Eya0910 commited on
Commit
b13d093
1 Parent(s): 02a4e0b

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- library_name: transformers
3
- tags: []
4
  ---
5
 
6
  # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
 
 
 
1
  ---
2
+ base_model: google/gemma-1.1-2b-it
3
+ library_name: peft
4
  ---
5
 
6
  # Model Card for Model ID
 
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
+
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
 
196
 
197
  ## Model Card Contact
198
 
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.8.2
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-1.1-2b-it",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 8,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "k_proj",
24
+ "gate_proj",
25
+ "q_proj",
26
+ "v_proj",
27
+ "up_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "TEXT_GENERATION",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e7ec7858af112989b9b7836e0feec74101588ae28e942c00e31119bddf1adf
3
+ size 19644912
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57958b65fa1081a0e5562acfde3bbbd1f1faee1b0cfa633a0d03ee889d6ab8e6
3
+ size 20359034
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c49b08dba45f98b85fa913aaa9c4cb77e2f0f0c6731a9826fb9be9dec7e7161
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
3
+ size 1064
special_tokens_map.json CHANGED
@@ -17,7 +17,13 @@
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
- "pad_token": "<eos>",
 
 
 
 
 
 
21
  "unk_token": {
22
  "content": "<unk>",
23
  "lstrip": false,
 
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
  "unk_token": {
28
  "content": "<unk>",
29
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c15eb04bc5ad609fb26533e8525302c5640a945e5f67f65b7c849900acda7d99
3
- size 17518497
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0adfe100f7aaea5ab4011f4643c4359be2df636f514cd0574085e7a633874c19
3
+ size 17518596
tokenizer_config.json CHANGED
@@ -1748,7 +1748,7 @@
1748
  "clean_up_tokenization_spaces": false,
1749
  "eos_token": "<eos>",
1750
  "model_max_length": 1000000000000000019884624838656,
1751
- "pad_token": "<eos>",
1752
  "sp_model_kwargs": {},
1753
  "spaces_between_special_tokens": false,
1754
  "tokenizer_class": "GemmaTokenizer",
 
1748
  "clean_up_tokenization_spaces": false,
1749
  "eos_token": "<eos>",
1750
  "model_max_length": 1000000000000000019884624838656,
1751
+ "pad_token": "<pad>",
1752
  "sp_model_kwargs": {},
1753
  "spaces_between_special_tokens": false,
1754
  "tokenizer_class": "GemmaTokenizer",
trainer_state.json ADDED
@@ -0,0 +1,1421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.1235955056179776,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 4.5,
14
+ "learning_rate": 0.00019902985447817174,
15
+ "loss": 2.5508,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 5.5,
21
+ "learning_rate": 0.00019802970445566834,
22
+ "loss": 2.7598,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 5.0625,
28
+ "learning_rate": 0.00019702955443316497,
29
+ "loss": 2.4902,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 4.84375,
35
+ "learning_rate": 0.0001960294044106616,
36
+ "loss": 2.4863,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "grad_norm": 8.9375,
42
+ "learning_rate": 0.00019502925438815824,
43
+ "loss": 3.25,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 5.4375,
49
+ "learning_rate": 0.00019402910436565487,
50
+ "loss": 3.0195,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 8.875,
56
+ "learning_rate": 0.0001930289543431515,
57
+ "loss": 3.6758,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 4.34375,
63
+ "learning_rate": 0.0001920288043206481,
64
+ "loss": 2.1699,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "grad_norm": 5.09375,
70
+ "learning_rate": 0.00019102865429814473,
71
+ "loss": 2.4805,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.06,
76
+ "grad_norm": 4.625,
77
+ "learning_rate": 0.00019002850427564136,
78
+ "loss": 2.6797,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.06,
83
+ "grad_norm": 5.59375,
84
+ "learning_rate": 0.000189028354253138,
85
+ "loss": 2.2031,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "grad_norm": 4.78125,
91
+ "learning_rate": 0.0001880282042306346,
92
+ "loss": 2.4688,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "grad_norm": 5.8125,
98
+ "learning_rate": 0.00018702805420813123,
99
+ "loss": 2.668,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.08,
104
+ "grad_norm": 6.3125,
105
+ "learning_rate": 0.00018602790418562786,
106
+ "loss": 2.8516,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.08,
111
+ "grad_norm": 6.28125,
112
+ "learning_rate": 0.0001850277541631245,
113
+ "loss": 2.3086,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.09,
118
+ "grad_norm": 4.5,
119
+ "learning_rate": 0.0001840276041406211,
120
+ "loss": 2.1504,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.1,
125
+ "grad_norm": 6.0,
126
+ "learning_rate": 0.00018302745411811772,
127
+ "loss": 2.5664,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.1,
132
+ "grad_norm": 5.90625,
133
+ "learning_rate": 0.00018202730409561436,
134
+ "loss": 2.4023,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "grad_norm": 6.9375,
140
+ "learning_rate": 0.00018102715407311096,
141
+ "loss": 2.6562,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.11,
146
+ "grad_norm": 5.59375,
147
+ "learning_rate": 0.0001800270040506076,
148
+ "loss": 1.9863,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.12,
153
+ "grad_norm": 6.78125,
154
+ "learning_rate": 0.00017902685402810422,
155
+ "loss": 2.4648,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.12,
160
+ "grad_norm": 6.375,
161
+ "learning_rate": 0.00017802670400560085,
162
+ "loss": 2.5781,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.13,
167
+ "grad_norm": 7.34375,
168
+ "learning_rate": 0.00017702655398309746,
169
+ "loss": 2.2715,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.13,
174
+ "grad_norm": 8.125,
175
+ "learning_rate": 0.00017602640396059409,
176
+ "loss": 2.5195,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.14,
181
+ "grad_norm": 4.90625,
182
+ "learning_rate": 0.00017502625393809074,
183
+ "loss": 2.4141,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.15,
188
+ "grad_norm": 5.34375,
189
+ "learning_rate": 0.00017402610391558735,
190
+ "loss": 2.2051,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.15,
195
+ "grad_norm": 6.65625,
196
+ "learning_rate": 0.00017302595389308398,
197
+ "loss": 2.5781,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.16,
202
+ "grad_norm": 5.59375,
203
+ "learning_rate": 0.0001720258038705806,
204
+ "loss": 2.2676,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.16,
209
+ "grad_norm": 6.34375,
210
+ "learning_rate": 0.00017102565384807724,
211
+ "loss": 2.291,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.17,
216
+ "grad_norm": 5.59375,
217
+ "learning_rate": 0.00017002550382557384,
218
+ "loss": 1.8398,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.17,
223
+ "grad_norm": 7.96875,
224
+ "learning_rate": 0.00016902535380307047,
225
+ "loss": 2.1543,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.18,
230
+ "grad_norm": 7.46875,
231
+ "learning_rate": 0.0001680252037805671,
232
+ "loss": 2.8789,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.19,
237
+ "grad_norm": 5.5,
238
+ "learning_rate": 0.0001670250537580637,
239
+ "loss": 2.1621,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.19,
244
+ "grad_norm": 5.28125,
245
+ "learning_rate": 0.00016602490373556034,
246
+ "loss": 2.2969,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.2,
251
+ "grad_norm": 8.3125,
252
+ "learning_rate": 0.00016502475371305697,
253
+ "loss": 2.4668,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.2,
258
+ "grad_norm": 8.0625,
259
+ "learning_rate": 0.0001640246036905536,
260
+ "loss": 2.7734,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.21,
265
+ "grad_norm": 5.5,
266
+ "learning_rate": 0.0001630244536680502,
267
+ "loss": 1.9102,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.21,
272
+ "grad_norm": 9.75,
273
+ "learning_rate": 0.00016202430364554684,
274
+ "loss": 2.6055,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.22,
279
+ "grad_norm": 7.46875,
280
+ "learning_rate": 0.00016102415362304347,
281
+ "loss": 2.0996,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.22,
286
+ "grad_norm": 7.53125,
287
+ "learning_rate": 0.0001600240036005401,
288
+ "loss": 2.5117,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.23,
293
+ "grad_norm": 8.125,
294
+ "learning_rate": 0.0001590238535780367,
295
+ "loss": 2.3262,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.24,
300
+ "grad_norm": 7.375,
301
+ "learning_rate": 0.00015802370355553333,
302
+ "loss": 2.4004,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.24,
307
+ "grad_norm": 6.75,
308
+ "learning_rate": 0.00015702355353302996,
309
+ "loss": 1.7539,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.25,
314
+ "grad_norm": 6.34375,
315
+ "learning_rate": 0.00015602340351052657,
316
+ "loss": 2.1699,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.25,
321
+ "grad_norm": 6.3125,
322
+ "learning_rate": 0.0001550232534880232,
323
+ "loss": 2.418,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.26,
328
+ "grad_norm": 7.0625,
329
+ "learning_rate": 0.00015402310346551986,
330
+ "loss": 2.1543,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.26,
335
+ "grad_norm": 6.875,
336
+ "learning_rate": 0.00015302295344301646,
337
+ "loss": 2.2812,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.27,
342
+ "grad_norm": 6.90625,
343
+ "learning_rate": 0.0001520228034205131,
344
+ "loss": 2.2422,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.28,
349
+ "grad_norm": 6.28125,
350
+ "learning_rate": 0.00015102265339800972,
351
+ "loss": 2.7344,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.28,
356
+ "grad_norm": 5.90625,
357
+ "learning_rate": 0.00015002250337550635,
358
+ "loss": 2.1504,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.29,
363
+ "grad_norm": 8.25,
364
+ "learning_rate": 0.00014902235335300296,
365
+ "loss": 2.6289,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.29,
370
+ "grad_norm": 5.84375,
371
+ "learning_rate": 0.00014802220333049959,
372
+ "loss": 2.0312,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.3,
377
+ "grad_norm": 9.75,
378
+ "learning_rate": 0.00014702205330799622,
379
+ "loss": 2.1367,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.3,
384
+ "grad_norm": 5.21875,
385
+ "learning_rate": 0.00014602190328549282,
386
+ "loss": 1.7891,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.31,
391
+ "grad_norm": 7.46875,
392
+ "learning_rate": 0.00014502175326298945,
393
+ "loss": 2.2305,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.31,
398
+ "grad_norm": 9.625,
399
+ "learning_rate": 0.00014402160324048608,
400
+ "loss": 2.4395,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.32,
405
+ "grad_norm": 6.4375,
406
+ "learning_rate": 0.0001430214532179827,
407
+ "loss": 2.1445,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.33,
412
+ "grad_norm": 8.6875,
413
+ "learning_rate": 0.00014202130319547932,
414
+ "loss": 2.5586,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.33,
419
+ "grad_norm": 7.71875,
420
+ "learning_rate": 0.00014102115317297595,
421
+ "loss": 2.7031,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.34,
426
+ "grad_norm": 6.65625,
427
+ "learning_rate": 0.00014002100315047258,
428
+ "loss": 2.373,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.34,
433
+ "grad_norm": 8.375,
434
+ "learning_rate": 0.0001390208531279692,
435
+ "loss": 2.582,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.35,
440
+ "grad_norm": 6.75,
441
+ "learning_rate": 0.0001380207031054658,
442
+ "loss": 1.9961,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.35,
447
+ "grad_norm": 7.96875,
448
+ "learning_rate": 0.00013702055308296244,
449
+ "loss": 2.4199,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.36,
454
+ "grad_norm": 8.8125,
455
+ "learning_rate": 0.00013602040306045908,
456
+ "loss": 2.875,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.37,
461
+ "grad_norm": 6.3125,
462
+ "learning_rate": 0.00013502025303795568,
463
+ "loss": 2.5273,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.37,
468
+ "grad_norm": 7.46875,
469
+ "learning_rate": 0.0001340201030154523,
470
+ "loss": 2.2988,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.38,
475
+ "grad_norm": 8.625,
476
+ "learning_rate": 0.00013301995299294897,
477
+ "loss": 2.9023,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.38,
482
+ "grad_norm": 7.1875,
483
+ "learning_rate": 0.00013201980297044557,
484
+ "loss": 2.8047,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.39,
489
+ "grad_norm": 9.625,
490
+ "learning_rate": 0.0001310196529479422,
491
+ "loss": 2.6328,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.39,
496
+ "grad_norm": 6.8125,
497
+ "learning_rate": 0.00013001950292543883,
498
+ "loss": 2.168,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.4,
503
+ "grad_norm": 7.59375,
504
+ "learning_rate": 0.00012901935290293546,
505
+ "loss": 2.5234,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.4,
510
+ "grad_norm": 10.3125,
511
+ "learning_rate": 0.00012801920288043207,
512
+ "loss": 2.8516,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.41,
517
+ "grad_norm": 9.3125,
518
+ "learning_rate": 0.0001270190528579287,
519
+ "loss": 2.5273,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.42,
524
+ "grad_norm": 9.375,
525
+ "learning_rate": 0.00012601890283542533,
526
+ "loss": 3.0469,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.42,
531
+ "grad_norm": 6.875,
532
+ "learning_rate": 0.00012501875281292196,
533
+ "loss": 2.543,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.43,
538
+ "grad_norm": 9.25,
539
+ "learning_rate": 0.00012401860279041856,
540
+ "loss": 3.3125,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.43,
545
+ "grad_norm": 6.96875,
546
+ "learning_rate": 0.0001230184527679152,
547
+ "loss": 2.1328,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.44,
552
+ "grad_norm": 7.875,
553
+ "learning_rate": 0.00012201830274541181,
554
+ "loss": 2.875,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.44,
559
+ "grad_norm": 8.25,
560
+ "learning_rate": 0.00012101815272290844,
561
+ "loss": 2.4727,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.45,
566
+ "grad_norm": 7.15625,
567
+ "learning_rate": 0.00012001800270040506,
568
+ "loss": 2.5703,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.46,
573
+ "grad_norm": 9.8125,
574
+ "learning_rate": 0.00011901785267790169,
575
+ "loss": 3.3555,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.46,
580
+ "grad_norm": 5.8125,
581
+ "learning_rate": 0.00011801770265539831,
582
+ "loss": 2.5352,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.47,
587
+ "grad_norm": 5.03125,
588
+ "learning_rate": 0.00011701755263289494,
589
+ "loss": 2.0664,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.47,
594
+ "grad_norm": 9.5,
595
+ "learning_rate": 0.00011601740261039156,
596
+ "loss": 2.9844,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.48,
601
+ "grad_norm": 7.59375,
602
+ "learning_rate": 0.00011501725258788819,
603
+ "loss": 2.6602,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.48,
608
+ "grad_norm": 6.21875,
609
+ "learning_rate": 0.0001140171025653848,
610
+ "loss": 2.1367,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.49,
615
+ "grad_norm": 6.46875,
616
+ "learning_rate": 0.00011301695254288145,
617
+ "loss": 2.459,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.49,
622
+ "grad_norm": 7.75,
623
+ "learning_rate": 0.00011201680252037807,
624
+ "loss": 2.1484,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.5,
629
+ "grad_norm": 7.90625,
630
+ "learning_rate": 0.0001110166524978747,
631
+ "loss": 2.8867,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.51,
636
+ "grad_norm": 11.3125,
637
+ "learning_rate": 0.00011001650247537131,
638
+ "loss": 3.5586,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.51,
643
+ "grad_norm": 6.375,
644
+ "learning_rate": 0.00010901635245286794,
645
+ "loss": 2.8594,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.52,
650
+ "grad_norm": 9.1875,
651
+ "learning_rate": 0.00010801620243036456,
652
+ "loss": 3.4688,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.52,
657
+ "grad_norm": 8.5,
658
+ "learning_rate": 0.00010701605240786119,
659
+ "loss": 2.7031,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.53,
664
+ "grad_norm": 10.0,
665
+ "learning_rate": 0.00010601590238535781,
666
+ "loss": 3.0859,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.53,
671
+ "grad_norm": 8.5,
672
+ "learning_rate": 0.00010501575236285444,
673
+ "loss": 3.0352,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.54,
678
+ "grad_norm": 5.1875,
679
+ "learning_rate": 0.00010401560234035106,
680
+ "loss": 2.084,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.54,
685
+ "grad_norm": 7.0,
686
+ "learning_rate": 0.00010301545231784769,
687
+ "loss": 2.0508,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.55,
692
+ "grad_norm": 8.1875,
693
+ "learning_rate": 0.0001020153022953443,
694
+ "loss": 2.9805,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.56,
699
+ "grad_norm": 7.5625,
700
+ "learning_rate": 0.00010101515227284092,
701
+ "loss": 2.9766,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.56,
706
+ "grad_norm": 8.125,
707
+ "learning_rate": 0.00010001500225033755,
708
+ "loss": 2.502,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.57,
713
+ "grad_norm": 6.34375,
714
+ "learning_rate": 9.901485222783417e-05,
715
+ "loss": 2.4844,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.57,
720
+ "grad_norm": 9.4375,
721
+ "learning_rate": 9.80147022053308e-05,
722
+ "loss": 2.4492,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.58,
727
+ "grad_norm": 7.8125,
728
+ "learning_rate": 9.701455218282743e-05,
729
+ "loss": 2.5742,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.58,
734
+ "grad_norm": 7.09375,
735
+ "learning_rate": 9.601440216032405e-05,
736
+ "loss": 2.4688,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.59,
741
+ "grad_norm": 7.5625,
742
+ "learning_rate": 9.501425213782068e-05,
743
+ "loss": 2.6211,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.6,
748
+ "grad_norm": 8.9375,
749
+ "learning_rate": 9.40141021153173e-05,
750
+ "loss": 2.8027,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.6,
755
+ "grad_norm": 9.3125,
756
+ "learning_rate": 9.301395209281393e-05,
757
+ "loss": 2.5742,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.61,
762
+ "grad_norm": 5.5625,
763
+ "learning_rate": 9.201380207031055e-05,
764
+ "loss": 2.4258,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.61,
769
+ "grad_norm": 9.25,
770
+ "learning_rate": 9.101365204780718e-05,
771
+ "loss": 2.9141,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.62,
776
+ "grad_norm": 7.78125,
777
+ "learning_rate": 9.00135020253038e-05,
778
+ "loss": 2.2578,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.62,
783
+ "grad_norm": 7.09375,
784
+ "learning_rate": 8.901335200280043e-05,
785
+ "loss": 2.5312,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.63,
790
+ "grad_norm": 6.78125,
791
+ "learning_rate": 8.801320198029704e-05,
792
+ "loss": 2.1133,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.63,
797
+ "grad_norm": 8.625,
798
+ "learning_rate": 8.701305195779367e-05,
799
+ "loss": 2.6523,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.64,
804
+ "grad_norm": 8.0625,
805
+ "learning_rate": 8.60129019352903e-05,
806
+ "loss": 2.9453,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.65,
811
+ "grad_norm": 7.15625,
812
+ "learning_rate": 8.501275191278692e-05,
813
+ "loss": 2.6816,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.65,
818
+ "grad_norm": 7.21875,
819
+ "learning_rate": 8.401260189028355e-05,
820
+ "loss": 2.7227,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.66,
825
+ "grad_norm": 8.3125,
826
+ "learning_rate": 8.301245186778017e-05,
827
+ "loss": 2.6191,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.66,
832
+ "grad_norm": 7.5625,
833
+ "learning_rate": 8.20123018452768e-05,
834
+ "loss": 2.459,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.67,
839
+ "grad_norm": 6.46875,
840
+ "learning_rate": 8.101215182277342e-05,
841
+ "loss": 2.4297,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.67,
846
+ "grad_norm": 8.375,
847
+ "learning_rate": 8.001200180027005e-05,
848
+ "loss": 2.4609,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.68,
853
+ "grad_norm": 7.875,
854
+ "learning_rate": 7.901185177776667e-05,
855
+ "loss": 2.7539,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.69,
860
+ "grad_norm": 6.3125,
861
+ "learning_rate": 7.801170175526328e-05,
862
+ "loss": 2.2148,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.69,
867
+ "grad_norm": 6.75,
868
+ "learning_rate": 7.701155173275993e-05,
869
+ "loss": 2.4512,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.7,
874
+ "grad_norm": 9.1875,
875
+ "learning_rate": 7.601140171025655e-05,
876
+ "loss": 2.5859,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.7,
881
+ "grad_norm": 8.3125,
882
+ "learning_rate": 7.501125168775318e-05,
883
+ "loss": 2.6797,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.71,
888
+ "grad_norm": 9.125,
889
+ "learning_rate": 7.401110166524979e-05,
890
+ "loss": 3.168,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.71,
895
+ "grad_norm": 6.15625,
896
+ "learning_rate": 7.301095164274641e-05,
897
+ "loss": 2.1816,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.72,
902
+ "grad_norm": 7.8125,
903
+ "learning_rate": 7.201080162024304e-05,
904
+ "loss": 2.9766,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.72,
909
+ "grad_norm": 6.625,
910
+ "learning_rate": 7.101065159773966e-05,
911
+ "loss": 2.1836,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.73,
916
+ "grad_norm": 10.5,
917
+ "learning_rate": 7.001050157523629e-05,
918
+ "loss": 2.8086,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.74,
923
+ "grad_norm": 6.15625,
924
+ "learning_rate": 6.90103515527329e-05,
925
+ "loss": 2.4141,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.74,
930
+ "grad_norm": 7.375,
931
+ "learning_rate": 6.801020153022954e-05,
932
+ "loss": 2.5742,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.75,
937
+ "grad_norm": 7.46875,
938
+ "learning_rate": 6.701005150772615e-05,
939
+ "loss": 2.9883,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.75,
944
+ "grad_norm": 8.0625,
945
+ "learning_rate": 6.600990148522279e-05,
946
+ "loss": 2.418,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.76,
951
+ "grad_norm": 7.53125,
952
+ "learning_rate": 6.500975146271942e-05,
953
+ "loss": 2.7578,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.76,
958
+ "grad_norm": 7.90625,
959
+ "learning_rate": 6.400960144021603e-05,
960
+ "loss": 3.0078,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.77,
965
+ "grad_norm": 6.125,
966
+ "learning_rate": 6.300945141771266e-05,
967
+ "loss": 2.2012,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.78,
972
+ "grad_norm": 8.0,
973
+ "learning_rate": 6.200930139520928e-05,
974
+ "loss": 3.0703,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.78,
979
+ "grad_norm": 6.90625,
980
+ "learning_rate": 6.1009151372705906e-05,
981
+ "loss": 2.7031,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.79,
986
+ "grad_norm": 5.15625,
987
+ "learning_rate": 6.000900135020253e-05,
988
+ "loss": 1.9014,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.79,
993
+ "grad_norm": 6.9375,
994
+ "learning_rate": 5.9008851327699154e-05,
995
+ "loss": 2.3809,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.8,
1000
+ "grad_norm": 6.8125,
1001
+ "learning_rate": 5.800870130519578e-05,
1002
+ "loss": 2.5469,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.8,
1007
+ "grad_norm": 6.0,
1008
+ "learning_rate": 5.70085512826924e-05,
1009
+ "loss": 3.0938,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.81,
1014
+ "grad_norm": 7.25,
1015
+ "learning_rate": 5.600840126018903e-05,
1016
+ "loss": 2.4395,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.81,
1021
+ "grad_norm": 6.59375,
1022
+ "learning_rate": 5.500825123768566e-05,
1023
+ "loss": 2.5254,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.82,
1028
+ "grad_norm": 6.96875,
1029
+ "learning_rate": 5.400810121518228e-05,
1030
+ "loss": 2.7773,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.83,
1035
+ "grad_norm": 8.0625,
1036
+ "learning_rate": 5.3007951192678905e-05,
1037
+ "loss": 2.6875,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.83,
1042
+ "grad_norm": 7.28125,
1043
+ "learning_rate": 5.200780117017553e-05,
1044
+ "loss": 3.0898,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.84,
1049
+ "grad_norm": 6.5625,
1050
+ "learning_rate": 5.100765114767215e-05,
1051
+ "loss": 2.3984,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.84,
1056
+ "grad_norm": 5.90625,
1057
+ "learning_rate": 5.000750112516878e-05,
1058
+ "loss": 2.1445,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.85,
1063
+ "grad_norm": 7.65625,
1064
+ "learning_rate": 4.90073511026654e-05,
1065
+ "loss": 2.8125,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.85,
1070
+ "grad_norm": 6.59375,
1071
+ "learning_rate": 4.8007201080162025e-05,
1072
+ "loss": 2.3242,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.86,
1077
+ "grad_norm": 7.0625,
1078
+ "learning_rate": 4.700705105765865e-05,
1079
+ "loss": 2.3965,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.87,
1084
+ "grad_norm": 6.3125,
1085
+ "learning_rate": 4.6006901035155273e-05,
1086
+ "loss": 2.4824,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.87,
1091
+ "grad_norm": 8.6875,
1092
+ "learning_rate": 4.50067510126519e-05,
1093
+ "loss": 2.6445,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.88,
1098
+ "grad_norm": 6.71875,
1099
+ "learning_rate": 4.400660099014852e-05,
1100
+ "loss": 2.1689,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.88,
1105
+ "grad_norm": 6.0625,
1106
+ "learning_rate": 4.300645096764515e-05,
1107
+ "loss": 2.4219,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.89,
1112
+ "grad_norm": 7.59375,
1113
+ "learning_rate": 4.2006300945141776e-05,
1114
+ "loss": 2.7227,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.89,
1119
+ "grad_norm": 6.25,
1120
+ "learning_rate": 4.10061509226384e-05,
1121
+ "loss": 2.7812,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.9,
1126
+ "grad_norm": 5.5,
1127
+ "learning_rate": 4.0006000900135024e-05,
1128
+ "loss": 2.3574,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.9,
1133
+ "grad_norm": 6.65625,
1134
+ "learning_rate": 3.900585087763164e-05,
1135
+ "loss": 2.6016,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.91,
1140
+ "grad_norm": 6.5625,
1141
+ "learning_rate": 3.800570085512827e-05,
1142
+ "loss": 2.7617,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.92,
1147
+ "grad_norm": 6.09375,
1148
+ "learning_rate": 3.7005550832624897e-05,
1149
+ "loss": 2.2285,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.92,
1154
+ "grad_norm": 7.75,
1155
+ "learning_rate": 3.600540081012152e-05,
1156
+ "loss": 3.0,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.93,
1161
+ "grad_norm": 5.90625,
1162
+ "learning_rate": 3.5005250787618145e-05,
1163
+ "loss": 2.6172,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.93,
1168
+ "grad_norm": 6.3125,
1169
+ "learning_rate": 3.400510076511477e-05,
1170
+ "loss": 2.3242,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.94,
1175
+ "grad_norm": 6.25,
1176
+ "learning_rate": 3.300495074261139e-05,
1177
+ "loss": 2.0098,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.94,
1182
+ "grad_norm": 7.25,
1183
+ "learning_rate": 3.200480072010802e-05,
1184
+ "loss": 1.9238,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.95,
1189
+ "grad_norm": 5.84375,
1190
+ "learning_rate": 3.100465069760464e-05,
1191
+ "loss": 2.4082,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.96,
1196
+ "grad_norm": 5.0625,
1197
+ "learning_rate": 3.0004500675101265e-05,
1198
+ "loss": 1.8848,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.96,
1203
+ "grad_norm": 5.28125,
1204
+ "learning_rate": 2.900435065259789e-05,
1205
+ "loss": 2.293,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.97,
1210
+ "grad_norm": 8.5,
1211
+ "learning_rate": 2.8004200630094516e-05,
1212
+ "loss": 3.332,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.97,
1217
+ "grad_norm": 5.84375,
1218
+ "learning_rate": 2.700405060759114e-05,
1219
+ "loss": 2.1543,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.98,
1224
+ "grad_norm": 9.0,
1225
+ "learning_rate": 2.6003900585087765e-05,
1226
+ "loss": 3.0156,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.98,
1231
+ "grad_norm": 6.3125,
1232
+ "learning_rate": 2.500375056258439e-05,
1233
+ "loss": 2.4844,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.99,
1238
+ "grad_norm": 7.15625,
1239
+ "learning_rate": 2.4003600540081013e-05,
1240
+ "loss": 2.4414,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.99,
1245
+ "grad_norm": 6.46875,
1246
+ "learning_rate": 2.3003450517577637e-05,
1247
+ "loss": 2.584,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.0,
1252
+ "grad_norm": 8.6875,
1253
+ "learning_rate": 2.200330049507426e-05,
1254
+ "loss": 2.9062,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.01,
1259
+ "grad_norm": 6.6875,
1260
+ "learning_rate": 2.1003150472570888e-05,
1261
+ "loss": 2.127,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.01,
1266
+ "grad_norm": 5.78125,
1267
+ "learning_rate": 2.0003000450067512e-05,
1268
+ "loss": 2.3066,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.02,
1273
+ "grad_norm": 6.75,
1274
+ "learning_rate": 1.9002850427564136e-05,
1275
+ "loss": 1.6729,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.02,
1280
+ "grad_norm": 6.09375,
1281
+ "learning_rate": 1.800270040506076e-05,
1282
+ "loss": 2.0488,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.03,
1287
+ "grad_norm": 5.53125,
1288
+ "learning_rate": 1.7002550382557384e-05,
1289
+ "loss": 1.5322,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.03,
1294
+ "grad_norm": 6.125,
1295
+ "learning_rate": 1.600240036005401e-05,
1296
+ "loss": 1.4639,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.04,
1301
+ "grad_norm": 6.8125,
1302
+ "learning_rate": 1.5002250337550632e-05,
1303
+ "loss": 2.5938,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.04,
1308
+ "grad_norm": 5.6875,
1309
+ "learning_rate": 1.4002100315047258e-05,
1310
+ "loss": 1.7109,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.05,
1315
+ "grad_norm": 5.875,
1316
+ "learning_rate": 1.3001950292543882e-05,
1317
+ "loss": 1.6211,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.06,
1322
+ "grad_norm": 6.25,
1323
+ "learning_rate": 1.2001800270040506e-05,
1324
+ "loss": 2.0449,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.06,
1329
+ "grad_norm": 5.59375,
1330
+ "learning_rate": 1.100165024753713e-05,
1331
+ "loss": 1.6562,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.07,
1336
+ "grad_norm": 7.21875,
1337
+ "learning_rate": 1.0001500225033756e-05,
1338
+ "loss": 2.041,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.07,
1343
+ "grad_norm": 5.5,
1344
+ "learning_rate": 9.00135020253038e-06,
1345
+ "loss": 1.8105,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.08,
1350
+ "grad_norm": 4.875,
1351
+ "learning_rate": 8.001200180027004e-06,
1352
+ "loss": 1.916,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.08,
1357
+ "grad_norm": 5.75,
1358
+ "learning_rate": 7.001050157523629e-06,
1359
+ "loss": 1.7607,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.09,
1364
+ "grad_norm": 5.4375,
1365
+ "learning_rate": 6.000900135020253e-06,
1366
+ "loss": 1.6367,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.1,
1371
+ "grad_norm": 5.0,
1372
+ "learning_rate": 5.000750112516878e-06,
1373
+ "loss": 2.0332,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.1,
1378
+ "grad_norm": 7.21875,
1379
+ "learning_rate": 4.000600090013502e-06,
1380
+ "loss": 1.7188,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.11,
1385
+ "grad_norm": 5.84375,
1386
+ "learning_rate": 3.0004500675101266e-06,
1387
+ "loss": 1.832,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.11,
1392
+ "grad_norm": 6.78125,
1393
+ "learning_rate": 2.000300045006751e-06,
1394
+ "loss": 2.0049,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.12,
1399
+ "grad_norm": 6.15625,
1400
+ "learning_rate": 1.0001500225033755e-06,
1401
+ "loss": 1.6953,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.12,
1406
+ "grad_norm": 6.875,
1407
+ "learning_rate": 0.0,
1408
+ "loss": 1.8525,
1409
+ "step": 200
1410
+ }
1411
+ ],
1412
+ "logging_steps": 1,
1413
+ "max_steps": 200,
1414
+ "num_input_tokens_seen": 0,
1415
+ "num_train_epochs": 2,
1416
+ "save_steps": 500,
1417
+ "total_flos": 509004324495360.0,
1418
+ "train_batch_size": 1,
1419
+ "trial_name": null,
1420
+ "trial_params": null
1421
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e087f86407314671ff729d60090d4b18b347518639673e7139cadbe0e56ffe0f
3
+ size 4920