terry69 commited on
Commit
3e5c819
1 Parent(s): b4faafa

Model save

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ model-index:
10
+ - name: llama10pGrad_2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # llama10pGrad_2
18
+
19
+ 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 None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.2419
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0002
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 128
48
+ - total_eval_batch_size: 16
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.842 | 1.0 | 812 | 1.2419 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.11.1
64
+ - Transformers 4.41.1
65
+ - Pytorch 2.3.0+cu121
66
+ - Datasets 2.19.1
67
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 6,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "gate_proj",
28
+ "o_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e21c165d7671148728932435a1b7478e324a0487728e9f3fa741956dc865d9
3
+ size 62973728
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2.0167297520684237e+18,
4
+ "train_loss": 0.8562019185479639,
5
+ "train_runtime": 32009.8427,
6
+ "train_samples": 103932,
7
+ "train_samples_per_second": 3.247,
8
+ "train_steps_per_second": 0.025
9
+ }
runs/Jun12_05-21-45_COE-CS-sv003/events.out.tfevents.1718170111.COE-CS-sv003.1146110.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e747720d71e14f4e9492602c32bc226cba29ae106ca493ba36dca227a38c13ad
3
- size 38943
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7272ca389df1b11459814e16de6c44b47d70d8ab09387e28a43f5abd0af61616
3
+ size 39990
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2.0167297520684237e+18,
4
+ "train_loss": 0.8562019185479639,
5
+ "train_runtime": 32009.8427,
6
+ "train_samples": 103932,
7
+ "train_samples_per_second": 3.247,
8
+ "train_steps_per_second": 0.025
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 812,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0012315270935960591,
13
+ "grad_norm": 0.2949771583080292,
14
+ "learning_rate": 2.4390243902439027e-06,
15
+ "loss": 0.9838,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006157635467980296,
20
+ "grad_norm": 0.3101727366447449,
21
+ "learning_rate": 1.2195121951219513e-05,
22
+ "loss": 0.9644,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.012315270935960592,
27
+ "grad_norm": 0.3715027868747711,
28
+ "learning_rate": 2.4390243902439026e-05,
29
+ "loss": 0.9825,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.01847290640394089,
34
+ "grad_norm": 0.11249574273824692,
35
+ "learning_rate": 3.6585365853658535e-05,
36
+ "loss": 0.9393,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.024630541871921183,
41
+ "grad_norm": 0.08815101534128189,
42
+ "learning_rate": 4.878048780487805e-05,
43
+ "loss": 0.9236,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.03078817733990148,
48
+ "grad_norm": 0.10426054894924164,
49
+ "learning_rate": 6.097560975609756e-05,
50
+ "loss": 0.9237,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.03694581280788178,
55
+ "grad_norm": 0.1105574294924736,
56
+ "learning_rate": 7.317073170731707e-05,
57
+ "loss": 0.9153,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.04310344827586207,
62
+ "grad_norm": 0.09308202564716339,
63
+ "learning_rate": 8.53658536585366e-05,
64
+ "loss": 0.9281,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.04926108374384237,
69
+ "grad_norm": 0.09463588148355484,
70
+ "learning_rate": 9.75609756097561e-05,
71
+ "loss": 0.9157,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.05541871921182266,
76
+ "grad_norm": 0.11583919823169708,
77
+ "learning_rate": 0.00010975609756097563,
78
+ "loss": 0.8853,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.06157635467980296,
83
+ "grad_norm": 0.09693233668804169,
84
+ "learning_rate": 0.00012195121951219512,
85
+ "loss": 0.8707,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.06773399014778325,
90
+ "grad_norm": 0.0934528186917305,
91
+ "learning_rate": 0.00013414634146341464,
92
+ "loss": 0.8749,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.07389162561576355,
97
+ "grad_norm": 0.10069940984249115,
98
+ "learning_rate": 0.00014634146341463414,
99
+ "loss": 0.8685,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.08004926108374384,
104
+ "grad_norm": 0.09800374507904053,
105
+ "learning_rate": 0.00015853658536585366,
106
+ "loss": 0.8713,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.08620689655172414,
111
+ "grad_norm": 0.12216204404830933,
112
+ "learning_rate": 0.0001707317073170732,
113
+ "loss": 0.8685,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.09236453201970443,
118
+ "grad_norm": 0.09282781183719635,
119
+ "learning_rate": 0.0001829268292682927,
120
+ "loss": 0.8689,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.09852216748768473,
125
+ "grad_norm": 0.09639699012041092,
126
+ "learning_rate": 0.0001951219512195122,
127
+ "loss": 0.8815,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.10467980295566502,
132
+ "grad_norm": 0.0974295362830162,
133
+ "learning_rate": 0.0001999916658654738,
134
+ "loss": 0.8761,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.11083743842364532,
139
+ "grad_norm": 0.08732698857784271,
140
+ "learning_rate": 0.0001999407400739705,
141
+ "loss": 0.8938,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.11699507389162561,
146
+ "grad_norm": 0.09193898737430573,
147
+ "learning_rate": 0.00019984354211555644,
148
+ "loss": 0.851,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.12315270935960591,
153
+ "grad_norm": 0.09586363285779953,
154
+ "learning_rate": 0.00019970011699250152,
155
+ "loss": 0.9015,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.12931034482758622,
160
+ "grad_norm": 0.10461977124214172,
161
+ "learning_rate": 0.00019951053111006976,
162
+ "loss": 0.8593,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.1354679802955665,
167
+ "grad_norm": 0.10003778338432312,
168
+ "learning_rate": 0.00019927487224577402,
169
+ "loss": 0.8596,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.1416256157635468,
174
+ "grad_norm": 0.08891289681196213,
175
+ "learning_rate": 0.0001989932495087353,
176
+ "loss": 0.8813,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.1477832512315271,
181
+ "grad_norm": 0.09503619372844696,
182
+ "learning_rate": 0.0001986657932891657,
183
+ "loss": 0.8774,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.1539408866995074,
188
+ "grad_norm": 0.08597695827484131,
189
+ "learning_rate": 0.0001982926551979982,
190
+ "loss": 0.85,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.16009852216748768,
195
+ "grad_norm": 0.0924694836139679,
196
+ "learning_rate": 0.00019787400799669154,
197
+ "loss": 0.8549,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.16625615763546797,
202
+ "grad_norm": 0.10183464735746384,
203
+ "learning_rate": 0.00019741004551724207,
204
+ "loss": 0.8501,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1724137931034483,
209
+ "grad_norm": 0.11476742476224899,
210
+ "learning_rate": 0.00019690098257244064,
211
+ "loss": 0.8757,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.17857142857142858,
216
+ "grad_norm": 0.10026735812425613,
217
+ "learning_rate": 0.00019634705485641488,
218
+ "loss": 0.8547,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.18472906403940886,
223
+ "grad_norm": 0.0951361283659935,
224
+ "learning_rate": 0.00019574851883550395,
225
+ "loss": 0.859,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.19088669950738915,
230
+ "grad_norm": 0.09267546981573105,
231
+ "learning_rate": 0.00019510565162951537,
232
+ "loss": 0.8635,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.19704433497536947,
237
+ "grad_norm": 0.10676441341638565,
238
+ "learning_rate": 0.00019441875088341997,
239
+ "loss": 0.8707,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.20320197044334976,
244
+ "grad_norm": 0.08962992578744888,
245
+ "learning_rate": 0.00019368813462954316,
246
+ "loss": 0.8341,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.20935960591133004,
251
+ "grad_norm": 0.10068422555923462,
252
+ "learning_rate": 0.00019291414114031743,
253
+ "loss": 0.8063,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.21551724137931033,
258
+ "grad_norm": 0.09436162561178207,
259
+ "learning_rate": 0.00019209712877166349,
260
+ "loss": 0.8477,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.22167487684729065,
265
+ "grad_norm": 0.0981898158788681,
266
+ "learning_rate": 0.00019123747579707275,
267
+ "loss": 0.8634,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.22783251231527094,
272
+ "grad_norm": 0.09050612151622772,
273
+ "learning_rate": 0.00019033558023246844,
274
+ "loss": 0.8693,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.23399014778325122,
279
+ "grad_norm": 0.09567181766033173,
280
+ "learning_rate": 0.0001893918596519257,
281
+ "loss": 0.8721,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.24014778325123154,
286
+ "grad_norm": 0.09379356354475021,
287
+ "learning_rate": 0.00018840675099433636,
288
+ "loss": 0.8572,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.24630541871921183,
293
+ "grad_norm": 0.09768428653478622,
294
+ "learning_rate": 0.00018738071036110808,
295
+ "loss": 0.8675,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.2524630541871921,
300
+ "grad_norm": 0.0965338945388794,
301
+ "learning_rate": 0.00018631421280499116,
302
+ "loss": 0.869,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.25862068965517243,
307
+ "grad_norm": 0.08635499328374863,
308
+ "learning_rate": 0.00018520775211013093,
309
+ "loss": 0.842,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.2647783251231527,
314
+ "grad_norm": 0.08754138648509979,
315
+ "learning_rate": 0.00018406184056344782,
316
+ "loss": 0.8305,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.270935960591133,
321
+ "grad_norm": 0.09839050471782684,
322
+ "learning_rate": 0.00018287700871745036,
323
+ "loss": 0.835,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.2770935960591133,
328
+ "grad_norm": 0.11136944591999054,
329
+ "learning_rate": 0.0001816538051445916,
330
+ "loss": 0.8588,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.2832512315270936,
335
+ "grad_norm": 0.0912737250328064,
336
+ "learning_rate": 0.00018039279618328212,
337
+ "loss": 0.8624,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.2894088669950739,
342
+ "grad_norm": 0.07793363183736801,
343
+ "learning_rate": 0.00017909456567567772,
344
+ "loss": 0.8345,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.2955665024630542,
349
+ "grad_norm": 0.10047736018896103,
350
+ "learning_rate": 0.0001777597146973627,
351
+ "loss": 0.8585,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.3017241379310345,
356
+ "grad_norm": 0.08737127482891083,
357
+ "learning_rate": 0.00017638886127905427,
358
+ "loss": 0.8397,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.3078817733990148,
363
+ "grad_norm": 0.1030949130654335,
364
+ "learning_rate": 0.00017498264012045687,
365
+ "loss": 0.8794,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.31403940886699505,
370
+ "grad_norm": 0.08828911185264587,
371
+ "learning_rate": 0.00017354170229639856,
372
+ "loss": 0.854,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.32019704433497537,
377
+ "grad_norm": 0.0845285952091217,
378
+ "learning_rate": 0.00017206671495538612,
379
+ "loss": 0.8413,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.3263546798029557,
384
+ "grad_norm": 0.09490133821964264,
385
+ "learning_rate": 0.0001705583610107178,
386
+ "loss": 0.8278,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.33251231527093594,
391
+ "grad_norm": 0.0908144861459732,
392
+ "learning_rate": 0.0001690173388242972,
393
+ "loss": 0.8589,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.33866995073891626,
398
+ "grad_norm": 0.09003310650587082,
399
+ "learning_rate": 0.00016744436188329456,
400
+ "loss": 0.8572,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.3448275862068966,
405
+ "grad_norm": 0.09844415634870529,
406
+ "learning_rate": 0.0001658401584698049,
407
+ "loss": 0.8628,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.35098522167487683,
412
+ "grad_norm": 0.09799636900424957,
413
+ "learning_rate": 0.00016420547132365635,
414
+ "loss": 0.86,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.35714285714285715,
419
+ "grad_norm": 0.0892237052321434,
420
+ "learning_rate": 0.00016254105729852464,
421
+ "loss": 0.8818,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.3633004926108374,
426
+ "grad_norm": 0.09125364571809769,
427
+ "learning_rate": 0.00016084768701151263,
428
+ "loss": 0.8788,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.3694581280788177,
433
+ "grad_norm": 0.09678944945335388,
434
+ "learning_rate": 0.00015912614448635782,
435
+ "loss": 0.8846,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.37561576354679804,
440
+ "grad_norm": 0.09397515654563904,
441
+ "learning_rate": 0.00015737722679043248,
442
+ "loss": 0.8566,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3817733990147783,
447
+ "grad_norm": 0.08986654132604599,
448
+ "learning_rate": 0.00015560174366570446,
449
+ "loss": 0.8321,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3879310344827586,
454
+ "grad_norm": 0.09454771876335144,
455
+ "learning_rate": 0.00015380051715382996,
456
+ "loss": 0.8826,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.39408866995073893,
461
+ "grad_norm": 0.092396080493927,
462
+ "learning_rate": 0.0001519743812155516,
463
+ "loss": 0.8526,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.4002463054187192,
468
+ "grad_norm": 0.10106166452169418,
469
+ "learning_rate": 0.00015012418134457755,
470
+ "loss": 0.847,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.4064039408866995,
475
+ "grad_norm": 0.091457299888134,
476
+ "learning_rate": 0.00014825077417612186,
477
+ "loss": 0.8469,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.4125615763546798,
482
+ "grad_norm": 0.09755238145589828,
483
+ "learning_rate": 0.0001463550270902851,
484
+ "loss": 0.8296,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.4187192118226601,
489
+ "grad_norm": 0.09282223135232925,
490
+ "learning_rate": 0.00014443781781046136,
491
+ "loss": 0.8452,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.4248768472906404,
496
+ "grad_norm": 0.09217504411935806,
497
+ "learning_rate": 0.0001425000339969554,
498
+ "loss": 0.8357,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.43103448275862066,
503
+ "grad_norm": 0.0990719348192215,
504
+ "learning_rate": 0.00014054257283599973,
505
+ "loss": 0.8402,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.437192118226601,
510
+ "grad_norm": 0.09021298587322235,
511
+ "learning_rate": 0.0001385663406243607,
512
+ "loss": 0.8454,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.4433497536945813,
517
+ "grad_norm": 0.09311360120773315,
518
+ "learning_rate": 0.00013657225234972695,
519
+ "loss": 0.8449,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.44950738916256155,
524
+ "grad_norm": 0.09712479263544083,
525
+ "learning_rate": 0.00013456123126707334,
526
+ "loss": 0.8718,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.45566502463054187,
531
+ "grad_norm": 0.098002128303051,
532
+ "learning_rate": 0.00013253420847119803,
533
+ "loss": 0.8467,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.4618226600985222,
538
+ "grad_norm": 0.08402260392904282,
539
+ "learning_rate": 0.0001304921224656289,
540
+ "loss": 0.8279,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.46798029556650245,
545
+ "grad_norm": 0.09465406835079193,
546
+ "learning_rate": 0.0001284359187281004,
547
+ "loss": 0.8749,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.47413793103448276,
552
+ "grad_norm": 0.08619461953639984,
553
+ "learning_rate": 0.00012636654927280073,
554
+ "loss": 0.8495,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.4802955665024631,
559
+ "grad_norm": 0.09889654070138931,
560
+ "learning_rate": 0.0001242849722095936,
561
+ "loss": 0.8447,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.48645320197044334,
566
+ "grad_norm": 0.0903097614645958,
567
+ "learning_rate": 0.00012219215130041656,
568
+ "loss": 0.8186,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.49261083743842365,
573
+ "grad_norm": 0.09543944150209427,
574
+ "learning_rate": 0.00012008905551306356,
575
+ "loss": 0.8497,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4987684729064039,
580
+ "grad_norm": 0.09465156495571136,
581
+ "learning_rate": 0.00011797665857255621,
582
+ "loss": 0.8496,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.5049261083743842,
587
+ "grad_norm": 0.09152977913618088,
588
+ "learning_rate": 0.00011585593851031347,
589
+ "loss": 0.8406,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.5110837438423645,
594
+ "grad_norm": 0.09556221961975098,
595
+ "learning_rate": 0.00011372787721132648,
596
+ "loss": 0.851,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.5172413793103449,
601
+ "grad_norm": 0.09278736263513565,
602
+ "learning_rate": 0.00011159345995955006,
603
+ "loss": 0.8636,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.5233990147783252,
608
+ "grad_norm": 0.09471924602985382,
609
+ "learning_rate": 0.00010945367498171993,
610
+ "loss": 0.8628,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.5295566502463054,
615
+ "grad_norm": 0.09358783066272736,
616
+ "learning_rate": 0.00010730951298980776,
617
+ "loss": 0.864,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.5357142857142857,
622
+ "grad_norm": 0.10094843059778214,
623
+ "learning_rate": 0.00010516196672232539,
624
+ "loss": 0.8698,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.541871921182266,
629
+ "grad_norm": 0.09740354865789413,
630
+ "learning_rate": 0.00010301203048469083,
631
+ "loss": 0.8419,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.5480295566502463,
636
+ "grad_norm": 0.09911592304706573,
637
+ "learning_rate": 0.00010086069968886885,
638
+ "loss": 0.8524,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.5541871921182266,
643
+ "grad_norm": 0.09378519654273987,
644
+ "learning_rate": 9.870897039249911e-05,
645
+ "loss": 0.8673,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.5603448275862069,
650
+ "grad_norm": 0.0991242304444313,
651
+ "learning_rate": 9.655783883772545e-05,
652
+ "loss": 0.8624,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.5665024630541872,
657
+ "grad_norm": 0.09386149048805237,
658
+ "learning_rate": 9.440830098993969e-05,
659
+ "loss": 0.8161,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5726600985221675,
664
+ "grad_norm": 0.09219907224178314,
665
+ "learning_rate": 9.22613520766537e-05,
666
+ "loss": 0.8519,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5788177339901478,
671
+ "grad_norm": 0.09010721743106842,
672
+ "learning_rate": 9.011798612671286e-05,
673
+ "loss": 0.8489,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5849753694581281,
678
+ "grad_norm": 0.10001237690448761,
679
+ "learning_rate": 8.797919551006475e-05,
680
+ "loss": 0.8526,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5911330049261084,
685
+ "grad_norm": 0.09620565176010132,
686
+ "learning_rate": 8.58459704782957e-05,
687
+ "loss": 0.85,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5972906403940886,
692
+ "grad_norm": 0.0897950753569603,
693
+ "learning_rate": 8.371929870614833e-05,
694
+ "loss": 0.8458,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.603448275862069,
699
+ "grad_norm": 0.08846917748451233,
700
+ "learning_rate": 8.160016483423199e-05,
701
+ "loss": 0.8512,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.6096059113300493,
706
+ "grad_norm": 0.09186448156833649,
707
+ "learning_rate": 7.948955001313811e-05,
708
+ "loss": 0.8699,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.6157635467980296,
713
+ "grad_norm": 0.10069604963064194,
714
+ "learning_rate": 7.738843144917119e-05,
715
+ "loss": 0.8398,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.6219211822660099,
720
+ "grad_norm": 0.09906591475009918,
721
+ "learning_rate": 7.529778195190645e-05,
722
+ "loss": 0.8378,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.6280788177339901,
727
+ "grad_norm": 0.09918715059757233,
728
+ "learning_rate": 7.321856948378259e-05,
729
+ "loss": 0.8584,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.6342364532019704,
734
+ "grad_norm": 0.09439591318368912,
735
+ "learning_rate": 7.115175671193913e-05,
736
+ "loss": 0.8519,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.6403940886699507,
741
+ "grad_norm": 0.0965607687830925,
742
+ "learning_rate": 6.909830056250527e-05,
743
+ "loss": 0.8607,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.646551724137931,
748
+ "grad_norm": 0.09937562048435211,
749
+ "learning_rate": 6.7059151777547e-05,
750
+ "loss": 0.8547,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.6527093596059114,
755
+ "grad_norm": 0.10041774064302444,
756
+ "learning_rate": 6.503525447487715e-05,
757
+ "loss": 0.8584,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.6588669950738916,
762
+ "grad_norm": 0.09252887219190598,
763
+ "learning_rate": 6.30275457109327e-05,
764
+ "loss": 0.8824,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.6650246305418719,
769
+ "grad_norm": 0.09451112896203995,
770
+ "learning_rate": 6.103695504692122e-05,
771
+ "loss": 0.8371,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.6711822660098522,
776
+ "grad_norm": 0.10130809247493744,
777
+ "learning_rate": 5.906440411843787e-05,
778
+ "loss": 0.8807,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.6773399014778325,
783
+ "grad_norm": 0.09514950215816498,
784
+ "learning_rate": 5.7110806208751655e-05,
785
+ "loss": 0.8571,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6834975369458128,
790
+ "grad_norm": 0.0906277671456337,
791
+ "learning_rate": 5.5177065825958966e-05,
792
+ "loss": 0.8376,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.6896551724137931,
797
+ "grad_norm": 0.08796288818120956,
798
+ "learning_rate": 5.326407828419979e-05,
799
+ "loss": 0.8283,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.6958128078817734,
804
+ "grad_norm": 0.09175130724906921,
805
+ "learning_rate": 5.137272928913097e-05,
806
+ "loss": 0.8502,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.7019704433497537,
811
+ "grad_norm": 0.09584875404834747,
812
+ "learning_rate": 4.9503894527847964e-05,
813
+ "loss": 0.8398,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.708128078817734,
818
+ "grad_norm": 0.09284964203834534,
819
+ "learning_rate": 4.7658439263445e-05,
820
+ "loss": 0.8328,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.7142857142857143,
825
+ "grad_norm": 0.09421636164188385,
826
+ "learning_rate": 4.583721793440188e-05,
827
+ "loss": 0.8395,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.7204433497536946,
832
+ "grad_norm": 0.1052021011710167,
833
+ "learning_rate": 4.4041073758982335e-05,
834
+ "loss": 0.8579,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.7266009852216748,
839
+ "grad_norm": 0.09751743078231812,
840
+ "learning_rate": 4.227083834482728e-05,
841
+ "loss": 0.8348,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.7327586206896551,
846
+ "grad_norm": 0.09555874764919281,
847
+ "learning_rate": 4.052733130392367e-05,
848
+ "loss": 0.8386,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.7389162561576355,
853
+ "grad_norm": 0.09556646645069122,
854
+ "learning_rate": 3.881135987312757e-05,
855
+ "loss": 0.8858,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.7450738916256158,
860
+ "grad_norm": 0.0967402383685112,
861
+ "learning_rate": 3.712371854041654e-05,
862
+ "loss": 0.8306,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.7512315270935961,
867
+ "grad_norm": 0.1028241440653801,
868
+ "learning_rate": 3.546518867704499e-05,
869
+ "loss": 0.8657,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.7573891625615764,
874
+ "grad_norm": 0.09105245769023895,
875
+ "learning_rate": 3.383653817577216e-05,
876
+ "loss": 0.8398,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.7635467980295566,
881
+ "grad_norm": 0.09858682006597519,
882
+ "learning_rate": 3.223852109533112e-05,
883
+ "loss": 0.8218,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.7697044334975369,
888
+ "grad_norm": 0.09542707353830338,
889
+ "learning_rate": 3.0671877311302244e-05,
890
+ "loss": 0.8243,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.7758620689655172,
895
+ "grad_norm": 0.09767568111419678,
896
+ "learning_rate": 2.9137332173554043e-05,
897
+ "loss": 0.8449,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.7820197044334976,
902
+ "grad_norm": 0.10336579382419586,
903
+ "learning_rate": 2.763559617040876e-05,
904
+ "loss": 0.8441,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.7881773399014779,
909
+ "grad_norm": 0.09993448853492737,
910
+ "learning_rate": 2.616736459968936e-05,
911
+ "loss": 0.8388,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7943349753694581,
916
+ "grad_norm": 0.09298530966043472,
917
+ "learning_rate": 2.473331724679917e-05,
918
+ "loss": 0.8385,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.8004926108374384,
923
+ "grad_norm": 0.09422852843999863,
924
+ "learning_rate": 2.33341180699841e-05,
925
+ "loss": 0.8178,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.8066502463054187,
930
+ "grad_norm": 0.09662608057260513,
931
+ "learning_rate": 2.1970414892922442e-05,
932
+ "loss": 0.8483,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.812807881773399,
937
+ "grad_norm": 0.09834180027246475,
938
+ "learning_rate": 2.0642839104785272e-05,
939
+ "loss": 0.8452,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.8189655172413793,
944
+ "grad_norm": 0.12449537217617035,
945
+ "learning_rate": 1.9352005367905536e-05,
946
+ "loss": 0.8379,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.8251231527093597,
951
+ "grad_norm": 0.10711503773927689,
952
+ "learning_rate": 1.8098511333192024e-05,
953
+ "loss": 0.8604,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.8312807881773399,
958
+ "grad_norm": 0.09627261012792587,
959
+ "learning_rate": 1.6882937363419203e-05,
960
+ "loss": 0.8234,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.8374384236453202,
965
+ "grad_norm": 0.10317688435316086,
966
+ "learning_rate": 1.570584626452173e-05,
967
+ "loss": 0.8325,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.8435960591133005,
972
+ "grad_norm": 0.10015459358692169,
973
+ "learning_rate": 1.4567783025017301e-05,
974
+ "loss": 0.8418,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.8497536945812808,
979
+ "grad_norm": 0.09650367498397827,
980
+ "learning_rate": 1.3469274563679402e-05,
981
+ "loss": 0.8248,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.8559113300492611,
986
+ "grad_norm": 0.10634295642375946,
987
+ "learning_rate": 1.2410829485575704e-05,
988
+ "loss": 0.8538,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.8620689655172413,
993
+ "grad_norm": 0.09615869075059891,
994
+ "learning_rate": 1.1392937846586215e-05,
995
+ "loss": 0.8669,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.8682266009852216,
1000
+ "grad_norm": 0.09273919463157654,
1001
+ "learning_rate": 1.0416070926509113e-05,
1002
+ "loss": 0.8374,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.874384236453202,
1007
+ "grad_norm": 0.10093870013952255,
1008
+ "learning_rate": 9.48068101086026e-06,
1009
+ "loss": 0.8638,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.8805418719211823,
1014
+ "grad_norm": 0.09216069430112839,
1015
+ "learning_rate": 8.58720118146662e-06,
1016
+ "loss": 0.8302,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.8866995073891626,
1021
+ "grad_norm": 0.09972187131643295,
1022
+ "learning_rate": 7.736045115951251e-06,
1023
+ "loss": 0.8679,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.8928571428571429,
1028
+ "grad_norm": 0.09708079695701599,
1029
+ "learning_rate": 6.927606896202066e-06,
1030
+ "loss": 0.8348,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.8990147783251231,
1035
+ "grad_norm": 0.09960056841373444,
1036
+ "learning_rate": 6.16226082591359e-06,
1037
+ "loss": 0.8403,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.9051724137931034,
1042
+ "grad_norm": 0.09734474867582321,
1043
+ "learning_rate": 5.440361257285742e-06,
1044
+ "loss": 0.8567,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.9113300492610837,
1049
+ "grad_norm": 0.0940781757235527,
1050
+ "learning_rate": 4.762242426960262e-06,
1051
+ "loss": 0.8456,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.9174876847290641,
1056
+ "grad_norm": 0.09184621274471283,
1057
+ "learning_rate": 4.128218301270359e-06,
1058
+ "loss": 0.8516,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.9236453201970444,
1063
+ "grad_norm": 0.095575712621212,
1064
+ "learning_rate": 3.5385824308756587e-06,
1065
+ "loss": 0.8433,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.9298029556650246,
1070
+ "grad_norm": 0.09812497347593307,
1071
+ "learning_rate": 2.9936078148492973e-06,
1072
+ "loss": 0.865,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.9359605911330049,
1077
+ "grad_norm": 0.09702542424201965,
1078
+ "learning_rate": 2.493546774280531e-06,
1079
+ "loss": 0.8249,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.9421182266009852,
1084
+ "grad_norm": 0.09994158893823624,
1085
+ "learning_rate": 2.0386308354509942e-06,
1086
+ "loss": 0.8355,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.9482758620689655,
1091
+ "grad_norm": 0.09425787627696991,
1092
+ "learning_rate": 1.6290706226390285e-06,
1093
+ "loss": 0.8094,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.9544334975369458,
1098
+ "grad_norm": 0.10560785979032516,
1099
+ "learning_rate": 1.2650557606013635e-06,
1100
+ "loss": 0.8512,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.9605911330049262,
1105
+ "grad_norm": 0.09790593385696411,
1106
+ "learning_rate": 9.46754786777726e-07,
1107
+ "loss": 0.8378,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.9667487684729064,
1112
+ "grad_norm": 0.09701854735612869,
1113
+ "learning_rate": 6.74315073258569e-07,
1114
+ "loss": 0.8201,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.9729064039408867,
1119
+ "grad_norm": 0.0912141278386116,
1120
+ "learning_rate": 4.4786275855247527e-07,
1121
+ "loss": 0.8304,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.979064039408867,
1126
+ "grad_norm": 0.10074811428785324,
1127
+ "learning_rate": 2.675026891844512e-07,
1128
+ "loss": 0.8649,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.9852216748768473,
1133
+ "grad_norm": 0.09760763496160507,
1134
+ "learning_rate": 1.333183711524133e-07,
1135
+ "loss": 0.8527,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.9913793103448276,
1140
+ "grad_norm": 0.10889925807714462,
1141
+ "learning_rate": 4.5371931264270864e-08,
1142
+ "loss": 0.8688,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.9975369458128078,
1147
+ "grad_norm": 0.0987965315580368,
1148
+ "learning_rate": 3.7040883734462683e-09,
1149
+ "loss": 0.842,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 1.0,
1154
+ "eval_loss": 1.241860270500183,
1155
+ "eval_runtime": 133.9183,
1156
+ "eval_samples_per_second": 8.625,
1157
+ "eval_steps_per_second": 0.545,
1158
+ "step": 812
1159
+ },
1160
+ {
1161
+ "epoch": 1.0,
1162
+ "step": 812,
1163
+ "total_flos": 2.0167297520684237e+18,
1164
+ "train_loss": 0.8562019185479639,
1165
+ "train_runtime": 32009.8427,
1166
+ "train_samples_per_second": 3.247,
1167
+ "train_steps_per_second": 0.025
1168
+ }
1169
+ ],
1170
+ "logging_steps": 5,
1171
+ "max_steps": 812,
1172
+ "num_input_tokens_seen": 0,
1173
+ "num_train_epochs": 1,
1174
+ "save_steps": 25,
1175
+ "stateful_callbacks": {
1176
+ "TrainerControl": {
1177
+ "args": {
1178
+ "should_epoch_stop": false,
1179
+ "should_evaluate": false,
1180
+ "should_log": false,
1181
+ "should_save": true,
1182
+ "should_training_stop": false
1183
+ },
1184
+ "attributes": {}
1185
+ }
1186
+ },
1187
+ "total_flos": 2.0167297520684237e+18,
1188
+ "train_batch_size": 8,
1189
+ "trial_name": null,
1190
+ "trial_params": null
1191
+ }