Hugging Face's logo

wabu
/
1e-06_AmpGPT2

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
wabu commited on
Commit
0e591a4
•
1 Parent(s): 7fde9f0

Upload 14 files

Browse files
Files changed (14) hide show
  1. README.md +109 -0
  2. all_results.json +15 -0
  3. config.json +39 -0
  4. eval_results.json +10 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. special_tokens_map.json +23 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +19 -0
  11. train_results.json +8 -0
  12. trainer_state.json +594 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: nferruz/ProtGPT2
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: output_dir_clean_df_10-100_noX_100_1_epoch_cluster
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # output_dir_clean_df_10-100_noX_100_1_epoch_cluster
17
+
18
+ This model is a fine-tuned version of [nferruz/ProtGPT2](https://huggingface.co/nferruz/ProtGPT2) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 5.3807
21
+ - Accuracy: 0.2682
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-06
41
+ - train_batch_size: 24
42
+ - eval_batch_size: 24
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 50.0
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 197 | 6.2811 | 0.2041 |
53
+ | No log | 2.0 | 394 | 6.1540 | 0.2116 |
54
+ | 6.3092 | 3.0 | 591 | 6.0786 | 0.2153 |
55
+ | 6.3092 | 4.0 | 788 | 6.0237 | 0.2177 |
56
+ | 6.3092 | 5.0 | 985 | 5.9779 | 0.2200 |
57
+ | 6.0762 | 6.0 | 1182 | 5.9383 | 0.2222 |
58
+ | 6.0762 | 7.0 | 1379 | 5.9011 | 0.2249 |
59
+ | 5.9715 | 8.0 | 1576 | 5.8651 | 0.2273 |
60
+ | 5.9715 | 9.0 | 1773 | 5.8307 | 0.2302 |
61
+ | 5.9715 | 10.0 | 1970 | 5.8002 | 0.2320 |
62
+ | 5.8814 | 11.0 | 2167 | 5.7723 | 0.2338 |
63
+ | 5.8814 | 12.0 | 2364 | 5.7463 | 0.2355 |
64
+ | 5.8123 | 13.0 | 2561 | 5.7220 | 0.2371 |
65
+ | 5.8123 | 14.0 | 2758 | 5.6994 | 0.2386 |
66
+ | 5.8123 | 15.0 | 2955 | 5.6781 | 0.2404 |
67
+ | 5.7544 | 16.0 | 3152 | 5.6581 | 0.2419 |
68
+ | 5.7544 | 17.0 | 3349 | 5.6391 | 0.2433 |
69
+ | 5.7009 | 18.0 | 3546 | 5.6211 | 0.2450 |
70
+ | 5.7009 | 19.0 | 3743 | 5.6044 | 0.2466 |
71
+ | 5.7009 | 20.0 | 3940 | 5.5888 | 0.2482 |
72
+ | 5.6629 | 21.0 | 4137 | 5.5735 | 0.2493 |
73
+ | 5.6629 | 22.0 | 4334 | 5.5588 | 0.2507 |
74
+ | 5.6235 | 23.0 | 4531 | 5.5451 | 0.2520 |
75
+ | 5.6235 | 24.0 | 4728 | 5.5320 | 0.2531 |
76
+ | 5.6235 | 25.0 | 4925 | 5.5197 | 0.2541 |
77
+ | 5.5865 | 26.0 | 5122 | 5.5078 | 0.2552 |
78
+ | 5.5865 | 27.0 | 5319 | 5.4969 | 0.2562 |
79
+ | 5.5649 | 28.0 | 5516 | 5.4866 | 0.2573 |
80
+ | 5.5649 | 29.0 | 5713 | 5.4765 | 0.2583 |
81
+ | 5.5649 | 30.0 | 5910 | 5.4670 | 0.2595 |
82
+ | 5.5322 | 31.0 | 6107 | 5.4582 | 0.2604 |
83
+ | 5.5322 | 32.0 | 6304 | 5.4500 | 0.2612 |
84
+ | 5.5168 | 33.0 | 6501 | 5.4424 | 0.2618 |
85
+ | 5.5168 | 34.0 | 6698 | 5.4350 | 0.2627 |
86
+ | 5.5168 | 35.0 | 6895 | 5.4283 | 0.2633 |
87
+ | 5.4984 | 36.0 | 7092 | 5.4219 | 0.2640 |
88
+ | 5.4984 | 37.0 | 7289 | 5.4161 | 0.2647 |
89
+ | 5.4984 | 38.0 | 7486 | 5.4107 | 0.2651 |
90
+ | 5.48 | 39.0 | 7683 | 5.4058 | 0.2656 |
91
+ | 5.48 | 40.0 | 7880 | 5.4014 | 0.2660 |
92
+ | 5.4665 | 41.0 | 8077 | 5.3974 | 0.2665 |
93
+ | 5.4665 | 42.0 | 8274 | 5.3936 | 0.2668 |
94
+ | 5.4665 | 43.0 | 8471 | 5.3905 | 0.2671 |
95
+ | 5.4612 | 44.0 | 8668 | 5.3878 | 0.2674 |
96
+ | 5.4612 | 45.0 | 8865 | 5.3855 | 0.2677 |
97
+ | 5.4515 | 46.0 | 9062 | 5.3836 | 0.2679 |
98
+ | 5.4515 | 47.0 | 9259 | 5.3822 | 0.2680 |
99
+ | 5.4515 | 48.0 | 9456 | 5.3812 | 0.2681 |
100
+ | 5.4453 | 49.0 | 9653 | 5.3808 | 0.2682 |
101
+ | 5.4453 | 50.0 | 9850 | 5.3807 | 0.2682 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.38.0.dev0
107
+ - Pytorch 2.2.0+cu121
108
+ - Datasets 2.16.1
109
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "eval_accuracy": 0.26820817239978917,
4
+ "eval_loss": 5.380664825439453,
5
+ "eval_runtime": 15.4842,
6
+ "eval_samples": 1169,
7
+ "eval_samples_per_second": 75.496,
8
+ "eval_steps_per_second": 3.165,
9
+ "perplexity": 217.16660532635697,
10
+ "train_loss": 5.665375294951618,
11
+ "train_runtime": 8010.6738,
12
+ "train_samples": 4718,
13
+ "train_samples_per_second": 29.448,
14
+ "train_steps_per_second": 1.23
15
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nferruz/ProtGPT2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 0,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "eval_accuracy": 0.26820817239978917,
4
+ "eval_loss": 5.380664825439453,
5
+ "eval_runtime": 15.4842,
6
+ "eval_samples": 1169,
7
+ "eval_samples_per_second": 75.496,
8
+ "eval_steps_per_second": 3.165,
9
+ "perplexity": 217.16660532635697
10
+ }
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": "4.38.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c9af14976615f4628bd7ef316fb4102e46cb7871af6d33dd6c8d0ff8ab26f5
3
+ size 3096165928
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "train_loss": 5.665375294951618,
4
+ "train_runtime": 8010.6738,
5
+ "train_samples": 4718,
6
+ "train_samples_per_second": 29.448,
7
+ "train_steps_per_second": 1.23
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
+ "eval_steps": 500,
6
+ "global_step": 9850,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.2041285394578808,
14
+ "eval_loss": 6.281060695648193,
15
+ "eval_runtime": 15.5858,
16
+ "eval_samples_per_second": 75.004,
17
+ "eval_steps_per_second": 3.144,
18
+ "step": 197
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.21164597212501404,
23
+ "eval_loss": 6.153988838195801,
24
+ "eval_runtime": 15.6138,
25
+ "eval_samples_per_second": 74.869,
26
+ "eval_steps_per_second": 3.138,
27
+ "step": 394
28
+ },
29
+ {
30
+ "epoch": 2.54,
31
+ "learning_rate": 9.49238578680203e-07,
32
+ "loss": 6.3092,
33
+ "step": 500
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.21526643682332305,
38
+ "eval_loss": 6.078564167022705,
39
+ "eval_runtime": 15.5839,
40
+ "eval_samples_per_second": 75.013,
41
+ "eval_steps_per_second": 3.144,
42
+ "step": 591
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_accuracy": 0.21773768480355307,
47
+ "eval_loss": 6.023652076721191,
48
+ "eval_runtime": 15.5937,
49
+ "eval_samples_per_second": 74.966,
50
+ "eval_steps_per_second": 3.142,
51
+ "step": 788
52
+ },
53
+ {
54
+ "epoch": 5.0,
55
+ "eval_accuracy": 0.22000155533089666,
56
+ "eval_loss": 5.977902412414551,
57
+ "eval_runtime": 15.5893,
58
+ "eval_samples_per_second": 74.987,
59
+ "eval_steps_per_second": 3.143,
60
+ "step": 985
61
+ },
62
+ {
63
+ "epoch": 5.08,
64
+ "learning_rate": 8.984771573604061e-07,
65
+ "loss": 6.0762,
66
+ "step": 1000
67
+ },
68
+ {
69
+ "epoch": 6.0,
70
+ "eval_accuracy": 0.22224814440383303,
71
+ "eval_loss": 5.93832540512085,
72
+ "eval_runtime": 15.5855,
73
+ "eval_samples_per_second": 75.005,
74
+ "eval_steps_per_second": 3.144,
75
+ "step": 1182
76
+ },
77
+ {
78
+ "epoch": 7.0,
79
+ "eval_accuracy": 0.22491812910974587,
80
+ "eval_loss": 5.901119709014893,
81
+ "eval_runtime": 15.5994,
82
+ "eval_samples_per_second": 74.939,
83
+ "eval_steps_per_second": 3.141,
84
+ "step": 1379
85
+ },
86
+ {
87
+ "epoch": 7.61,
88
+ "learning_rate": 8.47715736040609e-07,
89
+ "loss": 5.9715,
90
+ "step": 1500
91
+ },
92
+ {
93
+ "epoch": 8.0,
94
+ "eval_accuracy": 0.22732889199955067,
95
+ "eval_loss": 5.865082263946533,
96
+ "eval_runtime": 15.5774,
97
+ "eval_samples_per_second": 75.044,
98
+ "eval_steps_per_second": 3.146,
99
+ "step": 1576
100
+ },
101
+ {
102
+ "epoch": 9.0,
103
+ "eval_accuracy": 0.23017169124953557,
104
+ "eval_loss": 5.830700874328613,
105
+ "eval_runtime": 15.5777,
106
+ "eval_samples_per_second": 75.043,
107
+ "eval_steps_per_second": 3.146,
108
+ "step": 1773
109
+ },
110
+ {
111
+ "epoch": 10.0,
112
+ "eval_accuracy": 0.23200352541669908,
113
+ "eval_loss": 5.800230503082275,
114
+ "eval_runtime": 15.5656,
115
+ "eval_samples_per_second": 75.102,
116
+ "eval_steps_per_second": 3.148,
117
+ "step": 1970
118
+ },
119
+ {
120
+ "epoch": 10.15,
121
+ "learning_rate": 7.96954314720812e-07,
122
+ "loss": 5.8814,
123
+ "step": 2000
124
+ },
125
+ {
126
+ "epoch": 11.0,
127
+ "eval_accuracy": 0.23377487449343737,
128
+ "eval_loss": 5.772307872772217,
129
+ "eval_runtime": 15.4454,
130
+ "eval_samples_per_second": 75.686,
131
+ "eval_steps_per_second": 3.172,
132
+ "step": 2167
133
+ },
134
+ {
135
+ "epoch": 12.0,
136
+ "eval_accuracy": 0.23547709775254685,
137
+ "eval_loss": 5.7462639808654785,
138
+ "eval_runtime": 15.4201,
139
+ "eval_samples_per_second": 75.81,
140
+ "eval_steps_per_second": 3.178,
141
+ "step": 2364
142
+ },
143
+ {
144
+ "epoch": 12.69,
145
+ "learning_rate": 7.461928934010153e-07,
146
+ "loss": 5.8123,
147
+ "step": 2500
148
+ },
149
+ {
150
+ "epoch": 13.0,
151
+ "eval_accuracy": 0.23705835083080593,
152
+ "eval_loss": 5.721967697143555,
153
+ "eval_runtime": 15.4201,
154
+ "eval_samples_per_second": 75.81,
155
+ "eval_steps_per_second": 3.178,
156
+ "step": 2561
157
+ },
158
+ {
159
+ "epoch": 14.0,
160
+ "eval_accuracy": 0.23861368172745417,
161
+ "eval_loss": 5.699427127838135,
162
+ "eval_runtime": 15.4205,
163
+ "eval_samples_per_second": 75.808,
164
+ "eval_steps_per_second": 3.178,
165
+ "step": 2758
166
+ },
167
+ {
168
+ "epoch": 15.0,
169
+ "eval_accuracy": 0.24036774934978528,
170
+ "eval_loss": 5.678054332733154,
171
+ "eval_runtime": 15.4369,
172
+ "eval_samples_per_second": 75.728,
173
+ "eval_steps_per_second": 3.174,
174
+ "step": 2955
175
+ },
176
+ {
177
+ "epoch": 15.23,
178
+ "learning_rate": 6.954314720812183e-07,
179
+ "loss": 5.7544,
180
+ "step": 3000
181
+ },
182
+ {
183
+ "epoch": 16.0,
184
+ "eval_accuracy": 0.24193172097363713,
185
+ "eval_loss": 5.658110618591309,
186
+ "eval_runtime": 15.6095,
187
+ "eval_samples_per_second": 74.89,
188
+ "eval_steps_per_second": 3.139,
189
+ "step": 3152
190
+ },
191
+ {
192
+ "epoch": 17.0,
193
+ "eval_accuracy": 0.24325375223578816,
194
+ "eval_loss": 5.639050483703613,
195
+ "eval_runtime": 15.6045,
196
+ "eval_samples_per_second": 74.914,
197
+ "eval_steps_per_second": 3.14,
198
+ "step": 3349
199
+ },
200
+ {
201
+ "epoch": 17.77,
202
+ "learning_rate": 6.446700507614214e-07,
203
+ "loss": 5.7009,
204
+ "step": 3500
205
+ },
206
+ {
207
+ "epoch": 18.0,
208
+ "eval_accuracy": 0.24503374203973005,
209
+ "eval_loss": 5.621128082275391,
210
+ "eval_runtime": 15.5812,
211
+ "eval_samples_per_second": 75.026,
212
+ "eval_steps_per_second": 3.145,
213
+ "step": 3546
214
+ },
215
+ {
216
+ "epoch": 19.0,
217
+ "eval_accuracy": 0.24660635439078551,
218
+ "eval_loss": 5.604429721832275,
219
+ "eval_runtime": 15.5986,
220
+ "eval_samples_per_second": 74.943,
221
+ "eval_steps_per_second": 3.141,
222
+ "step": 3743
223
+ },
224
+ {
225
+ "epoch": 20.0,
226
+ "eval_accuracy": 0.24815304456023018,
227
+ "eval_loss": 5.588783264160156,
228
+ "eval_runtime": 15.5767,
229
+ "eval_samples_per_second": 75.048,
230
+ "eval_steps_per_second": 3.146,
231
+ "step": 3940
232
+ },
233
+ {
234
+ "epoch": 20.3,
235
+ "learning_rate": 5.939086294416243e-07,
236
+ "loss": 5.6629,
237
+ "step": 4000
238
+ },
239
+ {
240
+ "epoch": 21.0,
241
+ "eval_accuracy": 0.249284979823902,
242
+ "eval_loss": 5.573500156402588,
243
+ "eval_runtime": 15.589,
244
+ "eval_samples_per_second": 74.989,
245
+ "eval_steps_per_second": 3.143,
246
+ "step": 4137
247
+ },
248
+ {
249
+ "epoch": 22.0,
250
+ "eval_accuracy": 0.250693418358089,
251
+ "eval_loss": 5.55881929397583,
252
+ "eval_runtime": 15.5898,
253
+ "eval_samples_per_second": 74.985,
254
+ "eval_steps_per_second": 3.143,
255
+ "step": 4334
256
+ },
257
+ {
258
+ "epoch": 22.84,
259
+ "learning_rate": 5.431472081218273e-07,
260
+ "loss": 5.6235,
261
+ "step": 4500
262
+ },
263
+ {
264
+ "epoch": 23.0,
265
+ "eval_accuracy": 0.251972245984222,
266
+ "eval_loss": 5.545137405395508,
267
+ "eval_runtime": 15.5982,
268
+ "eval_samples_per_second": 74.945,
269
+ "eval_steps_per_second": 3.141,
270
+ "step": 4531
271
+ },
272
+ {
273
+ "epoch": 24.0,
274
+ "eval_accuracy": 0.2530523368846722,
275
+ "eval_loss": 5.532029628753662,
276
+ "eval_runtime": 15.5791,
277
+ "eval_samples_per_second": 75.037,
278
+ "eval_steps_per_second": 3.145,
279
+ "step": 4728
280
+ },
281
+ {
282
+ "epoch": 25.0,
283
+ "eval_accuracy": 0.2540633019674936,
284
+ "eval_loss": 5.519698619842529,
285
+ "eval_runtime": 15.5647,
286
+ "eval_samples_per_second": 75.106,
287
+ "eval_steps_per_second": 3.148,
288
+ "step": 4925
289
+ },
290
+ {
291
+ "epoch": 25.38,
292
+ "learning_rate": 4.923857868020304e-07,
293
+ "loss": 5.5865,
294
+ "step": 5000
295
+ },
296
+ {
297
+ "epoch": 26.0,
298
+ "eval_accuracy": 0.25520387795836896,
299
+ "eval_loss": 5.5077643394470215,
300
+ "eval_runtime": 15.5629,
301
+ "eval_samples_per_second": 75.115,
302
+ "eval_steps_per_second": 3.149,
303
+ "step": 5122
304
+ },
305
+ {
306
+ "epoch": 27.0,
307
+ "eval_accuracy": 0.25621484304119035,
308
+ "eval_loss": 5.49691915512085,
309
+ "eval_runtime": 15.545,
310
+ "eval_samples_per_second": 75.201,
311
+ "eval_steps_per_second": 3.152,
312
+ "step": 5319
313
+ },
314
+ {
315
+ "epoch": 27.92,
316
+ "learning_rate": 4.416243654822335e-07,
317
+ "loss": 5.5649,
318
+ "step": 5500
319
+ },
320
+ {
321
+ "epoch": 28.0,
322
+ "eval_accuracy": 0.25734677830486213,
323
+ "eval_loss": 5.486623287200928,
324
+ "eval_runtime": 15.5791,
325
+ "eval_samples_per_second": 75.036,
326
+ "eval_steps_per_second": 3.145,
327
+ "step": 5516
328
+ },
329
+ {
330
+ "epoch": 29.0,
331
+ "eval_accuracy": 0.2583491026604799,
332
+ "eval_loss": 5.476452350616455,
333
+ "eval_runtime": 15.4215,
334
+ "eval_samples_per_second": 75.803,
335
+ "eval_steps_per_second": 3.177,
336
+ "step": 5713
337
+ },
338
+ {
339
+ "epoch": 30.0,
340
+ "eval_accuracy": 0.2594723971969481,
341
+ "eval_loss": 5.46701717376709,
342
+ "eval_runtime": 15.4246,
343
+ "eval_samples_per_second": 75.788,
344
+ "eval_steps_per_second": 3.177,
345
+ "step": 5910
346
+ },
347
+ {
348
+ "epoch": 30.46,
349
+ "learning_rate": 3.9086294416243655e-07,
350
+ "loss": 5.5322,
351
+ "step": 6000
352
+ },
353
+ {
354
+ "epoch": 31.0,
355
+ "eval_accuracy": 0.26044879937095505,
356
+ "eval_loss": 5.458242416381836,
357
+ "eval_runtime": 15.4299,
358
+ "eval_samples_per_second": 75.762,
359
+ "eval_steps_per_second": 3.176,
360
+ "step": 6107
361
+ },
362
+ {
363
+ "epoch": 32.0,
364
+ "eval_accuracy": 0.2612437462736864,
365
+ "eval_loss": 5.449988842010498,
366
+ "eval_runtime": 15.4307,
367
+ "eval_samples_per_second": 75.758,
368
+ "eval_steps_per_second": 3.175,
369
+ "step": 6304
370
+ },
371
+ {
372
+ "epoch": 32.99,
373
+ "learning_rate": 3.401015228426396e-07,
374
+ "loss": 5.5168,
375
+ "step": 6500
376
+ },
377
+ {
378
+ "epoch": 33.0,
379
+ "eval_accuracy": 0.2618485971779385,
380
+ "eval_loss": 5.442422866821289,
381
+ "eval_runtime": 15.4236,
382
+ "eval_samples_per_second": 75.793,
383
+ "eval_steps_per_second": 3.177,
384
+ "step": 6501
385
+ },
386
+ {
387
+ "epoch": 34.0,
388
+ "eval_accuracy": 0.26266946626228066,
389
+ "eval_loss": 5.435012340545654,
390
+ "eval_runtime": 15.4335,
391
+ "eval_samples_per_second": 75.744,
392
+ "eval_steps_per_second": 3.175,
393
+ "step": 6698
394
+ },
395
+ {
396
+ "epoch": 35.0,
397
+ "eval_accuracy": 0.26333480225695793,
398
+ "eval_loss": 5.42825174331665,
399
+ "eval_runtime": 15.4283,
400
+ "eval_samples_per_second": 75.77,
401
+ "eval_steps_per_second": 3.176,
402
+ "step": 6895
403
+ },
404
+ {
405
+ "epoch": 35.53,
406
+ "learning_rate": 2.893401015228426e-07,
407
+ "loss": 5.4984,
408
+ "step": 7000
409
+ },
410
+ {
411
+ "epoch": 36.0,
412
+ "eval_accuracy": 0.26399149752443163,
413
+ "eval_loss": 5.421872615814209,
414
+ "eval_runtime": 15.4225,
415
+ "eval_samples_per_second": 75.798,
416
+ "eval_steps_per_second": 3.177,
417
+ "step": 7092
418
+ },
419
+ {
420
+ "epoch": 37.0,
421
+ "eval_accuracy": 0.2647086778823306,
422
+ "eval_loss": 5.4161458015441895,
423
+ "eval_runtime": 15.4337,
424
+ "eval_samples_per_second": 75.743,
425
+ "eval_steps_per_second": 3.175,
426
+ "step": 7289
427
+ },
428
+ {
429
+ "epoch": 38.0,
430
+ "eval_accuracy": 0.26512343278810346,
431
+ "eval_loss": 5.41073751449585,
432
+ "eval_runtime": 15.424,
433
+ "eval_samples_per_second": 75.791,
434
+ "eval_steps_per_second": 3.177,
435
+ "step": 7486
436
+ },
437
+ {
438
+ "epoch": 38.07,
439
+ "learning_rate": 2.3857868020304564e-07,
440
+ "loss": 5.48,
441
+ "step": 7500
442
+ },
443
+ {
444
+ "epoch": 39.0,
445
+ "eval_accuracy": 0.26559867278430155,
446
+ "eval_loss": 5.4057769775390625,
447
+ "eval_runtime": 15.4263,
448
+ "eval_samples_per_second": 75.78,
449
+ "eval_steps_per_second": 3.176,
450
+ "step": 7683
451
+ },
452
+ {
453
+ "epoch": 40.0,
454
+ "eval_accuracy": 0.2660047869628708,
455
+ "eval_loss": 5.401358127593994,
456
+ "eval_runtime": 15.4272,
457
+ "eval_samples_per_second": 75.775,
458
+ "eval_steps_per_second": 3.176,
459
+ "step": 7880
460
+ },
461
+ {
462
+ "epoch": 40.61,
463
+ "learning_rate": 1.8781725888324872e-07,
464
+ "loss": 5.4665,
465
+ "step": 8000
466
+ },
467
+ {
468
+ "epoch": 41.0,
469
+ "eval_accuracy": 0.26646274550466165,
470
+ "eval_loss": 5.3973612785339355,
471
+ "eval_runtime": 15.4315,
472
+ "eval_samples_per_second": 75.754,
473
+ "eval_steps_per_second": 3.175,
474
+ "step": 8077
475
+ },
476
+ {
477
+ "epoch": 42.0,
478
+ "eval_accuracy": 0.26681701532000934,
479
+ "eval_loss": 5.3936448097229,
480
+ "eval_runtime": 15.4239,
481
+ "eval_samples_per_second": 75.791,
482
+ "eval_steps_per_second": 3.177,
483
+ "step": 8274
484
+ },
485
+ {
486
+ "epoch": 43.0,
487
+ "eval_accuracy": 0.2671194407721354,
488
+ "eval_loss": 5.3905029296875,
489
+ "eval_runtime": 15.4322,
490
+ "eval_samples_per_second": 75.751,
491
+ "eval_steps_per_second": 3.175,
492
+ "step": 8471
493
+ },
494
+ {
495
+ "epoch": 43.15,
496
+ "learning_rate": 1.3705583756345177e-07,
497
+ "loss": 5.4612,
498
+ "step": 8500
499
+ },
500
+ {
501
+ "epoch": 44.0,
502
+ "eval_accuracy": 0.267387303315447,
503
+ "eval_loss": 5.387767791748047,
504
+ "eval_runtime": 15.4265,
505
+ "eval_samples_per_second": 75.779,
506
+ "eval_steps_per_second": 3.176,
507
+ "step": 8668
508
+ },
509
+ {
510
+ "epoch": 45.0,
511
+ "eval_accuracy": 0.2676897287675731,
512
+ "eval_loss": 5.385486125946045,
513
+ "eval_runtime": 15.4281,
514
+ "eval_samples_per_second": 75.771,
515
+ "eval_steps_per_second": 3.176,
516
+ "step": 8865
517
+ },
518
+ {
519
+ "epoch": 45.69,
520
+ "learning_rate": 8.629441624365482e-08,
521
+ "loss": 5.4515,
522
+ "step": 9000
523
+ },
524
+ {
525
+ "epoch": 46.0,
526
+ "eval_accuracy": 0.2679143876748667,
527
+ "eval_loss": 5.383605480194092,
528
+ "eval_runtime": 15.4217,
529
+ "eval_samples_per_second": 75.802,
530
+ "eval_steps_per_second": 3.177,
531
+ "step": 9062
532
+ },
533
+ {
534
+ "epoch": 47.0,
535
+ "eval_accuracy": 0.2680439985829207,
536
+ "eval_loss": 5.38220739364624,
537
+ "eval_runtime": 15.4274,
538
+ "eval_samples_per_second": 75.774,
539
+ "eval_steps_per_second": 3.176,
540
+ "step": 9259
541
+ },
542
+ {
543
+ "epoch": 48.0,
544
+ "eval_accuracy": 0.26812176512775315,
545
+ "eval_loss": 5.381243705749512,
546
+ "eval_runtime": 15.4276,
547
+ "eval_samples_per_second": 75.773,
548
+ "eval_steps_per_second": 3.176,
549
+ "step": 9456
550
+ },
551
+ {
552
+ "epoch": 48.22,
553
+ "learning_rate": 3.553299492385787e-08,
554
+ "loss": 5.4453,
555
+ "step": 9500
556
+ },
557
+ {
558
+ "epoch": 49.0,
559
+ "eval_accuracy": 0.2681822502181784,
560
+ "eval_loss": 5.380759239196777,
561
+ "eval_runtime": 15.4241,
562
+ "eval_samples_per_second": 75.791,
563
+ "eval_steps_per_second": 3.177,
564
+ "step": 9653
565
+ },
566
+ {
567
+ "epoch": 50.0,
568
+ "eval_accuracy": 0.26820817239978917,
569
+ "eval_loss": 5.380664825439453,
570
+ "eval_runtime": 15.4231,
571
+ "eval_samples_per_second": 75.796,
572
+ "eval_steps_per_second": 3.177,
573
+ "step": 9850
574
+ },
575
+ {
576
+ "epoch": 50.0,
577
+ "step": 9850,
578
+ "total_flos": 1.00265577216e+17,
579
+ "train_loss": 5.665375294951618,
580
+ "train_runtime": 8010.6738,
581
+ "train_samples_per_second": 29.448,
582
+ "train_steps_per_second": 1.23
583
+ }
584
+ ],
585
+ "logging_steps": 500,
586
+ "max_steps": 9850,
587
+ "num_input_tokens_seen": 0,
588
+ "num_train_epochs": 50,
589
+ "save_steps": 500,
590
+ "total_flos": 1.00265577216e+17,
591
+ "train_batch_size": 24,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2787c8f613acf96df2b7709c4c19c937abd3e0b5593a8c0e348aebeea72f067
3
+ size 4792
vocab.json ADDED
The diff for this file is too large to render. See raw diff