Finished training
Browse files- all_results.json +13 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- runs/Jun12_17-39-37_i16n5.ocelote.hpc.arizona.edu/events.out.tfevents.1655080792.i16n5.ocelote.hpc.arizona.edu.1350.0 +2 -2
- runs/Jun12_17-39-37_i16n5.ocelote.hpc.arizona.edu/events.out.tfevents.1655126979.i16n5.ocelote.hpc.arizona.edu.1350.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +580 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.36,
|
| 3 |
+
"eval_accuracy": 0.6470223174085522,
|
| 4 |
+
"eval_loss": 1.767507791519165,
|
| 5 |
+
"eval_runtime": 60.4981,
|
| 6 |
+
"eval_samples_per_second": 165.295,
|
| 7 |
+
"eval_steps_per_second": 10.331,
|
| 8 |
+
"perplexity": 5.8562401879466695,
|
| 9 |
+
"train_loss": 1.8697899763924735,
|
| 10 |
+
"train_runtime": 46126.5574,
|
| 11 |
+
"train_samples_per_second": 17343.588,
|
| 12 |
+
"train_steps_per_second": 2.168
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.36,
|
| 3 |
+
"eval_accuracy": 0.6470223174085522,
|
| 4 |
+
"eval_loss": 1.767507791519165,
|
| 5 |
+
"eval_runtime": 60.4981,
|
| 6 |
+
"eval_samples_per_second": 165.295,
|
| 7 |
+
"eval_steps_per_second": 10.331,
|
| 8 |
+
"perplexity": 5.8562401879466695
|
| 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:a21631d7306045d30d9ef68bb5237ab7f16eaa6bad5a717ce2a60bb3d9f7c214
|
| 3 |
size 438128811
|
runs/Jun12_17-39-37_i16n5.ocelote.hpc.arizona.edu/events.out.tfevents.1655080792.i16n5.ocelote.hpc.arizona.edu.1350.0
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:d8da4134c3b61c89ee395cb1a68bc2c9c8e66c7e14baafe46b380cd8b36662d5
|
| 3 |
+
size 19416
|
runs/Jun12_17-39-37_i16n5.ocelote.hpc.arizona.edu/events.out.tfevents.1655126979.i16n5.ocelote.hpc.arizona.edu.1350.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5425b8b98a60c99999edec21a54261ce156386da88a691bc7582d93eeff00294
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.36,
|
| 3 |
+
"train_loss": 1.8697899763924735,
|
| 4 |
+
"train_runtime": 46126.5574,
|
| 5 |
+
"train_samples_per_second": 17343.588,
|
| 6 |
+
"train_steps_per_second": 2.168
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,580 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6465878115264797,
|
| 3 |
+
"best_model_checkpoint": "/xdisk/msurdeanu/enoriega/kw_pubmed_experiments/kw_pubmed_vanilla_document_10000_0.0003/checkpoint-100",
|
| 4 |
+
"epoch": 1.3559903108724085,
|
| 5 |
+
"global_step": 350,
|
| 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": 0.00029998499999999995,
|
| 13 |
+
"loss": 2.5567,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 0.00029997,
|
| 19 |
+
"loss": 1.9715,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 0.00029995499999999997,
|
| 25 |
+
"loss": 1.8692,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 0.00029994,
|
| 31 |
+
"loss": 1.8491,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.1,
|
| 36 |
+
"learning_rate": 0.000299925,
|
| 37 |
+
"loss": 1.8861,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"eval_accuracy": 0.6368282710280374,
|
| 43 |
+
"eval_loss": 1.842035174369812,
|
| 44 |
+
"eval_runtime": 60.5692,
|
| 45 |
+
"eval_samples_per_second": 165.101,
|
| 46 |
+
"eval_steps_per_second": 10.319,
|
| 47 |
+
"step": 25
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.12,
|
| 51 |
+
"learning_rate": 0.00029991299999999996,
|
| 52 |
+
"loss": 1.8289,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 0.000299898,
|
| 58 |
+
"loss": 1.813,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15,
|
| 63 |
+
"learning_rate": 0.000299883,
|
| 64 |
+
"loss": 1.8096,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17,
|
| 69 |
+
"learning_rate": 0.00029986799999999996,
|
| 70 |
+
"loss": 1.8019,
|
| 71 |
+
"step": 45
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.19,
|
| 75 |
+
"learning_rate": 0.000299853,
|
| 76 |
+
"loss": 1.7913,
|
| 77 |
+
"step": 50
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.19,
|
| 81 |
+
"eval_accuracy": 0.6451718892607241,
|
| 82 |
+
"eval_loss": 1.7883105278015137,
|
| 83 |
+
"eval_runtime": 60.4628,
|
| 84 |
+
"eval_samples_per_second": 165.391,
|
| 85 |
+
"eval_steps_per_second": 10.337,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21,
|
| 90 |
+
"learning_rate": 0.00029983799999999997,
|
| 91 |
+
"loss": 1.7907,
|
| 92 |
+
"step": 55
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.23,
|
| 96 |
+
"learning_rate": 0.000299823,
|
| 97 |
+
"loss": 1.7853,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.25,
|
| 102 |
+
"learning_rate": 0.000299808,
|
| 103 |
+
"loss": 1.7915,
|
| 104 |
+
"step": 65
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.27,
|
| 108 |
+
"learning_rate": 0.00029979299999999997,
|
| 109 |
+
"loss": 1.7815,
|
| 110 |
+
"step": 70
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.29,
|
| 114 |
+
"learning_rate": 0.000299778,
|
| 115 |
+
"loss": 1.7876,
|
| 116 |
+
"step": 75
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.29,
|
| 120 |
+
"eval_accuracy": 0.6446729540614542,
|
| 121 |
+
"eval_loss": 1.7794435024261475,
|
| 122 |
+
"eval_runtime": 60.2635,
|
| 123 |
+
"eval_samples_per_second": 165.938,
|
| 124 |
+
"eval_steps_per_second": 10.371,
|
| 125 |
+
"step": 75
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.31,
|
| 129 |
+
"learning_rate": 0.000299763,
|
| 130 |
+
"loss": 1.7707,
|
| 131 |
+
"step": 80
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.33,
|
| 135 |
+
"learning_rate": 0.00029974799999999996,
|
| 136 |
+
"loss": 1.7773,
|
| 137 |
+
"step": 85
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.35,
|
| 141 |
+
"learning_rate": 0.000299733,
|
| 142 |
+
"loss": 1.7759,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.37,
|
| 147 |
+
"learning_rate": 0.000299718,
|
| 148 |
+
"loss": 1.7662,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.39,
|
| 153 |
+
"learning_rate": 0.00029970299999999996,
|
| 154 |
+
"loss": 1.7729,
|
| 155 |
+
"step": 100
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.39,
|
| 159 |
+
"eval_accuracy": 0.6465878115264797,
|
| 160 |
+
"eval_loss": 1.7647390365600586,
|
| 161 |
+
"eval_runtime": 60.2769,
|
| 162 |
+
"eval_samples_per_second": 165.901,
|
| 163 |
+
"eval_steps_per_second": 10.369,
|
| 164 |
+
"step": 100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.41,
|
| 168 |
+
"learning_rate": 0.00029968799999999994,
|
| 169 |
+
"loss": 1.7748,
|
| 170 |
+
"step": 105
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.43,
|
| 174 |
+
"learning_rate": 0.000299673,
|
| 175 |
+
"loss": 1.7706,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.44,
|
| 180 |
+
"learning_rate": 0.00029965799999999996,
|
| 181 |
+
"loss": 1.785,
|
| 182 |
+
"step": 115
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.46,
|
| 186 |
+
"learning_rate": 0.000299643,
|
| 187 |
+
"loss": 1.778,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.48,
|
| 192 |
+
"learning_rate": 0.00029962799999999997,
|
| 193 |
+
"loss": 1.7919,
|
| 194 |
+
"step": 125
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.48,
|
| 198 |
+
"eval_accuracy": 0.6427293636595962,
|
| 199 |
+
"eval_loss": 1.7991459369659424,
|
| 200 |
+
"eval_runtime": 60.2605,
|
| 201 |
+
"eval_samples_per_second": 165.946,
|
| 202 |
+
"eval_steps_per_second": 10.372,
|
| 203 |
+
"step": 125
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.5,
|
| 207 |
+
"learning_rate": 0.00029961299999999995,
|
| 208 |
+
"loss": 1.8059,
|
| 209 |
+
"step": 130
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.52,
|
| 213 |
+
"learning_rate": 0.000299598,
|
| 214 |
+
"loss": 1.7882,
|
| 215 |
+
"step": 135
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.54,
|
| 219 |
+
"learning_rate": 0.00029958299999999997,
|
| 220 |
+
"loss": 2.0033,
|
| 221 |
+
"step": 140
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.56,
|
| 225 |
+
"learning_rate": 0.00029956799999999995,
|
| 226 |
+
"loss": 1.9014,
|
| 227 |
+
"step": 145
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.58,
|
| 231 |
+
"learning_rate": 0.000299553,
|
| 232 |
+
"loss": 1.858,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.58,
|
| 237 |
+
"eval_accuracy": 0.6386691654294546,
|
| 238 |
+
"eval_loss": 1.8227039575576782,
|
| 239 |
+
"eval_runtime": 60.2921,
|
| 240 |
+
"eval_samples_per_second": 165.859,
|
| 241 |
+
"eval_steps_per_second": 10.366,
|
| 242 |
+
"step": 150
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.6,
|
| 246 |
+
"learning_rate": 0.00029953799999999996,
|
| 247 |
+
"loss": 1.8575,
|
| 248 |
+
"step": 155
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.62,
|
| 252 |
+
"learning_rate": 0.000299523,
|
| 253 |
+
"loss": 1.8191,
|
| 254 |
+
"step": 160
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.64,
|
| 258 |
+
"learning_rate": 0.00029951099999999997,
|
| 259 |
+
"loss": 1.8317,
|
| 260 |
+
"step": 165
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.66,
|
| 264 |
+
"learning_rate": 0.00029949599999999995,
|
| 265 |
+
"loss": 1.8389,
|
| 266 |
+
"step": 170
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.68,
|
| 270 |
+
"learning_rate": 0.000299481,
|
| 271 |
+
"loss": 1.8151,
|
| 272 |
+
"step": 175
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.68,
|
| 276 |
+
"eval_accuracy": 0.632689569566646,
|
| 277 |
+
"eval_loss": 1.8751027584075928,
|
| 278 |
+
"eval_runtime": 60.4671,
|
| 279 |
+
"eval_samples_per_second": 165.379,
|
| 280 |
+
"eval_steps_per_second": 10.336,
|
| 281 |
+
"step": 175
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.7,
|
| 285 |
+
"learning_rate": 0.00029946599999999997,
|
| 286 |
+
"loss": 1.8842,
|
| 287 |
+
"step": 180
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.72,
|
| 291 |
+
"learning_rate": 0.00029945099999999995,
|
| 292 |
+
"loss": 1.8344,
|
| 293 |
+
"step": 185
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.74,
|
| 297 |
+
"learning_rate": 0.000299436,
|
| 298 |
+
"loss": 1.8594,
|
| 299 |
+
"step": 190
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.75,
|
| 303 |
+
"learning_rate": 0.00029942099999999996,
|
| 304 |
+
"loss": 1.9278,
|
| 305 |
+
"step": 195
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.77,
|
| 309 |
+
"learning_rate": 0.000299406,
|
| 310 |
+
"loss": 1.8539,
|
| 311 |
+
"step": 200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.77,
|
| 315 |
+
"eval_accuracy": 0.6372984484332218,
|
| 316 |
+
"eval_loss": 1.8315496444702148,
|
| 317 |
+
"eval_runtime": 60.2374,
|
| 318 |
+
"eval_samples_per_second": 166.01,
|
| 319 |
+
"eval_steps_per_second": 10.376,
|
| 320 |
+
"step": 200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.79,
|
| 324 |
+
"learning_rate": 0.000299391,
|
| 325 |
+
"loss": 1.8632,
|
| 326 |
+
"step": 205
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.81,
|
| 330 |
+
"learning_rate": 0.00029937599999999996,
|
| 331 |
+
"loss": 1.907,
|
| 332 |
+
"step": 210
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.83,
|
| 336 |
+
"learning_rate": 0.000299361,
|
| 337 |
+
"loss": 1.8705,
|
| 338 |
+
"step": 215
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.85,
|
| 342 |
+
"learning_rate": 0.000299346,
|
| 343 |
+
"loss": 1.8825,
|
| 344 |
+
"step": 220
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.87,
|
| 348 |
+
"learning_rate": 0.000299331,
|
| 349 |
+
"loss": 1.8623,
|
| 350 |
+
"step": 225
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.87,
|
| 354 |
+
"eval_accuracy": 0.6348281107392759,
|
| 355 |
+
"eval_loss": 1.846932053565979,
|
| 356 |
+
"eval_runtime": 60.3517,
|
| 357 |
+
"eval_samples_per_second": 165.695,
|
| 358 |
+
"eval_steps_per_second": 10.356,
|
| 359 |
+
"step": 225
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.89,
|
| 363 |
+
"learning_rate": 0.000299316,
|
| 364 |
+
"loss": 1.8923,
|
| 365 |
+
"step": 230
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.91,
|
| 369 |
+
"learning_rate": 0.00029930099999999997,
|
| 370 |
+
"loss": 1.852,
|
| 371 |
+
"step": 235
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.93,
|
| 375 |
+
"learning_rate": 0.00029928599999999995,
|
| 376 |
+
"loss": 1.8754,
|
| 377 |
+
"step": 240
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.95,
|
| 381 |
+
"learning_rate": 0.00029927099999999993,
|
| 382 |
+
"loss": 1.9014,
|
| 383 |
+
"step": 245
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.97,
|
| 387 |
+
"learning_rate": 0.00029925599999999997,
|
| 388 |
+
"loss": 1.8992,
|
| 389 |
+
"step": 250
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.97,
|
| 393 |
+
"eval_accuracy": 0.6353137321715426,
|
| 394 |
+
"eval_loss": 1.846245288848877,
|
| 395 |
+
"eval_runtime": 60.4965,
|
| 396 |
+
"eval_samples_per_second": 165.299,
|
| 397 |
+
"eval_steps_per_second": 10.331,
|
| 398 |
+
"step": 250
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.99,
|
| 402 |
+
"learning_rate": 0.00029924099999999995,
|
| 403 |
+
"loss": 1.8759,
|
| 404 |
+
"step": 255
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.01,
|
| 408 |
+
"learning_rate": 0.000299226,
|
| 409 |
+
"loss": 2.0852,
|
| 410 |
+
"step": 260
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.03,
|
| 414 |
+
"learning_rate": 0.00029921099999999996,
|
| 415 |
+
"loss": 1.8663,
|
| 416 |
+
"step": 265
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.05,
|
| 420 |
+
"learning_rate": 0.00029919599999999995,
|
| 421 |
+
"loss": 1.8555,
|
| 422 |
+
"step": 270
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.07,
|
| 426 |
+
"learning_rate": 0.000299181,
|
| 427 |
+
"loss": 1.8717,
|
| 428 |
+
"step": 275
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.07,
|
| 432 |
+
"eval_accuracy": 0.6298189252336449,
|
| 433 |
+
"eval_loss": 1.8705145120620728,
|
| 434 |
+
"eval_runtime": 60.3399,
|
| 435 |
+
"eval_samples_per_second": 165.728,
|
| 436 |
+
"eval_steps_per_second": 10.358,
|
| 437 |
+
"step": 275
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.09,
|
| 441 |
+
"learning_rate": 0.00029916599999999996,
|
| 442 |
+
"loss": 1.9226,
|
| 443 |
+
"step": 280
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.1,
|
| 447 |
+
"learning_rate": 0.000299151,
|
| 448 |
+
"loss": 2.0094,
|
| 449 |
+
"step": 285
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.12,
|
| 453 |
+
"learning_rate": 0.000299136,
|
| 454 |
+
"loss": 1.9307,
|
| 455 |
+
"step": 290
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.14,
|
| 459 |
+
"learning_rate": 0.00029912099999999996,
|
| 460 |
+
"loss": 1.9055,
|
| 461 |
+
"step": 295
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.16,
|
| 465 |
+
"learning_rate": 0.000299106,
|
| 466 |
+
"loss": 1.9057,
|
| 467 |
+
"step": 300
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.16,
|
| 471 |
+
"eval_accuracy": 0.6247444509345794,
|
| 472 |
+
"eval_loss": 1.913194179534912,
|
| 473 |
+
"eval_runtime": 60.3218,
|
| 474 |
+
"eval_samples_per_second": 165.778,
|
| 475 |
+
"eval_steps_per_second": 10.361,
|
| 476 |
+
"step": 300
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.18,
|
| 480 |
+
"learning_rate": 0.00029909099999999997,
|
| 481 |
+
"loss": 1.8821,
|
| 482 |
+
"step": 305
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.2,
|
| 486 |
+
"learning_rate": 0.000299076,
|
| 487 |
+
"loss": 1.8635,
|
| 488 |
+
"step": 310
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.22,
|
| 492 |
+
"learning_rate": 0.000299061,
|
| 493 |
+
"loss": 1.8655,
|
| 494 |
+
"step": 315
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.24,
|
| 498 |
+
"learning_rate": 0.00029904599999999997,
|
| 499 |
+
"loss": 1.8642,
|
| 500 |
+
"step": 320
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.26,
|
| 504 |
+
"learning_rate": 0.000299031,
|
| 505 |
+
"loss": 1.8637,
|
| 506 |
+
"step": 325
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.26,
|
| 510 |
+
"eval_accuracy": 0.6270322235202492,
|
| 511 |
+
"eval_loss": 1.900992751121521,
|
| 512 |
+
"eval_runtime": 60.2836,
|
| 513 |
+
"eval_samples_per_second": 165.883,
|
| 514 |
+
"eval_steps_per_second": 10.368,
|
| 515 |
+
"step": 325
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.28,
|
| 519 |
+
"learning_rate": 0.000299016,
|
| 520 |
+
"loss": 1.9827,
|
| 521 |
+
"step": 330
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.3,
|
| 525 |
+
"learning_rate": 0.00029900099999999997,
|
| 526 |
+
"loss": 1.95,
|
| 527 |
+
"step": 335
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.32,
|
| 531 |
+
"learning_rate": 0.00029898599999999995,
|
| 532 |
+
"loss": 1.9358,
|
| 533 |
+
"step": 340
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.34,
|
| 537 |
+
"learning_rate": 0.000298971,
|
| 538 |
+
"loss": 1.9403,
|
| 539 |
+
"step": 345
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.36,
|
| 543 |
+
"learning_rate": 0.00029895599999999996,
|
| 544 |
+
"loss": 1.947,
|
| 545 |
+
"step": 350
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.36,
|
| 549 |
+
"eval_accuracy": 0.6236979166666666,
|
| 550 |
+
"eval_loss": 1.903308629989624,
|
| 551 |
+
"eval_runtime": 60.3153,
|
| 552 |
+
"eval_samples_per_second": 165.796,
|
| 553 |
+
"eval_steps_per_second": 10.362,
|
| 554 |
+
"step": 350
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.36,
|
| 558 |
+
"step": 350,
|
| 559 |
+
"total_flos": 1.899141968469924e+17,
|
| 560 |
+
"train_loss": 1.8697899763924735,
|
| 561 |
+
"train_runtime": 46126.5574,
|
| 562 |
+
"train_samples_per_second": 17343.588,
|
| 563 |
+
"train_steps_per_second": 2.168
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.36,
|
| 567 |
+
"eval_accuracy": 0.6470223174085522,
|
| 568 |
+
"eval_loss": 1.767507791519165,
|
| 569 |
+
"eval_runtime": 60.4981,
|
| 570 |
+
"eval_samples_per_second": 165.295,
|
| 571 |
+
"eval_steps_per_second": 10.331,
|
| 572 |
+
"step": 350
|
| 573 |
+
}
|
| 574 |
+
],
|
| 575 |
+
"max_steps": 100000,
|
| 576 |
+
"num_train_epochs": 388,
|
| 577 |
+
"total_flos": 1.899141968469924e+17,
|
| 578 |
+
"trial_name": null,
|
| 579 |
+
"trial_params": null
|
| 580 |
+
}
|