Xmm commited on
Commit
3826836
1 Parent(s): 93f72dc

Upload 11 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/gemma-2b-it",
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,
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": "unsloth",
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj",
24
+ "gate_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "up_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e587daa92aea01009aad6118424ce73bc512b06241f31b5cc570d8a84a52a021
3
+ size 78480072
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a20b45145a1ac95637aae5661f2b0b51c1c3fa84faa15c02875bcc6386b871
3
+ size 39594180
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4526d24dfcd6f7f05a227220d3f48a0ec6a8dae66cd141f8b21fa0efdd56cc22
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18070fab0b9756f02d25c0a163c5d05591888b6e42fab37a5382660fea70b3b0
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
3
+ size 17477929
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "106": {
38
+ "content": "<start_of_turn>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<end_of_turn>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<start_of_turn>",
56
+ "<end_of_turn>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 8192,
64
+ "pad_token": "<pad>",
65
+ "padding_side": "right",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "GemmaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": false
71
+ }
trainer_state.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.01714383679067375,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 1.4420362710952759,
14
+ "learning_rate": 4e-05,
15
+ "loss": 3.3293,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 4e-05,
22
+ "loss": 3.8207,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 1.3726439476013184,
28
+ "learning_rate": 8e-05,
29
+ "loss": 3.4594,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 1.2832139730453491,
35
+ "learning_rate": 0.00012,
36
+ "loss": 3.297,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "grad_norm": 1.2156065702438354,
42
+ "learning_rate": 0.00016,
43
+ "loss": 3.0036,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "grad_norm": 1.196576476097107,
49
+ "learning_rate": 0.0002,
50
+ "loss": 2.9488,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "grad_norm": NaN,
56
+ "learning_rate": 0.0002,
57
+ "loss": 2.7249,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0,
62
+ "grad_norm": 1.1029444932937622,
63
+ "learning_rate": 0.00019996568291008924,
64
+ "loss": 2.8809,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0,
69
+ "grad_norm": 1.0251176357269287,
70
+ "learning_rate": 0.00019993136582017846,
71
+ "loss": 2.728,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0,
76
+ "grad_norm": 1.7124559879302979,
77
+ "learning_rate": 0.0001998970487302677,
78
+ "loss": 2.6262,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.0,
83
+ "grad_norm": 1.3183832168579102,
84
+ "learning_rate": 0.00019986273164035692,
85
+ "loss": 2.765,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "grad_norm": NaN,
91
+ "learning_rate": 0.00019986273164035692,
92
+ "loss": 2.682,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "grad_norm": 1.2592570781707764,
98
+ "learning_rate": 0.00019982841455044615,
99
+ "loss": 2.7837,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0,
104
+ "grad_norm": 0.9486250877380371,
105
+ "learning_rate": 0.00019979409746053535,
106
+ "loss": 2.8407,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.0,
111
+ "grad_norm": 0.8232390284538269,
112
+ "learning_rate": 0.00019975978037062458,
113
+ "loss": 2.6573,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0,
118
+ "grad_norm": 1.1916477680206299,
119
+ "learning_rate": 0.0001997254632807138,
120
+ "loss": 2.8644,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.0,
125
+ "grad_norm": 0.6067786812782288,
126
+ "learning_rate": 0.00019969114619080303,
127
+ "loss": 2.582,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0,
132
+ "grad_norm": 0.9011898040771484,
133
+ "learning_rate": 0.00019965682910089226,
134
+ "loss": 2.7302,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "grad_norm": 0.8688616156578064,
140
+ "learning_rate": 0.00019962251201098149,
141
+ "loss": 2.3353,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0,
146
+ "grad_norm": 0.7956060767173767,
147
+ "learning_rate": 0.0001995881949210707,
148
+ "loss": 2.5263,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0,
153
+ "grad_norm": NaN,
154
+ "learning_rate": 0.0001995881949210707,
155
+ "loss": 2.4818,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.0,
160
+ "grad_norm": 0.8461011052131653,
161
+ "learning_rate": 0.00019955387783115994,
162
+ "loss": 2.542,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.0,
167
+ "grad_norm": 0.6973548531532288,
168
+ "learning_rate": 0.00019951956074124917,
169
+ "loss": 2.4787,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.0,
174
+ "grad_norm": 0.6046115756034851,
175
+ "learning_rate": 0.0001994852436513384,
176
+ "loss": 2.4436,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.0,
181
+ "grad_norm": 0.4711577594280243,
182
+ "learning_rate": 0.0001994509265614276,
183
+ "loss": 2.3658,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.0,
188
+ "grad_norm": NaN,
189
+ "learning_rate": 0.0001994509265614276,
190
+ "loss": 2.4518,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.0,
195
+ "grad_norm": 0.5012961030006409,
196
+ "learning_rate": 0.00019941660947151682,
197
+ "loss": 2.3782,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.0,
202
+ "grad_norm": 0.6144160628318787,
203
+ "learning_rate": 0.00019938229238160605,
204
+ "loss": 2.4487,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.0,
209
+ "grad_norm": NaN,
210
+ "learning_rate": 0.00019938229238160605,
211
+ "loss": 2.3935,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "grad_norm": 0.6648868322372437,
217
+ "learning_rate": 0.00019934797529169528,
218
+ "loss": 2.5339,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.01,
223
+ "grad_norm": 0.5968282222747803,
224
+ "learning_rate": 0.00019931365820178448,
225
+ "loss": 2.4238,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.01,
230
+ "grad_norm": NaN,
231
+ "learning_rate": 0.00019931365820178448,
232
+ "loss": 2.4432,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.01,
237
+ "grad_norm": NaN,
238
+ "learning_rate": 0.00019931365820178448,
239
+ "loss": 2.3153,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.01,
244
+ "grad_norm": 0.9555236101150513,
245
+ "learning_rate": 0.0001992793411118737,
246
+ "loss": 2.2495,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.01,
251
+ "grad_norm": 0.8204368352890015,
252
+ "learning_rate": 0.00019924502402196293,
253
+ "loss": 2.401,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.01,
258
+ "grad_norm": NaN,
259
+ "learning_rate": 0.00019924502402196293,
260
+ "loss": 2.31,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.01,
265
+ "grad_norm": 0.8206217885017395,
266
+ "learning_rate": 0.00019921070693205216,
267
+ "loss": 2.3511,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.01,
272
+ "grad_norm": NaN,
273
+ "learning_rate": 0.00019921070693205216,
274
+ "loss": 2.2848,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.01,
279
+ "grad_norm": 0.5887894630432129,
280
+ "learning_rate": 0.0001991763898421414,
281
+ "loss": 2.191,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.01,
286
+ "grad_norm": 0.5945093035697937,
287
+ "learning_rate": 0.00019914207275223062,
288
+ "loss": 2.345,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.01,
293
+ "grad_norm": NaN,
294
+ "learning_rate": 0.00019914207275223062,
295
+ "loss": 2.4744,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.01,
300
+ "grad_norm": 0.7511911988258362,
301
+ "learning_rate": 0.00019910775566231984,
302
+ "loss": 2.3624,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.01,
307
+ "grad_norm": NaN,
308
+ "learning_rate": 0.00019910775566231984,
309
+ "loss": 2.3179,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.01,
314
+ "grad_norm": 0.8779334425926208,
315
+ "learning_rate": 0.00019907343857240907,
316
+ "loss": 2.4634,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.01,
321
+ "grad_norm": 0.9247270226478577,
322
+ "learning_rate": 0.0001990391214824983,
323
+ "loss": 2.2699,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.01,
328
+ "grad_norm": 0.785952627658844,
329
+ "learning_rate": 0.0001990048043925875,
330
+ "loss": 2.2791,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.01,
335
+ "grad_norm": 1.0079773664474487,
336
+ "learning_rate": 0.00019897048730267673,
337
+ "loss": 2.4368,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.01,
342
+ "grad_norm": 1.1102200746536255,
343
+ "learning_rate": 0.00019893617021276595,
344
+ "loss": 2.4482,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.01,
349
+ "grad_norm": 1.1956760883331299,
350
+ "learning_rate": 0.00019890185312285518,
351
+ "loss": 2.4036,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.01,
356
+ "grad_norm": 0.7190561294555664,
357
+ "learning_rate": 0.0001988675360329444,
358
+ "loss": 2.2854,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.01,
363
+ "grad_norm": NaN,
364
+ "learning_rate": 0.0001988675360329444,
365
+ "loss": 2.404,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.01,
370
+ "grad_norm": 1.0126006603240967,
371
+ "learning_rate": 0.00019883321894303364,
372
+ "loss": 2.1978,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.01,
377
+ "grad_norm": NaN,
378
+ "learning_rate": 0.00019883321894303364,
379
+ "loss": 2.3899,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.01,
384
+ "grad_norm": 1.213659405708313,
385
+ "learning_rate": 0.00019879890185312286,
386
+ "loss": 2.0958,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.01,
391
+ "grad_norm": 1.3466947078704834,
392
+ "learning_rate": 0.0001987645847632121,
393
+ "loss": 2.4106,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.01,
398
+ "grad_norm": 1.2530690431594849,
399
+ "learning_rate": 0.00019873026767330132,
400
+ "loss": 2.5628,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.01,
405
+ "grad_norm": 1.6688309907913208,
406
+ "learning_rate": 0.00019869595058339055,
407
+ "loss": 2.233,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.01,
412
+ "grad_norm": 2.2483224868774414,
413
+ "learning_rate": 0.00019866163349347977,
414
+ "loss": 2.2923,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.01,
419
+ "grad_norm": 2.017726182937622,
420
+ "learning_rate": 0.000198627316403569,
421
+ "loss": 2.354,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.01,
426
+ "grad_norm": NaN,
427
+ "learning_rate": 0.000198627316403569,
428
+ "loss": 2.5311,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.01,
433
+ "grad_norm": 1.810524582862854,
434
+ "learning_rate": 0.0001985929993136582,
435
+ "loss": 2.24,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.01,
440
+ "grad_norm": 2.439291000366211,
441
+ "learning_rate": 0.00019855868222374743,
442
+ "loss": 2.8512,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.01,
447
+ "grad_norm": NaN,
448
+ "learning_rate": 0.00019855868222374743,
449
+ "loss": 2.5943,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.01,
454
+ "grad_norm": 2.2657182216644287,
455
+ "learning_rate": 0.00019852436513383666,
456
+ "loss": 2.8789,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.01,
461
+ "grad_norm": 2.1179282665252686,
462
+ "learning_rate": 0.00019849004804392589,
463
+ "loss": 2.6996,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.01,
468
+ "grad_norm": 2.0068299770355225,
469
+ "learning_rate": 0.0001984557309540151,
470
+ "loss": 2.3677,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.01,
475
+ "grad_norm": NaN,
476
+ "learning_rate": 0.0001984557309540151,
477
+ "loss": 2.577,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.01,
482
+ "grad_norm": NaN,
483
+ "learning_rate": 0.0001984557309540151,
484
+ "loss": 2.7072,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.01,
489
+ "grad_norm": 4.678086280822754,
490
+ "learning_rate": 0.00019842141386410434,
491
+ "loss": 2.658,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.01,
496
+ "grad_norm": 4.056044101715088,
497
+ "learning_rate": 0.00019838709677419357,
498
+ "loss": 2.5174,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.01,
503
+ "grad_norm": 4.784575462341309,
504
+ "learning_rate": 0.0001983527796842828,
505
+ "loss": 2.6965,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.01,
510
+ "grad_norm": 7.531276226043701,
511
+ "learning_rate": 0.00019831846259437202,
512
+ "loss": 2.9831,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.01,
517
+ "grad_norm": 4.478590965270996,
518
+ "learning_rate": 0.00019828414550446125,
519
+ "loss": 3.0535,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.01,
524
+ "grad_norm": NaN,
525
+ "learning_rate": 0.00019828414550446125,
526
+ "loss": 2.7639,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.01,
531
+ "grad_norm": 7.104541778564453,
532
+ "learning_rate": 0.00019824982841455048,
533
+ "loss": 3.0957,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.01,
538
+ "grad_norm": 5.70428991317749,
539
+ "learning_rate": 0.00019821551132463968,
540
+ "loss": 3.0107,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.01,
545
+ "grad_norm": 3.2724623680114746,
546
+ "learning_rate": 0.0001981811942347289,
547
+ "loss": 2.9372,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.01,
552
+ "grad_norm": NaN,
553
+ "learning_rate": 0.0001981811942347289,
554
+ "loss": 3.4289,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.01,
559
+ "grad_norm": NaN,
560
+ "learning_rate": 0.0001981811942347289,
561
+ "loss": 3.4832,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.01,
566
+ "grad_norm": 20.135986328125,
567
+ "learning_rate": 0.00019814687714481813,
568
+ "loss": 3.2707,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.01,
573
+ "grad_norm": 22.686079025268555,
574
+ "learning_rate": 0.00019811256005490736,
575
+ "loss": 3.8144,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.01,
580
+ "grad_norm": NaN,
581
+ "learning_rate": 0.00019811256005490736,
582
+ "loss": 4.5631,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.01,
587
+ "grad_norm": 28.4752197265625,
588
+ "learning_rate": 0.00019807824296499656,
589
+ "loss": 4.8363,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.01,
594
+ "grad_norm": 23.301496505737305,
595
+ "learning_rate": 0.0001980439258750858,
596
+ "loss": 5.3773,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.01,
601
+ "grad_norm": 19.411945343017578,
602
+ "learning_rate": 0.00019800960878517502,
603
+ "loss": 5.1105,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.01,
608
+ "grad_norm": NaN,
609
+ "learning_rate": 0.00019800960878517502,
610
+ "loss": 5.8669,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.01,
615
+ "grad_norm": 35.982608795166016,
616
+ "learning_rate": 0.00019797529169526424,
617
+ "loss": 5.4417,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.02,
622
+ "grad_norm": NaN,
623
+ "learning_rate": 0.00019797529169526424,
624
+ "loss": 5.4101,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.02,
629
+ "grad_norm": 69.57833862304688,
630
+ "learning_rate": 0.00019794097460535347,
631
+ "loss": 5.2831,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.02,
636
+ "grad_norm": 76.1761703491211,
637
+ "learning_rate": 0.0001979066575154427,
638
+ "loss": 6.0605,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.02,
643
+ "grad_norm": NaN,
644
+ "learning_rate": 0.0001979066575154427,
645
+ "loss": 6.9964,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.02,
650
+ "grad_norm": 104.58732604980469,
651
+ "learning_rate": 0.00019787234042553193,
652
+ "loss": 7.346,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.02,
657
+ "grad_norm": 45.56397247314453,
658
+ "learning_rate": 0.00019783802333562115,
659
+ "loss": 8.6069,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.02,
664
+ "grad_norm": NaN,
665
+ "learning_rate": 0.00019783802333562115,
666
+ "loss": 9.6728,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.02,
671
+ "grad_norm": NaN,
672
+ "learning_rate": 0.00019783802333562115,
673
+ "loss": 8.1841,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.02,
678
+ "grad_norm": NaN,
679
+ "learning_rate": 0.00019783802333562115,
680
+ "loss": 9.4986,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.02,
685
+ "grad_norm": 25.033235549926758,
686
+ "learning_rate": 0.00019780370624571035,
687
+ "loss": 9.8723,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.02,
692
+ "grad_norm": 74.37015533447266,
693
+ "learning_rate": 0.00019776938915579958,
694
+ "loss": 9.7078,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.02,
699
+ "grad_norm": 72.31209564208984,
700
+ "learning_rate": 0.0001977350720658888,
701
+ "loss": 12.0863,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.02,
706
+ "grad_norm": 47.87614059448242,
707
+ "learning_rate": 0.00019770075497597804,
708
+ "loss": 14.7985,
709
+ "step": 100
710
+ }
711
+ ],
712
+ "logging_steps": 1,
713
+ "max_steps": 5833,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 1,
716
+ "save_steps": 100,
717
+ "total_flos": 1.2504616383074304e+16,
718
+ "train_batch_size": 1,
719
+ "trial_name": null,
720
+ "trial_params": null
721
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c7fae7a260158c38df930a244e04cfe8b8cc1b1f85587f1974c004c5bb661c
3
+ size 4856