Hugging Face's logo

wabu
/
1e-05_AmpGPT2

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Community
wabu commited on
Commit
0325fe1
•
1 Parent(s): 9c047d1

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 +564 -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: 1e05_output_dir_clean_df_10-100_noX_100_50_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
+ # 1e05_output_dir_clean_df_10-100_noX_100_50_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: 3.9890
21
+ - Accuracy: 0.4213
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-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
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 | 148 | 5.8378 | 0.2287 |
53
+ | No log | 2.0 | 296 | 5.5732 | 0.2491 |
54
+ | No log | 3.0 | 444 | 5.3800 | 0.2680 |
55
+ | 5.761 | 4.0 | 592 | 5.2259 | 0.2842 |
56
+ | 5.761 | 5.0 | 740 | 5.1006 | 0.2963 |
57
+ | 5.761 | 6.0 | 888 | 4.9997 | 0.3067 |
58
+ | 5.1725 | 7.0 | 1036 | 4.9103 | 0.3153 |
59
+ | 5.1725 | 8.0 | 1184 | 4.8287 | 0.3230 |
60
+ | 5.1725 | 9.0 | 1332 | 4.7578 | 0.3301 |
61
+ | 5.1725 | 10.0 | 1480 | 4.6942 | 0.3376 |
62
+ | 4.8482 | 11.0 | 1628 | 4.6364 | 0.3439 |
63
+ | 4.8482 | 12.0 | 1776 | 4.5813 | 0.3497 |
64
+ | 4.8482 | 13.0 | 1924 | 4.5328 | 0.3554 |
65
+ | 4.609 | 14.0 | 2072 | 4.4897 | 0.3610 |
66
+ | 4.609 | 15.0 | 2220 | 4.4454 | 0.3657 |
67
+ | 4.609 | 16.0 | 2368 | 4.4132 | 0.3702 |
68
+ | 4.4241 | 17.0 | 2516 | 4.3742 | 0.3738 |
69
+ | 4.4241 | 18.0 | 2664 | 4.3438 | 0.3782 |
70
+ | 4.4241 | 19.0 | 2812 | 4.3164 | 0.3817 |
71
+ | 4.4241 | 20.0 | 2960 | 4.2879 | 0.3848 |
72
+ | 4.283 | 21.0 | 3108 | 4.2602 | 0.3878 |
73
+ | 4.283 | 22.0 | 3256 | 4.2373 | 0.3902 |
74
+ | 4.283 | 23.0 | 3404 | 4.2160 | 0.3932 |
75
+ | 4.1606 | 24.0 | 3552 | 4.1964 | 0.3954 |
76
+ | 4.1606 | 25.0 | 3700 | 4.1816 | 0.3976 |
77
+ | 4.1606 | 26.0 | 3848 | 4.1605 | 0.3995 |
78
+ | 4.1606 | 27.0 | 3996 | 4.1443 | 0.4016 |
79
+ | 4.0685 | 28.0 | 4144 | 4.1290 | 0.4034 |
80
+ | 4.0685 | 29.0 | 4292 | 4.1146 | 0.4052 |
81
+ | 4.0685 | 30.0 | 4440 | 4.1037 | 0.4067 |
82
+ | 3.9859 | 31.0 | 4588 | 4.0874 | 0.4082 |
83
+ | 3.9859 | 32.0 | 4736 | 4.0784 | 0.4098 |
84
+ | 3.9859 | 33.0 | 4884 | 4.0669 | 0.4115 |
85
+ | 3.9275 | 34.0 | 5032 | 4.0581 | 0.4125 |
86
+ | 3.9275 | 35.0 | 5180 | 4.0479 | 0.4136 |
87
+ | 3.9275 | 36.0 | 5328 | 4.0384 | 0.4148 |
88
+ | 3.9275 | 37.0 | 5476 | 4.0330 | 0.4159 |
89
+ | 3.8799 | 38.0 | 5624 | 4.0262 | 0.4166 |
90
+ | 3.8799 | 39.0 | 5772 | 4.0212 | 0.4174 |
91
+ | 3.8799 | 40.0 | 5920 | 4.0136 | 0.4180 |
92
+ | 3.8348 | 41.0 | 6068 | 4.0111 | 0.4186 |
93
+ | 3.8348 | 42.0 | 6216 | 4.0048 | 0.4193 |
94
+ | 3.8348 | 43.0 | 6364 | 4.0004 | 0.4195 |
95
+ | 3.8151 | 44.0 | 6512 | 3.9978 | 0.4199 |
96
+ | 3.8151 | 45.0 | 6660 | 3.9951 | 0.4203 |
97
+ | 3.8151 | 46.0 | 6808 | 3.9934 | 0.4207 |
98
+ | 3.8151 | 47.0 | 6956 | 3.9904 | 0.4209 |
99
+ | 3.7948 | 48.0 | 7104 | 3.9911 | 0.4211 |
100
+ | 3.7948 | 49.0 | 7252 | 3.9890 | 0.4213 |
101
+ | 3.7948 | 50.0 | 7400 | 3.9890 | 0.4213 |
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": 0.42128729553879257,
4
+ "eval_loss": 3.988962173461914,
5
+ "eval_runtime": 19.7085,
6
+ "eval_samples": 1169,
7
+ "eval_samples_per_second": 59.315,
8
+ "eval_steps_per_second": 1.877,
9
+ "perplexity": 53.99881886539013,
10
+ "train_loss": 4.29683648186761,
11
+ "train_runtime": 9035.6616,
12
+ "train_samples": 4718,
13
+ "train_samples_per_second": 26.108,
14
+ "train_steps_per_second": 0.819
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": 0.42128729553879257,
4
+ "eval_loss": 3.988962173461914,
5
+ "eval_runtime": 19.7085,
6
+ "eval_samples": 1169,
7
+ "eval_samples_per_second": 59.315,
8
+ "eval_steps_per_second": 1.877,
9
+ "perplexity": 53.99881886539013
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:d27e1686c85b38a0ca90392bcabb06d8a9cb850b3511d28d4accb2eaca8fccb7
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": 4.29683648186761,
4
+ "train_runtime": 9035.6616,
5
+ "train_samples": 4718,
6
+ "train_samples_per_second": 26.108,
7
+ "train_steps_per_second": 0.819
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,564 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7400,
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": 0.22874597126094132,
14
+ "eval_loss": 5.837828636169434,
15
+ "eval_runtime": 19.7897,
16
+ "eval_samples_per_second": 59.071,
17
+ "eval_steps_per_second": 1.87,
18
+ "step": 148
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.24914672818864436,
23
+ "eval_loss": 5.573156356811523,
24
+ "eval_runtime": 19.7414,
25
+ "eval_samples_per_second": 59.216,
26
+ "eval_steps_per_second": 1.874,
27
+ "step": 296
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.26800943567410634,
32
+ "eval_loss": 5.379988670349121,
33
+ "eval_runtime": 19.7422,
34
+ "eval_samples_per_second": 59.213,
35
+ "eval_steps_per_second": 1.874,
36
+ "step": 444
37
+ },
38
+ {
39
+ "epoch": 3.38,
40
+ "learning_rate": 9.324324324324325e-06,
41
+ "loss": 5.761,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_accuracy": 0.28418487699924827,
47
+ "eval_loss": 5.225850582122803,
48
+ "eval_runtime": 19.7377,
49
+ "eval_samples_per_second": 59.227,
50
+ "eval_steps_per_second": 1.875,
51
+ "step": 592
52
+ },
53
+ {
54
+ "epoch": 5.0,
55
+ "eval_accuracy": 0.2963078172659011,
56
+ "eval_loss": 5.1006011962890625,
57
+ "eval_runtime": 19.742,
58
+ "eval_samples_per_second": 59.214,
59
+ "eval_steps_per_second": 1.874,
60
+ "step": 740
61
+ },
62
+ {
63
+ "epoch": 6.0,
64
+ "eval_accuracy": 0.30673717500064807,
65
+ "eval_loss": 4.999685764312744,
66
+ "eval_runtime": 19.749,
67
+ "eval_samples_per_second": 59.193,
68
+ "eval_steps_per_second": 1.874,
69
+ "step": 888
70
+ },
71
+ {
72
+ "epoch": 6.76,
73
+ "learning_rate": 8.64864864864865e-06,
74
+ "loss": 5.1725,
75
+ "step": 1000
76
+ },
77
+ {
78
+ "epoch": 7.0,
79
+ "eval_accuracy": 0.3152828542050099,
80
+ "eval_loss": 4.910343170166016,
81
+ "eval_runtime": 19.7422,
82
+ "eval_samples_per_second": 59.213,
83
+ "eval_steps_per_second": 1.874,
84
+ "step": 1036
85
+ },
86
+ {
87
+ "epoch": 8.0,
88
+ "eval_accuracy": 0.322955819961808,
89
+ "eval_loss": 4.828683853149414,
90
+ "eval_runtime": 19.7403,
91
+ "eval_samples_per_second": 59.219,
92
+ "eval_steps_per_second": 1.874,
93
+ "step": 1184
94
+ },
95
+ {
96
+ "epoch": 9.0,
97
+ "eval_accuracy": 0.3300757791775756,
98
+ "eval_loss": 4.757791996002197,
99
+ "eval_runtime": 19.7469,
100
+ "eval_samples_per_second": 59.199,
101
+ "eval_steps_per_second": 1.874,
102
+ "step": 1332
103
+ },
104
+ {
105
+ "epoch": 10.0,
106
+ "eval_accuracy": 0.3375845711175052,
107
+ "eval_loss": 4.694174766540527,
108
+ "eval_runtime": 19.7442,
109
+ "eval_samples_per_second": 59.207,
110
+ "eval_steps_per_second": 1.874,
111
+ "step": 1480
112
+ },
113
+ {
114
+ "epoch": 10.14,
115
+ "learning_rate": 7.972972972972974e-06,
116
+ "loss": 4.8482,
117
+ "step": 1500
118
+ },
119
+ {
120
+ "epoch": 11.0,
121
+ "eval_accuracy": 0.3439355056121523,
122
+ "eval_loss": 4.63644552230835,
123
+ "eval_runtime": 19.7467,
124
+ "eval_samples_per_second": 59.2,
125
+ "eval_steps_per_second": 1.874,
126
+ "step": 1628
127
+ },
128
+ {
129
+ "epoch": 12.0,
130
+ "eval_accuracy": 0.34968158920254727,
131
+ "eval_loss": 4.5813164710998535,
132
+ "eval_runtime": 19.7421,
133
+ "eval_samples_per_second": 59.214,
134
+ "eval_steps_per_second": 1.874,
135
+ "step": 1776
136
+ },
137
+ {
138
+ "epoch": 13.0,
139
+ "eval_accuracy": 0.3554363135201459,
140
+ "eval_loss": 4.532833099365234,
141
+ "eval_runtime": 19.7462,
142
+ "eval_samples_per_second": 59.201,
143
+ "eval_steps_per_second": 1.874,
144
+ "step": 1924
145
+ },
146
+ {
147
+ "epoch": 13.51,
148
+ "learning_rate": 7.297297297297298e-06,
149
+ "loss": 4.609,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 14.0,
154
+ "eval_accuracy": 0.3610182232936724,
155
+ "eval_loss": 4.4896931648254395,
156
+ "eval_runtime": 19.7471,
157
+ "eval_samples_per_second": 59.199,
158
+ "eval_steps_per_second": 1.874,
159
+ "step": 2072
160
+ },
161
+ {
162
+ "epoch": 15.0,
163
+ "eval_accuracy": 0.3656582938020064,
164
+ "eval_loss": 4.4454345703125,
165
+ "eval_runtime": 19.7467,
166
+ "eval_samples_per_second": 59.2,
167
+ "eval_steps_per_second": 1.874,
168
+ "step": 2220
169
+ },
170
+ {
171
+ "epoch": 16.0,
172
+ "eval_accuracy": 0.37016011267508275,
173
+ "eval_loss": 4.413242340087891,
174
+ "eval_runtime": 19.7438,
175
+ "eval_samples_per_second": 59.208,
176
+ "eval_steps_per_second": 1.874,
177
+ "step": 2368
178
+ },
179
+ {
180
+ "epoch": 16.89,
181
+ "learning_rate": 6.621621621621622e-06,
182
+ "loss": 4.4241,
183
+ "step": 2500
184
+ },
185
+ {
186
+ "epoch": 17.0,
187
+ "eval_accuracy": 0.3737978588277989,
188
+ "eval_loss": 4.374161243438721,
189
+ "eval_runtime": 19.7484,
190
+ "eval_samples_per_second": 59.195,
191
+ "eval_steps_per_second": 1.874,
192
+ "step": 2516
193
+ },
194
+ {
195
+ "epoch": 18.0,
196
+ "eval_accuracy": 0.3782132704288393,
197
+ "eval_loss": 4.343791961669922,
198
+ "eval_runtime": 19.7509,
199
+ "eval_samples_per_second": 59.187,
200
+ "eval_steps_per_second": 1.873,
201
+ "step": 2664
202
+ },
203
+ {
204
+ "epoch": 19.0,
205
+ "eval_accuracy": 0.38171276494629786,
206
+ "eval_loss": 4.316366672515869,
207
+ "eval_runtime": 19.7486,
208
+ "eval_samples_per_second": 59.194,
209
+ "eval_steps_per_second": 1.874,
210
+ "step": 2812
211
+ },
212
+ {
213
+ "epoch": 20.0,
214
+ "eval_accuracy": 0.3847715823763728,
215
+ "eval_loss": 4.2879157066345215,
216
+ "eval_runtime": 19.7502,
217
+ "eval_samples_per_second": 59.189,
218
+ "eval_steps_per_second": 1.873,
219
+ "step": 2960
220
+ },
221
+ {
222
+ "epoch": 20.27,
223
+ "learning_rate": 5.945945945945947e-06,
224
+ "loss": 4.283,
225
+ "step": 3000
226
+ },
227
+ {
228
+ "epoch": 21.0,
229
+ "eval_accuracy": 0.3878131183520405,
230
+ "eval_loss": 4.260156631469727,
231
+ "eval_runtime": 19.7607,
232
+ "eval_samples_per_second": 59.158,
233
+ "eval_steps_per_second": 1.872,
234
+ "step": 3108
235
+ },
236
+ {
237
+ "epoch": 22.0,
238
+ "eval_accuracy": 0.39024116269625253,
239
+ "eval_loss": 4.23726224899292,
240
+ "eval_runtime": 19.749,
241
+ "eval_samples_per_second": 59.193,
242
+ "eval_steps_per_second": 1.874,
243
+ "step": 3256
244
+ },
245
+ {
246
+ "epoch": 23.0,
247
+ "eval_accuracy": 0.3931530877638662,
248
+ "eval_loss": 4.216041088104248,
249
+ "eval_runtime": 19.7399,
250
+ "eval_samples_per_second": 59.22,
251
+ "eval_steps_per_second": 1.874,
252
+ "step": 3404
253
+ },
254
+ {
255
+ "epoch": 23.65,
256
+ "learning_rate": 5.2702702702702705e-06,
257
+ "loss": 4.1606,
258
+ "step": 3500
259
+ },
260
+ {
261
+ "epoch": 24.0,
262
+ "eval_accuracy": 0.39539103610959897,
263
+ "eval_loss": 4.196435928344727,
264
+ "eval_runtime": 19.7434,
265
+ "eval_samples_per_second": 59.21,
266
+ "eval_steps_per_second": 1.874,
267
+ "step": 3552
268
+ },
269
+ {
270
+ "epoch": 25.0,
271
+ "eval_accuracy": 0.39759442154651736,
272
+ "eval_loss": 4.181632041931152,
273
+ "eval_runtime": 19.7448,
274
+ "eval_samples_per_second": 59.205,
275
+ "eval_steps_per_second": 1.874,
276
+ "step": 3700
277
+ },
278
+ {
279
+ "epoch": 26.0,
280
+ "eval_accuracy": 0.39951266298571686,
281
+ "eval_loss": 4.160492897033691,
282
+ "eval_runtime": 19.7431,
283
+ "eval_samples_per_second": 59.21,
284
+ "eval_steps_per_second": 1.874,
285
+ "step": 3848
286
+ },
287
+ {
288
+ "epoch": 27.0,
289
+ "eval_accuracy": 0.4016382818778028,
290
+ "eval_loss": 4.144294738769531,
291
+ "eval_runtime": 19.7428,
292
+ "eval_samples_per_second": 59.212,
293
+ "eval_steps_per_second": 1.874,
294
+ "step": 3996
295
+ },
296
+ {
297
+ "epoch": 27.03,
298
+ "learning_rate": 4.594594594594596e-06,
299
+ "loss": 4.0685,
300
+ "step": 4000
301
+ },
302
+ {
303
+ "epoch": 28.0,
304
+ "eval_accuracy": 0.4034355531361519,
305
+ "eval_loss": 4.129027366638184,
306
+ "eval_runtime": 19.7497,
307
+ "eval_samples_per_second": 59.191,
308
+ "eval_steps_per_second": 1.873,
309
+ "step": 4144
310
+ },
311
+ {
312
+ "epoch": 29.0,
313
+ "eval_accuracy": 0.40515505784966865,
314
+ "eval_loss": 4.114578723907471,
315
+ "eval_runtime": 19.7461,
316
+ "eval_samples_per_second": 59.202,
317
+ "eval_steps_per_second": 1.874,
318
+ "step": 4292
319
+ },
320
+ {
321
+ "epoch": 30.0,
322
+ "eval_accuracy": 0.40673631092792767,
323
+ "eval_loss": 4.103656768798828,
324
+ "eval_runtime": 19.7473,
325
+ "eval_samples_per_second": 59.198,
326
+ "eval_steps_per_second": 1.874,
327
+ "step": 4440
328
+ },
329
+ {
330
+ "epoch": 30.41,
331
+ "learning_rate": 3.918918918918919e-06,
332
+ "loss": 3.9859,
333
+ "step": 4500
334
+ },
335
+ {
336
+ "epoch": 31.0,
337
+ "eval_accuracy": 0.40824843818855794,
338
+ "eval_loss": 4.087373733520508,
339
+ "eval_runtime": 19.744,
340
+ "eval_samples_per_second": 59.208,
341
+ "eval_steps_per_second": 1.874,
342
+ "step": 4588
343
+ },
344
+ {
345
+ "epoch": 32.0,
346
+ "eval_accuracy": 0.4098124098124098,
347
+ "eval_loss": 4.078439235687256,
348
+ "eval_runtime": 19.7428,
349
+ "eval_samples_per_second": 59.211,
350
+ "eval_steps_per_second": 1.874,
351
+ "step": 4736
352
+ },
353
+ {
354
+ "epoch": 33.0,
355
+ "eval_accuracy": 0.4114714294355013,
356
+ "eval_loss": 4.066919803619385,
357
+ "eval_runtime": 19.7485,
358
+ "eval_samples_per_second": 59.194,
359
+ "eval_steps_per_second": 1.874,
360
+ "step": 4884
361
+ },
362
+ {
363
+ "epoch": 33.78,
364
+ "learning_rate": 3.2432432432432437e-06,
365
+ "loss": 3.9275,
366
+ "step": 5000
367
+ },
368
+ {
369
+ "epoch": 34.0,
370
+ "eval_accuracy": 0.41251695742713707,
371
+ "eval_loss": 4.058130264282227,
372
+ "eval_runtime": 19.7418,
373
+ "eval_samples_per_second": 59.215,
374
+ "eval_steps_per_second": 1.874,
375
+ "step": 5032
376
+ },
377
+ {
378
+ "epoch": 35.0,
379
+ "eval_accuracy": 0.41355384469156925,
380
+ "eval_loss": 4.047876834869385,
381
+ "eval_runtime": 19.7402,
382
+ "eval_samples_per_second": 59.219,
383
+ "eval_steps_per_second": 1.874,
384
+ "step": 5180
385
+ },
386
+ {
387
+ "epoch": 36.0,
388
+ "eval_accuracy": 0.41476354650007347,
389
+ "eval_loss": 4.038449287414551,
390
+ "eval_runtime": 19.7398,
391
+ "eval_samples_per_second": 59.22,
392
+ "eval_steps_per_second": 1.874,
393
+ "step": 5328
394
+ },
395
+ {
396
+ "epoch": 37.0,
397
+ "eval_accuracy": 0.4158868410365416,
398
+ "eval_loss": 4.033016204833984,
399
+ "eval_runtime": 19.7451,
400
+ "eval_samples_per_second": 59.204,
401
+ "eval_steps_per_second": 1.874,
402
+ "step": 5476
403
+ },
404
+ {
405
+ "epoch": 37.16,
406
+ "learning_rate": 2.5675675675675675e-06,
407
+ "loss": 3.8799,
408
+ "step": 5500
409
+ },
410
+ {
411
+ "epoch": 38.0,
412
+ "eval_accuracy": 0.41657809921282973,
413
+ "eval_loss": 4.026158332824707,
414
+ "eval_runtime": 19.7412,
415
+ "eval_samples_per_second": 59.216,
416
+ "eval_steps_per_second": 1.874,
417
+ "step": 5624
418
+ },
419
+ {
420
+ "epoch": 39.0,
421
+ "eval_accuracy": 0.4173989682971719,
422
+ "eval_loss": 4.021160125732422,
423
+ "eval_runtime": 19.7395,
424
+ "eval_samples_per_second": 59.221,
425
+ "eval_steps_per_second": 1.874,
426
+ "step": 5772
427
+ },
428
+ {
429
+ "epoch": 40.0,
430
+ "eval_accuracy": 0.418003819201424,
431
+ "eval_loss": 4.013641834259033,
432
+ "eval_runtime": 19.7429,
433
+ "eval_samples_per_second": 59.211,
434
+ "eval_steps_per_second": 1.874,
435
+ "step": 5920
436
+ },
437
+ {
438
+ "epoch": 40.54,
439
+ "learning_rate": 1.8918918918918922e-06,
440
+ "loss": 3.8348,
441
+ "step": 6000
442
+ },
443
+ {
444
+ "epoch": 41.0,
445
+ "eval_accuracy": 0.4185568257424545,
446
+ "eval_loss": 4.011115550994873,
447
+ "eval_runtime": 19.7447,
448
+ "eval_samples_per_second": 59.206,
449
+ "eval_steps_per_second": 1.874,
450
+ "step": 6068
451
+ },
452
+ {
453
+ "epoch": 42.0,
454
+ "eval_accuracy": 0.4192567246459462,
455
+ "eval_loss": 4.004785060882568,
456
+ "eval_runtime": 19.7414,
457
+ "eval_samples_per_second": 59.216,
458
+ "eval_steps_per_second": 1.874,
459
+ "step": 6216
460
+ },
461
+ {
462
+ "epoch": 43.0,
463
+ "eval_accuracy": 0.41952458718925784,
464
+ "eval_loss": 4.000365257263184,
465
+ "eval_runtime": 19.7443,
466
+ "eval_samples_per_second": 59.207,
467
+ "eval_steps_per_second": 1.874,
468
+ "step": 6364
469
+ },
470
+ {
471
+ "epoch": 43.92,
472
+ "learning_rate": 1.2162162162162164e-06,
473
+ "loss": 3.8151,
474
+ "step": 6500
475
+ },
476
+ {
477
+ "epoch": 44.0,
478
+ "eval_accuracy": 0.4198615755501983,
479
+ "eval_loss": 3.997826337814331,
480
+ "eval_runtime": 19.752,
481
+ "eval_samples_per_second": 59.184,
482
+ "eval_steps_per_second": 1.873,
483
+ "step": 6512
484
+ },
485
+ {
486
+ "epoch": 45.0,
487
+ "eval_accuracy": 0.4203195340919892,
488
+ "eval_loss": 3.9950661659240723,
489
+ "eval_runtime": 19.7402,
490
+ "eval_samples_per_second": 59.219,
491
+ "eval_steps_per_second": 1.874,
492
+ "step": 6660
493
+ },
494
+ {
495
+ "epoch": 46.0,
496
+ "eval_accuracy": 0.42070836681615126,
497
+ "eval_loss": 3.99338960647583,
498
+ "eval_runtime": 19.7409,
499
+ "eval_samples_per_second": 59.217,
500
+ "eval_steps_per_second": 1.874,
501
+ "step": 6808
502
+ },
503
+ {
504
+ "epoch": 47.0,
505
+ "eval_accuracy": 0.4209071035418341,
506
+ "eval_loss": 3.990373134613037,
507
+ "eval_runtime": 19.7427,
508
+ "eval_samples_per_second": 59.212,
509
+ "eval_steps_per_second": 1.874,
510
+ "step": 6956
511
+ },
512
+ {
513
+ "epoch": 47.3,
514
+ "learning_rate": 5.405405405405406e-07,
515
+ "loss": 3.7948,
516
+ "step": 7000
517
+ },
518
+ {
519
+ "epoch": 48.0,
520
+ "eval_accuracy": 0.4210626366314989,
521
+ "eval_loss": 3.9910764694213867,
522
+ "eval_runtime": 19.7469,
523
+ "eval_samples_per_second": 59.199,
524
+ "eval_steps_per_second": 1.874,
525
+ "step": 7104
526
+ },
527
+ {
528
+ "epoch": 49.0,
529
+ "eval_accuracy": 0.42127001408438536,
530
+ "eval_loss": 3.9890379905700684,
531
+ "eval_runtime": 19.7459,
532
+ "eval_samples_per_second": 59.202,
533
+ "eval_steps_per_second": 1.874,
534
+ "step": 7252
535
+ },
536
+ {
537
+ "epoch": 50.0,
538
+ "eval_accuracy": 0.42128729553879257,
539
+ "eval_loss": 3.988962173461914,
540
+ "eval_runtime": 19.7474,
541
+ "eval_samples_per_second": 59.198,
542
+ "eval_steps_per_second": 1.874,
543
+ "step": 7400
544
+ },
545
+ {
546
+ "epoch": 50.0,
547
+ "step": 7400,
548
+ "total_flos": 1.00265577216e+17,
549
+ "train_loss": 4.29683648186761,
550
+ "train_runtime": 9035.6616,
551
+ "train_samples_per_second": 26.108,
552
+ "train_steps_per_second": 0.819
553
+ }
554
+ ],
555
+ "logging_steps": 500,
556
+ "max_steps": 7400,
557
+ "num_input_tokens_seen": 0,
558
+ "num_train_epochs": 50,
559
+ "save_steps": 500,
560
+ "total_flos": 1.00265577216e+17,
561
+ "train_batch_size": 32,
562
+ "trial_name": null,
563
+ "trial_params": null
564
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e023e2de243e3969c141572dedb78b04496ec92200fff487d0ad73fede204bb
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff