Commit
•
7eab8d9
1
Parent(s):
865fded
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +133 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.10405463833386691,
|
| 4 |
+
"train_runtime": 977.5682,
|
| 5 |
+
"train_samples": 100821,
|
| 6 |
+
"train_samples_per_second": 309.403,
|
| 7 |
+
"train_steps_per_second": 9.67
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.10405463833386691,
|
| 4 |
+
"train_runtime": 977.5682,
|
| 5 |
+
"train_samples": 100821,
|
| 6 |
+
"train_samples_per_second": 309.403,
|
| 7 |
+
"train_steps_per_second": 9.67
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 9453,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 1.8952713424309745e-05,
|
| 13 |
+
"loss": 0.4879,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.32,
|
| 18 |
+
"learning_rate": 1.7894848196339786e-05,
|
| 19 |
+
"loss": 0.2154,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.48,
|
| 24 |
+
"learning_rate": 1.683698296836983e-05,
|
| 25 |
+
"loss": 0.1571,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.63,
|
| 30 |
+
"learning_rate": 1.5779117740399874e-05,
|
| 31 |
+
"loss": 0.1299,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.79,
|
| 36 |
+
"learning_rate": 1.4721252512429918e-05,
|
| 37 |
+
"loss": 0.1046,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.95,
|
| 42 |
+
"learning_rate": 1.3665503014915903e-05,
|
| 43 |
+
"loss": 0.0914,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.11,
|
| 48 |
+
"learning_rate": 1.2607637786945943e-05,
|
| 49 |
+
"loss": 0.0796,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.27,
|
| 54 |
+
"learning_rate": 1.1549772558975987e-05,
|
| 55 |
+
"loss": 0.0793,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.43,
|
| 60 |
+
"learning_rate": 1.049190733100603e-05,
|
| 61 |
+
"loss": 0.0767,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.59,
|
| 66 |
+
"learning_rate": 9.436157833492013e-06,
|
| 67 |
+
"loss": 0.0675,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.75,
|
| 72 |
+
"learning_rate": 8.378292605522057e-06,
|
| 73 |
+
"loss": 0.0679,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.9,
|
| 78 |
+
"learning_rate": 7.3204273775521e-06,
|
| 79 |
+
"loss": 0.0626,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.06,
|
| 84 |
+
"learning_rate": 6.264677880038084e-06,
|
| 85 |
+
"loss": 0.0603,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.22,
|
| 90 |
+
"learning_rate": 5.206812652068127e-06,
|
| 91 |
+
"loss": 0.0521,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.38,
|
| 96 |
+
"learning_rate": 4.1489474240981706e-06,
|
| 97 |
+
"loss": 0.052,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.54,
|
| 102 |
+
"learning_rate": 3.0910821961282134e-06,
|
| 103 |
+
"loss": 0.0491,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.7,
|
| 108 |
+
"learning_rate": 2.0332169681582567e-06,
|
| 109 |
+
"loss": 0.0464,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.86,
|
| 114 |
+
"learning_rate": 9.753517401883e-07,
|
| 115 |
+
"loss": 0.0491,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"step": 9453,
|
| 121 |
+
"total_flos": 1.989533978433792e+16,
|
| 122 |
+
"train_loss": 0.10405463833386691,
|
| 123 |
+
"train_runtime": 977.5682,
|
| 124 |
+
"train_samples_per_second": 309.403,
|
| 125 |
+
"train_steps_per_second": 9.67
|
| 126 |
+
}
|
| 127 |
+
],
|
| 128 |
+
"max_steps": 9453,
|
| 129 |
+
"num_train_epochs": 3,
|
| 130 |
+
"total_flos": 1.989533978433792e+16,
|
| 131 |
+
"trial_name": null,
|
| 132 |
+
"trial_params": null
|
| 133 |
+
}
|