Commit
•
3a0dc97
1
Parent(s):
e184710
End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +699 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.135531135531136,
|
| 3 |
+
"eval_accuracy": 0.5756097560975609,
|
| 4 |
+
"eval_loss": 1.497787356376648,
|
| 5 |
+
"eval_runtime": 33.1995,
|
| 6 |
+
"eval_samples_per_second": 6.175,
|
| 7 |
+
"eval_steps_per_second": 0.783
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.135531135531136,
|
| 3 |
+
"eval_accuracy": 0.5756097560975609,
|
| 4 |
+
"eval_loss": 1.497787356376648,
|
| 5 |
+
"eval_runtime": 33.1995,
|
| 6 |
+
"eval_samples_per_second": 6.175,
|
| 7 |
+
"eval_steps_per_second": 0.783
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,699 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6019417475728155,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-conflab-traj-direction-rh-v10/checkpoint-819",
|
| 4 |
+
"epoch": 6.135531135531136,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 819,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01221001221001221,
|
| 13 |
+
"grad_norm": 8.122791290283203,
|
| 14 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 15 |
+
"loss": 2.1095,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02442002442002442,
|
| 20 |
+
"grad_norm": 6.661695957183838,
|
| 21 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 22 |
+
"loss": 2.0298,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03663003663003663,
|
| 27 |
+
"grad_norm": 7.086618900299072,
|
| 28 |
+
"learning_rate": 1.8292682926829268e-05,
|
| 29 |
+
"loss": 2.0189,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04884004884004884,
|
| 34 |
+
"grad_norm": 8.178045272827148,
|
| 35 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 36 |
+
"loss": 2.0099,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06105006105006105,
|
| 41 |
+
"grad_norm": 7.585304260253906,
|
| 42 |
+
"learning_rate": 3.048780487804878e-05,
|
| 43 |
+
"loss": 1.9196,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07326007326007326,
|
| 48 |
+
"grad_norm": 7.4838409423828125,
|
| 49 |
+
"learning_rate": 3.6585365853658535e-05,
|
| 50 |
+
"loss": 1.9165,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08547008547008547,
|
| 55 |
+
"grad_norm": 6.174314498901367,
|
| 56 |
+
"learning_rate": 4.26829268292683e-05,
|
| 57 |
+
"loss": 1.8358,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09768009768009768,
|
| 62 |
+
"grad_norm": 5.699541091918945,
|
| 63 |
+
"learning_rate": 4.878048780487805e-05,
|
| 64 |
+
"loss": 1.8794,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10989010989010989,
|
| 69 |
+
"grad_norm": 6.571558475494385,
|
| 70 |
+
"learning_rate": 4.94572591587517e-05,
|
| 71 |
+
"loss": 1.8931,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1221001221001221,
|
| 76 |
+
"grad_norm": 7.583756446838379,
|
| 77 |
+
"learning_rate": 4.877883310719132e-05,
|
| 78 |
+
"loss": 1.8477,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1343101343101343,
|
| 83 |
+
"grad_norm": 6.113456726074219,
|
| 84 |
+
"learning_rate": 4.810040705563094e-05,
|
| 85 |
+
"loss": 1.989,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14407814407814407,
|
| 90 |
+
"eval_accuracy": 0.2669902912621359,
|
| 91 |
+
"eval_loss": 1.8786594867706299,
|
| 92 |
+
"eval_runtime": 28.8858,
|
| 93 |
+
"eval_samples_per_second": 7.132,
|
| 94 |
+
"eval_steps_per_second": 0.9,
|
| 95 |
+
"step": 118
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.0024420024420024,
|
| 99 |
+
"grad_norm": 6.775885105133057,
|
| 100 |
+
"learning_rate": 4.742198100407056e-05,
|
| 101 |
+
"loss": 1.7872,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.0146520146520146,
|
| 106 |
+
"grad_norm": 5.531322956085205,
|
| 107 |
+
"learning_rate": 4.674355495251018e-05,
|
| 108 |
+
"loss": 1.8331,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.0268620268620268,
|
| 113 |
+
"grad_norm": 7.1956353187561035,
|
| 114 |
+
"learning_rate": 4.60651289009498e-05,
|
| 115 |
+
"loss": 1.7703,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0390720390720392,
|
| 120 |
+
"grad_norm": 8.779479026794434,
|
| 121 |
+
"learning_rate": 4.5386702849389416e-05,
|
| 122 |
+
"loss": 1.6198,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0512820512820513,
|
| 127 |
+
"grad_norm": 10.621439933776855,
|
| 128 |
+
"learning_rate": 4.470827679782904e-05,
|
| 129 |
+
"loss": 1.6431,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0634920634920635,
|
| 134 |
+
"grad_norm": 7.896602630615234,
|
| 135 |
+
"learning_rate": 4.402985074626866e-05,
|
| 136 |
+
"loss": 1.6686,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0757020757020757,
|
| 141 |
+
"grad_norm": 6.063083171844482,
|
| 142 |
+
"learning_rate": 4.335142469470828e-05,
|
| 143 |
+
"loss": 1.4762,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.0879120879120878,
|
| 148 |
+
"grad_norm": 10.578692436218262,
|
| 149 |
+
"learning_rate": 4.26729986431479e-05,
|
| 150 |
+
"loss": 1.6948,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.1001221001221002,
|
| 155 |
+
"grad_norm": 8.612629890441895,
|
| 156 |
+
"learning_rate": 4.199457259158752e-05,
|
| 157 |
+
"loss": 1.5687,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.1123321123321124,
|
| 162 |
+
"grad_norm": 8.634360313415527,
|
| 163 |
+
"learning_rate": 4.131614654002714e-05,
|
| 164 |
+
"loss": 1.4138,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.1245421245421245,
|
| 169 |
+
"grad_norm": 8.842486381530762,
|
| 170 |
+
"learning_rate": 4.063772048846676e-05,
|
| 171 |
+
"loss": 1.4202,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.1367521367521367,
|
| 176 |
+
"grad_norm": 8.472060203552246,
|
| 177 |
+
"learning_rate": 3.995929443690638e-05,
|
| 178 |
+
"loss": 1.3092,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.144078144078144,
|
| 183 |
+
"eval_accuracy": 0.42718446601941745,
|
| 184 |
+
"eval_loss": 1.6427617073059082,
|
| 185 |
+
"eval_runtime": 21.3576,
|
| 186 |
+
"eval_samples_per_second": 9.645,
|
| 187 |
+
"eval_steps_per_second": 1.217,
|
| 188 |
+
"step": 236
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.004884004884005,
|
| 192 |
+
"grad_norm": 9.463373184204102,
|
| 193 |
+
"learning_rate": 3.9280868385345995e-05,
|
| 194 |
+
"loss": 1.5065,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.017094017094017,
|
| 199 |
+
"grad_norm": 8.447351455688477,
|
| 200 |
+
"learning_rate": 3.860244233378562e-05,
|
| 201 |
+
"loss": 1.3116,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.029304029304029,
|
| 206 |
+
"grad_norm": 9.61158561706543,
|
| 207 |
+
"learning_rate": 3.792401628222524e-05,
|
| 208 |
+
"loss": 1.0903,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.0415140415140414,
|
| 213 |
+
"grad_norm": 10.502912521362305,
|
| 214 |
+
"learning_rate": 3.724559023066486e-05,
|
| 215 |
+
"loss": 1.1713,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.0537240537240535,
|
| 220 |
+
"grad_norm": 11.798907279968262,
|
| 221 |
+
"learning_rate": 3.656716417910448e-05,
|
| 222 |
+
"loss": 1.1561,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.065934065934066,
|
| 227 |
+
"grad_norm": 16.395263671875,
|
| 228 |
+
"learning_rate": 3.58887381275441e-05,
|
| 229 |
+
"loss": 1.2809,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.0781440781440783,
|
| 234 |
+
"grad_norm": 11.183971405029297,
|
| 235 |
+
"learning_rate": 3.521031207598372e-05,
|
| 236 |
+
"loss": 1.1276,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.0903540903540905,
|
| 241 |
+
"grad_norm": 10.743521690368652,
|
| 242 |
+
"learning_rate": 3.453188602442334e-05,
|
| 243 |
+
"loss": 1.3756,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.1025641025641026,
|
| 248 |
+
"grad_norm": 8.513188362121582,
|
| 249 |
+
"learning_rate": 3.385345997286296e-05,
|
| 250 |
+
"loss": 0.9218,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.114774114774115,
|
| 255 |
+
"grad_norm": 12.773633003234863,
|
| 256 |
+
"learning_rate": 3.3175033921302575e-05,
|
| 257 |
+
"loss": 1.2335,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.126984126984127,
|
| 262 |
+
"grad_norm": 11.963506698608398,
|
| 263 |
+
"learning_rate": 3.24966078697422e-05,
|
| 264 |
+
"loss": 1.1391,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.139194139194139,
|
| 269 |
+
"grad_norm": 10.355384826660156,
|
| 270 |
+
"learning_rate": 3.181818181818182e-05,
|
| 271 |
+
"loss": 1.0096,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.144078144078144,
|
| 276 |
+
"eval_accuracy": 0.47572815533980584,
|
| 277 |
+
"eval_loss": 1.4351158142089844,
|
| 278 |
+
"eval_runtime": 27.857,
|
| 279 |
+
"eval_samples_per_second": 7.395,
|
| 280 |
+
"eval_steps_per_second": 0.933,
|
| 281 |
+
"step": 354
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.0073260073260073,
|
| 285 |
+
"grad_norm": 10.925836563110352,
|
| 286 |
+
"learning_rate": 3.113975576662144e-05,
|
| 287 |
+
"loss": 0.9783,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.0195360195360195,
|
| 292 |
+
"grad_norm": 6.559803009033203,
|
| 293 |
+
"learning_rate": 3.046132971506106e-05,
|
| 294 |
+
"loss": 0.8608,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.0317460317460316,
|
| 299 |
+
"grad_norm": 10.63405990600586,
|
| 300 |
+
"learning_rate": 2.9782903663500678e-05,
|
| 301 |
+
"loss": 0.7684,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.043956043956044,
|
| 306 |
+
"grad_norm": 11.322102546691895,
|
| 307 |
+
"learning_rate": 2.91044776119403e-05,
|
| 308 |
+
"loss": 0.8308,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.056166056166056,
|
| 313 |
+
"grad_norm": 5.719593524932861,
|
| 314 |
+
"learning_rate": 2.842605156037992e-05,
|
| 315 |
+
"loss": 0.7868,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.0683760683760686,
|
| 320 |
+
"grad_norm": 13.967921257019043,
|
| 321 |
+
"learning_rate": 2.7747625508819542e-05,
|
| 322 |
+
"loss": 0.7707,
|
| 323 |
+
"step": 410
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.0805860805860807,
|
| 327 |
+
"grad_norm": 9.134116172790527,
|
| 328 |
+
"learning_rate": 2.7069199457259158e-05,
|
| 329 |
+
"loss": 0.5804,
|
| 330 |
+
"step": 420
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.092796092796093,
|
| 334 |
+
"grad_norm": 14.580177307128906,
|
| 335 |
+
"learning_rate": 2.639077340569878e-05,
|
| 336 |
+
"loss": 0.7846,
|
| 337 |
+
"step": 430
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.105006105006105,
|
| 341 |
+
"grad_norm": 12.265727043151855,
|
| 342 |
+
"learning_rate": 2.57123473541384e-05,
|
| 343 |
+
"loss": 0.6807,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.1172161172161172,
|
| 348 |
+
"grad_norm": 15.816527366638184,
|
| 349 |
+
"learning_rate": 2.5033921302578023e-05,
|
| 350 |
+
"loss": 0.6878,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.1294261294261294,
|
| 355 |
+
"grad_norm": 9.39810848236084,
|
| 356 |
+
"learning_rate": 2.4355495251017642e-05,
|
| 357 |
+
"loss": 0.5625,
|
| 358 |
+
"step": 460
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.1416361416361416,
|
| 362 |
+
"grad_norm": 7.950680732727051,
|
| 363 |
+
"learning_rate": 2.367706919945726e-05,
|
| 364 |
+
"loss": 0.604,
|
| 365 |
+
"step": 470
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.144078144078144,
|
| 369 |
+
"eval_accuracy": 0.5,
|
| 370 |
+
"eval_loss": 1.3919281959533691,
|
| 371 |
+
"eval_runtime": 21.6391,
|
| 372 |
+
"eval_samples_per_second": 9.52,
|
| 373 |
+
"eval_steps_per_second": 1.202,
|
| 374 |
+
"step": 472
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.00976800976801,
|
| 378 |
+
"grad_norm": 3.859422206878662,
|
| 379 |
+
"learning_rate": 2.299864314789688e-05,
|
| 380 |
+
"loss": 0.3818,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.021978021978022,
|
| 385 |
+
"grad_norm": 4.586574077606201,
|
| 386 |
+
"learning_rate": 2.2320217096336503e-05,
|
| 387 |
+
"loss": 0.3743,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.034188034188034,
|
| 392 |
+
"grad_norm": 11.923030853271484,
|
| 393 |
+
"learning_rate": 2.164179104477612e-05,
|
| 394 |
+
"loss": 0.4857,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.046398046398046,
|
| 399 |
+
"grad_norm": 8.866025924682617,
|
| 400 |
+
"learning_rate": 2.0963364993215738e-05,
|
| 401 |
+
"loss": 0.5601,
|
| 402 |
+
"step": 510
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.058608058608058,
|
| 406 |
+
"grad_norm": 8.028688430786133,
|
| 407 |
+
"learning_rate": 2.028493894165536e-05,
|
| 408 |
+
"loss": 0.4649,
|
| 409 |
+
"step": 520
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.070818070818071,
|
| 413 |
+
"grad_norm": 8.852441787719727,
|
| 414 |
+
"learning_rate": 1.960651289009498e-05,
|
| 415 |
+
"loss": 0.3592,
|
| 416 |
+
"step": 530
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.083028083028083,
|
| 420 |
+
"grad_norm": 22.12917137145996,
|
| 421 |
+
"learning_rate": 1.89280868385346e-05,
|
| 422 |
+
"loss": 0.4787,
|
| 423 |
+
"step": 540
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.095238095238095,
|
| 427 |
+
"grad_norm": 9.262681007385254,
|
| 428 |
+
"learning_rate": 1.824966078697422e-05,
|
| 429 |
+
"loss": 0.4364,
|
| 430 |
+
"step": 550
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 4.107448107448107,
|
| 434 |
+
"grad_norm": 5.102321624755859,
|
| 435 |
+
"learning_rate": 1.757123473541384e-05,
|
| 436 |
+
"loss": 0.3868,
|
| 437 |
+
"step": 560
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.119658119658119,
|
| 441 |
+
"grad_norm": 13.144558906555176,
|
| 442 |
+
"learning_rate": 1.689280868385346e-05,
|
| 443 |
+
"loss": 0.4023,
|
| 444 |
+
"step": 570
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.131868131868132,
|
| 448 |
+
"grad_norm": 16.35342788696289,
|
| 449 |
+
"learning_rate": 1.6214382632293083e-05,
|
| 450 |
+
"loss": 0.4355,
|
| 451 |
+
"step": 580
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 4.1440781440781445,
|
| 455 |
+
"grad_norm": 12.760746955871582,
|
| 456 |
+
"learning_rate": 1.55359565807327e-05,
|
| 457 |
+
"loss": 0.2381,
|
| 458 |
+
"step": 590
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.1440781440781445,
|
| 462 |
+
"eval_accuracy": 0.5436893203883495,
|
| 463 |
+
"eval_loss": 1.355545163154602,
|
| 464 |
+
"eval_runtime": 21.2157,
|
| 465 |
+
"eval_samples_per_second": 9.71,
|
| 466 |
+
"eval_steps_per_second": 1.226,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.012210012210012,
|
| 471 |
+
"grad_norm": 7.593497276306152,
|
| 472 |
+
"learning_rate": 1.485753052917232e-05,
|
| 473 |
+
"loss": 0.2075,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.024420024420024,
|
| 478 |
+
"grad_norm": 4.697848320007324,
|
| 479 |
+
"learning_rate": 1.417910447761194e-05,
|
| 480 |
+
"loss": 0.2499,
|
| 481 |
+
"step": 610
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.0366300366300365,
|
| 485 |
+
"grad_norm": 5.646294116973877,
|
| 486 |
+
"learning_rate": 1.3500678426051561e-05,
|
| 487 |
+
"loss": 0.1955,
|
| 488 |
+
"step": 620
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.048840048840049,
|
| 492 |
+
"grad_norm": 1.646572232246399,
|
| 493 |
+
"learning_rate": 1.282225237449118e-05,
|
| 494 |
+
"loss": 0.2132,
|
| 495 |
+
"step": 630
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.061050061050061,
|
| 499 |
+
"grad_norm": 13.153250694274902,
|
| 500 |
+
"learning_rate": 1.2143826322930801e-05,
|
| 501 |
+
"loss": 0.2291,
|
| 502 |
+
"step": 640
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.073260073260073,
|
| 506 |
+
"grad_norm": 3.749263286590576,
|
| 507 |
+
"learning_rate": 1.1465400271370422e-05,
|
| 508 |
+
"loss": 0.2316,
|
| 509 |
+
"step": 650
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.085470085470085,
|
| 513 |
+
"grad_norm": 1.2367647886276245,
|
| 514 |
+
"learning_rate": 1.0786974219810041e-05,
|
| 515 |
+
"loss": 0.1593,
|
| 516 |
+
"step": 660
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 5.097680097680097,
|
| 520 |
+
"grad_norm": 14.28999137878418,
|
| 521 |
+
"learning_rate": 1.010854816824966e-05,
|
| 522 |
+
"loss": 0.1864,
|
| 523 |
+
"step": 670
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 5.1098901098901095,
|
| 527 |
+
"grad_norm": 4.065025329589844,
|
| 528 |
+
"learning_rate": 9.430122116689281e-06,
|
| 529 |
+
"loss": 0.261,
|
| 530 |
+
"step": 680
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 5.122100122100122,
|
| 534 |
+
"grad_norm": 5.471700668334961,
|
| 535 |
+
"learning_rate": 8.751696065128902e-06,
|
| 536 |
+
"loss": 0.1759,
|
| 537 |
+
"step": 690
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 5.134310134310135,
|
| 541 |
+
"grad_norm": 1.2977887392044067,
|
| 542 |
+
"learning_rate": 8.073270013568522e-06,
|
| 543 |
+
"loss": 0.2201,
|
| 544 |
+
"step": 700
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 5.1440781440781445,
|
| 548 |
+
"eval_accuracy": 0.5776699029126213,
|
| 549 |
+
"eval_loss": 1.3875343799591064,
|
| 550 |
+
"eval_runtime": 33.2439,
|
| 551 |
+
"eval_samples_per_second": 6.197,
|
| 552 |
+
"eval_steps_per_second": 0.782,
|
| 553 |
+
"step": 708
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.002442002442002,
|
| 557 |
+
"grad_norm": 5.552870750427246,
|
| 558 |
+
"learning_rate": 7.394843962008141e-06,
|
| 559 |
+
"loss": 0.2692,
|
| 560 |
+
"step": 710
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.014652014652015,
|
| 564 |
+
"grad_norm": 20.285839080810547,
|
| 565 |
+
"learning_rate": 6.716417910447762e-06,
|
| 566 |
+
"loss": 0.1318,
|
| 567 |
+
"step": 720
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.026862026862027,
|
| 571 |
+
"grad_norm": 1.199399471282959,
|
| 572 |
+
"learning_rate": 6.037991858887382e-06,
|
| 573 |
+
"loss": 0.0786,
|
| 574 |
+
"step": 730
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.039072039072039,
|
| 578 |
+
"grad_norm": 0.7117233872413635,
|
| 579 |
+
"learning_rate": 5.359565807327002e-06,
|
| 580 |
+
"loss": 0.0873,
|
| 581 |
+
"step": 740
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.051282051282051,
|
| 585 |
+
"grad_norm": 1.9136446714401245,
|
| 586 |
+
"learning_rate": 4.681139755766622e-06,
|
| 587 |
+
"loss": 0.1112,
|
| 588 |
+
"step": 750
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.063492063492063,
|
| 592 |
+
"grad_norm": 3.076906204223633,
|
| 593 |
+
"learning_rate": 4.002713704206242e-06,
|
| 594 |
+
"loss": 0.1026,
|
| 595 |
+
"step": 760
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 6.075702075702075,
|
| 599 |
+
"grad_norm": 26.244754791259766,
|
| 600 |
+
"learning_rate": 3.324287652645862e-06,
|
| 601 |
+
"loss": 0.1529,
|
| 602 |
+
"step": 770
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.087912087912088,
|
| 606 |
+
"grad_norm": 0.7138678431510925,
|
| 607 |
+
"learning_rate": 2.645861601085482e-06,
|
| 608 |
+
"loss": 0.1352,
|
| 609 |
+
"step": 780
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 6.1001221001221,
|
| 613 |
+
"grad_norm": 10.830814361572266,
|
| 614 |
+
"learning_rate": 1.967435549525102e-06,
|
| 615 |
+
"loss": 0.0969,
|
| 616 |
+
"step": 790
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 6.112332112332112,
|
| 620 |
+
"grad_norm": 5.247445106506348,
|
| 621 |
+
"learning_rate": 1.289009497964722e-06,
|
| 622 |
+
"loss": 0.1702,
|
| 623 |
+
"step": 800
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 6.124542124542124,
|
| 627 |
+
"grad_norm": 1.4733346700668335,
|
| 628 |
+
"learning_rate": 6.10583446404342e-07,
|
| 629 |
+
"loss": 0.1171,
|
| 630 |
+
"step": 810
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 6.135531135531136,
|
| 634 |
+
"eval_accuracy": 0.6019417475728155,
|
| 635 |
+
"eval_loss": 1.3527742624282837,
|
| 636 |
+
"eval_runtime": 23.7516,
|
| 637 |
+
"eval_samples_per_second": 8.673,
|
| 638 |
+
"eval_steps_per_second": 1.095,
|
| 639 |
+
"step": 819
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.135531135531136,
|
| 643 |
+
"step": 819,
|
| 644 |
+
"total_flos": 8.149698472747991e+18,
|
| 645 |
+
"train_loss": 0.8887154050216861,
|
| 646 |
+
"train_runtime": 1543.5432,
|
| 647 |
+
"train_samples_per_second": 4.245,
|
| 648 |
+
"train_steps_per_second": 0.531
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 6.135531135531136,
|
| 652 |
+
"eval_accuracy": 0.5756097560975609,
|
| 653 |
+
"eval_loss": 1.497787594795227,
|
| 654 |
+
"eval_runtime": 33.2888,
|
| 655 |
+
"eval_samples_per_second": 6.158,
|
| 656 |
+
"eval_steps_per_second": 0.781,
|
| 657 |
+
"step": 819
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 6.135531135531136,
|
| 661 |
+
"eval_accuracy": 0.5756097560975609,
|
| 662 |
+
"eval_loss": 1.497787356376648,
|
| 663 |
+
"eval_runtime": 33.1995,
|
| 664 |
+
"eval_samples_per_second": 6.175,
|
| 665 |
+
"eval_steps_per_second": 0.783,
|
| 666 |
+
"step": 819
|
| 667 |
+
}
|
| 668 |
+
],
|
| 669 |
+
"logging_steps": 10,
|
| 670 |
+
"max_steps": 819,
|
| 671 |
+
"num_input_tokens_seen": 0,
|
| 672 |
+
"num_train_epochs": 9223372036854775807,
|
| 673 |
+
"save_steps": 500,
|
| 674 |
+
"stateful_callbacks": {
|
| 675 |
+
"EarlyStoppingCallback": {
|
| 676 |
+
"args": {
|
| 677 |
+
"early_stopping_patience": 3,
|
| 678 |
+
"early_stopping_threshold": 0.0
|
| 679 |
+
},
|
| 680 |
+
"attributes": {
|
| 681 |
+
"early_stopping_patience_counter": 0
|
| 682 |
+
}
|
| 683 |
+
},
|
| 684 |
+
"TrainerControl": {
|
| 685 |
+
"args": {
|
| 686 |
+
"should_epoch_stop": false,
|
| 687 |
+
"should_evaluate": false,
|
| 688 |
+
"should_log": false,
|
| 689 |
+
"should_save": true,
|
| 690 |
+
"should_training_stop": true
|
| 691 |
+
},
|
| 692 |
+
"attributes": {}
|
| 693 |
+
}
|
| 694 |
+
},
|
| 695 |
+
"total_flos": 8.149698472747991e+18,
|
| 696 |
+
"train_batch_size": 8,
|
| 697 |
+
"trial_name": null,
|
| 698 |
+
"trial_params": null
|
| 699 |
+
}
|