minpeter commited on
Commit
6061456
·
verified ·
1 Parent(s): 121965b

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 31989,
8
+ "eos_token_id": 31989,
9
+ "head_dim": 4,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 16,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 64,
14
+ "max_position_embeddings": 1024,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 4,
18
+ "num_hidden_layers": 2,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 31989,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.54.1",
28
+ "use_cache": false,
29
+ "vocab_size": 32000
30
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 31989,
4
+ "eos_token_id": 31989,
5
+ "pad_token_id": 31989,
6
+ "transformers_version": "4.54.1",
7
+ "use_cache": false
8
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbcc431d60365d9892d0d125b963ba50e742d7006faa6b3c27de78364a2185a
3
+ size 2066752
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8ddf19cc92bc2fdec7d7142903454ff8a568ba7a1522791951a991b492aa7f
3
+ size 4121235
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4697ad772eee8caffe599f8ac855a6f23f3029ebef7ed8bcd2b6d591ce783b2d
3
+ size 14391
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6137085b09493da9d6159e8c050c83cf7c7c75be5fdb00e9604cb034d7c6e959
3
+ size 1401
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "31989": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "31990": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "31991": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "31992": {
30
+ "content": "<tool_call>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "31993": {
38
+ "content": "</tool_call>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "31994": {
46
+ "content": "<think>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "31995": {
54
+ "content": "</think>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "31996": {
62
+ "content": "<|unused_special_token_0|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "31997": {
70
+ "content": "<|unused_special_token_1|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "31998": {
78
+ "content": "<|unused_special_token_2|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "31999": {
86
+ "content": "<|unused_special_token_3|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ }
93
+ },
94
+ "bos_token": null,
95
+ "clean_up_tokenization_spaces": false,
96
+ "eos_token": "<|endoftext|>",
97
+ "extra_special_tokens": {},
98
+ "model_max_length": 1000000000000000019884624838656,
99
+ "pad_token": "<|endoftext|>",
100
+ "split_special_tokens": false,
101
+ "tokenizer_class": "PreTrainedTokenizerFast",
102
+ "unk_token": "<|endoftext|>"
103
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.004318908180012093,
6
+ "eval_steps": 100,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 4.3189081800120926e-05,
14
+ "grad_norm": 0.220703125,
15
+ "learning_rate": 0.0,
16
+ "loss": 10.3655,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 8.637816360024185e-05,
21
+ "grad_norm": 0.2158203125,
22
+ "learning_rate": 8.635578583765112e-07,
23
+ "loss": 10.3669,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0001295672454003628,
28
+ "grad_norm": 0.267578125,
29
+ "learning_rate": 1.7271157167530224e-06,
30
+ "loss": 10.3661,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0001727563272004837,
35
+ "grad_norm": 0.625,
36
+ "learning_rate": 2.5906735751295338e-06,
37
+ "loss": 10.352,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.00021594540900060464,
42
+ "grad_norm": 0.2060546875,
43
+ "learning_rate": 3.454231433506045e-06,
44
+ "loss": 10.3656,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0002591344908007256,
49
+ "grad_norm": 0.2041015625,
50
+ "learning_rate": 4.3177892918825564e-06,
51
+ "loss": 10.3658,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0003023235726008465,
56
+ "grad_norm": 0.275390625,
57
+ "learning_rate": 5.1813471502590676e-06,
58
+ "loss": 10.3697,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0003455126544009674,
63
+ "grad_norm": 0.318359375,
64
+ "learning_rate": 6.044905008635579e-06,
65
+ "loss": 10.3582,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.00038870173620108835,
70
+ "grad_norm": 0.2412109375,
71
+ "learning_rate": 6.90846286701209e-06,
72
+ "loss": 10.3657,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.0004318908180012093,
77
+ "grad_norm": 0.24609375,
78
+ "learning_rate": 7.772020725388602e-06,
79
+ "loss": 10.3693,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.00047507989980133023,
84
+ "grad_norm": 0.20703125,
85
+ "learning_rate": 8.635578583765113e-06,
86
+ "loss": 10.3664,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0005182689816014512,
91
+ "grad_norm": 0.26171875,
92
+ "learning_rate": 9.499136442141624e-06,
93
+ "loss": 10.3676,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.0005614580634015721,
98
+ "grad_norm": 0.21484375,
99
+ "learning_rate": 1.0362694300518135e-05,
100
+ "loss": 10.3704,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.000604647145201693,
105
+ "grad_norm": 0.23046875,
106
+ "learning_rate": 1.1226252158894646e-05,
107
+ "loss": 10.3665,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.000647836227001814,
112
+ "grad_norm": 0.189453125,
113
+ "learning_rate": 1.2089810017271157e-05,
114
+ "loss": 10.3679,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0006910253088019348,
119
+ "grad_norm": 0.21875,
120
+ "learning_rate": 1.2953367875647668e-05,
121
+ "loss": 10.3683,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.0007342143906020558,
126
+ "grad_norm": 0.234375,
127
+ "learning_rate": 1.381692573402418e-05,
128
+ "loss": 10.3693,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0007774034724021767,
133
+ "grad_norm": 0.28125,
134
+ "learning_rate": 1.468048359240069e-05,
135
+ "loss": 10.3655,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.0008205925542022976,
140
+ "grad_norm": 0.205078125,
141
+ "learning_rate": 1.5544041450777204e-05,
142
+ "loss": 10.3689,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.0008637816360024186,
147
+ "grad_norm": 0.255859375,
148
+ "learning_rate": 1.6407599309153716e-05,
149
+ "loss": 10.3656,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.0009069707178025395,
154
+ "grad_norm": 0.2314453125,
155
+ "learning_rate": 1.7271157167530226e-05,
156
+ "loss": 10.3666,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0009501597996026605,
161
+ "grad_norm": 0.25,
162
+ "learning_rate": 1.8134715025906735e-05,
163
+ "loss": 10.3641,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.0009933488814027813,
168
+ "grad_norm": 0.2216796875,
169
+ "learning_rate": 1.8998272884283248e-05,
170
+ "loss": 10.3662,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0010365379632029023,
175
+ "grad_norm": 0.201171875,
176
+ "learning_rate": 1.9861830742659757e-05,
177
+ "loss": 10.3682,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.0010797270450030232,
182
+ "grad_norm": 0.2109375,
183
+ "learning_rate": 2.072538860103627e-05,
184
+ "loss": 10.3673,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.0011229161268031442,
189
+ "grad_norm": 0.2216796875,
190
+ "learning_rate": 2.158894645941278e-05,
191
+ "loss": 10.3672,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.001166105208603265,
196
+ "grad_norm": 0.2734375,
197
+ "learning_rate": 2.2452504317789292e-05,
198
+ "loss": 10.3693,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.001209294290403386,
203
+ "grad_norm": 0.2890625,
204
+ "learning_rate": 2.3316062176165802e-05,
205
+ "loss": 10.3654,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.001252483372203507,
210
+ "grad_norm": 0.283203125,
211
+ "learning_rate": 2.4179620034542315e-05,
212
+ "loss": 10.3677,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.001295672454003628,
217
+ "grad_norm": 0.2353515625,
218
+ "learning_rate": 2.5043177892918828e-05,
219
+ "loss": 10.3649,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.0013388615358037488,
224
+ "grad_norm": 0.205078125,
225
+ "learning_rate": 2.5906735751295337e-05,
226
+ "loss": 10.3635,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.0013820506176038696,
231
+ "grad_norm": 0.2119140625,
232
+ "learning_rate": 2.677029360967185e-05,
233
+ "loss": 10.3665,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.0014252396994039907,
238
+ "grad_norm": 0.2001953125,
239
+ "learning_rate": 2.763385146804836e-05,
240
+ "loss": 10.3649,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.0014684287812041115,
245
+ "grad_norm": 0.263671875,
246
+ "learning_rate": 2.8497409326424872e-05,
247
+ "loss": 10.3654,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.0015116178630042326,
252
+ "grad_norm": 0.28515625,
253
+ "learning_rate": 2.936096718480138e-05,
254
+ "loss": 10.3687,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.0015548069448043534,
259
+ "grad_norm": 0.2734375,
260
+ "learning_rate": 3.0224525043177894e-05,
261
+ "loss": 10.3703,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.0015979960266044744,
266
+ "grad_norm": 0.208984375,
267
+ "learning_rate": 3.108808290155441e-05,
268
+ "loss": 10.3681,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.0016411851084045953,
273
+ "grad_norm": 0.2353515625,
274
+ "learning_rate": 3.195164075993091e-05,
275
+ "loss": 10.3671,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.0016843741902047163,
280
+ "grad_norm": 0.2109375,
281
+ "learning_rate": 3.281519861830743e-05,
282
+ "loss": 10.37,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.0017275632720048372,
287
+ "grad_norm": 0.24609375,
288
+ "learning_rate": 3.367875647668394e-05,
289
+ "loss": 10.366,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.0017707523538049582,
294
+ "grad_norm": 0.212890625,
295
+ "learning_rate": 3.454231433506045e-05,
296
+ "loss": 10.3706,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.001813941435605079,
301
+ "grad_norm": 0.1962890625,
302
+ "learning_rate": 3.540587219343696e-05,
303
+ "loss": 10.3664,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0018571305174051999,
308
+ "grad_norm": 0.21875,
309
+ "learning_rate": 3.626943005181347e-05,
310
+ "loss": 10.3726,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.001900319599205321,
315
+ "grad_norm": 0.3203125,
316
+ "learning_rate": 3.713298791018998e-05,
317
+ "loss": 10.3727,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.0019435086810054417,
322
+ "grad_norm": 0.255859375,
323
+ "learning_rate": 3.7996545768566496e-05,
324
+ "loss": 10.3631,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.0019866977628055626,
329
+ "grad_norm": 0.193359375,
330
+ "learning_rate": 3.8860103626943e-05,
331
+ "loss": 10.3614,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.002029886844605684,
336
+ "grad_norm": 0.2314453125,
337
+ "learning_rate": 3.9723661485319515e-05,
338
+ "loss": 10.3715,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.0020730759264058047,
343
+ "grad_norm": 0.224609375,
344
+ "learning_rate": 4.0587219343696034e-05,
345
+ "loss": 10.3669,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.0021162650082059255,
350
+ "grad_norm": 0.2734375,
351
+ "learning_rate": 4.145077720207254e-05,
352
+ "loss": 10.3595,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.0021594540900060463,
357
+ "grad_norm": 0.69921875,
358
+ "learning_rate": 4.231433506044905e-05,
359
+ "loss": 10.3658,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.0022026431718061676,
364
+ "grad_norm": 0.1953125,
365
+ "learning_rate": 4.317789291882556e-05,
366
+ "loss": 10.3619,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.0022458322536062884,
371
+ "grad_norm": 0.203125,
372
+ "learning_rate": 4.404145077720207e-05,
373
+ "loss": 10.3636,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.0022890213354064093,
378
+ "grad_norm": 0.224609375,
379
+ "learning_rate": 4.4905008635578585e-05,
380
+ "loss": 10.3652,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.00233221041720653,
385
+ "grad_norm": 0.2060546875,
386
+ "learning_rate": 4.57685664939551e-05,
387
+ "loss": 10.3709,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.002375399499006651,
392
+ "grad_norm": 0.22265625,
393
+ "learning_rate": 4.6632124352331604e-05,
394
+ "loss": 10.3691,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.002418588580806772,
399
+ "grad_norm": 0.1962890625,
400
+ "learning_rate": 4.7495682210708117e-05,
401
+ "loss": 10.3668,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.002461777662606893,
406
+ "grad_norm": 0.251953125,
407
+ "learning_rate": 4.835924006908463e-05,
408
+ "loss": 10.3635,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.002504966744407014,
413
+ "grad_norm": 0.20703125,
414
+ "learning_rate": 4.922279792746114e-05,
415
+ "loss": 10.3682,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.0025481558262071347,
420
+ "grad_norm": 0.2021484375,
421
+ "learning_rate": 5.0086355785837655e-05,
422
+ "loss": 10.3633,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.002591344908007256,
427
+ "grad_norm": 0.1943359375,
428
+ "learning_rate": 5.094991364421416e-05,
429
+ "loss": 10.3658,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.002634533989807377,
434
+ "grad_norm": 0.2119140625,
435
+ "learning_rate": 5.1813471502590674e-05,
436
+ "loss": 10.3674,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.0026777230716074976,
441
+ "grad_norm": 0.1875,
442
+ "learning_rate": 5.267702936096719e-05,
443
+ "loss": 10.3652,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.0027209121534076184,
448
+ "grad_norm": 0.1962890625,
449
+ "learning_rate": 5.35405872193437e-05,
450
+ "loss": 10.3715,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.0027641012352077393,
455
+ "grad_norm": 0.3125,
456
+ "learning_rate": 5.4404145077720206e-05,
457
+ "loss": 10.3699,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.0028072903170078605,
462
+ "grad_norm": 0.263671875,
463
+ "learning_rate": 5.526770293609672e-05,
464
+ "loss": 10.361,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.0028504793988079814,
469
+ "grad_norm": 0.2412109375,
470
+ "learning_rate": 5.613126079447323e-05,
471
+ "loss": 10.3627,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.002893668480608102,
476
+ "grad_norm": 0.20703125,
477
+ "learning_rate": 5.6994818652849744e-05,
478
+ "loss": 10.3659,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.002936857562408223,
483
+ "grad_norm": 0.19921875,
484
+ "learning_rate": 5.785837651122625e-05,
485
+ "loss": 10.3686,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.0029800466442083443,
490
+ "grad_norm": 0.2177734375,
491
+ "learning_rate": 5.872193436960276e-05,
492
+ "loss": 10.367,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.003023235726008465,
497
+ "grad_norm": 0.22265625,
498
+ "learning_rate": 5.9585492227979276e-05,
499
+ "loss": 10.3683,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.003066424807808586,
504
+ "grad_norm": 0.244140625,
505
+ "learning_rate": 6.044905008635579e-05,
506
+ "loss": 10.3621,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.003109613889608707,
511
+ "grad_norm": 0.2470703125,
512
+ "learning_rate": 6.13126079447323e-05,
513
+ "loss": 10.3657,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.003152802971408828,
518
+ "grad_norm": 0.32421875,
519
+ "learning_rate": 6.217616580310881e-05,
520
+ "loss": 10.3647,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.003195992053208949,
525
+ "grad_norm": 0.2275390625,
526
+ "learning_rate": 6.303972366148531e-05,
527
+ "loss": 10.3607,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.0032391811350090697,
532
+ "grad_norm": 0.2041015625,
533
+ "learning_rate": 6.390328151986183e-05,
534
+ "loss": 10.3647,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.0032823702168091906,
539
+ "grad_norm": 0.185546875,
540
+ "learning_rate": 6.476683937823834e-05,
541
+ "loss": 10.3695,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.0033255592986093114,
546
+ "grad_norm": 0.203125,
547
+ "learning_rate": 6.563039723661487e-05,
548
+ "loss": 10.3706,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.0033687483804094327,
553
+ "grad_norm": 0.271484375,
554
+ "learning_rate": 6.649395509499136e-05,
555
+ "loss": 10.3686,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.0034119374622095535,
560
+ "grad_norm": 0.224609375,
561
+ "learning_rate": 6.735751295336788e-05,
562
+ "loss": 10.3653,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.0034551265440096743,
567
+ "grad_norm": 0.2197265625,
568
+ "learning_rate": 6.822107081174439e-05,
569
+ "loss": 10.3645,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.003498315625809795,
574
+ "grad_norm": 0.2109375,
575
+ "learning_rate": 6.90846286701209e-05,
576
+ "loss": 10.3627,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.0035415047076099164,
581
+ "grad_norm": 0.27734375,
582
+ "learning_rate": 6.994818652849742e-05,
583
+ "loss": 10.3682,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.0035846937894100372,
588
+ "grad_norm": 0.2041015625,
589
+ "learning_rate": 7.081174438687392e-05,
590
+ "loss": 10.367,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.003627882871210158,
595
+ "grad_norm": 0.318359375,
596
+ "learning_rate": 7.167530224525043e-05,
597
+ "loss": 10.3674,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.003671071953010279,
602
+ "grad_norm": 0.24609375,
603
+ "learning_rate": 7.253886010362694e-05,
604
+ "loss": 10.3654,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.0037142610348103997,
609
+ "grad_norm": 0.2734375,
610
+ "learning_rate": 7.340241796200347e-05,
611
+ "loss": 10.3628,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.003757450116610521,
616
+ "grad_norm": 0.2060546875,
617
+ "learning_rate": 7.426597582037997e-05,
618
+ "loss": 10.3677,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.003800639198410642,
623
+ "grad_norm": 0.255859375,
624
+ "learning_rate": 7.512953367875648e-05,
625
+ "loss": 10.3702,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.0038438282802107627,
630
+ "grad_norm": 0.2216796875,
631
+ "learning_rate": 7.599309153713299e-05,
632
+ "loss": 10.3669,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.0038870173620108835,
637
+ "grad_norm": 0.25390625,
638
+ "learning_rate": 7.68566493955095e-05,
639
+ "loss": 10.3623,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.003930206443811005,
644
+ "grad_norm": 0.216796875,
645
+ "learning_rate": 7.7720207253886e-05,
646
+ "loss": 10.3645,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.003973395525611125,
651
+ "grad_norm": 0.2109375,
652
+ "learning_rate": 7.858376511226252e-05,
653
+ "loss": 10.3628,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.004016584607411246,
658
+ "grad_norm": 0.32421875,
659
+ "learning_rate": 7.944732297063903e-05,
660
+ "loss": 10.3751,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.004059773689211368,
665
+ "grad_norm": 0.294921875,
666
+ "learning_rate": 8.031088082901554e-05,
667
+ "loss": 10.3659,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.004102962771011488,
672
+ "grad_norm": 0.31640625,
673
+ "learning_rate": 8.117443868739207e-05,
674
+ "loss": 10.3579,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.004146151852811609,
679
+ "grad_norm": 0.27734375,
680
+ "learning_rate": 8.203799654576857e-05,
681
+ "loss": 10.364,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.00418934093461173,
686
+ "grad_norm": 0.212890625,
687
+ "learning_rate": 8.290155440414508e-05,
688
+ "loss": 10.3689,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.004232530016411851,
693
+ "grad_norm": 0.19921875,
694
+ "learning_rate": 8.37651122625216e-05,
695
+ "loss": 10.3659,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.004275719098211972,
700
+ "grad_norm": 0.1904296875,
701
+ "learning_rate": 8.46286701208981e-05,
702
+ "loss": 10.3626,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.004318908180012093,
707
+ "grad_norm": 0.19921875,
708
+ "learning_rate": 8.54922279792746e-05,
709
+ "loss": 10.3679,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.004318908180012093,
714
+ "eval_loss": 10.376812934875488,
715
+ "eval_runtime": 15.7661,
716
+ "eval_samples_per_second": 1.522,
717
+ "eval_steps_per_second": 0.19,
718
+ "step": 100
719
+ }
720
+ ],
721
+ "logging_steps": 1,
722
+ "max_steps": 23154,
723
+ "num_input_tokens_seen": 0,
724
+ "num_train_epochs": 1,
725
+ "save_steps": 100,
726
+ "stateful_callbacks": {
727
+ "TrainerControl": {
728
+ "args": {
729
+ "should_epoch_stop": false,
730
+ "should_evaluate": false,
731
+ "should_log": false,
732
+ "should_save": true,
733
+ "should_training_stop": false
734
+ },
735
+ "attributes": {}
736
+ }
737
+ },
738
+ "total_flos": 319655116800.0,
739
+ "train_batch_size": 1,
740
+ "trial_name": null,
741
+ "trial_params": null
742
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5311951ebd78d801b2004d2883a9a33463eb75dabd82156ef0e18165de4dd6c9
3
+ size 5777