Mumamonster commited on
Commit
e307b81
·
verified ·
1 Parent(s): 79a32fd

Model save

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: Qwen2.5-1.5B-Open-R1-Distill
4
+ tags:
5
+ - generated_from_trainer
6
+ - trl
7
+ - sft
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for Qwen2.5-1.5B-Open-R1-Distill
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
22
+ generator = pipeline("text-generation", model="Mumamonster/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chi-zhang-working/huggingface/runs/177axnqk)
30
+
31
+
32
+ This model was trained with SFT.
33
+
34
+ ### Framework versions
35
+
36
+ - TRL: 0.16.0.dev0
37
+ - Transformers: 4.49.0
38
+ - Pytorch: 2.5.1
39
+ - Datasets: 3.3.2
40
+ - Tokenizers: 0.21.0
41
+
42
+ ## Citations
43
+
44
+
45
+
46
+ Cite TRL as:
47
+
48
+ ```bibtex
49
+ @misc{vonwerra2022trl,
50
+ title = {{TRL: Transformer Reinforcement Learning}},
51
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
52
+ year = 2020,
53
+ journal = {GitHub repository},
54
+ publisher = {GitHub},
55
+ howpublished = {\url{https://github.com/huggingface/trl}}
56
+ }
57
+ ```
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 102527278252032.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 1.3976,
5
+ "train_samples": 24772,
6
+ "train_samples_per_second": 5132.403,
7
+ "train_steps_per_second": 80.138
8
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.49.0"
14
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f50d7444bbe6e6adc26e3b1a8530c2e302f11d433df36327e64c7bfb3fab840
3
  size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959b7363530b70aed7aa54030fd31d9881cf14fb2bcff5e7c2bd785e113a5629
3
  size 3087467144
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 102527278252032.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 1.3976,
5
+ "train_samples": 24772,
6
+ "train_samples_per_second": 5132.403,
7
+ "train_steps_per_second": 80.138
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.21015761821366025,
5
+ "eval_steps": 500,
6
+ "global_step": 900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0011675423234092236,
13
+ "grad_norm": 2.5127346776517427,
14
+ "learning_rate": 1.1627906976744186e-06,
15
+ "loss": 0.9966,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.002335084646818447,
20
+ "grad_norm": 2.09708226442615,
21
+ "learning_rate": 2.325581395348837e-06,
22
+ "loss": 0.9925,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.0035026269702276708,
27
+ "grad_norm": 1.4734405270533653,
28
+ "learning_rate": 3.488372093023256e-06,
29
+ "loss": 0.9868,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.004670169293636894,
34
+ "grad_norm": 1.3838947335985932,
35
+ "learning_rate": 4.651162790697674e-06,
36
+ "loss": 0.9573,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.005837711617046118,
41
+ "grad_norm": 0.9249234118632634,
42
+ "learning_rate": 5.8139534883720935e-06,
43
+ "loss": 0.8709,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.0070052539404553416,
48
+ "grad_norm": 0.8820525269459344,
49
+ "learning_rate": 6.976744186046512e-06,
50
+ "loss": 0.8603,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.008172796263864565,
55
+ "grad_norm": 0.6997651909534601,
56
+ "learning_rate": 8.139534883720931e-06,
57
+ "loss": 0.8138,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.009340338587273789,
62
+ "grad_norm": 0.6385035962555277,
63
+ "learning_rate": 9.302325581395349e-06,
64
+ "loss": 0.8144,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.010507880910683012,
69
+ "grad_norm": 0.6459756376057639,
70
+ "learning_rate": 1.0465116279069768e-05,
71
+ "loss": 0.799,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.011675423234092236,
76
+ "grad_norm": 0.6011999115316619,
77
+ "learning_rate": 1.1627906976744187e-05,
78
+ "loss": 0.7696,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.01284296555750146,
83
+ "grad_norm": 0.5942896008568019,
84
+ "learning_rate": 1.2790697674418606e-05,
85
+ "loss": 0.779,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.014010507880910683,
90
+ "grad_norm": 0.6142073839262744,
91
+ "learning_rate": 1.3953488372093024e-05,
92
+ "loss": 0.7534,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.015178050204319907,
97
+ "grad_norm": 0.5945400236546515,
98
+ "learning_rate": 1.5116279069767441e-05,
99
+ "loss": 0.7705,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.01634559252772913,
104
+ "grad_norm": 0.6213344800847622,
105
+ "learning_rate": 1.6279069767441862e-05,
106
+ "loss": 0.7453,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.017513134851138354,
111
+ "grad_norm": 0.6234527297129722,
112
+ "learning_rate": 1.744186046511628e-05,
113
+ "loss": 0.7345,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.018680677174547577,
118
+ "grad_norm": 0.7664963436446808,
119
+ "learning_rate": 1.8604651162790697e-05,
120
+ "loss": 0.7426,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.0198482194979568,
125
+ "grad_norm": 0.6386219561082004,
126
+ "learning_rate": 1.9767441860465116e-05,
127
+ "loss": 0.7312,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.021015761821366025,
132
+ "grad_norm": 0.644937218393417,
133
+ "learning_rate": 2.0930232558139536e-05,
134
+ "loss": 0.7385,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.022183304144775248,
139
+ "grad_norm": 0.6754323077367341,
140
+ "learning_rate": 2.2093023255813955e-05,
141
+ "loss": 0.7269,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.023350846468184472,
146
+ "grad_norm": 0.6697056123087642,
147
+ "learning_rate": 2.3255813953488374e-05,
148
+ "loss": 0.7363,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.024518388791593695,
153
+ "grad_norm": 0.6741873152820539,
154
+ "learning_rate": 2.441860465116279e-05,
155
+ "loss": 0.7225,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.02568593111500292,
160
+ "grad_norm": 0.6792595483910896,
161
+ "learning_rate": 2.5581395348837212e-05,
162
+ "loss": 0.7247,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.026853473438412143,
167
+ "grad_norm": 0.6690512509599283,
168
+ "learning_rate": 2.674418604651163e-05,
169
+ "loss": 0.7293,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.028021015761821366,
174
+ "grad_norm": 0.6131690372558509,
175
+ "learning_rate": 2.7906976744186048e-05,
176
+ "loss": 0.6901,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.02918855808523059,
181
+ "grad_norm": 0.6430555073765273,
182
+ "learning_rate": 2.9069767441860467e-05,
183
+ "loss": 0.7332,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.030356100408639813,
188
+ "grad_norm": 0.6981936370986412,
189
+ "learning_rate": 3.0232558139534883e-05,
190
+ "loss": 0.712,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.03152364273204904,
195
+ "grad_norm": 0.627939736457028,
196
+ "learning_rate": 3.13953488372093e-05,
197
+ "loss": 0.6979,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.03269118505545826,
202
+ "grad_norm": 0.7456802010945889,
203
+ "learning_rate": 3.2558139534883724e-05,
204
+ "loss": 0.7307,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.033858727378867484,
209
+ "grad_norm": 0.6734236441922247,
210
+ "learning_rate": 3.372093023255814e-05,
211
+ "loss": 0.7355,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.03502626970227671,
216
+ "grad_norm": 0.9148944262002179,
217
+ "learning_rate": 3.488372093023256e-05,
218
+ "loss": 0.7157,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.03619381202568593,
223
+ "grad_norm": 0.7021510205127233,
224
+ "learning_rate": 3.604651162790698e-05,
225
+ "loss": 0.7202,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.037361354349095155,
230
+ "grad_norm": 0.9136518568600357,
231
+ "learning_rate": 3.7209302325581394e-05,
232
+ "loss": 0.7184,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.03852889667250438,
237
+ "grad_norm": 0.7359457550212143,
238
+ "learning_rate": 3.837209302325582e-05,
239
+ "loss": 0.7091,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.0396964389959136,
244
+ "grad_norm": 0.7309833656506266,
245
+ "learning_rate": 3.953488372093023e-05,
246
+ "loss": 0.7154,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.040863981319322826,
251
+ "grad_norm": 0.8118267428281774,
252
+ "learning_rate": 4.0697674418604655e-05,
253
+ "loss": 0.7397,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.04203152364273205,
258
+ "grad_norm": 0.8385733048051603,
259
+ "learning_rate": 4.186046511627907e-05,
260
+ "loss": 0.7373,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.04319906596614127,
265
+ "grad_norm": 0.7641709928876936,
266
+ "learning_rate": 4.302325581395349e-05,
267
+ "loss": 0.7167,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.044366608289550497,
272
+ "grad_norm": 0.8375032184986964,
273
+ "learning_rate": 4.418604651162791e-05,
274
+ "loss": 0.7157,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.04553415061295972,
279
+ "grad_norm": 0.9064930434497387,
280
+ "learning_rate": 4.5348837209302326e-05,
281
+ "loss": 0.7246,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.046701692936368944,
286
+ "grad_norm": 0.7695848116875716,
287
+ "learning_rate": 4.651162790697675e-05,
288
+ "loss": 0.7156,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.04786923525977817,
293
+ "grad_norm": 0.733983040623003,
294
+ "learning_rate": 4.7674418604651164e-05,
295
+ "loss": 0.7019,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.04903677758318739,
300
+ "grad_norm": 0.8310748449815144,
301
+ "learning_rate": 4.883720930232558e-05,
302
+ "loss": 0.7053,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.050204319906596614,
307
+ "grad_norm": 0.7138124934818736,
308
+ "learning_rate": 5e-05,
309
+ "loss": 0.7371,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.05137186223000584,
314
+ "grad_norm": 0.7373207758866321,
315
+ "learning_rate": 4.9999832180125564e-05,
316
+ "loss": 0.7208,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.05253940455341506,
321
+ "grad_norm": 0.61763988667967,
322
+ "learning_rate": 4.999932872300567e-05,
323
+ "loss": 0.7209,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.053706946876824285,
328
+ "grad_norm": 0.7958325034766942,
329
+ "learning_rate": 4.9998489636150545e-05,
330
+ "loss": 0.7197,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.05487448920023351,
335
+ "grad_norm": 0.7579619991421102,
336
+ "learning_rate": 4.999731493207714e-05,
337
+ "loss": 0.7138,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.05604203152364273,
342
+ "grad_norm": 0.7625510966416409,
343
+ "learning_rate": 4.999580462830887e-05,
344
+ "loss": 0.709,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.057209573847051956,
349
+ "grad_norm": 0.5824690773593582,
350
+ "learning_rate": 4.999395874737543e-05,
351
+ "loss": 0.7058,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.05837711617046118,
356
+ "grad_norm": 0.6333769528651304,
357
+ "learning_rate": 4.9991777316812435e-05,
358
+ "loss": 0.7122,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.0595446584938704,
363
+ "grad_norm": 0.6865471951313481,
364
+ "learning_rate": 4.998926036916096e-05,
365
+ "loss": 0.7074,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.06071220081727963,
370
+ "grad_norm": 0.6491742841354096,
371
+ "learning_rate": 4.9986407941967145e-05,
372
+ "loss": 0.7047,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.06187974314068885,
377
+ "grad_norm": 0.6711749887007579,
378
+ "learning_rate": 4.998322007778156e-05,
379
+ "loss": 0.7147,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.06304728546409807,
384
+ "grad_norm": 0.8465861812583904,
385
+ "learning_rate": 4.9979696824158613e-05,
386
+ "loss": 0.6877,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.0642148277875073,
391
+ "grad_norm": 0.71297093375199,
392
+ "learning_rate": 4.997583823365579e-05,
393
+ "loss": 0.6992,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.06538237011091652,
398
+ "grad_norm": 0.6545203939783993,
399
+ "learning_rate": 4.997164436383294e-05,
400
+ "loss": 0.7078,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.06654991243432574,
405
+ "grad_norm": 0.6519819497594413,
406
+ "learning_rate": 4.996711527725137e-05,
407
+ "loss": 0.7107,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.06771745475773497,
412
+ "grad_norm": 0.6993623377981596,
413
+ "learning_rate": 4.9962251041472936e-05,
414
+ "loss": 0.7208,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.06888499708114419,
419
+ "grad_norm": 0.648613406568837,
420
+ "learning_rate": 4.9957051729058994e-05,
421
+ "loss": 0.6879,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.07005253940455342,
426
+ "grad_norm": 0.7127685542022537,
427
+ "learning_rate": 4.9951517417569365e-05,
428
+ "loss": 0.7166,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.07122008172796264,
433
+ "grad_norm": 0.706094493069307,
434
+ "learning_rate": 4.994564818956116e-05,
435
+ "loss": 0.6857,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.07238762405137186,
440
+ "grad_norm": 0.6178576381979423,
441
+ "learning_rate": 4.993944413258755e-05,
442
+ "loss": 0.7068,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.07355516637478109,
447
+ "grad_norm": 0.5982448161453142,
448
+ "learning_rate": 4.993290533919644e-05,
449
+ "loss": 0.7154,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.07472270869819031,
454
+ "grad_norm": 0.6270320614638317,
455
+ "learning_rate": 4.9926031906929114e-05,
456
+ "loss": 0.704,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.07589025102159953,
461
+ "grad_norm": 0.6197640246960802,
462
+ "learning_rate": 4.9918823938318796e-05,
463
+ "loss": 0.7016,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.07705779334500876,
468
+ "grad_norm": 0.7359756470563305,
469
+ "learning_rate": 4.991128154088906e-05,
470
+ "loss": 0.7013,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.07822533566841798,
475
+ "grad_norm": 0.6720218756243642,
476
+ "learning_rate": 4.990340482715228e-05,
477
+ "loss": 0.6996,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.0793928779918272,
482
+ "grad_norm": 0.5925386151271446,
483
+ "learning_rate": 4.989519391460794e-05,
484
+ "loss": 0.7207,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.08056042031523643,
489
+ "grad_norm": 0.5902543605954019,
490
+ "learning_rate": 4.988664892574086e-05,
491
+ "loss": 0.7067,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.08172796263864565,
496
+ "grad_norm": 0.6222759073596537,
497
+ "learning_rate": 4.987776998801939e-05,
498
+ "loss": 0.6951,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.08289550496205488,
503
+ "grad_norm": 0.6101124606146439,
504
+ "learning_rate": 4.986855723389351e-05,
505
+ "loss": 0.6834,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.0840630472854641,
510
+ "grad_norm": 0.5521729567786234,
511
+ "learning_rate": 4.9859010800792855e-05,
512
+ "loss": 0.7058,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.08523058960887332,
517
+ "grad_norm": 0.5997828983186825,
518
+ "learning_rate": 4.984913083112462e-05,
519
+ "loss": 0.7055,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.08639813193228255,
524
+ "grad_norm": 0.685636903832874,
525
+ "learning_rate": 4.9838917472271495e-05,
526
+ "loss": 0.697,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.08756567425569177,
531
+ "grad_norm": 0.5899607924142912,
532
+ "learning_rate": 4.982837087658947e-05,
533
+ "loss": 0.6891,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.08873321657910099,
538
+ "grad_norm": 0.5832999949555281,
539
+ "learning_rate": 4.981749120140547e-05,
540
+ "loss": 0.6916,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.08990075890251022,
545
+ "grad_norm": 0.5501342674246906,
546
+ "learning_rate": 4.980627860901516e-05,
547
+ "loss": 0.692,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.09106830122591944,
552
+ "grad_norm": 0.6156319618368346,
553
+ "learning_rate": 4.9794733266680364e-05,
554
+ "loss": 0.6835,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 0.09223584354932866,
559
+ "grad_norm": 0.6648904756503935,
560
+ "learning_rate": 4.978285534662669e-05,
561
+ "loss": 0.7115,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 0.09340338587273789,
566
+ "grad_norm": 0.750574007629335,
567
+ "learning_rate": 4.977064502604089e-05,
568
+ "loss": 0.6874,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 0.09457092819614711,
573
+ "grad_norm": 0.6282717605845722,
574
+ "learning_rate": 4.975810248706824e-05,
575
+ "loss": 0.6929,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 0.09573847051955633,
580
+ "grad_norm": 0.559968165186596,
581
+ "learning_rate": 4.974522791680985e-05,
582
+ "loss": 0.6937,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 0.09690601284296556,
587
+ "grad_norm": 0.5712581921517633,
588
+ "learning_rate": 4.9732021507319814e-05,
589
+ "loss": 0.6763,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 0.09807355516637478,
594
+ "grad_norm": 0.5972119499481222,
595
+ "learning_rate": 4.971848345560243e-05,
596
+ "loss": 0.6847,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 0.099241097489784,
601
+ "grad_norm": 0.5576942154957365,
602
+ "learning_rate": 4.970461396360914e-05,
603
+ "loss": 0.6831,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 0.10040863981319323,
608
+ "grad_norm": 0.5712258586876164,
609
+ "learning_rate": 4.969041323823565e-05,
610
+ "loss": 0.6986,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 0.10157618213660245,
615
+ "grad_norm": 0.5660135736483292,
616
+ "learning_rate": 4.9675881491318735e-05,
617
+ "loss": 0.6938,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 0.10274372446001168,
622
+ "grad_norm": 0.6202667863714418,
623
+ "learning_rate": 4.966101893963317e-05,
624
+ "loss": 0.6741,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 0.1039112667834209,
629
+ "grad_norm": 0.6530868448205541,
630
+ "learning_rate": 4.9645825804888416e-05,
631
+ "loss": 0.6818,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 0.10507880910683012,
636
+ "grad_norm": 0.6777514742609368,
637
+ "learning_rate": 4.9630302313725354e-05,
638
+ "loss": 0.6804,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 0.10624635143023935,
643
+ "grad_norm": 0.6571600249956766,
644
+ "learning_rate": 4.96144486977129e-05,
645
+ "loss": 0.6892,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 0.10741389375364857,
650
+ "grad_norm": 0.652600788102656,
651
+ "learning_rate": 4.959826519334456e-05,
652
+ "loss": 0.6746,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 0.1085814360770578,
657
+ "grad_norm": 0.6141340591754272,
658
+ "learning_rate": 4.958175204203488e-05,
659
+ "loss": 0.6802,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 0.10974897840046702,
664
+ "grad_norm": 0.6455039458573127,
665
+ "learning_rate": 4.9564909490115864e-05,
666
+ "loss": 0.6789,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 0.11091652072387624,
671
+ "grad_norm": 0.5658472639112537,
672
+ "learning_rate": 4.9547737788833274e-05,
673
+ "loss": 0.6946,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 0.11208406304728546,
678
+ "grad_norm": 0.5656645798879412,
679
+ "learning_rate": 4.953023719434292e-05,
680
+ "loss": 0.6801,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 0.11325160537069469,
685
+ "grad_norm": 0.6339701712723772,
686
+ "learning_rate": 4.95124079677068e-05,
687
+ "loss": 0.684,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 0.11441914769410391,
692
+ "grad_norm": 0.549060506810349,
693
+ "learning_rate": 4.9494250374889235e-05,
694
+ "loss": 0.6678,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 0.11558669001751314,
699
+ "grad_norm": 0.6950518638333417,
700
+ "learning_rate": 4.947576468675289e-05,
701
+ "loss": 0.6692,
702
+ "step": 495
703
+ },
704
+ {
705
+ "epoch": 0.11675423234092236,
706
+ "grad_norm": 0.5221510459831169,
707
+ "learning_rate": 4.9456951179054725e-05,
708
+ "loss": 0.6753,
709
+ "step": 500
710
+ },
711
+ {
712
+ "epoch": 0.11792177466433158,
713
+ "grad_norm": 0.5546382592565675,
714
+ "learning_rate": 4.94378101324419e-05,
715
+ "loss": 0.6854,
716
+ "step": 505
717
+ },
718
+ {
719
+ "epoch": 0.1190893169877408,
720
+ "grad_norm": 0.5713482480639444,
721
+ "learning_rate": 4.9418341832447575e-05,
722
+ "loss": 0.6807,
723
+ "step": 510
724
+ },
725
+ {
726
+ "epoch": 0.12025685931115003,
727
+ "grad_norm": 0.5414388299943901,
728
+ "learning_rate": 4.939854656948665e-05,
729
+ "loss": 0.673,
730
+ "step": 515
731
+ },
732
+ {
733
+ "epoch": 0.12142440163455925,
734
+ "grad_norm": 0.594323665364383,
735
+ "learning_rate": 4.937842463885143e-05,
736
+ "loss": 0.6883,
737
+ "step": 520
738
+ },
739
+ {
740
+ "epoch": 0.12259194395796848,
741
+ "grad_norm": 0.553478548766972,
742
+ "learning_rate": 4.935797634070726e-05,
743
+ "loss": 0.7048,
744
+ "step": 525
745
+ },
746
+ {
747
+ "epoch": 0.1237594862813777,
748
+ "grad_norm": 0.5605780800682596,
749
+ "learning_rate": 4.933720198008798e-05,
750
+ "loss": 0.6877,
751
+ "step": 530
752
+ },
753
+ {
754
+ "epoch": 0.12492702860478692,
755
+ "grad_norm": 0.5870470112417832,
756
+ "learning_rate": 4.9316101866891414e-05,
757
+ "loss": 0.6835,
758
+ "step": 535
759
+ },
760
+ {
761
+ "epoch": 0.12609457092819615,
762
+ "grad_norm": 0.6417809835924543,
763
+ "learning_rate": 4.9294676315874756e-05,
764
+ "loss": 0.67,
765
+ "step": 540
766
+ },
767
+ {
768
+ "epoch": 0.12726211325160536,
769
+ "grad_norm": 0.5733147322116063,
770
+ "learning_rate": 4.927292564664985e-05,
771
+ "loss": 0.6632,
772
+ "step": 545
773
+ },
774
+ {
775
+ "epoch": 0.1284296555750146,
776
+ "grad_norm": 0.5862624837218928,
777
+ "learning_rate": 4.925085018367844e-05,
778
+ "loss": 0.6708,
779
+ "step": 550
780
+ },
781
+ {
782
+ "epoch": 0.1295971978984238,
783
+ "grad_norm": 0.5974113571603092,
784
+ "learning_rate": 4.922845025626732e-05,
785
+ "loss": 0.6835,
786
+ "step": 555
787
+ },
788
+ {
789
+ "epoch": 0.13076474022183304,
790
+ "grad_norm": 0.6542521321417366,
791
+ "learning_rate": 4.9205726198563415e-05,
792
+ "loss": 0.68,
793
+ "step": 560
794
+ },
795
+ {
796
+ "epoch": 0.13193228254524225,
797
+ "grad_norm": 0.599831408114888,
798
+ "learning_rate": 4.918267834954882e-05,
799
+ "loss": 0.6873,
800
+ "step": 565
801
+ },
802
+ {
803
+ "epoch": 0.1330998248686515,
804
+ "grad_norm": 0.7202647495555032,
805
+ "learning_rate": 4.915930705303572e-05,
806
+ "loss": 0.6896,
807
+ "step": 570
808
+ },
809
+ {
810
+ "epoch": 0.1342673671920607,
811
+ "grad_norm": 0.5882125532921776,
812
+ "learning_rate": 4.913561265766129e-05,
813
+ "loss": 0.6673,
814
+ "step": 575
815
+ },
816
+ {
817
+ "epoch": 0.13543490951546994,
818
+ "grad_norm": 0.6578196777426495,
819
+ "learning_rate": 4.911159551688244e-05,
820
+ "loss": 0.6785,
821
+ "step": 580
822
+ },
823
+ {
824
+ "epoch": 0.13660245183887915,
825
+ "grad_norm": 0.594562463032614,
826
+ "learning_rate": 4.908725598897061e-05,
827
+ "loss": 0.6732,
828
+ "step": 585
829
+ },
830
+ {
831
+ "epoch": 0.13776999416228838,
832
+ "grad_norm": 0.6040563629336885,
833
+ "learning_rate": 4.906259443700638e-05,
834
+ "loss": 0.6693,
835
+ "step": 590
836
+ },
837
+ {
838
+ "epoch": 0.1389375364856976,
839
+ "grad_norm": 0.6461468680651782,
840
+ "learning_rate": 4.9037611228874045e-05,
841
+ "loss": 0.6661,
842
+ "step": 595
843
+ },
844
+ {
845
+ "epoch": 0.14010507880910683,
846
+ "grad_norm": 0.5729590002869202,
847
+ "learning_rate": 4.90123067372562e-05,
848
+ "loss": 0.6774,
849
+ "step": 600
850
+ },
851
+ {
852
+ "epoch": 0.14127262113251604,
853
+ "grad_norm": 0.5903250131921434,
854
+ "learning_rate": 4.8986681339628077e-05,
855
+ "loss": 0.6649,
856
+ "step": 605
857
+ },
858
+ {
859
+ "epoch": 0.14244016345592528,
860
+ "grad_norm": 0.5740779177974161,
861
+ "learning_rate": 4.8960735418252004e-05,
862
+ "loss": 0.6803,
863
+ "step": 610
864
+ },
865
+ {
866
+ "epoch": 0.1436077057793345,
867
+ "grad_norm": 0.5388317280553481,
868
+ "learning_rate": 4.893446936017162e-05,
869
+ "loss": 0.6756,
870
+ "step": 615
871
+ },
872
+ {
873
+ "epoch": 0.14477524810274373,
874
+ "grad_norm": 0.5571144991003452,
875
+ "learning_rate": 4.890788355720621e-05,
876
+ "loss": 0.679,
877
+ "step": 620
878
+ },
879
+ {
880
+ "epoch": 0.14594279042615294,
881
+ "grad_norm": 0.6218993167281257,
882
+ "learning_rate": 4.888097840594475e-05,
883
+ "loss": 0.6689,
884
+ "step": 625
885
+ },
886
+ {
887
+ "epoch": 0.14711033274956217,
888
+ "grad_norm": 0.5868172370833116,
889
+ "learning_rate": 4.8853754307740043e-05,
890
+ "loss": 0.6743,
891
+ "step": 630
892
+ },
893
+ {
894
+ "epoch": 0.14827787507297138,
895
+ "grad_norm": 0.5191378123088599,
896
+ "learning_rate": 4.8826211668702744e-05,
897
+ "loss": 0.6679,
898
+ "step": 635
899
+ },
900
+ {
901
+ "epoch": 0.14944541739638062,
902
+ "grad_norm": 0.5092530035164934,
903
+ "learning_rate": 4.879835089969526e-05,
904
+ "loss": 0.6751,
905
+ "step": 640
906
+ },
907
+ {
908
+ "epoch": 0.15061295971978983,
909
+ "grad_norm": 0.6504883049198265,
910
+ "learning_rate": 4.877017241632567e-05,
911
+ "loss": 0.6755,
912
+ "step": 645
913
+ },
914
+ {
915
+ "epoch": 0.15178050204319907,
916
+ "grad_norm": 0.5577825579467539,
917
+ "learning_rate": 4.874167663894148e-05,
918
+ "loss": 0.6553,
919
+ "step": 650
920
+ },
921
+ {
922
+ "epoch": 0.15294804436660828,
923
+ "grad_norm": 0.5546035491522867,
924
+ "learning_rate": 4.871286399262338e-05,
925
+ "loss": 0.6729,
926
+ "step": 655
927
+ },
928
+ {
929
+ "epoch": 0.15411558669001751,
930
+ "grad_norm": 0.5433685032657724,
931
+ "learning_rate": 4.868373490717891e-05,
932
+ "loss": 0.6693,
933
+ "step": 660
934
+ },
935
+ {
936
+ "epoch": 0.15528312901342672,
937
+ "grad_norm": 0.552710617301973,
938
+ "learning_rate": 4.8654289817136014e-05,
939
+ "loss": 0.6649,
940
+ "step": 665
941
+ },
942
+ {
943
+ "epoch": 0.15645067133683596,
944
+ "grad_norm": 0.5507433796337713,
945
+ "learning_rate": 4.8624529161736585e-05,
946
+ "loss": 0.666,
947
+ "step": 670
948
+ },
949
+ {
950
+ "epoch": 0.15761821366024517,
951
+ "grad_norm": 0.5120857427927407,
952
+ "learning_rate": 4.859445338492991e-05,
953
+ "loss": 0.6742,
954
+ "step": 675
955
+ },
956
+ {
957
+ "epoch": 0.1587857559836544,
958
+ "grad_norm": 0.6178433514220235,
959
+ "learning_rate": 4.856406293536604e-05,
960
+ "loss": 0.6742,
961
+ "step": 680
962
+ },
963
+ {
964
+ "epoch": 0.15995329830706362,
965
+ "grad_norm": 0.5621670673190233,
966
+ "learning_rate": 4.8533358266389114e-05,
967
+ "loss": 0.6806,
968
+ "step": 685
969
+ },
970
+ {
971
+ "epoch": 0.16112084063047286,
972
+ "grad_norm": 0.530079236665643,
973
+ "learning_rate": 4.8502339836030557e-05,
974
+ "loss": 0.6753,
975
+ "step": 690
976
+ },
977
+ {
978
+ "epoch": 0.16228838295388207,
979
+ "grad_norm": 0.5715227897366831,
980
+ "learning_rate": 4.847100810700228e-05,
981
+ "loss": 0.6826,
982
+ "step": 695
983
+ },
984
+ {
985
+ "epoch": 0.1634559252772913,
986
+ "grad_norm": 0.6562252266149332,
987
+ "learning_rate": 4.843936354668981e-05,
988
+ "loss": 0.6719,
989
+ "step": 700
990
+ },
991
+ {
992
+ "epoch": 0.1646234676007005,
993
+ "grad_norm": 0.5778430160807131,
994
+ "learning_rate": 4.8407406627145223e-05,
995
+ "loss": 0.6618,
996
+ "step": 705
997
+ },
998
+ {
999
+ "epoch": 0.16579100992410975,
1000
+ "grad_norm": 0.5939646842898266,
1001
+ "learning_rate": 4.837513782508018e-05,
1002
+ "loss": 0.6613,
1003
+ "step": 710
1004
+ },
1005
+ {
1006
+ "epoch": 0.16695855224751896,
1007
+ "grad_norm": 0.5521562356047192,
1008
+ "learning_rate": 4.834255762185882e-05,
1009
+ "loss": 0.6657,
1010
+ "step": 715
1011
+ },
1012
+ {
1013
+ "epoch": 0.1681260945709282,
1014
+ "grad_norm": 0.5506464069499719,
1015
+ "learning_rate": 4.830966650349051e-05,
1016
+ "loss": 0.6498,
1017
+ "step": 720
1018
+ },
1019
+ {
1020
+ "epoch": 0.1692936368943374,
1021
+ "grad_norm": 0.504907588505334,
1022
+ "learning_rate": 4.827646496062267e-05,
1023
+ "loss": 0.6711,
1024
+ "step": 725
1025
+ },
1026
+ {
1027
+ "epoch": 0.17046117921774664,
1028
+ "grad_norm": 0.49865656610170683,
1029
+ "learning_rate": 4.8242953488533405e-05,
1030
+ "loss": 0.6748,
1031
+ "step": 730
1032
+ },
1033
+ {
1034
+ "epoch": 0.17162872154115585,
1035
+ "grad_norm": 0.566907250566616,
1036
+ "learning_rate": 4.820913258712415e-05,
1037
+ "loss": 0.6645,
1038
+ "step": 735
1039
+ },
1040
+ {
1041
+ "epoch": 0.1727962638645651,
1042
+ "grad_norm": 0.5840434147062887,
1043
+ "learning_rate": 4.817500276091218e-05,
1044
+ "loss": 0.6711,
1045
+ "step": 740
1046
+ },
1047
+ {
1048
+ "epoch": 0.1739638061879743,
1049
+ "grad_norm": 0.5707207892181994,
1050
+ "learning_rate": 4.8140564519023104e-05,
1051
+ "loss": 0.6582,
1052
+ "step": 745
1053
+ },
1054
+ {
1055
+ "epoch": 0.17513134851138354,
1056
+ "grad_norm": 0.6038737922024617,
1057
+ "learning_rate": 4.810581837518329e-05,
1058
+ "loss": 0.6598,
1059
+ "step": 750
1060
+ },
1061
+ {
1062
+ "epoch": 0.17629889083479275,
1063
+ "grad_norm": 0.5400957574912046,
1064
+ "learning_rate": 4.807076484771214e-05,
1065
+ "loss": 0.6585,
1066
+ "step": 755
1067
+ },
1068
+ {
1069
+ "epoch": 0.17746643315820199,
1070
+ "grad_norm": 0.6206248349540344,
1071
+ "learning_rate": 4.803540445951443e-05,
1072
+ "loss": 0.6611,
1073
+ "step": 760
1074
+ },
1075
+ {
1076
+ "epoch": 0.1786339754816112,
1077
+ "grad_norm": 0.5384357416640436,
1078
+ "learning_rate": 4.7999737738072454e-05,
1079
+ "loss": 0.6656,
1080
+ "step": 765
1081
+ },
1082
+ {
1083
+ "epoch": 0.17980151780502043,
1084
+ "grad_norm": 0.5614613345381276,
1085
+ "learning_rate": 4.796376521543818e-05,
1086
+ "loss": 0.6536,
1087
+ "step": 770
1088
+ },
1089
+ {
1090
+ "epoch": 0.18096906012842964,
1091
+ "grad_norm": 0.5403930821292826,
1092
+ "learning_rate": 4.792748742822534e-05,
1093
+ "loss": 0.6653,
1094
+ "step": 775
1095
+ },
1096
+ {
1097
+ "epoch": 0.18213660245183888,
1098
+ "grad_norm": 0.5469852898591198,
1099
+ "learning_rate": 4.789090491760136e-05,
1100
+ "loss": 0.6458,
1101
+ "step": 780
1102
+ },
1103
+ {
1104
+ "epoch": 0.1833041447752481,
1105
+ "grad_norm": 0.5271070176741515,
1106
+ "learning_rate": 4.785401822927933e-05,
1107
+ "loss": 0.663,
1108
+ "step": 785
1109
+ },
1110
+ {
1111
+ "epoch": 0.18447168709865733,
1112
+ "grad_norm": 0.5200290447627971,
1113
+ "learning_rate": 4.781682791350988e-05,
1114
+ "loss": 0.6619,
1115
+ "step": 790
1116
+ },
1117
+ {
1118
+ "epoch": 0.18563922942206654,
1119
+ "grad_norm": 0.5732678229356464,
1120
+ "learning_rate": 4.777933452507292e-05,
1121
+ "loss": 0.6547,
1122
+ "step": 795
1123
+ },
1124
+ {
1125
+ "epoch": 0.18680677174547577,
1126
+ "grad_norm": 0.5354575627455573,
1127
+ "learning_rate": 4.774153862326941e-05,
1128
+ "loss": 0.6826,
1129
+ "step": 800
1130
+ },
1131
+ {
1132
+ "epoch": 0.18797431406888498,
1133
+ "grad_norm": 0.6036615103150955,
1134
+ "learning_rate": 4.770344077191298e-05,
1135
+ "loss": 0.6417,
1136
+ "step": 805
1137
+ },
1138
+ {
1139
+ "epoch": 0.18914185639229422,
1140
+ "grad_norm": 0.6247836327871729,
1141
+ "learning_rate": 4.7665041539321575e-05,
1142
+ "loss": 0.6691,
1143
+ "step": 810
1144
+ },
1145
+ {
1146
+ "epoch": 0.19030939871570343,
1147
+ "grad_norm": 0.6581916329571659,
1148
+ "learning_rate": 4.762634149830891e-05,
1149
+ "loss": 0.6655,
1150
+ "step": 815
1151
+ },
1152
+ {
1153
+ "epoch": 0.19147694103911267,
1154
+ "grad_norm": 0.5713689891793854,
1155
+ "learning_rate": 4.758734122617596e-05,
1156
+ "loss": 0.6851,
1157
+ "step": 820
1158
+ },
1159
+ {
1160
+ "epoch": 0.19264448336252188,
1161
+ "grad_norm": 0.6537243443496534,
1162
+ "learning_rate": 4.7548041304702354e-05,
1163
+ "loss": 0.671,
1164
+ "step": 825
1165
+ },
1166
+ {
1167
+ "epoch": 0.19381202568593112,
1168
+ "grad_norm": 0.5524240796431374,
1169
+ "learning_rate": 4.750844232013767e-05,
1170
+ "loss": 0.6546,
1171
+ "step": 830
1172
+ },
1173
+ {
1174
+ "epoch": 0.19497956800934033,
1175
+ "grad_norm": 0.585496623761136,
1176
+ "learning_rate": 4.746854486319274e-05,
1177
+ "loss": 0.6843,
1178
+ "step": 835
1179
+ },
1180
+ {
1181
+ "epoch": 0.19614711033274956,
1182
+ "grad_norm": 0.5316480721204311,
1183
+ "learning_rate": 4.742834952903077e-05,
1184
+ "loss": 0.6576,
1185
+ "step": 840
1186
+ },
1187
+ {
1188
+ "epoch": 0.19731465265615877,
1189
+ "grad_norm": 0.5352165728165146,
1190
+ "learning_rate": 4.738785691725851e-05,
1191
+ "loss": 0.6709,
1192
+ "step": 845
1193
+ },
1194
+ {
1195
+ "epoch": 0.198482194979568,
1196
+ "grad_norm": 0.5301735920045355,
1197
+ "learning_rate": 4.73470676319173e-05,
1198
+ "loss": 0.6784,
1199
+ "step": 850
1200
+ },
1201
+ {
1202
+ "epoch": 0.19964973730297722,
1203
+ "grad_norm": 0.5991107299004165,
1204
+ "learning_rate": 4.7305982281474044e-05,
1205
+ "loss": 0.6555,
1206
+ "step": 855
1207
+ },
1208
+ {
1209
+ "epoch": 0.20081727962638646,
1210
+ "grad_norm": 0.5289780942574344,
1211
+ "learning_rate": 4.726460147881215e-05,
1212
+ "loss": 0.6643,
1213
+ "step": 860
1214
+ },
1215
+ {
1216
+ "epoch": 0.20198482194979567,
1217
+ "grad_norm": 0.5691639668751877,
1218
+ "learning_rate": 4.7222925841222396e-05,
1219
+ "loss": 0.6462,
1220
+ "step": 865
1221
+ },
1222
+ {
1223
+ "epoch": 0.2031523642732049,
1224
+ "grad_norm": 0.5418269405653413,
1225
+ "learning_rate": 4.7180955990393685e-05,
1226
+ "loss": 0.6531,
1227
+ "step": 870
1228
+ },
1229
+ {
1230
+ "epoch": 0.20431990659661411,
1231
+ "grad_norm": 0.5486670082318458,
1232
+ "learning_rate": 4.71386925524038e-05,
1233
+ "loss": 0.6488,
1234
+ "step": 875
1235
+ },
1236
+ {
1237
+ "epoch": 0.20548744892002335,
1238
+ "grad_norm": 0.5276040254806676,
1239
+ "learning_rate": 4.709613615771008e-05,
1240
+ "loss": 0.6667,
1241
+ "step": 880
1242
+ },
1243
+ {
1244
+ "epoch": 0.20665499124343256,
1245
+ "grad_norm": 0.5407981342058974,
1246
+ "learning_rate": 4.705328744113994e-05,
1247
+ "loss": 0.6448,
1248
+ "step": 885
1249
+ },
1250
+ {
1251
+ "epoch": 0.2078225335668418,
1252
+ "grad_norm": 0.5643190048970039,
1253
+ "learning_rate": 4.701014704188153e-05,
1254
+ "loss": 0.6643,
1255
+ "step": 890
1256
+ },
1257
+ {
1258
+ "epoch": 0.208990075890251,
1259
+ "grad_norm": 0.5155536107792693,
1260
+ "learning_rate": 4.696671560347405e-05,
1261
+ "loss": 0.6445,
1262
+ "step": 895
1263
+ },
1264
+ {
1265
+ "epoch": 0.21015761821366025,
1266
+ "grad_norm": 0.5253675582885029,
1267
+ "learning_rate": 4.692299377379829e-05,
1268
+ "loss": 0.6468,
1269
+ "step": 900
1270
+ },
1271
+ {
1272
+ "epoch": 0.21015761821366025,
1273
+ "step": 900,
1274
+ "total_flos": 102527278252032.0,
1275
+ "train_loss": 0.0,
1276
+ "train_runtime": 1.3976,
1277
+ "train_samples_per_second": 5132.403,
1278
+ "train_steps_per_second": 80.138
1279
+ }
1280
+ ],
1281
+ "logging_steps": 5,
1282
+ "max_steps": 112,
1283
+ "num_input_tokens_seen": 0,
1284
+ "num_train_epochs": 1,
1285
+ "save_steps": 100,
1286
+ "stateful_callbacks": {
1287
+ "TrainerControl": {
1288
+ "args": {
1289
+ "should_epoch_stop": false,
1290
+ "should_evaluate": false,
1291
+ "should_log": false,
1292
+ "should_save": true,
1293
+ "should_training_stop": false
1294
+ },
1295
+ "attributes": {}
1296
+ }
1297
+ },
1298
+ "total_flos": 102527278252032.0,
1299
+ "train_batch_size": 16,
1300
+ "trial_name": null,
1301
+ "trial_params": null
1302
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:429263d37784054b77ebba189c20d197b802c9bf0a1d600509e16df3e11ad628
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d64ff30d93ba531ed5601517e02a5860b10e71867b0561691a359d344b52964
3
  size 7480