Training in progress, epoch 0
Browse files- all_results.json +8 -0
- config.json +1 -1
- model.safetensors +1 -1
- runs/Jul24_11-05-58_gurame007/events.out.tfevents.1721793959.gurame007.75786.0 +3 -0
- runs/Jul24_11-07-21_gurame007/events.out.tfevents.1721794043.gurame007.76188.0 +3 -0
- runs/Jul24_11-08-28_gurame007/events.out.tfevents.1721794110.gurame007.76562.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +344 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 24.137931034482758,
|
| 3 |
+
"total_flos": 8.67232581632557e+17,
|
| 4 |
+
"train_loss": 0.1937425845861435,
|
| 5 |
+
"train_runtime": 510.3099,
|
| 6 |
+
"train_samples_per_second": 22.29,
|
| 7 |
+
"train_steps_per_second": 0.343
|
| 8 |
+
}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"CLIPForImageClassification"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "ktp-kk-crop",
|
| 3 |
"architectures": [
|
| 4 |
"CLIPForImageClassification"
|
| 5 |
],
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 349854120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7caaae9e372e66cbd7c6d6013d871552ddd7320e0019bf0a24574122f605bb06
|
| 3 |
size 349854120
|
runs/Jul24_11-05-58_gurame007/events.out.tfevents.1721793959.gurame007.75786.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4796e8c58e1b89097946702e2c95898ddef77ab816c6bd6863414daaeb321bbc
|
| 3 |
+
size 5040
|
runs/Jul24_11-07-21_gurame007/events.out.tfevents.1721794043.gurame007.76188.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd9a92ebb747759ffa6d6f57d6735e4bfc05814664a492339a1eb6334b5aaa7
|
| 3 |
+
size 5040
|
runs/Jul24_11-08-28_gurame007/events.out.tfevents.1721794110.gurame007.76562.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5949ef91cbeada18efcd8b6ce055756752c7cb2f4858bd88b96b74553dd85a9d
|
| 3 |
+
size 5117
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 24.137931034482758,
|
| 3 |
+
"total_flos": 8.67232581632557e+17,
|
| 4 |
+
"train_loss": 0.1937425845861435,
|
| 5 |
+
"train_runtime": 510.3099,
|
| 6 |
+
"train_samples_per_second": 22.29,
|
| 7 |
+
"train_steps_per_second": 0.343
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,344 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9120879120879121,
|
| 3 |
+
"best_model_checkpoint": "document-crop/checkpoint-166",
|
| 4 |
+
"epoch": 24.137931034482758,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 175,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.9655172413793104,
|
| 13 |
+
"eval_accuracy": 0.5494505494505495,
|
| 14 |
+
"eval_loss": 0.7309015393257141,
|
| 15 |
+
"eval_runtime": 2.5551,
|
| 16 |
+
"eval_samples_per_second": 35.615,
|
| 17 |
+
"eval_steps_per_second": 2.348,
|
| 18 |
+
"step": 7
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.9310344827586206,
|
| 22 |
+
"eval_accuracy": 0.5934065934065934,
|
| 23 |
+
"eval_loss": 0.6288828253746033,
|
| 24 |
+
"eval_runtime": 2.6587,
|
| 25 |
+
"eval_samples_per_second": 34.228,
|
| 26 |
+
"eval_steps_per_second": 2.257,
|
| 27 |
+
"step": 14
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0689655172413794,
|
| 31 |
+
"grad_norm": 25.187419891357422,
|
| 32 |
+
"learning_rate": 4.166666666666667e-05,
|
| 33 |
+
"loss": 0.6408,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.896551724137931,
|
| 38 |
+
"eval_accuracy": 0.6923076923076923,
|
| 39 |
+
"eval_loss": 0.5929833054542542,
|
| 40 |
+
"eval_runtime": 2.6282,
|
| 41 |
+
"eval_samples_per_second": 34.625,
|
| 42 |
+
"eval_steps_per_second": 2.283,
|
| 43 |
+
"step": 21
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 4.0,
|
| 47 |
+
"eval_accuracy": 0.6153846153846154,
|
| 48 |
+
"eval_loss": 0.896169126033783,
|
| 49 |
+
"eval_runtime": 2.573,
|
| 50 |
+
"eval_samples_per_second": 35.368,
|
| 51 |
+
"eval_steps_per_second": 2.332,
|
| 52 |
+
"step": 29
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 4.137931034482759,
|
| 56 |
+
"grad_norm": 14.1068754196167,
|
| 57 |
+
"learning_rate": 4.617834394904459e-05,
|
| 58 |
+
"loss": 0.4193,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.9655172413793105,
|
| 63 |
+
"eval_accuracy": 0.8021978021978022,
|
| 64 |
+
"eval_loss": 0.4717129170894623,
|
| 65 |
+
"eval_runtime": 2.6421,
|
| 66 |
+
"eval_samples_per_second": 34.442,
|
| 67 |
+
"eval_steps_per_second": 2.271,
|
| 68 |
+
"step": 36
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.931034482758621,
|
| 72 |
+
"eval_accuracy": 0.8241758241758241,
|
| 73 |
+
"eval_loss": 0.4143160581588745,
|
| 74 |
+
"eval_runtime": 2.7032,
|
| 75 |
+
"eval_samples_per_second": 33.663,
|
| 76 |
+
"eval_steps_per_second": 2.22,
|
| 77 |
+
"step": 43
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.206896551724138,
|
| 81 |
+
"grad_norm": 17.542375564575195,
|
| 82 |
+
"learning_rate": 4.1401273885350325e-05,
|
| 83 |
+
"loss": 0.3622,
|
| 84 |
+
"step": 45
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.896551724137931,
|
| 88 |
+
"eval_accuracy": 0.8241758241758241,
|
| 89 |
+
"eval_loss": 0.4415420591831207,
|
| 90 |
+
"eval_runtime": 2.674,
|
| 91 |
+
"eval_samples_per_second": 34.031,
|
| 92 |
+
"eval_steps_per_second": 2.244,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.0,
|
| 97 |
+
"eval_accuracy": 0.8461538461538461,
|
| 98 |
+
"eval_loss": 0.3617265224456787,
|
| 99 |
+
"eval_runtime": 2.614,
|
| 100 |
+
"eval_samples_per_second": 34.813,
|
| 101 |
+
"eval_steps_per_second": 2.295,
|
| 102 |
+
"step": 58
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.275862068965518,
|
| 106 |
+
"grad_norm": 15.421939849853516,
|
| 107 |
+
"learning_rate": 3.662420382165605e-05,
|
| 108 |
+
"loss": 0.2049,
|
| 109 |
+
"step": 60
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 8.96551724137931,
|
| 113 |
+
"eval_accuracy": 0.8351648351648352,
|
| 114 |
+
"eval_loss": 0.4249739944934845,
|
| 115 |
+
"eval_runtime": 2.7136,
|
| 116 |
+
"eval_samples_per_second": 33.534,
|
| 117 |
+
"eval_steps_per_second": 2.211,
|
| 118 |
+
"step": 65
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 9.931034482758621,
|
| 122 |
+
"eval_accuracy": 0.8461538461538461,
|
| 123 |
+
"eval_loss": 0.40621432662010193,
|
| 124 |
+
"eval_runtime": 2.6749,
|
| 125 |
+
"eval_samples_per_second": 34.02,
|
| 126 |
+
"eval_steps_per_second": 2.243,
|
| 127 |
+
"step": 72
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 10.344827586206897,
|
| 131 |
+
"grad_norm": 30.14670181274414,
|
| 132 |
+
"learning_rate": 3.184713375796178e-05,
|
| 133 |
+
"loss": 0.1712,
|
| 134 |
+
"step": 75
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.89655172413793,
|
| 138 |
+
"eval_accuracy": 0.8241758241758241,
|
| 139 |
+
"eval_loss": 0.4119836986064911,
|
| 140 |
+
"eval_runtime": 2.729,
|
| 141 |
+
"eval_samples_per_second": 33.345,
|
| 142 |
+
"eval_steps_per_second": 2.199,
|
| 143 |
+
"step": 79
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 12.0,
|
| 147 |
+
"eval_accuracy": 0.8131868131868132,
|
| 148 |
+
"eval_loss": 0.5776697397232056,
|
| 149 |
+
"eval_runtime": 2.6961,
|
| 150 |
+
"eval_samples_per_second": 33.753,
|
| 151 |
+
"eval_steps_per_second": 2.225,
|
| 152 |
+
"step": 87
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.413793103448276,
|
| 156 |
+
"grad_norm": 28.829450607299805,
|
| 157 |
+
"learning_rate": 2.707006369426752e-05,
|
| 158 |
+
"loss": 0.1291,
|
| 159 |
+
"step": 90
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.96551724137931,
|
| 163 |
+
"eval_accuracy": 0.8571428571428571,
|
| 164 |
+
"eval_loss": 0.35304272174835205,
|
| 165 |
+
"eval_runtime": 2.6568,
|
| 166 |
+
"eval_samples_per_second": 34.252,
|
| 167 |
+
"eval_steps_per_second": 2.258,
|
| 168 |
+
"step": 94
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.931034482758621,
|
| 172 |
+
"eval_accuracy": 0.8571428571428571,
|
| 173 |
+
"eval_loss": 0.3431708812713623,
|
| 174 |
+
"eval_runtime": 2.6667,
|
| 175 |
+
"eval_samples_per_second": 34.124,
|
| 176 |
+
"eval_steps_per_second": 2.25,
|
| 177 |
+
"step": 101
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 14.482758620689655,
|
| 181 |
+
"grad_norm": 11.376550674438477,
|
| 182 |
+
"learning_rate": 2.229299363057325e-05,
|
| 183 |
+
"loss": 0.0836,
|
| 184 |
+
"step": 105
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 14.89655172413793,
|
| 188 |
+
"eval_accuracy": 0.8901098901098901,
|
| 189 |
+
"eval_loss": 0.2557763159275055,
|
| 190 |
+
"eval_runtime": 2.6632,
|
| 191 |
+
"eval_samples_per_second": 34.169,
|
| 192 |
+
"eval_steps_per_second": 2.253,
|
| 193 |
+
"step": 108
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 16.0,
|
| 197 |
+
"eval_accuracy": 0.8351648351648352,
|
| 198 |
+
"eval_loss": 0.45357275009155273,
|
| 199 |
+
"eval_runtime": 2.6883,
|
| 200 |
+
"eval_samples_per_second": 33.85,
|
| 201 |
+
"eval_steps_per_second": 2.232,
|
| 202 |
+
"step": 116
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 16.551724137931036,
|
| 206 |
+
"grad_norm": 5.885956287384033,
|
| 207 |
+
"learning_rate": 1.751592356687898e-05,
|
| 208 |
+
"loss": 0.1053,
|
| 209 |
+
"step": 120
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 16.96551724137931,
|
| 213 |
+
"eval_accuracy": 0.8461538461538461,
|
| 214 |
+
"eval_loss": 0.46378985047340393,
|
| 215 |
+
"eval_runtime": 2.6068,
|
| 216 |
+
"eval_samples_per_second": 34.909,
|
| 217 |
+
"eval_steps_per_second": 2.302,
|
| 218 |
+
"step": 123
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 17.93103448275862,
|
| 222 |
+
"eval_accuracy": 0.8351648351648352,
|
| 223 |
+
"eval_loss": 0.5922185182571411,
|
| 224 |
+
"eval_runtime": 2.6604,
|
| 225 |
+
"eval_samples_per_second": 34.205,
|
| 226 |
+
"eval_steps_per_second": 2.255,
|
| 227 |
+
"step": 130
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 18.620689655172413,
|
| 231 |
+
"grad_norm": 5.540600299835205,
|
| 232 |
+
"learning_rate": 1.2738853503184714e-05,
|
| 233 |
+
"loss": 0.0734,
|
| 234 |
+
"step": 135
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 18.896551724137932,
|
| 238 |
+
"eval_accuracy": 0.8681318681318682,
|
| 239 |
+
"eval_loss": 0.3474012613296509,
|
| 240 |
+
"eval_runtime": 2.7317,
|
| 241 |
+
"eval_samples_per_second": 33.313,
|
| 242 |
+
"eval_steps_per_second": 2.196,
|
| 243 |
+
"step": 137
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 20.0,
|
| 247 |
+
"eval_accuracy": 0.8461538461538461,
|
| 248 |
+
"eval_loss": 0.5510861277580261,
|
| 249 |
+
"eval_runtime": 2.6777,
|
| 250 |
+
"eval_samples_per_second": 33.984,
|
| 251 |
+
"eval_steps_per_second": 2.241,
|
| 252 |
+
"step": 145
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.689655172413794,
|
| 256 |
+
"grad_norm": 7.2109575271606445,
|
| 257 |
+
"learning_rate": 7.961783439490445e-06,
|
| 258 |
+
"loss": 0.046,
|
| 259 |
+
"step": 150
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 20.96551724137931,
|
| 263 |
+
"eval_accuracy": 0.8461538461538461,
|
| 264 |
+
"eval_loss": 0.5115231275558472,
|
| 265 |
+
"eval_runtime": 2.7397,
|
| 266 |
+
"eval_samples_per_second": 33.215,
|
| 267 |
+
"eval_steps_per_second": 2.19,
|
| 268 |
+
"step": 152
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 21.93103448275862,
|
| 272 |
+
"eval_accuracy": 0.9010989010989011,
|
| 273 |
+
"eval_loss": 0.3096972107887268,
|
| 274 |
+
"eval_runtime": 2.8257,
|
| 275 |
+
"eval_samples_per_second": 32.204,
|
| 276 |
+
"eval_steps_per_second": 2.123,
|
| 277 |
+
"step": 159
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 22.75862068965517,
|
| 281 |
+
"grad_norm": 5.06452751159668,
|
| 282 |
+
"learning_rate": 3.1847133757961785e-06,
|
| 283 |
+
"loss": 0.0139,
|
| 284 |
+
"step": 165
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 22.896551724137932,
|
| 288 |
+
"eval_accuracy": 0.9120879120879121,
|
| 289 |
+
"eval_loss": 0.2510547637939453,
|
| 290 |
+
"eval_runtime": 2.7875,
|
| 291 |
+
"eval_samples_per_second": 32.645,
|
| 292 |
+
"eval_steps_per_second": 2.152,
|
| 293 |
+
"step": 166
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 24.0,
|
| 297 |
+
"eval_accuracy": 0.9120879120879121,
|
| 298 |
+
"eval_loss": 0.28634488582611084,
|
| 299 |
+
"eval_runtime": 2.6795,
|
| 300 |
+
"eval_samples_per_second": 33.961,
|
| 301 |
+
"eval_steps_per_second": 2.239,
|
| 302 |
+
"step": 174
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 24.137931034482758,
|
| 306 |
+
"eval_accuracy": 0.9120879120879121,
|
| 307 |
+
"eval_loss": 0.28424757719039917,
|
| 308 |
+
"eval_runtime": 2.9131,
|
| 309 |
+
"eval_samples_per_second": 31.238,
|
| 310 |
+
"eval_steps_per_second": 2.06,
|
| 311 |
+
"step": 175
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 24.137931034482758,
|
| 315 |
+
"step": 175,
|
| 316 |
+
"total_flos": 8.67232581632557e+17,
|
| 317 |
+
"train_loss": 0.1937425845861435,
|
| 318 |
+
"train_runtime": 510.3099,
|
| 319 |
+
"train_samples_per_second": 22.29,
|
| 320 |
+
"train_steps_per_second": 0.343
|
| 321 |
+
}
|
| 322 |
+
],
|
| 323 |
+
"logging_steps": 15,
|
| 324 |
+
"max_steps": 175,
|
| 325 |
+
"num_input_tokens_seen": 0,
|
| 326 |
+
"num_train_epochs": 25,
|
| 327 |
+
"save_steps": 500,
|
| 328 |
+
"stateful_callbacks": {
|
| 329 |
+
"TrainerControl": {
|
| 330 |
+
"args": {
|
| 331 |
+
"should_epoch_stop": false,
|
| 332 |
+
"should_evaluate": false,
|
| 333 |
+
"should_log": false,
|
| 334 |
+
"should_save": true,
|
| 335 |
+
"should_training_stop": true
|
| 336 |
+
},
|
| 337 |
+
"attributes": {}
|
| 338 |
+
}
|
| 339 |
+
},
|
| 340 |
+
"total_flos": 8.67232581632557e+17,
|
| 341 |
+
"train_batch_size": 16,
|
| 342 |
+
"trial_name": null,
|
| 343 |
+
"trial_params": null
|
| 344 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea6a0c157d895bd61838d31585af25facef08d9f0026f770573053513da974f8
|
| 3 |
size 5176
|