Finished training
Browse files- all_results.json +13 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- runs/Jun12_17-39-26_i16n1.ocelote.hpc.arizona.edu/events.out.tfevents.1655080779.i16n1.ocelote.hpc.arizona.edu.25711.0 +2 -2
- runs/Jun12_17-39-26_i16n1.ocelote.hpc.arizona.edu/events.out.tfevents.1655116971.i16n1.ocelote.hpc.arizona.edu.25711.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +463 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.07,
|
| 3 |
+
"eval_accuracy": 0.7343260188087775,
|
| 4 |
+
"eval_loss": NaN,
|
| 5 |
+
"eval_runtime": 59.7956,
|
| 6 |
+
"eval_samples_per_second": 167.236,
|
| 7 |
+
"eval_steps_per_second": 10.452,
|
| 8 |
+
"perplexity": NaN,
|
| 9 |
+
"train_loss": 1.9488013319535689,
|
| 10 |
+
"train_runtime": 36132.536,
|
| 11 |
+
"train_samples_per_second": 22140.71,
|
| 12 |
+
"train_steps_per_second": 2.768
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.07,
|
| 3 |
+
"eval_accuracy": 0.7343260188087775,
|
| 4 |
+
"eval_loss": NaN,
|
| 5 |
+
"eval_runtime": 59.7956,
|
| 6 |
+
"eval_samples_per_second": 167.236,
|
| 7 |
+
"eval_steps_per_second": 10.452,
|
| 8 |
+
"perplexity": NaN
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438128811
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93853913b51a725fe33d36f9613a604439071e3bc41711f9640b05ebbfb338d7
|
| 3 |
size 438128811
|
runs/Jun12_17-39-26_i16n1.ocelote.hpc.arizona.edu/events.out.tfevents.1655080779.i16n1.ocelote.hpc.arizona.edu.25711.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcd8a30fa1a782d7d169d60e31ba439494819ff0614230e84aeff65a924ea487
|
| 3 |
+
size 16092
|
runs/Jun12_17-39-26_i16n1.ocelote.hpc.arizona.edu/events.out.tfevents.1655116971.i16n1.ocelote.hpc.arizona.edu.25711.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4da9b543c5085516c656114f6b16c197e9b10e45499c8fd5e0330663a15439d2
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.07,
|
| 3 |
+
"train_loss": 1.9488013319535689,
|
| 4 |
+
"train_runtime": 36132.536,
|
| 5 |
+
"train_samples_per_second": 22140.71,
|
| 6 |
+
"train_steps_per_second": 2.768
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,463 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.735632183908046,
|
| 3 |
+
"best_model_checkpoint": "/xdisk/msurdeanu/enoriega/kw_pubmed_experiments/kw_pubmed_keyword_sentence_10000_0.0003/checkpoint-25",
|
| 4 |
+
"epoch": 1.06578081831338,
|
| 5 |
+
"global_step": 275,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 0.000299991,
|
| 13 |
+
"loss": 2.0241,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 0.000299976,
|
| 19 |
+
"loss": 1.3033,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 0.000299961,
|
| 25 |
+
"loss": 1.5029,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 0.000299946,
|
| 31 |
+
"loss": 1.2483,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.1,
|
| 36 |
+
"learning_rate": 0.00029993099999999997,
|
| 37 |
+
"loss": 1.4697,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"eval_accuracy": 0.735632183908046,
|
| 43 |
+
"eval_loss": NaN,
|
| 44 |
+
"eval_runtime": 59.6178,
|
| 45 |
+
"eval_samples_per_second": 167.735,
|
| 46 |
+
"eval_steps_per_second": 10.483,
|
| 47 |
+
"step": 25
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.12,
|
| 51 |
+
"learning_rate": 0.000299916,
|
| 52 |
+
"loss": 1.2378,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 0.00029990099999999993,
|
| 58 |
+
"loss": 1.7161,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15,
|
| 63 |
+
"learning_rate": 0.00029988599999999997,
|
| 64 |
+
"loss": 2.0569,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17,
|
| 69 |
+
"learning_rate": 0.00029987099999999995,
|
| 70 |
+
"loss": 2.1263,
|
| 71 |
+
"step": 45
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.19,
|
| 75 |
+
"learning_rate": 0.000299856,
|
| 76 |
+
"loss": 2.5526,
|
| 77 |
+
"step": 50
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.19,
|
| 81 |
+
"eval_accuracy": 0.723092998955068,
|
| 82 |
+
"eval_loss": NaN,
|
| 83 |
+
"eval_runtime": 59.378,
|
| 84 |
+
"eval_samples_per_second": 168.412,
|
| 85 |
+
"eval_steps_per_second": 10.526,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21,
|
| 90 |
+
"learning_rate": 0.00029984099999999996,
|
| 91 |
+
"loss": 1.2865,
|
| 92 |
+
"step": 55
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.23,
|
| 96 |
+
"learning_rate": 0.000299829,
|
| 97 |
+
"loss": 2.0071,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.25,
|
| 102 |
+
"learning_rate": 0.00029981399999999997,
|
| 103 |
+
"loss": 2.3439,
|
| 104 |
+
"step": 65
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.27,
|
| 108 |
+
"learning_rate": 0.000299799,
|
| 109 |
+
"loss": 1.5348,
|
| 110 |
+
"step": 70
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.29,
|
| 114 |
+
"learning_rate": 0.00029978399999999993,
|
| 115 |
+
"loss": 2.3377,
|
| 116 |
+
"step": 75
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.29,
|
| 120 |
+
"eval_accuracy": 0.7082027168234065,
|
| 121 |
+
"eval_loss": NaN,
|
| 122 |
+
"eval_runtime": 59.6718,
|
| 123 |
+
"eval_samples_per_second": 167.583,
|
| 124 |
+
"eval_steps_per_second": 10.474,
|
| 125 |
+
"step": 75
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.31,
|
| 129 |
+
"learning_rate": 0.00029976899999999997,
|
| 130 |
+
"loss": 1.7853,
|
| 131 |
+
"step": 80
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.33,
|
| 135 |
+
"learning_rate": 0.00029975399999999995,
|
| 136 |
+
"loss": 1.9305,
|
| 137 |
+
"step": 85
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.35,
|
| 141 |
+
"learning_rate": 0.000299739,
|
| 142 |
+
"loss": 1.9862,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.37,
|
| 147 |
+
"learning_rate": 0.00029972399999999996,
|
| 148 |
+
"loss": 3.8541,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.39,
|
| 153 |
+
"learning_rate": 0.00029970899999999995,
|
| 154 |
+
"loss": 2.9479,
|
| 155 |
+
"step": 100
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.39,
|
| 159 |
+
"eval_accuracy": 0.6987983281086729,
|
| 160 |
+
"eval_loss": NaN,
|
| 161 |
+
"eval_runtime": 59.6999,
|
| 162 |
+
"eval_samples_per_second": 167.505,
|
| 163 |
+
"eval_steps_per_second": 10.469,
|
| 164 |
+
"step": 100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.41,
|
| 168 |
+
"learning_rate": 0.000299694,
|
| 169 |
+
"loss": 2.1467,
|
| 170 |
+
"step": 105
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.43,
|
| 174 |
+
"learning_rate": 0.00029967899999999996,
|
| 175 |
+
"loss": 2.8996,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.44,
|
| 180 |
+
"learning_rate": 0.000299664,
|
| 181 |
+
"loss": 3.0211,
|
| 182 |
+
"step": 115
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.46,
|
| 186 |
+
"learning_rate": 0.000299649,
|
| 187 |
+
"loss": 2.2422,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.48,
|
| 192 |
+
"learning_rate": 0.00029963399999999996,
|
| 193 |
+
"loss": 1.4212,
|
| 194 |
+
"step": 125
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.48,
|
| 198 |
+
"eval_accuracy": 0.705067920585162,
|
| 199 |
+
"eval_loss": NaN,
|
| 200 |
+
"eval_runtime": 59.6589,
|
| 201 |
+
"eval_samples_per_second": 167.62,
|
| 202 |
+
"eval_steps_per_second": 10.476,
|
| 203 |
+
"step": 125
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.5,
|
| 207 |
+
"learning_rate": 0.000299619,
|
| 208 |
+
"loss": 1.8562,
|
| 209 |
+
"step": 130
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.52,
|
| 213 |
+
"learning_rate": 0.00029960399999999997,
|
| 214 |
+
"loss": 2.0218,
|
| 215 |
+
"step": 135
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.54,
|
| 219 |
+
"learning_rate": 0.00029958899999999995,
|
| 220 |
+
"loss": 1.331,
|
| 221 |
+
"step": 140
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.56,
|
| 225 |
+
"learning_rate": 0.000299574,
|
| 226 |
+
"loss": 1.9291,
|
| 227 |
+
"step": 145
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.58,
|
| 231 |
+
"learning_rate": 0.00029955899999999997,
|
| 232 |
+
"loss": 1.8373,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.58,
|
| 237 |
+
"eval_accuracy": 0.7189132706374086,
|
| 238 |
+
"eval_loss": NaN,
|
| 239 |
+
"eval_runtime": 59.6305,
|
| 240 |
+
"eval_samples_per_second": 167.699,
|
| 241 |
+
"eval_steps_per_second": 10.481,
|
| 242 |
+
"step": 150
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.6,
|
| 246 |
+
"learning_rate": 0.000299544,
|
| 247 |
+
"loss": 1.9669,
|
| 248 |
+
"step": 155
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.62,
|
| 252 |
+
"learning_rate": 0.000299529,
|
| 253 |
+
"loss": 1.8719,
|
| 254 |
+
"step": 160
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.64,
|
| 258 |
+
"learning_rate": 0.00029951399999999997,
|
| 259 |
+
"loss": 2.4312,
|
| 260 |
+
"step": 165
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.66,
|
| 264 |
+
"learning_rate": 0.000299499,
|
| 265 |
+
"loss": 3.1182,
|
| 266 |
+
"step": 170
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.68,
|
| 270 |
+
"learning_rate": 0.000299484,
|
| 271 |
+
"loss": 1.5001,
|
| 272 |
+
"step": 175
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.68,
|
| 276 |
+
"eval_accuracy": 0.6812957157784744,
|
| 277 |
+
"eval_loss": NaN,
|
| 278 |
+
"eval_runtime": 59.7742,
|
| 279 |
+
"eval_samples_per_second": 167.296,
|
| 280 |
+
"eval_steps_per_second": 10.456,
|
| 281 |
+
"step": 175
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.7,
|
| 285 |
+
"learning_rate": 0.00029946899999999996,
|
| 286 |
+
"loss": 1.493,
|
| 287 |
+
"step": 180
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.72,
|
| 291 |
+
"learning_rate": 0.00029945399999999994,
|
| 292 |
+
"loss": 1.5281,
|
| 293 |
+
"step": 185
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.74,
|
| 297 |
+
"learning_rate": 0.000299439,
|
| 298 |
+
"loss": 1.6081,
|
| 299 |
+
"step": 190
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.75,
|
| 303 |
+
"learning_rate": 0.00029942399999999996,
|
| 304 |
+
"loss": 1.4183,
|
| 305 |
+
"step": 195
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.77,
|
| 309 |
+
"learning_rate": 0.000299409,
|
| 310 |
+
"loss": 1.9615,
|
| 311 |
+
"step": 200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.77,
|
| 315 |
+
"eval_accuracy": 0.7055903866248694,
|
| 316 |
+
"eval_loss": NaN,
|
| 317 |
+
"eval_runtime": 59.6776,
|
| 318 |
+
"eval_samples_per_second": 167.567,
|
| 319 |
+
"eval_steps_per_second": 10.473,
|
| 320 |
+
"step": 200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.79,
|
| 324 |
+
"learning_rate": 0.000299394,
|
| 325 |
+
"loss": 1.7213,
|
| 326 |
+
"step": 205
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.81,
|
| 330 |
+
"learning_rate": 0.00029937899999999995,
|
| 331 |
+
"loss": 1.5657,
|
| 332 |
+
"step": 210
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.83,
|
| 336 |
+
"learning_rate": 0.000299364,
|
| 337 |
+
"loss": 1.6782,
|
| 338 |
+
"step": 215
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.85,
|
| 342 |
+
"learning_rate": 0.00029934899999999997,
|
| 343 |
+
"loss": 2.0081,
|
| 344 |
+
"step": 220
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.87,
|
| 348 |
+
"learning_rate": 0.00029933399999999995,
|
| 349 |
+
"loss": 1.4458,
|
| 350 |
+
"step": 225
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.87,
|
| 354 |
+
"eval_accuracy": 0.6974921630094044,
|
| 355 |
+
"eval_loss": NaN,
|
| 356 |
+
"eval_runtime": 59.7906,
|
| 357 |
+
"eval_samples_per_second": 167.25,
|
| 358 |
+
"eval_steps_per_second": 10.453,
|
| 359 |
+
"step": 225
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.89,
|
| 363 |
+
"learning_rate": 0.000299322,
|
| 364 |
+
"loss": 1.7357,
|
| 365 |
+
"step": 230
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.91,
|
| 369 |
+
"learning_rate": 0.00029930699999999996,
|
| 370 |
+
"loss": 4.7272,
|
| 371 |
+
"step": 235
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.93,
|
| 375 |
+
"learning_rate": 0.00029929199999999994,
|
| 376 |
+
"loss": 1.6994,
|
| 377 |
+
"step": 240
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.95,
|
| 381 |
+
"learning_rate": 0.000299277,
|
| 382 |
+
"loss": 1.6879,
|
| 383 |
+
"step": 245
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.97,
|
| 387 |
+
"learning_rate": 0.00029926199999999995,
|
| 388 |
+
"loss": 1.4237,
|
| 389 |
+
"step": 250
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.97,
|
| 393 |
+
"eval_accuracy": 0.7087251828631139,
|
| 394 |
+
"eval_loss": NaN,
|
| 395 |
+
"eval_runtime": 59.7381,
|
| 396 |
+
"eval_samples_per_second": 167.397,
|
| 397 |
+
"eval_steps_per_second": 10.462,
|
| 398 |
+
"step": 250
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.99,
|
| 402 |
+
"learning_rate": 0.000299247,
|
| 403 |
+
"loss": 1.5802,
|
| 404 |
+
"step": 255
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.01,
|
| 408 |
+
"learning_rate": 0.00029923199999999997,
|
| 409 |
+
"loss": 2.2637,
|
| 410 |
+
"step": 260
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.03,
|
| 414 |
+
"learning_rate": 0.00029921699999999995,
|
| 415 |
+
"loss": 1.4615,
|
| 416 |
+
"step": 265
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.05,
|
| 420 |
+
"learning_rate": 0.000299202,
|
| 421 |
+
"loss": 1.6544,
|
| 422 |
+
"step": 270
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.07,
|
| 426 |
+
"learning_rate": 0.00029918699999999997,
|
| 427 |
+
"loss": 1.6758,
|
| 428 |
+
"step": 275
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.07,
|
| 432 |
+
"eval_accuracy": 0.6922675026123302,
|
| 433 |
+
"eval_loss": NaN,
|
| 434 |
+
"eval_runtime": 59.6857,
|
| 435 |
+
"eval_samples_per_second": 167.544,
|
| 436 |
+
"eval_steps_per_second": 10.472,
|
| 437 |
+
"step": 275
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.07,
|
| 441 |
+
"step": 275,
|
| 442 |
+
"total_flos": 1.493606932357716e+17,
|
| 443 |
+
"train_loss": 1.9488013319535689,
|
| 444 |
+
"train_runtime": 36132.536,
|
| 445 |
+
"train_samples_per_second": 22140.71,
|
| 446 |
+
"train_steps_per_second": 2.768
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.07,
|
| 450 |
+
"eval_accuracy": 0.7343260188087775,
|
| 451 |
+
"eval_loss": NaN,
|
| 452 |
+
"eval_runtime": 59.7956,
|
| 453 |
+
"eval_samples_per_second": 167.236,
|
| 454 |
+
"eval_steps_per_second": 10.452,
|
| 455 |
+
"step": 275
|
| 456 |
+
}
|
| 457 |
+
],
|
| 458 |
+
"max_steps": 100000,
|
| 459 |
+
"num_train_epochs": 388,
|
| 460 |
+
"total_flos": 1.493606932357716e+17,
|
| 461 |
+
"trial_name": null,
|
| 462 |
+
"trial_params": null
|
| 463 |
+
}
|