Hugging Face's logo

CodeIsAbstract
/
Hybrid_test_model_continued_modal

Safetensors
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
ee0d016
·
verified ·
1 Parent(s): 2115aab

Training in progress, step 500, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/model.safetensors +3 -0
  2. last-checkpoint/optimizer.pt +3 -0
  3. last-checkpoint/rng_state_0.pth +3 -0
  4. last-checkpoint/rng_state_1.pth +3 -0
  5. last-checkpoint/scheduler.pt +3 -0
  6. last-checkpoint/special_tokens_map.json +24 -0
  7. last-checkpoint/tokenizer.json +0 -0
  8. last-checkpoint/tokenizer_config.json +215 -0
  9. last-checkpoint/trainer_state.json +122 -0
  10. last-checkpoint/training_args.bin +3 -0
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07794a4766223bc04ee621df668181809a9680efb7f3402e9062c1d647bca82
3
+ size 847599616
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600a58d2b953c32b2ed9d106d83156d177ccdf78fe0147dc9a9c11b343b6fb6a
3
+ size 1386414411
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd45c472c02f69686aade1ec7cee7512c8dba6e6bde5e0bd023fd4f8f2f3548
3
+ size 14917
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09714a2ef70dd987c21ebd404103aea88be622e980ab90fe03c4cb22a4d6d0de
3
+ size 14917
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d607aeebc80b296b5bbc4bdd6acb23e9a6ea5c0feecf9462250a533d1c816c4
3
+ size 1465
last-checkpoint/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
+ }
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 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
209
+ "eos_token": "<|endoftext|>",
210
+ "extra_special_tokens": {},
211
+ "model_max_length": 1000000000,
212
+ "pad_token": "<|endoftext|>",
213
+ "tokenizer_class": "GPTNeoXTokenizer",
214
+ "unk_token": "<|endoftext|>"
215
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.16666666666666666,
6
+ "eval_steps": 200,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.016666666666666666,
14
+ "grad_norm": 688.1050415039062,
15
+ "learning_rate": 3.266666666666667e-05,
16
+ "loss": 75.5622,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.03333333333333333,
21
+ "grad_norm": 2096.35986328125,
22
+ "learning_rate": 6.6e-05,
23
+ "loss": 72.8577,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.05,
28
+ "grad_norm": 9884.8369140625,
29
+ "learning_rate": 9.933333333333334e-05,
30
+ "loss": 72.1371,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.06666666666666667,
35
+ "grad_norm": 6535.71044921875,
36
+ "learning_rate": 9.99270816881235e-05,
37
+ "loss": 71.871,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.06666666666666667,
42
+ "eval_accuracy": 0.2704493860434324,
43
+ "eval_loss": 4.5415215492248535,
44
+ "eval_runtime": 7.9125,
45
+ "eval_samples_per_second": 63.191,
46
+ "eval_steps_per_second": 2.022,
47
+ "step": 200
48
+ },
49
+ {
50
+ "epoch": 0.08333333333333333,
51
+ "grad_norm": 2549.314208984375,
52
+ "learning_rate": 9.970256684745258e-05,
53
+ "loss": 73.4509,
54
+ "step": 250
55
+ },
56
+ {
57
+ "epoch": 0.1,
58
+ "grad_norm": 30061.046875,
59
+ "learning_rate": 9.932710694482191e-05,
60
+ "loss": 75.4218,
61
+ "step": 300
62
+ },
63
+ {
64
+ "epoch": 0.11666666666666667,
65
+ "grad_norm": 48175.3359375,
66
+ "learning_rate": 9.880184223961573e-05,
67
+ "loss": 76.206,
68
+ "step": 350
69
+ },
70
+ {
71
+ "epoch": 0.13333333333333333,
72
+ "grad_norm": 32999.78515625,
73
+ "learning_rate": 9.812836794348004e-05,
74
+ "loss": 76.8908,
75
+ "step": 400
76
+ },
77
+ {
78
+ "epoch": 0.13333333333333333,
79
+ "eval_accuracy": 0.23184523867818646,
80
+ "eval_loss": 4.965036869049072,
81
+ "eval_runtime": 7.7766,
82
+ "eval_samples_per_second": 64.296,
83
+ "eval_steps_per_second": 2.057,
84
+ "step": 400
85
+ },
86
+ {
87
+ "epoch": 0.15,
88
+ "grad_norm": 41767.6640625,
89
+ "learning_rate": 9.730872937571739e-05,
90
+ "loss": 76.9205,
91
+ "step": 450
92
+ },
93
+ {
94
+ "epoch": 0.16666666666666666,
95
+ "grad_norm": 112764.3515625,
96
+ "learning_rate": 9.634541575171929e-05,
97
+ "loss": 77.5796,
98
+ "step": 500
99
+ }
100
+ ],
101
+ "logging_steps": 50,
102
+ "max_steps": 3000,
103
+ "num_input_tokens_seen": 0,
104
+ "num_train_epochs": 9223372036854775807,
105
+ "save_steps": 500,
106
+ "stateful_callbacks": {
107
+ "TrainerControl": {
108
+ "args": {
109
+ "should_epoch_stop": false,
110
+ "should_evaluate": false,
111
+ "should_log": false,
112
+ "should_save": true,
113
+ "should_training_stop": false
114
+ },
115
+ "attributes": {}
116
+ }
117
+ },
118
+ "total_flos": 0.0,
119
+ "train_batch_size": 16,
120
+ "trial_name": null,
121
+ "trial_params": null
122
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986c335dce0a01e0698e3f66cfceb6465b40d305cc210f79ef029898df312e46
3
+ size 5841