doaa18 commited on
Commit
0065b7c
·
verified ·
1 Parent(s): 3bf607d

Upload folder using huggingface_hub

Browse files
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
+ }
checkpoint-3277/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
+ }
checkpoint-3277/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "CodeGenForCausalLM"
5
+ ],
6
+ "attn_pdrop": 0.0,
7
+ "bos_token_id": 1,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": 50256,
10
+ "gradient_checkpointing": false,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "codegen",
14
+ "n_ctx": 2048,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 20,
19
+ "n_positions": 2048,
20
+ "pad_token_id": 50256,
21
+ "resid_pdrop": 0.0,
22
+ "rotary_dim": 32,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50,
33
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.51.3",
40
+ "use_cache": true,
41
+ "vocab_size": 51200
42
+ }
checkpoint-3277/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.51.3"
6
+ }
checkpoint-3277/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3277/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2743b83bd34964e6bf8daedc2f860b4a30c339c56695b6c8f9a4873dd99301a
3
+ size 1426867192
checkpoint-3277/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebfa699772561a53a180d8af4af081d6c1c66af4578f2449908f100e99c0e617
3
+ size 2853838010
checkpoint-3277/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0dd1c0cc9cc6623d47dbb6acd4025631d8cd8cc4f7ef46b26f9a385eec4f7ba
3
+ size 14244
checkpoint-3277/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cacae68fe81bc55988af6f3d11d9508a04a9adeda387c9a4cda91636da835e4
3
+ size 988
checkpoint-3277/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca16a8dbd0040dfd4b15c295fdcb350dd76494d77959ac430bb8a5208701232
3
+ size 1064
checkpoint-3277/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-3277/tokenizer_config.json ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": " ",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": " ",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": " ",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": " ",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": " ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": " ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": " ",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": " ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": " ",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": " ",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": " ",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": " ",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": " ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": " ",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": " ",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": " ",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": " ",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": " ",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": " ",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50276": {
166
+ "content": " ",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50277": {
174
+ "content": " ",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50278": {
182
+ "content": " ",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50279": {
190
+ "content": " ",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50280": {
198
+ "content": " ",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50281": {
206
+ "content": " ",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50282": {
214
+ "content": " ",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50283": {
222
+ "content": " ",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50284": {
230
+ "content": " ",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50285": {
238
+ "content": " ",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50286": {
246
+ "content": " ",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50287": {
254
+ "content": "\t\t\t\t\t\t\t\t\t",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50288": {
262
+ "content": "\t\t\t\t\t\t\t\t",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50289": {
270
+ "content": "\t\t\t\t\t\t\t",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50290": {
278
+ "content": "\t\t\t\t\t\t",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50291": {
286
+ "content": "\t\t\t\t\t",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50292": {
294
+ "content": "\t\t\t\t",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50293": {
302
+ "content": "\t\t\t",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50294": {
310
+ "content": "\t\t",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ }
317
+ },
318
+ "bos_token": "<|endoftext|>",
319
+ "clean_up_tokenization_spaces": false,
320
+ "eos_token": "<|endoftext|>",
321
+ "errors": "replace",
322
+ "extra_special_tokens": {},
323
+ "model_max_length": 2048,
324
+ "pad_token": "<|endoftext|>",
325
+ "return_token_type_ids": false,
326
+ "tokenizer_class": "CodeGenTokenizer",
327
+ "unk_token": "<|endoftext|>"
328
+ }
checkpoint-3277/trainer_state.json ADDED
@@ -0,0 +1,2323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9998474446987032,
6
+ "eval_steps": 500,
7
+ "global_step": 3277,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0030511060259344014,
14
+ "grad_norm": 4.5989179611206055,
15
+ "learning_rate": 9e-06,
16
+ "loss": 1.1046,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.006102212051868803,
21
+ "grad_norm": 4.813294887542725,
22
+ "learning_rate": 1.9e-05,
23
+ "loss": 0.8003,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.009153318077803204,
28
+ "grad_norm": 4.563686847686768,
29
+ "learning_rate": 2.9e-05,
30
+ "loss": 0.7886,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.012204424103737605,
35
+ "grad_norm": 5.083153247833252,
36
+ "learning_rate": 3.9000000000000006e-05,
37
+ "loss": 0.7638,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.015255530129672006,
42
+ "grad_norm": 4.403526306152344,
43
+ "learning_rate": 4.9e-05,
44
+ "loss": 0.7635,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.018306636155606407,
49
+ "grad_norm": 3.6779983043670654,
50
+ "learning_rate": 4.986055159590952e-05,
51
+ "loss": 0.841,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.02135774218154081,
56
+ "grad_norm": 3.7986652851104736,
57
+ "learning_rate": 4.970560892469787e-05,
58
+ "loss": 0.9439,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.02440884820747521,
63
+ "grad_norm": 3.810528516769409,
64
+ "learning_rate": 4.955066625348621e-05,
65
+ "loss": 0.843,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.02745995423340961,
70
+ "grad_norm": 3.7793450355529785,
71
+ "learning_rate": 4.939572358227456e-05,
72
+ "loss": 0.9459,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.03051106025934401,
77
+ "grad_norm": 4.002682685852051,
78
+ "learning_rate": 4.924078091106291e-05,
79
+ "loss": 0.9242,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.033562166285278416,
84
+ "grad_norm": 3.5819356441497803,
85
+ "learning_rate": 4.908583823985126e-05,
86
+ "loss": 0.8683,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.036613272311212815,
91
+ "grad_norm": 3.728360891342163,
92
+ "learning_rate": 4.893089556863961e-05,
93
+ "loss": 0.9133,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.03966437833714721,
98
+ "grad_norm": 4.5038981437683105,
99
+ "learning_rate": 4.8775952897427956e-05,
100
+ "loss": 0.8466,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.04271548436308162,
105
+ "grad_norm": 3.0992960929870605,
106
+ "learning_rate": 4.8621010226216305e-05,
107
+ "loss": 0.8424,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.04576659038901602,
112
+ "grad_norm": 3.688044786453247,
113
+ "learning_rate": 4.8466067555004654e-05,
114
+ "loss": 0.8283,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.04881769641495042,
119
+ "grad_norm": 4.070577621459961,
120
+ "learning_rate": 4.8311124883792996e-05,
121
+ "loss": 0.9207,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.05186880244088482,
126
+ "grad_norm": 3.9466311931610107,
127
+ "learning_rate": 4.8156182212581345e-05,
128
+ "loss": 0.8095,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.05491990846681922,
133
+ "grad_norm": 3.0422556400299072,
134
+ "learning_rate": 4.8001239541369694e-05,
135
+ "loss": 0.8649,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.057971014492753624,
140
+ "grad_norm": 3.414745330810547,
141
+ "learning_rate": 4.784629687015804e-05,
142
+ "loss": 0.8963,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.06102212051868802,
147
+ "grad_norm": 3.7459030151367188,
148
+ "learning_rate": 4.769135419894639e-05,
149
+ "loss": 0.8352,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.06407322654462243,
154
+ "grad_norm": 2.6838042736053467,
155
+ "learning_rate": 4.753641152773474e-05,
156
+ "loss": 0.8089,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.06712433257055683,
161
+ "grad_norm": 5.595691680908203,
162
+ "learning_rate": 4.738146885652309e-05,
163
+ "loss": 0.8701,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.07017543859649122,
168
+ "grad_norm": 3.1771981716156006,
169
+ "learning_rate": 4.722652618531144e-05,
170
+ "loss": 0.8714,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.07322654462242563,
175
+ "grad_norm": 2.728522539138794,
176
+ "learning_rate": 4.707158351409979e-05,
177
+ "loss": 0.8655,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.07627765064836003,
182
+ "grad_norm": 3.781033515930176,
183
+ "learning_rate": 4.691664084288813e-05,
184
+ "loss": 0.7953,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.07932875667429443,
189
+ "grad_norm": 2.9846785068511963,
190
+ "learning_rate": 4.676169817167648e-05,
191
+ "loss": 0.8079,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.08237986270022883,
196
+ "grad_norm": 3.5596115589141846,
197
+ "learning_rate": 4.6606755500464835e-05,
198
+ "loss": 0.8413,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.08543096872616324,
203
+ "grad_norm": 3.188471555709839,
204
+ "learning_rate": 4.645181282925318e-05,
205
+ "loss": 0.8411,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.08848207475209764,
210
+ "grad_norm": 4.387840270996094,
211
+ "learning_rate": 4.629687015804153e-05,
212
+ "loss": 0.9073,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.09153318077803203,
217
+ "grad_norm": 3.842625379562378,
218
+ "learning_rate": 4.6141927486829876e-05,
219
+ "loss": 0.8269,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.09458428680396644,
224
+ "grad_norm": 4.832952499389648,
225
+ "learning_rate": 4.5986984815618225e-05,
226
+ "loss": 0.9064,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.09763539282990084,
231
+ "grad_norm": 2.8753535747528076,
232
+ "learning_rate": 4.5832042144406574e-05,
233
+ "loss": 0.8873,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.10068649885583524,
238
+ "grad_norm": 2.5598573684692383,
239
+ "learning_rate": 4.5677099473194916e-05,
240
+ "loss": 0.8913,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.10373760488176964,
245
+ "grad_norm": 2.9012229442596436,
246
+ "learning_rate": 4.5522156801983265e-05,
247
+ "loss": 0.7988,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.10678871090770405,
252
+ "grad_norm": 2.888648748397827,
253
+ "learning_rate": 4.536721413077162e-05,
254
+ "loss": 0.8404,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.10983981693363844,
259
+ "grad_norm": 3.794020891189575,
260
+ "learning_rate": 4.521227145955996e-05,
261
+ "loss": 0.8429,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.11289092295957284,
266
+ "grad_norm": 3.925490617752075,
267
+ "learning_rate": 4.505732878834831e-05,
268
+ "loss": 0.8768,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.11594202898550725,
273
+ "grad_norm": 3.4535255432128906,
274
+ "learning_rate": 4.490238611713666e-05,
275
+ "loss": 0.7951,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.11899313501144165,
280
+ "grad_norm": 3.9904849529266357,
281
+ "learning_rate": 4.474744344592501e-05,
282
+ "loss": 0.8524,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.12204424103737604,
287
+ "grad_norm": 2.6464405059814453,
288
+ "learning_rate": 4.459250077471336e-05,
289
+ "loss": 0.8194,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.12509534706331046,
294
+ "grad_norm": 3.6185855865478516,
295
+ "learning_rate": 4.443755810350171e-05,
296
+ "loss": 0.7706,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.12814645308924486,
301
+ "grad_norm": 4.222907543182373,
302
+ "learning_rate": 4.428261543229005e-05,
303
+ "loss": 0.7858,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.13119755911517925,
308
+ "grad_norm": 2.8912553787231445,
309
+ "learning_rate": 4.4127672761078406e-05,
310
+ "loss": 0.7658,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.13424866514111367,
315
+ "grad_norm": 2.9529941082000732,
316
+ "learning_rate": 4.3972730089866755e-05,
317
+ "loss": 0.8415,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.13729977116704806,
322
+ "grad_norm": 3.296875238418579,
323
+ "learning_rate": 4.38177874186551e-05,
324
+ "loss": 0.818,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.14035087719298245,
329
+ "grad_norm": 2.736250400543213,
330
+ "learning_rate": 4.366284474744345e-05,
331
+ "loss": 0.819,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.14340198321891687,
336
+ "grad_norm": 3.2874772548675537,
337
+ "learning_rate": 4.3507902076231796e-05,
338
+ "loss": 0.8381,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.14645308924485126,
343
+ "grad_norm": 2.9855446815490723,
344
+ "learning_rate": 4.3352959405020145e-05,
345
+ "loss": 0.7591,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.14950419527078565,
350
+ "grad_norm": 3.37127947807312,
351
+ "learning_rate": 4.3198016733808494e-05,
352
+ "loss": 0.7815,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.15255530129672007,
357
+ "grad_norm": 3.162848472595215,
358
+ "learning_rate": 4.3043074062596836e-05,
359
+ "loss": 0.8115,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.15560640732265446,
364
+ "grad_norm": 3.0527734756469727,
365
+ "learning_rate": 4.288813139138519e-05,
366
+ "loss": 0.8871,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.15865751334858885,
371
+ "grad_norm": 3.1467580795288086,
372
+ "learning_rate": 4.273318872017354e-05,
373
+ "loss": 0.9112,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.16170861937452327,
378
+ "grad_norm": 3.414907455444336,
379
+ "learning_rate": 4.257824604896188e-05,
380
+ "loss": 0.8089,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.16475972540045766,
385
+ "grad_norm": 3.9576640129089355,
386
+ "learning_rate": 4.242330337775023e-05,
387
+ "loss": 0.7847,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.16781083142639205,
392
+ "grad_norm": 3.8652496337890625,
393
+ "learning_rate": 4.226836070653858e-05,
394
+ "loss": 0.801,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.17086193745232647,
399
+ "grad_norm": 3.028764247894287,
400
+ "learning_rate": 4.211341803532693e-05,
401
+ "loss": 0.8323,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.17391304347826086,
406
+ "grad_norm": 3.1638927459716797,
407
+ "learning_rate": 4.195847536411528e-05,
408
+ "loss": 0.8575,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.17696414950419528,
413
+ "grad_norm": 3.3378586769104004,
414
+ "learning_rate": 4.180353269290363e-05,
415
+ "loss": 0.8048,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.18001525553012968,
420
+ "grad_norm": 2.5703723430633545,
421
+ "learning_rate": 4.164859002169198e-05,
422
+ "loss": 0.8557,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.18306636155606407,
427
+ "grad_norm": 4.101804733276367,
428
+ "learning_rate": 4.1493647350480326e-05,
429
+ "loss": 0.8358,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.18611746758199849,
434
+ "grad_norm": 3.845407009124756,
435
+ "learning_rate": 4.1338704679268675e-05,
436
+ "loss": 0.8777,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.18916857360793288,
441
+ "grad_norm": 3.370732545852661,
442
+ "learning_rate": 4.118376200805702e-05,
443
+ "loss": 0.8485,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.19221967963386727,
448
+ "grad_norm": 2.168769121170044,
449
+ "learning_rate": 4.102881933684537e-05,
450
+ "loss": 0.7416,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.1952707856598017,
455
+ "grad_norm": 3.819798707962036,
456
+ "learning_rate": 4.087387666563372e-05,
457
+ "loss": 0.9199,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.19832189168573608,
462
+ "grad_norm": 3.19429612159729,
463
+ "learning_rate": 4.0718933994422065e-05,
464
+ "loss": 0.7747,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.20137299771167047,
469
+ "grad_norm": 3.17229962348938,
470
+ "learning_rate": 4.0563991323210414e-05,
471
+ "loss": 0.7394,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.2044241037376049,
476
+ "grad_norm": 2.316675901412964,
477
+ "learning_rate": 4.040904865199876e-05,
478
+ "loss": 0.7368,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.20747520976353928,
483
+ "grad_norm": 3.350698471069336,
484
+ "learning_rate": 4.025410598078711e-05,
485
+ "loss": 0.8839,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.21052631578947367,
490
+ "grad_norm": 2.5842721462249756,
491
+ "learning_rate": 4.009916330957546e-05,
492
+ "loss": 0.7665,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.2135774218154081,
497
+ "grad_norm": 2.9108049869537354,
498
+ "learning_rate": 3.99442206383638e-05,
499
+ "loss": 0.8145,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.21662852784134248,
504
+ "grad_norm": 2.9678006172180176,
505
+ "learning_rate": 3.978927796715215e-05,
506
+ "loss": 0.7719,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.21967963386727687,
511
+ "grad_norm": 2.911322832107544,
512
+ "learning_rate": 3.963433529594051e-05,
513
+ "loss": 0.7354,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.2227307398932113,
518
+ "grad_norm": 3.1599249839782715,
519
+ "learning_rate": 3.947939262472885e-05,
520
+ "loss": 0.7873,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.22578184591914569,
525
+ "grad_norm": 2.6644296646118164,
526
+ "learning_rate": 3.93244499535172e-05,
527
+ "loss": 0.8311,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.2288329519450801,
532
+ "grad_norm": 3.263995885848999,
533
+ "learning_rate": 3.916950728230555e-05,
534
+ "loss": 0.8185,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.2318840579710145,
539
+ "grad_norm": 2.542343854904175,
540
+ "learning_rate": 3.90145646110939e-05,
541
+ "loss": 0.7769,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.2349351639969489,
546
+ "grad_norm": 2.4859440326690674,
547
+ "learning_rate": 3.8859621939882246e-05,
548
+ "loss": 0.8328,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.2379862700228833,
553
+ "grad_norm": 2.632722854614258,
554
+ "learning_rate": 3.8704679268670596e-05,
555
+ "loss": 0.7859,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.2410373760488177,
560
+ "grad_norm": 3.209907054901123,
561
+ "learning_rate": 3.854973659745894e-05,
562
+ "loss": 0.8394,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.2440884820747521,
567
+ "grad_norm": 2.4981114864349365,
568
+ "learning_rate": 3.8394793926247294e-05,
569
+ "loss": 0.8241,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.2471395881006865,
574
+ "grad_norm": 2.5217268466949463,
575
+ "learning_rate": 3.823985125503564e-05,
576
+ "loss": 0.7501,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.2501906941266209,
581
+ "grad_norm": 3.676504611968994,
582
+ "learning_rate": 3.8084908583823985e-05,
583
+ "loss": 0.8782,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.2532418001525553,
588
+ "grad_norm": 2.651146173477173,
589
+ "learning_rate": 3.7929965912612334e-05,
590
+ "loss": 0.848,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.2562929061784897,
595
+ "grad_norm": 3.1401736736297607,
596
+ "learning_rate": 3.777502324140068e-05,
597
+ "loss": 0.7991,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.2593440122044241,
602
+ "grad_norm": 3.0251362323760986,
603
+ "learning_rate": 3.762008057018903e-05,
604
+ "loss": 0.8723,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.2623951182303585,
609
+ "grad_norm": 2.1540679931640625,
610
+ "learning_rate": 3.746513789897738e-05,
611
+ "loss": 0.7478,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.2654462242562929,
616
+ "grad_norm": 2.6065683364868164,
617
+ "learning_rate": 3.731019522776572e-05,
618
+ "loss": 0.7488,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.26849733028222733,
623
+ "grad_norm": 2.697063684463501,
624
+ "learning_rate": 3.715525255655408e-05,
625
+ "loss": 0.7778,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.2715484363081617,
630
+ "grad_norm": 3.4640157222747803,
631
+ "learning_rate": 3.700030988534243e-05,
632
+ "loss": 1.0205,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.2745995423340961,
637
+ "grad_norm": 3.5426061153411865,
638
+ "learning_rate": 3.684536721413077e-05,
639
+ "loss": 0.762,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.2776506483600305,
644
+ "grad_norm": 2.219358444213867,
645
+ "learning_rate": 3.669042454291912e-05,
646
+ "loss": 0.7996,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.2807017543859649,
651
+ "grad_norm": 2.7404627799987793,
652
+ "learning_rate": 3.6535481871707475e-05,
653
+ "loss": 0.7611,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.2837528604118993,
658
+ "grad_norm": 2.950205087661743,
659
+ "learning_rate": 3.638053920049582e-05,
660
+ "loss": 0.7685,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.28680396643783374,
665
+ "grad_norm": 2.676258087158203,
666
+ "learning_rate": 3.6225596529284167e-05,
667
+ "loss": 0.7864,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.2898550724637681,
672
+ "grad_norm": 2.5284500122070312,
673
+ "learning_rate": 3.6070653858072516e-05,
674
+ "loss": 0.7856,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.2929061784897025,
679
+ "grad_norm": 2.2837953567504883,
680
+ "learning_rate": 3.5915711186860865e-05,
681
+ "loss": 0.7965,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.2959572845156369,
686
+ "grad_norm": 3.223839044570923,
687
+ "learning_rate": 3.5760768515649214e-05,
688
+ "loss": 0.8123,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.2990083905415713,
693
+ "grad_norm": 2.8053982257843018,
694
+ "learning_rate": 3.560582584443756e-05,
695
+ "loss": 0.7813,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.30205949656750575,
700
+ "grad_norm": 2.799560785293579,
701
+ "learning_rate": 3.5450883173225905e-05,
702
+ "loss": 0.8418,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.30511060259344014,
707
+ "grad_norm": 3.838677406311035,
708
+ "learning_rate": 3.529594050201426e-05,
709
+ "loss": 0.7948,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.30816170861937453,
714
+ "grad_norm": 2.587244749069214,
715
+ "learning_rate": 3.51409978308026e-05,
716
+ "loss": 0.784,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.3112128146453089,
721
+ "grad_norm": 3.555494785308838,
722
+ "learning_rate": 3.498605515959095e-05,
723
+ "loss": 0.7854,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.3142639206712433,
728
+ "grad_norm": 2.900275468826294,
729
+ "learning_rate": 3.48311124883793e-05,
730
+ "loss": 0.8536,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.3173150266971777,
735
+ "grad_norm": 3.058786153793335,
736
+ "learning_rate": 3.467616981716765e-05,
737
+ "loss": 0.8163,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.32036613272311215,
742
+ "grad_norm": 3.0138072967529297,
743
+ "learning_rate": 3.4521227145956e-05,
744
+ "loss": 0.8534,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.32341723874904654,
749
+ "grad_norm": 2.71114182472229,
750
+ "learning_rate": 3.436628447474435e-05,
751
+ "loss": 0.8401,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.32646834477498093,
756
+ "grad_norm": 2.574453592300415,
757
+ "learning_rate": 3.421134180353269e-05,
758
+ "loss": 0.7596,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.3295194508009153,
763
+ "grad_norm": 2.7125132083892822,
764
+ "learning_rate": 3.4056399132321046e-05,
765
+ "loss": 0.8042,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.3325705568268497,
770
+ "grad_norm": 3.0520405769348145,
771
+ "learning_rate": 3.3901456461109395e-05,
772
+ "loss": 0.7713,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.3356216628527841,
777
+ "grad_norm": 2.5527734756469727,
778
+ "learning_rate": 3.374651378989774e-05,
779
+ "loss": 0.7929,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.33867276887871856,
784
+ "grad_norm": 2.1792235374450684,
785
+ "learning_rate": 3.3591571118686087e-05,
786
+ "loss": 0.7102,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.34172387490465295,
791
+ "grad_norm": 3.192811965942383,
792
+ "learning_rate": 3.3436628447474436e-05,
793
+ "loss": 0.7956,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.34477498093058734,
798
+ "grad_norm": 3.0279996395111084,
799
+ "learning_rate": 3.3281685776262785e-05,
800
+ "loss": 0.7883,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.34782608695652173,
805
+ "grad_norm": 3.0758237838745117,
806
+ "learning_rate": 3.3126743105051134e-05,
807
+ "loss": 0.7457,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.3508771929824561,
812
+ "grad_norm": 2.2491872310638428,
813
+ "learning_rate": 3.297180043383948e-05,
814
+ "loss": 0.7712,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.35392829900839057,
819
+ "grad_norm": 2.543558120727539,
820
+ "learning_rate": 3.281685776262783e-05,
821
+ "loss": 0.8013,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.35697940503432496,
826
+ "grad_norm": 2.996823310852051,
827
+ "learning_rate": 3.266191509141618e-05,
828
+ "loss": 0.7769,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.36003051106025935,
833
+ "grad_norm": 2.1455206871032715,
834
+ "learning_rate": 3.250697242020452e-05,
835
+ "loss": 0.7778,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.36308161708619374,
840
+ "grad_norm": 3.1174466609954834,
841
+ "learning_rate": 3.235202974899287e-05,
842
+ "loss": 0.7519,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.36613272311212813,
847
+ "grad_norm": 2.6810905933380127,
848
+ "learning_rate": 3.219708707778122e-05,
849
+ "loss": 0.8112,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.3691838291380625,
854
+ "grad_norm": 2.6105597019195557,
855
+ "learning_rate": 3.204214440656957e-05,
856
+ "loss": 0.7344,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.37223493516399697,
861
+ "grad_norm": 3.3781626224517822,
862
+ "learning_rate": 3.188720173535792e-05,
863
+ "loss": 0.8401,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.37528604118993136,
868
+ "grad_norm": 3.3649299144744873,
869
+ "learning_rate": 3.173225906414627e-05,
870
+ "loss": 0.7849,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.37833714721586575,
875
+ "grad_norm": 2.6910207271575928,
876
+ "learning_rate": 3.157731639293462e-05,
877
+ "loss": 0.8165,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.38138825324180015,
882
+ "grad_norm": 2.5760819911956787,
883
+ "learning_rate": 3.1422373721722966e-05,
884
+ "loss": 0.8043,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.38443935926773454,
889
+ "grad_norm": 2.5498452186584473,
890
+ "learning_rate": 3.1267431050511315e-05,
891
+ "loss": 0.7566,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.38749046529366893,
896
+ "grad_norm": 1.8285728693008423,
897
+ "learning_rate": 3.111248837929966e-05,
898
+ "loss": 0.7152,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.3905415713196034,
903
+ "grad_norm": 2.509260654449463,
904
+ "learning_rate": 3.0957545708088007e-05,
905
+ "loss": 0.8489,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.39359267734553777,
910
+ "grad_norm": 2.905968427658081,
911
+ "learning_rate": 3.080260303687636e-05,
912
+ "loss": 0.7369,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.39664378337147216,
917
+ "grad_norm": 2.5083484649658203,
918
+ "learning_rate": 3.0647660365664705e-05,
919
+ "loss": 0.7331,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.39969488939740655,
924
+ "grad_norm": 2.2442944049835205,
925
+ "learning_rate": 3.0492717694453054e-05,
926
+ "loss": 0.7282,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.40274599542334094,
931
+ "grad_norm": 2.856735944747925,
932
+ "learning_rate": 3.0337775023241406e-05,
933
+ "loss": 0.7009,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.4057971014492754,
938
+ "grad_norm": 2.9385952949523926,
939
+ "learning_rate": 3.018283235202975e-05,
940
+ "loss": 0.7225,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.4088482074752098,
945
+ "grad_norm": 3.0979793071746826,
946
+ "learning_rate": 3.00278896808181e-05,
947
+ "loss": 0.764,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.41189931350114417,
952
+ "grad_norm": 2.6863820552825928,
953
+ "learning_rate": 2.9872947009606443e-05,
954
+ "loss": 0.7475,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.41495041952707856,
959
+ "grad_norm": 2.9140465259552,
960
+ "learning_rate": 2.9718004338394795e-05,
961
+ "loss": 0.7468,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.41800152555301295,
966
+ "grad_norm": 2.702855348587036,
967
+ "learning_rate": 2.9563061667183144e-05,
968
+ "loss": 0.7444,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.42105263157894735,
973
+ "grad_norm": 2.646045207977295,
974
+ "learning_rate": 2.940811899597149e-05,
975
+ "loss": 0.7911,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.4241037376048818,
980
+ "grad_norm": 2.568760395050049,
981
+ "learning_rate": 2.925317632475984e-05,
982
+ "loss": 0.7815,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.4271548436308162,
987
+ "grad_norm": 2.381138801574707,
988
+ "learning_rate": 2.909823365354819e-05,
989
+ "loss": 0.7411,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.4302059496567506,
994
+ "grad_norm": 2.6686244010925293,
995
+ "learning_rate": 2.8943290982336534e-05,
996
+ "loss": 0.7593,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.43325705568268497,
1001
+ "grad_norm": 3.8091323375701904,
1002
+ "learning_rate": 2.8788348311124886e-05,
1003
+ "loss": 0.7731,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.43630816170861936,
1008
+ "grad_norm": 3.0860376358032227,
1009
+ "learning_rate": 2.8633405639913235e-05,
1010
+ "loss": 0.7617,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.43935926773455375,
1015
+ "grad_norm": 3.304323196411133,
1016
+ "learning_rate": 2.847846296870158e-05,
1017
+ "loss": 0.8343,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.4424103737604882,
1022
+ "grad_norm": 2.6195857524871826,
1023
+ "learning_rate": 2.832352029748993e-05,
1024
+ "loss": 0.688,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.4454614797864226,
1029
+ "grad_norm": 2.3896477222442627,
1030
+ "learning_rate": 2.8168577626278282e-05,
1031
+ "loss": 0.8032,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.448512585812357,
1036
+ "grad_norm": 2.9045519828796387,
1037
+ "learning_rate": 2.8013634955066625e-05,
1038
+ "loss": 0.8131,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.45156369183829137,
1043
+ "grad_norm": 2.5903823375701904,
1044
+ "learning_rate": 2.7858692283854977e-05,
1045
+ "loss": 0.7219,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.45461479786422576,
1050
+ "grad_norm": 2.8301548957824707,
1051
+ "learning_rate": 2.7703749612643326e-05,
1052
+ "loss": 0.7661,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.4576659038901602,
1057
+ "grad_norm": 2.5708298683166504,
1058
+ "learning_rate": 2.7548806941431672e-05,
1059
+ "loss": 0.7673,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.4607170099160946,
1064
+ "grad_norm": 2.4464125633239746,
1065
+ "learning_rate": 2.739386427022002e-05,
1066
+ "loss": 0.7328,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.463768115942029,
1071
+ "grad_norm": 3.007063627243042,
1072
+ "learning_rate": 2.7238921599008366e-05,
1073
+ "loss": 0.7449,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.4668192219679634,
1078
+ "grad_norm": 2.8109517097473145,
1079
+ "learning_rate": 2.7083978927796715e-05,
1080
+ "loss": 0.8403,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.4698703279938978,
1085
+ "grad_norm": 2.756274461746216,
1086
+ "learning_rate": 2.6929036256585068e-05,
1087
+ "loss": 0.786,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.47292143401983217,
1092
+ "grad_norm": 3.142169237136841,
1093
+ "learning_rate": 2.677409358537341e-05,
1094
+ "loss": 0.7738,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.4759725400457666,
1099
+ "grad_norm": 2.546050548553467,
1100
+ "learning_rate": 2.6619150914161763e-05,
1101
+ "loss": 0.7806,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.479023646071701,
1106
+ "grad_norm": 2.3914120197296143,
1107
+ "learning_rate": 2.646420824295011e-05,
1108
+ "loss": 0.7641,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.4820747520976354,
1113
+ "grad_norm": 2.156118869781494,
1114
+ "learning_rate": 2.6309265571738457e-05,
1115
+ "loss": 0.8034,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.4851258581235698,
1120
+ "grad_norm": 2.6585230827331543,
1121
+ "learning_rate": 2.6154322900526806e-05,
1122
+ "loss": 0.7609,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.4881769641495042,
1127
+ "grad_norm": 2.175424814224243,
1128
+ "learning_rate": 2.5999380229315155e-05,
1129
+ "loss": 0.6381,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.49122807017543857,
1134
+ "grad_norm": 3.3766794204711914,
1135
+ "learning_rate": 2.58444375581035e-05,
1136
+ "loss": 0.7187,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.494279176201373,
1141
+ "grad_norm": 2.665618419647217,
1142
+ "learning_rate": 2.568949488689185e-05,
1143
+ "loss": 0.7492,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.4973302822273074,
1148
+ "grad_norm": 2.5544931888580322,
1149
+ "learning_rate": 2.5534552215680202e-05,
1150
+ "loss": 0.7473,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.5003813882532419,
1155
+ "grad_norm": 2.091601848602295,
1156
+ "learning_rate": 2.5379609544468548e-05,
1157
+ "loss": 0.7364,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.5034324942791762,
1162
+ "grad_norm": 2.7752933502197266,
1163
+ "learning_rate": 2.5224666873256897e-05,
1164
+ "loss": 0.8124,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.5064836003051106,
1169
+ "grad_norm": 2.3963379859924316,
1170
+ "learning_rate": 2.5069724202045246e-05,
1171
+ "loss": 0.7213,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.509534706331045,
1176
+ "grad_norm": 2.0520660877227783,
1177
+ "learning_rate": 2.4914781530833592e-05,
1178
+ "loss": 0.7954,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.5125858123569794,
1183
+ "grad_norm": 2.9152419567108154,
1184
+ "learning_rate": 2.475983885962194e-05,
1185
+ "loss": 0.7114,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.5156369183829138,
1190
+ "grad_norm": 3.4632716178894043,
1191
+ "learning_rate": 2.460489618841029e-05,
1192
+ "loss": 0.7557,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.5186880244088482,
1197
+ "grad_norm": 3.0776329040527344,
1198
+ "learning_rate": 2.4449953517198636e-05,
1199
+ "loss": 0.7867,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.5217391304347826,
1204
+ "grad_norm": 2.640956163406372,
1205
+ "learning_rate": 2.4295010845986985e-05,
1206
+ "loss": 0.717,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.524790236460717,
1211
+ "grad_norm": 3.0681939125061035,
1212
+ "learning_rate": 2.4140068174775334e-05,
1213
+ "loss": 0.779,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.5278413424866514,
1218
+ "grad_norm": 3.3912854194641113,
1219
+ "learning_rate": 2.3985125503563683e-05,
1220
+ "loss": 0.7602,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.5308924485125858,
1225
+ "grad_norm": 3.4418396949768066,
1226
+ "learning_rate": 2.3830182832352028e-05,
1227
+ "loss": 0.7719,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.5339435545385202,
1232
+ "grad_norm": 2.5723013877868652,
1233
+ "learning_rate": 2.367524016114038e-05,
1234
+ "loss": 0.6693,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.5369946605644547,
1239
+ "grad_norm": 3.5987260341644287,
1240
+ "learning_rate": 2.3520297489928726e-05,
1241
+ "loss": 0.7202,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.540045766590389,
1246
+ "grad_norm": 3.0256638526916504,
1247
+ "learning_rate": 2.3365354818717075e-05,
1248
+ "loss": 0.769,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.5430968726163234,
1253
+ "grad_norm": 2.5137994289398193,
1254
+ "learning_rate": 2.3210412147505424e-05,
1255
+ "loss": 0.7133,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.5461479786422578,
1260
+ "grad_norm": 2.394585132598877,
1261
+ "learning_rate": 2.3055469476293773e-05,
1262
+ "loss": 0.7089,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.5491990846681922,
1267
+ "grad_norm": 2.6688249111175537,
1268
+ "learning_rate": 2.290052680508212e-05,
1269
+ "loss": 0.7819,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.5522501906941266,
1274
+ "grad_norm": 3.030775785446167,
1275
+ "learning_rate": 2.2745584133870468e-05,
1276
+ "loss": 0.7545,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.555301296720061,
1281
+ "grad_norm": 3.2252886295318604,
1282
+ "learning_rate": 2.2590641462658817e-05,
1283
+ "loss": 0.7854,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.5583524027459954,
1288
+ "grad_norm": 1.8850343227386475,
1289
+ "learning_rate": 2.2435698791447166e-05,
1290
+ "loss": 0.708,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.5614035087719298,
1295
+ "grad_norm": 3.511936902999878,
1296
+ "learning_rate": 2.2280756120235512e-05,
1297
+ "loss": 0.7384,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.5644546147978642,
1302
+ "grad_norm": 3.171138286590576,
1303
+ "learning_rate": 2.2125813449023864e-05,
1304
+ "loss": 0.7831,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.5675057208237986,
1309
+ "grad_norm": 2.5248336791992188,
1310
+ "learning_rate": 2.197087077781221e-05,
1311
+ "loss": 0.7011,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.5705568268497331,
1316
+ "grad_norm": 3.0410759449005127,
1317
+ "learning_rate": 2.181592810660056e-05,
1318
+ "loss": 0.7252,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.5736079328756675,
1323
+ "grad_norm": 3.691617012023926,
1324
+ "learning_rate": 2.1660985435388905e-05,
1325
+ "loss": 0.7585,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.5766590389016019,
1330
+ "grad_norm": 2.653752565383911,
1331
+ "learning_rate": 2.1506042764177257e-05,
1332
+ "loss": 0.7948,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.5797101449275363,
1337
+ "grad_norm": 2.0451462268829346,
1338
+ "learning_rate": 2.1351100092965603e-05,
1339
+ "loss": 0.6916,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.5827612509534706,
1344
+ "grad_norm": 2.8858132362365723,
1345
+ "learning_rate": 2.1196157421753952e-05,
1346
+ "loss": 0.682,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.585812356979405,
1351
+ "grad_norm": 2.553213596343994,
1352
+ "learning_rate": 2.10412147505423e-05,
1353
+ "loss": 0.7501,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.5888634630053394,
1358
+ "grad_norm": 2.1616005897521973,
1359
+ "learning_rate": 2.088627207933065e-05,
1360
+ "loss": 0.7536,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.5919145690312738,
1365
+ "grad_norm": 3.390302896499634,
1366
+ "learning_rate": 2.0731329408118995e-05,
1367
+ "loss": 0.787,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.5949656750572082,
1372
+ "grad_norm": 2.695875883102417,
1373
+ "learning_rate": 2.0576386736907348e-05,
1374
+ "loss": 0.7717,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.5980167810831426,
1379
+ "grad_norm": 2.517509698867798,
1380
+ "learning_rate": 2.0421444065695693e-05,
1381
+ "loss": 0.7527,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.601067887109077,
1386
+ "grad_norm": 2.498511552810669,
1387
+ "learning_rate": 2.0266501394484043e-05,
1388
+ "loss": 0.6925,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.6041189931350115,
1393
+ "grad_norm": 2.409759044647217,
1394
+ "learning_rate": 2.0111558723272388e-05,
1395
+ "loss": 0.7283,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.6071700991609459,
1400
+ "grad_norm": 3.212092876434326,
1401
+ "learning_rate": 1.995661605206074e-05,
1402
+ "loss": 0.6655,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.6102212051868803,
1407
+ "grad_norm": 2.577396869659424,
1408
+ "learning_rate": 1.9801673380849086e-05,
1409
+ "loss": 0.6565,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.6132723112128147,
1414
+ "grad_norm": 2.715590715408325,
1415
+ "learning_rate": 1.9646730709637435e-05,
1416
+ "loss": 0.6705,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.6163234172387491,
1421
+ "grad_norm": 2.6704838275909424,
1422
+ "learning_rate": 1.9491788038425784e-05,
1423
+ "loss": 0.7789,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.6193745232646835,
1428
+ "grad_norm": 2.4763495922088623,
1429
+ "learning_rate": 1.9336845367214133e-05,
1430
+ "loss": 0.8014,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.6224256292906178,
1435
+ "grad_norm": 2.754671573638916,
1436
+ "learning_rate": 1.918190269600248e-05,
1437
+ "loss": 0.7272,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.6254767353165522,
1442
+ "grad_norm": 3.223806858062744,
1443
+ "learning_rate": 1.9026960024790828e-05,
1444
+ "loss": 0.7103,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.6285278413424866,
1449
+ "grad_norm": 2.489527702331543,
1450
+ "learning_rate": 1.8872017353579177e-05,
1451
+ "loss": 0.6492,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.631578947368421,
1456
+ "grad_norm": 3.088130235671997,
1457
+ "learning_rate": 1.8717074682367526e-05,
1458
+ "loss": 0.6808,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.6346300533943554,
1463
+ "grad_norm": 3.130558967590332,
1464
+ "learning_rate": 1.8562132011155872e-05,
1465
+ "loss": 0.7399,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.6376811594202898,
1470
+ "grad_norm": 2.672267436981201,
1471
+ "learning_rate": 1.840718933994422e-05,
1472
+ "loss": 0.7012,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.6407322654462243,
1477
+ "grad_norm": 3.445889472961426,
1478
+ "learning_rate": 1.825224666873257e-05,
1479
+ "loss": 0.7329,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.6437833714721587,
1484
+ "grad_norm": 2.1221354007720947,
1485
+ "learning_rate": 1.809730399752092e-05,
1486
+ "loss": 0.7105,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.6468344774980931,
1491
+ "grad_norm": 2.5181918144226074,
1492
+ "learning_rate": 1.7942361326309268e-05,
1493
+ "loss": 0.7719,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.6498855835240275,
1498
+ "grad_norm": 3.100332021713257,
1499
+ "learning_rate": 1.7787418655097614e-05,
1500
+ "loss": 0.6837,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.6529366895499619,
1505
+ "grad_norm": 3.2809691429138184,
1506
+ "learning_rate": 1.7632475983885963e-05,
1507
+ "loss": 0.7173,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.6559877955758963,
1512
+ "grad_norm": 2.191570520401001,
1513
+ "learning_rate": 1.747753331267431e-05,
1514
+ "loss": 0.6494,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.6590389016018307,
1519
+ "grad_norm": 2.8507699966430664,
1520
+ "learning_rate": 1.732259064146266e-05,
1521
+ "loss": 0.7094,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.662090007627765,
1526
+ "grad_norm": 2.7249112129211426,
1527
+ "learning_rate": 1.7167647970251006e-05,
1528
+ "loss": 0.6549,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.6651411136536994,
1533
+ "grad_norm": 1.7811733484268188,
1534
+ "learning_rate": 1.7012705299039355e-05,
1535
+ "loss": 0.6353,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.6681922196796338,
1540
+ "grad_norm": 2.451258659362793,
1541
+ "learning_rate": 1.6857762627827704e-05,
1542
+ "loss": 0.7104,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.6712433257055682,
1547
+ "grad_norm": 2.2157397270202637,
1548
+ "learning_rate": 1.6702819956616053e-05,
1549
+ "loss": 0.7135,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.6742944317315027,
1554
+ "grad_norm": 2.1415586471557617,
1555
+ "learning_rate": 1.65478772854044e-05,
1556
+ "loss": 0.6959,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.6773455377574371,
1561
+ "grad_norm": 2.9360268115997314,
1562
+ "learning_rate": 1.6392934614192748e-05,
1563
+ "loss": 0.7511,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.6803966437833715,
1568
+ "grad_norm": 2.7337160110473633,
1569
+ "learning_rate": 1.6237991942981097e-05,
1570
+ "loss": 0.7181,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.6834477498093059,
1575
+ "grad_norm": 3.827877998352051,
1576
+ "learning_rate": 1.6083049271769446e-05,
1577
+ "loss": 0.6735,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.6864988558352403,
1582
+ "grad_norm": 2.284428834915161,
1583
+ "learning_rate": 1.5928106600557792e-05,
1584
+ "loss": 0.6822,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.6895499618611747,
1589
+ "grad_norm": 2.9292097091674805,
1590
+ "learning_rate": 1.5773163929346144e-05,
1591
+ "loss": 0.7522,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.6926010678871091,
1596
+ "grad_norm": 2.607977867126465,
1597
+ "learning_rate": 1.561822125813449e-05,
1598
+ "loss": 0.656,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.6956521739130435,
1603
+ "grad_norm": 3.1531264781951904,
1604
+ "learning_rate": 1.546327858692284e-05,
1605
+ "loss": 0.7427,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.6987032799389779,
1610
+ "grad_norm": 2.421393871307373,
1611
+ "learning_rate": 1.5308335915711188e-05,
1612
+ "loss": 0.6408,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.7017543859649122,
1617
+ "grad_norm": 3.7150917053222656,
1618
+ "learning_rate": 1.5153393244499537e-05,
1619
+ "loss": 0.7536,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.7048054919908466,
1624
+ "grad_norm": 2.622455358505249,
1625
+ "learning_rate": 1.4998450573287884e-05,
1626
+ "loss": 0.7359,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.7078565980167811,
1631
+ "grad_norm": 2.524982452392578,
1632
+ "learning_rate": 1.4843507902076232e-05,
1633
+ "loss": 0.689,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.7109077040427155,
1638
+ "grad_norm": 3.156085729598999,
1639
+ "learning_rate": 1.4688565230864582e-05,
1640
+ "loss": 0.7111,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.7139588100686499,
1645
+ "grad_norm": 2.8505616188049316,
1646
+ "learning_rate": 1.453362255965293e-05,
1647
+ "loss": 0.6698,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.7170099160945843,
1652
+ "grad_norm": 2.8530240058898926,
1653
+ "learning_rate": 1.4378679888441277e-05,
1654
+ "loss": 0.7196,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.7200610221205187,
1659
+ "grad_norm": 2.8734195232391357,
1660
+ "learning_rate": 1.4223737217229626e-05,
1661
+ "loss": 0.7656,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.7231121281464531,
1666
+ "grad_norm": 2.84820556640625,
1667
+ "learning_rate": 1.4068794546017975e-05,
1668
+ "loss": 0.6777,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.7261632341723875,
1673
+ "grad_norm": 2.4297478199005127,
1674
+ "learning_rate": 1.3913851874806322e-05,
1675
+ "loss": 0.7145,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.7292143401983219,
1680
+ "grad_norm": 2.734090566635132,
1681
+ "learning_rate": 1.375890920359467e-05,
1682
+ "loss": 0.6577,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.7322654462242563,
1687
+ "grad_norm": 2.2257931232452393,
1688
+ "learning_rate": 1.3603966532383019e-05,
1689
+ "loss": 0.6857,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.7353165522501907,
1694
+ "grad_norm": 2.3681576251983643,
1695
+ "learning_rate": 1.3449023861171368e-05,
1696
+ "loss": 0.7619,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.738367658276125,
1701
+ "grad_norm": 2.033923864364624,
1702
+ "learning_rate": 1.3294081189959715e-05,
1703
+ "loss": 0.691,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.7414187643020596,
1708
+ "grad_norm": 2.131638526916504,
1709
+ "learning_rate": 1.3139138518748064e-05,
1710
+ "loss": 0.7191,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.7444698703279939,
1715
+ "grad_norm": 2.609546661376953,
1716
+ "learning_rate": 1.2984195847536412e-05,
1717
+ "loss": 0.6737,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.7475209763539283,
1722
+ "grad_norm": 2.4548799991607666,
1723
+ "learning_rate": 1.282925317632476e-05,
1724
+ "loss": 0.6301,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.7505720823798627,
1729
+ "grad_norm": 2.644568920135498,
1730
+ "learning_rate": 1.267431050511311e-05,
1731
+ "loss": 0.6824,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.7536231884057971,
1736
+ "grad_norm": 2.595654249191284,
1737
+ "learning_rate": 1.2519367833901457e-05,
1738
+ "loss": 0.654,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.7566742944317315,
1743
+ "grad_norm": 2.7976434230804443,
1744
+ "learning_rate": 1.2364425162689804e-05,
1745
+ "loss": 0.7883,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.7597254004576659,
1750
+ "grad_norm": 2.874528646469116,
1751
+ "learning_rate": 1.2209482491478153e-05,
1752
+ "loss": 0.7202,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.7627765064836003,
1757
+ "grad_norm": 2.6641483306884766,
1758
+ "learning_rate": 1.20545398202665e-05,
1759
+ "loss": 0.6692,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.7658276125095347,
1764
+ "grad_norm": 2.610469102859497,
1765
+ "learning_rate": 1.189959714905485e-05,
1766
+ "loss": 0.7201,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.7688787185354691,
1771
+ "grad_norm": 2.2959210872650146,
1772
+ "learning_rate": 1.1744654477843199e-05,
1773
+ "loss": 0.6302,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.7719298245614035,
1778
+ "grad_norm": 2.454118013381958,
1779
+ "learning_rate": 1.1589711806631546e-05,
1780
+ "loss": 0.7102,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.7749809305873379,
1785
+ "grad_norm": 2.6348319053649902,
1786
+ "learning_rate": 1.1434769135419895e-05,
1787
+ "loss": 0.7214,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.7780320366132724,
1792
+ "grad_norm": 2.254340887069702,
1793
+ "learning_rate": 1.1279826464208242e-05,
1794
+ "loss": 0.6973,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.7810831426392068,
1799
+ "grad_norm": 2.1454594135284424,
1800
+ "learning_rate": 1.1124883792996592e-05,
1801
+ "loss": 0.7037,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.7841342486651411,
1806
+ "grad_norm": 2.7335195541381836,
1807
+ "learning_rate": 1.096994112178494e-05,
1808
+ "loss": 0.7059,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.7871853546910755,
1813
+ "grad_norm": 3.499448776245117,
1814
+ "learning_rate": 1.0814998450573288e-05,
1815
+ "loss": 0.6518,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.7902364607170099,
1820
+ "grad_norm": 2.517699956893921,
1821
+ "learning_rate": 1.0660055779361637e-05,
1822
+ "loss": 0.6884,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.7932875667429443,
1827
+ "grad_norm": 2.7374229431152344,
1828
+ "learning_rate": 1.0505113108149984e-05,
1829
+ "loss": 0.6146,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.7963386727688787,
1834
+ "grad_norm": 3.5942227840423584,
1835
+ "learning_rate": 1.0350170436938333e-05,
1836
+ "loss": 0.7788,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.7993897787948131,
1841
+ "grad_norm": 2.709524393081665,
1842
+ "learning_rate": 1.019522776572668e-05,
1843
+ "loss": 0.6843,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.8024408848207475,
1848
+ "grad_norm": 2.7754933834075928,
1849
+ "learning_rate": 1.004028509451503e-05,
1850
+ "loss": 0.7694,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.8054919908466819,
1855
+ "grad_norm": 2.025585412979126,
1856
+ "learning_rate": 9.885342423303379e-06,
1857
+ "loss": 0.6237,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.8085430968726163,
1862
+ "grad_norm": 2.5337514877319336,
1863
+ "learning_rate": 9.730399752091726e-06,
1864
+ "loss": 0.7284,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.8115942028985508,
1869
+ "grad_norm": 2.5185277462005615,
1870
+ "learning_rate": 9.575457080880075e-06,
1871
+ "loss": 0.695,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.8146453089244852,
1876
+ "grad_norm": 3.0368494987487793,
1877
+ "learning_rate": 9.420514409668422e-06,
1878
+ "loss": 0.7291,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.8176964149504196,
1883
+ "grad_norm": 2.6141366958618164,
1884
+ "learning_rate": 9.265571738456771e-06,
1885
+ "loss": 0.6768,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.820747520976354,
1890
+ "grad_norm": 2.2215969562530518,
1891
+ "learning_rate": 9.11062906724512e-06,
1892
+ "loss": 0.6832,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.8237986270022883,
1897
+ "grad_norm": 3.0464236736297607,
1898
+ "learning_rate": 8.955686396033468e-06,
1899
+ "loss": 0.7362,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.8268497330282227,
1904
+ "grad_norm": 2.384838104248047,
1905
+ "learning_rate": 8.800743724821817e-06,
1906
+ "loss": 0.6501,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.8299008390541571,
1911
+ "grad_norm": 2.2411282062530518,
1912
+ "learning_rate": 8.645801053610164e-06,
1913
+ "loss": 0.6274,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.8329519450800915,
1918
+ "grad_norm": 2.8559658527374268,
1919
+ "learning_rate": 8.490858382398513e-06,
1920
+ "loss": 0.6282,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.8360030511060259,
1925
+ "grad_norm": 2.729321002960205,
1926
+ "learning_rate": 8.335915711186862e-06,
1927
+ "loss": 0.6966,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.8390541571319603,
1932
+ "grad_norm": 2.846073865890503,
1933
+ "learning_rate": 8.18097303997521e-06,
1934
+ "loss": 0.6925,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.8421052631578947,
1939
+ "grad_norm": 2.1397573947906494,
1940
+ "learning_rate": 8.026030368763559e-06,
1941
+ "loss": 0.6435,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.8451563691838292,
1946
+ "grad_norm": 3.3590445518493652,
1947
+ "learning_rate": 7.871087697551906e-06,
1948
+ "loss": 0.6592,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.8482074752097636,
1953
+ "grad_norm": 2.7317698001861572,
1954
+ "learning_rate": 7.716145026340255e-06,
1955
+ "loss": 0.6915,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.851258581235698,
1960
+ "grad_norm": 2.3746912479400635,
1961
+ "learning_rate": 7.561202355128602e-06,
1962
+ "loss": 0.7039,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.8543096872616324,
1967
+ "grad_norm": 3.0164999961853027,
1968
+ "learning_rate": 7.4062596839169505e-06,
1969
+ "loss": 0.7024,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.8573607932875668,
1974
+ "grad_norm": 3.2100493907928467,
1975
+ "learning_rate": 7.2513170127053e-06,
1976
+ "loss": 0.7137,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.8604118993135011,
1981
+ "grad_norm": 2.1263020038604736,
1982
+ "learning_rate": 7.096374341493647e-06,
1983
+ "loss": 0.6334,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.8634630053394355,
1988
+ "grad_norm": 2.614156484603882,
1989
+ "learning_rate": 6.941431670281996e-06,
1990
+ "loss": 0.7299,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.8665141113653699,
1995
+ "grad_norm": 4.311347961425781,
1996
+ "learning_rate": 6.786488999070343e-06,
1997
+ "loss": 0.6464,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.8695652173913043,
2002
+ "grad_norm": 2.2194840908050537,
2003
+ "learning_rate": 6.631546327858692e-06,
2004
+ "loss": 0.7055,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.8726163234172387,
2009
+ "grad_norm": 2.8160476684570312,
2010
+ "learning_rate": 6.476603656647041e-06,
2011
+ "loss": 0.7233,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.8756674294431731,
2016
+ "grad_norm": 1.9882564544677734,
2017
+ "learning_rate": 6.321660985435389e-06,
2018
+ "loss": 0.7041,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.8787185354691075,
2023
+ "grad_norm": 2.381114959716797,
2024
+ "learning_rate": 6.166718314223738e-06,
2025
+ "loss": 0.6916,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.881769641495042,
2030
+ "grad_norm": 2.911763906478882,
2031
+ "learning_rate": 6.011775643012086e-06,
2032
+ "loss": 0.6493,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.8848207475209764,
2037
+ "grad_norm": 2.830087900161743,
2038
+ "learning_rate": 5.856832971800434e-06,
2039
+ "loss": 0.6497,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.8878718535469108,
2044
+ "grad_norm": 2.609445333480835,
2045
+ "learning_rate": 5.701890300588782e-06,
2046
+ "loss": 0.6923,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.8909229595728452,
2051
+ "grad_norm": 2.1896908283233643,
2052
+ "learning_rate": 5.5469476293771305e-06,
2053
+ "loss": 0.6325,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.8939740655987796,
2058
+ "grad_norm": 3.2182352542877197,
2059
+ "learning_rate": 5.392004958165479e-06,
2060
+ "loss": 0.6613,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.897025171624714,
2065
+ "grad_norm": 2.7768335342407227,
2066
+ "learning_rate": 5.237062286953828e-06,
2067
+ "loss": 0.6944,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.9000762776506483,
2072
+ "grad_norm": 2.458332061767578,
2073
+ "learning_rate": 5.082119615742176e-06,
2074
+ "loss": 0.6689,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.9031273836765827,
2079
+ "grad_norm": 2.2689878940582275,
2080
+ "learning_rate": 4.927176944530524e-06,
2081
+ "loss": 0.6729,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.9061784897025171,
2086
+ "grad_norm": 3.256464719772339,
2087
+ "learning_rate": 4.772234273318872e-06,
2088
+ "loss": 0.6158,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.9092295957284515,
2093
+ "grad_norm": 3.0589096546173096,
2094
+ "learning_rate": 4.6172916021072205e-06,
2095
+ "loss": 0.7551,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.9122807017543859,
2100
+ "grad_norm": 2.630323648452759,
2101
+ "learning_rate": 4.4623489308955695e-06,
2102
+ "loss": 0.6235,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.9153318077803204,
2107
+ "grad_norm": 2.285128593444824,
2108
+ "learning_rate": 4.307406259683918e-06,
2109
+ "loss": 0.6948,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.9183829138062548,
2114
+ "grad_norm": 2.4126858711242676,
2115
+ "learning_rate": 4.152463588472266e-06,
2116
+ "loss": 0.6249,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.9214340198321892,
2121
+ "grad_norm": 2.4043056964874268,
2122
+ "learning_rate": 3.997520917260614e-06,
2123
+ "loss": 0.6822,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.9244851258581236,
2128
+ "grad_norm": 2.084949254989624,
2129
+ "learning_rate": 3.842578246048962e-06,
2130
+ "loss": 0.7345,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.927536231884058,
2135
+ "grad_norm": 2.251657247543335,
2136
+ "learning_rate": 3.68763557483731e-06,
2137
+ "loss": 0.6048,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.9305873379099924,
2142
+ "grad_norm": 2.20843505859375,
2143
+ "learning_rate": 3.532692903625659e-06,
2144
+ "loss": 0.6687,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.9336384439359268,
2149
+ "grad_norm": 2.692772150039673,
2150
+ "learning_rate": 3.3777502324140072e-06,
2151
+ "loss": 0.651,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.9366895499618612,
2156
+ "grad_norm": 2.778233766555786,
2157
+ "learning_rate": 3.2228075612023554e-06,
2158
+ "loss": 0.7709,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.9397406559877955,
2163
+ "grad_norm": 2.2121570110321045,
2164
+ "learning_rate": 3.0678648899907036e-06,
2165
+ "loss": 0.6741,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.9427917620137299,
2170
+ "grad_norm": 2.814641237258911,
2171
+ "learning_rate": 2.9129222187790522e-06,
2172
+ "loss": 0.6409,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.9458428680396643,
2177
+ "grad_norm": 2.183281660079956,
2178
+ "learning_rate": 2.7579795475674004e-06,
2179
+ "loss": 0.6192,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.9488939740655988,
2184
+ "grad_norm": 1.998976230621338,
2185
+ "learning_rate": 2.6030368763557486e-06,
2186
+ "loss": 0.5924,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.9519450800915332,
2191
+ "grad_norm": 2.7774434089660645,
2192
+ "learning_rate": 2.4480942051440968e-06,
2193
+ "loss": 0.7145,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.9549961861174676,
2198
+ "grad_norm": 2.510991334915161,
2199
+ "learning_rate": 2.293151533932445e-06,
2200
+ "loss": 0.6985,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.958047292143402,
2205
+ "grad_norm": 2.820533037185669,
2206
+ "learning_rate": 2.138208862720793e-06,
2207
+ "loss": 0.673,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.9610983981693364,
2212
+ "grad_norm": 3.7463274002075195,
2213
+ "learning_rate": 1.9832661915091418e-06,
2214
+ "loss": 0.6753,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.9641495041952708,
2219
+ "grad_norm": 2.6098906993865967,
2220
+ "learning_rate": 1.82832352029749e-06,
2221
+ "loss": 0.6077,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.9672006102212052,
2226
+ "grad_norm": 3.7235538959503174,
2227
+ "learning_rate": 1.6733808490858381e-06,
2228
+ "loss": 0.6528,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.9702517162471396,
2233
+ "grad_norm": 2.551973342895508,
2234
+ "learning_rate": 1.5184381778741865e-06,
2235
+ "loss": 0.7123,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.973302822273074,
2240
+ "grad_norm": 2.60445237159729,
2241
+ "learning_rate": 1.363495506662535e-06,
2242
+ "loss": 0.6368,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.9763539282990084,
2247
+ "grad_norm": 2.7576358318328857,
2248
+ "learning_rate": 1.2085528354508833e-06,
2249
+ "loss": 0.6172,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.9794050343249427,
2254
+ "grad_norm": 2.23207426071167,
2255
+ "learning_rate": 1.0536101642392315e-06,
2256
+ "loss": 0.6227,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.9824561403508771,
2261
+ "grad_norm": 3.0700480937957764,
2262
+ "learning_rate": 8.986674930275798e-07,
2263
+ "loss": 0.7168,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.9855072463768116,
2268
+ "grad_norm": 2.6852805614471436,
2269
+ "learning_rate": 7.437248218159281e-07,
2270
+ "loss": 0.6322,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.988558352402746,
2275
+ "grad_norm": 2.6967718601226807,
2276
+ "learning_rate": 5.887821506042764e-07,
2277
+ "loss": 0.6357,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.9916094584286804,
2282
+ "grad_norm": 3.2857532501220703,
2283
+ "learning_rate": 4.3383947939262475e-07,
2284
+ "loss": 0.7225,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.9946605644546148,
2289
+ "grad_norm": 2.565335750579834,
2290
+ "learning_rate": 2.788968081809731e-07,
2291
+ "loss": 0.6709,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.9977116704805492,
2296
+ "grad_norm": 3.099731922149658,
2297
+ "learning_rate": 1.2395413696932136e-07,
2298
+ "loss": 0.7549,
2299
+ "step": 3270
2300
+ }
2301
+ ],
2302
+ "logging_steps": 10,
2303
+ "max_steps": 3277,
2304
+ "num_input_tokens_seen": 0,
2305
+ "num_train_epochs": 1,
2306
+ "save_steps": 500,
2307
+ "stateful_callbacks": {
2308
+ "TrainerControl": {
2309
+ "args": {
2310
+ "should_epoch_stop": false,
2311
+ "should_evaluate": false,
2312
+ "should_log": false,
2313
+ "should_save": true,
2314
+ "should_training_stop": true
2315
+ },
2316
+ "attributes": {}
2317
+ }
2318
+ },
2319
+ "total_flos": 1.2252825778126848e+16,
2320
+ "train_batch_size": 2,
2321
+ "trial_name": null,
2322
+ "trial_params": null
2323
+ }
checkpoint-3277/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b02cca399c2f404f3c49402159bd0a9037c91c59db2a0b02996f6dda4b3b8a
3
+ size 5304
checkpoint-3277/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "CodeGenForCausalLM"
5
+ ],
6
+ "attn_pdrop": 0.0,
7
+ "bos_token_id": 1,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": 50256,
10
+ "gradient_checkpointing": false,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "codegen",
14
+ "n_ctx": 2048,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 20,
19
+ "n_positions": 2048,
20
+ "pad_token_id": 50256,
21
+ "resid_pdrop": 0.0,
22
+ "rotary_dim": 32,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50,
33
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.51.3",
40
+ "use_cache": true,
41
+ "vocab_size": 51200
42
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.51.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2743b83bd34964e6bf8daedc2f860b4a30c339c56695b6c8f9a4873dd99301a
3
+ size 1426867192
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": " ",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": " ",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": " ",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": " ",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": " ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": " ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": " ",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": " ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": " ",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": " ",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": " ",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": " ",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": " ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": " ",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": " ",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": " ",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": " ",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": " ",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": " ",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50276": {
166
+ "content": " ",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50277": {
174
+ "content": " ",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50278": {
182
+ "content": " ",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50279": {
190
+ "content": " ",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50280": {
198
+ "content": " ",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50281": {
206
+ "content": " ",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50282": {
214
+ "content": " ",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50283": {
222
+ "content": " ",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50284": {
230
+ "content": " ",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50285": {
238
+ "content": " ",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50286": {
246
+ "content": " ",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50287": {
254
+ "content": "\t\t\t\t\t\t\t\t\t",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50288": {
262
+ "content": "\t\t\t\t\t\t\t\t",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50289": {
270
+ "content": "\t\t\t\t\t\t\t",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50290": {
278
+ "content": "\t\t\t\t\t\t",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50291": {
286
+ "content": "\t\t\t\t\t",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50292": {
294
+ "content": "\t\t\t\t",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50293": {
302
+ "content": "\t\t\t",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50294": {
310
+ "content": "\t\t",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ }
317
+ },
318
+ "bos_token": "<|endoftext|>",
319
+ "clean_up_tokenization_spaces": false,
320
+ "eos_token": "<|endoftext|>",
321
+ "errors": "replace",
322
+ "extra_special_tokens": {},
323
+ "model_max_length": 2048,
324
+ "pad_token": "<|endoftext|>",
325
+ "return_token_type_ids": false,
326
+ "tokenizer_class": "CodeGenTokenizer",
327
+ "unk_token": "<|endoftext|>"
328
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff