Training in progress, epoch 1, checkpoint
Browse files- checkpoint-2500/README.md +9 -0
- checkpoint-2500/adapter_config.json +23 -0
- checkpoint-2500/adapter_model.bin +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +7 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2500/tokenizer_config.json +13 -0
- checkpoint-2500/trainer_state.json +328 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-2500/vocab.txt +0 -0
checkpoint-2500/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.4.0
|
checkpoint-2500/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "bert-base-cased",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": [
|
| 13 |
+
"classifier"
|
| 14 |
+
],
|
| 15 |
+
"peft_type": "LORA",
|
| 16 |
+
"r": 8,
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"query",
|
| 20 |
+
"value"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "SEQ_CLS"
|
| 23 |
+
}
|
checkpoint-2500/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a3721af677f4d41c0ae9d14145c9af9c6092931340247d409bbf14777976e7
|
| 3 |
+
size 1203911
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11a088bb62079202ad2d12e886f4cc479fd2f891eda3a9b1ffb94a9aac92a726
|
| 3 |
+
size 2413509
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb0db5c6f55fb01c1231142ed0148747b218782e048cd527ab44ea3bea5b7fe3
|
| 3 |
+
size 14575
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf35227d733b94e0ad85c746120f70db99d2298a4f3586908049e97443c7396b
|
| 3 |
+
size 627
|
checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,328 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9037,
|
| 3 |
+
"best_model_checkpoint": "output/checkpoint-2500",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 3.3333333333333337e-06,
|
| 14 |
+
"loss": 0.8125,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 6.6666666666666675e-06,
|
| 20 |
+
"loss": 0.7599,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"learning_rate": 1e-05,
|
| 26 |
+
"loss": 0.7309,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.08,
|
| 31 |
+
"learning_rate": 1.3333333333333335e-05,
|
| 32 |
+
"loss": 0.7104,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 38 |
+
"loss": 0.6939,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.12,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 0.6824,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.14,
|
| 49 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 50 |
+
"loss": 0.686,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16,
|
| 55 |
+
"learning_rate": 2.666666666666667e-05,
|
| 56 |
+
"loss": 0.6693,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.18,
|
| 61 |
+
"learning_rate": 3e-05,
|
| 62 |
+
"loss": 0.6436,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.2,
|
| 67 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 68 |
+
"loss": 0.6101,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.22,
|
| 73 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 74 |
+
"loss": 0.493,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.24,
|
| 79 |
+
"learning_rate": 3.993333333333333e-05,
|
| 80 |
+
"loss": 0.4239,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.26,
|
| 85 |
+
"learning_rate": 4.326666666666667e-05,
|
| 86 |
+
"loss": 0.3391,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.28,
|
| 91 |
+
"learning_rate": 4.66e-05,
|
| 92 |
+
"loss": 0.3332,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3,
|
| 97 |
+
"learning_rate": 4.986666666666666e-05,
|
| 98 |
+
"loss": 0.3966,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.32,
|
| 103 |
+
"learning_rate": 5.32e-05,
|
| 104 |
+
"loss": 0.3137,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.34,
|
| 109 |
+
"learning_rate": 5.653333333333333e-05,
|
| 110 |
+
"loss": 0.3072,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.36,
|
| 115 |
+
"learning_rate": 5.986666666666667e-05,
|
| 116 |
+
"loss": 0.272,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.38,
|
| 121 |
+
"learning_rate": 6.32e-05,
|
| 122 |
+
"loss": 0.2715,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.4,
|
| 127 |
+
"learning_rate": 6.653333333333333e-05,
|
| 128 |
+
"loss": 0.2892,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.42,
|
| 133 |
+
"learning_rate": 6.986666666666667e-05,
|
| 134 |
+
"loss": 0.28,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.44,
|
| 139 |
+
"learning_rate": 7.32e-05,
|
| 140 |
+
"loss": 0.3102,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.46,
|
| 145 |
+
"learning_rate": 7.653333333333333e-05,
|
| 146 |
+
"loss": 0.2663,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.48,
|
| 151 |
+
"learning_rate": 7.986666666666667e-05,
|
| 152 |
+
"loss": 0.2778,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.5,
|
| 157 |
+
"learning_rate": 8.32e-05,
|
| 158 |
+
"loss": 0.3414,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.52,
|
| 163 |
+
"learning_rate": 8.653333333333334e-05,
|
| 164 |
+
"loss": 0.2608,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.54,
|
| 169 |
+
"learning_rate": 8.986666666666666e-05,
|
| 170 |
+
"loss": 0.2847,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.56,
|
| 175 |
+
"learning_rate": 9.32e-05,
|
| 176 |
+
"loss": 0.2801,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.58,
|
| 181 |
+
"learning_rate": 9.653333333333334e-05,
|
| 182 |
+
"loss": 0.2777,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.6,
|
| 187 |
+
"learning_rate": 9.986666666666668e-05,
|
| 188 |
+
"loss": 0.2819,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.62,
|
| 193 |
+
"learning_rate": 0.0001032,
|
| 194 |
+
"loss": 0.2631,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.64,
|
| 199 |
+
"learning_rate": 0.00010653333333333333,
|
| 200 |
+
"loss": 0.255,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.66,
|
| 205 |
+
"learning_rate": 0.00010986666666666668,
|
| 206 |
+
"loss": 0.3253,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.68,
|
| 211 |
+
"learning_rate": 0.0001132,
|
| 212 |
+
"loss": 0.2632,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.7,
|
| 217 |
+
"learning_rate": 0.00011653333333333334,
|
| 218 |
+
"loss": 0.2808,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.72,
|
| 223 |
+
"learning_rate": 0.00011986666666666666,
|
| 224 |
+
"loss": 0.2487,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.74,
|
| 229 |
+
"learning_rate": 0.0001232,
|
| 230 |
+
"loss": 0.1958,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.76,
|
| 235 |
+
"learning_rate": 0.00012653333333333334,
|
| 236 |
+
"loss": 0.2882,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.78,
|
| 241 |
+
"learning_rate": 0.00012986666666666666,
|
| 242 |
+
"loss": 0.2877,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.8,
|
| 247 |
+
"learning_rate": 0.0001332,
|
| 248 |
+
"loss": 0.2412,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.82,
|
| 253 |
+
"learning_rate": 0.00013653333333333334,
|
| 254 |
+
"loss": 0.2608,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.84,
|
| 259 |
+
"learning_rate": 0.00013986666666666666,
|
| 260 |
+
"loss": 0.2296,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.86,
|
| 265 |
+
"learning_rate": 0.00014319999999999998,
|
| 266 |
+
"loss": 0.2311,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.88,
|
| 271 |
+
"learning_rate": 0.00014653333333333334,
|
| 272 |
+
"loss": 0.2603,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.9,
|
| 277 |
+
"learning_rate": 0.00014986666666666669,
|
| 278 |
+
"loss": 0.2923,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.92,
|
| 283 |
+
"learning_rate": 0.0001532,
|
| 284 |
+
"loss": 0.2415,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.94,
|
| 289 |
+
"learning_rate": 0.00015646666666666668,
|
| 290 |
+
"loss": 0.2671,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.96,
|
| 295 |
+
"learning_rate": 0.0001598,
|
| 296 |
+
"loss": 0.2421,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.98,
|
| 301 |
+
"learning_rate": 0.00016313333333333333,
|
| 302 |
+
"loss": 0.2449,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.0,
|
| 307 |
+
"learning_rate": 0.00016646666666666668,
|
| 308 |
+
"loss": 0.2399,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.0,
|
| 313 |
+
"eval_accuracy": 0.9037,
|
| 314 |
+
"eval_loss": 0.2539164125919342,
|
| 315 |
+
"eval_runtime": 132.4594,
|
| 316 |
+
"eval_samples_per_second": 75.495,
|
| 317 |
+
"eval_steps_per_second": 4.718,
|
| 318 |
+
"step": 2500
|
| 319 |
+
}
|
| 320 |
+
],
|
| 321 |
+
"logging_steps": 50,
|
| 322 |
+
"max_steps": 25000,
|
| 323 |
+
"num_train_epochs": 10,
|
| 324 |
+
"save_steps": 500,
|
| 325 |
+
"total_flos": 5833552310267520.0,
|
| 326 |
+
"trial_name": null,
|
| 327 |
+
"trial_params": null
|
| 328 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec3775b4601d79665325e377c01a163d9ef09a7fa47af2b3ae8cc93ce5670761
|
| 3 |
+
size 4027
|
checkpoint-2500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|