Hugging Face's logo

SystemAdmin123
/
pythia-70m-deduped

Text Generation
Transformers
Safetensors
gpt_neox
axolotl
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
e3ee5a8
·
verified ·
1 Parent(s): a2b1ac4

Training in progress, step 100, checkpoint

Browse files
Files changed (14) hide show
  1. last-checkpoint/config.json +32 -0
  2. last-checkpoint/generation_config.json +7 -0
  3. last-checkpoint/model.safetensors +3 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/rng_state_0.pth +3 -0
  6. last-checkpoint/rng_state_1.pth +3 -0
  7. last-checkpoint/rng_state_2.pth +3 -0
  8. last-checkpoint/rng_state_3.pth +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/special_tokens_map.json +30 -0
  11. last-checkpoint/tokenizer.json +0 -0
  12. last-checkpoint/tokenizer_config.json +225 -0
  13. last-checkpoint/trainer_state.json +111 -0
  14. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-70m-deduped",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
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": 512,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
21
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.48.1",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50278
32
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "do_sample": true,
5
+ "eos_token_id": 0,
6
+ "transformers_version": "4.48.1"
7
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c113d8eb74e82df98d81f99bac3ece04382ceba4810f0cf895c30270d84a2c
3
+ size 140808752
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65d944f58636576490eb1308142ac897173c7cbaf7d06a5880cef4950e079e7
3
+ size 143306810
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4651e32e118f1ea1a8e26dfbbe64298593e12e6a71bcd36cb77f04f86d3f86d
3
+ size 15024
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c1eba909fbb51daca773a25c075f182b4096aff21c9b4ff19dbada2080ac99
3
+ size 15024
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28adb9f06e220aefdc723ea4380a84d42b8bfb87cc53ce65859d55ce1876f51c
3
+ size 15024
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423c49ed521f6986d20d8b29112b383f4b0f3f2e228084ef82c2ad7dcd5d1de8
3
+ size 15024
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
3
+ size 1064
last-checkpoint/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": "<|endoftext|>",
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
+ }
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 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50277": {
207
+ "content": "[PAD]",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ }
214
+ },
215
+ "bos_token": "<|endoftext|>",
216
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
217
+ "clean_up_tokenization_spaces": false,
218
+ "eos_token": "<|endoftext|>",
219
+ "extra_special_tokens": {},
220
+ "model_max_length": 1000000000000000019884624838656,
221
+ "pad_token": "<|endoftext|>",
222
+ "tokenizer_class": "GPTNeoXTokenizer",
223
+ "unk_token": "<|endoftext|>",
224
+ "use_fast": true
225
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 16.666666666666668,
5
+ "eval_steps": 200,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16666666666666666,
13
+ "eval_loss": 49.111328125,
14
+ "eval_runtime": 5.1361,
15
+ "eval_samples_per_second": 292.246,
16
+ "eval_steps_per_second": 2.336,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 1.6666666666666665,
21
+ "grad_norm": 88.0,
22
+ "learning_rate": 0.00019863613034027224,
23
+ "loss": 23.7299,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 3.3333333333333335,
28
+ "grad_norm": 1152.0,
29
+ "learning_rate": 0.0001879473751206489,
30
+ "loss": 19.5606,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "grad_norm": 235.0,
36
+ "learning_rate": 0.00016772815716257412,
37
+ "loss": 13.4897,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 6.666666666666667,
42
+ "grad_norm": 189.0,
43
+ "learning_rate": 0.00014016954246529696,
44
+ "loss": 26.7554,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 8.333333333333334,
49
+ "grad_norm": 74.5,
50
+ "learning_rate": 0.00010825793454723325,
51
+ "loss": 9.9479,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 10.0,
56
+ "grad_norm": 82.0,
57
+ "learning_rate": 7.54514512859201e-05,
58
+ "loss": 9.4116,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 11.666666666666666,
63
+ "grad_norm": 59.75,
64
+ "learning_rate": 4.530518418775733e-05,
65
+ "loss": 9.0891,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 13.333333333333334,
70
+ "grad_norm": 48.25,
71
+ "learning_rate": 2.1085949060360654e-05,
72
+ "loss": 8.7062,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 15.0,
77
+ "grad_norm": 41.5,
78
+ "learning_rate": 5.418275829936537e-06,
79
+ "loss": 8.604,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 16.666666666666668,
84
+ "grad_norm": 60.0,
85
+ "learning_rate": 0.0,
86
+ "loss": 8.5869,
87
+ "step": 100
88
+ }
89
+ ],
90
+ "logging_steps": 10,
91
+ "max_steps": 100,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 17,
94
+ "save_steps": 200,
95
+ "stateful_callbacks": {
96
+ "TrainerControl": {
97
+ "args": {
98
+ "should_epoch_stop": false,
99
+ "should_evaluate": false,
100
+ "should_log": false,
101
+ "should_save": true,
102
+ "should_training_stop": true
103
+ },
104
+ "attributes": {}
105
+ }
106
+ },
107
+ "total_flos": 6845149694918656.0,
108
+ "train_batch_size": 32,
109
+ "trial_name": null,
110
+ "trial_params": null
111
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1eff9c6436cd71f23ebc702d358448743c3d70e368f911cf52306011ce71d9f
3
+ size 6840