Commit
•
9145e94
1
Parent(s):
a5f9ff9
Upload folder using huggingface_hub
Browse files- config.json +33 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +317 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "general",
|
| 15 |
+
"1": "generate",
|
| 16 |
+
"2": "retrieve"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-05,
|
| 21 |
+
"max_position_embeddings": 514,
|
| 22 |
+
"model_type": "roberta",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 1,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.37.2",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 50265
|
| 33 |
+
}
|
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 sha256:704c1bcc3dc01b99d893322cb3014f64e0c20a3135c3b2118ae07ad29a41a7ec
|
| 3 |
+
size 498615900
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0006509709637612104,
|
| 3 |
+
"best_model_checkpoint": "humza-sami/prompt-classifier/checkpoint-247",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 247,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.77,
|
| 13 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 14 |
+
"loss": 1.1265,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 1.111129641532898,
|
| 20 |
+
"eval_runtime": 0.0855,
|
| 21 |
+
"eval_samples_per_second": 292.39,
|
| 22 |
+
"eval_steps_per_second": 46.782,
|
| 23 |
+
"step": 13
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.54,
|
| 27 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 28 |
+
"loss": 1.1033,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 1.108482837677002,
|
| 34 |
+
"eval_runtime": 0.0857,
|
| 35 |
+
"eval_samples_per_second": 291.796,
|
| 36 |
+
"eval_steps_per_second": 46.687,
|
| 37 |
+
"step": 26
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.31,
|
| 41 |
+
"learning_rate": 3e-06,
|
| 42 |
+
"loss": 1.0507,
|
| 43 |
+
"step": 30
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.0,
|
| 47 |
+
"eval_loss": 1.1056454181671143,
|
| 48 |
+
"eval_runtime": 0.0827,
|
| 49 |
+
"eval_samples_per_second": 302.186,
|
| 50 |
+
"eval_steps_per_second": 48.35,
|
| 51 |
+
"step": 39
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 3.08,
|
| 55 |
+
"learning_rate": 4.000000000000001e-06,
|
| 56 |
+
"loss": 1.0898,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.85,
|
| 61 |
+
"learning_rate": 5e-06,
|
| 62 |
+
"loss": 1.0706,
|
| 63 |
+
"step": 50
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.0,
|
| 67 |
+
"eval_loss": 1.0947411060333252,
|
| 68 |
+
"eval_runtime": 0.0864,
|
| 69 |
+
"eval_samples_per_second": 289.336,
|
| 70 |
+
"eval_steps_per_second": 46.294,
|
| 71 |
+
"step": 52
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.62,
|
| 75 |
+
"learning_rate": 6e-06,
|
| 76 |
+
"loss": 1.0614,
|
| 77 |
+
"step": 60
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.0,
|
| 81 |
+
"eval_loss": 1.051918387413025,
|
| 82 |
+
"eval_runtime": 0.0973,
|
| 83 |
+
"eval_samples_per_second": 256.927,
|
| 84 |
+
"eval_steps_per_second": 41.108,
|
| 85 |
+
"step": 65
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.38,
|
| 89 |
+
"learning_rate": 7.000000000000001e-06,
|
| 90 |
+
"loss": 1.0133,
|
| 91 |
+
"step": 70
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.0,
|
| 95 |
+
"eval_loss": 0.8626992702484131,
|
| 96 |
+
"eval_runtime": 0.0947,
|
| 97 |
+
"eval_samples_per_second": 264.056,
|
| 98 |
+
"eval_steps_per_second": 42.249,
|
| 99 |
+
"step": 78
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.15,
|
| 103 |
+
"learning_rate": 8.000000000000001e-06,
|
| 104 |
+
"loss": 0.892,
|
| 105 |
+
"step": 80
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.92,
|
| 109 |
+
"learning_rate": 9e-06,
|
| 110 |
+
"loss": 0.7292,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 7.0,
|
| 115 |
+
"eval_loss": 0.5572385787963867,
|
| 116 |
+
"eval_runtime": 0.0833,
|
| 117 |
+
"eval_samples_per_second": 299.954,
|
| 118 |
+
"eval_steps_per_second": 47.993,
|
| 119 |
+
"step": 91
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 7.69,
|
| 123 |
+
"learning_rate": 1e-05,
|
| 124 |
+
"loss": 0.4992,
|
| 125 |
+
"step": 100
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 8.0,
|
| 129 |
+
"eval_loss": 0.19228488206863403,
|
| 130 |
+
"eval_runtime": 0.0864,
|
| 131 |
+
"eval_samples_per_second": 289.389,
|
| 132 |
+
"eval_steps_per_second": 46.302,
|
| 133 |
+
"step": 104
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 8.46,
|
| 137 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 138 |
+
"loss": 0.3048,
|
| 139 |
+
"step": 110
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 9.0,
|
| 143 |
+
"eval_loss": 0.05422622710466385,
|
| 144 |
+
"eval_runtime": 0.0847,
|
| 145 |
+
"eval_samples_per_second": 295.026,
|
| 146 |
+
"eval_steps_per_second": 47.204,
|
| 147 |
+
"step": 117
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 9.23,
|
| 151 |
+
"learning_rate": 1.2e-05,
|
| 152 |
+
"loss": 0.1196,
|
| 153 |
+
"step": 120
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 158 |
+
"loss": 0.0357,
|
| 159 |
+
"step": 130
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 10.0,
|
| 163 |
+
"eval_loss": 0.02210908569395542,
|
| 164 |
+
"eval_runtime": 0.0776,
|
| 165 |
+
"eval_samples_per_second": 321.978,
|
| 166 |
+
"eval_steps_per_second": 51.516,
|
| 167 |
+
"step": 130
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 10.77,
|
| 171 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 172 |
+
"loss": 0.0143,
|
| 173 |
+
"step": 140
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 11.0,
|
| 177 |
+
"eval_loss": 0.008073830977082253,
|
| 178 |
+
"eval_runtime": 0.0889,
|
| 179 |
+
"eval_samples_per_second": 281.316,
|
| 180 |
+
"eval_steps_per_second": 45.011,
|
| 181 |
+
"step": 143
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 11.54,
|
| 185 |
+
"learning_rate": 1.5e-05,
|
| 186 |
+
"loss": 0.0071,
|
| 187 |
+
"step": 150
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 12.0,
|
| 191 |
+
"eval_loss": 0.01958407461643219,
|
| 192 |
+
"eval_runtime": 0.0969,
|
| 193 |
+
"eval_samples_per_second": 257.94,
|
| 194 |
+
"eval_steps_per_second": 41.27,
|
| 195 |
+
"step": 156
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.31,
|
| 199 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 200 |
+
"loss": 0.0041,
|
| 201 |
+
"step": 160
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"eval_loss": 0.00249945605173707,
|
| 206 |
+
"eval_runtime": 0.0789,
|
| 207 |
+
"eval_samples_per_second": 316.996,
|
| 208 |
+
"eval_steps_per_second": 50.719,
|
| 209 |
+
"step": 169
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 13.08,
|
| 213 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 214 |
+
"loss": 0.003,
|
| 215 |
+
"step": 170
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 13.85,
|
| 219 |
+
"learning_rate": 1.8e-05,
|
| 220 |
+
"loss": 0.0024,
|
| 221 |
+
"step": 180
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 14.0,
|
| 225 |
+
"eval_loss": 0.0013755728723481297,
|
| 226 |
+
"eval_runtime": 0.0872,
|
| 227 |
+
"eval_samples_per_second": 286.818,
|
| 228 |
+
"eval_steps_per_second": 45.891,
|
| 229 |
+
"step": 182
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 14.62,
|
| 233 |
+
"learning_rate": 1.9e-05,
|
| 234 |
+
"loss": 0.002,
|
| 235 |
+
"step": 190
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 15.0,
|
| 239 |
+
"eval_loss": 0.0011439197696745396,
|
| 240 |
+
"eval_runtime": 0.0872,
|
| 241 |
+
"eval_samples_per_second": 286.641,
|
| 242 |
+
"eval_steps_per_second": 45.863,
|
| 243 |
+
"step": 195
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 15.38,
|
| 247 |
+
"learning_rate": 2e-05,
|
| 248 |
+
"loss": 0.0017,
|
| 249 |
+
"step": 200
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"eval_loss": 0.0010419671889394522,
|
| 254 |
+
"eval_runtime": 0.0861,
|
| 255 |
+
"eval_samples_per_second": 290.515,
|
| 256 |
+
"eval_steps_per_second": 46.482,
|
| 257 |
+
"step": 208
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 16.15,
|
| 261 |
+
"learning_rate": 2.1e-05,
|
| 262 |
+
"loss": 0.0016,
|
| 263 |
+
"step": 210
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 16.92,
|
| 267 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 268 |
+
"loss": 0.0014,
|
| 269 |
+
"step": 220
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 17.0,
|
| 273 |
+
"eval_loss": 0.0008559968555346131,
|
| 274 |
+
"eval_runtime": 0.0864,
|
| 275 |
+
"eval_samples_per_second": 289.468,
|
| 276 |
+
"eval_steps_per_second": 46.315,
|
| 277 |
+
"step": 221
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 17.69,
|
| 281 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 282 |
+
"loss": 0.0012,
|
| 283 |
+
"step": 230
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 18.0,
|
| 287 |
+
"eval_loss": 0.000737538211978972,
|
| 288 |
+
"eval_runtime": 0.0854,
|
| 289 |
+
"eval_samples_per_second": 292.593,
|
| 290 |
+
"eval_steps_per_second": 46.815,
|
| 291 |
+
"step": 234
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 18.46,
|
| 295 |
+
"learning_rate": 2.4e-05,
|
| 296 |
+
"loss": 0.0011,
|
| 297 |
+
"step": 240
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"eval_loss": 0.0006509709637612104,
|
| 302 |
+
"eval_runtime": 0.0863,
|
| 303 |
+
"eval_samples_per_second": 289.626,
|
| 304 |
+
"eval_steps_per_second": 46.34,
|
| 305 |
+
"step": 247
|
| 306 |
+
}
|
| 307 |
+
],
|
| 308 |
+
"logging_steps": 10,
|
| 309 |
+
"max_steps": 260,
|
| 310 |
+
"num_input_tokens_seen": 0,
|
| 311 |
+
"num_train_epochs": 20,
|
| 312 |
+
"save_steps": 500,
|
| 313 |
+
"total_flos": 181727093133432.0,
|
| 314 |
+
"train_batch_size": 8,
|
| 315 |
+
"trial_name": null,
|
| 316 |
+
"trial_params": null
|
| 317 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29033f933f703755b001d38d5e140e62b9f6e1069f707c5289317054360d7dd4
|
| 3 |
+
size 4664
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|