mnoukhov commited on
Commit
c3cadf0
1 Parent(s): 765d379

Training in progress, step 873, checkpoint

Browse files
checkpoint-873/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mnoukhov/pythia410m-sft-tldr",
3
+ "architectures": [
4
+ "GPTNeoXForSequenceClassification"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 2048,
24
+ "model_type": "gpt_neox",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 1,
28
+ "rope_scaling": null,
29
+ "rotary_emb_base": 10000,
30
+ "rotary_pct": 0.25,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.41.1",
34
+ "use_cache": true,
35
+ "use_parallel_residual": true,
36
+ "vocab_size": 50304
37
+ }
checkpoint-873/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd9bd17c42177e349f5ba87fd8a5536aa9d00b0b96302f87a3408650d068f982
3
+ size 1415329032
checkpoint-873/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c259c32f7bcf0a18eee31ffd2949f2ea393cd4d79b49775781ba7f79100acff
3
+ size 2830833850
checkpoint-873/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce3f1fd7866b93bfea3f328fd35124d6c8818c1dd3b24d163380d4a576714e9
3
+ size 14244
checkpoint-873/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa6c7732367401f5dbb2ac690c561b5de753159878c16a608f9d7eaa3badb59
3
+ size 1064
checkpoint-873/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|padding|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-873/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-873/tokenizer_config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "max_length": 580,
211
+ "model_max_length": 1000000000000000019884624838656,
212
+ "pad_token": "<|padding|>",
213
+ "stride": 0,
214
+ "tokenizer_class": "GPTNeoXTokenizer",
215
+ "truncation_side": "right",
216
+ "truncation_strategy": "longest_first",
217
+ "unk_token": "<|endoftext|>"
218
+ }
checkpoint-873/trainer_state.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6016540317022743,
5
+ "eval_steps": 291,
6
+ "global_step": 873,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06891798759476224,
13
+ "grad_norm": 18.475433349609375,
14
+ "learning_rate": 9.890136982846565e-06,
15
+ "loss": 0.6101,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.13783597518952448,
20
+ "grad_norm": 16.318273544311523,
21
+ "learning_rate": 9.552035901252971e-06,
22
+ "loss": 0.5632,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.2005513439007581,
27
+ "eval_accuracy": 0.7079783298727954,
28
+ "eval_loss": 0.5585106015205383,
29
+ "eval_runtime": 1152.8471,
30
+ "eval_samples_per_second": 72.691,
31
+ "eval_steps_per_second": 9.087,
32
+ "step": 291
33
+ },
34
+ {
35
+ "epoch": 0.2067539627842867,
36
+ "grad_norm": 16.05835723876953,
37
+ "learning_rate": 9.001378813765828e-06,
38
+ "loss": 0.5318,
39
+ "step": 300
40
+ },
41
+ {
42
+ "epoch": 0.27567195037904896,
43
+ "grad_norm": 6.903239727020264,
44
+ "learning_rate": 8.263878494553072e-06,
45
+ "loss": 0.5267,
46
+ "step": 400
47
+ },
48
+ {
49
+ "epoch": 0.34458993797381116,
50
+ "grad_norm": 9.29619026184082,
51
+ "learning_rate": 7.373972308696536e-06,
52
+ "loss": 0.4947,
53
+ "step": 500
54
+ },
55
+ {
56
+ "epoch": 0.4011026878015162,
57
+ "eval_accuracy": 0.7299706450920026,
58
+ "eval_loss": 0.5314406156539917,
59
+ "eval_runtime": 1150.6522,
60
+ "eval_samples_per_second": 72.83,
61
+ "eval_steps_per_second": 9.104,
62
+ "step": 582
63
+ },
64
+ {
65
+ "epoch": 0.4135079255685734,
66
+ "grad_norm": 7.382317543029785,
67
+ "learning_rate": 6.3732141693438686e-06,
68
+ "loss": 0.4753,
69
+ "step": 600
70
+ },
71
+ {
72
+ "epoch": 0.4824259131633356,
73
+ "grad_norm": 6.72527551651001,
74
+ "learning_rate": 5.308334189697317e-06,
75
+ "loss": 0.4647,
76
+ "step": 700
77
+ },
78
+ {
79
+ "epoch": 0.5513439007580979,
80
+ "grad_norm": 10.617219924926758,
81
+ "learning_rate": 4.2290566338312015e-06,
82
+ "loss": 0.4384,
83
+ "step": 800
84
+ },
85
+ {
86
+ "epoch": 0.6016540317022743,
87
+ "eval_accuracy": 0.7359967542540751,
88
+ "eval_loss": 0.5269714593887329,
89
+ "eval_runtime": 1151.3002,
90
+ "eval_samples_per_second": 72.789,
91
+ "eval_steps_per_second": 9.099,
92
+ "step": 873
93
+ }
94
+ ],
95
+ "logging_steps": 100,
96
+ "max_steps": 1451,
97
+ "num_input_tokens_seen": 0,
98
+ "num_train_epochs": 1,
99
+ "save_steps": 291,
100
+ "stateful_callbacks": {
101
+ "TrainerControl": {
102
+ "args": {
103
+ "should_epoch_stop": false,
104
+ "should_evaluate": false,
105
+ "should_log": false,
106
+ "should_save": true,
107
+ "should_training_stop": false
108
+ },
109
+ "attributes": {}
110
+ }
111
+ },
112
+ "total_flos": 0.0,
113
+ "train_batch_size": 8,
114
+ "trial_name": null,
115
+ "trial_params": null
116
+ }
checkpoint-873/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f067a16d006438bd235f769421ca0804d0ba51fb682819c90b04f5c99aad4f
3
+ size 5304