hidude562 commited on
Commit
19d0ff2
·
verified ·
1 Parent(s): b641a17

Upload 15 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|pad|>": 50258,
3
+ "<|startoftext|>": 50257
4
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hidude562/Maestro-ctx-V5",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "fp16": true,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 1024,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.38.1",
32
+ "use_cache": true,
33
+ "vocab_size": 50257
34
+ }
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": "4.38.1"
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 sha256:5a43e7157860e1e8828bba6bc4320c4de8ebddefe811a6496dfc6bfdb71036b1
3
+ size 1423517184
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83896555904e4d15b258aafe3cfc3f0ee2518381fe05950bcdca132bd0d6e333
3
+ size 2847217850
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973b9a81cde240d53a5df2864cf7972ebfc20a84e4b4826c365ab15e46d972ae
3
+ size 14244
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92319ba9cd94af301ec8564f35427b276247fc3c9ff7c091960d9bcb2edf54ad
3
+ size 14512
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3dce23ddc53fae01928392cbd30ab6e87c85b7dec461450f9a1e7f05e03928
3
+ size 14512
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f9ad0bb327439c0eec0c594244d4256942dbf9b394f41814c39cfe9cebd262
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
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": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|startoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<|pad|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
trainer_state.json ADDED
@@ -0,0 +1,749 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.1196327604545708,
5
+ "eval_steps": 500,
6
+ "global_step": 52000,
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": 0.3076048195362091,
14
+ "learning_rate": 4.994617057468295e-05,
15
+ "loss": 0.6146,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 0.28934741020202637,
21
+ "learning_rate": 4.989234114936589e-05,
22
+ "loss": 0.5914,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "grad_norm": 0.32335227727890015,
28
+ "learning_rate": 4.9838511724048836e-05,
29
+ "loss": 0.6077,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.04,
34
+ "grad_norm": 0.23465125262737274,
35
+ "learning_rate": 4.9784682298731785e-05,
36
+ "loss": 0.6017,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.05,
41
+ "grad_norm": 0.3192775845527649,
42
+ "learning_rate": 4.973085287341472e-05,
43
+ "loss": 0.5961,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.06,
48
+ "grad_norm": 0.2321719229221344,
49
+ "learning_rate": 4.967702344809767e-05,
50
+ "loss": 0.5917,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "grad_norm": 0.29103726148605347,
56
+ "learning_rate": 4.962319402278062e-05,
57
+ "loss": 0.5936,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.09,
62
+ "grad_norm": 0.24932251870632172,
63
+ "learning_rate": 4.956936459746356e-05,
64
+ "loss": 0.6019,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.1,
69
+ "grad_norm": 0.3346109092235565,
70
+ "learning_rate": 4.9515535172146503e-05,
71
+ "loss": 0.6121,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.11,
76
+ "grad_norm": 0.2718544602394104,
77
+ "learning_rate": 4.946170574682945e-05,
78
+ "loss": 0.6042,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.12,
83
+ "grad_norm": 0.27134013175964355,
84
+ "learning_rate": 4.940798398036303e-05,
85
+ "loss": 0.594,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.13,
90
+ "grad_norm": 0.35403260588645935,
91
+ "learning_rate": 4.9354154555045976e-05,
92
+ "loss": 0.5987,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.14,
97
+ "grad_norm": 0.32682767510414124,
98
+ "learning_rate": 4.930032512972892e-05,
99
+ "loss": 0.5937,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.15,
104
+ "grad_norm": 0.34741413593292236,
105
+ "learning_rate": 4.924649570441186e-05,
106
+ "loss": 0.602,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.16,
111
+ "grad_norm": 0.29353055357933044,
112
+ "learning_rate": 4.919266627909481e-05,
113
+ "loss": 0.6093,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.17,
118
+ "grad_norm": 0.2304825335741043,
119
+ "learning_rate": 4.913883685377775e-05,
120
+ "loss": 0.6024,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.18,
125
+ "grad_norm": 0.32337111234664917,
126
+ "learning_rate": 4.9085007428460694e-05,
127
+ "loss": 0.5968,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.19,
132
+ "grad_norm": 0.21958841383457184,
133
+ "learning_rate": 4.903117800314364e-05,
134
+ "loss": 0.6019,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.2,
139
+ "grad_norm": 0.23487211763858795,
140
+ "learning_rate": 4.8977348577826585e-05,
141
+ "loss": 0.5883,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.22,
146
+ "grad_norm": 0.2670685350894928,
147
+ "learning_rate": 4.892351915250953e-05,
148
+ "loss": 0.5883,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.23,
153
+ "grad_norm": 0.3000301420688629,
154
+ "learning_rate": 4.886968972719248e-05,
155
+ "loss": 0.6039,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.24,
160
+ "grad_norm": 0.2296791523694992,
161
+ "learning_rate": 4.881586030187542e-05,
162
+ "loss": 0.5979,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.25,
167
+ "grad_norm": 0.23062767088413239,
168
+ "learning_rate": 4.876213853540899e-05,
169
+ "loss": 0.5996,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.26,
174
+ "grad_norm": 0.3908576965332031,
175
+ "learning_rate": 4.870830911009194e-05,
176
+ "loss": 0.5965,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.27,
181
+ "grad_norm": 0.3430127799510956,
182
+ "learning_rate": 4.865447968477489e-05,
183
+ "loss": 0.5857,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.28,
188
+ "grad_norm": 0.352638304233551,
189
+ "learning_rate": 4.8600650259457834e-05,
190
+ "loss": 0.6033,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.29,
195
+ "grad_norm": 0.2627607583999634,
196
+ "learning_rate": 4.8546820834140776e-05,
197
+ "loss": 0.5903,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.3,
202
+ "grad_norm": 0.3584256172180176,
203
+ "learning_rate": 4.849309906767436e-05,
204
+ "loss": 0.5973,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.31,
209
+ "grad_norm": 0.2537979185581207,
210
+ "learning_rate": 4.84392696423573e-05,
211
+ "loss": 0.591,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.32,
216
+ "grad_norm": 0.29915836453437805,
217
+ "learning_rate": 4.838544021704025e-05,
218
+ "loss": 0.5846,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.33,
223
+ "grad_norm": 0.2917690575122833,
224
+ "learning_rate": 4.833161079172319e-05,
225
+ "loss": 0.5958,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.34,
230
+ "grad_norm": 0.2941623628139496,
231
+ "learning_rate": 4.8277889025256765e-05,
232
+ "loss": 0.5969,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.36,
237
+ "grad_norm": 0.23406459391117096,
238
+ "learning_rate": 4.8224059599939714e-05,
239
+ "loss": 0.5849,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.37,
244
+ "grad_norm": 0.2897736728191376,
245
+ "learning_rate": 4.817023017462266e-05,
246
+ "loss": 0.5947,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.38,
251
+ "grad_norm": 0.2664598524570465,
252
+ "learning_rate": 4.81164007493056e-05,
253
+ "loss": 0.5951,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 0.39,
258
+ "grad_norm": 0.22176018357276917,
259
+ "learning_rate": 4.806257132398855e-05,
260
+ "loss": 0.5965,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 0.4,
265
+ "grad_norm": 0.2701508402824402,
266
+ "learning_rate": 4.8008741898671496e-05,
267
+ "loss": 0.5928,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 0.41,
272
+ "grad_norm": 0.23263579607009888,
273
+ "learning_rate": 4.795491247335443e-05,
274
+ "loss": 0.5957,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 0.42,
279
+ "grad_norm": 0.34762224555015564,
280
+ "learning_rate": 4.790108304803738e-05,
281
+ "loss": 0.5871,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 0.43,
286
+ "grad_norm": 0.30906400084495544,
287
+ "learning_rate": 4.784725362272033e-05,
288
+ "loss": 0.593,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 0.44,
293
+ "grad_norm": 0.28025567531585693,
294
+ "learning_rate": 4.779342419740327e-05,
295
+ "loss": 0.5817,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 0.45,
300
+ "grad_norm": 0.3143500089645386,
301
+ "learning_rate": 4.773970243093685e-05,
302
+ "loss": 0.5937,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 0.46,
307
+ "grad_norm": 0.32620757818222046,
308
+ "learning_rate": 4.7685980664470434e-05,
309
+ "loss": 0.5884,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 0.47,
314
+ "grad_norm": 0.25027623772621155,
315
+ "learning_rate": 4.763215123915337e-05,
316
+ "loss": 0.583,
317
+ "step": 22000
318
+ },
319
+ {
320
+ "epoch": 0.48,
321
+ "grad_norm": 0.23277850449085236,
322
+ "learning_rate": 4.757832181383632e-05,
323
+ "loss": 0.5869,
324
+ "step": 22500
325
+ },
326
+ {
327
+ "epoch": 0.5,
328
+ "grad_norm": 0.2901150584220886,
329
+ "learning_rate": 4.752449238851927e-05,
330
+ "loss": 0.5731,
331
+ "step": 23000
332
+ },
333
+ {
334
+ "epoch": 0.51,
335
+ "grad_norm": 0.20858778059482574,
336
+ "learning_rate": 4.7470662963202203e-05,
337
+ "loss": 0.5845,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 0.52,
342
+ "grad_norm": 0.23019325733184814,
343
+ "learning_rate": 4.7416941196735784e-05,
344
+ "loss": 0.5881,
345
+ "step": 24000
346
+ },
347
+ {
348
+ "epoch": 0.53,
349
+ "grad_norm": 0.30065199732780457,
350
+ "learning_rate": 4.7363111771418733e-05,
351
+ "loss": 0.5743,
352
+ "step": 24500
353
+ },
354
+ {
355
+ "epoch": 0.54,
356
+ "grad_norm": 0.24830493330955505,
357
+ "learning_rate": 4.7309282346101676e-05,
358
+ "loss": 0.574,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 0.55,
363
+ "grad_norm": 0.2857877314090729,
364
+ "learning_rate": 4.725545292078462e-05,
365
+ "loss": 0.5731,
366
+ "step": 25500
367
+ },
368
+ {
369
+ "epoch": 0.56,
370
+ "grad_norm": 0.3333861827850342,
371
+ "learning_rate": 4.720162349546757e-05,
372
+ "loss": 0.5832,
373
+ "step": 26000
374
+ },
375
+ {
376
+ "epoch": 0.57,
377
+ "grad_norm": 0.2669144868850708,
378
+ "learning_rate": 4.714779407015051e-05,
379
+ "loss": 0.5777,
380
+ "step": 26500
381
+ },
382
+ {
383
+ "epoch": 0.58,
384
+ "grad_norm": 0.20388497412204742,
385
+ "learning_rate": 4.709396464483345e-05,
386
+ "loss": 0.5956,
387
+ "step": 27000
388
+ },
389
+ {
390
+ "epoch": 0.59,
391
+ "grad_norm": 0.2957603633403778,
392
+ "learning_rate": 4.70401352195164e-05,
393
+ "loss": 0.5897,
394
+ "step": 27500
395
+ },
396
+ {
397
+ "epoch": 0.6,
398
+ "grad_norm": 0.1999462991952896,
399
+ "learning_rate": 4.6986413453049975e-05,
400
+ "loss": 0.586,
401
+ "step": 28000
402
+ },
403
+ {
404
+ "epoch": 0.61,
405
+ "grad_norm": 0.38801008462905884,
406
+ "learning_rate": 4.6932584027732924e-05,
407
+ "loss": 0.5837,
408
+ "step": 28500
409
+ },
410
+ {
411
+ "epoch": 0.62,
412
+ "grad_norm": 0.2928718626499176,
413
+ "learning_rate": 4.6878754602415866e-05,
414
+ "loss": 0.5794,
415
+ "step": 29000
416
+ },
417
+ {
418
+ "epoch": 0.64,
419
+ "grad_norm": 0.3175244927406311,
420
+ "learning_rate": 4.682492517709881e-05,
421
+ "loss": 0.5853,
422
+ "step": 29500
423
+ },
424
+ {
425
+ "epoch": 0.65,
426
+ "grad_norm": 0.2631368935108185,
427
+ "learning_rate": 4.677120341063239e-05,
428
+ "loss": 0.5829,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 0.66,
433
+ "grad_norm": 0.24740691483020782,
434
+ "learning_rate": 4.6717481644165964e-05,
435
+ "loss": 0.582,
436
+ "step": 30500
437
+ },
438
+ {
439
+ "epoch": 0.67,
440
+ "grad_norm": 0.31048133969306946,
441
+ "learning_rate": 4.666365221884891e-05,
442
+ "loss": 0.5942,
443
+ "step": 31000
444
+ },
445
+ {
446
+ "epoch": 0.68,
447
+ "grad_norm": 0.2478443831205368,
448
+ "learning_rate": 4.660982279353186e-05,
449
+ "loss": 0.6,
450
+ "step": 31500
451
+ },
452
+ {
453
+ "epoch": 0.69,
454
+ "grad_norm": 0.24174700677394867,
455
+ "learning_rate": 4.6555993368214804e-05,
456
+ "loss": 0.5768,
457
+ "step": 32000
458
+ },
459
+ {
460
+ "epoch": 0.7,
461
+ "grad_norm": 0.25594571232795715,
462
+ "learning_rate": 4.6502163942897746e-05,
463
+ "loss": 0.5791,
464
+ "step": 32500
465
+ },
466
+ {
467
+ "epoch": 0.71,
468
+ "grad_norm": 0.2157001793384552,
469
+ "learning_rate": 4.6448334517580696e-05,
470
+ "loss": 0.5743,
471
+ "step": 33000
472
+ },
473
+ {
474
+ "epoch": 0.72,
475
+ "grad_norm": 0.3016982078552246,
476
+ "learning_rate": 4.639450509226364e-05,
477
+ "loss": 0.5788,
478
+ "step": 33500
479
+ },
480
+ {
481
+ "epoch": 0.73,
482
+ "grad_norm": 0.28101280331611633,
483
+ "learning_rate": 4.634078332579722e-05,
484
+ "loss": 0.5957,
485
+ "step": 34000
486
+ },
487
+ {
488
+ "epoch": 0.74,
489
+ "grad_norm": 0.24969856441020966,
490
+ "learning_rate": 4.628695390048016e-05,
491
+ "loss": 0.5789,
492
+ "step": 34500
493
+ },
494
+ {
495
+ "epoch": 0.75,
496
+ "grad_norm": 0.2322104573249817,
497
+ "learning_rate": 4.62331244751631e-05,
498
+ "loss": 0.5804,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 0.76,
503
+ "grad_norm": 0.28361350297927856,
504
+ "learning_rate": 4.617929504984605e-05,
505
+ "loss": 0.579,
506
+ "step": 35500
507
+ },
508
+ {
509
+ "epoch": 0.78,
510
+ "grad_norm": 0.29101938009262085,
511
+ "learning_rate": 4.6125465624528995e-05,
512
+ "loss": 0.5685,
513
+ "step": 36000
514
+ },
515
+ {
516
+ "epoch": 0.79,
517
+ "grad_norm": 0.3486846685409546,
518
+ "learning_rate": 4.607163619921194e-05,
519
+ "loss": 0.5854,
520
+ "step": 36500
521
+ },
522
+ {
523
+ "epoch": 0.8,
524
+ "grad_norm": 0.2890051603317261,
525
+ "learning_rate": 4.6017806773894886e-05,
526
+ "loss": 0.5726,
527
+ "step": 37000
528
+ },
529
+ {
530
+ "epoch": 0.81,
531
+ "grad_norm": 0.24968238174915314,
532
+ "learning_rate": 4.596397734857783e-05,
533
+ "loss": 0.5685,
534
+ "step": 37500
535
+ },
536
+ {
537
+ "epoch": 0.82,
538
+ "grad_norm": 0.25876086950302124,
539
+ "learning_rate": 4.591014792326077e-05,
540
+ "loss": 0.5839,
541
+ "step": 38000
542
+ },
543
+ {
544
+ "epoch": 0.83,
545
+ "grad_norm": 0.1987730860710144,
546
+ "learning_rate": 4.585642615679435e-05,
547
+ "loss": 0.5547,
548
+ "step": 38500
549
+ },
550
+ {
551
+ "epoch": 0.84,
552
+ "grad_norm": 0.27402666211128235,
553
+ "learning_rate": 4.58025967314773e-05,
554
+ "loss": 0.5802,
555
+ "step": 39000
556
+ },
557
+ {
558
+ "epoch": 0.85,
559
+ "grad_norm": 0.31150248646736145,
560
+ "learning_rate": 4.5748767306160236e-05,
561
+ "loss": 0.5879,
562
+ "step": 39500
563
+ },
564
+ {
565
+ "epoch": 0.86,
566
+ "grad_norm": 0.32700014114379883,
567
+ "learning_rate": 4.5694937880843185e-05,
568
+ "loss": 0.5755,
569
+ "step": 40000
570
+ },
571
+ {
572
+ "epoch": 0.87,
573
+ "grad_norm": 0.23694302141666412,
574
+ "learning_rate": 4.5641216114376766e-05,
575
+ "loss": 0.5826,
576
+ "step": 40500
577
+ },
578
+ {
579
+ "epoch": 0.88,
580
+ "grad_norm": 0.25343358516693115,
581
+ "learning_rate": 4.558738668905971e-05,
582
+ "loss": 0.5716,
583
+ "step": 41000
584
+ },
585
+ {
586
+ "epoch": 0.89,
587
+ "grad_norm": 0.22144146263599396,
588
+ "learning_rate": 4.553355726374266e-05,
589
+ "loss": 0.5777,
590
+ "step": 41500
591
+ },
592
+ {
593
+ "epoch": 0.9,
594
+ "grad_norm": 0.23369935154914856,
595
+ "learning_rate": 4.547983549727624e-05,
596
+ "loss": 0.5673,
597
+ "step": 42000
598
+ },
599
+ {
600
+ "epoch": 0.92,
601
+ "grad_norm": 0.3007163405418396,
602
+ "learning_rate": 4.5426006071959174e-05,
603
+ "loss": 0.5785,
604
+ "step": 42500
605
+ },
606
+ {
607
+ "epoch": 0.93,
608
+ "grad_norm": 0.21664878726005554,
609
+ "learning_rate": 4.537217664664212e-05,
610
+ "loss": 0.5679,
611
+ "step": 43000
612
+ },
613
+ {
614
+ "epoch": 0.94,
615
+ "grad_norm": 0.2804299592971802,
616
+ "learning_rate": 4.531834722132507e-05,
617
+ "loss": 0.5673,
618
+ "step": 43500
619
+ },
620
+ {
621
+ "epoch": 0.95,
622
+ "grad_norm": 0.2640630900859833,
623
+ "learning_rate": 4.526451779600801e-05,
624
+ "loss": 0.5713,
625
+ "step": 44000
626
+ },
627
+ {
628
+ "epoch": 0.96,
629
+ "grad_norm": 0.2232804000377655,
630
+ "learning_rate": 4.521068837069096e-05,
631
+ "loss": 0.5689,
632
+ "step": 44500
633
+ },
634
+ {
635
+ "epoch": 0.97,
636
+ "grad_norm": 0.2426728457212448,
637
+ "learning_rate": 4.5156858945373906e-05,
638
+ "loss": 0.579,
639
+ "step": 45000
640
+ },
641
+ {
642
+ "epoch": 0.98,
643
+ "grad_norm": 0.3089877665042877,
644
+ "learning_rate": 4.510313717890748e-05,
645
+ "loss": 0.5792,
646
+ "step": 45500
647
+ },
648
+ {
649
+ "epoch": 0.99,
650
+ "grad_norm": 0.29300886392593384,
651
+ "learning_rate": 4.504930775359042e-05,
652
+ "loss": 0.5711,
653
+ "step": 46000
654
+ },
655
+ {
656
+ "epoch": 1.0,
657
+ "grad_norm": 0.21948744356632233,
658
+ "learning_rate": 4.499547832827337e-05,
659
+ "loss": 0.5725,
660
+ "step": 46500
661
+ },
662
+ {
663
+ "epoch": 1.01,
664
+ "grad_norm": 0.31533685326576233,
665
+ "learning_rate": 4.4941648902956314e-05,
666
+ "loss": 0.5691,
667
+ "step": 47000
668
+ },
669
+ {
670
+ "epoch": 1.02,
671
+ "grad_norm": 0.2665063738822937,
672
+ "learning_rate": 4.4887819477639256e-05,
673
+ "loss": 0.5681,
674
+ "step": 47500
675
+ },
676
+ {
677
+ "epoch": 1.03,
678
+ "grad_norm": 0.3198137879371643,
679
+ "learning_rate": 4.4833990052322205e-05,
680
+ "loss": 0.5639,
681
+ "step": 48000
682
+ },
683
+ {
684
+ "epoch": 1.04,
685
+ "grad_norm": 0.27481958270072937,
686
+ "learning_rate": 4.478026828585578e-05,
687
+ "loss": 0.5642,
688
+ "step": 48500
689
+ },
690
+ {
691
+ "epoch": 1.06,
692
+ "grad_norm": 0.2723371982574463,
693
+ "learning_rate": 4.472643886053873e-05,
694
+ "loss": 0.5609,
695
+ "step": 49000
696
+ },
697
+ {
698
+ "epoch": 1.07,
699
+ "grad_norm": 0.29230979084968567,
700
+ "learning_rate": 4.467260943522168e-05,
701
+ "loss": 0.5521,
702
+ "step": 49500
703
+ },
704
+ {
705
+ "epoch": 1.08,
706
+ "grad_norm": 0.25512951612472534,
707
+ "learning_rate": 4.461878000990461e-05,
708
+ "loss": 0.5509,
709
+ "step": 50000
710
+ },
711
+ {
712
+ "epoch": 1.09,
713
+ "grad_norm": 0.19084623456001282,
714
+ "learning_rate": 4.456495058458756e-05,
715
+ "loss": 0.5613,
716
+ "step": 50500
717
+ },
718
+ {
719
+ "epoch": 1.1,
720
+ "grad_norm": 0.2515014410018921,
721
+ "learning_rate": 4.451112115927051e-05,
722
+ "loss": 0.5647,
723
+ "step": 51000
724
+ },
725
+ {
726
+ "epoch": 1.11,
727
+ "grad_norm": 0.24781277775764465,
728
+ "learning_rate": 4.4457399392804085e-05,
729
+ "loss": 0.5635,
730
+ "step": 51500
731
+ },
732
+ {
733
+ "epoch": 1.12,
734
+ "grad_norm": 0.30817893147468567,
735
+ "learning_rate": 4.440356996748703e-05,
736
+ "loss": 0.5499,
737
+ "step": 52000
738
+ }
739
+ ],
740
+ "logging_steps": 500,
741
+ "max_steps": 464430,
742
+ "num_input_tokens_seen": 0,
743
+ "num_train_epochs": 10,
744
+ "save_steps": 2000,
745
+ "total_flos": 9.6584872230912e+17,
746
+ "train_batch_size": 1,
747
+ "trial_name": null,
748
+ "trial_params": null
749
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c74dc971d3ac85dec76d83a1d935d118eb35c37b7602b1b868c958e6f693ee
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff