zaid002 commited on
Commit
f90ef82
·
verified ·
1 Parent(s): 9167292

Upload folder using huggingface_hub

Browse files
checkpoint-290/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a93bd1f6d320fc94c2714571e9d8d8a080519f8cf21009ed9bb87e5467c9cb0
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7c41912fa23359ed8a11dfcd06991be05d3f01c8b746ff858bb2231ba03985
3
  size 5777
checkpoint-300/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "transformers_version": "4.56.1",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
checkpoint-300/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": "4.56.1"
6
+ }
checkpoint-300/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f12dbad4356a30bc93bfddad0124032a8bfecc51de2f1001a681ffd086482b4
3
+ size 497774208
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630a4bdd48ef1eb74b690b2baae50191c6dd96963e7326e0f0d21663aa7a7c7d
3
+ size 995638603
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9991831d411ddeaa6323ba954f7ee65fc0bbac71cd2c6f9b5e5776e6c92f7e5b
3
+ size 14455
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6899f9f82cea064fe52ac09813b47d526ed686cbe04f0925eb7e665a0e61bfae
3
+ size 1465
checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.16666666666666666,
14
+ "grad_norm": 31.59705352783203,
15
+ "learning_rate": 4.85e-05,
16
+ "loss": 3.9397,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.3333333333333333,
21
+ "grad_norm": 80.66327667236328,
22
+ "learning_rate": 4.683333333333334e-05,
23
+ "loss": 3.325,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.5,
28
+ "grad_norm": 32.49787521362305,
29
+ "learning_rate": 4.516666666666667e-05,
30
+ "loss": 3.3738,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.6666666666666666,
35
+ "grad_norm": 66.78797912597656,
36
+ "learning_rate": 4.35e-05,
37
+ "loss": 3.3993,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.8333333333333334,
42
+ "grad_norm": 51.33676528930664,
43
+ "learning_rate": 4.183333333333334e-05,
44
+ "loss": 2.8263,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.0,
49
+ "grad_norm": 39.879756927490234,
50
+ "learning_rate": 4.016666666666667e-05,
51
+ "loss": 3.3037,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.1666666666666667,
56
+ "grad_norm": 25.068859100341797,
57
+ "learning_rate": 3.85e-05,
58
+ "loss": 2.476,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.3333333333333333,
63
+ "grad_norm": 26.87322425842285,
64
+ "learning_rate": 3.683333333333334e-05,
65
+ "loss": 2.4806,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.5,
70
+ "grad_norm": 0.0,
71
+ "learning_rate": 3.516666666666667e-05,
72
+ "loss": 2.121,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.6666666666666665,
77
+ "grad_norm": 0.0,
78
+ "learning_rate": 3.35e-05,
79
+ "loss": 2.5916,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 1.8333333333333335,
84
+ "grad_norm": 31.49118995666504,
85
+ "learning_rate": 3.183333333333334e-05,
86
+ "loss": 2.1819,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.0,
91
+ "grad_norm": 119.10132598876953,
92
+ "learning_rate": 3.016666666666667e-05,
93
+ "loss": 2.2888,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 2.1666666666666665,
98
+ "grad_norm": 28.438146591186523,
99
+ "learning_rate": 2.8499999999999998e-05,
100
+ "loss": 1.7975,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 2.3333333333333335,
105
+ "grad_norm": 48.78792190551758,
106
+ "learning_rate": 2.6833333333333333e-05,
107
+ "loss": 1.7283,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 2.5,
112
+ "grad_norm": 31.457948684692383,
113
+ "learning_rate": 2.5166666666666667e-05,
114
+ "loss": 1.4195,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 2.6666666666666665,
119
+ "grad_norm": 38.928916931152344,
120
+ "learning_rate": 2.35e-05,
121
+ "loss": 1.6701,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 2.8333333333333335,
126
+ "grad_norm": 30.7103271484375,
127
+ "learning_rate": 2.1833333333333333e-05,
128
+ "loss": 1.8877,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 3.0,
133
+ "grad_norm": 21.397253036499023,
134
+ "learning_rate": 2.0166666666666668e-05,
135
+ "loss": 1.4899,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 3.1666666666666665,
140
+ "grad_norm": 21.640207290649414,
141
+ "learning_rate": 1.85e-05,
142
+ "loss": 1.3078,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 3.3333333333333335,
147
+ "grad_norm": 57.379486083984375,
148
+ "learning_rate": 1.6833333333333334e-05,
149
+ "loss": 1.7813,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 3.5,
154
+ "grad_norm": 0.0,
155
+ "learning_rate": 1.5166666666666668e-05,
156
+ "loss": 1.0279,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 3.6666666666666665,
161
+ "grad_norm": 30.761775970458984,
162
+ "learning_rate": 1.3500000000000001e-05,
163
+ "loss": 1.4832,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 3.8333333333333335,
168
+ "grad_norm": 25.48395347595215,
169
+ "learning_rate": 1.1833333333333334e-05,
170
+ "loss": 1.4439,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 4.0,
175
+ "grad_norm": 24.583587646484375,
176
+ "learning_rate": 1.0166666666666667e-05,
177
+ "loss": 1.5456,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 4.166666666666667,
182
+ "grad_norm": 0.0,
183
+ "learning_rate": 8.500000000000002e-06,
184
+ "loss": 1.0711,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 4.333333333333333,
189
+ "grad_norm": 26.963958740234375,
190
+ "learning_rate": 6.833333333333333e-06,
191
+ "loss": 1.1717,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 4.5,
196
+ "grad_norm": 63.18416213989258,
197
+ "learning_rate": 5.166666666666667e-06,
198
+ "loss": 1.6026,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 4.666666666666667,
203
+ "grad_norm": 14.477971076965332,
204
+ "learning_rate": 3.5000000000000004e-06,
205
+ "loss": 0.8868,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 4.833333333333333,
210
+ "grad_norm": 29.6923770904541,
211
+ "learning_rate": 1.8333333333333335e-06,
212
+ "loss": 0.7481,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 5.0,
217
+ "grad_norm": 25.294342041015625,
218
+ "learning_rate": 1.6666666666666668e-07,
219
+ "loss": 1.1015,
220
+ "step": 300
221
+ }
222
+ ],
223
+ "logging_steps": 10,
224
+ "max_steps": 300,
225
+ "num_input_tokens_seen": 0,
226
+ "num_train_epochs": 5,
227
+ "save_steps": 10,
228
+ "stateful_callbacks": {
229
+ "TrainerControl": {
230
+ "args": {
231
+ "should_epoch_stop": false,
232
+ "should_evaluate": false,
233
+ "should_log": false,
234
+ "should_save": true,
235
+ "should_training_stop": true
236
+ },
237
+ "attributes": {}
238
+ }
239
+ },
240
+ "total_flos": 39193804800000.0,
241
+ "train_batch_size": 2,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7c41912fa23359ed8a11dfcd06991be05d3f01c8b746ff858bb2231ba03985
3
+ size 5777
checkpoint-300/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Sep22_05-50-37_4e0151b39184/events.out.tfevents.1758520244.4e0151b39184.299.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c03691c8b93d92862a10f5ba7eb68c3ddf781b7f3315d185315ed1b7a8071d6
3
+ size 11851