Hugging Face's logo

RylanSchaeffer
/
pythia-70m_tatsu-lab_alpaca_farm_sftsd0_policy_pythia-6.9b_gold_pythia-6.9b_noise0.25_rmsd2

Text Classification
Transformers
Safetensors
gpt_neox
trl
reward-trainer
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
RylanSchaeffer commited on
Commit
2c376f8
·
verified ·
1 Parent(s): 838018b

End of training

Browse files
Files changed (7) hide show
  1. README.md +143 -0
  2. config.json +37 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +214 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0
4
+ tags:
5
+ - trl
6
+ - reward-trainer
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: pythia-70m_tatsu-lab_alpaca_farm_sftsd0_policy_pythia-6.9b_gold_pythia-6.9b_noise0.25_rmsd2
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/rylan/switching-rms-rm/runs/gent74g7)
19
+ # pythia-70m_tatsu-lab_alpaca_farm_sftsd0_policy_pythia-6.9b_gold_pythia-6.9b_noise0.25_rmsd2
20
+
21
+ This model is a fine-tuned version of [RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0](https://huggingface.co/RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.7529
24
+ - Accuracy: 0.5671
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 1e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
+ - seed: 2
47
+ - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 32
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.025
52
+ - num_epochs: 5
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
58
+ | No log | 0 | 0 | 0.8944 | 0.5170 |
59
+ | 0.8921 | 0.0648 | 100 | 0.8872 | 0.5112 |
60
+ | 0.8152 | 0.1296 | 200 | 0.8723 | 0.5193 |
61
+ | 0.8792 | 0.1944 | 300 | 0.8443 | 0.5158 |
62
+ | 0.7962 | 0.2592 | 400 | 0.8243 | 0.5201 |
63
+ | 0.8746 | 0.3239 | 500 | 0.8063 | 0.5316 |
64
+ | 0.8337 | 0.3887 | 600 | 0.8026 | 0.5324 |
65
+ | 0.773 | 0.4535 | 700 | 0.7967 | 0.5309 |
66
+ | 0.819 | 0.5183 | 800 | 0.7868 | 0.5475 |
67
+ | 0.8003 | 0.5831 | 900 | 0.7928 | 0.5355 |
68
+ | 0.8102 | 0.6479 | 1000 | 0.7819 | 0.5471 |
69
+ | 0.8276 | 0.7127 | 1100 | 0.7800 | 0.5482 |
70
+ | 0.8129 | 0.7775 | 1200 | 0.7744 | 0.5509 |
71
+ | 0.799 | 0.8422 | 1300 | 0.7689 | 0.5475 |
72
+ | 0.8093 | 0.9070 | 1400 | 0.7677 | 0.5502 |
73
+ | 0.7476 | 0.9718 | 1500 | 0.7668 | 0.5498 |
74
+ | 0.803 | 1.0366 | 1600 | 0.7681 | 0.5529 |
75
+ | 0.7528 | 1.1014 | 1700 | 0.7713 | 0.5494 |
76
+ | 0.7498 | 1.1662 | 1800 | 0.7679 | 0.5475 |
77
+ | 0.7593 | 1.2310 | 1900 | 0.7623 | 0.5513 |
78
+ | 0.7437 | 1.2958 | 2000 | 0.7591 | 0.5556 |
79
+ | 0.734 | 1.3605 | 2100 | 0.7615 | 0.5525 |
80
+ | 0.7392 | 1.4253 | 2200 | 0.7642 | 0.5590 |
81
+ | 0.7948 | 1.4901 | 2300 | 0.7619 | 0.5633 |
82
+ | 0.7133 | 1.5549 | 2400 | 0.7618 | 0.5656 |
83
+ | 0.7591 | 1.6197 | 2500 | 0.7576 | 0.5590 |
84
+ | 0.7204 | 1.6845 | 2600 | 0.7589 | 0.5579 |
85
+ | 0.7805 | 1.7493 | 2700 | 0.7555 | 0.5625 |
86
+ | 0.7388 | 1.8141 | 2800 | 0.7595 | 0.5463 |
87
+ | 0.7981 | 1.8788 | 2900 | 0.7601 | 0.5556 |
88
+ | 0.7379 | 1.9436 | 3000 | 0.7593 | 0.5525 |
89
+ | 0.7778 | 2.0084 | 3100 | 0.7615 | 0.5575 |
90
+ | 0.783 | 2.0732 | 3200 | 0.7577 | 0.5629 |
91
+ | 0.7619 | 2.1380 | 3300 | 0.7528 | 0.5594 |
92
+ | 0.7627 | 2.2028 | 3400 | 0.7545 | 0.5610 |
93
+ | 0.7603 | 2.2676 | 3500 | 0.7548 | 0.5660 |
94
+ | 0.7184 | 2.3324 | 3600 | 0.7563 | 0.5571 |
95
+ | 0.7477 | 2.3971 | 3700 | 0.7547 | 0.5563 |
96
+ | 0.7507 | 2.4619 | 3800 | 0.7531 | 0.5567 |
97
+ | 0.8013 | 2.5267 | 3900 | 0.7462 | 0.5640 |
98
+ | 0.6982 | 2.5915 | 4000 | 0.7576 | 0.5660 |
99
+ | 0.7461 | 2.6563 | 4100 | 0.7539 | 0.5671 |
100
+ | 0.7397 | 2.7211 | 4200 | 0.7548 | 0.5606 |
101
+ | 0.8002 | 2.7859 | 4300 | 0.7543 | 0.5583 |
102
+ | 0.7243 | 2.8507 | 4400 | 0.7529 | 0.5571 |
103
+ | 0.7277 | 2.9155 | 4500 | 0.7545 | 0.5606 |
104
+ | 0.7793 | 2.9802 | 4600 | 0.7523 | 0.5656 |
105
+ | 0.695 | 3.0450 | 4700 | 0.7563 | 0.5629 |
106
+ | 0.7799 | 3.1098 | 4800 | 0.7573 | 0.5594 |
107
+ | 0.7404 | 3.1746 | 4900 | 0.7558 | 0.5544 |
108
+ | 0.7078 | 3.2394 | 5000 | 0.7523 | 0.5656 |
109
+ | 0.7769 | 3.3042 | 5100 | 0.7490 | 0.5679 |
110
+ | 0.7502 | 3.3690 | 5200 | 0.7528 | 0.5625 |
111
+ | 0.7593 | 3.4338 | 5300 | 0.7550 | 0.5660 |
112
+ | 0.7613 | 3.4985 | 5400 | 0.7552 | 0.5625 |
113
+ | 0.7496 | 3.5633 | 5500 | 0.7535 | 0.5640 |
114
+ | 0.7696 | 3.6281 | 5600 | 0.7542 | 0.5621 |
115
+ | 0.737 | 3.6929 | 5700 | 0.7530 | 0.5656 |
116
+ | 0.773 | 3.7577 | 5800 | 0.7558 | 0.5586 |
117
+ | 0.7388 | 3.8225 | 5900 | 0.7509 | 0.5633 |
118
+ | 0.741 | 3.8873 | 6000 | 0.7521 | 0.5571 |
119
+ | 0.7451 | 3.9521 | 6100 | 0.7522 | 0.5698 |
120
+ | 0.7434 | 4.0168 | 6200 | 0.7559 | 0.5617 |
121
+ | 0.7884 | 4.0816 | 6300 | 0.7523 | 0.5579 |
122
+ | 0.8049 | 4.1464 | 6400 | 0.7544 | 0.5706 |
123
+ | 0.8049 | 4.2112 | 6500 | 0.7534 | 0.5629 |
124
+ | 0.741 | 4.2760 | 6600 | 0.7539 | 0.5613 |
125
+ | 0.7505 | 4.3408 | 6700 | 0.7550 | 0.5691 |
126
+ | 0.7879 | 4.4056 | 6800 | 0.7530 | 0.5687 |
127
+ | 0.7291 | 4.4704 | 6900 | 0.7572 | 0.5540 |
128
+ | 0.7485 | 4.5351 | 7000 | 0.7535 | 0.5629 |
129
+ | 0.7656 | 4.5999 | 7100 | 0.7547 | 0.5656 |
130
+ | 0.7713 | 4.6647 | 7200 | 0.7500 | 0.5648 |
131
+ | 0.7772 | 4.7295 | 7300 | 0.7536 | 0.5617 |
132
+ | 0.7662 | 4.7943 | 7400 | 0.7538 | 0.5610 |
133
+ | 0.741 | 4.8591 | 7500 | 0.7531 | 0.5640 |
134
+ | 0.7274 | 4.9239 | 7600 | 0.7543 | 0.5629 |
135
+ | 0.7833 | 4.9887 | 7700 | 0.7530 | 0.5664 |
136
+
137
+
138
+ ### Framework versions
139
+
140
+ - Transformers 4.42.4
141
+ - Pytorch 2.3.0+cu121
142
+ - Datasets 2.20.0
143
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "RylanSchaeffer/EleutherAI_pythia-70m_tatsu-lab_alpaca_farm_sftseed0",
3
+ "architectures": [
4
+ "GPTNeoXForSequenceClassification"
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
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2048,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 2048,
24
+ "model_type": "gpt_neox",
25
+ "num_attention_heads": 8,
26
+ "num_hidden_layers": 6,
27
+ "pad_token_id": 0,
28
+ "rope_scaling": null,
29
+ "rotary_emb_base": 10000,
30
+ "rotary_pct": 0.25,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.42.4",
34
+ "use_cache": false,
35
+ "use_parallel_residual": true,
36
+ "vocab_size": 50304
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e868d4e6b702f35cd62f50479a41e533ff2d5963ec4504f63dac32ccf4136c55
3
+ size 89351576
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "model_max_length": 1000000000000000019884624838656,
211
+ "pad_token": "<|endoftext|>",
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "unk_token": "<|endoftext|>"
214
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30320e3e587500e4916832ce7b10ac67752c7d502bf1e317de747c9a84d5b70
3
+ size 5304