End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- runs/Aug03_12-07-59_5f3a3d0f848f/events.out.tfevents.1659530533.5f3a3d0f848f.384.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +115 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.39690118338084135,
|
| 4 |
+
"eval_loss": 3.037240505218506,
|
| 5 |
+
"eval_runtime": 31.7078,
|
| 6 |
+
"eval_samples": 1816,
|
| 7 |
+
"eval_samples_per_second": 57.273,
|
| 8 |
+
"eval_steps_per_second": 14.318,
|
| 9 |
+
"perplexity": 20.84763484705914,
|
| 10 |
+
"train_loss": 3.0642820732502996,
|
| 11 |
+
"train_runtime": 1709.0811,
|
| 12 |
+
"train_samples": 10112,
|
| 13 |
+
"train_samples_per_second": 17.75,
|
| 14 |
+
"train_steps_per_second": 4.437
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.39690118338084135,
|
| 4 |
+
"eval_loss": 3.037240505218506,
|
| 5 |
+
"eval_runtime": 31.7078,
|
| 6 |
+
"eval_samples": 1816,
|
| 7 |
+
"eval_samples_per_second": 57.273,
|
| 8 |
+
"eval_steps_per_second": 14.318,
|
| 9 |
+
"perplexity": 20.84763484705914
|
| 10 |
+
}
|
runs/Aug03_12-07-59_5f3a3d0f848f/events.out.tfevents.1659530533.5f3a3d0f848f.384.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4053d99e1b6776a65b620431a5216a9b7297a10f4738389f6a11a2965729af3d
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 3.0642820732502996,
|
| 4 |
+
"train_runtime": 1709.0811,
|
| 5 |
+
"train_samples": 10112,
|
| 6 |
+
"train_samples_per_second": 17.75,
|
| 7 |
+
"train_steps_per_second": 4.437
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 7584,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.2,
|
| 12 |
+
"learning_rate": 4.6703586497890296e-05,
|
| 13 |
+
"loss": 3.3817,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.4,
|
| 18 |
+
"learning_rate": 4.340717299578059e-05,
|
| 19 |
+
"loss": 3.2354,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.59,
|
| 24 |
+
"learning_rate": 4.011075949367088e-05,
|
| 25 |
+
"loss": 3.1946,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.79,
|
| 30 |
+
"learning_rate": 3.6814345991561184e-05,
|
| 31 |
+
"loss": 3.1541,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.99,
|
| 36 |
+
"learning_rate": 3.351793248945148e-05,
|
| 37 |
+
"loss": 3.1354,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.19,
|
| 42 |
+
"learning_rate": 3.0221518987341774e-05,
|
| 43 |
+
"loss": 3.0363,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.38,
|
| 48 |
+
"learning_rate": 2.6925105485232068e-05,
|
| 49 |
+
"loss": 3.0444,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.58,
|
| 54 |
+
"learning_rate": 2.3628691983122365e-05,
|
| 55 |
+
"loss": 3.0292,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.78,
|
| 60 |
+
"learning_rate": 2.033227848101266e-05,
|
| 61 |
+
"loss": 3.0086,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.98,
|
| 66 |
+
"learning_rate": 1.7035864978902955e-05,
|
| 67 |
+
"loss": 2.9992,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.18,
|
| 72 |
+
"learning_rate": 1.3739451476793249e-05,
|
| 73 |
+
"loss": 2.9701,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.37,
|
| 78 |
+
"learning_rate": 1.0443037974683544e-05,
|
| 79 |
+
"loss": 2.9505,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.57,
|
| 84 |
+
"learning_rate": 7.14662447257384e-06,
|
| 85 |
+
"loss": 2.9507,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.77,
|
| 90 |
+
"learning_rate": 3.850210970464136e-06,
|
| 91 |
+
"loss": 2.9395,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.97,
|
| 96 |
+
"learning_rate": 5.537974683544304e-07,
|
| 97 |
+
"loss": 2.9615,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.0,
|
| 102 |
+
"step": 7584,
|
| 103 |
+
"total_flos": 1981674556489728.0,
|
| 104 |
+
"train_loss": 3.0642820732502996,
|
| 105 |
+
"train_runtime": 1709.0811,
|
| 106 |
+
"train_samples_per_second": 17.75,
|
| 107 |
+
"train_steps_per_second": 4.437
|
| 108 |
+
}
|
| 109 |
+
],
|
| 110 |
+
"max_steps": 7584,
|
| 111 |
+
"num_train_epochs": 3,
|
| 112 |
+
"total_flos": 1981674556489728.0,
|
| 113 |
+
"trial_name": null,
|
| 114 |
+
"trial_params": null
|
| 115 |
+
}
|