Hugging Face's logo

CodeIsAbstract
/
LLAMA_RoPE_Baseline

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
87c8fc1
·
verified ·
1 Parent(s): b997171

Training in progress, step 4000, checkpoint

Browse files
Files changed (12) hide show
  1. last-checkpoint/config.json +30 -0
  2. last-checkpoint/generation_config.json +7 -0
  3. last-checkpoint/model.safetensors +3 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/special_tokens_map.json +24 -0
  8. last-checkpoint/tokenizer.json +0 -0
  9. last-checkpoint/tokenizer.model +3 -0
  10. last-checkpoint/tokenizer_config.json +0 -0
  11. last-checkpoint/trainer_state.json +346 -0
  12. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2048,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "num_key_value_heads": 12,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "transformers_version": "4.56.0",
28
+ "use_cache": true,
29
+ "vocab_size": 32768
30
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.56.0"
7
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195264f4189d85c3b420f3c7ede63faa40b60d80bcb0a67ef9a76fbfa01db140
3
+ size 541154336
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6addff14bf805b5812fe850aec8f4687d039d8b226f53eba8e2bd87eb56179
3
+ size 1082379659
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636ce205a7d25245e8bf516169992a8697e5d28e02c0cbb97c0ae7b282b76a7d
3
+ size 1465
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
last-checkpoint/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.05194805194805195,
6
+ "eval_steps": 1000,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0012987012987012987,
14
+ "grad_norm": 0.8535653352737427,
15
+ "learning_rate": 9.42857142857143e-05,
16
+ "loss": 8.6239,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.0025974025974025974,
21
+ "grad_norm": 0.9884688258171082,
22
+ "learning_rate": 0.0001895238095238095,
23
+ "loss": 6.7685,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.003896103896103896,
28
+ "grad_norm": 0.5704336762428284,
29
+ "learning_rate": 0.0002847619047619048,
30
+ "loss": 5.9666,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.005194805194805195,
35
+ "grad_norm": 0.6232308149337769,
36
+ "learning_rate": 0.00038,
37
+ "loss": 5.518,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.006493506493506494,
42
+ "grad_norm": 0.6595708131790161,
43
+ "learning_rate": 0.00047523809523809525,
44
+ "loss": 5.205,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.007792207792207792,
49
+ "grad_norm": 0.5402975678443909,
50
+ "learning_rate": 0.0005704761904761905,
51
+ "loss": 4.9366,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.00909090909090909,
56
+ "grad_norm": 0.5196501016616821,
57
+ "learning_rate": 0.0006657142857142858,
58
+ "loss": 4.7613,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.01038961038961039,
63
+ "grad_norm": 0.6473610401153564,
64
+ "learning_rate": 0.0007609523809523809,
65
+ "loss": 4.6361,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.011688311688311689,
70
+ "grad_norm": 0.4435962736606598,
71
+ "learning_rate": 0.0008561904761904762,
72
+ "loss": 4.5062,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.012987012987012988,
77
+ "grad_norm": 0.46511825919151306,
78
+ "learning_rate": 0.0009514285714285714,
79
+ "loss": 4.3812,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.012987012987012988,
84
+ "eval_loss": 4.666484355926514,
85
+ "eval_runtime": 15.6105,
86
+ "eval_samples_per_second": 36.898,
87
+ "eval_steps_per_second": 9.225,
88
+ "step": 1000
89
+ },
90
+ {
91
+ "epoch": 0.014285714285714285,
92
+ "grad_norm": 0.38127702474594116,
93
+ "learning_rate": 0.0009999995009117187,
94
+ "loss": 4.2976,
95
+ "step": 1100
96
+ },
97
+ {
98
+ "epoch": 0.015584415584415584,
99
+ "grad_norm": 0.4769284129142761,
100
+ "learning_rate": 0.0009999953851546302,
101
+ "loss": 4.1888,
102
+ "step": 1200
103
+ },
104
+ {
105
+ "epoch": 0.016883116883116882,
106
+ "grad_norm": 0.4059095084667206,
107
+ "learning_rate": 0.000999987112101314,
108
+ "loss": 4.0874,
109
+ "step": 1300
110
+ },
111
+ {
112
+ "epoch": 0.01818181818181818,
113
+ "grad_norm": 0.34086140990257263,
114
+ "learning_rate": 0.0009999746818205575,
115
+ "loss": 3.974,
116
+ "step": 1400
117
+ },
118
+ {
119
+ "epoch": 0.01948051948051948,
120
+ "grad_norm": 0.32273247838020325,
121
+ "learning_rate": 0.0009999580944157148,
122
+ "loss": 3.9202,
123
+ "step": 1500
124
+ },
125
+ {
126
+ "epoch": 0.02077922077922078,
127
+ "grad_norm": 0.36565664410591125,
128
+ "learning_rate": 0.000999937350024705,
129
+ "loss": 3.8821,
130
+ "step": 1600
131
+ },
132
+ {
133
+ "epoch": 0.02207792207792208,
134
+ "grad_norm": 0.3269343376159668,
135
+ "learning_rate": 0.0009999124488200097,
136
+ "loss": 3.7686,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 0.023376623376623377,
141
+ "grad_norm": 0.3859221339225769,
142
+ "learning_rate": 0.0009998833910086751,
143
+ "loss": 3.7079,
144
+ "step": 1800
145
+ },
146
+ {
147
+ "epoch": 0.024675324675324677,
148
+ "grad_norm": 0.3663485646247864,
149
+ "learning_rate": 0.000999850176832307,
150
+ "loss": 3.6803,
151
+ "step": 1900
152
+ },
153
+ {
154
+ "epoch": 0.025974025974025976,
155
+ "grad_norm": 0.46907544136047363,
156
+ "learning_rate": 0.0009998128065670706,
157
+ "loss": 3.6502,
158
+ "step": 2000
159
+ },
160
+ {
161
+ "epoch": 0.025974025974025976,
162
+ "eval_loss": 3.9888415336608887,
163
+ "eval_runtime": 15.6284,
164
+ "eval_samples_per_second": 36.856,
165
+ "eval_steps_per_second": 9.214,
166
+ "step": 2000
167
+ },
168
+ {
169
+ "epoch": 0.02727272727272727,
170
+ "grad_norm": 0.3356938362121582,
171
+ "learning_rate": 0.0009997712805236867,
172
+ "loss": 3.6339,
173
+ "step": 2100
174
+ },
175
+ {
176
+ "epoch": 0.02857142857142857,
177
+ "grad_norm": 0.2554614543914795,
178
+ "learning_rate": 0.0009997255990474312,
179
+ "loss": 3.601,
180
+ "step": 2200
181
+ },
182
+ {
183
+ "epoch": 0.02987012987012987,
184
+ "grad_norm": 0.2642477750778198,
185
+ "learning_rate": 0.00099967576251813,
186
+ "loss": 3.5622,
187
+ "step": 2300
188
+ },
189
+ {
190
+ "epoch": 0.03116883116883117,
191
+ "grad_norm": 0.2671547532081604,
192
+ "learning_rate": 0.0009996217713501576,
193
+ "loss": 3.517,
194
+ "step": 2400
195
+ },
196
+ {
197
+ "epoch": 0.032467532467532464,
198
+ "grad_norm": 0.26076218485832214,
199
+ "learning_rate": 0.0009995636259924328,
200
+ "loss": 3.5058,
201
+ "step": 2500
202
+ },
203
+ {
204
+ "epoch": 0.033766233766233764,
205
+ "grad_norm": 0.39065253734588623,
206
+ "learning_rate": 0.0009995013269284145,
207
+ "loss": 3.5262,
208
+ "step": 2600
209
+ },
210
+ {
211
+ "epoch": 0.03506493506493506,
212
+ "grad_norm": 0.23748748004436493,
213
+ "learning_rate": 0.0009994348746760996,
214
+ "loss": 3.4818,
215
+ "step": 2700
216
+ },
217
+ {
218
+ "epoch": 0.03636363636363636,
219
+ "grad_norm": 0.23590387403964996,
220
+ "learning_rate": 0.000999364269788016,
221
+ "loss": 3.4639,
222
+ "step": 2800
223
+ },
224
+ {
225
+ "epoch": 0.03766233766233766,
226
+ "grad_norm": 0.2318197786808014,
227
+ "learning_rate": 0.00099928951285122,
228
+ "loss": 3.4444,
229
+ "step": 2900
230
+ },
231
+ {
232
+ "epoch": 0.03896103896103896,
233
+ "grad_norm": 0.2852722406387329,
234
+ "learning_rate": 0.0009992106044872913,
235
+ "loss": 3.4227,
236
+ "step": 3000
237
+ },
238
+ {
239
+ "epoch": 0.03896103896103896,
240
+ "eval_loss": 3.778900623321533,
241
+ "eval_runtime": 15.1585,
242
+ "eval_samples_per_second": 37.998,
243
+ "eval_steps_per_second": 9.5,
244
+ "step": 3000
245
+ },
246
+ {
247
+ "epoch": 0.04025974025974026,
248
+ "grad_norm": 0.23955008387565613,
249
+ "learning_rate": 0.0009991275453523263,
250
+ "loss": 3.3974,
251
+ "step": 3100
252
+ },
253
+ {
254
+ "epoch": 0.04155844155844156,
255
+ "grad_norm": 0.2509465217590332,
256
+ "learning_rate": 0.0009990403361369346,
257
+ "loss": 3.4157,
258
+ "step": 3200
259
+ },
260
+ {
261
+ "epoch": 0.04285714285714286,
262
+ "grad_norm": 0.24335195124149323,
263
+ "learning_rate": 0.0009989489775662315,
264
+ "loss": 3.3972,
265
+ "step": 3300
266
+ },
267
+ {
268
+ "epoch": 0.04415584415584416,
269
+ "grad_norm": 0.7076203227043152,
270
+ "learning_rate": 0.000998853470399834,
271
+ "loss": 3.4082,
272
+ "step": 3400
273
+ },
274
+ {
275
+ "epoch": 0.045454545454545456,
276
+ "grad_norm": 0.25543642044067383,
277
+ "learning_rate": 0.0009987538154318518,
278
+ "loss": 3.373,
279
+ "step": 3500
280
+ },
281
+ {
282
+ "epoch": 0.046753246753246755,
283
+ "grad_norm": 0.7122920155525208,
284
+ "learning_rate": 0.0009986500134908838,
285
+ "loss": 3.3898,
286
+ "step": 3600
287
+ },
288
+ {
289
+ "epoch": 0.048051948051948054,
290
+ "grad_norm": 0.2252849042415619,
291
+ "learning_rate": 0.000998542065440008,
292
+ "loss": 3.3739,
293
+ "step": 3700
294
+ },
295
+ {
296
+ "epoch": 0.04935064935064935,
297
+ "grad_norm": 0.20722781121730804,
298
+ "learning_rate": 0.0009984299721767773,
299
+ "loss": 3.353,
300
+ "step": 3800
301
+ },
302
+ {
303
+ "epoch": 0.05064935064935065,
304
+ "grad_norm": 0.2006598860025406,
305
+ "learning_rate": 0.00099831373463321,
306
+ "loss": 3.3124,
307
+ "step": 3900
308
+ },
309
+ {
310
+ "epoch": 0.05194805194805195,
311
+ "grad_norm": 0.2024812549352646,
312
+ "learning_rate": 0.0009981933537757828,
313
+ "loss": 3.3367,
314
+ "step": 4000
315
+ },
316
+ {
317
+ "epoch": 0.05194805194805195,
318
+ "eval_loss": 3.681532144546509,
319
+ "eval_runtime": 16.9008,
320
+ "eval_samples_per_second": 34.081,
321
+ "eval_steps_per_second": 8.52,
322
+ "step": 4000
323
+ }
324
+ ],
325
+ "logging_steps": 100,
326
+ "max_steps": 77000,
327
+ "num_input_tokens_seen": 0,
328
+ "num_train_epochs": 9223372036854775807,
329
+ "save_steps": 4000,
330
+ "stateful_callbacks": {
331
+ "TrainerControl": {
332
+ "args": {
333
+ "should_epoch_stop": false,
334
+ "should_evaluate": false,
335
+ "should_log": false,
336
+ "should_save": true,
337
+ "should_training_stop": false
338
+ },
339
+ "attributes": {}
340
+ }
341
+ },
342
+ "total_flos": 1.1907725524992e+17,
343
+ "train_batch_size": 22,
344
+ "trial_name": null,
345
+ "trial_params": null
346
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46737e9bac89bc9b57f33fbb261caf48e30a3b2b9c5244699fad37f3cc509337
3
+ size 5841