gabrielaltay commited on
Commit
168eb16
·
verified ·
1 Parent(s): ea07915

Training in progress, step 1011, checkpoint

Browse files
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PhiForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "embd_pdrop": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu_new",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "phi",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "num_key_value_heads": 12,
19
+ "partial_rotary_factor": 0.5,
20
+ "qk_layernorm": false,
21
+ "resid_pdrop": 0.0,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.39.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 51200
29
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.39.0.dev0"
6
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c450a6b90a273d4970bdc4c476950a93b7364fbc9c613bee94fa07c87daf77d
3
+ size 654946216
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b590524aa0d0fd4db033b20eddb51e9d4d33042cb8b65f25ca0dc20be36fc453
3
+ size 1310000698
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8737607d4827ca20f570457cff0b478870d9ecd52f64f38c7add083d30874001
3
+ size 14512
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a43eb6b0542dcac8ca938e059f90a276bd49523d304391423a800d90bb479ec
3
+ size 14512
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca7a75920b8ac3def8a4b2f7af8febd1b57aaf0fb047f07a76730c988c0f5e5
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "tokenizer_class": "CodeGenTokenizer",
322
+ "unk_token": "<|endoftext|>"
323
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.10002968239833779,
5
+ "eval_steps": 500,
6
+ "global_step": 1011,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 3.023737668991089,
14
+ "learning_rate": 4.998021173444148e-05,
15
+ "loss": 10.2295,
16
+ "step": 4
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 2.7276954650878906,
21
+ "learning_rate": 4.9960423468882955e-05,
22
+ "loss": 9.2429,
23
+ "step": 8
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 2.202863931655884,
28
+ "learning_rate": 4.9940635203324435e-05,
29
+ "loss": 8.8335,
30
+ "step": 12
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 2.1424026489257812,
35
+ "learning_rate": 4.992084693776591e-05,
36
+ "loss": 8.5825,
37
+ "step": 16
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "grad_norm": 2.1057238578796387,
42
+ "learning_rate": 4.990105867220739e-05,
43
+ "loss": 8.2023,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "grad_norm": 2.0647401809692383,
49
+ "learning_rate": 4.988127040664886e-05,
50
+ "loss": 7.7905,
51
+ "step": 24
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "grad_norm": 1.845037817955017,
56
+ "learning_rate": 4.986148214109034e-05,
57
+ "loss": 7.5639,
58
+ "step": 28
59
+ },
60
+ {
61
+ "epoch": 0.0,
62
+ "grad_norm": 1.766366958618164,
63
+ "learning_rate": 4.984169387553181e-05,
64
+ "loss": 7.3338,
65
+ "step": 32
66
+ },
67
+ {
68
+ "epoch": 0.0,
69
+ "grad_norm": 1.7267919778823853,
70
+ "learning_rate": 4.982190560997329e-05,
71
+ "loss": 7.3396,
72
+ "step": 36
73
+ },
74
+ {
75
+ "epoch": 0.0,
76
+ "grad_norm": 1.3584438562393188,
77
+ "learning_rate": 4.9802117344414766e-05,
78
+ "loss": 7.2269,
79
+ "step": 40
80
+ },
81
+ {
82
+ "epoch": 0.0,
83
+ "grad_norm": 1.5067508220672607,
84
+ "learning_rate": 4.978232907885624e-05,
85
+ "loss": 6.8696,
86
+ "step": 44
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "grad_norm": 1.3194962739944458,
91
+ "learning_rate": 4.976254081329771e-05,
92
+ "loss": 6.7392,
93
+ "step": 48
94
+ },
95
+ {
96
+ "epoch": 0.01,
97
+ "grad_norm": 1.4466848373413086,
98
+ "learning_rate": 4.974275254773919e-05,
99
+ "loss": 6.5025,
100
+ "step": 52
101
+ },
102
+ {
103
+ "epoch": 0.01,
104
+ "grad_norm": 1.3488733768463135,
105
+ "learning_rate": 4.9722964282180664e-05,
106
+ "loss": 6.4044,
107
+ "step": 56
108
+ },
109
+ {
110
+ "epoch": 0.01,
111
+ "grad_norm": 1.301389217376709,
112
+ "learning_rate": 4.9703176016622144e-05,
113
+ "loss": 6.2985,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.01,
118
+ "grad_norm": 1.354225754737854,
119
+ "learning_rate": 4.9683387751063624e-05,
120
+ "loss": 6.1545,
121
+ "step": 64
122
+ },
123
+ {
124
+ "epoch": 0.01,
125
+ "grad_norm": 1.1548670530319214,
126
+ "learning_rate": 4.9663599485505096e-05,
127
+ "loss": 6.1522,
128
+ "step": 68
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "grad_norm": 1.2819015979766846,
133
+ "learning_rate": 4.9643811219946576e-05,
134
+ "loss": 5.9876,
135
+ "step": 72
136
+ },
137
+ {
138
+ "epoch": 0.01,
139
+ "grad_norm": 0.9923768639564514,
140
+ "learning_rate": 4.962402295438805e-05,
141
+ "loss": 5.8414,
142
+ "step": 76
143
+ },
144
+ {
145
+ "epoch": 0.01,
146
+ "grad_norm": 1.005074381828308,
147
+ "learning_rate": 4.960423468882953e-05,
148
+ "loss": 5.7825,
149
+ "step": 80
150
+ },
151
+ {
152
+ "epoch": 0.01,
153
+ "grad_norm": 0.9730919599533081,
154
+ "learning_rate": 4.9584446423271e-05,
155
+ "loss": 5.675,
156
+ "step": 84
157
+ },
158
+ {
159
+ "epoch": 0.01,
160
+ "grad_norm": 1.032512903213501,
161
+ "learning_rate": 4.956465815771248e-05,
162
+ "loss": 5.644,
163
+ "step": 88
164
+ },
165
+ {
166
+ "epoch": 0.01,
167
+ "grad_norm": 1.2836546897888184,
168
+ "learning_rate": 4.9544869892153954e-05,
169
+ "loss": 5.7789,
170
+ "step": 92
171
+ },
172
+ {
173
+ "epoch": 0.01,
174
+ "grad_norm": 0.9425686001777649,
175
+ "learning_rate": 4.9525081626595434e-05,
176
+ "loss": 5.429,
177
+ "step": 96
178
+ },
179
+ {
180
+ "epoch": 0.01,
181
+ "grad_norm": 0.8604844212532043,
182
+ "learning_rate": 4.950529336103691e-05,
183
+ "loss": 5.4202,
184
+ "step": 100
185
+ },
186
+ {
187
+ "epoch": 0.01,
188
+ "grad_norm": 0.8457801342010498,
189
+ "learning_rate": 4.948550509547839e-05,
190
+ "loss": 5.2959,
191
+ "step": 104
192
+ },
193
+ {
194
+ "epoch": 0.01,
195
+ "grad_norm": 0.9246242046356201,
196
+ "learning_rate": 4.946571682991986e-05,
197
+ "loss": 5.4305,
198
+ "step": 108
199
+ },
200
+ {
201
+ "epoch": 0.01,
202
+ "grad_norm": 0.9483153223991394,
203
+ "learning_rate": 4.944592856436134e-05,
204
+ "loss": 5.382,
205
+ "step": 112
206
+ },
207
+ {
208
+ "epoch": 0.01,
209
+ "grad_norm": 0.8151757717132568,
210
+ "learning_rate": 4.942614029880281e-05,
211
+ "loss": 5.2487,
212
+ "step": 116
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "grad_norm": 0.8092381954193115,
217
+ "learning_rate": 4.940635203324429e-05,
218
+ "loss": 5.4251,
219
+ "step": 120
220
+ },
221
+ {
222
+ "epoch": 0.01,
223
+ "grad_norm": 1.0206758975982666,
224
+ "learning_rate": 4.9386563767685765e-05,
225
+ "loss": 5.245,
226
+ "step": 124
227
+ },
228
+ {
229
+ "epoch": 0.01,
230
+ "grad_norm": 0.9263086318969727,
231
+ "learning_rate": 4.936677550212724e-05,
232
+ "loss": 5.3408,
233
+ "step": 128
234
+ },
235
+ {
236
+ "epoch": 0.01,
237
+ "grad_norm": 0.8204173445701599,
238
+ "learning_rate": 4.934698723656872e-05,
239
+ "loss": 5.3163,
240
+ "step": 132
241
+ },
242
+ {
243
+ "epoch": 0.01,
244
+ "grad_norm": 0.817661702632904,
245
+ "learning_rate": 4.932719897101019e-05,
246
+ "loss": 5.2058,
247
+ "step": 136
248
+ },
249
+ {
250
+ "epoch": 0.01,
251
+ "grad_norm": 0.8175525069236755,
252
+ "learning_rate": 4.930741070545167e-05,
253
+ "loss": 5.0683,
254
+ "step": 140
255
+ },
256
+ {
257
+ "epoch": 0.01,
258
+ "grad_norm": 0.8956682682037354,
259
+ "learning_rate": 4.928762243989314e-05,
260
+ "loss": 5.285,
261
+ "step": 144
262
+ },
263
+ {
264
+ "epoch": 0.01,
265
+ "grad_norm": 1.1034317016601562,
266
+ "learning_rate": 4.926783417433462e-05,
267
+ "loss": 5.2186,
268
+ "step": 148
269
+ },
270
+ {
271
+ "epoch": 0.02,
272
+ "grad_norm": 0.8372359275817871,
273
+ "learning_rate": 4.9248045908776096e-05,
274
+ "loss": 5.0079,
275
+ "step": 152
276
+ },
277
+ {
278
+ "epoch": 0.02,
279
+ "grad_norm": 0.8574570417404175,
280
+ "learning_rate": 4.9228257643217576e-05,
281
+ "loss": 5.1058,
282
+ "step": 156
283
+ },
284
+ {
285
+ "epoch": 0.02,
286
+ "grad_norm": 1.0270808935165405,
287
+ "learning_rate": 4.920846937765905e-05,
288
+ "loss": 5.3269,
289
+ "step": 160
290
+ },
291
+ {
292
+ "epoch": 0.02,
293
+ "grad_norm": 0.8500723242759705,
294
+ "learning_rate": 4.918868111210053e-05,
295
+ "loss": 5.1533,
296
+ "step": 164
297
+ },
298
+ {
299
+ "epoch": 0.02,
300
+ "grad_norm": 0.8077535033226013,
301
+ "learning_rate": 4.9168892846542e-05,
302
+ "loss": 4.9847,
303
+ "step": 168
304
+ },
305
+ {
306
+ "epoch": 0.02,
307
+ "grad_norm": 0.9095591902732849,
308
+ "learning_rate": 4.914910458098348e-05,
309
+ "loss": 4.8715,
310
+ "step": 172
311
+ },
312
+ {
313
+ "epoch": 0.02,
314
+ "grad_norm": 1.0022218227386475,
315
+ "learning_rate": 4.9129316315424954e-05,
316
+ "loss": 4.9394,
317
+ "step": 176
318
+ },
319
+ {
320
+ "epoch": 0.02,
321
+ "grad_norm": 1.0106725692749023,
322
+ "learning_rate": 4.9109528049866433e-05,
323
+ "loss": 5.1306,
324
+ "step": 180
325
+ },
326
+ {
327
+ "epoch": 0.02,
328
+ "grad_norm": 0.980566143989563,
329
+ "learning_rate": 4.9089739784307906e-05,
330
+ "loss": 5.0595,
331
+ "step": 184
332
+ },
333
+ {
334
+ "epoch": 0.02,
335
+ "grad_norm": 1.0247553586959839,
336
+ "learning_rate": 4.9069951518749386e-05,
337
+ "loss": 5.0103,
338
+ "step": 188
339
+ },
340
+ {
341
+ "epoch": 0.02,
342
+ "grad_norm": 0.925584077835083,
343
+ "learning_rate": 4.905016325319086e-05,
344
+ "loss": 4.7923,
345
+ "step": 192
346
+ },
347
+ {
348
+ "epoch": 0.02,
349
+ "grad_norm": 0.9778655171394348,
350
+ "learning_rate": 4.903037498763234e-05,
351
+ "loss": 4.8465,
352
+ "step": 196
353
+ },
354
+ {
355
+ "epoch": 0.02,
356
+ "grad_norm": 0.8761100172996521,
357
+ "learning_rate": 4.901058672207381e-05,
358
+ "loss": 4.856,
359
+ "step": 200
360
+ },
361
+ {
362
+ "epoch": 0.02,
363
+ "grad_norm": 0.8272585272789001,
364
+ "learning_rate": 4.899079845651529e-05,
365
+ "loss": 4.8365,
366
+ "step": 204
367
+ },
368
+ {
369
+ "epoch": 0.02,
370
+ "grad_norm": 0.8929518461227417,
371
+ "learning_rate": 4.8971010190956764e-05,
372
+ "loss": 4.7708,
373
+ "step": 208
374
+ },
375
+ {
376
+ "epoch": 0.02,
377
+ "grad_norm": 1.0088162422180176,
378
+ "learning_rate": 4.895122192539824e-05,
379
+ "loss": 4.8667,
380
+ "step": 212
381
+ },
382
+ {
383
+ "epoch": 0.02,
384
+ "grad_norm": 1.0307660102844238,
385
+ "learning_rate": 4.893143365983972e-05,
386
+ "loss": 4.9297,
387
+ "step": 216
388
+ },
389
+ {
390
+ "epoch": 0.02,
391
+ "grad_norm": 0.8324564099311829,
392
+ "learning_rate": 4.891164539428119e-05,
393
+ "loss": 4.6895,
394
+ "step": 220
395
+ },
396
+ {
397
+ "epoch": 0.02,
398
+ "grad_norm": 0.9149929285049438,
399
+ "learning_rate": 4.889185712872267e-05,
400
+ "loss": 5.0596,
401
+ "step": 224
402
+ },
403
+ {
404
+ "epoch": 0.02,
405
+ "grad_norm": 0.9188018441200256,
406
+ "learning_rate": 4.887206886316414e-05,
407
+ "loss": 4.7217,
408
+ "step": 228
409
+ },
410
+ {
411
+ "epoch": 0.02,
412
+ "grad_norm": 0.8771291971206665,
413
+ "learning_rate": 4.885228059760562e-05,
414
+ "loss": 4.5893,
415
+ "step": 232
416
+ },
417
+ {
418
+ "epoch": 0.02,
419
+ "grad_norm": 0.9374723434448242,
420
+ "learning_rate": 4.8832492332047095e-05,
421
+ "loss": 4.7205,
422
+ "step": 236
423
+ },
424
+ {
425
+ "epoch": 0.02,
426
+ "grad_norm": 0.9590020179748535,
427
+ "learning_rate": 4.8812704066488575e-05,
428
+ "loss": 4.6909,
429
+ "step": 240
430
+ },
431
+ {
432
+ "epoch": 0.02,
433
+ "grad_norm": 0.8914527893066406,
434
+ "learning_rate": 4.879291580093005e-05,
435
+ "loss": 4.7799,
436
+ "step": 244
437
+ },
438
+ {
439
+ "epoch": 0.02,
440
+ "grad_norm": 0.96151202917099,
441
+ "learning_rate": 4.877312753537153e-05,
442
+ "loss": 4.6818,
443
+ "step": 248
444
+ },
445
+ {
446
+ "epoch": 0.02,
447
+ "grad_norm": 0.9983839988708496,
448
+ "learning_rate": 4.8753339269813e-05,
449
+ "loss": 4.9377,
450
+ "step": 252
451
+ },
452
+ {
453
+ "epoch": 0.03,
454
+ "grad_norm": 1.3818860054016113,
455
+ "learning_rate": 4.873355100425448e-05,
456
+ "loss": 4.8015,
457
+ "step": 256
458
+ },
459
+ {
460
+ "epoch": 0.03,
461
+ "grad_norm": 0.8486915826797485,
462
+ "learning_rate": 4.871376273869595e-05,
463
+ "loss": 4.6542,
464
+ "step": 260
465
+ },
466
+ {
467
+ "epoch": 0.03,
468
+ "grad_norm": 0.9783093333244324,
469
+ "learning_rate": 4.869397447313743e-05,
470
+ "loss": 4.635,
471
+ "step": 264
472
+ },
473
+ {
474
+ "epoch": 0.03,
475
+ "grad_norm": 0.9911454916000366,
476
+ "learning_rate": 4.8674186207578906e-05,
477
+ "loss": 4.7617,
478
+ "step": 268
479
+ },
480
+ {
481
+ "epoch": 0.03,
482
+ "grad_norm": 0.8163164258003235,
483
+ "learning_rate": 4.8654397942020385e-05,
484
+ "loss": 4.6394,
485
+ "step": 272
486
+ },
487
+ {
488
+ "epoch": 0.03,
489
+ "grad_norm": 0.9522330164909363,
490
+ "learning_rate": 4.8634609676461865e-05,
491
+ "loss": 4.661,
492
+ "step": 276
493
+ },
494
+ {
495
+ "epoch": 0.03,
496
+ "grad_norm": 1.0596697330474854,
497
+ "learning_rate": 4.861482141090334e-05,
498
+ "loss": 4.5832,
499
+ "step": 280
500
+ },
501
+ {
502
+ "epoch": 0.03,
503
+ "grad_norm": 0.9185882806777954,
504
+ "learning_rate": 4.859503314534482e-05,
505
+ "loss": 4.5482,
506
+ "step": 284
507
+ },
508
+ {
509
+ "epoch": 0.03,
510
+ "grad_norm": 0.980002760887146,
511
+ "learning_rate": 4.857524487978629e-05,
512
+ "loss": 4.6268,
513
+ "step": 288
514
+ },
515
+ {
516
+ "epoch": 0.03,
517
+ "grad_norm": 0.7909073829650879,
518
+ "learning_rate": 4.855545661422777e-05,
519
+ "loss": 4.735,
520
+ "step": 292
521
+ },
522
+ {
523
+ "epoch": 0.03,
524
+ "grad_norm": 0.9752382636070251,
525
+ "learning_rate": 4.853566834866924e-05,
526
+ "loss": 4.6384,
527
+ "step": 296
528
+ },
529
+ {
530
+ "epoch": 0.03,
531
+ "grad_norm": 1.0073622465133667,
532
+ "learning_rate": 4.8515880083110716e-05,
533
+ "loss": 4.5566,
534
+ "step": 300
535
+ },
536
+ {
537
+ "epoch": 0.03,
538
+ "grad_norm": 1.1823135614395142,
539
+ "learning_rate": 4.849609181755219e-05,
540
+ "loss": 4.6323,
541
+ "step": 304
542
+ },
543
+ {
544
+ "epoch": 0.03,
545
+ "grad_norm": 0.8075012564659119,
546
+ "learning_rate": 4.847630355199367e-05,
547
+ "loss": 4.4955,
548
+ "step": 308
549
+ },
550
+ {
551
+ "epoch": 0.03,
552
+ "grad_norm": 0.9888399839401245,
553
+ "learning_rate": 4.845651528643514e-05,
554
+ "loss": 4.5405,
555
+ "step": 312
556
+ },
557
+ {
558
+ "epoch": 0.03,
559
+ "grad_norm": 0.9254989624023438,
560
+ "learning_rate": 4.843672702087662e-05,
561
+ "loss": 4.4871,
562
+ "step": 316
563
+ },
564
+ {
565
+ "epoch": 0.03,
566
+ "grad_norm": 1.068520426750183,
567
+ "learning_rate": 4.8416938755318095e-05,
568
+ "loss": 4.7617,
569
+ "step": 320
570
+ },
571
+ {
572
+ "epoch": 0.03,
573
+ "grad_norm": 0.8666436672210693,
574
+ "learning_rate": 4.8397150489759574e-05,
575
+ "loss": 4.6256,
576
+ "step": 324
577
+ },
578
+ {
579
+ "epoch": 0.03,
580
+ "grad_norm": 0.9162269830703735,
581
+ "learning_rate": 4.837736222420105e-05,
582
+ "loss": 4.3914,
583
+ "step": 328
584
+ },
585
+ {
586
+ "epoch": 0.03,
587
+ "grad_norm": 0.8688908219337463,
588
+ "learning_rate": 4.835757395864253e-05,
589
+ "loss": 4.469,
590
+ "step": 332
591
+ },
592
+ {
593
+ "epoch": 0.03,
594
+ "grad_norm": 0.9131215214729309,
595
+ "learning_rate": 4.8337785693084007e-05,
596
+ "loss": 4.5437,
597
+ "step": 336
598
+ },
599
+ {
600
+ "epoch": 0.03,
601
+ "grad_norm": 0.847606360912323,
602
+ "learning_rate": 4.831799742752548e-05,
603
+ "loss": 4.6195,
604
+ "step": 340
605
+ },
606
+ {
607
+ "epoch": 0.03,
608
+ "grad_norm": 0.9658231735229492,
609
+ "learning_rate": 4.829820916196696e-05,
610
+ "loss": 4.5982,
611
+ "step": 344
612
+ },
613
+ {
614
+ "epoch": 0.03,
615
+ "grad_norm": 0.8523685336112976,
616
+ "learning_rate": 4.827842089640843e-05,
617
+ "loss": 4.42,
618
+ "step": 348
619
+ },
620
+ {
621
+ "epoch": 0.03,
622
+ "grad_norm": 0.9430307149887085,
623
+ "learning_rate": 4.825863263084991e-05,
624
+ "loss": 4.5254,
625
+ "step": 352
626
+ },
627
+ {
628
+ "epoch": 0.04,
629
+ "grad_norm": 1.079181432723999,
630
+ "learning_rate": 4.8238844365291385e-05,
631
+ "loss": 4.76,
632
+ "step": 356
633
+ },
634
+ {
635
+ "epoch": 0.04,
636
+ "grad_norm": 0.9053409099578857,
637
+ "learning_rate": 4.8219056099732865e-05,
638
+ "loss": 4.3891,
639
+ "step": 360
640
+ },
641
+ {
642
+ "epoch": 0.04,
643
+ "grad_norm": 1.0313445329666138,
644
+ "learning_rate": 4.819926783417434e-05,
645
+ "loss": 4.6794,
646
+ "step": 364
647
+ },
648
+ {
649
+ "epoch": 0.04,
650
+ "grad_norm": 0.9754608273506165,
651
+ "learning_rate": 4.817947956861582e-05,
652
+ "loss": 4.3483,
653
+ "step": 368
654
+ },
655
+ {
656
+ "epoch": 0.04,
657
+ "grad_norm": 0.8928918838500977,
658
+ "learning_rate": 4.815969130305729e-05,
659
+ "loss": 4.3506,
660
+ "step": 372
661
+ },
662
+ {
663
+ "epoch": 0.04,
664
+ "grad_norm": 0.9732823967933655,
665
+ "learning_rate": 4.813990303749877e-05,
666
+ "loss": 4.4418,
667
+ "step": 376
668
+ },
669
+ {
670
+ "epoch": 0.04,
671
+ "grad_norm": 0.9762834906578064,
672
+ "learning_rate": 4.8120114771940236e-05,
673
+ "loss": 4.4823,
674
+ "step": 380
675
+ },
676
+ {
677
+ "epoch": 0.04,
678
+ "grad_norm": 1.0655723810195923,
679
+ "learning_rate": 4.8100326506381716e-05,
680
+ "loss": 4.3974,
681
+ "step": 384
682
+ },
683
+ {
684
+ "epoch": 0.04,
685
+ "grad_norm": 0.9439470767974854,
686
+ "learning_rate": 4.808053824082319e-05,
687
+ "loss": 4.5157,
688
+ "step": 388
689
+ },
690
+ {
691
+ "epoch": 0.04,
692
+ "grad_norm": 0.9962547421455383,
693
+ "learning_rate": 4.806074997526467e-05,
694
+ "loss": 4.3487,
695
+ "step": 392
696
+ },
697
+ {
698
+ "epoch": 0.04,
699
+ "grad_norm": 1.0140503644943237,
700
+ "learning_rate": 4.804096170970615e-05,
701
+ "loss": 4.2984,
702
+ "step": 396
703
+ },
704
+ {
705
+ "epoch": 0.04,
706
+ "grad_norm": 0.9673125147819519,
707
+ "learning_rate": 4.802117344414762e-05,
708
+ "loss": 4.361,
709
+ "step": 400
710
+ },
711
+ {
712
+ "epoch": 0.04,
713
+ "grad_norm": 1.0120090246200562,
714
+ "learning_rate": 4.80013851785891e-05,
715
+ "loss": 4.4019,
716
+ "step": 404
717
+ },
718
+ {
719
+ "epoch": 0.04,
720
+ "grad_norm": 0.902720034122467,
721
+ "learning_rate": 4.7981596913030574e-05,
722
+ "loss": 4.392,
723
+ "step": 408
724
+ },
725
+ {
726
+ "epoch": 0.04,
727
+ "grad_norm": 0.8929727077484131,
728
+ "learning_rate": 4.796180864747205e-05,
729
+ "loss": 4.7008,
730
+ "step": 412
731
+ },
732
+ {
733
+ "epoch": 0.04,
734
+ "grad_norm": 1.045725703239441,
735
+ "learning_rate": 4.7942020381913526e-05,
736
+ "loss": 4.4655,
737
+ "step": 416
738
+ },
739
+ {
740
+ "epoch": 0.04,
741
+ "grad_norm": 0.9211822748184204,
742
+ "learning_rate": 4.7922232116355006e-05,
743
+ "loss": 4.464,
744
+ "step": 420
745
+ },
746
+ {
747
+ "epoch": 0.04,
748
+ "grad_norm": 0.9875116348266602,
749
+ "learning_rate": 4.790244385079648e-05,
750
+ "loss": 4.3493,
751
+ "step": 424
752
+ },
753
+ {
754
+ "epoch": 0.04,
755
+ "grad_norm": 0.9416815042495728,
756
+ "learning_rate": 4.788265558523796e-05,
757
+ "loss": 4.2362,
758
+ "step": 428
759
+ },
760
+ {
761
+ "epoch": 0.04,
762
+ "grad_norm": 0.9395657777786255,
763
+ "learning_rate": 4.786286731967943e-05,
764
+ "loss": 4.3159,
765
+ "step": 432
766
+ },
767
+ {
768
+ "epoch": 0.04,
769
+ "grad_norm": 0.8677350878715515,
770
+ "learning_rate": 4.784307905412091e-05,
771
+ "loss": 4.3343,
772
+ "step": 436
773
+ },
774
+ {
775
+ "epoch": 0.04,
776
+ "grad_norm": 0.9983429908752441,
777
+ "learning_rate": 4.7823290788562384e-05,
778
+ "loss": 4.3666,
779
+ "step": 440
780
+ },
781
+ {
782
+ "epoch": 0.04,
783
+ "grad_norm": 1.076252818107605,
784
+ "learning_rate": 4.7803502523003864e-05,
785
+ "loss": 4.4674,
786
+ "step": 444
787
+ },
788
+ {
789
+ "epoch": 0.04,
790
+ "grad_norm": 0.8906400203704834,
791
+ "learning_rate": 4.778371425744534e-05,
792
+ "loss": 4.3918,
793
+ "step": 448
794
+ },
795
+ {
796
+ "epoch": 0.04,
797
+ "grad_norm": 0.9424994587898254,
798
+ "learning_rate": 4.7763925991886817e-05,
799
+ "loss": 4.3358,
800
+ "step": 452
801
+ },
802
+ {
803
+ "epoch": 0.05,
804
+ "grad_norm": 0.9982520341873169,
805
+ "learning_rate": 4.774413772632829e-05,
806
+ "loss": 4.4196,
807
+ "step": 456
808
+ },
809
+ {
810
+ "epoch": 0.05,
811
+ "grad_norm": 0.9584160447120667,
812
+ "learning_rate": 4.772434946076977e-05,
813
+ "loss": 4.2583,
814
+ "step": 460
815
+ },
816
+ {
817
+ "epoch": 0.05,
818
+ "grad_norm": 0.9916421175003052,
819
+ "learning_rate": 4.770456119521124e-05,
820
+ "loss": 4.4004,
821
+ "step": 464
822
+ },
823
+ {
824
+ "epoch": 0.05,
825
+ "grad_norm": 1.0897949934005737,
826
+ "learning_rate": 4.7684772929652715e-05,
827
+ "loss": 4.3993,
828
+ "step": 468
829
+ },
830
+ {
831
+ "epoch": 0.05,
832
+ "grad_norm": 1.3799035549163818,
833
+ "learning_rate": 4.7664984664094195e-05,
834
+ "loss": 4.3915,
835
+ "step": 472
836
+ },
837
+ {
838
+ "epoch": 0.05,
839
+ "grad_norm": 1.0133105516433716,
840
+ "learning_rate": 4.764519639853567e-05,
841
+ "loss": 4.0608,
842
+ "step": 476
843
+ },
844
+ {
845
+ "epoch": 0.05,
846
+ "grad_norm": 1.1998016834259033,
847
+ "learning_rate": 4.762540813297715e-05,
848
+ "loss": 4.4948,
849
+ "step": 480
850
+ },
851
+ {
852
+ "epoch": 0.05,
853
+ "grad_norm": 1.1928074359893799,
854
+ "learning_rate": 4.760561986741862e-05,
855
+ "loss": 4.1837,
856
+ "step": 484
857
+ },
858
+ {
859
+ "epoch": 0.05,
860
+ "grad_norm": 1.0764780044555664,
861
+ "learning_rate": 4.75858316018601e-05,
862
+ "loss": 4.3355,
863
+ "step": 488
864
+ },
865
+ {
866
+ "epoch": 0.05,
867
+ "grad_norm": 1.0785058736801147,
868
+ "learning_rate": 4.756604333630157e-05,
869
+ "loss": 4.3751,
870
+ "step": 492
871
+ },
872
+ {
873
+ "epoch": 0.05,
874
+ "grad_norm": 1.0299701690673828,
875
+ "learning_rate": 4.754625507074305e-05,
876
+ "loss": 4.2652,
877
+ "step": 496
878
+ },
879
+ {
880
+ "epoch": 0.05,
881
+ "grad_norm": 0.9715741276741028,
882
+ "learning_rate": 4.7526466805184526e-05,
883
+ "loss": 4.2677,
884
+ "step": 500
885
+ },
886
+ {
887
+ "epoch": 0.05,
888
+ "grad_norm": 1.1598002910614014,
889
+ "learning_rate": 4.7506678539626005e-05,
890
+ "loss": 4.2647,
891
+ "step": 504
892
+ },
893
+ {
894
+ "epoch": 0.05,
895
+ "grad_norm": 0.9881719946861267,
896
+ "learning_rate": 4.748689027406748e-05,
897
+ "loss": 4.2163,
898
+ "step": 508
899
+ },
900
+ {
901
+ "epoch": 0.05,
902
+ "grad_norm": 1.0998167991638184,
903
+ "learning_rate": 4.746710200850896e-05,
904
+ "loss": 4.1632,
905
+ "step": 512
906
+ },
907
+ {
908
+ "epoch": 0.05,
909
+ "grad_norm": 1.055464267730713,
910
+ "learning_rate": 4.744731374295043e-05,
911
+ "loss": 4.2287,
912
+ "step": 516
913
+ },
914
+ {
915
+ "epoch": 0.05,
916
+ "grad_norm": 1.1115161180496216,
917
+ "learning_rate": 4.742752547739191e-05,
918
+ "loss": 4.3554,
919
+ "step": 520
920
+ },
921
+ {
922
+ "epoch": 0.05,
923
+ "grad_norm": 0.8956658840179443,
924
+ "learning_rate": 4.7407737211833384e-05,
925
+ "loss": 3.9656,
926
+ "step": 524
927
+ },
928
+ {
929
+ "epoch": 0.05,
930
+ "grad_norm": 1.2546039819717407,
931
+ "learning_rate": 4.738794894627486e-05,
932
+ "loss": 4.2604,
933
+ "step": 528
934
+ },
935
+ {
936
+ "epoch": 0.05,
937
+ "grad_norm": 1.1724745035171509,
938
+ "learning_rate": 4.7368160680716336e-05,
939
+ "loss": 4.291,
940
+ "step": 532
941
+ },
942
+ {
943
+ "epoch": 0.05,
944
+ "grad_norm": 1.068641185760498,
945
+ "learning_rate": 4.7348372415157816e-05,
946
+ "loss": 4.0505,
947
+ "step": 536
948
+ },
949
+ {
950
+ "epoch": 0.05,
951
+ "grad_norm": 1.0498847961425781,
952
+ "learning_rate": 4.732858414959929e-05,
953
+ "loss": 4.2438,
954
+ "step": 540
955
+ },
956
+ {
957
+ "epoch": 0.05,
958
+ "grad_norm": 1.0670949220657349,
959
+ "learning_rate": 4.730879588404077e-05,
960
+ "loss": 4.1264,
961
+ "step": 544
962
+ },
963
+ {
964
+ "epoch": 0.05,
965
+ "grad_norm": 1.076369285583496,
966
+ "learning_rate": 4.728900761848225e-05,
967
+ "loss": 4.2795,
968
+ "step": 548
969
+ },
970
+ {
971
+ "epoch": 0.05,
972
+ "grad_norm": 1.1954712867736816,
973
+ "learning_rate": 4.7269219352923714e-05,
974
+ "loss": 4.2029,
975
+ "step": 552
976
+ },
977
+ {
978
+ "epoch": 0.06,
979
+ "grad_norm": 0.9923123717308044,
980
+ "learning_rate": 4.7249431087365194e-05,
981
+ "loss": 4.2668,
982
+ "step": 556
983
+ },
984
+ {
985
+ "epoch": 0.06,
986
+ "grad_norm": 1.1335583925247192,
987
+ "learning_rate": 4.722964282180667e-05,
988
+ "loss": 3.9782,
989
+ "step": 560
990
+ },
991
+ {
992
+ "epoch": 0.06,
993
+ "grad_norm": 1.0587942600250244,
994
+ "learning_rate": 4.720985455624815e-05,
995
+ "loss": 4.0898,
996
+ "step": 564
997
+ },
998
+ {
999
+ "epoch": 0.06,
1000
+ "grad_norm": 0.9978137016296387,
1001
+ "learning_rate": 4.719006629068962e-05,
1002
+ "loss": 3.9701,
1003
+ "step": 568
1004
+ },
1005
+ {
1006
+ "epoch": 0.06,
1007
+ "grad_norm": 1.0784775018692017,
1008
+ "learning_rate": 4.71702780251311e-05,
1009
+ "loss": 4.0768,
1010
+ "step": 572
1011
+ },
1012
+ {
1013
+ "epoch": 0.06,
1014
+ "grad_norm": 1.1316741704940796,
1015
+ "learning_rate": 4.715048975957257e-05,
1016
+ "loss": 4.1185,
1017
+ "step": 576
1018
+ },
1019
+ {
1020
+ "epoch": 0.06,
1021
+ "grad_norm": 1.1574583053588867,
1022
+ "learning_rate": 4.713070149401405e-05,
1023
+ "loss": 4.1627,
1024
+ "step": 580
1025
+ },
1026
+ {
1027
+ "epoch": 0.06,
1028
+ "grad_norm": 1.4153751134872437,
1029
+ "learning_rate": 4.7110913228455525e-05,
1030
+ "loss": 4.4233,
1031
+ "step": 584
1032
+ },
1033
+ {
1034
+ "epoch": 0.06,
1035
+ "grad_norm": 1.0705913305282593,
1036
+ "learning_rate": 4.7091124962897005e-05,
1037
+ "loss": 4.1492,
1038
+ "step": 588
1039
+ },
1040
+ {
1041
+ "epoch": 0.06,
1042
+ "grad_norm": 1.3845056295394897,
1043
+ "learning_rate": 4.707133669733848e-05,
1044
+ "loss": 4.1557,
1045
+ "step": 592
1046
+ },
1047
+ {
1048
+ "epoch": 0.06,
1049
+ "grad_norm": 0.989825427532196,
1050
+ "learning_rate": 4.705154843177996e-05,
1051
+ "loss": 4.1221,
1052
+ "step": 596
1053
+ },
1054
+ {
1055
+ "epoch": 0.06,
1056
+ "grad_norm": 1.1429495811462402,
1057
+ "learning_rate": 4.703176016622143e-05,
1058
+ "loss": 4.1611,
1059
+ "step": 600
1060
+ },
1061
+ {
1062
+ "epoch": 0.06,
1063
+ "grad_norm": 1.1858593225479126,
1064
+ "learning_rate": 4.701197190066291e-05,
1065
+ "loss": 4.121,
1066
+ "step": 604
1067
+ },
1068
+ {
1069
+ "epoch": 0.06,
1070
+ "grad_norm": 0.9340394735336304,
1071
+ "learning_rate": 4.699218363510439e-05,
1072
+ "loss": 4.0173,
1073
+ "step": 608
1074
+ },
1075
+ {
1076
+ "epoch": 0.06,
1077
+ "grad_norm": 1.0611008405685425,
1078
+ "learning_rate": 4.697239536954586e-05,
1079
+ "loss": 4.0978,
1080
+ "step": 612
1081
+ },
1082
+ {
1083
+ "epoch": 0.06,
1084
+ "grad_norm": 1.1144658327102661,
1085
+ "learning_rate": 4.695260710398734e-05,
1086
+ "loss": 3.9948,
1087
+ "step": 616
1088
+ },
1089
+ {
1090
+ "epoch": 0.06,
1091
+ "grad_norm": 1.0355262756347656,
1092
+ "learning_rate": 4.6932818838428815e-05,
1093
+ "loss": 3.9703,
1094
+ "step": 620
1095
+ },
1096
+ {
1097
+ "epoch": 0.06,
1098
+ "grad_norm": 1.0302252769470215,
1099
+ "learning_rate": 4.6913030572870295e-05,
1100
+ "loss": 4.055,
1101
+ "step": 624
1102
+ },
1103
+ {
1104
+ "epoch": 0.06,
1105
+ "grad_norm": 0.9846487641334534,
1106
+ "learning_rate": 4.689324230731177e-05,
1107
+ "loss": 4.0066,
1108
+ "step": 628
1109
+ },
1110
+ {
1111
+ "epoch": 0.06,
1112
+ "grad_norm": 1.2877755165100098,
1113
+ "learning_rate": 4.687345404175325e-05,
1114
+ "loss": 4.1539,
1115
+ "step": 632
1116
+ },
1117
+ {
1118
+ "epoch": 0.06,
1119
+ "grad_norm": 1.046048641204834,
1120
+ "learning_rate": 4.6853665776194714e-05,
1121
+ "loss": 3.8136,
1122
+ "step": 636
1123
+ },
1124
+ {
1125
+ "epoch": 0.06,
1126
+ "grad_norm": 1.0364129543304443,
1127
+ "learning_rate": 4.6833877510636193e-05,
1128
+ "loss": 4.1889,
1129
+ "step": 640
1130
+ },
1131
+ {
1132
+ "epoch": 0.06,
1133
+ "grad_norm": 1.102586030960083,
1134
+ "learning_rate": 4.6814089245077666e-05,
1135
+ "loss": 3.9993,
1136
+ "step": 644
1137
+ },
1138
+ {
1139
+ "epoch": 0.06,
1140
+ "grad_norm": 1.0004945993423462,
1141
+ "learning_rate": 4.6794300979519146e-05,
1142
+ "loss": 3.9929,
1143
+ "step": 648
1144
+ },
1145
+ {
1146
+ "epoch": 0.06,
1147
+ "grad_norm": 1.0600558519363403,
1148
+ "learning_rate": 4.677451271396062e-05,
1149
+ "loss": 4.0179,
1150
+ "step": 652
1151
+ },
1152
+ {
1153
+ "epoch": 0.06,
1154
+ "grad_norm": 1.0851588249206543,
1155
+ "learning_rate": 4.67547244484021e-05,
1156
+ "loss": 3.9701,
1157
+ "step": 656
1158
+ },
1159
+ {
1160
+ "epoch": 0.07,
1161
+ "grad_norm": 1.2407004833221436,
1162
+ "learning_rate": 4.673493618284357e-05,
1163
+ "loss": 4.1936,
1164
+ "step": 660
1165
+ },
1166
+ {
1167
+ "epoch": 0.07,
1168
+ "grad_norm": 1.4276139736175537,
1169
+ "learning_rate": 4.671514791728505e-05,
1170
+ "loss": 4.0371,
1171
+ "step": 664
1172
+ },
1173
+ {
1174
+ "epoch": 0.07,
1175
+ "grad_norm": 1.1554222106933594,
1176
+ "learning_rate": 4.669535965172653e-05,
1177
+ "loss": 4.1037,
1178
+ "step": 668
1179
+ },
1180
+ {
1181
+ "epoch": 0.07,
1182
+ "grad_norm": 1.062843918800354,
1183
+ "learning_rate": 4.6675571386168004e-05,
1184
+ "loss": 3.8831,
1185
+ "step": 672
1186
+ },
1187
+ {
1188
+ "epoch": 0.07,
1189
+ "grad_norm": 1.2357606887817383,
1190
+ "learning_rate": 4.6655783120609484e-05,
1191
+ "loss": 4.0885,
1192
+ "step": 676
1193
+ },
1194
+ {
1195
+ "epoch": 0.07,
1196
+ "grad_norm": 1.1083883047103882,
1197
+ "learning_rate": 4.663599485505096e-05,
1198
+ "loss": 3.8199,
1199
+ "step": 680
1200
+ },
1201
+ {
1202
+ "epoch": 0.07,
1203
+ "grad_norm": 1.0669097900390625,
1204
+ "learning_rate": 4.6616206589492436e-05,
1205
+ "loss": 4.1267,
1206
+ "step": 684
1207
+ },
1208
+ {
1209
+ "epoch": 0.07,
1210
+ "grad_norm": 1.0153981447219849,
1211
+ "learning_rate": 4.659641832393391e-05,
1212
+ "loss": 3.833,
1213
+ "step": 688
1214
+ },
1215
+ {
1216
+ "epoch": 0.07,
1217
+ "grad_norm": 1.2568185329437256,
1218
+ "learning_rate": 4.657663005837539e-05,
1219
+ "loss": 4.1119,
1220
+ "step": 692
1221
+ },
1222
+ {
1223
+ "epoch": 0.07,
1224
+ "grad_norm": 1.2034963369369507,
1225
+ "learning_rate": 4.655684179281686e-05,
1226
+ "loss": 3.7792,
1227
+ "step": 696
1228
+ },
1229
+ {
1230
+ "epoch": 0.07,
1231
+ "grad_norm": 1.192213773727417,
1232
+ "learning_rate": 4.653705352725834e-05,
1233
+ "loss": 4.0965,
1234
+ "step": 700
1235
+ },
1236
+ {
1237
+ "epoch": 0.07,
1238
+ "grad_norm": 1.1414371728897095,
1239
+ "learning_rate": 4.6517265261699815e-05,
1240
+ "loss": 3.8453,
1241
+ "step": 704
1242
+ },
1243
+ {
1244
+ "epoch": 0.07,
1245
+ "grad_norm": 1.2463369369506836,
1246
+ "learning_rate": 4.6497476996141294e-05,
1247
+ "loss": 3.9088,
1248
+ "step": 708
1249
+ },
1250
+ {
1251
+ "epoch": 0.07,
1252
+ "grad_norm": 1.062708854675293,
1253
+ "learning_rate": 4.647768873058277e-05,
1254
+ "loss": 3.9295,
1255
+ "step": 712
1256
+ },
1257
+ {
1258
+ "epoch": 0.07,
1259
+ "grad_norm": 1.05110764503479,
1260
+ "learning_rate": 4.645790046502425e-05,
1261
+ "loss": 3.9937,
1262
+ "step": 716
1263
+ },
1264
+ {
1265
+ "epoch": 0.07,
1266
+ "grad_norm": 1.0769037008285522,
1267
+ "learning_rate": 4.643811219946571e-05,
1268
+ "loss": 3.9416,
1269
+ "step": 720
1270
+ },
1271
+ {
1272
+ "epoch": 0.07,
1273
+ "grad_norm": 1.1095948219299316,
1274
+ "learning_rate": 4.641832393390719e-05,
1275
+ "loss": 3.7524,
1276
+ "step": 724
1277
+ },
1278
+ {
1279
+ "epoch": 0.07,
1280
+ "grad_norm": 1.1786772012710571,
1281
+ "learning_rate": 4.639853566834867e-05,
1282
+ "loss": 3.7961,
1283
+ "step": 728
1284
+ },
1285
+ {
1286
+ "epoch": 0.07,
1287
+ "grad_norm": 1.1711845397949219,
1288
+ "learning_rate": 4.6378747402790145e-05,
1289
+ "loss": 3.9437,
1290
+ "step": 732
1291
+ },
1292
+ {
1293
+ "epoch": 0.07,
1294
+ "grad_norm": 1.0217204093933105,
1295
+ "learning_rate": 4.6358959137231625e-05,
1296
+ "loss": 3.8099,
1297
+ "step": 736
1298
+ },
1299
+ {
1300
+ "epoch": 0.07,
1301
+ "grad_norm": 1.1621912717819214,
1302
+ "learning_rate": 4.63391708716731e-05,
1303
+ "loss": 3.9684,
1304
+ "step": 740
1305
+ },
1306
+ {
1307
+ "epoch": 0.07,
1308
+ "grad_norm": 1.2898588180541992,
1309
+ "learning_rate": 4.631938260611458e-05,
1310
+ "loss": 3.8558,
1311
+ "step": 744
1312
+ },
1313
+ {
1314
+ "epoch": 0.07,
1315
+ "grad_norm": 1.2988104820251465,
1316
+ "learning_rate": 4.629959434055605e-05,
1317
+ "loss": 3.8503,
1318
+ "step": 748
1319
+ },
1320
+ {
1321
+ "epoch": 0.07,
1322
+ "grad_norm": 1.1195327043533325,
1323
+ "learning_rate": 4.627980607499753e-05,
1324
+ "loss": 3.8956,
1325
+ "step": 752
1326
+ },
1327
+ {
1328
+ "epoch": 0.07,
1329
+ "grad_norm": 1.2289355993270874,
1330
+ "learning_rate": 4.6260017809439003e-05,
1331
+ "loss": 3.6909,
1332
+ "step": 756
1333
+ },
1334
+ {
1335
+ "epoch": 0.08,
1336
+ "grad_norm": 1.2389601469039917,
1337
+ "learning_rate": 4.624022954388048e-05,
1338
+ "loss": 3.9477,
1339
+ "step": 760
1340
+ },
1341
+ {
1342
+ "epoch": 0.08,
1343
+ "grad_norm": 1.2713934183120728,
1344
+ "learning_rate": 4.6220441278321956e-05,
1345
+ "loss": 3.9466,
1346
+ "step": 764
1347
+ },
1348
+ {
1349
+ "epoch": 0.08,
1350
+ "grad_norm": 1.19290292263031,
1351
+ "learning_rate": 4.6200653012763436e-05,
1352
+ "loss": 3.7048,
1353
+ "step": 768
1354
+ },
1355
+ {
1356
+ "epoch": 0.08,
1357
+ "grad_norm": 1.107513666152954,
1358
+ "learning_rate": 4.618086474720491e-05,
1359
+ "loss": 3.8013,
1360
+ "step": 772
1361
+ },
1362
+ {
1363
+ "epoch": 0.08,
1364
+ "grad_norm": 0.9974806904792786,
1365
+ "learning_rate": 4.616107648164639e-05,
1366
+ "loss": 3.7578,
1367
+ "step": 776
1368
+ },
1369
+ {
1370
+ "epoch": 0.08,
1371
+ "grad_norm": 1.180731177330017,
1372
+ "learning_rate": 4.614128821608786e-05,
1373
+ "loss": 3.9304,
1374
+ "step": 780
1375
+ },
1376
+ {
1377
+ "epoch": 0.08,
1378
+ "grad_norm": 1.5762641429901123,
1379
+ "learning_rate": 4.612149995052934e-05,
1380
+ "loss": 3.9271,
1381
+ "step": 784
1382
+ },
1383
+ {
1384
+ "epoch": 0.08,
1385
+ "grad_norm": 1.1390140056610107,
1386
+ "learning_rate": 4.6101711684970814e-05,
1387
+ "loss": 4.0947,
1388
+ "step": 788
1389
+ },
1390
+ {
1391
+ "epoch": 0.08,
1392
+ "grad_norm": 1.2429100275039673,
1393
+ "learning_rate": 4.6081923419412294e-05,
1394
+ "loss": 3.9939,
1395
+ "step": 792
1396
+ },
1397
+ {
1398
+ "epoch": 0.08,
1399
+ "grad_norm": 1.1867088079452515,
1400
+ "learning_rate": 4.606213515385377e-05,
1401
+ "loss": 3.8247,
1402
+ "step": 796
1403
+ },
1404
+ {
1405
+ "epoch": 0.08,
1406
+ "grad_norm": 1.0802291631698608,
1407
+ "learning_rate": 4.6042346888295246e-05,
1408
+ "loss": 3.6472,
1409
+ "step": 800
1410
+ },
1411
+ {
1412
+ "epoch": 0.08,
1413
+ "grad_norm": 1.3064371347427368,
1414
+ "learning_rate": 4.602255862273672e-05,
1415
+ "loss": 3.785,
1416
+ "step": 804
1417
+ },
1418
+ {
1419
+ "epoch": 0.08,
1420
+ "grad_norm": 1.3858779668807983,
1421
+ "learning_rate": 4.600277035717819e-05,
1422
+ "loss": 4.0065,
1423
+ "step": 808
1424
+ },
1425
+ {
1426
+ "epoch": 0.08,
1427
+ "grad_norm": 1.09247887134552,
1428
+ "learning_rate": 4.598298209161967e-05,
1429
+ "loss": 3.8801,
1430
+ "step": 812
1431
+ },
1432
+ {
1433
+ "epoch": 0.08,
1434
+ "grad_norm": 1.1438707113265991,
1435
+ "learning_rate": 4.5963193826061145e-05,
1436
+ "loss": 3.7864,
1437
+ "step": 816
1438
+ },
1439
+ {
1440
+ "epoch": 0.08,
1441
+ "grad_norm": 1.107773780822754,
1442
+ "learning_rate": 4.5943405560502625e-05,
1443
+ "loss": 3.6436,
1444
+ "step": 820
1445
+ },
1446
+ {
1447
+ "epoch": 0.08,
1448
+ "grad_norm": 1.0622732639312744,
1449
+ "learning_rate": 4.59236172949441e-05,
1450
+ "loss": 3.8597,
1451
+ "step": 824
1452
+ },
1453
+ {
1454
+ "epoch": 0.08,
1455
+ "grad_norm": 1.0812435150146484,
1456
+ "learning_rate": 4.590382902938558e-05,
1457
+ "loss": 3.8085,
1458
+ "step": 828
1459
+ },
1460
+ {
1461
+ "epoch": 0.08,
1462
+ "grad_norm": 1.1576310396194458,
1463
+ "learning_rate": 4.588404076382705e-05,
1464
+ "loss": 3.6459,
1465
+ "step": 832
1466
+ },
1467
+ {
1468
+ "epoch": 0.08,
1469
+ "grad_norm": 1.1088974475860596,
1470
+ "learning_rate": 4.586425249826853e-05,
1471
+ "loss": 3.8514,
1472
+ "step": 836
1473
+ },
1474
+ {
1475
+ "epoch": 0.08,
1476
+ "grad_norm": 1.1565968990325928,
1477
+ "learning_rate": 4.584446423271e-05,
1478
+ "loss": 3.7429,
1479
+ "step": 840
1480
+ },
1481
+ {
1482
+ "epoch": 0.08,
1483
+ "grad_norm": 1.226541519165039,
1484
+ "learning_rate": 4.582467596715148e-05,
1485
+ "loss": 3.9345,
1486
+ "step": 844
1487
+ },
1488
+ {
1489
+ "epoch": 0.08,
1490
+ "grad_norm": 1.3901216983795166,
1491
+ "learning_rate": 4.5804887701592955e-05,
1492
+ "loss": 4.0038,
1493
+ "step": 848
1494
+ },
1495
+ {
1496
+ "epoch": 0.08,
1497
+ "grad_norm": 1.0757673978805542,
1498
+ "learning_rate": 4.5785099436034435e-05,
1499
+ "loss": 3.6689,
1500
+ "step": 852
1501
+ },
1502
+ {
1503
+ "epoch": 0.08,
1504
+ "grad_norm": 1.0806201696395874,
1505
+ "learning_rate": 4.576531117047591e-05,
1506
+ "loss": 3.8034,
1507
+ "step": 856
1508
+ },
1509
+ {
1510
+ "epoch": 0.09,
1511
+ "grad_norm": 1.0815987586975098,
1512
+ "learning_rate": 4.574552290491739e-05,
1513
+ "loss": 3.5688,
1514
+ "step": 860
1515
+ },
1516
+ {
1517
+ "epoch": 0.09,
1518
+ "grad_norm": 1.2539079189300537,
1519
+ "learning_rate": 4.572573463935886e-05,
1520
+ "loss": 3.7314,
1521
+ "step": 864
1522
+ },
1523
+ {
1524
+ "epoch": 0.09,
1525
+ "grad_norm": 1.2489246129989624,
1526
+ "learning_rate": 4.570594637380034e-05,
1527
+ "loss": 3.7358,
1528
+ "step": 868
1529
+ },
1530
+ {
1531
+ "epoch": 0.09,
1532
+ "grad_norm": 1.188781976699829,
1533
+ "learning_rate": 4.568615810824181e-05,
1534
+ "loss": 3.8216,
1535
+ "step": 872
1536
+ },
1537
+ {
1538
+ "epoch": 0.09,
1539
+ "grad_norm": 1.1977195739746094,
1540
+ "learning_rate": 4.566636984268329e-05,
1541
+ "loss": 3.7418,
1542
+ "step": 876
1543
+ },
1544
+ {
1545
+ "epoch": 0.09,
1546
+ "grad_norm": 1.3144996166229248,
1547
+ "learning_rate": 4.564658157712477e-05,
1548
+ "loss": 3.8569,
1549
+ "step": 880
1550
+ },
1551
+ {
1552
+ "epoch": 0.09,
1553
+ "grad_norm": 1.194718360900879,
1554
+ "learning_rate": 4.5626793311566246e-05,
1555
+ "loss": 3.9339,
1556
+ "step": 884
1557
+ },
1558
+ {
1559
+ "epoch": 0.09,
1560
+ "grad_norm": 1.1180779933929443,
1561
+ "learning_rate": 4.560700504600772e-05,
1562
+ "loss": 3.7593,
1563
+ "step": 888
1564
+ },
1565
+ {
1566
+ "epoch": 0.09,
1567
+ "grad_norm": 1.2359132766723633,
1568
+ "learning_rate": 4.558721678044919e-05,
1569
+ "loss": 3.7554,
1570
+ "step": 892
1571
+ },
1572
+ {
1573
+ "epoch": 0.09,
1574
+ "grad_norm": 1.456741213798523,
1575
+ "learning_rate": 4.556742851489067e-05,
1576
+ "loss": 3.8741,
1577
+ "step": 896
1578
+ },
1579
+ {
1580
+ "epoch": 0.09,
1581
+ "grad_norm": 1.21878981590271,
1582
+ "learning_rate": 4.5547640249332144e-05,
1583
+ "loss": 3.7214,
1584
+ "step": 900
1585
+ },
1586
+ {
1587
+ "epoch": 0.09,
1588
+ "grad_norm": 1.2724573612213135,
1589
+ "learning_rate": 4.5527851983773624e-05,
1590
+ "loss": 3.7083,
1591
+ "step": 904
1592
+ },
1593
+ {
1594
+ "epoch": 0.09,
1595
+ "grad_norm": 1.3674492835998535,
1596
+ "learning_rate": 4.55080637182151e-05,
1597
+ "loss": 3.7782,
1598
+ "step": 908
1599
+ },
1600
+ {
1601
+ "epoch": 0.09,
1602
+ "grad_norm": 1.1962213516235352,
1603
+ "learning_rate": 4.5488275452656577e-05,
1604
+ "loss": 3.8053,
1605
+ "step": 912
1606
+ },
1607
+ {
1608
+ "epoch": 0.09,
1609
+ "grad_norm": 1.204624056816101,
1610
+ "learning_rate": 4.546848718709805e-05,
1611
+ "loss": 3.8807,
1612
+ "step": 916
1613
+ },
1614
+ {
1615
+ "epoch": 0.09,
1616
+ "grad_norm": 1.162916660308838,
1617
+ "learning_rate": 4.544869892153953e-05,
1618
+ "loss": 3.62,
1619
+ "step": 920
1620
+ },
1621
+ {
1622
+ "epoch": 0.09,
1623
+ "grad_norm": 1.1495506763458252,
1624
+ "learning_rate": 4.5428910655981e-05,
1625
+ "loss": 3.6001,
1626
+ "step": 924
1627
+ },
1628
+ {
1629
+ "epoch": 0.09,
1630
+ "grad_norm": 1.1593899726867676,
1631
+ "learning_rate": 4.540912239042248e-05,
1632
+ "loss": 4.0318,
1633
+ "step": 928
1634
+ },
1635
+ {
1636
+ "epoch": 0.09,
1637
+ "grad_norm": 1.1468162536621094,
1638
+ "learning_rate": 4.5389334124863955e-05,
1639
+ "loss": 3.6793,
1640
+ "step": 932
1641
+ },
1642
+ {
1643
+ "epoch": 0.09,
1644
+ "grad_norm": 1.0815014839172363,
1645
+ "learning_rate": 4.5369545859305434e-05,
1646
+ "loss": 3.8516,
1647
+ "step": 936
1648
+ },
1649
+ {
1650
+ "epoch": 0.09,
1651
+ "grad_norm": 1.1018073558807373,
1652
+ "learning_rate": 4.5349757593746914e-05,
1653
+ "loss": 3.7732,
1654
+ "step": 940
1655
+ },
1656
+ {
1657
+ "epoch": 0.09,
1658
+ "grad_norm": 1.1128356456756592,
1659
+ "learning_rate": 4.532996932818839e-05,
1660
+ "loss": 3.5784,
1661
+ "step": 944
1662
+ },
1663
+ {
1664
+ "epoch": 0.09,
1665
+ "grad_norm": 1.449112057685852,
1666
+ "learning_rate": 4.531018106262987e-05,
1667
+ "loss": 3.8318,
1668
+ "step": 948
1669
+ },
1670
+ {
1671
+ "epoch": 0.09,
1672
+ "grad_norm": 1.1925861835479736,
1673
+ "learning_rate": 4.529039279707134e-05,
1674
+ "loss": 3.7108,
1675
+ "step": 952
1676
+ },
1677
+ {
1678
+ "epoch": 0.09,
1679
+ "grad_norm": 1.1462700366973877,
1680
+ "learning_rate": 4.527060453151282e-05,
1681
+ "loss": 3.6801,
1682
+ "step": 956
1683
+ },
1684
+ {
1685
+ "epoch": 0.09,
1686
+ "grad_norm": 1.218001127243042,
1687
+ "learning_rate": 4.525081626595429e-05,
1688
+ "loss": 3.7581,
1689
+ "step": 960
1690
+ },
1691
+ {
1692
+ "epoch": 0.1,
1693
+ "grad_norm": 1.09965980052948,
1694
+ "learning_rate": 4.523102800039577e-05,
1695
+ "loss": 3.661,
1696
+ "step": 964
1697
+ },
1698
+ {
1699
+ "epoch": 0.1,
1700
+ "grad_norm": 1.1705689430236816,
1701
+ "learning_rate": 4.5211239734837245e-05,
1702
+ "loss": 3.8608,
1703
+ "step": 968
1704
+ },
1705
+ {
1706
+ "epoch": 0.1,
1707
+ "grad_norm": 1.2540526390075684,
1708
+ "learning_rate": 4.519145146927872e-05,
1709
+ "loss": 3.5236,
1710
+ "step": 972
1711
+ },
1712
+ {
1713
+ "epoch": 0.1,
1714
+ "grad_norm": 1.1072841882705688,
1715
+ "learning_rate": 4.517166320372019e-05,
1716
+ "loss": 3.5754,
1717
+ "step": 976
1718
+ },
1719
+ {
1720
+ "epoch": 0.1,
1721
+ "grad_norm": 1.0101158618927002,
1722
+ "learning_rate": 4.515187493816167e-05,
1723
+ "loss": 3.7373,
1724
+ "step": 980
1725
+ },
1726
+ {
1727
+ "epoch": 0.1,
1728
+ "grad_norm": 1.3311535120010376,
1729
+ "learning_rate": 4.5132086672603144e-05,
1730
+ "loss": 3.7958,
1731
+ "step": 984
1732
+ },
1733
+ {
1734
+ "epoch": 0.1,
1735
+ "grad_norm": 1.1845935583114624,
1736
+ "learning_rate": 4.511229840704462e-05,
1737
+ "loss": 3.8895,
1738
+ "step": 988
1739
+ },
1740
+ {
1741
+ "epoch": 0.1,
1742
+ "grad_norm": 1.1750415563583374,
1743
+ "learning_rate": 4.5092510141486096e-05,
1744
+ "loss": 3.8246,
1745
+ "step": 992
1746
+ },
1747
+ {
1748
+ "epoch": 0.1,
1749
+ "grad_norm": 1.423757553100586,
1750
+ "learning_rate": 4.5072721875927576e-05,
1751
+ "loss": 3.5447,
1752
+ "step": 996
1753
+ },
1754
+ {
1755
+ "epoch": 0.1,
1756
+ "grad_norm": 1.1389232873916626,
1757
+ "learning_rate": 4.5052933610369056e-05,
1758
+ "loss": 3.5603,
1759
+ "step": 1000
1760
+ },
1761
+ {
1762
+ "epoch": 0.1,
1763
+ "grad_norm": 1.1800868511199951,
1764
+ "learning_rate": 4.503314534481053e-05,
1765
+ "loss": 3.9599,
1766
+ "step": 1004
1767
+ },
1768
+ {
1769
+ "epoch": 0.1,
1770
+ "grad_norm": 1.163454294204712,
1771
+ "learning_rate": 4.501335707925201e-05,
1772
+ "loss": 3.7299,
1773
+ "step": 1008
1774
+ }
1775
+ ],
1776
+ "logging_steps": 4,
1777
+ "max_steps": 10107,
1778
+ "num_input_tokens_seen": 0,
1779
+ "num_train_epochs": 1,
1780
+ "save_steps": 1011,
1781
+ "total_flos": 1.2364567220846592e+16,
1782
+ "train_batch_size": 4,
1783
+ "trial_name": null,
1784
+ "trial_params": null
1785
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dc190beaaaaff42a87d901c27510cc834c8a6f90f69a3e79036787272d323d
3
+ size 4920
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff