mllm-dev commited on
Commit
81b02de
·
verified ·
1 Parent(s): ecc52d0

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
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
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8,
34
+ "LABEL_9": 9
35
+ },
36
+ "layer_norm_epsilon": 1e-05,
37
+ "model_type": "gpt2",
38
+ "n_ctx": 1024,
39
+ "n_embd": 768,
40
+ "n_head": 12,
41
+ "n_inner": null,
42
+ "n_layer": 12,
43
+ "n_positions": 1024,
44
+ "pad_token_id": 50256,
45
+ "problem_type": "single_label_classification",
46
+ "reorder_and_upcast_attn": false,
47
+ "resid_pdrop": 0.1,
48
+ "scale_attn_by_inverse_layer_idx": false,
49
+ "scale_attn_weights": true,
50
+ "summary_activation": null,
51
+ "summary_first_dropout": 0.1,
52
+ "summary_proj_to_labels": true,
53
+ "summary_type": "cls_index",
54
+ "summary_use_proj": true,
55
+ "task_specific_params": {
56
+ "text-generation": {
57
+ "do_sample": true,
58
+ "max_length": 50
59
+ }
60
+ },
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.37.1",
63
+ "use_cache": true,
64
+ "vocab_size": 50257
65
+ }
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:d8af7f4863b3eb11939a1fc5be1414b8788c5b6b60b2b513d5a8d7163db4206c
3
+ size 497805008
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af763c157a8e740c6c1852b15876bb860d2118a41fe576ec5a606caacea4132f
3
+ size 995704133
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67720abb52f501e2410e504467e576e1b76d58ea5fbdf49308334defd3b5b833
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30db70340a474b482c4e5374dfafc4bc44d14a9cfa0fb0ea5ca9e76e8bb49251
3
+ size 627
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.4374622106552124,
3
+ "best_model_checkpoint": "tam_test_out_drug_data_new_run/checkpoint-1009",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1009,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 3.026759167492567e-05,
14
+ "loss": 1.7095,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.99,
19
+ "learning_rate": 5.351833498513379e-07,
20
+ "loss": 1.4953,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_accuracy": 0.4675904398772436,
26
+ "eval_loss": 1.4374622106552124,
27
+ "eval_runtime": 29.6408,
28
+ "eval_samples_per_second": 362.777,
29
+ "eval_steps_per_second": 11.369,
30
+ "step": 1009
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 1009,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 1,
37
+ "save_steps": 500,
38
+ "total_flos": 3744085871185920.0,
39
+ "train_batch_size": 32,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18968ba4e4b7978c301d5a9c7d13c1e497d070ab0f9ffdd56988e472b485f204
3
+ size 4411
vocab.json ADDED
The diff for this file is too large to render. See raw diff