Hugging Face's logo

arun-AiBharat
/
gpt-2-bookcorpus

Text Generation
Transformers
Safetensors
English
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
2
arun-AiBharat commited on
Commit
8749055
·
verified ·
1 Parent(s): 625dfcd

Initial commit chkpoint 5k

Browse files
Files changed (10) hide show
  1. config.json +31 -0
  2. generation_config.json +6 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +20 -0
  8. trainer_state.json +171 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 1024,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.38.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50257
31
+ }
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": "4.38.2"
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 sha256:0d589264ba67f36eefae0140c4488d2e3bf4662dfb4ed8282a5cdf65330b057c
3
+ size 497774208
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 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.06988608568034105,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 1.1361215114593506,
14
+ "learning_rate": 3.4935718278367804e-05,
15
+ "loss": 7.3406,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "eval_loss": 5.7022929191589355,
21
+ "eval_runtime": 29.28,
22
+ "eval_samples_per_second": 27.083,
23
+ "eval_steps_per_second": 3.415,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 0.8447604775428772,
29
+ "learning_rate": 6.987143655673561e-05,
30
+ "loss": 5.4549,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "eval_loss": 5.279269695281982,
36
+ "eval_runtime": 29.2904,
37
+ "eval_samples_per_second": 27.074,
38
+ "eval_steps_per_second": 3.414,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "grad_norm": 0.7530624866485596,
44
+ "learning_rate": 0.00010480715483510341,
45
+ "loss": 5.2047,
46
+ "step": 1500
47
+ },
48
+ {
49
+ "epoch": 0.02,
50
+ "eval_loss": 5.1141037940979,
51
+ "eval_runtime": 29.315,
52
+ "eval_samples_per_second": 27.051,
53
+ "eval_steps_per_second": 3.411,
54
+ "step": 1500
55
+ },
56
+ {
57
+ "epoch": 0.03,
58
+ "grad_norm": 0.9565019607543945,
59
+ "learning_rate": 0.00013974287311347122,
60
+ "loss": 5.003,
61
+ "step": 2000
62
+ },
63
+ {
64
+ "epoch": 0.03,
65
+ "eval_loss": 4.823694229125977,
66
+ "eval_runtime": 29.3039,
67
+ "eval_samples_per_second": 27.061,
68
+ "eval_steps_per_second": 3.413,
69
+ "step": 2000
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "grad_norm": 0.7762724161148071,
74
+ "learning_rate": 0.00017467859139183903,
75
+ "loss": 4.7353,
76
+ "step": 2500
77
+ },
78
+ {
79
+ "epoch": 0.03,
80
+ "eval_loss": 4.599145412445068,
81
+ "eval_runtime": 29.2873,
82
+ "eval_samples_per_second": 27.077,
83
+ "eval_steps_per_second": 3.414,
84
+ "step": 2500
85
+ },
86
+ {
87
+ "epoch": 0.04,
88
+ "grad_norm": 0.6923783421516418,
89
+ "learning_rate": 0.00020961430967020682,
90
+ "loss": 4.565,
91
+ "step": 3000
92
+ },
93
+ {
94
+ "epoch": 0.04,
95
+ "eval_loss": 4.469151020050049,
96
+ "eval_runtime": 29.3283,
97
+ "eval_samples_per_second": 27.039,
98
+ "eval_steps_per_second": 3.41,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "grad_norm": 0.6830642819404602,
104
+ "learning_rate": 0.0002445500279485746,
105
+ "loss": 4.4583,
106
+ "step": 3500
107
+ },
108
+ {
109
+ "epoch": 0.05,
110
+ "eval_loss": 4.370917797088623,
111
+ "eval_runtime": 29.2477,
112
+ "eval_samples_per_second": 27.113,
113
+ "eval_steps_per_second": 3.419,
114
+ "step": 3500
115
+ },
116
+ {
117
+ "epoch": 0.06,
118
+ "grad_norm": 0.6420345902442932,
119
+ "learning_rate": 0.0002499762209394527,
120
+ "loss": 4.3647,
121
+ "step": 4000
122
+ },
123
+ {
124
+ "epoch": 0.06,
125
+ "eval_loss": 4.299973011016846,
126
+ "eval_runtime": 29.2476,
127
+ "eval_samples_per_second": 27.113,
128
+ "eval_steps_per_second": 3.419,
129
+ "step": 4000
130
+ },
131
+ {
132
+ "epoch": 0.06,
133
+ "grad_norm": 0.6263813972473145,
134
+ "learning_rate": 0.00024988650423117477,
135
+ "loss": 4.3035,
136
+ "step": 4500
137
+ },
138
+ {
139
+ "epoch": 0.06,
140
+ "eval_loss": 4.233543872833252,
141
+ "eval_runtime": 29.222,
142
+ "eval_samples_per_second": 27.137,
143
+ "eval_steps_per_second": 3.422,
144
+ "step": 4500
145
+ },
146
+ {
147
+ "epoch": 0.07,
148
+ "grad_norm": 0.6064193248748779,
149
+ "learning_rate": 0.0002497300853885875,
150
+ "loss": 4.2468,
151
+ "step": 5000
152
+ },
153
+ {
154
+ "epoch": 0.07,
155
+ "eval_loss": 4.18317985534668,
156
+ "eval_runtime": 29.2822,
157
+ "eval_samples_per_second": 27.081,
158
+ "eval_steps_per_second": 3.415,
159
+ "step": 5000
160
+ }
161
+ ],
162
+ "logging_steps": 500,
163
+ "max_steps": 71545,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 1,
166
+ "save_steps": 5000,
167
+ "total_flos": 2.090336256e+16,
168
+ "train_batch_size": 8,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eacdaa8bddf45070d8b5088e62814a87af31756609b1ce78afa155c284d0518d
3
+ size 4411
vocab.json ADDED
The diff for this file is too large to render. See raw diff