mllm-dev commited on
Commit
950ae7f
1 Parent(s): ef0d74e

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3,
24
+ "LABEL_4": 4
25
+ },
26
+ "layer_norm_epsilon": 1e-05,
27
+ "model_type": "gpt2",
28
+ "n_ctx": 1024,
29
+ "n_embd": 768,
30
+ "n_head": 12,
31
+ "n_inner": null,
32
+ "n_layer": 12,
33
+ "n_positions": 1024,
34
+ "pad_token_id": 50256,
35
+ "problem_type": "single_label_classification",
36
+ "reorder_and_upcast_attn": false,
37
+ "resid_pdrop": 0.1,
38
+ "scale_attn_by_inverse_layer_idx": false,
39
+ "scale_attn_weights": true,
40
+ "summary_activation": null,
41
+ "summary_first_dropout": 0.1,
42
+ "summary_proj_to_labels": true,
43
+ "summary_type": "cls_index",
44
+ "summary_use_proj": true,
45
+ "task_specific_params": {
46
+ "text-generation": {
47
+ "do_sample": true,
48
+ "max_length": 50
49
+ }
50
+ },
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.38.2",
53
+ "use_cache": true,
54
+ "vocab_size": 50257
55
+ }
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:bdd26392e733acc2bf07df4499675cff7c49cca3856bde1da7f12a201123c995
3
+ size 497789648
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afaffdb5a9c70a4c9418f3e115da46e1fd9b34022e32a476bee055c519a6b9f0
3
+ size 995673413
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797a471cad23917b9d403805f42f62679ccfae6a770a87408a15debfc23e4507
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f4f1b94cd49b030804b6e9c96d8faa07f56dfc10847cc9c67d1bcd0647a578
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": 1.4518036842346191,
3
+ "best_model_checkpoint": "sean_test_out/checkpoint-42",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 42,
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": 0.353,
14
+ "eval_loss": 1.4518036842346191,
15
+ "eval_runtime": 58.1635,
16
+ "eval_samples_per_second": 171.929,
17
+ "eval_steps_per_second": 7.169,
18
+ "step": 42
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 42,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 311359843123200.0,
27
+ "train_batch_size": 24,
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:e644ad3ad93c3cbe7dcd6662ac6c0e8467ec74e918b978d4cb18c413c6c07f11
3
+ size 4539
vocab.json ADDED
The diff for this file is too large to render. See raw diff