Hugging Face's logo

CodeIsAbstract
/
HybridModelScratch_

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
96bdda0
·
verified ·
1 Parent(s): 14aa430

Training in progress, step 200, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +31 -0
  2. last-checkpoint/model.safetensors +3 -0
  3. last-checkpoint/optimizer.pt +3 -0
  4. last-checkpoint/rng_state.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 +80 -0
  10. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridFourierLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "dropout": 0.05,
7
+ "dtype": "float32",
8
+ "eos_token_id": 0,
9
+ "latent_dim": 768,
10
+ "layer_types": [
11
+ "linear",
12
+ "linear",
13
+ "linear",
14
+ "softmax",
15
+ "linear",
16
+ "linear",
17
+ "linear",
18
+ "softmax",
19
+ "linear",
20
+ "linear",
21
+ "linear",
22
+ "softmax"
23
+ ],
24
+ "model_type": "hybrid_fourier_lm",
25
+ "num_layers": 12,
26
+ "num_modes": 64,
27
+ "pad_token_id": 0,
28
+ "time_scale": 128.0,
29
+ "transformers_version": "4.56.0",
30
+ "vocab_size": 50277
31
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66886050e435756ef5a7c49a69ae84363711c5f2bc7b3b5ebe3bf6a9bda5b749
3
+ size 579824888
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f7b73ea97ba098f486f95967fa0a7351e9d606099e9de265782b06a33955a2
3
+ size 1159794763
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f879f5f67a208b766c17cb348fca9d544480e749ad05d8f2acb8625bebbaf11
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a613d380f06e14f7b3ddc807a9d67116b9bcb0317fb8fbbd77c2d40723ed0e8
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 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.2,
6
+ "eval_steps": 100,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05,
14
+ "grad_norm": 6.820826530456543,
15
+ "learning_rate": 3.266666666666667e-05,
16
+ "loss": 39.8282,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.1,
21
+ "grad_norm": 2.321176290512085,
22
+ "learning_rate": 6.6e-05,
23
+ "loss": 32.0977,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.1,
28
+ "eval_accuracy": 0.11411070917707537,
29
+ "eval_loss": 7.302488327026367,
30
+ "eval_runtime": 12.8861,
31
+ "eval_samples_per_second": 75.275,
32
+ "eval_steps_per_second": 4.734,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "grad_norm": 2.403538465499878,
38
+ "learning_rate": 9.933333333333334e-05,
39
+ "loss": 27.9639,
40
+ "step": 150
41
+ },
42
+ {
43
+ "epoch": 0.2,
44
+ "grad_norm": 2.440488338470459,
45
+ "learning_rate": 9.91822760447871e-05,
46
+ "loss": 26.0238,
47
+ "step": 200
48
+ },
49
+ {
50
+ "epoch": 0.2,
51
+ "eval_accuracy": 0.16184917453329808,
52
+ "eval_loss": 6.333618640899658,
53
+ "eval_runtime": 13.3491,
54
+ "eval_samples_per_second": 72.664,
55
+ "eval_steps_per_second": 4.57,
56
+ "step": 200
57
+ }
58
+ ],
59
+ "logging_steps": 50,
60
+ "max_steps": 1000,
61
+ "num_input_tokens_seen": 0,
62
+ "num_train_epochs": 9223372036854775807,
63
+ "save_steps": 200,
64
+ "stateful_callbacks": {
65
+ "TrainerControl": {
66
+ "args": {
67
+ "should_epoch_stop": false,
68
+ "should_evaluate": false,
69
+ "should_log": false,
70
+ "should_save": true,
71
+ "should_training_stop": false
72
+ },
73
+ "attributes": {}
74
+ }
75
+ },
76
+ "total_flos": 3.34503327301632e+16,
77
+ "train_batch_size": 64,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec0634c3bc1f1b261fa029e521f51d3974d5a8f44775595be1925837769a398d
3
+ size 5841