mllm-dev commited on
Commit
d369988
1 Parent(s): b81d7d0

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": "4.40.0.dev0",
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:a66480d8b9c03e9e84b95cc5f02aaa0d9130c7b73a919b6cff9b209e19c9ff20
3
+ size 497805008
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deabbc96207d4a909ff0018aa4a1c5c1ebe8394957ee86f8f3f900d2b99f8ac5
3
+ size 995704133
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802fce84ad05868499d41c3b4634506178ec2c020c0346ca354a18a41f72992e
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0047e8b68a19aa877b6a4bcd5ce94edb0399e72f95b6be40ac9296398686a72b
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.4712163209915161,
3
+ "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-449",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 449,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.4585697014786571,
14
+ "eval_loss": 1.4712163209915161,
15
+ "eval_runtime": 17.6779,
16
+ "eval_samples_per_second": 608.275,
17
+ "eval_steps_per_second": 8.485,
18
+ "step": 449
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 449,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 4063042006732800.0,
27
+ "train_batch_size": 72,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85757fa5a7c40d93f0cb6e733f2b595904dc099ef42ed9699bf72eae6bcbd0b
3
+ size 4603
vocab.json ADDED
The diff for this file is too large to render. See raw diff