Ritvik19 commited on
Commit
a2d8bbc
1 Parent(s): f487a64

Upload 15 files

Browse files
README.md CHANGED
@@ -1,3 +1,52 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ base_model: microsoft/phi-1_5
8
+ datasets:
9
+ - HuggingFaceH4/ultrachat_200k
10
+ model-index:
11
+ - name: zephyr-phi-1_5-sft-qlora
12
+ results: []
13
+ ---
14
+
15
+ **Note**: This model card has been generated automatically according to the information the Trainer had access to.
16
+ Visit the [model card](https://ritvik19.github.io/zephyr-mini/) to see the full description.
17
+
18
+ # zephyr-phi-1_5-sft-qlora
19
+
20
+ This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the HuggingFaceH4/ultrachat_200k dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.3434
23
+
24
+ ### Training hyperparameters
25
+
26
+ The following hyperparameters were used during training:
27
+ - learning_rate: 0.0002
28
+ - train_batch_size: 1
29
+ - eval_batch_size: 1
30
+ - seed: 42
31
+ - distributed_type: multi-GPU
32
+ - gradient_accumulation_steps: 128
33
+ - total_train_batch_size: 128
34
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
35
+ - lr_scheduler_type: cosine
36
+ - lr_scheduler_warmup_ratio: 0.1
37
+ - num_epochs: 1
38
+
39
+ ### Training results
40
+
41
+ | Training Loss | Epoch | Step | Validation Loss |
42
+ |:-------------:|:------:|:----:|:---------------:|
43
+ | 1.3423 | 0.9998 | 999 | 1.3434 |
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - PEFT 0.7.1
49
+ - Transformers 4.40.1
50
+ - Pytorch 2.1.2+cu121
51
+ - Datasets 2.19.0
52
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "v_proj",
24
+ "o_proj",
25
+ "up_proj",
26
+ "q_proj",
27
+ "down_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47acc619d6bf0cda08002d92dc906b4a593ede4291b29f8b836ba832c01081d7
3
+ size 9456424
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
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99981234753237,
3
+ "eval_loss": 1.343445897102356,
4
+ "eval_runtime": 1996.3113,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 7.089,
7
+ "eval_steps_per_second": 7.089,
8
+ "total_flos": 2.0711686751461048e+18,
9
+ "train_loss": 0.052138939037456644,
10
+ "train_runtime": 4093.6241,
11
+ "train_samples": 207864,
12
+ "train_samples_per_second": 31.243,
13
+ "train_steps_per_second": 0.244
14
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-1_5",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": null,
10
+ "hidden_act": "gelu_new",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "phi",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 32,
20
+ "partial_rotary_factor": 0.5,
21
+ "qk_layernorm": false,
22
+ "resid_pdrop": 0.0,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.40.1",
28
+ "use_cache": true,
29
+ "vocab_size": 51200
30
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99981234753237,
3
+ "eval_loss": 1.343445897102356,
4
+ "eval_runtime": 1996.3113,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 7.089,
7
+ "eval_steps_per_second": 7.089
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,326 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
319
+ "clean_up_tokenization_spaces": true,
320
+ "eos_token": "<|endoftext|>",
321
+ "model_max_length": 2048,
322
+ "pad_token": "<|endoftext|>",
323
+ "return_token_type_ids": false,
324
+ "tokenizer_class": "CodeGenTokenizer",
325
+ "unk_token": "<|endoftext|>"
326
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.99981234753237,
3
+ "total_flos": 2.0711686751461048e+18,
4
+ "train_loss": 0.052138939037456644,
5
+ "train_runtime": 4093.6241,
6
+ "train_samples": 207864,
7
+ "train_samples_per_second": 31.243,
8
+ "train_steps_per_second": 0.244
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1438 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.99981234753237,
5
+ "eval_steps": 500,
6
+ "global_step": 999,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0010008131606930632,
13
+ "grad_norm": 0.09912109375,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.7364,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.005004065803465315,
20
+ "grad_norm": 0.09228515625,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.7255,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.01000813160693063,
27
+ "grad_norm": 0.10009765625,
28
+ "learning_rate": 2e-05,
29
+ "loss": 1.693,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.015012197410395946,
34
+ "grad_norm": 0.10546875,
35
+ "learning_rate": 3e-05,
36
+ "loss": 1.7131,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.02001626321386126,
41
+ "grad_norm": 0.1298828125,
42
+ "learning_rate": 4e-05,
43
+ "loss": 1.6944,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.02502032901732658,
48
+ "grad_norm": 0.162109375,
49
+ "learning_rate": 5e-05,
50
+ "loss": 1.6902,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.030024394820791892,
55
+ "grad_norm": 0.1982421875,
56
+ "learning_rate": 6e-05,
57
+ "loss": 1.6689,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.035028460624257206,
62
+ "grad_norm": 0.173828125,
63
+ "learning_rate": 7e-05,
64
+ "loss": 1.6255,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.04003252642772252,
69
+ "grad_norm": 0.1611328125,
70
+ "learning_rate": 8e-05,
71
+ "loss": 1.5785,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.04503659223118784,
76
+ "grad_norm": 0.1357421875,
77
+ "learning_rate": 9e-05,
78
+ "loss": 1.5011,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.05004065803465316,
83
+ "grad_norm": 0.1376953125,
84
+ "learning_rate": 0.0001,
85
+ "loss": 1.4936,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.055044723838118474,
90
+ "grad_norm": 0.08740234375,
91
+ "learning_rate": 0.00011000000000000002,
92
+ "loss": 1.48,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.060048789641583784,
97
+ "grad_norm": 0.06591796875,
98
+ "learning_rate": 0.00012,
99
+ "loss": 1.4597,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.0650528554450491,
104
+ "grad_norm": 0.04345703125,
105
+ "learning_rate": 0.00013000000000000002,
106
+ "loss": 1.4573,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.07005692124851441,
111
+ "grad_norm": 0.0322265625,
112
+ "learning_rate": 0.00014,
113
+ "loss": 1.4094,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.07506098705197974,
118
+ "grad_norm": 0.037353515625,
119
+ "learning_rate": 0.00015000000000000001,
120
+ "loss": 1.4073,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.08006505285544505,
125
+ "grad_norm": 0.0277099609375,
126
+ "learning_rate": 0.00016,
127
+ "loss": 1.4222,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.08506911865891037,
132
+ "grad_norm": 0.0230712890625,
133
+ "learning_rate": 0.00017,
134
+ "loss": 1.4125,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.09007318446237568,
139
+ "grad_norm": 0.021728515625,
140
+ "learning_rate": 0.00018,
141
+ "loss": 1.3956,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.09507725026584099,
146
+ "grad_norm": 0.0211181640625,
147
+ "learning_rate": 0.00019,
148
+ "loss": 1.4091,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.10008131606930631,
153
+ "grad_norm": 0.0198974609375,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.368,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.10508538187277162,
160
+ "grad_norm": 0.0196533203125,
161
+ "learning_rate": 0.00019998473561448797,
162
+ "loss": 1.381,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.11008944767623695,
167
+ "grad_norm": 0.01806640625,
168
+ "learning_rate": 0.0001999389471179811,
169
+ "loss": 1.3798,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.11509351347970226,
174
+ "grad_norm": 0.017333984375,
175
+ "learning_rate": 0.00019986264848914474,
176
+ "loss": 1.3918,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.12009757928316757,
181
+ "grad_norm": 0.017578125,
182
+ "learning_rate": 0.00019975586302101248,
183
+ "loss": 1.3851,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.12510164508663288,
188
+ "grad_norm": 0.017578125,
189
+ "learning_rate": 0.00019961862331387543,
190
+ "loss": 1.3727,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.1301057108900982,
195
+ "grad_norm": 0.0169677734375,
196
+ "learning_rate": 0.00019945097126532955,
197
+ "loss": 1.3798,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.13510977669356353,
202
+ "grad_norm": 0.016357421875,
203
+ "learning_rate": 0.0001992529580574848,
204
+ "loss": 1.3553,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.14011384249702882,
209
+ "grad_norm": 0.01953125,
210
+ "learning_rate": 0.00019902464414134005,
211
+ "loss": 1.3801,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.14511790830049415,
216
+ "grad_norm": 0.0203857421875,
217
+ "learning_rate": 0.000198766099218328,
218
+ "loss": 1.354,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.15012197410395947,
223
+ "grad_norm": 0.01806640625,
224
+ "learning_rate": 0.0001984774022190361,
225
+ "loss": 1.3874,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.1551260399074248,
230
+ "grad_norm": 0.0166015625,
231
+ "learning_rate": 0.0001981586412791103,
232
+ "loss": 1.3565,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.1601301057108901,
237
+ "grad_norm": 0.0177001953125,
238
+ "learning_rate": 0.00019780991371234801,
239
+ "loss": 1.3525,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.16513417151435542,
244
+ "grad_norm": 0.01806640625,
245
+ "learning_rate": 0.00019743132598098963,
246
+ "loss": 1.3537,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.17013823731782074,
251
+ "grad_norm": 0.02734375,
252
+ "learning_rate": 0.00019702299366321677,
253
+ "loss": 1.3681,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.17514230312128604,
258
+ "grad_norm": 0.0201416015625,
259
+ "learning_rate": 0.00019658504141786774,
260
+ "loss": 1.3453,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.18014636892475136,
265
+ "grad_norm": 0.0184326171875,
266
+ "learning_rate": 0.0001961176029463807,
267
+ "loss": 1.3701,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.18515043472821668,
272
+ "grad_norm": 0.021240234375,
273
+ "learning_rate": 0.00019562082095197632,
274
+ "loss": 1.3525,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.19015450053168198,
279
+ "grad_norm": 0.02001953125,
280
+ "learning_rate": 0.00019509484709609215,
281
+ "loss": 1.3427,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.1951585663351473,
286
+ "grad_norm": 0.02001953125,
287
+ "learning_rate": 0.0001945398419520823,
288
+ "loss": 1.3469,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.20016263213861263,
293
+ "grad_norm": 0.021484375,
294
+ "learning_rate": 0.00019395597495619634,
295
+ "loss": 1.3413,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.20516669794207792,
300
+ "grad_norm": 0.0230712890625,
301
+ "learning_rate": 0.00019334342435585255,
302
+ "loss": 1.3604,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.21017076374554325,
307
+ "grad_norm": 0.0211181640625,
308
+ "learning_rate": 0.00019270237715522112,
309
+ "loss": 1.3695,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.21517482954900857,
314
+ "grad_norm": 0.02197265625,
315
+ "learning_rate": 0.00019203302905813406,
316
+ "loss": 1.3443,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2201788953524739,
321
+ "grad_norm": 0.0211181640625,
322
+ "learning_rate": 0.00019133558440833926,
323
+ "loss": 1.336,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.2251829611559392,
328
+ "grad_norm": 0.0234375,
329
+ "learning_rate": 0.00019061025612711699,
330
+ "loss": 1.373,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.23018702695940452,
335
+ "grad_norm": 0.021728515625,
336
+ "learning_rate": 0.00018985726564827728,
337
+ "loss": 1.3571,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.23519109276286984,
342
+ "grad_norm": 0.0218505859375,
343
+ "learning_rate": 0.0001890768428505593,
344
+ "loss": 1.3279,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.24019515856633514,
349
+ "grad_norm": 0.023193359375,
350
+ "learning_rate": 0.00018826922598745197,
351
+ "loss": 1.358,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.24519922436980046,
356
+ "grad_norm": 0.0250244140625,
357
+ "learning_rate": 0.00018743466161445823,
358
+ "loss": 1.3361,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.25020329017326576,
363
+ "grad_norm": 0.02197265625,
364
+ "learning_rate": 0.00018657340451382447,
365
+ "loss": 1.3324,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.2552073559767311,
370
+ "grad_norm": 0.0213623046875,
371
+ "learning_rate": 0.00018568571761675893,
372
+ "loss": 1.3304,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.2602114217801964,
377
+ "grad_norm": 0.0225830078125,
378
+ "learning_rate": 0.00018477187192316184,
379
+ "loss": 1.3585,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.2652154875836617,
384
+ "grad_norm": 0.0250244140625,
385
+ "learning_rate": 0.00018383214641889243,
386
+ "loss": 1.3295,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.27021955338712705,
391
+ "grad_norm": 0.024658203125,
392
+ "learning_rate": 0.00018286682799059824,
393
+ "loss": 1.3565,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.27522361919059235,
398
+ "grad_norm": 0.0223388671875,
399
+ "learning_rate": 0.00018187621133813187,
400
+ "loss": 1.3314,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.28022768499405765,
405
+ "grad_norm": 0.0228271484375,
406
+ "learning_rate": 0.00018086059888458288,
407
+ "loss": 1.3395,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.285231750797523,
412
+ "grad_norm": 0.0218505859375,
413
+ "learning_rate": 0.0001798203006839517,
414
+ "loss": 1.3486,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.2902358166009883,
419
+ "grad_norm": 0.022216796875,
420
+ "learning_rate": 0.00017875563432649392,
421
+ "loss": 1.3341,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.29523988240445365,
426
+ "grad_norm": 0.0245361328125,
427
+ "learning_rate": 0.0001776669248417641,
428
+ "loss": 1.3409,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.30024394820791894,
433
+ "grad_norm": 0.0235595703125,
434
+ "learning_rate": 0.00017655450459938784,
435
+ "loss": 1.3506,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.30524801401138424,
440
+ "grad_norm": 0.0242919921875,
441
+ "learning_rate": 0.00017541871320759378,
442
+ "loss": 1.3523,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3102520798148496,
447
+ "grad_norm": 0.0230712890625,
448
+ "learning_rate": 0.0001742598974095353,
449
+ "loss": 1.3328,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3152561456183149,
454
+ "grad_norm": 0.0220947265625,
455
+ "learning_rate": 0.0001730784109774339,
456
+ "loss": 1.3394,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.3202602114217802,
461
+ "grad_norm": 0.0224609375,
462
+ "learning_rate": 0.00017187461460457717,
463
+ "loss": 1.3379,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.32526427722524553,
468
+ "grad_norm": 0.0233154296875,
469
+ "learning_rate": 0.00017064887579520334,
470
+ "loss": 1.317,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.33026834302871083,
475
+ "grad_norm": 0.02197265625,
476
+ "learning_rate": 0.00016940156875230687,
477
+ "loss": 1.3257,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.3352724088321761,
482
+ "grad_norm": 0.0220947265625,
483
+ "learning_rate": 0.00016813307426339892,
484
+ "loss": 1.3265,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.3402764746356415,
489
+ "grad_norm": 0.0235595703125,
490
+ "learning_rate": 0.0001668437795842574,
491
+ "loss": 1.3372,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.3452805404391068,
496
+ "grad_norm": 0.024658203125,
497
+ "learning_rate": 0.00016553407832070277,
498
+ "loss": 1.3559,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.35028460624257207,
503
+ "grad_norm": 0.02490234375,
504
+ "learning_rate": 0.00016420437030843484,
505
+ "loss": 1.3396,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.3552886720460374,
510
+ "grad_norm": 0.025634765625,
511
+ "learning_rate": 0.00016285506149096794,
512
+ "loss": 1.3437,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.3602927378495027,
517
+ "grad_norm": 0.0269775390625,
518
+ "learning_rate": 0.00016148656379570144,
519
+ "loss": 1.3409,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.365296803652968,
524
+ "grad_norm": 0.029052734375,
525
+ "learning_rate": 0.0001600992950081632,
526
+ "loss": 1.3445,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.37030086945643337,
531
+ "grad_norm": 0.026123046875,
532
+ "learning_rate": 0.0001586936786444648,
533
+ "loss": 1.3533,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.37530493525989866,
538
+ "grad_norm": 0.0234375,
539
+ "learning_rate": 0.0001572701438220074,
540
+ "loss": 1.343,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.38030900106336396,
545
+ "grad_norm": 0.026611328125,
546
+ "learning_rate": 0.0001558291251284774,
547
+ "loss": 1.3617,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.3853130668668293,
552
+ "grad_norm": 0.0274658203125,
553
+ "learning_rate": 0.00015437106248917217,
554
+ "loss": 1.323,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.3903171326702946,
559
+ "grad_norm": 0.0235595703125,
560
+ "learning_rate": 0.00015289640103269625,
561
+ "loss": 1.3186,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.3953211984737599,
566
+ "grad_norm": 0.0262451171875,
567
+ "learning_rate": 0.00015140559095506908,
568
+ "loss": 1.3228,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.40032526427722526,
573
+ "grad_norm": 0.02685546875,
574
+ "learning_rate": 0.00014989908738228567,
575
+ "loss": 1.3341,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.40532933008069055,
580
+ "grad_norm": 0.024658203125,
581
+ "learning_rate": 0.00014837735023137216,
582
+ "loss": 1.3479,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.41033339588415585,
587
+ "grad_norm": 0.0267333984375,
588
+ "learning_rate": 0.00014684084406997903,
589
+ "loss": 1.3272,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.4153374616876212,
594
+ "grad_norm": 0.0262451171875,
595
+ "learning_rate": 0.00014529003797455402,
596
+ "loss": 1.338,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.4203415274910865,
601
+ "grad_norm": 0.024658203125,
602
+ "learning_rate": 0.000143725405387139,
603
+ "loss": 1.3344,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.42534559329455185,
608
+ "grad_norm": 0.023681640625,
609
+ "learning_rate": 0.000142147423970834,
610
+ "loss": 1.3262,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.43034965909801715,
615
+ "grad_norm": 0.024658203125,
616
+ "learning_rate": 0.0001405565754639724,
617
+ "loss": 1.3282,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.43535372490148244,
622
+ "grad_norm": 0.0238037109375,
623
+ "learning_rate": 0.00013895334553305216,
624
+ "loss": 1.3363,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.4403577907049478,
629
+ "grad_norm": 0.0281982421875,
630
+ "learning_rate": 0.0001373382236244679,
631
+ "loss": 1.3365,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.4453618565084131,
636
+ "grad_norm": 0.0242919921875,
637
+ "learning_rate": 0.0001357117028150889,
638
+ "loss": 1.338,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.4503659223118784,
643
+ "grad_norm": 0.0240478515625,
644
+ "learning_rate": 0.00013407427966172865,
645
+ "loss": 1.3344,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.45536998811534374,
650
+ "grad_norm": 0.0257568359375,
651
+ "learning_rate": 0.00013242645404955237,
652
+ "loss": 1.3576,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.46037405391880903,
657
+ "grad_norm": 0.02734375,
658
+ "learning_rate": 0.00013076872903946806,
659
+ "loss": 1.3258,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.46537811972227433,
664
+ "grad_norm": 0.02490234375,
665
+ "learning_rate": 0.0001291016107145483,
666
+ "loss": 1.3441,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.4703821855257397,
671
+ "grad_norm": 0.02490234375,
672
+ "learning_rate": 0.00012742560802552912,
673
+ "loss": 1.3255,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.475386251329205,
678
+ "grad_norm": 0.0272216796875,
679
+ "learning_rate": 0.00012574123263543388,
680
+ "loss": 1.3483,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.4803903171326703,
685
+ "grad_norm": 0.025146484375,
686
+ "learning_rate": 0.0001240489987633686,
687
+ "loss": 1.3465,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.4853943829361356,
692
+ "grad_norm": 0.0247802734375,
693
+ "learning_rate": 0.0001223494230275372,
694
+ "loss": 1.3419,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.4903984487396009,
699
+ "grad_norm": 0.0244140625,
700
+ "learning_rate": 0.0001206430242875246,
701
+ "loss": 1.3168,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.4954025145430662,
706
+ "grad_norm": 0.0247802734375,
707
+ "learning_rate": 0.00011893032348589478,
708
+ "loss": 1.3379,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.5004065803465315,
713
+ "grad_norm": 0.025390625,
714
+ "learning_rate": 0.00011721184348915384,
715
+ "loss": 1.3195,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5054106461499969,
720
+ "grad_norm": 0.024169921875,
721
+ "learning_rate": 0.00011548810892812505,
722
+ "loss": 1.3169,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5104147119534622,
727
+ "grad_norm": 0.0245361328125,
728
+ "learning_rate": 0.00011375964603778561,
729
+ "loss": 1.3208,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.5154187777569275,
734
+ "grad_norm": 0.025390625,
735
+ "learning_rate": 0.00011202698249661364,
736
+ "loss": 1.3139,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.5204228435603928,
741
+ "grad_norm": 0.0238037109375,
742
+ "learning_rate": 0.00011029064726549412,
743
+ "loss": 1.3217,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.5254269093638582,
748
+ "grad_norm": 0.025634765625,
749
+ "learning_rate": 0.000108551170426234,
750
+ "loss": 1.3115,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.5304309751673234,
755
+ "grad_norm": 0.0272216796875,
756
+ "learning_rate": 0.0001068090830197346,
757
+ "loss": 1.3709,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.5354350409707888,
762
+ "grad_norm": 0.0257568359375,
763
+ "learning_rate": 0.00010506491688387127,
764
+ "loss": 1.3332,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.5404391067742541,
769
+ "grad_norm": 0.025634765625,
770
+ "learning_rate": 0.00010331920449112991,
771
+ "loss": 1.3496,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.5454431725777193,
776
+ "grad_norm": 0.0260009765625,
777
+ "learning_rate": 0.00010157247878604961,
778
+ "loss": 1.3611,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.5504472383811847,
783
+ "grad_norm": 0.024658203125,
784
+ "learning_rate": 9.982527302252135e-05,
785
+ "loss": 1.3502,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.55545130418465,
790
+ "grad_norm": 0.0235595703125,
791
+ "learning_rate": 9.807812060099191e-05,
792
+ "loss": 1.3278,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.5604553699881153,
797
+ "grad_norm": 0.0244140625,
798
+ "learning_rate": 9.633155490562358e-05,
799
+ "loss": 1.3605,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.5654594357915806,
804
+ "grad_norm": 0.0235595703125,
805
+ "learning_rate": 9.458610914145826e-05,
806
+ "loss": 1.3379,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.570463501595046,
811
+ "grad_norm": 0.0257568359375,
812
+ "learning_rate": 9.284231617163666e-05,
813
+ "loss": 1.3085,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.5754675673985112,
818
+ "grad_norm": 0.0252685546875,
819
+ "learning_rate": 9.11007083547216e-05,
820
+ "loss": 1.3415,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.5804716332019766,
825
+ "grad_norm": 0.0252685546875,
826
+ "learning_rate": 8.936181738217571e-05,
827
+ "loss": 1.3251,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.5854756990054419,
832
+ "grad_norm": 0.0262451171875,
833
+ "learning_rate": 8.762617411604235e-05,
834
+ "loss": 1.3519,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.5904797648089073,
839
+ "grad_norm": 0.0252685546875,
840
+ "learning_rate": 8.589430842688001e-05,
841
+ "loss": 1.3148,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.5954838306123725,
846
+ "grad_norm": 0.02685546875,
847
+ "learning_rate": 8.41667490319994e-05,
848
+ "loss": 1.3169,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.6004878964158379,
853
+ "grad_norm": 0.024658203125,
854
+ "learning_rate": 8.244402333405252e-05,
855
+ "loss": 1.3561,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6054919622193032,
860
+ "grad_norm": 0.025146484375,
861
+ "learning_rate": 8.0726657260023e-05,
862
+ "loss": 1.3059,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.6104960280227685,
867
+ "grad_norm": 0.0245361328125,
868
+ "learning_rate": 7.901517510066724e-05,
869
+ "loss": 1.329,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.6155000938262338,
874
+ "grad_norm": 0.0250244140625,
875
+ "learning_rate": 7.73100993504548e-05,
876
+ "loss": 1.3412,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.6205041596296992,
881
+ "grad_norm": 0.025146484375,
882
+ "learning_rate": 7.561195054805729e-05,
883
+ "loss": 1.3447,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.6255082254331644,
888
+ "grad_norm": 0.02392578125,
889
+ "learning_rate": 7.392124711743422e-05,
890
+ "loss": 1.3445,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.6305122912366298,
895
+ "grad_norm": 0.025634765625,
896
+ "learning_rate": 7.223850520956457e-05,
897
+ "loss": 1.3078,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.6355163570400951,
902
+ "grad_norm": 0.026123046875,
903
+ "learning_rate": 7.056423854487236e-05,
904
+ "loss": 1.3427,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.6405204228435604,
909
+ "grad_norm": 0.0244140625,
910
+ "learning_rate": 6.889895825639401e-05,
911
+ "loss": 1.3364,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.6455244886470257,
916
+ "grad_norm": 0.0263671875,
917
+ "learning_rate": 6.724317273373563e-05,
918
+ "loss": 1.3555,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.6505285544504911,
923
+ "grad_norm": 0.02587890625,
924
+ "learning_rate": 6.55973874678682e-05,
925
+ "loss": 1.3542,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.6555326202539563,
930
+ "grad_norm": 0.025390625,
931
+ "learning_rate": 6.396210489680699e-05,
932
+ "loss": 1.3421,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.6605366860574217,
937
+ "grad_norm": 0.0240478515625,
938
+ "learning_rate": 6.23378242522237e-05,
939
+ "loss": 1.3395,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.665540751860887,
944
+ "grad_norm": 0.02490234375,
945
+ "learning_rate": 6.072504140703714e-05,
946
+ "loss": 1.3291,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.6705448176643523,
951
+ "grad_norm": 0.0255126953125,
952
+ "learning_rate": 5.912424872402927e-05,
953
+ "loss": 1.33,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.6755488834678176,
958
+ "grad_norm": 0.0257568359375,
959
+ "learning_rate": 5.7535934905532816e-05,
960
+ "loss": 1.3547,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.680552949271283,
965
+ "grad_norm": 0.02490234375,
966
+ "learning_rate": 5.596058484423656e-05,
967
+ "loss": 1.344,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.6855570150747482,
972
+ "grad_norm": 0.025390625,
973
+ "learning_rate": 5.43986794751536e-05,
974
+ "loss": 1.3617,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.6905610808782136,
979
+ "grad_norm": 0.023193359375,
980
+ "learning_rate": 5.285069562879758e-05,
981
+ "loss": 1.3275,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.6955651466816789,
986
+ "grad_norm": 0.0245361328125,
987
+ "learning_rate": 5.1317105885612524e-05,
988
+ "loss": 1.3459,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.7005692124851441,
993
+ "grad_norm": 0.026123046875,
994
+ "learning_rate": 4.9798378431699585e-05,
995
+ "loss": 1.3345,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.7055732782886095,
1000
+ "grad_norm": 0.0260009765625,
1001
+ "learning_rate": 4.829497691588557e-05,
1002
+ "loss": 1.3208,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.7105773440920748,
1007
+ "grad_norm": 0.02587890625,
1008
+ "learning_rate": 4.680736030817687e-05,
1009
+ "loss": 1.3546,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.7155814098955401,
1014
+ "grad_norm": 0.0240478515625,
1015
+ "learning_rate": 4.533598275964139e-05,
1016
+ "loss": 1.326,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.7205854756990054,
1021
+ "grad_norm": 0.0250244140625,
1022
+ "learning_rate": 4.388129346376178e-05,
1023
+ "loss": 1.3337,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.7255895415024708,
1028
+ "grad_norm": 0.025390625,
1029
+ "learning_rate": 4.2443736519302314e-05,
1030
+ "loss": 1.3264,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.730593607305936,
1035
+ "grad_norm": 0.0250244140625,
1036
+ "learning_rate": 4.102375079473087e-05,
1037
+ "loss": 1.3214,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.7355976731094014,
1042
+ "grad_norm": 0.0255126953125,
1043
+ "learning_rate": 3.9621769794237894e-05,
1044
+ "loss": 1.3318,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.7406017389128667,
1049
+ "grad_norm": 0.0247802734375,
1050
+ "learning_rate": 3.823822152539286e-05,
1051
+ "loss": 1.3327,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.745605804716332,
1056
+ "grad_norm": 0.025146484375,
1057
+ "learning_rate": 3.687352836847874e-05,
1058
+ "loss": 1.3486,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.7506098705197973,
1063
+ "grad_norm": 0.0252685546875,
1064
+ "learning_rate": 3.552810694754463e-05,
1065
+ "loss": 1.329,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.7556139363232627,
1070
+ "grad_norm": 0.025634765625,
1071
+ "learning_rate": 3.42023680032154e-05,
1072
+ "loss": 1.3553,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.7606180021267279,
1077
+ "grad_norm": 0.0240478515625,
1078
+ "learning_rate": 3.289671626729772e-05,
1079
+ "loss": 1.3087,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.7656220679301933,
1084
+ "grad_norm": 0.0244140625,
1085
+ "learning_rate": 3.161155033922045e-05,
1086
+ "loss": 1.3299,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.7706261337336586,
1091
+ "grad_norm": 0.02392578125,
1092
+ "learning_rate": 3.0347262564347057e-05,
1093
+ "loss": 1.3156,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.7756301995371239,
1098
+ "grad_norm": 0.02587890625,
1099
+ "learning_rate": 2.9104238914197445e-05,
1100
+ "loss": 1.3171,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.7806342653405892,
1105
+ "grad_norm": 0.02392578125,
1106
+ "learning_rate": 2.7882858868615467e-05,
1107
+ "loss": 1.3415,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.7856383311440546,
1112
+ "grad_norm": 0.023193359375,
1113
+ "learning_rate": 2.6683495299918648e-05,
1114
+ "loss": 1.3576,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.7906423969475198,
1119
+ "grad_norm": 0.025146484375,
1120
+ "learning_rate": 2.550651435906456e-05,
1121
+ "loss": 1.309,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.7956464627509852,
1126
+ "grad_norm": 0.0272216796875,
1127
+ "learning_rate": 2.435227536386967e-05,
1128
+ "loss": 1.3299,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.8006505285544505,
1133
+ "grad_norm": 0.0240478515625,
1134
+ "learning_rate": 2.3221130689313907e-05,
1135
+ "loss": 1.3354,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.8056545943579158,
1140
+ "grad_norm": 0.023681640625,
1141
+ "learning_rate": 2.211342565996487e-05,
1142
+ "loss": 1.3262,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.8106586601613811,
1147
+ "grad_norm": 0.025390625,
1148
+ "learning_rate": 2.1029498444554618e-05,
1149
+ "loss": 1.3339,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.8156627259648465,
1154
+ "grad_norm": 0.02490234375,
1155
+ "learning_rate": 1.9969679952740805e-05,
1156
+ "loss": 1.3516,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.8206667917683117,
1161
+ "grad_norm": 0.0234375,
1162
+ "learning_rate": 1.893429373408411e-05,
1163
+ "loss": 1.3399,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.825670857571777,
1168
+ "grad_norm": 0.0242919921875,
1169
+ "learning_rate": 1.7923655879272393e-05,
1170
+ "loss": 1.3149,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.8306749233752424,
1175
+ "grad_norm": 0.0242919921875,
1176
+ "learning_rate": 1.6938074923622227e-05,
1177
+ "loss": 1.3292,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.8356789891787078,
1182
+ "grad_norm": 0.0242919921875,
1183
+ "learning_rate": 1.597785175288683e-05,
1184
+ "loss": 1.3325,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.840683054982173,
1189
+ "grad_norm": 0.0245361328125,
1190
+ "learning_rate": 1.5043279511399333e-05,
1191
+ "loss": 1.3544,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.8456871207856383,
1196
+ "grad_norm": 0.0245361328125,
1197
+ "learning_rate": 1.4134643512579382e-05,
1198
+ "loss": 1.3601,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.8506911865891037,
1203
+ "grad_norm": 0.0238037109375,
1204
+ "learning_rate": 1.3252221151830513e-05,
1205
+ "loss": 1.3447,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.8556952523925689,
1210
+ "grad_norm": 0.0238037109375,
1211
+ "learning_rate": 1.2396281821854683e-05,
1212
+ "loss": 1.3296,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.8606993181960343,
1217
+ "grad_norm": 0.024169921875,
1218
+ "learning_rate": 1.156708683041008e-05,
1219
+ "loss": 1.3187,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.8657033839994996,
1224
+ "grad_norm": 0.024169921875,
1225
+ "learning_rate": 1.0764889320536931e-05,
1226
+ "loss": 1.3136,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.8707074498029649,
1231
+ "grad_norm": 0.023193359375,
1232
+ "learning_rate": 9.989934193276219e-06,
1233
+ "loss": 1.323,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.8757115156064302,
1238
+ "grad_norm": 0.024658203125,
1239
+ "learning_rate": 9.242458032904311e-06,
1240
+ "loss": 1.3221,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.8807155814098956,
1245
+ "grad_norm": 0.02587890625,
1246
+ "learning_rate": 8.52268903470661e-06,
1247
+ "loss": 1.3413,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.8857196472133608,
1252
+ "grad_norm": 0.0242919921875,
1253
+ "learning_rate": 7.830846935312509e-06,
1254
+ "loss": 1.3342,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.8907237130168262,
1259
+ "grad_norm": 0.0245361328125,
1260
+ "learning_rate": 7.167142945612393e-06,
1261
+ "loss": 1.3265,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.8957277788202915,
1266
+ "grad_norm": 0.0238037109375,
1267
+ "learning_rate": 6.531779686277528e-06,
1268
+ "loss": 1.3387,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.9007318446237568,
1273
+ "grad_norm": 0.02392578125,
1274
+ "learning_rate": 5.924951125902545e-06,
1275
+ "loss": 1.3167,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.9057359104272221,
1280
+ "grad_norm": 0.0235595703125,
1281
+ "learning_rate": 5.346842521789141e-06,
1282
+ "loss": 1.3465,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.9107399762306875,
1287
+ "grad_norm": 0.0244140625,
1288
+ "learning_rate": 4.7976303633893384e-06,
1289
+ "loss": 1.3396,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.9157440420341527,
1294
+ "grad_norm": 0.0250244140625,
1295
+ "learning_rate": 4.277482318425408e-06,
1296
+ "loss": 1.3569,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.9207481078376181,
1301
+ "grad_norm": 0.025390625,
1302
+ "learning_rate": 3.7865571817029877e-06,
1303
+ "loss": 1.3265,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.9257521736410834,
1308
+ "grad_norm": 0.025390625,
1309
+ "learning_rate": 3.3250048266329825e-06,
1310
+ "loss": 1.3392,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.9307562394445487,
1315
+ "grad_norm": 0.024658203125,
1316
+ "learning_rate": 2.8929661594770174e-06,
1317
+ "loss": 1.3597,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.935760305248014,
1322
+ "grad_norm": 0.0257568359375,
1323
+ "learning_rate": 2.4905730763305047e-06,
1324
+ "loss": 1.3329,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.9407643710514794,
1329
+ "grad_norm": 0.025146484375,
1330
+ "learning_rate": 2.1179484228564305e-06,
1331
+ "loss": 1.3497,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.9457684368549446,
1336
+ "grad_norm": 0.02392578125,
1337
+ "learning_rate": 1.7752059567820333e-06,
1338
+ "loss": 1.3367,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.95077250265841,
1343
+ "grad_norm": 0.0245361328125,
1344
+ "learning_rate": 1.4624503131699828e-06,
1345
+ "loss": 1.3459,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 0.9557765684618753,
1350
+ "grad_norm": 0.02490234375,
1351
+ "learning_rate": 1.1797769724745888e-06,
1352
+ "loss": 1.3326,
1353
+ "step": 955
1354
+ },
1355
+ {
1356
+ "epoch": 0.9607806342653405,
1357
+ "grad_norm": 0.024169921875,
1358
+ "learning_rate": 9.272722313927617e-07,
1359
+ "loss": 1.3487,
1360
+ "step": 960
1361
+ },
1362
+ {
1363
+ "epoch": 0.9657847000688059,
1364
+ "grad_norm": 0.0247802734375,
1365
+ "learning_rate": 7.05013176518754e-07,
1366
+ "loss": 1.3647,
1367
+ "step": 965
1368
+ },
1369
+ {
1370
+ "epoch": 0.9707887658722713,
1371
+ "grad_norm": 0.0233154296875,
1372
+ "learning_rate": 5.130676608104845e-07,
1373
+ "loss": 1.3482,
1374
+ "step": 970
1375
+ },
1376
+ {
1377
+ "epoch": 0.9757928316757365,
1378
+ "grad_norm": 0.0247802734375,
1379
+ "learning_rate": 3.5149428287495343e-07,
1380
+ "loss": 1.3423,
1381
+ "step": 975
1382
+ },
1383
+ {
1384
+ "epoch": 0.9807968974792018,
1385
+ "grad_norm": 0.02587890625,
1386
+ "learning_rate": 2.2034236907874094e-07,
1387
+ "loss": 1.3267,
1388
+ "step": 980
1389
+ },
1390
+ {
1391
+ "epoch": 0.9858009632826672,
1392
+ "grad_norm": 0.0238037109375,
1393
+ "learning_rate": 1.1965195848929745e-07,
1394
+ "loss": 1.3185,
1395
+ "step": 985
1396
+ },
1397
+ {
1398
+ "epoch": 0.9908050290861324,
1399
+ "grad_norm": 0.02392578125,
1400
+ "learning_rate": 4.945379065152134e-08,
1401
+ "loss": 1.3129,
1402
+ "step": 990
1403
+ },
1404
+ {
1405
+ "epoch": 0.9958090948895978,
1406
+ "grad_norm": 0.024658203125,
1407
+ "learning_rate": 9.769296203332446e-09,
1408
+ "loss": 1.3423,
1409
+ "step": 995
1410
+ },
1411
+ {
1412
+ "epoch": 0.99981234753237,
1413
+ "eval_loss": 1.343445897102356,
1414
+ "eval_runtime": 1960.9798,
1415
+ "eval_samples_per_second": 7.216,
1416
+ "eval_steps_per_second": 7.216,
1417
+ "step": 999
1418
+ },
1419
+ {
1420
+ "epoch": 0.99981234753237,
1421
+ "step": 999,
1422
+ "total_flos": 2.0711686751461048e+18,
1423
+ "train_loss": 0.052138939037456644,
1424
+ "train_runtime": 4093.6241,
1425
+ "train_samples_per_second": 31.243,
1426
+ "train_steps_per_second": 0.244
1427
+ }
1428
+ ],
1429
+ "logging_steps": 5,
1430
+ "max_steps": 999,
1431
+ "num_input_tokens_seen": 0,
1432
+ "num_train_epochs": 1,
1433
+ "save_steps": 20,
1434
+ "total_flos": 2.0711686751461048e+18,
1435
+ "train_batch_size": 1,
1436
+ "trial_name": null,
1437
+ "trial_params": null
1438
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f47130eda4d0dae3c562175b12c7e11cce7d449fa04558842de4f9e72243252
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff