JackBosco commited on
Commit
ae5cb33
·
1 Parent(s): 5acec7a

unpacked checkpoint-1750

Browse files
README.md CHANGED
@@ -1,7 +1,40 @@
1
  ---
2
- license: mit
3
- language:
4
- - en
5
- base_model: microsoft/phi-2
6
- adapter_for: microsoft/phi-2
7
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - _load_in_8bit: False
10
+ - _load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: float32
18
+ - bnb_4bit_quant_storage: uint8
19
+ - load_in_4bit: True
20
+ - load_in_8bit: False
21
+
22
+ The following `bitsandbytes` quantization config was used during training:
23
+ - quant_method: bitsandbytes
24
+ - _load_in_8bit: False
25
+ - _load_in_4bit: True
26
+ - llm_int8_threshold: 6.0
27
+ - llm_int8_skip_modules: None
28
+ - llm_int8_enable_fp32_cpu_offload: False
29
+ - llm_int8_has_fp16_weight: False
30
+ - bnb_4bit_quant_type: nf4
31
+ - bnb_4bit_use_double_quant: True
32
+ - bnb_4bit_compute_dtype: float32
33
+ - bnb_4bit_quant_storage: uint8
34
+ - load_in_4bit: True
35
+ - load_in_8bit: False
36
+ ### Framework versions
37
+
38
+ - PEFT 0.4.0
39
+
40
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "microsoft/phi-2",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "dense",
19
+ "k_proj",
20
+ "q_proj",
21
+ "fc1",
22
+ "fc2"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0ae375bc8d8c3d6b21a33c1109373b5b7246e742e707abef2ef9a8469a6325
3
+ size 377538512
adapter_model/README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - _load_in_8bit: False
10
+ - _load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: float32
18
+ - bnb_4bit_quant_storage: uint8
19
+ - load_in_4bit: True
20
+ - load_in_8bit: False
21
+
22
+ The following `bitsandbytes` quantization config was used during training:
23
+ - quant_method: bitsandbytes
24
+ - _load_in_8bit: False
25
+ - _load_in_4bit: True
26
+ - llm_int8_threshold: 6.0
27
+ - llm_int8_skip_modules: None
28
+ - llm_int8_enable_fp32_cpu_offload: False
29
+ - llm_int8_has_fp16_weight: False
30
+ - bnb_4bit_quant_type: nf4
31
+ - bnb_4bit_use_double_quant: True
32
+ - bnb_4bit_compute_dtype: float32
33
+ - bnb_4bit_quant_storage: uint8
34
+ - load_in_4bit: True
35
+ - load_in_8bit: False
36
+
37
+ The following `bitsandbytes` quantization config was used during training:
38
+ - quant_method: bitsandbytes
39
+ - _load_in_8bit: False
40
+ - _load_in_4bit: True
41
+ - llm_int8_threshold: 6.0
42
+ - llm_int8_skip_modules: None
43
+ - llm_int8_enable_fp32_cpu_offload: False
44
+ - llm_int8_has_fp16_weight: False
45
+ - bnb_4bit_quant_type: nf4
46
+ - bnb_4bit_use_double_quant: True
47
+ - bnb_4bit_compute_dtype: float32
48
+ - bnb_4bit_quant_storage: uint8
49
+ - load_in_4bit: True
50
+ - load_in_8bit: False
51
+ ### Framework versions
52
+
53
+ - PEFT 0.4.0
54
+ - PEFT 0.4.0
55
+
56
+ - PEFT 0.4.0
adapter_model/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "microsoft/phi-2",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "dense",
19
+ "k_proj",
20
+ "q_proj",
21
+ "fc1",
22
+ "fc2"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b21ec176d92c27df47667649aff9ecf6410a4e9d2591a44d30ea1506ee2cd62
3
+ size 377625610
added_tokens.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "[PAD]": 50295
41
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf111a8319d37f040010c70e2976f2340e39d52e12b9fee2467fc636d83d9473
3
+ size 755212730
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d7de1a1afdd2358e7ef8901aa2e2b8d27f97b598373d92789f1b1346228917
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c637c522eb7be4f20db9bf30934ffbcff195e29b30bd9e03e47a7a09113597c
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50295": {
318
+ "content": "[PAD]",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ }
325
+ },
326
+ "bos_token": "<|endoftext|>",
327
+ "clean_up_tokenization_spaces": true,
328
+ "eos_token": "<|endoftext|>",
329
+ "errors": "replace",
330
+ "model_max_length": 2048,
331
+ "pad_token": "[PAD]",
332
+ "padding_side": "right",
333
+ "tokenizer_class": "CodeGenTokenizer",
334
+ "unk_token": "<|endoftext|>"
335
+ }
trainer_state.json ADDED
@@ -0,0 +1,1246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.121212121212121,
5
+ "eval_steps": 500,
6
+ "global_step": 1750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07,
13
+ "grad_norm": 0.03181853145360947,
14
+ "learning_rate": 0.0002,
15
+ "loss": 0.0117,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.14,
20
+ "grad_norm": 0.03301709145307541,
21
+ "learning_rate": 0.0002,
22
+ "loss": 0.0061,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.21,
27
+ "grad_norm": 0.12774519622325897,
28
+ "learning_rate": 0.0002,
29
+ "loss": 0.008,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.28,
34
+ "grad_norm": 0.189144566655159,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.0167,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.35,
41
+ "grad_norm": 0.15458767116069794,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.0116,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.42,
48
+ "grad_norm": 0.23779332637786865,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.0124,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.48,
55
+ "grad_norm": 0.17651872336864471,
56
+ "learning_rate": 0.0002,
57
+ "loss": 0.0081,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.55,
62
+ "grad_norm": 0.2730236053466797,
63
+ "learning_rate": 0.0002,
64
+ "loss": 0.0196,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.62,
69
+ "grad_norm": 0.17761944234371185,
70
+ "learning_rate": 0.0002,
71
+ "loss": 0.0123,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.69,
76
+ "grad_norm": 0.02090522274374962,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.008,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.76,
83
+ "grad_norm": 0.19568940997123718,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.0137,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.83,
90
+ "grad_norm": 0.09299980849027634,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.0179,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.9,
97
+ "grad_norm": 0.039965927600860596,
98
+ "learning_rate": 0.0002,
99
+ "loss": 0.0094,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.97,
104
+ "grad_norm": 0.05453222617506981,
105
+ "learning_rate": 0.0002,
106
+ "loss": 0.0082,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.04,
111
+ "grad_norm": 0.08042442053556442,
112
+ "learning_rate": 0.0002,
113
+ "loss": 0.0144,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.11,
118
+ "grad_norm": 0.066365547478199,
119
+ "learning_rate": 0.0002,
120
+ "loss": 0.0106,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.18,
125
+ "grad_norm": 0.06514760106801987,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.0104,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 1.25,
132
+ "grad_norm": 0.019024183973670006,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.0088,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.32,
139
+ "grad_norm": 0.1361686736345291,
140
+ "learning_rate": 0.0002,
141
+ "loss": 0.013,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.39,
146
+ "grad_norm": 0.07207699865102768,
147
+ "learning_rate": 0.0002,
148
+ "loss": 0.0093,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 1.45,
153
+ "grad_norm": 0.03459335118532181,
154
+ "learning_rate": 0.0002,
155
+ "loss": 0.0106,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 1.52,
160
+ "grad_norm": 0.03898346796631813,
161
+ "learning_rate": 0.0002,
162
+ "loss": 0.0103,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 1.59,
167
+ "grad_norm": 0.17066022753715515,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.0154,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 1.66,
174
+ "grad_norm": 0.11916259676218033,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.0054,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.73,
181
+ "grad_norm": 0.1582280397415161,
182
+ "learning_rate": 0.0002,
183
+ "loss": 0.0058,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.8,
188
+ "grad_norm": 0.11945289373397827,
189
+ "learning_rate": 0.0002,
190
+ "loss": 0.0168,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 1.87,
195
+ "grad_norm": 0.11030268669128418,
196
+ "learning_rate": 0.0002,
197
+ "loss": 0.0062,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.94,
202
+ "grad_norm": 0.19329409301280975,
203
+ "learning_rate": 0.0002,
204
+ "loss": 0.0107,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 2.01,
209
+ "grad_norm": 0.19244401156902313,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.0079,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 2.08,
216
+ "grad_norm": 0.17133064568042755,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.0121,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 2.15,
223
+ "grad_norm": 0.2458006590604782,
224
+ "learning_rate": 0.0002,
225
+ "loss": 0.0099,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 2.22,
230
+ "grad_norm": 0.04351121559739113,
231
+ "learning_rate": 0.0002,
232
+ "loss": 0.0151,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 2.29,
237
+ "grad_norm": 0.11653552204370499,
238
+ "learning_rate": 0.0002,
239
+ "loss": 0.0215,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 2.35,
244
+ "grad_norm": 0.17622575163841248,
245
+ "learning_rate": 0.0002,
246
+ "loss": 0.0113,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 2.42,
251
+ "grad_norm": 0.06326813995838165,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.0088,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 2.49,
258
+ "grad_norm": 0.05258811265230179,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.0209,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 2.56,
265
+ "grad_norm": 0.14271198213100433,
266
+ "learning_rate": 0.0002,
267
+ "loss": 0.0165,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 2.63,
272
+ "grad_norm": 0.2666095495223999,
273
+ "learning_rate": 0.0002,
274
+ "loss": 0.0074,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 2.7,
279
+ "grad_norm": 0.33327990770339966,
280
+ "learning_rate": 0.0002,
281
+ "loss": 0.0119,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 2.77,
286
+ "grad_norm": 0.16939572989940643,
287
+ "learning_rate": 0.0002,
288
+ "loss": 0.0198,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 2.84,
293
+ "grad_norm": 0.15744081139564514,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.0128,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 2.91,
300
+ "grad_norm": 0.08405949920415878,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.0097,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 2.98,
307
+ "grad_norm": 0.19052201509475708,
308
+ "learning_rate": 0.0002,
309
+ "loss": 0.0044,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 3.05,
314
+ "grad_norm": 0.07543158531188965,
315
+ "learning_rate": 0.0002,
316
+ "loss": 0.013,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 3.12,
321
+ "grad_norm": 0.13838960230350494,
322
+ "learning_rate": 0.0002,
323
+ "loss": 0.0128,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 3.19,
328
+ "grad_norm": 0.1489538550376892,
329
+ "learning_rate": 0.0002,
330
+ "loss": 0.0107,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 3.26,
335
+ "grad_norm": 0.14335639774799347,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.0095,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 3.32,
342
+ "grad_norm": 0.07466119527816772,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.0124,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 3.39,
349
+ "grad_norm": 0.175484761595726,
350
+ "learning_rate": 0.0002,
351
+ "loss": 0.012,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 3.46,
356
+ "grad_norm": 0.15107689797878265,
357
+ "learning_rate": 0.0002,
358
+ "loss": 0.0091,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 3.53,
363
+ "grad_norm": 0.18606631457805634,
364
+ "learning_rate": 0.0002,
365
+ "loss": 0.0141,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 3.6,
370
+ "grad_norm": 0.12696044147014618,
371
+ "learning_rate": 0.0002,
372
+ "loss": 0.0125,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 3.67,
377
+ "grad_norm": 0.11616098135709763,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.0129,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 3.74,
384
+ "grad_norm": 0.3160938620567322,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.0085,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 3.81,
391
+ "grad_norm": 0.08054643124341965,
392
+ "learning_rate": 0.0002,
393
+ "loss": 0.0163,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 3.88,
398
+ "grad_norm": 0.06550751626491547,
399
+ "learning_rate": 0.0002,
400
+ "loss": 0.0133,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 3.95,
405
+ "grad_norm": 0.04109380394220352,
406
+ "learning_rate": 0.0002,
407
+ "loss": 0.0085,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 4.02,
412
+ "grad_norm": 0.09408660233020782,
413
+ "learning_rate": 0.0002,
414
+ "loss": 0.0127,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 4.09,
419
+ "grad_norm": 0.2768724858760834,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.0114,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 4.16,
426
+ "grad_norm": 0.02514655888080597,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.0071,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 4.23,
433
+ "grad_norm": 0.26696744561195374,
434
+ "learning_rate": 0.0002,
435
+ "loss": 0.0066,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 4.29,
440
+ "grad_norm": 0.19320635497570038,
441
+ "learning_rate": 0.0002,
442
+ "loss": 0.0135,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 4.36,
447
+ "grad_norm": 0.08179598301649094,
448
+ "learning_rate": 0.0002,
449
+ "loss": 0.0067,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 4.43,
454
+ "grad_norm": 0.30935776233673096,
455
+ "learning_rate": 0.0002,
456
+ "loss": 0.0083,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 4.5,
461
+ "grad_norm": 0.21668316423892975,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.0144,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 4.57,
468
+ "grad_norm": 0.18344347178936005,
469
+ "learning_rate": 0.0002,
470
+ "loss": 0.0131,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 4.64,
475
+ "grad_norm": 0.31796884536743164,
476
+ "learning_rate": 0.0002,
477
+ "loss": 0.0101,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 4.71,
482
+ "grad_norm": 0.04909071326255798,
483
+ "learning_rate": 0.0002,
484
+ "loss": 0.0108,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 4.78,
489
+ "grad_norm": 0.08679769188165665,
490
+ "learning_rate": 0.0002,
491
+ "loss": 0.0197,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 4.85,
496
+ "grad_norm": 0.05100365728139877,
497
+ "learning_rate": 0.0002,
498
+ "loss": 0.013,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 4.92,
503
+ "grad_norm": 0.08279485255479813,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.0062,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 4.99,
510
+ "grad_norm": 0.05374281853437424,
511
+ "learning_rate": 0.0002,
512
+ "loss": 0.0101,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 5.06,
517
+ "grad_norm": 0.10421579331159592,
518
+ "learning_rate": 0.0002,
519
+ "loss": 0.0115,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 5.13,
524
+ "grad_norm": 0.022278541699051857,
525
+ "learning_rate": 0.0002,
526
+ "loss": 0.0071,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 5.19,
531
+ "grad_norm": 0.014159414917230606,
532
+ "learning_rate": 0.0002,
533
+ "loss": 0.0076,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 5.26,
538
+ "grad_norm": 0.15521597862243652,
539
+ "learning_rate": 0.0002,
540
+ "loss": 0.0122,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 5.33,
545
+ "grad_norm": 0.0737166702747345,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.0077,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 5.4,
552
+ "grad_norm": 0.03631032258272171,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.0051,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 5.47,
559
+ "grad_norm": 0.11575569957494736,
560
+ "learning_rate": 0.0002,
561
+ "loss": 0.0057,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 5.54,
566
+ "grad_norm": 0.13107435405254364,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.0104,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 5.61,
573
+ "grad_norm": 0.11719845235347748,
574
+ "learning_rate": 0.0002,
575
+ "loss": 0.004,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 5.68,
580
+ "grad_norm": 0.024636002257466316,
581
+ "learning_rate": 0.0002,
582
+ "loss": 0.0048,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 5.75,
587
+ "grad_norm": 0.05650615319609642,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.009,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 5.82,
594
+ "grad_norm": 0.11958178132772446,
595
+ "learning_rate": 0.0002,
596
+ "loss": 0.0096,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 5.89,
601
+ "grad_norm": 0.3462698757648468,
602
+ "learning_rate": 0.0002,
603
+ "loss": 0.0079,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 5.96,
608
+ "grad_norm": 0.07302005589008331,
609
+ "learning_rate": 0.0002,
610
+ "loss": 0.007,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 6.03,
615
+ "grad_norm": 0.24322502315044403,
616
+ "learning_rate": 0.0002,
617
+ "loss": 0.0118,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 6.1,
622
+ "grad_norm": 0.024749072268605232,
623
+ "learning_rate": 0.0002,
624
+ "loss": 0.0076,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 6.16,
629
+ "grad_norm": 0.03444315120577812,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.0056,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 6.23,
636
+ "grad_norm": 0.36686971783638,
637
+ "learning_rate": 0.0002,
638
+ "loss": 0.0066,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 6.3,
643
+ "grad_norm": 0.25445130467414856,
644
+ "learning_rate": 0.0002,
645
+ "loss": 0.0114,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 6.37,
650
+ "grad_norm": 0.09220030158758163,
651
+ "learning_rate": 0.0002,
652
+ "loss": 0.0076,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 6.44,
657
+ "grad_norm": 0.2540806531906128,
658
+ "learning_rate": 0.0002,
659
+ "loss": 0.0102,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 6.51,
664
+ "grad_norm": 0.1557808369398117,
665
+ "learning_rate": 0.0002,
666
+ "loss": 0.0074,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 6.58,
671
+ "grad_norm": 0.05450637638568878,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.0086,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 6.65,
678
+ "grad_norm": 0.04527583718299866,
679
+ "learning_rate": 0.0002,
680
+ "loss": 0.0038,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 6.72,
685
+ "grad_norm": 0.11897213757038116,
686
+ "learning_rate": 0.0002,
687
+ "loss": 0.0034,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 6.79,
692
+ "grad_norm": 0.10568214952945709,
693
+ "learning_rate": 0.0002,
694
+ "loss": 0.0158,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 6.86,
699
+ "grad_norm": 0.07142580300569534,
700
+ "learning_rate": 0.0002,
701
+ "loss": 0.0077,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 6.93,
706
+ "grad_norm": 0.04490859434008598,
707
+ "learning_rate": 0.0002,
708
+ "loss": 0.0061,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 7.0,
713
+ "grad_norm": 0.030944261699914932,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.0049,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 7.06,
720
+ "grad_norm": 0.23092027008533478,
721
+ "learning_rate": 0.0002,
722
+ "loss": 0.012,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 7.13,
727
+ "grad_norm": 0.07528150826692581,
728
+ "learning_rate": 0.0002,
729
+ "loss": 0.005,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 7.2,
734
+ "grad_norm": 0.011815500445663929,
735
+ "learning_rate": 0.0002,
736
+ "loss": 0.0074,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 7.27,
741
+ "grad_norm": 0.08818691223859787,
742
+ "learning_rate": 0.0002,
743
+ "loss": 0.007,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 7.34,
748
+ "grad_norm": 0.013633369468152523,
749
+ "learning_rate": 0.0002,
750
+ "loss": 0.0069,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 7.41,
755
+ "grad_norm": 0.014418787322938442,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.0071,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 7.48,
762
+ "grad_norm": 0.12523452937602997,
763
+ "learning_rate": 0.0002,
764
+ "loss": 0.0072,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 7.55,
769
+ "grad_norm": 0.13877837359905243,
770
+ "learning_rate": 0.0002,
771
+ "loss": 0.0097,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 7.62,
776
+ "grad_norm": 0.24948883056640625,
777
+ "learning_rate": 0.0002,
778
+ "loss": 0.006,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 7.69,
783
+ "grad_norm": 0.021404897794127464,
784
+ "learning_rate": 0.0002,
785
+ "loss": 0.0038,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 7.76,
790
+ "grad_norm": 0.1368672251701355,
791
+ "learning_rate": 0.0002,
792
+ "loss": 0.0059,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 7.83,
797
+ "grad_norm": 0.03312192112207413,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.007,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 7.9,
804
+ "grad_norm": 0.032206010073423386,
805
+ "learning_rate": 0.0002,
806
+ "loss": 0.0021,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 7.97,
811
+ "grad_norm": 0.03399817645549774,
812
+ "learning_rate": 0.0002,
813
+ "loss": 0.0045,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 8.03,
818
+ "grad_norm": 0.18925493955612183,
819
+ "learning_rate": 0.0002,
820
+ "loss": 0.0093,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 8.1,
825
+ "grad_norm": 0.1772252917289734,
826
+ "learning_rate": 0.0002,
827
+ "loss": 0.003,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 8.17,
832
+ "grad_norm": 0.007787138223648071,
833
+ "learning_rate": 0.0002,
834
+ "loss": 0.0034,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 8.24,
839
+ "grad_norm": 0.01511111855506897,
840
+ "learning_rate": 0.0002,
841
+ "loss": 0.002,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 8.31,
846
+ "grad_norm": 0.03841459006071091,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.0072,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 8.38,
853
+ "grad_norm": 0.0446455255150795,
854
+ "learning_rate": 0.0002,
855
+ "loss": 0.0066,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 8.45,
860
+ "grad_norm": 0.050412483513355255,
861
+ "learning_rate": 0.0002,
862
+ "loss": 0.0038,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 8.52,
867
+ "grad_norm": 0.05555203557014465,
868
+ "learning_rate": 0.0002,
869
+ "loss": 0.0088,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 8.59,
874
+ "grad_norm": 0.07313160598278046,
875
+ "learning_rate": 0.0002,
876
+ "loss": 0.0096,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 8.66,
881
+ "grad_norm": 0.06051426753401756,
882
+ "learning_rate": 0.0002,
883
+ "loss": 0.0176,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 8.73,
888
+ "grad_norm": 0.052646949887275696,
889
+ "learning_rate": 0.0002,
890
+ "loss": 0.0038,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 8.8,
895
+ "grad_norm": 0.05086590349674225,
896
+ "learning_rate": 0.0002,
897
+ "loss": 0.0099,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 8.87,
902
+ "grad_norm": 0.07178761065006256,
903
+ "learning_rate": 0.0002,
904
+ "loss": 0.0074,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 8.94,
909
+ "grad_norm": 0.009413959458470345,
910
+ "learning_rate": 0.0002,
911
+ "loss": 0.0064,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 9.0,
916
+ "grad_norm": 0.10240955650806427,
917
+ "learning_rate": 0.0002,
918
+ "loss": 0.0143,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 9.07,
923
+ "grad_norm": 0.01897740177810192,
924
+ "learning_rate": 0.0002,
925
+ "loss": 0.0074,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 9.14,
930
+ "grad_norm": 0.022444820031523705,
931
+ "learning_rate": 0.0002,
932
+ "loss": 0.0062,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 9.21,
937
+ "grad_norm": 0.0814051404595375,
938
+ "learning_rate": 0.0002,
939
+ "loss": 0.0061,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 9.28,
944
+ "grad_norm": 0.18547141551971436,
945
+ "learning_rate": 0.0002,
946
+ "loss": 0.0112,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 9.35,
951
+ "grad_norm": 0.022853808477520943,
952
+ "learning_rate": 0.0002,
953
+ "loss": 0.0082,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 9.42,
958
+ "grad_norm": 0.14588187634944916,
959
+ "learning_rate": 0.0002,
960
+ "loss": 0.0068,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 9.49,
965
+ "grad_norm": 0.10406211018562317,
966
+ "learning_rate": 0.0002,
967
+ "loss": 0.0045,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 9.56,
972
+ "grad_norm": 0.02087993547320366,
973
+ "learning_rate": 0.0002,
974
+ "loss": 0.0144,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 9.63,
979
+ "grad_norm": 0.015244157053530216,
980
+ "learning_rate": 0.0002,
981
+ "loss": 0.0044,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 9.7,
986
+ "grad_norm": 0.030207380652427673,
987
+ "learning_rate": 0.0002,
988
+ "loss": 0.0062,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 9.77,
993
+ "grad_norm": 0.17009080946445465,
994
+ "learning_rate": 0.0002,
995
+ "loss": 0.0113,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 9.84,
1000
+ "grad_norm": 0.11179855465888977,
1001
+ "learning_rate": 0.0002,
1002
+ "loss": 0.0095,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 9.9,
1007
+ "grad_norm": 0.07035847008228302,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 0.0051,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 9.97,
1014
+ "grad_norm": 0.2190101593732834,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 0.0058,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 10.04,
1021
+ "grad_norm": 0.043730515986680984,
1022
+ "learning_rate": 0.0002,
1023
+ "loss": 0.0096,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 10.11,
1028
+ "grad_norm": 0.05817865580320358,
1029
+ "learning_rate": 0.0002,
1030
+ "loss": 0.0084,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 10.18,
1035
+ "grad_norm": 0.26322343945503235,
1036
+ "learning_rate": 0.0002,
1037
+ "loss": 0.0069,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 10.25,
1042
+ "grad_norm": 0.0707869678735733,
1043
+ "learning_rate": 0.0002,
1044
+ "loss": 0.0063,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 10.32,
1049
+ "grad_norm": 0.06895614415407181,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 0.0107,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 10.39,
1056
+ "grad_norm": 0.014940924942493439,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 0.006,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 10.46,
1063
+ "grad_norm": 0.12346550822257996,
1064
+ "learning_rate": 0.0002,
1065
+ "loss": 0.0101,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 10.53,
1070
+ "grad_norm": 0.06773683428764343,
1071
+ "learning_rate": 0.0002,
1072
+ "loss": 0.0108,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 10.6,
1077
+ "grad_norm": 0.08521382510662079,
1078
+ "learning_rate": 0.0002,
1079
+ "loss": 0.0088,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 10.67,
1084
+ "grad_norm": 0.3153349459171295,
1085
+ "learning_rate": 0.0002,
1086
+ "loss": 0.0113,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 10.74,
1091
+ "grad_norm": 0.32351627945899963,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 0.0095,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 10.81,
1098
+ "grad_norm": 0.1824280321598053,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 0.0163,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 10.87,
1105
+ "grad_norm": 0.1012108325958252,
1106
+ "learning_rate": 0.0002,
1107
+ "loss": 0.0078,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 10.94,
1112
+ "grad_norm": 0.12629801034927368,
1113
+ "learning_rate": 0.0002,
1114
+ "loss": 0.0086,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 11.01,
1119
+ "grad_norm": 0.0864088237285614,
1120
+ "learning_rate": 0.0002,
1121
+ "loss": 0.0104,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 11.08,
1126
+ "grad_norm": 0.09980332106351852,
1127
+ "learning_rate": 0.0002,
1128
+ "loss": 0.0082,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 11.15,
1133
+ "grad_norm": 0.3955361545085907,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 0.0161,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 11.22,
1140
+ "grad_norm": 0.3551037013530731,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 0.0105,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 11.29,
1147
+ "grad_norm": 0.1988571435213089,
1148
+ "learning_rate": 0.0002,
1149
+ "loss": 0.013,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 11.36,
1154
+ "grad_norm": 0.09209605306386948,
1155
+ "learning_rate": 0.0002,
1156
+ "loss": 0.009,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 11.43,
1161
+ "grad_norm": 0.08203499764204025,
1162
+ "learning_rate": 0.0002,
1163
+ "loss": 0.0118,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 11.5,
1168
+ "grad_norm": 0.05315827578306198,
1169
+ "learning_rate": 0.0002,
1170
+ "loss": 0.0074,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 11.57,
1175
+ "grad_norm": 0.06285399943590164,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 0.014,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 11.64,
1182
+ "grad_norm": 0.2484624832868576,
1183
+ "learning_rate": 0.0002,
1184
+ "loss": 0.0154,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 11.71,
1189
+ "grad_norm": 0.2875213623046875,
1190
+ "learning_rate": 0.0002,
1191
+ "loss": 0.0061,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 11.77,
1196
+ "grad_norm": 0.043303802609443665,
1197
+ "learning_rate": 0.0002,
1198
+ "loss": 0.0096,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 11.84,
1203
+ "grad_norm": 0.1575409173965454,
1204
+ "learning_rate": 0.0002,
1205
+ "loss": 0.0129,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 11.91,
1210
+ "grad_norm": 0.07893040031194687,
1211
+ "learning_rate": 0.0002,
1212
+ "loss": 0.0061,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 11.98,
1217
+ "grad_norm": 0.18039758503437042,
1218
+ "learning_rate": 0.0002,
1219
+ "loss": 0.0118,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 12.05,
1224
+ "grad_norm": 0.07571464776992798,
1225
+ "learning_rate": 0.0002,
1226
+ "loss": 0.0135,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 12.12,
1231
+ "grad_norm": 0.3126212954521179,
1232
+ "learning_rate": 0.0002,
1233
+ "loss": 0.0086,
1234
+ "step": 1750
1235
+ }
1236
+ ],
1237
+ "logging_steps": 10,
1238
+ "max_steps": 1750,
1239
+ "num_input_tokens_seen": 0,
1240
+ "num_train_epochs": 13,
1241
+ "save_steps": 250,
1242
+ "total_flos": 2.123929865873141e+16,
1243
+ "train_batch_size": 1,
1244
+ "trial_name": null,
1245
+ "trial_params": null
1246
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4e710ea7ef905109b2e9384a1426f31c8ad63bacf851c8c6262199e9377bb5
3
+ size 6968
vocab.json ADDED
The diff for this file is too large to render. See raw diff