PsychicMoon commited on
Commit
aeb0d4b
·
verified ·
1 Parent(s): 2cc22f9

manual upload

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]
@@ -199,3 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
199
  [More Information Needed]
200
 
201
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
+ base_model: HuggingFaceH4/zephyr-7b-beta
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]
 
199
  [More Information Needed]
200
 
201
 
202
+ ### Framework versions
203
+
204
+ - PEFT 0.7.2.dev0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
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": 32,
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
+ "up_proj",
23
+ "v_proj",
24
+ "down_proj",
25
+ "q_proj",
26
+ "o_proj",
27
+ "gate_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
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:a8cb623b1c82c15f0f5fa86487ad5b5c46dfcf8495d33f2d4e61b20cb947c28b
3
+ size 83945296
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3948cf120d51764918ee9eda2316710ff1fff93e01d6bac2ae67aeda7a37dcb1
3
+ size 42545311
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251475e7aa2dde3aa93427e88d56ddd22d3d76e69f31cc7fce21f0f57e0297db
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d192557382fc296cf4231345651e7500c21a945d50df66d5efb4af87da5a481
3
+ size 627
special_tokens_map.json CHANGED
@@ -18,7 +18,13 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "pad_token": "</s>",
 
 
 
 
 
 
22
  "unk_token": {
23
  "content": "<unk>",
24
  "lstrip": false,
 
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
  "unk_token": {
29
  "content": "<unk>",
30
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -37,15 +37,12 @@
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
  "legacy": true,
40
- "max_length": 1024,
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "</s>",
43
  "sp_model_kwargs": {},
44
  "spaces_between_special_tokens": false,
45
- "stride": 0,
46
  "tokenizer_class": "LlamaTokenizer",
47
  "truncation_side": "left",
48
- "truncation_strategy": "longest_first",
49
  "unk_token": "<unk>",
50
  "use_default_system_prompt": true
51
  }
 
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
  "legacy": true,
 
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "</s>",
42
  "sp_model_kwargs": {},
43
  "spaces_between_special_tokens": false,
 
44
  "tokenizer_class": "LlamaTokenizer",
45
  "truncation_side": "left",
 
46
  "unk_token": "<unk>",
47
  "use_default_system_prompt": true
48
  }
trainer_state.json ADDED
@@ -0,0 +1,1461 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.0588235294117645,
5
+ "eval_steps": 500,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 0.00019922390686882426,
14
+ "loss": 1.5465,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.00019842381085730289,
20
+ "loss": 1.4494,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.00019762371484578152,
26
+ "loss": 1.2437,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 0.00019682361883426012,
32
+ "loss": 1.3019,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 0.00019602352282273875,
38
+ "loss": 1.4664,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 0.00019522342681121735,
44
+ "loss": 1.1706,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 0.00019442333079969598,
50
+ "loss": 1.2089,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 0.00019362323478817458,
56
+ "loss": 1.0329,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.0001928231387766532,
62
+ "loss": 1.3136,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.00019202304276513184,
68
+ "loss": 1.0903,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.32,
73
+ "learning_rate": 0.00019122294675361044,
74
+ "loss": 1.089,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.35,
79
+ "learning_rate": 0.00019042285074208904,
80
+ "loss": 1.2918,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.38,
85
+ "learning_rate": 0.00018962275473056767,
86
+ "loss": 1.0208,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.41,
91
+ "learning_rate": 0.0001888226587190463,
92
+ "loss": 1.2414,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.44,
97
+ "learning_rate": 0.00018802256270752493,
98
+ "loss": 0.8309,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.47,
103
+ "learning_rate": 0.00018722246669600353,
104
+ "loss": 1.0701,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.5,
109
+ "learning_rate": 0.00018642237068448213,
110
+ "loss": 1.103,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.53,
115
+ "learning_rate": 0.00018562227467296076,
116
+ "loss": 1.1536,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.56,
121
+ "learning_rate": 0.0001848221786614394,
122
+ "loss": 0.9786,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.59,
127
+ "learning_rate": 0.000184022082649918,
128
+ "loss": 1.0474,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.62,
133
+ "learning_rate": 0.00018322198663839662,
134
+ "loss": 0.9066,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.65,
139
+ "learning_rate": 0.00018242189062687522,
140
+ "loss": 1.0756,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.68,
145
+ "learning_rate": 0.00018162179461535385,
146
+ "loss": 0.9649,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.71,
151
+ "learning_rate": 0.00018082169860383248,
152
+ "loss": 1.0698,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.74,
157
+ "learning_rate": 0.00018002160259231108,
158
+ "loss": 1.0971,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.76,
163
+ "learning_rate": 0.0001792215065807897,
164
+ "loss": 1.0154,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.79,
169
+ "learning_rate": 0.00017842141056926834,
170
+ "loss": 1.2113,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.82,
175
+ "learning_rate": 0.00017762131455774694,
176
+ "loss": 1.0433,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.85,
181
+ "learning_rate": 0.00017682121854622554,
182
+ "loss": 0.9149,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.88,
187
+ "learning_rate": 0.00017602112253470417,
188
+ "loss": 1.294,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.91,
193
+ "learning_rate": 0.0001752210265231828,
194
+ "loss": 0.8756,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.94,
199
+ "learning_rate": 0.00017442093051166143,
200
+ "loss": 0.9514,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.97,
205
+ "learning_rate": 0.00017362083450014,
206
+ "loss": 0.7657,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 1.0,
211
+ "learning_rate": 0.00017282073848861863,
212
+ "loss": 0.9848,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 1.03,
217
+ "learning_rate": 0.00017202064247709726,
218
+ "loss": 0.9737,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 1.06,
223
+ "learning_rate": 0.0001712205464655759,
224
+ "loss": 0.6804,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 1.09,
229
+ "learning_rate": 0.0001704204504540545,
230
+ "loss": 1.0733,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.12,
235
+ "learning_rate": 0.0001696203544425331,
236
+ "loss": 0.984,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.15,
241
+ "learning_rate": 0.00016882025843101172,
242
+ "loss": 0.7753,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 1.18,
247
+ "learning_rate": 0.00016802016241949035,
248
+ "loss": 0.9925,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 1.21,
253
+ "learning_rate": 0.00016722006640796896,
254
+ "loss": 0.4777,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 1.24,
259
+ "learning_rate": 0.00016641997039644758,
260
+ "loss": 0.8519,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 1.26,
265
+ "learning_rate": 0.00016561987438492621,
266
+ "loss": 0.8004,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 1.29,
271
+ "learning_rate": 0.00016481977837340482,
272
+ "loss": 0.8533,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 1.32,
277
+ "learning_rate": 0.00016401968236188344,
278
+ "loss": 0.5997,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 1.35,
283
+ "learning_rate": 0.00016321958635036205,
284
+ "loss": 0.7882,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 1.38,
289
+ "learning_rate": 0.00016241949033884068,
290
+ "loss": 1.0804,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 1.41,
295
+ "learning_rate": 0.0001616193943273193,
296
+ "loss": 0.4132,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 1.44,
301
+ "learning_rate": 0.0001608192983157979,
302
+ "loss": 0.9914,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 1.47,
307
+ "learning_rate": 0.0001600192023042765,
308
+ "loss": 0.3964,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 1.5,
313
+ "learning_rate": 0.00015921910629275514,
314
+ "loss": 0.5703,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 1.53,
319
+ "learning_rate": 0.00015841901028123377,
320
+ "loss": 0.7238,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 1.56,
325
+ "learning_rate": 0.00015761891426971237,
326
+ "loss": 0.6712,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 1.59,
331
+ "learning_rate": 0.00015681881825819097,
332
+ "loss": 0.6738,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 1.62,
337
+ "learning_rate": 0.0001560187222466696,
338
+ "loss": 0.6217,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 1.65,
343
+ "learning_rate": 0.00015521862623514823,
344
+ "loss": 0.5953,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 1.68,
349
+ "learning_rate": 0.00015441853022362686,
350
+ "loss": 0.8303,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 1.71,
355
+ "learning_rate": 0.00015361843421210546,
356
+ "loss": 0.6253,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 1.74,
361
+ "learning_rate": 0.0001528183382005841,
362
+ "loss": 0.3754,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 1.76,
367
+ "learning_rate": 0.0001520182421890627,
368
+ "loss": 0.6664,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.79,
373
+ "learning_rate": 0.00015121814617754132,
374
+ "loss": 0.6756,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.82,
379
+ "learning_rate": 0.00015041805016601992,
380
+ "loss": 0.8601,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.85,
385
+ "learning_rate": 0.00014961795415449855,
386
+ "loss": 0.6088,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.88,
391
+ "learning_rate": 0.00014881785814297718,
392
+ "loss": 0.5837,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.91,
397
+ "learning_rate": 0.00014801776213145578,
398
+ "loss": 0.5813,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.94,
403
+ "learning_rate": 0.00014721766611993438,
404
+ "loss": 0.672,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.97,
409
+ "learning_rate": 0.000146417570108413,
410
+ "loss": 0.9818,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 2.0,
415
+ "learning_rate": 0.00014561747409689164,
416
+ "loss": 0.7044,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 2.03,
421
+ "learning_rate": 0.00014481737808537027,
422
+ "loss": 0.4525,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 2.06,
427
+ "learning_rate": 0.00014401728207384887,
428
+ "loss": 0.3649,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 2.09,
433
+ "learning_rate": 0.00014321718606232747,
434
+ "loss": 0.4089,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 2.12,
439
+ "learning_rate": 0.0001424170900508061,
440
+ "loss": 0.4102,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 2.15,
445
+ "learning_rate": 0.00014161699403928473,
446
+ "loss": 0.2403,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 2.18,
451
+ "learning_rate": 0.00014081689802776333,
452
+ "loss": 0.3113,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 2.21,
457
+ "learning_rate": 0.00014001680201624196,
458
+ "loss": 0.5503,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 2.24,
463
+ "learning_rate": 0.00013921670600472056,
464
+ "loss": 0.6021,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 2.26,
469
+ "learning_rate": 0.0001384166099931992,
470
+ "loss": 0.5271,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 2.29,
475
+ "learning_rate": 0.00013761651398167782,
476
+ "loss": 0.3207,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 2.32,
481
+ "learning_rate": 0.00013681641797015642,
482
+ "loss": 0.4899,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 2.35,
487
+ "learning_rate": 0.00013601632195863505,
488
+ "loss": 0.3858,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 2.38,
493
+ "learning_rate": 0.00013521622594711365,
494
+ "loss": 0.4361,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 2.41,
499
+ "learning_rate": 0.00013441612993559228,
500
+ "loss": 0.3672,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 2.44,
505
+ "learning_rate": 0.00013361603392407088,
506
+ "loss": 0.5378,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 2.47,
511
+ "learning_rate": 0.00013281593791254951,
512
+ "loss": 0.3577,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 2.5,
517
+ "learning_rate": 0.00013201584190102814,
518
+ "loss": 0.2658,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 2.53,
523
+ "learning_rate": 0.00013121574588950674,
524
+ "loss": 0.2015,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 2.56,
529
+ "learning_rate": 0.00013041564987798535,
530
+ "loss": 0.4888,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 2.59,
535
+ "learning_rate": 0.00012961555386646398,
536
+ "loss": 0.3641,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 2.62,
541
+ "learning_rate": 0.0001288154578549426,
542
+ "loss": 0.3613,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 2.65,
547
+ "learning_rate": 0.00012801536184342123,
548
+ "loss": 0.3576,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 2.68,
553
+ "learning_rate": 0.00012721526583189984,
554
+ "loss": 0.1833,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 2.71,
559
+ "learning_rate": 0.00012641516982037844,
560
+ "loss": 0.1528,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 2.74,
565
+ "learning_rate": 0.00012561507380885707,
566
+ "loss": 0.5194,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 2.76,
571
+ "learning_rate": 0.0001248149777973357,
572
+ "loss": 0.543,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 2.79,
577
+ "learning_rate": 0.0001240148817858143,
578
+ "loss": 0.2746,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 2.82,
583
+ "learning_rate": 0.00012321478577429293,
584
+ "loss": 0.1863,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 2.85,
589
+ "learning_rate": 0.00012241468976277153,
590
+ "loss": 0.4064,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 2.88,
595
+ "learning_rate": 0.00012161459375125014,
596
+ "loss": 0.4429,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 2.91,
601
+ "learning_rate": 0.00012081449773972877,
602
+ "loss": 0.32,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 2.94,
607
+ "learning_rate": 0.00012001440172820739,
608
+ "loss": 0.266,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 2.97,
613
+ "learning_rate": 0.00011921430571668602,
614
+ "loss": 0.4243,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 3.0,
619
+ "learning_rate": 0.00011841420970516463,
620
+ "loss": 0.381,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 3.03,
625
+ "learning_rate": 0.00011761411369364323,
626
+ "loss": 0.1964,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 3.06,
631
+ "learning_rate": 0.00011681401768212186,
632
+ "loss": 0.2786,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 3.09,
637
+ "learning_rate": 0.00011601392167060048,
638
+ "loss": 0.2606,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 3.12,
643
+ "learning_rate": 0.0001152138256590791,
644
+ "loss": 0.1124,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 3.15,
649
+ "learning_rate": 0.00011441372964755772,
650
+ "loss": 0.242,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 3.18,
655
+ "learning_rate": 0.00011361363363603632,
656
+ "loss": 0.1387,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 3.21,
661
+ "learning_rate": 0.00011281353762451494,
662
+ "loss": 0.1772,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 3.24,
667
+ "learning_rate": 0.00011201344161299357,
668
+ "loss": 0.1568,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 3.26,
673
+ "learning_rate": 0.00011121334560147218,
674
+ "loss": 0.2883,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 3.29,
679
+ "learning_rate": 0.00011041324958995081,
680
+ "loss": 0.2013,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 3.32,
685
+ "learning_rate": 0.00010961315357842943,
686
+ "loss": 0.2457,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 3.35,
691
+ "learning_rate": 0.00010881305756690803,
692
+ "loss": 0.1284,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 3.38,
697
+ "learning_rate": 0.00010801296155538665,
698
+ "loss": 0.1901,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 3.41,
703
+ "learning_rate": 0.00010721286554386528,
704
+ "loss": 0.1334,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 3.44,
709
+ "learning_rate": 0.00010641276953234389,
710
+ "loss": 0.1461,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 3.47,
715
+ "learning_rate": 0.00010561267352082252,
716
+ "loss": 0.2129,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 3.5,
721
+ "learning_rate": 0.00010481257750930111,
722
+ "loss": 0.0939,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 3.53,
727
+ "learning_rate": 0.00010401248149777974,
728
+ "loss": 0.1209,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 3.56,
733
+ "learning_rate": 0.00010321238548625835,
734
+ "loss": 0.1331,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 3.59,
739
+ "learning_rate": 0.00010241228947473698,
740
+ "loss": 0.0941,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 3.62,
745
+ "learning_rate": 0.0001016121934632156,
746
+ "loss": 0.2107,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 3.65,
751
+ "learning_rate": 0.0001008120974516942,
752
+ "loss": 0.2211,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 3.68,
757
+ "learning_rate": 0.00010001200144017281,
758
+ "loss": 0.145,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 3.71,
763
+ "learning_rate": 9.921190542865144e-05,
764
+ "loss": 0.1024,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 3.74,
769
+ "learning_rate": 9.841180941713006e-05,
770
+ "loss": 0.0663,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 3.76,
775
+ "learning_rate": 9.761171340560867e-05,
776
+ "loss": 0.1352,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 3.79,
781
+ "learning_rate": 9.681161739408729e-05,
782
+ "loss": 0.2258,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 3.82,
787
+ "learning_rate": 9.601152138256592e-05,
788
+ "loss": 0.1926,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 3.85,
793
+ "learning_rate": 9.521142537104452e-05,
794
+ "loss": 0.1149,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 3.88,
799
+ "learning_rate": 9.441132935952315e-05,
800
+ "loss": 0.1301,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 3.91,
805
+ "learning_rate": 9.361123334800176e-05,
806
+ "loss": 0.0552,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 3.94,
811
+ "learning_rate": 9.281113733648038e-05,
812
+ "loss": 0.1837,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 3.97,
817
+ "learning_rate": 9.2011041324959e-05,
818
+ "loss": 0.1085,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 4.0,
823
+ "learning_rate": 9.121094531343761e-05,
824
+ "loss": 0.2303,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 4.03,
829
+ "learning_rate": 9.041084930191624e-05,
830
+ "loss": 0.0498,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 4.06,
835
+ "learning_rate": 8.961075329039486e-05,
836
+ "loss": 0.0452,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 4.09,
841
+ "learning_rate": 8.881065727887347e-05,
842
+ "loss": 0.1161,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 4.12,
847
+ "learning_rate": 8.801056126735209e-05,
848
+ "loss": 0.0441,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 4.15,
853
+ "learning_rate": 8.721046525583072e-05,
854
+ "loss": 0.0704,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 4.18,
859
+ "learning_rate": 8.641036924430932e-05,
860
+ "loss": 0.1103,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 4.21,
865
+ "learning_rate": 8.561027323278795e-05,
866
+ "loss": 0.0313,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 4.24,
871
+ "learning_rate": 8.481017722126655e-05,
872
+ "loss": 0.0494,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 4.26,
877
+ "learning_rate": 8.401008120974518e-05,
878
+ "loss": 0.0805,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 4.29,
883
+ "learning_rate": 8.320998519822379e-05,
884
+ "loss": 0.0512,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 4.32,
889
+ "learning_rate": 8.240988918670241e-05,
890
+ "loss": 0.0442,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 4.35,
895
+ "learning_rate": 8.160979317518102e-05,
896
+ "loss": 0.0944,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 4.38,
901
+ "learning_rate": 8.080969716365965e-05,
902
+ "loss": 0.0621,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 4.41,
907
+ "learning_rate": 8.000960115213825e-05,
908
+ "loss": 0.1191,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 4.44,
913
+ "learning_rate": 7.920950514061688e-05,
914
+ "loss": 0.1518,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 4.47,
919
+ "learning_rate": 7.840940912909548e-05,
920
+ "loss": 0.1002,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 4.5,
925
+ "learning_rate": 7.760931311757411e-05,
926
+ "loss": 0.0803,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 4.53,
931
+ "learning_rate": 7.680921710605273e-05,
932
+ "loss": 0.0582,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 4.56,
937
+ "learning_rate": 7.600912109453134e-05,
938
+ "loss": 0.0745,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 4.59,
943
+ "learning_rate": 7.520902508300996e-05,
944
+ "loss": 0.0844,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 4.62,
949
+ "learning_rate": 7.440892907148859e-05,
950
+ "loss": 0.056,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 4.65,
955
+ "learning_rate": 7.360883305996719e-05,
956
+ "loss": 0.1091,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 4.68,
961
+ "learning_rate": 7.280873704844582e-05,
962
+ "loss": 0.0561,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 4.71,
967
+ "learning_rate": 7.200864103692444e-05,
968
+ "loss": 0.0815,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 4.74,
973
+ "learning_rate": 7.120854502540305e-05,
974
+ "loss": 0.0704,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 4.76,
979
+ "learning_rate": 7.040844901388167e-05,
980
+ "loss": 0.0954,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 4.79,
985
+ "learning_rate": 6.960835300236028e-05,
986
+ "loss": 0.0915,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 4.82,
991
+ "learning_rate": 6.880825699083891e-05,
992
+ "loss": 0.0539,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 4.85,
997
+ "learning_rate": 6.800816097931753e-05,
998
+ "loss": 0.0694,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 4.88,
1003
+ "learning_rate": 6.720806496779614e-05,
1004
+ "loss": 0.0763,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 4.91,
1009
+ "learning_rate": 6.640796895627476e-05,
1010
+ "loss": 0.0388,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 4.94,
1015
+ "learning_rate": 6.560787294475337e-05,
1016
+ "loss": 0.1189,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 4.97,
1021
+ "learning_rate": 6.480777693323199e-05,
1022
+ "loss": 0.0441,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 5.0,
1027
+ "learning_rate": 6.400768092171062e-05,
1028
+ "loss": 0.0801,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 5.03,
1033
+ "learning_rate": 6.320758491018922e-05,
1034
+ "loss": 0.027,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 5.06,
1039
+ "learning_rate": 6.240748889866785e-05,
1040
+ "loss": 0.0346,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 5.09,
1045
+ "learning_rate": 6.160739288714646e-05,
1046
+ "loss": 0.0385,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 5.12,
1051
+ "learning_rate": 6.080729687562507e-05,
1052
+ "loss": 0.0575,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 5.15,
1057
+ "learning_rate": 6.0007200864103694e-05,
1058
+ "loss": 0.042,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 5.18,
1063
+ "learning_rate": 5.9207104852582316e-05,
1064
+ "loss": 0.0521,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 5.21,
1069
+ "learning_rate": 5.840700884106093e-05,
1070
+ "loss": 0.054,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 5.24,
1075
+ "learning_rate": 5.760691282953955e-05,
1076
+ "loss": 0.0503,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 5.26,
1081
+ "learning_rate": 5.680681681801816e-05,
1082
+ "loss": 0.0285,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 5.29,
1087
+ "learning_rate": 5.6006720806496785e-05,
1088
+ "loss": 0.0281,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 5.32,
1093
+ "learning_rate": 5.520662479497541e-05,
1094
+ "loss": 0.0402,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 5.35,
1099
+ "learning_rate": 5.4406528783454015e-05,
1100
+ "loss": 0.04,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 5.38,
1105
+ "learning_rate": 5.360643277193264e-05,
1106
+ "loss": 0.044,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 5.41,
1111
+ "learning_rate": 5.280633676041126e-05,
1112
+ "loss": 0.0264,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 5.44,
1117
+ "learning_rate": 5.200624074888987e-05,
1118
+ "loss": 0.0379,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 5.47,
1123
+ "learning_rate": 5.120614473736849e-05,
1124
+ "loss": 0.037,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 5.5,
1129
+ "learning_rate": 5.04060487258471e-05,
1130
+ "loss": 0.0422,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 5.53,
1135
+ "learning_rate": 4.960595271432572e-05,
1136
+ "loss": 0.0313,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 5.56,
1141
+ "learning_rate": 4.880585670280434e-05,
1142
+ "loss": 0.0241,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 5.59,
1147
+ "learning_rate": 4.800576069128296e-05,
1148
+ "loss": 0.0546,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 5.62,
1153
+ "learning_rate": 4.7205664679761575e-05,
1154
+ "loss": 0.0305,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 5.65,
1159
+ "learning_rate": 4.640556866824019e-05,
1160
+ "loss": 0.0364,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 5.68,
1165
+ "learning_rate": 4.5605472656718805e-05,
1166
+ "loss": 0.0329,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 5.71,
1171
+ "learning_rate": 4.480537664519743e-05,
1172
+ "loss": 0.0453,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 5.74,
1177
+ "learning_rate": 4.400528063367604e-05,
1178
+ "loss": 0.0386,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 5.76,
1183
+ "learning_rate": 4.320518462215466e-05,
1184
+ "loss": 0.0401,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 5.79,
1189
+ "learning_rate": 4.2405088610633274e-05,
1190
+ "loss": 0.0527,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 5.82,
1195
+ "learning_rate": 4.1604992599111896e-05,
1196
+ "loss": 0.0342,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 5.85,
1201
+ "learning_rate": 4.080489658759051e-05,
1202
+ "loss": 0.0336,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 5.88,
1207
+ "learning_rate": 4.000480057606913e-05,
1208
+ "loss": 0.034,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 5.91,
1213
+ "learning_rate": 3.920470456454774e-05,
1214
+ "loss": 0.0316,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 5.94,
1219
+ "learning_rate": 3.8404608553026365e-05,
1220
+ "loss": 0.0537,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 5.97,
1225
+ "learning_rate": 3.760451254150498e-05,
1226
+ "loss": 0.0348,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 6.0,
1231
+ "learning_rate": 3.6804416529983595e-05,
1232
+ "loss": 0.0525,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 6.03,
1237
+ "learning_rate": 3.600432051846222e-05,
1238
+ "loss": 0.0264,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 6.06,
1243
+ "learning_rate": 3.520422450694083e-05,
1244
+ "loss": 0.0216,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 6.09,
1249
+ "learning_rate": 3.4404128495419455e-05,
1250
+ "loss": 0.0232,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 6.12,
1255
+ "learning_rate": 3.360403248389807e-05,
1256
+ "loss": 0.0342,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 6.15,
1261
+ "learning_rate": 3.2803936472376686e-05,
1262
+ "loss": 0.0196,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 6.18,
1267
+ "learning_rate": 3.200384046085531e-05,
1268
+ "loss": 0.0292,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 6.21,
1273
+ "learning_rate": 3.1203744449333924e-05,
1274
+ "loss": 0.02,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 6.24,
1279
+ "learning_rate": 3.0403648437812536e-05,
1280
+ "loss": 0.0243,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 6.26,
1285
+ "learning_rate": 2.9603552426291158e-05,
1286
+ "loss": 0.0223,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 6.29,
1291
+ "learning_rate": 2.8803456414769773e-05,
1292
+ "loss": 0.017,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 6.32,
1297
+ "learning_rate": 2.8003360403248392e-05,
1298
+ "loss": 0.0201,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 6.35,
1303
+ "learning_rate": 2.7203264391727008e-05,
1304
+ "loss": 0.0368,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 6.38,
1309
+ "learning_rate": 2.640316838020563e-05,
1310
+ "loss": 0.0228,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 6.41,
1315
+ "learning_rate": 2.5603072368684245e-05,
1316
+ "loss": 0.0241,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 6.44,
1321
+ "learning_rate": 2.480297635716286e-05,
1322
+ "loss": 0.025,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 6.47,
1327
+ "learning_rate": 2.400288034564148e-05,
1328
+ "loss": 0.0261,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 6.5,
1333
+ "learning_rate": 2.3202784334120095e-05,
1334
+ "loss": 0.026,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 6.53,
1339
+ "learning_rate": 2.2402688322598714e-05,
1340
+ "loss": 0.0242,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 6.56,
1345
+ "learning_rate": 2.160259231107733e-05,
1346
+ "loss": 0.029,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 6.59,
1351
+ "learning_rate": 2.0802496299555948e-05,
1352
+ "loss": 0.0305,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 6.62,
1357
+ "learning_rate": 2.0002400288034563e-05,
1358
+ "loss": 0.0263,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 6.65,
1363
+ "learning_rate": 1.9202304276513182e-05,
1364
+ "loss": 0.021,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 6.68,
1369
+ "learning_rate": 1.8402208264991798e-05,
1370
+ "loss": 0.0295,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 6.71,
1375
+ "learning_rate": 1.7602112253470417e-05,
1376
+ "loss": 0.0276,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 6.74,
1381
+ "learning_rate": 1.6802016241949035e-05,
1382
+ "loss": 0.023,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 6.76,
1387
+ "learning_rate": 1.6001920230427654e-05,
1388
+ "loss": 0.0251,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 6.79,
1393
+ "learning_rate": 1.5201824218906268e-05,
1394
+ "loss": 0.0415,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 6.82,
1399
+ "learning_rate": 1.4401728207384887e-05,
1400
+ "loss": 0.0292,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 6.85,
1405
+ "learning_rate": 1.3601632195863504e-05,
1406
+ "loss": 0.0268,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 6.88,
1411
+ "learning_rate": 1.2801536184342123e-05,
1412
+ "loss": 0.0265,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 6.91,
1417
+ "learning_rate": 1.200144017282074e-05,
1418
+ "loss": 0.0208,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 6.94,
1423
+ "learning_rate": 1.1201344161299357e-05,
1424
+ "loss": 0.0231,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 6.97,
1429
+ "learning_rate": 1.0401248149777974e-05,
1430
+ "loss": 0.022,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 7.0,
1435
+ "learning_rate": 9.601152138256591e-06,
1436
+ "loss": 0.0242,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 7.03,
1441
+ "learning_rate": 8.801056126735208e-06,
1442
+ "loss": 0.0155,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 7.06,
1447
+ "learning_rate": 8.000960115213827e-06,
1448
+ "loss": 0.0183,
1449
+ "step": 240
1450
+ }
1451
+ ],
1452
+ "logging_steps": 1,
1453
+ "max_steps": 250,
1454
+ "num_input_tokens_seen": 0,
1455
+ "num_train_epochs": 8,
1456
+ "save_steps": 20,
1457
+ "total_flos": 1.5323280428875776e+16,
1458
+ "train_batch_size": 1,
1459
+ "trial_name": null,
1460
+ "trial_params": null
1461
+ }