Commit
•
2545755
1
Parent(s):
632bf29
End of training
Browse files- all_results.json +11 -0
- eval_results.json +6 -0
- runs/Oct08_15-24-49_g3076/events.out.tfevents.1665278298.g3076.79686.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +127 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_exact_match": 76.80227057710502,
|
| 4 |
+
"eval_f1": 86.23125164566527,
|
| 5 |
+
"eval_samples": 10570,
|
| 6 |
+
"train_loss": 0.73073171547481,
|
| 7 |
+
"train_runtime": 9923.8172,
|
| 8 |
+
"train_samples": 1024,
|
| 9 |
+
"train_samples_per_second": 3.612,
|
| 10 |
+
"train_steps_per_second": 0.903
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_exact_match": 76.80227057710502,
|
| 4 |
+
"eval_f1": 86.23125164566527,
|
| 5 |
+
"eval_samples": 10570
|
| 6 |
+
}
|
runs/Oct08_15-24-49_g3076/events.out.tfevents.1665278298.g3076.79686.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1042670e8365ebf8727d8510e4acbd8f5f06ee28660e8f9527d8458c313750cb
|
| 3 |
+
size 191
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"train_loss": 0.73073171547481,
|
| 4 |
+
"train_runtime": 9923.8172,
|
| 5 |
+
"train_samples": 1024,
|
| 6 |
+
"train_samples_per_second": 3.612,
|
| 7 |
+
"train_steps_per_second": 0.903
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 35.0,
|
| 5 |
+
"global_step": 8960,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.95,
|
| 12 |
+
"learning_rate": 1.8883928571428573e-05,
|
| 13 |
+
"loss": 3.8837,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 3.91,
|
| 18 |
+
"learning_rate": 1.7767857142857143e-05,
|
| 19 |
+
"loss": 1.5477,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 5.86,
|
| 24 |
+
"learning_rate": 1.6651785714285714e-05,
|
| 25 |
+
"loss": 1.0661,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 7.81,
|
| 30 |
+
"learning_rate": 1.553571428571429e-05,
|
| 31 |
+
"loss": 0.8451,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 9.77,
|
| 36 |
+
"learning_rate": 1.441964285714286e-05,
|
| 37 |
+
"loss": 0.6782,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 11.72,
|
| 42 |
+
"learning_rate": 1.3303571428571429e-05,
|
| 43 |
+
"loss": 0.612,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 13.67,
|
| 48 |
+
"learning_rate": 1.2187500000000001e-05,
|
| 49 |
+
"loss": 0.5626,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 15.62,
|
| 54 |
+
"learning_rate": 1.1071428571428572e-05,
|
| 55 |
+
"loss": 0.528,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 17.58,
|
| 60 |
+
"learning_rate": 9.955357142857143e-06,
|
| 61 |
+
"loss": 0.4551,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 19.53,
|
| 66 |
+
"learning_rate": 8.839285714285714e-06,
|
| 67 |
+
"loss": 0.4146,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 21.48,
|
| 72 |
+
"learning_rate": 7.723214285714287e-06,
|
| 73 |
+
"loss": 0.3509,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 23.44,
|
| 78 |
+
"learning_rate": 6.607142857142858e-06,
|
| 79 |
+
"loss": 0.3772,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 25.39,
|
| 84 |
+
"learning_rate": 5.4910714285714295e-06,
|
| 85 |
+
"loss": 0.3423,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 27.34,
|
| 90 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 91 |
+
"loss": 0.3111,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 29.3,
|
| 96 |
+
"learning_rate": 3.258928571428572e-06,
|
| 97 |
+
"loss": 0.2952,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 31.25,
|
| 102 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 103 |
+
"loss": 0.2921,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 33.2,
|
| 108 |
+
"learning_rate": 1.0267857142857143e-06,
|
| 109 |
+
"loss": 0.2882,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 35.0,
|
| 114 |
+
"step": 8960,
|
| 115 |
+
"total_flos": 1.328845115418624e+16,
|
| 116 |
+
"train_loss": 0.73073171547481,
|
| 117 |
+
"train_runtime": 9923.8172,
|
| 118 |
+
"train_samples_per_second": 3.612,
|
| 119 |
+
"train_steps_per_second": 0.903
|
| 120 |
+
}
|
| 121 |
+
],
|
| 122 |
+
"max_steps": 8960,
|
| 123 |
+
"num_train_epochs": 35,
|
| 124 |
+
"total_flos": 1.328845115418624e+16,
|
| 125 |
+
"trial_name": null,
|
| 126 |
+
"trial_params": null
|
| 127 |
+
}
|