Commit
•
de29d9d
1
Parent(s):
49c19b3
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +130 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.046216869705728e+19,
|
| 4 |
+
"train_loss": 0.3684066082989728,
|
| 5 |
+
"train_runtime": 5023.6729,
|
| 6 |
+
"train_samples_per_second": 26.873,
|
| 7 |
+
"train_steps_per_second": 1.344
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.046216869705728e+19,
|
| 4 |
+
"train_loss": 0.3684066082989728,
|
| 5 |
+
"train_runtime": 5023.6729,
|
| 6 |
+
"train_samples_per_second": 26.873,
|
| 7 |
+
"train_steps_per_second": 1.344
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.99,
|
| 3 |
+
"best_model_checkpoint": "tknnguyen.2022_AML_A2_Q4/checkpoint-6750",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 6750,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.22,
|
| 12 |
+
"learning_rate": 1.851851851851852e-05,
|
| 13 |
+
"loss": 1.2124,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.44,
|
| 18 |
+
"learning_rate": 1.7037037037037038e-05,
|
| 19 |
+
"loss": 0.5279,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.67,
|
| 24 |
+
"learning_rate": 1.555555555555556e-05,
|
| 25 |
+
"loss": 0.4215,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.89,
|
| 30 |
+
"learning_rate": 1.4074074074074075e-05,
|
| 31 |
+
"loss": 0.3597,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"eval_accuracy": 0.9822,
|
| 37 |
+
"eval_loss": 0.12298029661178589,
|
| 38 |
+
"eval_runtime": 68.6299,
|
| 39 |
+
"eval_samples_per_second": 72.855,
|
| 40 |
+
"eval_steps_per_second": 18.214,
|
| 41 |
+
"step": 2250
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.11,
|
| 45 |
+
"learning_rate": 1.2592592592592593e-05,
|
| 46 |
+
"loss": 0.3305,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.33,
|
| 51 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 52 |
+
"loss": 0.3042,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.56,
|
| 57 |
+
"learning_rate": 9.62962962962963e-06,
|
| 58 |
+
"loss": 0.2858,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.78,
|
| 63 |
+
"learning_rate": 8.148148148148148e-06,
|
| 64 |
+
"loss": 0.2576,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.0,
|
| 69 |
+
"learning_rate": 6.666666666666667e-06,
|
| 70 |
+
"loss": 0.2548,
|
| 71 |
+
"step": 4500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.0,
|
| 75 |
+
"eval_accuracy": 0.9854,
|
| 76 |
+
"eval_loss": 0.07198980450630188,
|
| 77 |
+
"eval_runtime": 68.7186,
|
| 78 |
+
"eval_samples_per_second": 72.76,
|
| 79 |
+
"eval_steps_per_second": 18.19,
|
| 80 |
+
"step": 4500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.22,
|
| 84 |
+
"learning_rate": 5.185185185185185e-06,
|
| 85 |
+
"loss": 0.2411,
|
| 86 |
+
"step": 5000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.44,
|
| 90 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 91 |
+
"loss": 0.2268,
|
| 92 |
+
"step": 5500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.67,
|
| 96 |
+
"learning_rate": 2.222222222222222e-06,
|
| 97 |
+
"loss": 0.2267,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.89,
|
| 102 |
+
"learning_rate": 7.407407407407407e-07,
|
| 103 |
+
"loss": 0.2234,
|
| 104 |
+
"step": 6500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.0,
|
| 108 |
+
"eval_accuracy": 0.99,
|
| 109 |
+
"eval_loss": 0.05685313791036606,
|
| 110 |
+
"eval_runtime": 68.3871,
|
| 111 |
+
"eval_samples_per_second": 73.113,
|
| 112 |
+
"eval_steps_per_second": 18.278,
|
| 113 |
+
"step": 6750
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.0,
|
| 117 |
+
"step": 6750,
|
| 118 |
+
"total_flos": 1.046216869705728e+19,
|
| 119 |
+
"train_loss": 0.3684066082989728,
|
| 120 |
+
"train_runtime": 5023.6729,
|
| 121 |
+
"train_samples_per_second": 26.873,
|
| 122 |
+
"train_steps_per_second": 1.344
|
| 123 |
+
}
|
| 124 |
+
],
|
| 125 |
+
"max_steps": 6750,
|
| 126 |
+
"num_train_epochs": 3,
|
| 127 |
+
"total_flos": 1.046216869705728e+19,
|
| 128 |
+
"trial_name": null,
|
| 129 |
+
"trial_params": null
|
| 130 |
+
}
|