
273 |
+
"learning_rate": 2.991967871485944e-05,
|
274 |
+
"loss": 0.5595,
|
275 |
+
"step": 1900
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.2365250475586556,
|
279 |
+
"grad_norm": 0.40859177708625793,
|
280 |
+
"learning_rate": 2.939124920735574e-05,
|
281 |
+
"loss": 0.5012,
|
282 |
+
"step": 1950
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.2682308180088775,
|
286 |
+
"grad_norm": 0.8433944582939148,
|
287 |
+
"learning_rate": 2.886281969985204e-05,
|
288 |
+
"loss": 0.6965,
|
289 |
+
"step": 2000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.2999365884590994,
|
293 |
+
"grad_norm": 0.2780860662460327,
|
294 |
+
"learning_rate": 2.833439019234834e-05,
|
295 |
+
"loss": 0.6852,
|
296 |
+
"step": 2050
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.3316423589093214,
|
300 |
+
"grad_norm": 0.4954093098640442,
|
301 |
+
"learning_rate": 2.7805960684844646e-05,
|
302 |
+
"loss": 0.5412,
|
303 |
+
"step": 2100
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.3633481293595433,
|
307 |
+
"grad_norm": 0.9253292083740234,
|
308 |
+
"learning_rate": 2.7277531177340943e-05,
|
309 |
+
"loss": 0.5013,
|
310 |
+
"step": 2150
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.3950538998097652,
|
314 |
+
"grad_norm": 0.5632855892181396,
|
315 |
+
"learning_rate": 2.6749101669837247e-05,
|
316 |
+
"loss": 0.5343,
|
317 |
+
"step": 2200
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.4267596702599874,
|
321 |
+
"grad_norm": 0.5401332974433899,
|
322 |
+
"learning_rate": 2.6220672162333547e-05,
|
323 |
+
"loss": 0.4798,
|
324 |
+
"step": 2250
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.4584654407102093,
|
328 |
+
"grad_norm": 0.6006923913955688,
|
329 |
+
"learning_rate": 2.5692242654829844e-05,
|
330 |
+
"loss": 0.5151,
|
331 |
+
"step": 2300
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.4901712111604313,
|
335 |
+
"grad_norm": 1.1926701068878174,
|
336 |
+
"learning_rate": 2.5163813147326148e-05,
|
337 |
+
"loss": 0.4518,
|
338 |
+
"step": 2350
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.521876981610653,
|
342 |
+
"grad_norm": 0.37329962849617004,
|
343 |
+
"learning_rate": 2.463538363982245e-05,
|
344 |
+
"loss": 0.5288,
|
345 |
+
"step": 2400
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.553582752060875,
|
349 |
+
"grad_norm": 0.49744054675102234,
|
350 |
+
"learning_rate": 2.410695413231875e-05,
|
351 |
+
"loss": 0.5408,
|
352 |
+
"step": 2450
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.5852885225110969,
|
356 |
+
"grad_norm": 0.4050131142139435,
|
357 |
+
"learning_rate": 2.357852462481505e-05,
|
358 |
+
"loss": 0.5719,
|
359 |
+
"step": 2500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.6169942929613188,
|
363 |
+
"grad_norm": 0.34927618503570557,
|
364 |
+
"learning_rate": 2.305009511731135e-05,
|
365 |
+
"loss": 0.4688,
|
366 |
+
"step": 2550
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.6487000634115407,
|
370 |
+
"grad_norm": 0.3404935896396637,
|
371 |
+
"learning_rate": 2.252166560980765e-05,
|
372 |
+
"loss": 0.5272,
|
373 |
+
"step": 2600
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.6804058338617627,
|
377 |
+
"grad_norm": 0.3460475504398346,
|
378 |
+
"learning_rate": 2.1993236102303955e-05,
|
379 |
+
"loss": 0.632,
|
380 |
+
"step": 2650
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.7121116043119848,
|
384 |
+
"grad_norm": 0.47324368357658386,
|
385 |
+
"learning_rate": 2.1464806594800255e-05,
|
386 |
+
"loss": 0.5488,
|
387 |
+
"step": 2700
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.7438173747622068,
|
391 |
+
"grad_norm": 0.7189714908599854,
|
392 |
+
"learning_rate": 2.0936377087296556e-05,
|
393 |
+
"loss": 0.5807,
|
394 |
+
"step": 2750
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.7755231452124287,
|
398 |
+
"grad_norm": 0.7753428816795349,
|
399 |
+
"learning_rate": 2.0407947579792857e-05,
|
400 |
+
"loss": 0.5803,
|
401 |
+
"step": 2800
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.8072289156626506,
|
405 |
+
"grad_norm": 0.32366201281547546,
|
406 |
+
"learning_rate": 1.9879518072289157e-05,
|
407 |
+
"loss": 0.5606,
|
408 |
+
"step": 2850
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.8389346861128726,
|
412 |
+
"grad_norm": 0.42843538522720337,
|
413 |
+
"learning_rate": 1.9351088564785458e-05,
|
414 |
+
"loss": 0.4822,
|
415 |
+
"step": 2900
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.8706404565630945,
|
419 |
+
"grad_norm": 0.8468919992446899,
|
420 |
+
"learning_rate": 1.882265905728176e-05,
|
421 |
+
"loss": 0.7272,
|
422 |
+
"step": 2950
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.9023462270133165,
|
426 |
+
"grad_norm": 1.0852563381195068,
|
427 |
+
"learning_rate": 1.8294229549778062e-05,
|
428 |
+
"loss": 0.5527,
|
429 |
+
"step": 3000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.9340519974635384,
|
433 |
+
"grad_norm": 0.41115501523017883,
|
434 |
+
"learning_rate": 1.776580004227436e-05,
|
435 |
+
"loss": 0.5216,
|
436 |
+
"step": 3050
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.9657577679137603,
|
440 |
+
"grad_norm": 0.4568431079387665,
|
441 |
+
"learning_rate": 1.7237370534770663e-05,
|
442 |
+
"loss": 0.5098,
|
443 |
+
"step": 3100
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.9974635383639823,
|
447 |
+
"grad_norm": 0.3544299602508545,
|
448 |
+
"learning_rate": 1.6708941027266964e-05,
|
449 |
+
"loss": 0.584,
|
450 |
+
"step": 3150
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.029169308814204,
|
454 |
+
"grad_norm": 0.8790750503540039,
|
455 |
+
"learning_rate": 1.6180511519763264e-05,
|
456 |
+
"loss": 0.43,
|
457 |
+
"step": 3200
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.060875079264426,
|
461 |
+
"grad_norm": 0.4061146080493927,
|
462 |
+
"learning_rate": 1.5652082012259565e-05,
|
463 |
+
"loss": 0.4727,
|
464 |
+
"step": 3250
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.092580849714648,
|
468 |
+
"grad_norm": 0.4029136002063751,
|
469 |
+
"learning_rate": 1.5123652504755867e-05,
|
470 |
+
"loss": 0.4701,
|
471 |
+
"step": 3300
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.12428662016487,
|
475 |
+
"grad_norm": 0.7732370495796204,
|
476 |
+
"learning_rate": 1.4595222997252168e-05,
|
477 |
+
"loss": 0.4954,
|
478 |
+
"step": 3350
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.1559923906150917,
|
482 |
+
"grad_norm": 0.7356324791908264,
|
483 |
+
"learning_rate": 1.4066793489748466e-05,
|
484 |
+
"loss": 0.6128,
|
485 |
+
"step": 3400
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.187698161065314,
|
489 |
+
"grad_norm": 0.8712078332901001,
|
490 |
+
"learning_rate": 1.353836398224477e-05,
|
491 |
+
"loss": 0.6239,
|
492 |
+
"step": 3450
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.2194039315155356,
|
496 |
+
"grad_norm": 0.44863361120224,
|
497 |
+
"learning_rate": 1.3009934474741071e-05,
|
498 |
+
"loss": 0.5606,
|
499 |
+
"step": 3500
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.251109701965758,
|
503 |
+
"grad_norm": 0.9408974051475525,
|
504 |
+
"learning_rate": 1.2481504967237371e-05,
|
505 |
+
"loss": 0.514,
|
506 |
+
"step": 3550
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.2828154724159795,
|
510 |
+
"grad_norm": 0.3982991874217987,
|
511 |
+
"learning_rate": 1.1953075459733672e-05,
|
512 |
+
"loss": 0.47,
|
513 |
+
"step": 3600
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.314521242866202,
|
517 |
+
"grad_norm": 0.4143155813217163,
|
518 |
+
"learning_rate": 1.1424645952229973e-05,
|
519 |
+
"loss": 0.5677,
|
520 |
+
"step": 3650
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 2.3462270133164234,
|
524 |
+
"grad_norm": 0.31523430347442627,
|
525 |
+
"learning_rate": 1.0896216444726275e-05,
|
526 |
+
"loss": 0.5579,
|
527 |
+
"step": 3700
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 2.3779327837666457,
|
531 |
+
"grad_norm": 0.41940435767173767,
|
532 |
+
"learning_rate": 1.0367786937222575e-05,
|
533 |
+
"loss": 0.5204,
|
534 |
+
"step": 3750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.4096385542168672,
|
538 |
+
"grad_norm": 0.7688931226730347,
|
539 |
+
"learning_rate": 9.839357429718876e-06,
|
540 |
+
"loss": 0.5144,
|
541 |
+
"step": 3800
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.4413443246670896,
|
545 |
+
"grad_norm": 0.3608909845352173,
|
546 |
+
"learning_rate": 9.310927922215176e-06,
|
547 |
+
"loss": 0.4891,
|
548 |
+
"step": 3850
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.473050095117311,
|
552 |
+
"grad_norm": 0.47781404852867126,
|
553 |
+
"learning_rate": 8.782498414711479e-06,
|
554 |
+
"loss": 0.4892,
|
555 |
+
"step": 3900
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 2.5047558655675335,
|
559 |
+
"grad_norm": 0.3204675316810608,
|
560 |
+
"learning_rate": 8.254068907207779e-06,
|
561 |
+
"loss": 0.5816,
|
562 |
+
"step": 3950
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 2.536461636017755,
|
566 |
+
"grad_norm": 0.806425929069519,
|
567 |
+
"learning_rate": 7.72563939970408e-06,
|
568 |
+
"loss": 0.5725,
|
569 |
+
"step": 4000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 2.5681674064679774,
|
573 |
+
"grad_norm": 0.8784732818603516,
|
574 |
+
"learning_rate": 7.197209892200381e-06,
|
575 |
+
"loss": 0.63,
|
576 |
+
"step": 4050
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 2.599873176918199,
|
580 |
+
"grad_norm": 0.26710501313209534,
|
581 |
+
"learning_rate": 6.6687803846966825e-06,
|
582 |
+
"loss": 0.4984,
|
583 |
+
"step": 4100
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 2.6315789473684212,
|
587 |
+
"grad_norm": 0.46410611271858215,
|
588 |
+
"learning_rate": 6.140350877192982e-06,
|
589 |
+
"loss": 0.5894,
|
590 |
+
"step": 4150
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.6632847178186427,
|
594 |
+
"grad_norm": 0.39962610602378845,
|
595 |
+
"learning_rate": 5.6119213696892836e-06,
|
596 |
+
"loss": 0.5719,
|
597 |
+
"step": 4200
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 2.694990488268865,
|
601 |
+
"grad_norm": 0.42166388034820557,
|
602 |
+
"learning_rate": 5.083491862185585e-06,
|
603 |
+
"loss": 0.611,
|
604 |
+
"step": 4250
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 2.7266962587190866,
|
608 |
+
"grad_norm": 0.3567692041397095,
|
609 |
+
"learning_rate": 4.5550623546818855e-06,
|
610 |
+
"loss": 0.536,
|
611 |
+
"step": 4300
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 2.758402029169309,
|
615 |
+
"grad_norm": 0.7851996421813965,
|
616 |
+
"learning_rate": 4.026632847178187e-06,
|
617 |
+
"loss": 0.5243,
|
618 |
+
"step": 4350
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 2.7901077996195305,
|
622 |
+
"grad_norm": 0.49054574966430664,
|
623 |
+
"learning_rate": 3.498203339674488e-06,
|
624 |
+
"loss": 0.4414,
|
625 |
+
"step": 4400
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 2.821813570069753,
|
629 |
+
"grad_norm": 0.3000207841396332,
|
630 |
+
"learning_rate": 2.9697738321707884e-06,
|
631 |
+
"loss": 0.4498,
|
632 |
+
"step": 4450
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.853519340519975,
|
636 |
+
"grad_norm": 0.7114095091819763,
|
637 |
+
"learning_rate": 2.4413443246670898e-06,
|
638 |
+
"loss": 0.5504,
|
639 |
+
"step": 4500
|
640 |
+
}
|
641 |
+
],
|
642 |
+
"logging_steps": 50,
|
643 |
+
"max_steps": 4731,
|
644 |
+
"num_input_tokens_seen": 0,
|
645 |
+
"num_train_epochs": 3,
|
646 |
+
"save_steps": 500,
|
647 |
+
"stateful_callbacks": {
|
648 |
+
"TrainerControl": {
|
649 |
+
"args": {
|
650 |
+
"should_epoch_stop": false,
|
651 |
+
"should_evaluate": false,
|
652 |
+
"should_log": false,
|
653 |
+
"should_save": true,
|
654 |
+
"should_training_stop": false
|
655 |
+
},
|
656 |
+
"attributes": {}
|
657 |
+
}
|
658 |
+
},
|
659 |
+
"total_flos": 2351409458577408.0,
|
660 |
+
"train_batch_size": 4,
|
661 |
+
"trial_name": null,
|
662 |
+
"trial_params": null
|
663 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae0827d776cdc0cdb487f464a3caf81e458ff5f4615c2d023ec38a4e57a539cf
|
3 |
+
size 5240
|
checkpoint-4500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4731/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<C-Plus-Plus>": 50259,
|
3 |
+
"<C>": 50258,
|
4 |
+
"<pad>": 50257
|
5 |
+
}
|
checkpoint-4731/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "abhinema/distillgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.47.1",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50260
|
46 |
+
}
|
checkpoint-4731/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.47.1"
|
6 |
+
}
|
checkpoint-4731/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4731/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d013aac25e8642699c549de22bc9c1d4cf6f70178cb0c4a42dbbb5df982405a3
|
3 |
+
size 327667144
|
checkpoint-4731/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc4ec799aafbfb76b797c23e5542bf0dded0d4652342f84a4c18bc8d8a022710
|
3 |
+
size 655382906
|
checkpoint-4731/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27e97b29a76717a0089e7831ee223224578e71551f5e6472d6147e2b8e395ae3
|
3 |
+
size 14244
|
checkpoint-4731/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb1e5f56db38b8325e7dbc1394998aa9fa153404486cb734ca0ad4044f0c0899
|
3 |
+
size 1064
|
checkpoint-4731/special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<C>",
|
4 |
+
"<C-Plus-Plus>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-4731/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4731/tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<pad>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": "<C>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"50259": {
|
30 |
+
"content": "<C-Plus-Plus>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [
|
39 |
+
"<C>",
|
40 |
+
"<C-Plus-Plus>"
|
41 |
+
],
|
42 |
+
"bos_token": "<|endoftext|>",
|
43 |
+
"clean_up_tokenization_spaces": false,
|
44 |
+
"do_lower_case": false,
|
45 |
+
"eos_token": "<|endoftext|>",
|
46 |
+
"errors": "replace",
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"model_max_length": 1024,
|
49 |
+
"pad_token": "<pad>",
|
50 |
+
"tokenizer_class": "GPT2Tokenizer",
|
51 |
+
"unk_token": "<|endoftext|>"
|
52 |
+
}
|
checkpoint-4731/trainer_state.json
ADDED
@@ -0,0 +1,691 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4731,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03170577045022194,
|
13 |
+
"grad_norm": 1.268200397491455,
|
14 |
+
"learning_rate": 4.94715704924963e-05,
|
15 |
+
"loss": 3.4652,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06341154090044387,
|
20 |
+
"grad_norm": 0.5000430345535278,
|
21 |
+
"learning_rate": 4.8943140984992603e-05,
|
22 |
+
"loss": 0.7541,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09511731135066583,
|
27 |
+
"grad_norm": 0.5261800289154053,
|
28 |
+
"learning_rate": 4.8414711477488904e-05,
|
29 |
+
"loss": 0.644,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.12682308180088775,
|
34 |
+
"grad_norm": 0.4932628571987152,
|
35 |
+
"learning_rate": 4.788628196998521e-05,
|
36 |
+
"loss": 0.6921,
|
37 |
+
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.15852885225110971,
|
41 |
+
"grad_norm": 0.42867496609687805,
|
42 |
+
"learning_rate": 4.7357852462481505e-05,
|
43 |
+
"loss": 0.5897,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19023462270133165,
|
48 |
+
"grad_norm": 0.8850355744361877,
|
49 |
+
"learning_rate": 4.6829422954977806e-05,
|
50 |
+
"loss": 0.6959,
|
51 |
+
"step": 300
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2219403931515536,
|
55 |
+
"grad_norm": 0.5738270878791809,
|
56 |
+
"learning_rate": 4.630099344747411e-05,
|
57 |
+
"loss": 0.754,
|
58 |
+
"step": 350
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2536461636017755,
|
62 |
+
"grad_norm": 0.2961026728153229,
|
63 |
+
"learning_rate": 4.577256393997041e-05,
|
64 |
+
"loss": 0.6201,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2853519340519975,
|
69 |
+
"grad_norm": 0.35886821150779724,
|
70 |
+
"learning_rate": 4.5244134432466714e-05,
|
71 |
+
"loss": 0.5422,
|
72 |
+
"step": 450
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.31705770450221943,
|
76 |
+
"grad_norm": 0.45828256011009216,
|
77 |
+
"learning_rate": 4.4715704924963015e-05,
|
78 |
+
"loss": 0.6895,
|
79 |
+
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.34876347495244137,
|
83 |
+
"grad_norm": 0.40253156423568726,
|
84 |
+
"learning_rate": 4.4187275417459315e-05,
|
85 |
+
"loss": 0.5722,
|
86 |
+
"step": 550
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.3804692454026633,
|
90 |
+
"grad_norm": 0.55234295129776,
|
91 |
+
"learning_rate": 4.3658845909955616e-05,
|
92 |
+
"loss": 0.6205,
|
93 |
+
"step": 600
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.41217501585288524,
|
97 |
+
"grad_norm": 0.38063228130340576,
|
98 |
+
"learning_rate": 4.3130416402451916e-05,
|
99 |
+
"loss": 0.6161,
|
100 |
+
"step": 650
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4438807863031072,
|
104 |
+
"grad_norm": 0.8910940289497375,
|
105 |
+
"learning_rate": 4.260198689494822e-05,
|
106 |
+
"loss": 0.6756,
|
107 |
+
"step": 700
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4755865567533291,
|
111 |
+
"grad_norm": 0.569128692150116,
|
112 |
+
"learning_rate": 4.207355738744452e-05,
|
113 |
+
"loss": 0.5942,
|
114 |
+
"step": 750
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.507292327203551,
|
118 |
+
"grad_norm": 0.713485062122345,
|
119 |
+
"learning_rate": 4.154512787994082e-05,
|
120 |
+
"loss": 0.5872,
|
121 |
+
"step": 800
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5389980976537729,
|
125 |
+
"grad_norm": 0.547140896320343,
|
126 |
+
"learning_rate": 4.101669837243712e-05,
|
127 |
+
"loss": 0.6482,
|
128 |
+
"step": 850
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.570703868103995,
|
132 |
+
"grad_norm": 0.8154194355010986,
|
133 |
+
"learning_rate": 4.048826886493342e-05,
|
134 |
+
"loss": 0.5775,
|
135 |
+
"step": 900
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6024096385542169,
|
139 |
+
"grad_norm": 0.37084701657295227,
|
140 |
+
"learning_rate": 3.995983935742972e-05,
|
141 |
+
"loss": 0.5649,
|
142 |
+
"step": 950
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6341154090044389,
|
146 |
+
"grad_norm": 0.6335868835449219,
|
147 |
+
"learning_rate": 3.943140984992602e-05,
|
148 |
+
"loss": 0.5654,
|
149 |
+
"step": 1000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.6658211794546608,
|
153 |
+
"grad_norm": 0.3464125990867615,
|
154 |
+
"learning_rate": 3.890298034242232e-05,
|
155 |
+
"loss": 0.5236,
|
156 |
+
"step": 1050
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.6975269499048827,
|
160 |
+
"grad_norm": 0.3801315128803253,
|
161 |
+
"learning_rate": 3.837455083491862e-05,
|
162 |
+
"loss": 0.5876,
|
163 |
+
"step": 1100
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7292327203551047,
|
167 |
+
"grad_norm": 0.489006370306015,
|
168 |
+
"learning_rate": 3.784612132741492e-05,
|
169 |
+
"loss": 0.5639,
|
170 |
+
"step": 1150
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7609384908053266,
|
174 |
+
"grad_norm": 0.9908373951911926,
|
175 |
+
"learning_rate": 3.731769181991123e-05,
|
176 |
+
"loss": 0.6626,
|
177 |
+
"step": 1200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.7926442612555485,
|
181 |
+
"grad_norm": 0.39679229259490967,
|
182 |
+
"learning_rate": 3.678926231240752e-05,
|
183 |
+
"loss": 0.6259,
|
184 |
+
"step": 1250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8243500317057705,
|
188 |
+
"grad_norm": 0.3946998715400696,
|
189 |
+
"learning_rate": 3.626083280490383e-05,
|
190 |
+
"loss": 0.573,
|
191 |
+
"step": 1300
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8560558021559924,
|
195 |
+
"grad_norm": 0.41675782203674316,
|
196 |
+
"learning_rate": 3.573240329740013e-05,
|
197 |
+
"loss": 0.6568,
|
198 |
+
"step": 1350
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.8877615726062144,
|
202 |
+
"grad_norm": 0.2899385988712311,
|
203 |
+
"learning_rate": 3.5203973789896424e-05,
|
204 |
+
"loss": 0.5031,
|
205 |
+
"step": 1400
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9194673430564363,
|
209 |
+
"grad_norm": 0.8684162497520447,
|
210 |
+
"learning_rate": 3.467554428239273e-05,
|
211 |
+
"loss": 0.5836,
|
212 |
+
"step": 1450
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.9511731135066582,
|
216 |
+
"grad_norm": 0.9390568137168884,
|
217 |
+
"learning_rate": 3.414711477488903e-05,
|
218 |
+
"loss": 0.5832,
|
219 |
+
"step": 1500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.9828788839568802,
|
223 |
+
"grad_norm": 0.6241053342819214,
|
224 |
+
"learning_rate": 3.361868526738533e-05,
|
225 |
+
"loss": 0.6668,
|
226 |
+
"step": 1550
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.014584654407102,
|
230 |
+
"grad_norm": 0.43029874563217163,
|
231 |
+
"learning_rate": 3.309025575988163e-05,
|
232 |
+
"loss": 0.5516,
|
233 |
+
"step": 1600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.046290424857324,
|
237 |
+
"grad_norm": 0.3394105136394501,
|
238 |
+
"learning_rate": 3.2561826252377934e-05,
|
239 |
+
"loss": 0.5909,
|
240 |
+
"step": 1650
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.0779961953075459,
|
244 |
+
"grad_norm": 0.76275634765625,
|
245 |
+
"learning_rate": 3.2033396744874234e-05,
|
246 |
+
"loss": 0.5535,
|
247 |
+
"step": 1700
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.1097019657577678,
|
251 |
+
"grad_norm": 0.6357107162475586,
|
252 |
+
"learning_rate": 3.1504967237370535e-05,
|
253 |
+
"loss": 0.5632,
|
254 |
+
"step": 1750
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.1414077362079897,
|
258 |
+
"grad_norm": 0.3675929009914398,
|
259 |
+
"learning_rate": 3.097653772986684e-05,
|
260 |
+
"loss": 0.5744,
|
261 |
+
"step": 1800
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.1731135066582117,
|
265 |
+
"grad_norm": 0.3702389895915985,
|
266 |
+
"learning_rate": 3.0448108222363136e-05,
|
267 |
+
"loss": 0.6319,
|
268 |
+
"step": 1850
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.2048192771084336,
|
272 |
+
"grad_norm": 0.43757855892181396,
|
273 |
+
"learning_rate": 2.991967871485944e-05,
|
274 |
+
"loss": 0.5595,
|
275 |
+
"step": 1900
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.2365250475586556,
|
279 |
+
"grad_norm": 0.40859177708625793,
|
280 |
+
"learning_rate": 2.939124920735574e-05,
|
281 |
+
"loss": 0.5012,
|
282 |
+
"step": 1950
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.2682308180088775,
|
286 |
+
"grad_norm": 0.8433944582939148,
|
287 |
+
"learning_rate": 2.886281969985204e-05,
|
288 |
+
"loss": 0.6965,
|
289 |
+
"step": 2000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.2999365884590994,
|
293 |
+
"grad_norm": 0.2780860662460327,
|
294 |
+
"learning_rate": 2.833439019234834e-05,
|
295 |
+
"loss": 0.6852,
|
296 |
+
"step": 2050
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.3316423589093214,
|
300 |
+
"grad_norm": 0.4954093098640442,
|
301 |
+
"learning_rate": 2.7805960684844646e-05,
|
302 |
+
"loss": 0.5412,
|
303 |
+
"step": 2100
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.3633481293595433,
|
307 |
+
"grad_norm": 0.9253292083740234,
|
308 |
+
"learning_rate": 2.7277531177340943e-05,
|
309 |
+
"loss": 0.5013,
|
310 |
+
"step": 2150
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.3950538998097652,
|
314 |
+
"grad_norm": 0.5632855892181396,
|
315 |
+
"learning_rate": 2.6749101669837247e-05,
|
316 |
+
"loss": 0.5343,
|
317 |
+
"step": 2200
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.4267596702599874,
|
321 |
+
"grad_norm": 0.5401332974433899,
|
322 |
+
"learning_rate": 2.6220672162333547e-05,
|
323 |
+
"loss": 0.4798,
|
324 |
+
"step": 2250
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.4584654407102093,
|
328 |
+
"grad_norm": 0.6006923913955688,
|
329 |
+
"learning_rate": 2.5692242654829844e-05,
|
330 |
+
"loss": 0.5151,
|
331 |
+
"step": 2300
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.4901712111604313,
|
335 |
+
"grad_norm": 1.1926701068878174,
|
336 |
+
"learning_rate": 2.5163813147326148e-05,
|
337 |
+
"loss": 0.4518,
|
338 |
+
"step": 2350
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.521876981610653,
|
342 |
+
"grad_norm": 0.37329962849617004,
|
343 |
+
"learning_rate": 2.463538363982245e-05,
|
344 |
+
"loss": 0.5288,
|
345 |
+
"step": 2400
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.553582752060875,
|
349 |
+
"grad_norm": 0.49744054675102234,
|
350 |
+
"learning_rate": 2.410695413231875e-05,
|
351 |
+
"loss": 0.5408,
|
352 |
+
"step": 2450
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.5852885225110969,
|
356 |
+
"grad_norm": 0.4050131142139435,
|
357 |
+
"learning_rate": 2.357852462481505e-05,
|
358 |
+
"loss": 0.5719,
|
359 |
+
"step": 2500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.6169942929613188,
|
363 |
+
"grad_norm": 0.34927618503570557,
|
364 |
+
"learning_rate": 2.305009511731135e-05,
|
365 |
+
"loss": 0.4688,
|
366 |
+
"step": 2550
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.6487000634115407,
|
370 |
+
"grad_norm": 0.3404935896396637,
|
371 |
+
"learning_rate": 2.252166560980765e-05,
|
372 |
+
"loss": 0.5272,
|
373 |
+
"step": 2600
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.6804058338617627,
|
377 |
+
"grad_norm": 0.3460475504398346,
|
378 |
+
"learning_rate": 2.1993236102303955e-05,
|
379 |
+
"loss": 0.632,
|
380 |
+
"step": 2650
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.7121116043119848,
|
384 |
+
"grad_norm": 0.47324368357658386,
|
385 |
+
"learning_rate": 2.1464806594800255e-05,
|
386 |
+
"loss": 0.5488,
|
387 |
+
"step": 2700
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.7438173747622068,
|
391 |
+
"grad_norm": 0.7189714908599854,
|
392 |
+
"learning_rate": 2.0936377087296556e-05,
|
393 |
+
"loss": 0.5807,
|
394 |
+
"step": 2750
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.7755231452124287,
|
398 |
+
"grad_norm": 0.7753428816795349,
|
399 |
+
"learning_rate": 2.0407947579792857e-05,
|
400 |
+
"loss": 0.5803,
|
401 |
+
"step": 2800
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.8072289156626506,
|
405 |
+
"grad_norm": 0.32366201281547546,
|
406 |
+
"learning_rate": 1.9879518072289157e-05,
|
407 |
+
"loss": 0.5606,
|
408 |
+
"step": 2850
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.8389346861128726,
|
412 |
+
"grad_norm": 0.42843538522720337,
|
413 |
+
"learning_rate": 1.9351088564785458e-05,
|
414 |
+
"loss": 0.4822,
|
415 |
+
"step": 2900
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.8706404565630945,
|
419 |
+
"grad_norm": 0.8468919992446899,
|
420 |
+
"learning_rate": 1.882265905728176e-05,
|
421 |
+
"loss": 0.7272,
|
422 |
+
"step": 2950
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.9023462270133165,
|
426 |
+
"grad_norm": 1.0852563381195068,
|
427 |
+
"learning_rate": 1.8294229549778062e-05,
|
428 |
+
"loss": 0.5527,
|
429 |
+
"step": 3000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.9340519974635384,
|
433 |
+
"grad_norm": 0.41115501523017883,
|
434 |
+
"learning_rate": 1.776580004227436e-05,
|
435 |
+
"loss": 0.5216,
|
436 |
+
"step": 3050
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.9657577679137603,
|
440 |
+
"grad_norm": 0.4568431079387665,
|
441 |
+
"learning_rate": 1.7237370534770663e-05,
|
442 |
+
"loss": 0.5098,
|
443 |
+
"step": 3100
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.9974635383639823,
|
447 |
+
"grad_norm": 0.3544299602508545,
|
448 |
+
"learning_rate": 1.6708941027266964e-05,
|
449 |
+
"loss": 0.584,
|
450 |
+
"step": 3150
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.029169308814204,
|
454 |
+
"grad_norm": 0.8790750503540039,
|
455 |
+
"learning_rate": 1.6180511519763264e-05,
|
456 |
+
"loss": 0.43,
|
457 |
+
"step": 3200
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.060875079264426,
|
461 |
+
"grad_norm": 0.4061146080493927,
|
462 |
+
"learning_rate": 1.5652082012259565e-05,
|
463 |
+
"loss": 0.4727,
|
464 |
+
"step": 3250
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.092580849714648,
|
468 |
+
"grad_norm": 0.4029136002063751,
|
469 |
+
"learning_rate": 1.5123652504755867e-05,
|
470 |
+
"loss": 0.4701,
|
471 |
+
"step": 3300
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.12428662016487,
|
475 |
+
"grad_norm": 0.7732370495796204,
|
476 |
+
"learning_rate": 1.4595222997252168e-05,
|
477 |
+
"loss": 0.4954,
|
478 |
+
"step": 3350
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.1559923906150917,
|
482 |
+
"grad_norm": 0.7356324791908264,
|
483 |
+
"learning_rate": 1.4066793489748466e-05,
|
484 |
+
"loss": 0.6128,
|
485 |
+
"step": 3400
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.187698161065314,
|
489 |
+
"grad_norm": 0.8712078332901001,
|
490 |
+
"learning_rate": 1.353836398224477e-05,
|
491 |
+
"loss": 0.6239,
|
492 |
+
"step": 3450
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.2194039315155356,
|
496 |
+
"grad_norm": 0.44863361120224,
|
497 |
+
"learning_rate": 1.3009934474741071e-05,
|
498 |
+
"loss": 0.5606,
|
499 |
+
"step": 3500
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.251109701965758,
|
503 |
+
"grad_norm": 0.9408974051475525,
|
504 |
+
"learning_rate": 1.2481504967237371e-05,
|
505 |
+
"loss": 0.514,
|
506 |
+
"step": 3550
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.2828154724159795,
|
510 |
+
"grad_norm": 0.3982991874217987,
|
511 |
+
"learning_rate": 1.1953075459733672e-05,
|
512 |
+
"loss": 0.47,
|
513 |
+
"step": 3600
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.314521242866202,
|
517 |
+
"grad_norm": 0.4143155813217163,
|
518 |
+
"learning_rate": 1.1424645952229973e-05,
|
519 |
+
"loss": 0.5677,
|
520 |
+
"step": 3650
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 2.3462270133164234,
|
524 |
+
"grad_norm": 0.31523430347442627,
|
525 |
+
"learning_rate": 1.0896216444726275e-05,
|
526 |
+
"loss": 0.5579,
|
527 |
+
"step": 3700
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 2.3779327837666457,
|
531 |
+
"grad_norm": 0.41940435767173767,
|
532 |
+
"learning_rate": 1.0367786937222575e-05,
|
533 |
+
"loss": 0.5204,
|
534 |
+
"step": 3750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.4096385542168672,
|
538 |
+
"grad_norm": 0.7688931226730347,
|
539 |
+
"learning_rate": 9.839357429718876e-06,
|
540 |
+
"loss": 0.5144,
|
541 |
+
"step": 3800
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.4413443246670896,
|
545 |
+
"grad_norm": 0.3608909845352173,
|
546 |
+
"learning_rate": 9.310927922215176e-06,
|
547 |
+
"loss": 0.4891,
|
548 |
+
"step": 3850
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.473050095117311,
|
552 |
+
"grad_norm": 0.47781404852867126,
|
553 |
+
"learning_rate": 8.782498414711479e-06,
|
554 |
+
"loss": 0.4892,
|
555 |
+
"step": 3900
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 2.5047558655675335,
|
559 |
+
"grad_norm": 0.3204675316810608,
|
560 |
+
"learning_rate": 8.254068907207779e-06,
|
561 |
+
"loss": 0.5816,
|
562 |
+
"step": 3950
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 2.536461636017755,
|
566 |
+
"grad_norm": 0.806425929069519,
|
567 |
+
"learning_rate": 7.72563939970408e-06,
|
568 |
+
"loss": 0.5725,
|
569 |
+
"step": 4000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 2.5681674064679774,
|
573 |
+
"grad_norm": 0.8784732818603516,
|
574 |
+
"learning_rate": 7.197209892200381e-06,
|
575 |
+
"loss": 0.63,
|
576 |
+
"step": 4050
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 2.599873176918199,
|
580 |
+
"grad_norm": 0.26710501313209534,
|
581 |
+
"learning_rate": 6.6687803846966825e-06,
|
582 |
+
"loss": 0.4984,
|
583 |
+
"step": 4100
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 2.6315789473684212,
|
587 |
+
"grad_norm": 0.46410611271858215,
|
588 |
+
"learning_rate": 6.140350877192982e-06,
|
589 |
+
"loss": 0.5894,
|
590 |
+
"step": 4150
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.6632847178186427,
|
594 |
+
"grad_norm": 0.39962610602378845,
|
595 |
+
"learning_rate": 5.6119213696892836e-06,
|
596 |
+
"loss": 0.5719,
|
597 |
+
"step": 4200
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 2.694990488268865,
|
601 |
+
"grad_norm": 0.42166388034820557,
|
602 |
+
"learning_rate": 5.083491862185585e-06,
|
603 |
+
"loss": 0.611,
|
604 |
+
"step": 4250
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 2.7266962587190866,
|
608 |
+
"grad_norm": 0.3567692041397095,
|
609 |
+
"learning_rate": 4.5550623546818855e-06,
|
610 |
+
"loss": 0.536,
|
611 |
+
"step": 4300
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 2.758402029169309,
|
615 |
+
"grad_norm": 0.7851996421813965,
|
616 |
+
"learning_rate": 4.026632847178187e-06,
|
617 |
+
"loss": 0.5243,
|
618 |
+
"step": 4350
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 2.7901077996195305,
|
622 |
+
"grad_norm": 0.49054574966430664,
|
623 |
+
"learning_rate": 3.498203339674488e-06,
|
624 |
+
"loss": 0.4414,
|
625 |
+
"step": 4400
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 2.821813570069753,
|
629 |
+
"grad_norm": 0.3000207841396332,
|
630 |
+
"learning_rate": 2.9697738321707884e-06,
|
631 |
+
"loss": 0.4498,
|
632 |
+
"step": 4450
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.853519340519975,
|
636 |
+
"grad_norm": 0.7114095091819763,
|
637 |
+
"learning_rate": 2.4413443246670898e-06,
|
638 |
+
"loss": 0.5504,
|
639 |
+
"step": 4500
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 2.8852251109701967,
|
643 |
+
"grad_norm": 0.9974462985992432,
|
644 |
+
"learning_rate": 1.9129148171633903e-06,
|
645 |
+
"loss": 0.6545,
|
646 |
+
"step": 4550
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 2.9169308814204187,
|
650 |
+
"grad_norm": 0.339517205953598,
|
651 |
+
"learning_rate": 1.3844853096596915e-06,
|
652 |
+
"loss": 0.482,
|
653 |
+
"step": 4600
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 2.9486366518706406,
|
657 |
+
"grad_norm": 0.3462202548980713,
|
658 |
+
"learning_rate": 8.560558021559924e-07,
|
659 |
+
"loss": 0.5029,
|
660 |
+
"step": 4650
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.9803424223208625,
|
664 |
+
"grad_norm": 0.6948489546775818,
|
665 |
+
"learning_rate": 3.276262946522934e-07,
|
666 |
+
"loss": 0.4969,
|
667 |
+
"step": 4700
|
668 |
+
}
|
669 |
+
],
|
670 |
+
"logging_steps": 50,
|
671 |
+
"max_steps": 4731,
|
672 |
+
"num_input_tokens_seen": 0,
|
673 |
+
"num_train_epochs": 3,
|
674 |
+
"save_steps": 500,
|
675 |
+
"stateful_callbacks": {
|
676 |
+
"TrainerControl": {
|
677 |
+
"args": {
|
678 |
+
"should_epoch_stop": false,
|
679 |
+
"should_evaluate": false,
|
680 |
+
"should_log": false,
|
681 |
+
"should_save": true,
|
682 |
+
"should_training_stop": true
|
683 |
+
},
|
684 |
+
"attributes": {}
|
685 |
+
}
|
686 |
+
},
|
687 |
+
"total_flos": 2471997908975616.0,
|
688 |
+
"train_batch_size": 4,
|
689 |
+
"trial_name": null,
|
690 |
+
"trial_params": null
|
691 |
+
}
|
checkpoint-4731/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae0827d776cdc0cdb487f464a3caf81e458ff5f4615c2d023ec38a4e57a539cf
|
3 |
+
size 5240
|
checkpoint-4731/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "abhinema/distillgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.47.1",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50260
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.47.1"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d013aac25e8642699c549de22bc9c1d4cf6f70178cb0c4a42dbbb5df982405a3
|
3 |
+
size 327667144
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<C>",
|
4 |
+
"<C-Plus-Plus>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<pad>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": "<C>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"50259": {
|
30 |
+
"content": "<C-Plus-Plus>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [
|
39 |
+
"<C>",
|
40 |
+
"<C-Plus-Plus>"
|
41 |
+
],
|
42 |
+
"bos_token": "<|endoftext|>",
|
43 |
+
"clean_up_tokenization_spaces": false,
|
44 |
+
"do_lower_case": false,
|
45 |
+
"eos_token": "<|endoftext|>",
|
46 |
+
"errors": "replace",
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"model_max_length": 1024,
|
49 |
+
"pad_token": "<pad>",
|
50 |
+
"tokenizer_class": "GPT2Tokenizer",
|
51 |
+
"unk_token": "<|endoftext|>"
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae0827d776cdc0cdb487f464a3caf81e458ff5f4615c2d023ec38a4e57a539cf
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|