terry69 commited on
Commit
5566327
·
verified ·
1 Parent(s): c8f7730

Model save

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: meta-llama/Meta-Llama-3-8B
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: sanity_syntax_20p_100k
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # sanity_syntax_20p_100k
20
+
21
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.1748
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 4
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 64
50
+ - total_eval_batch_size: 16
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 1
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:------:|:----:|:---------------:|
60
+ | 1.2359 | 0.9992 | 895 | 1.1748 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.11.1
66
+ - Transformers 4.43.4
67
+ - Pytorch 2.3.1+cu121
68
+ - Datasets 2.19.1
69
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.999162712810494,
3
+ "total_flos": 1.1254972268150784e+16,
4
+ "train_loss": 1.2433469767011078,
5
+ "train_runtime": 20318.3129,
6
+ "train_samples": 99914,
7
+ "train_samples_per_second": 2.821,
8
+ "train_steps_per_second": 0.044
9
+ }
runs/Aug23_04-22-51_COE-CS-sv003/events.out.tfevents.1724387248.COE-CS-sv003.2786887.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb033a66841284ecbc39d1046b14c0e7acfbdd3337a9234b991bb7c7230650c1
3
- size 43103
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb463d1f832330e6f98d93125078df65300115d463e1f933aa1cefaa31615e9
3
+ size 43728
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.999162712810494,
3
+ "total_flos": 1.1254972268150784e+16,
4
+ "train_loss": 1.2433469767011078,
5
+ "train_runtime": 20318.3129,
6
+ "train_samples": 99914,
7
+ "train_samples_per_second": 2.821,
8
+ "train_steps_per_second": 0.044
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.999162712810494,
5
+ "eval_steps": 500,
6
+ "global_step": 895,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0011163829193413341,
13
+ "grad_norm": 0.3974737008844776,
14
+ "learning_rate": 2.2222222222222225e-06,
15
+ "loss": 1.607,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0055819145967066705,
20
+ "grad_norm": 0.4252789938746273,
21
+ "learning_rate": 1.1111111111111112e-05,
22
+ "loss": 1.5942,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.011163829193413341,
27
+ "grad_norm": 0.4658525758416883,
28
+ "learning_rate": 2.2222222222222223e-05,
29
+ "loss": 1.5877,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.01674574379012001,
34
+ "grad_norm": 0.27282017063503095,
35
+ "learning_rate": 3.3333333333333335e-05,
36
+ "loss": 1.5695,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.022327658386826682,
41
+ "grad_norm": 0.24165395076839943,
42
+ "learning_rate": 4.4444444444444447e-05,
43
+ "loss": 1.558,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.027909572983533353,
48
+ "grad_norm": 0.1767403193777301,
49
+ "learning_rate": 5.555555555555556e-05,
50
+ "loss": 1.4678,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.03349148758024002,
55
+ "grad_norm": 0.16356442786177314,
56
+ "learning_rate": 6.666666666666667e-05,
57
+ "loss": 1.467,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.039073402176946694,
62
+ "grad_norm": 0.15556520577978836,
63
+ "learning_rate": 7.777777777777778e-05,
64
+ "loss": 1.429,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.044655316773653364,
69
+ "grad_norm": 0.1263609432879071,
70
+ "learning_rate": 8.888888888888889e-05,
71
+ "loss": 1.4253,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.050237231370360035,
76
+ "grad_norm": 0.1696978939183065,
77
+ "learning_rate": 0.0001,
78
+ "loss": 1.3895,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.055819145967066705,
83
+ "grad_norm": 0.10830406775154863,
84
+ "learning_rate": 0.00011111111111111112,
85
+ "loss": 1.3645,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.061401060563773376,
90
+ "grad_norm": 0.08414898733986972,
91
+ "learning_rate": 0.00012222222222222224,
92
+ "loss": 1.3082,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.06698297516048005,
97
+ "grad_norm": 0.07973185533121883,
98
+ "learning_rate": 0.00013333333333333334,
99
+ "loss": 1.2962,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.07256488975718671,
104
+ "grad_norm": 0.09811845100733502,
105
+ "learning_rate": 0.00014444444444444444,
106
+ "loss": 1.3061,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.07814680435389339,
111
+ "grad_norm": 0.08298371354138047,
112
+ "learning_rate": 0.00015555555555555556,
113
+ "loss": 1.3017,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.08372871895060005,
118
+ "grad_norm": 0.07510078793315819,
119
+ "learning_rate": 0.0001666666666666667,
120
+ "loss": 1.2989,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.08931063354730673,
125
+ "grad_norm": 0.07085309149624731,
126
+ "learning_rate": 0.00017777777777777779,
127
+ "loss": 1.2787,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.09489254814401339,
132
+ "grad_norm": 0.09400917029194135,
133
+ "learning_rate": 0.00018888888888888888,
134
+ "loss": 1.2843,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.10047446274072007,
139
+ "grad_norm": 0.09230059652672952,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.262,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.10605637733742673,
146
+ "grad_norm": 0.10009657676945562,
147
+ "learning_rate": 0.00019998096274980728,
148
+ "loss": 1.2821,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.11163829193413341,
153
+ "grad_norm": 0.12201167887174731,
154
+ "learning_rate": 0.000199923858247567,
155
+ "loss": 1.2668,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.11722020653084007,
160
+ "grad_norm": 0.09628889966493127,
161
+ "learning_rate": 0.00019982870823553308,
162
+ "loss": 1.2503,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.12280212112754675,
167
+ "grad_norm": 0.10028621820088561,
168
+ "learning_rate": 0.00019969554894159723,
169
+ "loss": 1.2632,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.12838403572425341,
174
+ "grad_norm": 0.08593461106683208,
175
+ "learning_rate": 0.00019952443106549533,
176
+ "loss": 1.2396,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.1339659503209601,
181
+ "grad_norm": 0.08827739693201113,
182
+ "learning_rate": 0.00019931541975950378,
183
+ "loss": 1.2784,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.13954786491766677,
188
+ "grad_norm": 0.0911508607290428,
189
+ "learning_rate": 0.00019906859460363307,
190
+ "loss": 1.2689,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.14512977951437342,
195
+ "grad_norm": 0.12157025851983183,
196
+ "learning_rate": 0.00019878404957532814,
197
+ "loss": 1.2563,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.1507116941110801,
202
+ "grad_norm": 0.10772740664174668,
203
+ "learning_rate": 0.0001984618930136869,
204
+ "loss": 1.2853,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.15629360870778677,
209
+ "grad_norm": 0.09940063564218579,
210
+ "learning_rate": 0.00019810224757821064,
211
+ "loss": 1.241,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.16187552330449345,
216
+ "grad_norm": 0.09118466185918958,
217
+ "learning_rate": 0.00019770525020210204,
218
+ "loss": 1.2746,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.1674574379012001,
223
+ "grad_norm": 0.09674538853934604,
224
+ "learning_rate": 0.0001972710520401287,
225
+ "loss": 1.2561,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.17303935249790678,
230
+ "grad_norm": 0.1126652956332537,
231
+ "learning_rate": 0.0001967998184110713,
232
+ "loss": 1.257,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.17862126709461346,
237
+ "grad_norm": 0.0869341846350413,
238
+ "learning_rate": 0.00019629172873477995,
239
+ "loss": 1.2529,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.18420318169132013,
244
+ "grad_norm": 0.09888626799953022,
245
+ "learning_rate": 0.00019574697646386027,
246
+ "loss": 1.244,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.18978509628802678,
251
+ "grad_norm": 0.09785278620381999,
252
+ "learning_rate": 0.0001951657690100178,
253
+ "loss": 1.2334,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.19536701088473346,
258
+ "grad_norm": 0.07378537831469305,
259
+ "learning_rate": 0.0001945483276650868,
260
+ "loss": 1.2415,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.20094892548144014,
265
+ "grad_norm": 0.08814263560160436,
266
+ "learning_rate": 0.0001938948875167745,
267
+ "loss": 1.2512,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.20653084007814682,
272
+ "grad_norm": 0.09775538276417937,
273
+ "learning_rate": 0.00019320569735915271,
274
+ "loss": 1.2213,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.21211275467485347,
279
+ "grad_norm": 0.09538626874304115,
280
+ "learning_rate": 0.00019248101959793066,
281
+ "loss": 1.2354,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.21769466927156014,
286
+ "grad_norm": 0.08332625788355251,
287
+ "learning_rate": 0.00019172113015054532,
288
+ "loss": 1.2444,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.22327658386826682,
293
+ "grad_norm": 0.08309090570657847,
294
+ "learning_rate": 0.00019092631834110723,
295
+ "loss": 1.2316,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.2288584984649735,
300
+ "grad_norm": 0.09054323693110126,
301
+ "learning_rate": 0.0001900968867902419,
302
+ "loss": 1.27,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.23444041306168015,
307
+ "grad_norm": 0.08549436898181585,
308
+ "learning_rate": 0.00018923315129986835,
309
+ "loss": 1.2348,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.24002232765838682,
314
+ "grad_norm": 0.086610993256363,
315
+ "learning_rate": 0.00018833544073295917,
316
+ "loss": 1.2461,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2456042422550935,
321
+ "grad_norm": 0.08146109722648563,
322
+ "learning_rate": 0.00018740409688832764,
323
+ "loss": 1.2431,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.2511861568518002,
328
+ "grad_norm": 0.08232534290451142,
329
+ "learning_rate": 0.00018643947437048944,
330
+ "loss": 1.2408,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.25676807144850683,
335
+ "grad_norm": 0.08507739560575232,
336
+ "learning_rate": 0.00018544194045464886,
337
+ "loss": 1.243,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.26234998604521353,
342
+ "grad_norm": 0.09782665661618925,
343
+ "learning_rate": 0.00018441187494686053,
344
+ "loss": 1.2426,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.2679319006419202,
349
+ "grad_norm": 0.0809973818897895,
350
+ "learning_rate": 0.0001833496700394202,
351
+ "loss": 1.2345,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.27351381523862683,
356
+ "grad_norm": 0.09269081567542259,
357
+ "learning_rate": 0.00018225573016153945,
358
+ "loss": 1.2343,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.27909572983533354,
363
+ "grad_norm": 0.09671785308848269,
364
+ "learning_rate": 0.00018113047182536127,
365
+ "loss": 1.2327,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.2846776444320402,
370
+ "grad_norm": 0.0906432644454991,
371
+ "learning_rate": 0.00017997432346737524,
372
+ "loss": 1.2532,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.29025955902874684,
377
+ "grad_norm": 0.08371586611488784,
378
+ "learning_rate": 0.00017878772528529232,
379
+ "loss": 1.2384,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.29584147362545354,
384
+ "grad_norm": 0.08640773776491195,
385
+ "learning_rate": 0.000177571129070442,
386
+ "loss": 1.2193,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.3014233882221602,
391
+ "grad_norm": 0.08164649256677078,
392
+ "learning_rate": 0.00017632499803575474,
393
+ "loss": 1.2327,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.3070053028188669,
398
+ "grad_norm": 0.09156690890905773,
399
+ "learning_rate": 0.00017504980663939613,
400
+ "loss": 1.2534,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.31258721741557355,
405
+ "grad_norm": 0.08393163680296412,
406
+ "learning_rate": 0.00017374604040411935,
407
+ "loss": 1.2411,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.3181691320122802,
412
+ "grad_norm": 0.08340859881557235,
413
+ "learning_rate": 0.00017241419573240462,
414
+ "loss": 1.2398,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3237510466089869,
419
+ "grad_norm": 0.08622506272483123,
420
+ "learning_rate": 0.00017105477971745666,
421
+ "loss": 1.2321,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.32933296120569355,
426
+ "grad_norm": 0.08338497396964428,
427
+ "learning_rate": 0.00016966830995013133,
428
+ "loss": 1.2453,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.3349148758024002,
433
+ "grad_norm": 0.08718794446584939,
434
+ "learning_rate": 0.00016825531432186543,
435
+ "loss": 1.2134,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.3404967903991069,
440
+ "grad_norm": 0.09158015865602193,
441
+ "learning_rate": 0.00016681633082368498,
442
+ "loss": 1.223,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.34607870499581356,
447
+ "grad_norm": 0.08768121171152027,
448
+ "learning_rate": 0.0001653519073413675,
449
+ "loss": 1.235,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3516606195925202,
454
+ "grad_norm": 0.08907125432704804,
455
+ "learning_rate": 0.00016386260144683745,
456
+ "loss": 1.2169,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.3572425341892269,
461
+ "grad_norm": 0.08767993008424768,
462
+ "learning_rate": 0.00016234898018587337,
463
+ "loss": 1.2435,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.36282444878593356,
468
+ "grad_norm": 0.08991663909567185,
469
+ "learning_rate": 0.00016081161986220807,
470
+ "loss": 1.2371,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.36840636338264027,
475
+ "grad_norm": 0.07876061570647706,
476
+ "learning_rate": 0.00015925110581810394,
477
+ "loss": 1.2118,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.3739882779793469,
482
+ "grad_norm": 0.09088539514665886,
483
+ "learning_rate": 0.00015766803221148673,
484
+ "loss": 1.2333,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.37957019257605357,
489
+ "grad_norm": 0.09371191064756335,
490
+ "learning_rate": 0.00015606300178972287,
491
+ "loss": 1.2192,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.38515210717276027,
496
+ "grad_norm": 0.0988524027231739,
497
+ "learning_rate": 0.00015443662566012645,
498
+ "loss": 1.2201,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.3907340217694669,
503
+ "grad_norm": 0.08068655015289312,
504
+ "learning_rate": 0.00015278952305728324,
505
+ "loss": 1.2312,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.39631593636617357,
510
+ "grad_norm": 0.08530580419429784,
511
+ "learning_rate": 0.00015112232110728015,
512
+ "loss": 1.2103,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.4018978509628803,
517
+ "grad_norm": 0.0832856621155852,
518
+ "learning_rate": 0.00014943565458893,
519
+ "loss": 1.2049,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.4074797655595869,
524
+ "grad_norm": 0.10112900442930213,
525
+ "learning_rate": 0.00014773016569208283,
526
+ "loss": 1.2381,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.41306168015629363,
531
+ "grad_norm": 0.08250019530921109,
532
+ "learning_rate": 0.00014600650377311522,
533
+ "loss": 1.2185,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.4186435947530003,
538
+ "grad_norm": 0.0987578329954232,
539
+ "learning_rate": 0.0001442653251076912,
540
+ "loss": 1.2222,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.42422550934970693,
545
+ "grad_norm": 0.08530899013880136,
546
+ "learning_rate": 0.00014250729264088843,
547
+ "loss": 1.2556,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.42980742394641364,
552
+ "grad_norm": 0.10267562745822716,
553
+ "learning_rate": 0.00014073307573478526,
554
+ "loss": 1.2146,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.4353893385431203,
559
+ "grad_norm": 0.09189285950155643,
560
+ "learning_rate": 0.00013894334991360448,
561
+ "loss": 1.2206,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.44097125313982694,
566
+ "grad_norm": 0.08370196846674145,
567
+ "learning_rate": 0.00013713879660651068,
568
+ "loss": 1.2076,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.44655316773653364,
573
+ "grad_norm": 0.08423557906306067,
574
+ "learning_rate": 0.0001353201028881598,
575
+ "loss": 1.2223,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4521350823332403,
580
+ "grad_norm": 0.08292081122541138,
581
+ "learning_rate": 0.00013348796121709862,
582
+ "loss": 1.2294,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.457716996929947,
587
+ "grad_norm": 0.08767079524531268,
588
+ "learning_rate": 0.00013164306917211476,
589
+ "loss": 1.2229,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.46329891152665365,
594
+ "grad_norm": 0.0865942463810843,
595
+ "learning_rate": 0.000129786129186637,
596
+ "loss": 1.2163,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.4688808261233603,
601
+ "grad_norm": 0.08101515714055764,
602
+ "learning_rate": 0.00012791784828128724,
603
+ "loss": 1.2337,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.474462740720067,
608
+ "grad_norm": 0.09009147490161429,
609
+ "learning_rate": 0.00012603893779468604,
610
+ "loss": 1.2148,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.48004465531677365,
615
+ "grad_norm": 0.08757351279515291,
616
+ "learning_rate": 0.0001241501131126138,
617
+ "loss": 1.2056,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.4856265699134803,
622
+ "grad_norm": 0.08418609867162384,
623
+ "learning_rate": 0.00012225209339563145,
624
+ "loss": 1.2419,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.491208484510187,
629
+ "grad_norm": 0.08790367723325618,
630
+ "learning_rate": 0.0001203456013052634,
631
+ "loss": 1.2115,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.49679039910689365,
636
+ "grad_norm": 0.08071789319204539,
637
+ "learning_rate": 0.00011843136272884794,
638
+ "loss": 1.2072,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.5023723137036004,
643
+ "grad_norm": 0.0879278395825441,
644
+ "learning_rate": 0.00011651010650315923,
645
+ "loss": 1.2194,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.507954228300307,
650
+ "grad_norm": 0.08506166782358492,
651
+ "learning_rate": 0.00011458256413690633,
652
+ "loss": 1.2077,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.5135361428970137,
657
+ "grad_norm": 0.08984730610411729,
658
+ "learning_rate": 0.00011264946953221496,
659
+ "loss": 1.2484,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5191180574937203,
664
+ "grad_norm": 0.2978083078661545,
665
+ "learning_rate": 0.00011071155870519777,
666
+ "loss": 1.2491,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5246999720904271,
671
+ "grad_norm": 0.08504227931172395,
672
+ "learning_rate": 0.00010876956950572006,
673
+ "loss": 1.2268,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5302818866871337,
678
+ "grad_norm": 0.08620167875904892,
679
+ "learning_rate": 0.0001068242413364671,
680
+ "loss": 1.2252,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5358638012838404,
685
+ "grad_norm": 0.08669957736640198,
686
+ "learning_rate": 0.00010487631487142017,
687
+ "loss": 1.217,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.541445715880547,
692
+ "grad_norm": 0.08577871896034497,
693
+ "learning_rate": 0.00010292653177384876,
694
+ "loss": 1.2169,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.5470276304772537,
699
+ "grad_norm": 0.08417260057895289,
700
+ "learning_rate": 0.00010097563441392581,
701
+ "loss": 1.2354,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.5526095450739603,
706
+ "grad_norm": 0.08676422431924583,
707
+ "learning_rate": 9.90243655860742e-05,
708
+ "loss": 1.2039,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.5581914596706671,
713
+ "grad_norm": 0.09103906295111437,
714
+ "learning_rate": 9.707346822615128e-05,
715
+ "loss": 1.2194,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5637733742673737,
720
+ "grad_norm": 0.08594537537719427,
721
+ "learning_rate": 9.512368512857984e-05,
722
+ "loss": 1.1949,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5693552888640804,
727
+ "grad_norm": 0.08392759057088481,
728
+ "learning_rate": 9.317575866353292e-05,
729
+ "loss": 1.2196,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.574937203460787,
734
+ "grad_norm": 0.08201912454761111,
735
+ "learning_rate": 9.123043049427995e-05,
736
+ "loss": 1.2131,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.5805191180574937,
741
+ "grad_norm": 0.08925291750313868,
742
+ "learning_rate": 8.928844129480227e-05,
743
+ "loss": 1.2369,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.5861010326542004,
748
+ "grad_norm": 0.08954980070951671,
749
+ "learning_rate": 8.735053046778506e-05,
750
+ "loss": 1.2175,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.5916829472509071,
755
+ "grad_norm": 0.08574100993825345,
756
+ "learning_rate": 8.541743586309365e-05,
757
+ "loss": 1.2166,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.5972648618476137,
762
+ "grad_norm": 0.08840883290578404,
763
+ "learning_rate": 8.348989349684076e-05,
764
+ "loss": 1.2271,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.6028467764443204,
769
+ "grad_norm": 0.08443946017557556,
770
+ "learning_rate": 8.156863727115211e-05,
771
+ "loss": 1.2329,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.608428691041027,
776
+ "grad_norm": 0.0902640782545258,
777
+ "learning_rate": 7.965439869473664e-05,
778
+ "loss": 1.2253,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.6140106056377338,
783
+ "grad_norm": 0.08988630625422679,
784
+ "learning_rate": 7.774790660436858e-05,
785
+ "loss": 1.1785,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6195925202344404,
790
+ "grad_norm": 0.08134808753957644,
791
+ "learning_rate": 7.584988688738622e-05,
792
+ "loss": 1.2261,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.6251744348311471,
797
+ "grad_norm": 0.08768193779762151,
798
+ "learning_rate": 7.396106220531398e-05,
799
+ "loss": 1.2463,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.6307563494278537,
804
+ "grad_norm": 0.0885816930556393,
805
+ "learning_rate": 7.208215171871277e-05,
806
+ "loss": 1.2141,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6363382640245604,
811
+ "grad_norm": 0.08553683878588977,
812
+ "learning_rate": 7.021387081336301e-05,
813
+ "loss": 1.2026,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.641920178621267,
818
+ "grad_norm": 0.09505838067263224,
819
+ "learning_rate": 6.835693082788525e-05,
820
+ "loss": 1.2168,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.6475020932179738,
825
+ "grad_norm": 0.08769224685329463,
826
+ "learning_rate": 6.651203878290139e-05,
827
+ "loss": 1.2493,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.6530840078146805,
832
+ "grad_norm": 0.07990213288377576,
833
+ "learning_rate": 6.46798971118402e-05,
834
+ "loss": 1.2308,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.6586659224113871,
839
+ "grad_norm": 0.08133261350163556,
840
+ "learning_rate": 6.286120339348935e-05,
841
+ "loss": 1.2014,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.6642478370080938,
846
+ "grad_norm": 0.09363089434544866,
847
+ "learning_rate": 6.105665008639557e-05,
848
+ "loss": 1.2238,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.6698297516048004,
853
+ "grad_norm": 0.07910287951552411,
854
+ "learning_rate": 5.926692426521474e-05,
855
+ "loss": 1.2473,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6754116662015072,
860
+ "grad_norm": 0.0801209902764544,
861
+ "learning_rate": 5.749270735911158e-05,
862
+ "loss": 1.1975,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.6809935807982138,
867
+ "grad_norm": 0.08087293360533905,
868
+ "learning_rate": 5.573467489230879e-05,
869
+ "loss": 1.1966,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.6865754953949205,
874
+ "grad_norm": 0.08220997258417966,
875
+ "learning_rate": 5.399349622688479e-05,
876
+ "loss": 1.2345,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.6921574099916271,
881
+ "grad_norm": 0.0825575277760057,
882
+ "learning_rate": 5.226983430791722e-05,
883
+ "loss": 1.2289,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.6977393245883338,
888
+ "grad_norm": 0.08305460425818378,
889
+ "learning_rate": 5.0564345411070025e-05,
890
+ "loss": 1.204,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.7033212391850404,
895
+ "grad_norm": 0.08011105262542664,
896
+ "learning_rate": 4.8877678892719866e-05,
897
+ "loss": 1.1946,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.7089031537817472,
902
+ "grad_norm": 0.08686069747720479,
903
+ "learning_rate": 4.721047694271676e-05,
904
+ "loss": 1.2,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.7144850683784538,
909
+ "grad_norm": 0.08537977661965272,
910
+ "learning_rate": 4.556337433987359e-05,
911
+ "loss": 1.2054,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7200669829751605,
916
+ "grad_norm": 0.08857193949478791,
917
+ "learning_rate": 4.393699821027716e-05,
918
+ "loss": 1.1988,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.7256488975718671,
923
+ "grad_norm": 0.09608004999262602,
924
+ "learning_rate": 4.2331967788513295e-05,
925
+ "loss": 1.2226,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.7312308121685738,
930
+ "grad_norm": 0.08235757922811432,
931
+ "learning_rate": 4.074889418189608e-05,
932
+ "loss": 1.2202,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.7368127267652805,
937
+ "grad_norm": 0.08660069823512372,
938
+ "learning_rate": 3.9188380137791936e-05,
939
+ "loss": 1.215,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.7423946413619872,
944
+ "grad_norm": 0.08090639704744831,
945
+ "learning_rate": 3.7651019814126654e-05,
946
+ "loss": 1.2255,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.7479765559586938,
951
+ "grad_norm": 0.08082821477995833,
952
+ "learning_rate": 3.613739855316257e-05,
953
+ "loss": 1.2176,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.7535584705554005,
958
+ "grad_norm": 0.08469395080984878,
959
+ "learning_rate": 3.46480926586325e-05,
960
+ "loss": 1.2275,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.7591403851521071,
965
+ "grad_norm": 0.0871555466504494,
966
+ "learning_rate": 3.3183669176315045e-05,
967
+ "loss": 1.2351,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.7647222997488139,
972
+ "grad_norm": 0.08170223557553191,
973
+ "learning_rate": 3.174468567813461e-05,
974
+ "loss": 1.2074,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.7703042143455205,
979
+ "grad_norm": 0.0838318843856818,
980
+ "learning_rate": 3.033169004986873e-05,
981
+ "loss": 1.2396,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.7758861289422272,
986
+ "grad_norm": 0.08831381148889993,
987
+ "learning_rate": 2.894522028254334e-05,
988
+ "loss": 1.1947,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.7814680435389338,
993
+ "grad_norm": 0.08158536981215994,
994
+ "learning_rate": 2.7585804267595384e-05,
995
+ "loss": 1.208,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.7870499581356405,
1000
+ "grad_norm": 0.08116519613000232,
1001
+ "learning_rate": 2.6253959595880673e-05,
1002
+ "loss": 1.2191,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.7926318727323471,
1007
+ "grad_norm": 0.08294169676184929,
1008
+ "learning_rate": 2.495019336060387e-05,
1009
+ "loss": 1.195,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.7982137873290539,
1014
+ "grad_norm": 0.08406756837278591,
1015
+ "learning_rate": 2.367500196424529e-05,
1016
+ "loss": 1.2203,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.8037957019257606,
1021
+ "grad_norm": 0.08211403607563178,
1022
+ "learning_rate": 2.242887092955801e-05,
1023
+ "loss": 1.2041,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.8093776165224672,
1028
+ "grad_norm": 0.07980978787138238,
1029
+ "learning_rate": 2.121227471470768e-05,
1030
+ "loss": 1.2394,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.8149595311191739,
1035
+ "grad_norm": 0.08416184610807921,
1036
+ "learning_rate": 2.002567653262479e-05,
1037
+ "loss": 1.2228,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.8205414457158805,
1042
+ "grad_norm": 0.08256062792318115,
1043
+ "learning_rate": 1.8869528174638752e-05,
1044
+ "loss": 1.203,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.8261233603125873,
1049
+ "grad_norm": 0.09043351264554417,
1050
+ "learning_rate": 1.774426983846058e-05,
1051
+ "loss": 1.2275,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.8317052749092939,
1056
+ "grad_norm": 0.08486147964302236,
1057
+ "learning_rate": 1.6650329960579792e-05,
1058
+ "loss": 1.2208,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.8372871895060006,
1063
+ "grad_norm": 0.0935945466460169,
1064
+ "learning_rate": 1.5588125053139468e-05,
1065
+ "loss": 1.2131,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.8428691041027072,
1070
+ "grad_norm": 0.08282716353976063,
1071
+ "learning_rate": 1.4558059545351143e-05,
1072
+ "loss": 1.2284,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.8484510186994139,
1077
+ "grad_norm": 0.08286515378820142,
1078
+ "learning_rate": 1.3560525629510568e-05,
1079
+ "loss": 1.2086,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.8540329332961206,
1084
+ "grad_norm": 0.08295259360853054,
1085
+ "learning_rate": 1.259590311167238e-05,
1086
+ "loss": 1.2061,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.8596148478928273,
1091
+ "grad_norm": 0.08358389042910293,
1092
+ "learning_rate": 1.166455926704082e-05,
1093
+ "loss": 1.222,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.8651967624895339,
1098
+ "grad_norm": 0.08388863476839661,
1099
+ "learning_rate": 1.0766848700131648e-05,
1100
+ "loss": 1.2143,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.8707786770862406,
1105
+ "grad_norm": 0.08277339984932784,
1106
+ "learning_rate": 9.903113209758096e-06,
1107
+ "loss": 1.2192,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.8763605916829472,
1112
+ "grad_norm": 0.08938310164317657,
1113
+ "learning_rate": 9.073681658892775e-06,
1114
+ "loss": 1.2191,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.8819425062796539,
1119
+ "grad_norm": 0.07910593096708422,
1120
+ "learning_rate": 8.278869849454718e-06,
1121
+ "loss": 1.2269,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.8875244208763606,
1126
+ "grad_norm": 0.08295037453317607,
1127
+ "learning_rate": 7.5189804020693536e-06,
1128
+ "loss": 1.2021,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.8931063354730673,
1133
+ "grad_norm": 0.08199446080472911,
1134
+ "learning_rate": 6.794302640847294e-06,
1135
+ "loss": 1.1961,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.8986882500697739,
1140
+ "grad_norm": 0.08481342663212112,
1141
+ "learning_rate": 6.1051124832254944e-06,
1142
+ "loss": 1.2069,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.9042701646664806,
1147
+ "grad_norm": 0.08217551850800063,
1148
+ "learning_rate": 5.451672334913216e-06,
1149
+ "loss": 1.2055,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.9098520792631872,
1154
+ "grad_norm": 0.08322503504827561,
1155
+ "learning_rate": 4.834230989982213e-06,
1156
+ "loss": 1.2156,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.915433993859894,
1161
+ "grad_norm": 0.08125961805104615,
1162
+ "learning_rate": 4.253023536139733e-06,
1163
+ "loss": 1.2005,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.9210159084566006,
1168
+ "grad_norm": 0.09037682759604541,
1169
+ "learning_rate": 3.7082712652200867e-06,
1170
+ "loss": 1.2079,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.9265978230533073,
1175
+ "grad_norm": 0.08711894287392291,
1176
+ "learning_rate": 3.2001815889286856e-06,
1177
+ "loss": 1.232,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.9321797376500139,
1182
+ "grad_norm": 0.08367132801462379,
1183
+ "learning_rate": 2.728947959871353e-06,
1184
+ "loss": 1.1858,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.9377616522467206,
1189
+ "grad_norm": 0.0809801248589102,
1190
+ "learning_rate": 2.294749797897955e-06,
1191
+ "loss": 1.1871,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.9433435668434274,
1196
+ "grad_norm": 0.08412969109149288,
1197
+ "learning_rate": 1.8977524217893783e-06,
1198
+ "loss": 1.2248,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.948925481440134,
1203
+ "grad_norm": 0.08014128153610968,
1204
+ "learning_rate": 1.5381069863131037e-06,
1205
+ "loss": 1.2312,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.9545073960368406,
1210
+ "grad_norm": 0.08040835492341503,
1211
+ "learning_rate": 1.2159504246718522e-06,
1212
+ "loss": 1.2213,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.9600893106335473,
1217
+ "grad_norm": 0.08170226749481643,
1218
+ "learning_rate": 9.314053963669245e-07,
1219
+ "loss": 1.2114,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.965671225230254,
1224
+ "grad_norm": 0.08123838559159317,
1225
+ "learning_rate": 6.845802404962243e-07,
1226
+ "loss": 1.2455,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.9712531398269606,
1231
+ "grad_norm": 0.08532355248950987,
1232
+ "learning_rate": 4.7556893450466653e-07,
1233
+ "loss": 1.2017,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.9768350544236674,
1238
+ "grad_norm": 0.07935413274906811,
1239
+ "learning_rate": 3.044510584027771e-07,
1240
+ "loss": 1.203,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.982416969020374,
1245
+ "grad_norm": 0.07922680701516337,
1246
+ "learning_rate": 1.7129176446692984e-07,
1247
+ "loss": 1.1993,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.9879988836170807,
1252
+ "grad_norm": 0.08007277288266887,
1253
+ "learning_rate": 7.614175243301213e-08,
1254
+ "loss": 1.221,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.9935807982137873,
1259
+ "grad_norm": 0.08190648675567455,
1260
+ "learning_rate": 1.9037250192732726e-08,
1261
+ "loss": 1.2245,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.999162712810494,
1266
+ "grad_norm": 0.07884795604109555,
1267
+ "learning_rate": 0.0,
1268
+ "loss": 1.2359,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.999162712810494,
1273
+ "eval_loss": 1.1748292446136475,
1274
+ "eval_runtime": 1569.4225,
1275
+ "eval_samples_per_second": 8.524,
1276
+ "eval_steps_per_second": 0.533,
1277
+ "step": 895
1278
+ },
1279
+ {
1280
+ "epoch": 0.999162712810494,
1281
+ "step": 895,
1282
+ "total_flos": 1.1254972268150784e+16,
1283
+ "train_loss": 1.2433469767011078,
1284
+ "train_runtime": 20318.3129,
1285
+ "train_samples_per_second": 2.821,
1286
+ "train_steps_per_second": 0.044
1287
+ }
1288
+ ],
1289
+ "logging_steps": 5,
1290
+ "max_steps": 895,
1291
+ "num_input_tokens_seen": 0,
1292
+ "num_train_epochs": 1,
1293
+ "save_steps": 25,
1294
+ "stateful_callbacks": {
1295
+ "TrainerControl": {
1296
+ "args": {
1297
+ "should_epoch_stop": false,
1298
+ "should_evaluate": false,
1299
+ "should_log": false,
1300
+ "should_save": true,
1301
+ "should_training_stop": true
1302
+ },
1303
+ "attributes": {}
1304
+ }
1305
+ },
1306
+ "total_flos": 1.1254972268150784e+16,
1307
+ "train_batch_size": 4,
1308
+ "trial_name": null,
1309
+ "trial_params": null
1310
+ }