Hugging Face's logo

EleutherAI
/
pythia-1b-sentiment-first-ft

Text Generation
Transformers
Safetensors
gpt_neox
text-generation-inference
Model card Files
xet
Community
atmallen commited on
Commit
fe56b43
·
verified ·
1 Parent(s): 7ed026c

Training in progress, step 32768

Browse files
Files changed (12) hide show
  1. model.safetensors +1 -1
  2. tmp-checkpoint-1/config.json +29 -0
  3. tmp-checkpoint-1/generation_config.json +6 -0
  4. tmp-checkpoint-1/model.safetensors +3 -0
  5. tmp-checkpoint-1/optimizer.pt +3 -0
  6. tmp-checkpoint-1/rng_state.pth +3 -0
  7. tmp-checkpoint-1/scheduler.pt +3 -0
  8. tmp-checkpoint-1/special_tokens_map.json +24 -0
  9. tmp-checkpoint-1/tokenizer.json +0 -0
  10. tmp-checkpoint-1/tokenizer_config.json +212 -0
  11. tmp-checkpoint-1/trainer_state.json +61 -0
  12. tmp-checkpoint-1/training_args.bin +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebdfe570f6b0fbfb3422d7e53abfd2eb0976a57dac434a2d3d6c955b7ad97eea
3
  size 2023586384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257f6c4ef1ffeee93d13bab7fc2406c936ac3ba7b5a09accc30c0894cc46e69e
3
  size 2023586384
tmp-checkpoint-1/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 16,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 50304
29
+ }
tmp-checkpoint-1/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.36.2"
6
+ }
tmp-checkpoint-1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391e4f45aca253742873407d9d67053057e2b9e6596019681487103c5cbb275d
3
+ size 2023586384
tmp-checkpoint-1/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b03b0b35ebfebeb161ad58d5786483a4e80ce7144c2d03459ee6c657962118
3
+ size 2028891770
tmp-checkpoint-1/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
tmp-checkpoint-1/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651ea065d85e7962b015fecbe16bd3ae3cb5cff61fc329ee6f81f7577d260698
3
+ size 1064
tmp-checkpoint-1/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
+ }
tmp-checkpoint-1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tmp-checkpoint-1/tokenizer_config.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "model_max_length": 1000000000000000019884624838656,
209
+ "pad_token": "<|endoftext|>",
210
+ "tokenizer_class": "GPTNeoXTokenizer",
211
+ "unk_token": "<|endoftext|>"
212
+ }
tmp-checkpoint-1/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 4.2374186515808105,
3
+ "best_model_checkpoint": "/admin/home-alexmallen/elk-generalization/sft-models/pythia-1b-sentiment-first-ft/checkpoint-1",
4
+ "epoch": 0.0006129798482874875,
5
+ "eval_steps": 10000000000,
6
+ "global_step": 1,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "eval_val_acc_stderr": 0.007124041923148224,
14
+ "eval_val_accuracy": 0.5301548492257538,
15
+ "eval_val_loss": 4.2374186515808105,
16
+ "eval_val_runtime": 26.8554,
17
+ "eval_val_samples_per_second": 182.757,
18
+ "eval_val_steps_per_second": 45.689,
19
+ "step": 1
20
+ },
21
+ {
22
+ "epoch": 0.0,
23
+ "eval_val_alice_acc_stderr": 0.009082794641258494,
24
+ "eval_val_alice_accuracy": 0.3908523908523909,
25
+ "eval_val_alice_loss": 4.348449230194092,
26
+ "eval_val_alice_runtime": 15.021,
27
+ "eval_val_alice_samples_per_second": 192.131,
28
+ "eval_val_alice_steps_per_second": 48.066,
29
+ "step": 1
30
+ },
31
+ {
32
+ "epoch": 0.0,
33
+ "eval_val_bob_acc_stderr": 0.009912923089384363,
34
+ "eval_val_bob_accuracy": 0.7265084075173096,
35
+ "eval_val_bob_loss": 4.0783257484436035,
36
+ "eval_val_bob_runtime": 10.2741,
37
+ "eval_val_bob_samples_per_second": 196.806,
38
+ "eval_val_bob_steps_per_second": 49.25,
39
+ "step": 1
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "eval_val_bob_gt_acc_stderr": 0.011083605680821933,
44
+ "eval_val_bob_gt_accuracy": 0.5400593471810089,
45
+ "eval_val_bob_gt_loss": 4.27299690246582,
46
+ "eval_val_bob_gt_runtime": 10.2876,
47
+ "eval_val_bob_gt_samples_per_second": 196.546,
48
+ "eval_val_bob_gt_steps_per_second": 49.185,
49
+ "step": 1
50
+ }
51
+ ],
52
+ "logging_steps": 50,
53
+ "max_steps": 122325,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 75,
56
+ "save_steps": 10000000000,
57
+ "total_flos": 28080654336000.0,
58
+ "train_batch_size": 2,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
tmp-checkpoint-1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d808ebe4f651553008cbd261be24c43a69086777c5c4aea4b7c40fc156c995a3
3
+ size 4920