End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_bleu": 7.5091,
|
| 4 |
+
"eval_gen_len": 43.958,
|
| 5 |
+
"eval_loss": 2.810835123062134,
|
| 6 |
+
"eval_runtime": 520.509,
|
| 7 |
+
"eval_samples": 1999,
|
| 8 |
+
"eval_samples_per_second": 3.84,
|
| 9 |
+
"eval_steps_per_second": 0.48,
|
| 10 |
+
"train_loss": 3.97135716796875,
|
| 11 |
+
"train_runtime": 2537.2035,
|
| 12 |
+
"train_samples": 10000,
|
| 13 |
+
"train_samples_per_second": 19.707,
|
| 14 |
+
"train_steps_per_second": 4.927
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_bleu": 7.5091,
|
| 4 |
+
"eval_gen_len": 43.958,
|
| 5 |
+
"eval_loss": 2.810835123062134,
|
| 6 |
+
"eval_runtime": 520.509,
|
| 7 |
+
"eval_samples": 1999,
|
| 8 |
+
"eval_samples_per_second": 3.84,
|
| 9 |
+
"eval_steps_per_second": 0.48
|
| 10 |
+
}
|
runs/Aug17_10-41-57_CIP-GPUSERVER-144/events.out.tfevents.1660708868.CIP-GPUSERVER-144.3284929.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c56bc3d01d80a3dc253ab26a56760eec35cb288e0a7ed4024ec45719ea60541b
|
| 3 |
+
size 410
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 3.97135716796875,
|
| 4 |
+
"train_runtime": 2537.2035,
|
| 5 |
+
"train_samples": 10000,
|
| 6 |
+
"train_samples_per_second": 19.707,
|
| 7 |
+
"train_steps_per_second": 4.927
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 12500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.2,
|
| 12 |
+
"learning_rate": 4.8e-05,
|
| 13 |
+
"loss": 17.0239,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.4,
|
| 18 |
+
"learning_rate": 4.600000000000001e-05,
|
| 19 |
+
"loss": 7.0095,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.6,
|
| 24 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 25 |
+
"loss": 5.1037,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.8,
|
| 30 |
+
"learning_rate": 4.2e-05,
|
| 31 |
+
"loss": 4.3776,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"learning_rate": 4e-05,
|
| 37 |
+
"loss": 4.0551,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.2,
|
| 42 |
+
"learning_rate": 3.8e-05,
|
| 43 |
+
"loss": 3.7753,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.4,
|
| 48 |
+
"learning_rate": 3.6e-05,
|
| 49 |
+
"loss": 3.6329,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.6,
|
| 54 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 55 |
+
"loss": 3.5096,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8,
|
| 60 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 61 |
+
"loss": 3.3955,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.0,
|
| 66 |
+
"learning_rate": 3e-05,
|
| 67 |
+
"loss": 3.2954,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.2,
|
| 72 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 73 |
+
"loss": 3.2394,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4,
|
| 78 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 79 |
+
"loss": 3.1177,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.6,
|
| 84 |
+
"learning_rate": 2.4e-05,
|
| 85 |
+
"loss": 3.0952,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.8,
|
| 90 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 91 |
+
"loss": 3.0372,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.0,
|
| 96 |
+
"learning_rate": 2e-05,
|
| 97 |
+
"loss": 3.0354,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.2,
|
| 102 |
+
"learning_rate": 1.8e-05,
|
| 103 |
+
"loss": 2.9562,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.4,
|
| 108 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 109 |
+
"loss": 2.9576,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.6,
|
| 114 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 115 |
+
"loss": 2.8647,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.8,
|
| 120 |
+
"learning_rate": 1.2e-05,
|
| 121 |
+
"loss": 2.9043,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.0,
|
| 126 |
+
"learning_rate": 1e-05,
|
| 127 |
+
"loss": 2.8477,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.2,
|
| 132 |
+
"learning_rate": 8.000000000000001e-06,
|
| 133 |
+
"loss": 2.807,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.4,
|
| 138 |
+
"learning_rate": 6e-06,
|
| 139 |
+
"loss": 2.7769,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.6,
|
| 144 |
+
"learning_rate": 4.000000000000001e-06,
|
| 145 |
+
"loss": 2.8152,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.8,
|
| 150 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 151 |
+
"loss": 2.8554,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.0,
|
| 156 |
+
"learning_rate": 0.0,
|
| 157 |
+
"loss": 2.7955,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 5.0,
|
| 162 |
+
"step": 12500,
|
| 163 |
+
"total_flos": 2522355797975040.0,
|
| 164 |
+
"train_loss": 3.97135716796875,
|
| 165 |
+
"train_runtime": 2537.2035,
|
| 166 |
+
"train_samples_per_second": 19.707,
|
| 167 |
+
"train_steps_per_second": 4.927
|
| 168 |
+
}
|
| 169 |
+
],
|
| 170 |
+
"max_steps": 12500,
|
| 171 |
+
"num_train_epochs": 5,
|
| 172 |
+
"total_flos": 2522355797975040.0,
|
| 173 |
+
"trial_name": null,
|
| 174 |
+
"trial_params": null
|
| 175 |
+
}
|