Hugging Face's logo

CodeIsAbstract
/
HybridModelScratch_2

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
cb844de
·
verified ·
1 Parent(s): 8dce070

Training in progress, step 900, 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 +169 -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:b8845500a4dc1993ae580f65cd736c2ce8c1bff15668b71002335c45a51a47e8
3
+ size 579824888
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4954cdf965a3940fc6de41f864ead162d174b26dbc7b9885233f859011033e6f
3
+ size 1159794763
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11940f1313899a11d3e47a2d43f508134dd8e03ac7613f4eca32c754da2d1839
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16279ec4c3e65a1b1efa54fea9187732ebc8942013041dc30c624760de297a84
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 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9,
6
+ "eval_steps": 500,
7
+ "global_step": 900,
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": 2.1411664485931396,
15
+ "learning_rate": 0.0003266666666666667,
16
+ "loss": 34.3079,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.1,
21
+ "grad_norm": 2.7123711109161377,
22
+ "learning_rate": 0.00066,
23
+ "loss": 26.3975,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.15,
28
+ "grad_norm": 2.4478516578674316,
29
+ "learning_rate": 0.0009933333333333333,
30
+ "loss": 24.208,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.2,
35
+ "grad_norm": 1.5827449560165405,
36
+ "learning_rate": 0.000991822760447871,
37
+ "loss": 22.3278,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.25,
42
+ "grad_norm": 1.648890495300293,
43
+ "learning_rate": 0.0009669005017492141,
44
+ "loss": 21.0842,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.3,
49
+ "grad_norm": 1.509036660194397,
50
+ "learning_rate": 0.000926078506448917,
51
+ "loss": 20.095,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.35,
56
+ "grad_norm": 1.3168805837631226,
57
+ "learning_rate": 0.0008707469186363446,
58
+ "loss": 19.4834,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.4,
63
+ "grad_norm": 1.297710657119751,
64
+ "learning_rate": 0.0008027899891715287,
65
+ "loss": 18.9437,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.45,
70
+ "grad_norm": 1.1592856645584106,
71
+ "learning_rate": 0.0007245219097820409,
72
+ "loss": 18.3749,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.5,
77
+ "grad_norm": 1.155800461769104,
78
+ "learning_rate": 0.0006386080060392753,
79
+ "loss": 17.8605,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.5,
84
+ "eval_accuracy": 0.28156454336549924,
85
+ "eval_loss": 4.3490142822265625,
86
+ "eval_runtime": 9.9325,
87
+ "eval_samples_per_second": 97.66,
88
+ "eval_steps_per_second": 6.141,
89
+ "step": 500
90
+ },
91
+ {
92
+ "epoch": 0.55,
93
+ "grad_norm": 1.1437630653381348,
94
+ "learning_rate": 0.000547973972892822,
95
+ "loss": 17.3699,
96
+ "step": 550
97
+ },
98
+ {
99
+ "epoch": 0.6,
100
+ "grad_norm": 1.1172058582305908,
101
+ "learning_rate": 0.00045570624363794224,
102
+ "loss": 17.0134,
103
+ "step": 600
104
+ },
105
+ {
106
+ "epoch": 0.65,
107
+ "grad_norm": 1.0678249597549438,
108
+ "learning_rate": 0.0003649468851314669,
109
+ "loss": 16.751,
110
+ "step": 650
111
+ },
112
+ {
113
+ "epoch": 0.7,
114
+ "grad_norm": 0.9996118545532227,
115
+ "learning_rate": 0.00027878659847348176,
116
+ "loss": 16.5556,
117
+ "step": 700
118
+ },
119
+ {
120
+ "epoch": 0.75,
121
+ "grad_norm": 0.8965609669685364,
122
+ "learning_rate": 0.00020015946888825076,
123
+ "loss": 16.3919,
124
+ "step": 750
125
+ },
126
+ {
127
+ "epoch": 0.8,
128
+ "grad_norm": 0.7993431091308594,
129
+ "learning_rate": 0.00013174304897095113,
130
+ "loss": 16.2651,
131
+ "step": 800
132
+ },
133
+ {
134
+ "epoch": 0.85,
135
+ "grad_norm": 0.8439401388168335,
136
+ "learning_rate": 7.58671778454153e-05,
137
+ "loss": 16.1115,
138
+ "step": 850
139
+ },
140
+ {
141
+ "epoch": 0.9,
142
+ "grad_norm": 0.8115217685699463,
143
+ "learning_rate": 3.443464128710239e-05,
144
+ "loss": 16.0619,
145
+ "step": 900
146
+ }
147
+ ],
148
+ "logging_steps": 50,
149
+ "max_steps": 1000,
150
+ "num_input_tokens_seen": 0,
151
+ "num_train_epochs": 9223372036854775807,
152
+ "save_steps": 900,
153
+ "stateful_callbacks": {
154
+ "TrainerControl": {
155
+ "args": {
156
+ "should_epoch_stop": false,
157
+ "should_evaluate": false,
158
+ "should_log": false,
159
+ "should_save": true,
160
+ "should_training_stop": false
161
+ },
162
+ "attributes": {}
163
+ }
164
+ },
165
+ "total_flos": 1.505264972857344e+17,
166
+ "train_batch_size": 64,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de8bbaae5fe33a499938d0a9fff730e2e2f5b1a36b20f60bebb093bbde9edae
3
+ size 5841