End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +766 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.098863636363637,
|
| 3 |
+
"eval_f1": 0.719188596491228,
|
| 4 |
+
"eval_loss": 0.9494466781616211,
|
| 5 |
+
"eval_runtime": 72.4119,
|
| 6 |
+
"eval_samples_per_second": 2.651,
|
| 7 |
+
"eval_steps_per_second": 0.331
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.098863636363637,
|
| 3 |
+
"eval_f1": 0.719188596491228,
|
| 4 |
+
"eval_loss": 0.9494466781616211,
|
| 5 |
+
"eval_runtime": 72.4119,
|
| 6 |
+
"eval_samples_per_second": 2.651,
|
| 7 |
+
"eval_steps_per_second": 0.331
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,766 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.719188596491228,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-shoplifting-dataset/checkpoint-353",
|
| 4 |
+
"epoch": 9.098863636363637,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 880,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011363636363636364,
|
| 13 |
+
"grad_norm": 0.7822037935256958,
|
| 14 |
+
"learning_rate": 5.681818181818182e-06,
|
| 15 |
+
"loss": 0.1251,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022727272727272728,
|
| 20 |
+
"grad_norm": 6.924298286437988,
|
| 21 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 22 |
+
"loss": 0.2906,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03409090909090909,
|
| 27 |
+
"grad_norm": 0.3597455322742462,
|
| 28 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 29 |
+
"loss": 0.1046,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.045454545454545456,
|
| 34 |
+
"grad_norm": 20.039451599121094,
|
| 35 |
+
"learning_rate": 2.272727272727273e-05,
|
| 36 |
+
"loss": 0.3495,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.056818181818181816,
|
| 41 |
+
"grad_norm": 19.18282127380371,
|
| 42 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 43 |
+
"loss": 0.3138,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06818181818181818,
|
| 48 |
+
"grad_norm": 6.543797016143799,
|
| 49 |
+
"learning_rate": 3.409090909090909e-05,
|
| 50 |
+
"loss": 0.2203,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07954545454545454,
|
| 55 |
+
"grad_norm": 9.147849082946777,
|
| 56 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 57 |
+
"loss": 0.3068,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09090909090909091,
|
| 62 |
+
"grad_norm": 1.336655616760254,
|
| 63 |
+
"learning_rate": 4.545454545454546e-05,
|
| 64 |
+
"loss": 0.1824,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10113636363636364,
|
| 69 |
+
"eval_f1": 0.6832431989511635,
|
| 70 |
+
"eval_loss": 1.0067527294158936,
|
| 71 |
+
"eval_runtime": 76.7216,
|
| 72 |
+
"eval_samples_per_second": 2.503,
|
| 73 |
+
"eval_steps_per_second": 0.313,
|
| 74 |
+
"step": 89
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0011363636363637,
|
| 78 |
+
"grad_norm": 8.309718132019043,
|
| 79 |
+
"learning_rate": 4.9873737373737375e-05,
|
| 80 |
+
"loss": 0.2712,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0125,
|
| 85 |
+
"grad_norm": 1.4587355852127075,
|
| 86 |
+
"learning_rate": 4.9242424242424245e-05,
|
| 87 |
+
"loss": 0.1706,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0238636363636364,
|
| 92 |
+
"grad_norm": 24.91333770751953,
|
| 93 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 94 |
+
"loss": 0.2993,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.0352272727272727,
|
| 99 |
+
"grad_norm": 2.1657192707061768,
|
| 100 |
+
"learning_rate": 4.797979797979798e-05,
|
| 101 |
+
"loss": 0.1297,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.0465909090909091,
|
| 106 |
+
"grad_norm": 0.5277124643325806,
|
| 107 |
+
"learning_rate": 4.7348484848484855e-05,
|
| 108 |
+
"loss": 0.2617,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.0579545454545454,
|
| 113 |
+
"grad_norm": 1.7243237495422363,
|
| 114 |
+
"learning_rate": 4.671717171717172e-05,
|
| 115 |
+
"loss": 0.1424,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0693181818181818,
|
| 120 |
+
"grad_norm": 1.7403205633163452,
|
| 121 |
+
"learning_rate": 4.608585858585859e-05,
|
| 122 |
+
"loss": 0.5873,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.080681818181818,
|
| 127 |
+
"grad_norm": 2.7504332065582275,
|
| 128 |
+
"learning_rate": 4.545454545454546e-05,
|
| 129 |
+
"loss": 0.2966,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0920454545454545,
|
| 134 |
+
"grad_norm": 6.052179336547852,
|
| 135 |
+
"learning_rate": 4.482323232323233e-05,
|
| 136 |
+
"loss": 0.334,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1,
|
| 141 |
+
"eval_f1": 0.6804519337964154,
|
| 142 |
+
"eval_loss": 0.9260269999504089,
|
| 143 |
+
"eval_runtime": 73.8445,
|
| 144 |
+
"eval_samples_per_second": 2.6,
|
| 145 |
+
"eval_steps_per_second": 0.325,
|
| 146 |
+
"step": 177
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.003409090909091,
|
| 150 |
+
"grad_norm": 0.761626124382019,
|
| 151 |
+
"learning_rate": 4.41919191919192e-05,
|
| 152 |
+
"loss": 0.6221,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.014772727272727,
|
| 157 |
+
"grad_norm": 0.5840346813201904,
|
| 158 |
+
"learning_rate": 4.356060606060606e-05,
|
| 159 |
+
"loss": 0.1877,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.026136363636364,
|
| 164 |
+
"grad_norm": 1.2796881198883057,
|
| 165 |
+
"learning_rate": 4.292929292929293e-05,
|
| 166 |
+
"loss": 0.1515,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.0375,
|
| 171 |
+
"grad_norm": 14.390783309936523,
|
| 172 |
+
"learning_rate": 4.2297979797979795e-05,
|
| 173 |
+
"loss": 0.1208,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0488636363636363,
|
| 178 |
+
"grad_norm": 8.565354347229004,
|
| 179 |
+
"learning_rate": 4.166666666666667e-05,
|
| 180 |
+
"loss": 0.1364,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.0602272727272726,
|
| 185 |
+
"grad_norm": 39.79494094848633,
|
| 186 |
+
"learning_rate": 4.1035353535353535e-05,
|
| 187 |
+
"loss": 0.2243,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.0715909090909093,
|
| 192 |
+
"grad_norm": 11.125761985778809,
|
| 193 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 194 |
+
"loss": 0.1289,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.0829545454545455,
|
| 199 |
+
"grad_norm": 0.10636977106332779,
|
| 200 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 201 |
+
"loss": 0.2634,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.0943181818181817,
|
| 206 |
+
"grad_norm": 6.6989617347717285,
|
| 207 |
+
"learning_rate": 3.9141414141414145e-05,
|
| 208 |
+
"loss": 0.2202,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.1,
|
| 213 |
+
"eval_f1": 0.7139075032998273,
|
| 214 |
+
"eval_loss": 0.9855768084526062,
|
| 215 |
+
"eval_runtime": 80.7383,
|
| 216 |
+
"eval_samples_per_second": 2.378,
|
| 217 |
+
"eval_steps_per_second": 0.297,
|
| 218 |
+
"step": 265
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.0056818181818183,
|
| 222 |
+
"grad_norm": 7.529367446899414,
|
| 223 |
+
"learning_rate": 3.8510101010101015e-05,
|
| 224 |
+
"loss": 0.1857,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.0170454545454546,
|
| 229 |
+
"grad_norm": 1.7394098043441772,
|
| 230 |
+
"learning_rate": 3.787878787878788e-05,
|
| 231 |
+
"loss": 0.1633,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.028409090909091,
|
| 236 |
+
"grad_norm": 35.92728805541992,
|
| 237 |
+
"learning_rate": 3.724747474747475e-05,
|
| 238 |
+
"loss": 0.147,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.039772727272727,
|
| 243 |
+
"grad_norm": 6.699644565582275,
|
| 244 |
+
"learning_rate": 3.661616161616162e-05,
|
| 245 |
+
"loss": 0.1791,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.0511363636363638,
|
| 250 |
+
"grad_norm": 7.0385894775390625,
|
| 251 |
+
"learning_rate": 3.598484848484849e-05,
|
| 252 |
+
"loss": 0.148,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.0625,
|
| 257 |
+
"grad_norm": 3.4319474697113037,
|
| 258 |
+
"learning_rate": 3.535353535353535e-05,
|
| 259 |
+
"loss": 0.1414,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0738636363636362,
|
| 264 |
+
"grad_norm": 1.3963415622711182,
|
| 265 |
+
"learning_rate": 3.472222222222222e-05,
|
| 266 |
+
"loss": 0.0888,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.085227272727273,
|
| 271 |
+
"grad_norm": 0.17751815915107727,
|
| 272 |
+
"learning_rate": 3.409090909090909e-05,
|
| 273 |
+
"loss": 0.1007,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.096590909090909,
|
| 278 |
+
"grad_norm": 8.843611717224121,
|
| 279 |
+
"learning_rate": 3.345959595959596e-05,
|
| 280 |
+
"loss": 0.2074,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.1,
|
| 285 |
+
"eval_f1": 0.719188596491228,
|
| 286 |
+
"eval_loss": 0.9494466781616211,
|
| 287 |
+
"eval_runtime": 66.0371,
|
| 288 |
+
"eval_samples_per_second": 2.907,
|
| 289 |
+
"eval_steps_per_second": 0.363,
|
| 290 |
+
"step": 353
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.007954545454545,
|
| 294 |
+
"grad_norm": 0.11681011319160461,
|
| 295 |
+
"learning_rate": 3.282828282828283e-05,
|
| 296 |
+
"loss": 0.1654,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.019318181818182,
|
| 301 |
+
"grad_norm": 0.03579840064048767,
|
| 302 |
+
"learning_rate": 3.2196969696969696e-05,
|
| 303 |
+
"loss": 0.0781,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.030681818181818,
|
| 308 |
+
"grad_norm": 0.28152555227279663,
|
| 309 |
+
"learning_rate": 3.1565656565656566e-05,
|
| 310 |
+
"loss": 0.0961,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.0420454545454545,
|
| 315 |
+
"grad_norm": 0.36765220761299133,
|
| 316 |
+
"learning_rate": 3.0934343434343436e-05,
|
| 317 |
+
"loss": 0.0591,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.053409090909091,
|
| 322 |
+
"grad_norm": 13.338018417358398,
|
| 323 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 324 |
+
"loss": 0.0945,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.064772727272727,
|
| 329 |
+
"grad_norm": 9.662626266479492,
|
| 330 |
+
"learning_rate": 2.9671717171717172e-05,
|
| 331 |
+
"loss": 0.1343,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.076136363636364,
|
| 336 |
+
"grad_norm": 1.916236400604248,
|
| 337 |
+
"learning_rate": 2.904040404040404e-05,
|
| 338 |
+
"loss": 0.3043,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.0875,
|
| 343 |
+
"grad_norm": 12.770139694213867,
|
| 344 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 345 |
+
"loss": 0.2391,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.098863636363636,
|
| 350 |
+
"grad_norm": 7.032412052154541,
|
| 351 |
+
"learning_rate": 2.777777777777778e-05,
|
| 352 |
+
"loss": 0.0916,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.1,
|
| 357 |
+
"eval_f1": 0.671078431372549,
|
| 358 |
+
"eval_loss": 1.3867233991622925,
|
| 359 |
+
"eval_runtime": 69.8609,
|
| 360 |
+
"eval_samples_per_second": 2.748,
|
| 361 |
+
"eval_steps_per_second": 0.344,
|
| 362 |
+
"step": 441
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.010227272727272,
|
| 366 |
+
"grad_norm": 9.611908912658691,
|
| 367 |
+
"learning_rate": 2.714646464646465e-05,
|
| 368 |
+
"loss": 0.1568,
|
| 369 |
+
"step": 450
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.021590909090909,
|
| 373 |
+
"grad_norm": 3.7834885120391846,
|
| 374 |
+
"learning_rate": 2.6515151515151516e-05,
|
| 375 |
+
"loss": 0.3173,
|
| 376 |
+
"step": 460
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 5.032954545454546,
|
| 380 |
+
"grad_norm": 0.057657867670059204,
|
| 381 |
+
"learning_rate": 2.5883838383838382e-05,
|
| 382 |
+
"loss": 0.1004,
|
| 383 |
+
"step": 470
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 5.0443181818181815,
|
| 387 |
+
"grad_norm": 1.133195161819458,
|
| 388 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 389 |
+
"loss": 0.0869,
|
| 390 |
+
"step": 480
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.055681818181818,
|
| 394 |
+
"grad_norm": 6.4852166175842285,
|
| 395 |
+
"learning_rate": 2.4621212121212123e-05,
|
| 396 |
+
"loss": 0.0964,
|
| 397 |
+
"step": 490
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 5.067045454545455,
|
| 401 |
+
"grad_norm": 0.01637670025229454,
|
| 402 |
+
"learning_rate": 2.398989898989899e-05,
|
| 403 |
+
"loss": 0.0511,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.078409090909091,
|
| 408 |
+
"grad_norm": 20.669986724853516,
|
| 409 |
+
"learning_rate": 2.335858585858586e-05,
|
| 410 |
+
"loss": 0.2204,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 5.089772727272727,
|
| 415 |
+
"grad_norm": 0.07228785008192062,
|
| 416 |
+
"learning_rate": 2.272727272727273e-05,
|
| 417 |
+
"loss": 0.1092,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 5.1,
|
| 422 |
+
"eval_f1": 0.6919812909064125,
|
| 423 |
+
"eval_loss": 1.3757562637329102,
|
| 424 |
+
"eval_runtime": 68.2311,
|
| 425 |
+
"eval_samples_per_second": 2.814,
|
| 426 |
+
"eval_steps_per_second": 0.352,
|
| 427 |
+
"step": 529
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 6.0011363636363635,
|
| 431 |
+
"grad_norm": 0.03453134745359421,
|
| 432 |
+
"learning_rate": 2.20959595959596e-05,
|
| 433 |
+
"loss": 0.1523,
|
| 434 |
+
"step": 530
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.0125,
|
| 438 |
+
"grad_norm": 0.4955722689628601,
|
| 439 |
+
"learning_rate": 2.1464646464646466e-05,
|
| 440 |
+
"loss": 0.1371,
|
| 441 |
+
"step": 540
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.023863636363636,
|
| 445 |
+
"grad_norm": 0.6915594339370728,
|
| 446 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 447 |
+
"loss": 0.0278,
|
| 448 |
+
"step": 550
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 6.035227272727273,
|
| 452 |
+
"grad_norm": 0.030776426196098328,
|
| 453 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 454 |
+
"loss": 0.0441,
|
| 455 |
+
"step": 560
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 6.046590909090909,
|
| 459 |
+
"grad_norm": 0.008703567087650299,
|
| 460 |
+
"learning_rate": 1.9570707070707073e-05,
|
| 461 |
+
"loss": 0.0117,
|
| 462 |
+
"step": 570
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 6.057954545454545,
|
| 466 |
+
"grad_norm": 12.471619606018066,
|
| 467 |
+
"learning_rate": 1.893939393939394e-05,
|
| 468 |
+
"loss": 0.0576,
|
| 469 |
+
"step": 580
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 6.069318181818182,
|
| 473 |
+
"grad_norm": 0.023786788806319237,
|
| 474 |
+
"learning_rate": 1.830808080808081e-05,
|
| 475 |
+
"loss": 0.0282,
|
| 476 |
+
"step": 590
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 6.0806818181818185,
|
| 480 |
+
"grad_norm": 0.24424441158771515,
|
| 481 |
+
"learning_rate": 1.7676767676767676e-05,
|
| 482 |
+
"loss": 0.1136,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.092045454545454,
|
| 487 |
+
"grad_norm": 0.014285405166447163,
|
| 488 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 489 |
+
"loss": 0.0804,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6.1,
|
| 494 |
+
"eval_f1": 0.6967864271457085,
|
| 495 |
+
"eval_loss": 1.3787533044815063,
|
| 496 |
+
"eval_runtime": 70.4409,
|
| 497 |
+
"eval_samples_per_second": 2.726,
|
| 498 |
+
"eval_steps_per_second": 0.341,
|
| 499 |
+
"step": 617
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.0034090909090905,
|
| 503 |
+
"grad_norm": 0.14964497089385986,
|
| 504 |
+
"learning_rate": 1.6414141414141416e-05,
|
| 505 |
+
"loss": 0.0217,
|
| 506 |
+
"step": 620
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.014772727272727,
|
| 510 |
+
"grad_norm": 22.6522274017334,
|
| 511 |
+
"learning_rate": 1.5782828282828283e-05,
|
| 512 |
+
"loss": 0.2281,
|
| 513 |
+
"step": 630
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.026136363636364,
|
| 517 |
+
"grad_norm": 0.24736760556697845,
|
| 518 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 519 |
+
"loss": 0.0425,
|
| 520 |
+
"step": 640
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.0375,
|
| 524 |
+
"grad_norm": 0.11569665372371674,
|
| 525 |
+
"learning_rate": 1.452020202020202e-05,
|
| 526 |
+
"loss": 0.004,
|
| 527 |
+
"step": 650
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.048863636363636,
|
| 531 |
+
"grad_norm": 7.235473155975342,
|
| 532 |
+
"learning_rate": 1.388888888888889e-05,
|
| 533 |
+
"loss": 0.0268,
|
| 534 |
+
"step": 660
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.060227272727273,
|
| 538 |
+
"grad_norm": 0.006639318075031042,
|
| 539 |
+
"learning_rate": 1.3257575757575758e-05,
|
| 540 |
+
"loss": 0.0387,
|
| 541 |
+
"step": 670
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.071590909090909,
|
| 545 |
+
"grad_norm": 0.07593043893575668,
|
| 546 |
+
"learning_rate": 1.2626262626262628e-05,
|
| 547 |
+
"loss": 0.0685,
|
| 548 |
+
"step": 680
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.0829545454545455,
|
| 552 |
+
"grad_norm": 0.02903686836361885,
|
| 553 |
+
"learning_rate": 1.1994949494949495e-05,
|
| 554 |
+
"loss": 0.0889,
|
| 555 |
+
"step": 690
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.094318181818182,
|
| 559 |
+
"grad_norm": 0.10437527298927307,
|
| 560 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 561 |
+
"loss": 0.0654,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.1,
|
| 566 |
+
"eval_f1": 0.697334455667789,
|
| 567 |
+
"eval_loss": 1.2969599962234497,
|
| 568 |
+
"eval_runtime": 75.4359,
|
| 569 |
+
"eval_samples_per_second": 2.545,
|
| 570 |
+
"eval_steps_per_second": 0.318,
|
| 571 |
+
"step": 705
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 8.005681818181818,
|
| 575 |
+
"grad_norm": 0.3526234030723572,
|
| 576 |
+
"learning_rate": 1.0732323232323233e-05,
|
| 577 |
+
"loss": 0.1004,
|
| 578 |
+
"step": 710
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 8.017045454545455,
|
| 582 |
+
"grad_norm": 0.544172465801239,
|
| 583 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 584 |
+
"loss": 0.0323,
|
| 585 |
+
"step": 720
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.028409090909092,
|
| 589 |
+
"grad_norm": 27.582374572753906,
|
| 590 |
+
"learning_rate": 9.46969696969697e-06,
|
| 591 |
+
"loss": 0.0817,
|
| 592 |
+
"step": 730
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 8.039772727272727,
|
| 596 |
+
"grad_norm": 0.03466358035802841,
|
| 597 |
+
"learning_rate": 8.838383838383838e-06,
|
| 598 |
+
"loss": 0.033,
|
| 599 |
+
"step": 740
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 8.051136363636363,
|
| 603 |
+
"grad_norm": 0.2677808105945587,
|
| 604 |
+
"learning_rate": 8.207070707070708e-06,
|
| 605 |
+
"loss": 0.0078,
|
| 606 |
+
"step": 750
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 8.0625,
|
| 610 |
+
"grad_norm": 0.026267457753419876,
|
| 611 |
+
"learning_rate": 7.5757575757575764e-06,
|
| 612 |
+
"loss": 0.1072,
|
| 613 |
+
"step": 760
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 8.073863636363637,
|
| 617 |
+
"grad_norm": 0.036878038197755814,
|
| 618 |
+
"learning_rate": 6.944444444444445e-06,
|
| 619 |
+
"loss": 0.175,
|
| 620 |
+
"step": 770
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 8.085227272727273,
|
| 624 |
+
"grad_norm": 3.7212748527526855,
|
| 625 |
+
"learning_rate": 6.313131313131314e-06,
|
| 626 |
+
"loss": 0.0646,
|
| 627 |
+
"step": 780
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 8.096590909090908,
|
| 631 |
+
"grad_norm": 0.06381477415561676,
|
| 632 |
+
"learning_rate": 5.681818181818182e-06,
|
| 633 |
+
"loss": 0.0065,
|
| 634 |
+
"step": 790
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 8.1,
|
| 638 |
+
"eval_f1": 0.7006284557943339,
|
| 639 |
+
"eval_loss": 1.4780327081680298,
|
| 640 |
+
"eval_runtime": 71.4359,
|
| 641 |
+
"eval_samples_per_second": 2.688,
|
| 642 |
+
"eval_steps_per_second": 0.336,
|
| 643 |
+
"step": 793
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 9.007954545454545,
|
| 647 |
+
"grad_norm": 0.14042355120182037,
|
| 648 |
+
"learning_rate": 5.050505050505051e-06,
|
| 649 |
+
"loss": 0.0604,
|
| 650 |
+
"step": 800
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 9.019318181818182,
|
| 654 |
+
"grad_norm": 0.007114021107554436,
|
| 655 |
+
"learning_rate": 4.419191919191919e-06,
|
| 656 |
+
"loss": 0.1103,
|
| 657 |
+
"step": 810
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 9.030681818181819,
|
| 661 |
+
"grad_norm": 3.3601884841918945,
|
| 662 |
+
"learning_rate": 3.7878787878787882e-06,
|
| 663 |
+
"loss": 0.1139,
|
| 664 |
+
"step": 820
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 9.042045454545455,
|
| 668 |
+
"grad_norm": 0.0043687219731509686,
|
| 669 |
+
"learning_rate": 3.156565656565657e-06,
|
| 670 |
+
"loss": 0.0034,
|
| 671 |
+
"step": 830
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 9.05340909090909,
|
| 675 |
+
"grad_norm": 0.04162032902240753,
|
| 676 |
+
"learning_rate": 2.5252525252525253e-06,
|
| 677 |
+
"loss": 0.0108,
|
| 678 |
+
"step": 840
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 9.064772727272727,
|
| 682 |
+
"grad_norm": 1.4939607381820679,
|
| 683 |
+
"learning_rate": 1.8939393939393941e-06,
|
| 684 |
+
"loss": 0.0889,
|
| 685 |
+
"step": 850
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 9.076136363636364,
|
| 689 |
+
"grad_norm": 0.6243687868118286,
|
| 690 |
+
"learning_rate": 1.2626262626262627e-06,
|
| 691 |
+
"loss": 0.0082,
|
| 692 |
+
"step": 860
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 9.0875,
|
| 696 |
+
"grad_norm": 0.010640038177371025,
|
| 697 |
+
"learning_rate": 6.313131313131313e-07,
|
| 698 |
+
"loss": 0.0318,
|
| 699 |
+
"step": 870
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 9.098863636363637,
|
| 703 |
+
"grad_norm": 0.6547775864601135,
|
| 704 |
+
"learning_rate": 0.0,
|
| 705 |
+
"loss": 0.0024,
|
| 706 |
+
"step": 880
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 9.098863636363637,
|
| 710 |
+
"eval_f1": 0.7006284557943339,
|
| 711 |
+
"eval_loss": 1.4463977813720703,
|
| 712 |
+
"eval_runtime": 70.5842,
|
| 713 |
+
"eval_samples_per_second": 2.72,
|
| 714 |
+
"eval_steps_per_second": 0.34,
|
| 715 |
+
"step": 880
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 9.098863636363637,
|
| 719 |
+
"step": 880,
|
| 720 |
+
"total_flos": 8.763572257754776e+18,
|
| 721 |
+
"train_loss": 0.14181382804474033,
|
| 722 |
+
"train_runtime": 4562.3352,
|
| 723 |
+
"train_samples_per_second": 1.543,
|
| 724 |
+
"train_steps_per_second": 0.193
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 9.098863636363637,
|
| 728 |
+
"eval_f1": 0.719188596491228,
|
| 729 |
+
"eval_loss": 0.9494466781616211,
|
| 730 |
+
"eval_runtime": 71.753,
|
| 731 |
+
"eval_samples_per_second": 2.676,
|
| 732 |
+
"eval_steps_per_second": 0.334,
|
| 733 |
+
"step": 880
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 9.098863636363637,
|
| 737 |
+
"eval_f1": 0.719188596491228,
|
| 738 |
+
"eval_loss": 0.9494466781616211,
|
| 739 |
+
"eval_runtime": 72.4119,
|
| 740 |
+
"eval_samples_per_second": 2.651,
|
| 741 |
+
"eval_steps_per_second": 0.331,
|
| 742 |
+
"step": 880
|
| 743 |
+
}
|
| 744 |
+
],
|
| 745 |
+
"logging_steps": 10,
|
| 746 |
+
"max_steps": 880,
|
| 747 |
+
"num_input_tokens_seen": 0,
|
| 748 |
+
"num_train_epochs": 9223372036854775807,
|
| 749 |
+
"save_steps": 500,
|
| 750 |
+
"stateful_callbacks": {
|
| 751 |
+
"TrainerControl": {
|
| 752 |
+
"args": {
|
| 753 |
+
"should_epoch_stop": false,
|
| 754 |
+
"should_evaluate": false,
|
| 755 |
+
"should_log": false,
|
| 756 |
+
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
+
},
|
| 759 |
+
"attributes": {}
|
| 760 |
+
}
|
| 761 |
+
},
|
| 762 |
+
"total_flos": 8.763572257754776e+18,
|
| 763 |
+
"train_batch_size": 8,
|
| 764 |
+
"trial_name": null,
|
| 765 |
+
"trial_params": null
|
| 766 |
+
}
|