End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.2534329295158386,
|
| 4 |
+
"eval_runtime": 132.1673,
|
| 5 |
+
"eval_samples": 1549,
|
| 6 |
+
"eval_samples_per_second": 11.72,
|
| 7 |
+
"eval_steps_per_second": 1.468,
|
| 8 |
+
"eval_wer": 0.8469980632666236,
|
| 9 |
+
"train_loss": 2.1141159319460474,
|
| 10 |
+
"train_runtime": 3966.7132,
|
| 11 |
+
"train_samples": 11892,
|
| 12 |
+
"train_samples_per_second": 5.996,
|
| 13 |
+
"train_steps_per_second": 0.375
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.2534329295158386,
|
| 4 |
+
"eval_runtime": 132.1673,
|
| 5 |
+
"eval_samples": 1549,
|
| 6 |
+
"eval_samples_per_second": 11.72,
|
| 7 |
+
"eval_steps_per_second": 1.468,
|
| 8 |
+
"eval_wer": 0.8469980632666236
|
| 9 |
+
}
|
runs/Nov20_15-08-10_1b9bc83390b4/events.out.tfevents.1668962831.1b9bc83390b4.1924.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea778af9913453b8d06f0544a61618b5bf5015a4da19d6cfb40b7e8cd37394bc
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 2.1141159319460474,
|
| 4 |
+
"train_runtime": 3966.7132,
|
| 5 |
+
"train_samples": 11892,
|
| 6 |
+
"train_samples_per_second": 5.996,
|
| 7 |
+
"train_steps_per_second": 0.375
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2534329295158386,
|
| 3 |
+
"best_model_checkpoint": "./xls-r-300m-bemba-fullset/checkpoint-1000",
|
| 4 |
+
"epoch": 1.9993275050437123,
|
| 5 |
+
"global_step": 1486,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 1.47e-05,
|
| 13 |
+
"loss": 11.7638,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"learning_rate": 2.97e-05,
|
| 19 |
+
"loss": 3.7497,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.4,
|
| 24 |
+
"learning_rate": 4.4699999999999996e-05,
|
| 25 |
+
"loss": 3.0287,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.54,
|
| 30 |
+
"learning_rate": 5.97e-05,
|
| 31 |
+
"loss": 2.8222,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.67,
|
| 36 |
+
"learning_rate": 7.47e-05,
|
| 37 |
+
"loss": 2.268,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.67,
|
| 42 |
+
"eval_loss": 1.0355395078659058,
|
| 43 |
+
"eval_runtime": 140.0953,
|
| 44 |
+
"eval_samples_per_second": 11.057,
|
| 45 |
+
"eval_steps_per_second": 1.385,
|
| 46 |
+
"eval_wer": 0.9928986442866365,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.81,
|
| 51 |
+
"learning_rate": 8.969999999999998e-05,
|
| 52 |
+
"loss": 1.1597,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.94,
|
| 57 |
+
"learning_rate": 0.00010469999999999998,
|
| 58 |
+
"loss": 0.9172,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.08,
|
| 63 |
+
"learning_rate": 0.0001197,
|
| 64 |
+
"loss": 0.8284,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.21,
|
| 69 |
+
"learning_rate": 0.0001347,
|
| 70 |
+
"loss": 0.7667,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.35,
|
| 75 |
+
"learning_rate": 0.00014969999999999998,
|
| 76 |
+
"loss": 0.7365,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.35,
|
| 81 |
+
"eval_loss": 0.2534329295158386,
|
| 82 |
+
"eval_runtime": 132.8836,
|
| 83 |
+
"eval_samples_per_second": 11.657,
|
| 84 |
+
"eval_steps_per_second": 1.46,
|
| 85 |
+
"eval_wer": 0.8469980632666236,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.48,
|
| 90 |
+
"learning_rate": 0.0001647,
|
| 91 |
+
"loss": 0.7227,
|
| 92 |
+
"step": 1100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.61,
|
| 96 |
+
"learning_rate": 0.00017969999999999998,
|
| 97 |
+
"loss": 0.7068,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.75,
|
| 102 |
+
"learning_rate": 0.0001947,
|
| 103 |
+
"loss": 0.6875,
|
| 104 |
+
"step": 1300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.88,
|
| 108 |
+
"learning_rate": 0.00020969999999999997,
|
| 109 |
+
"loss": 0.6798,
|
| 110 |
+
"step": 1400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.0,
|
| 114 |
+
"step": 1486,
|
| 115 |
+
"total_flos": 4.4337322315078743e+18,
|
| 116 |
+
"train_loss": 2.1141159319460474,
|
| 117 |
+
"train_runtime": 3966.7132,
|
| 118 |
+
"train_samples_per_second": 5.996,
|
| 119 |
+
"train_steps_per_second": 0.375
|
| 120 |
+
}
|
| 121 |
+
],
|
| 122 |
+
"max_steps": 1486,
|
| 123 |
+
"num_train_epochs": 2,
|
| 124 |
+
"total_flos": 4.4337322315078743e+18,
|
| 125 |
+
"trial_name": null,
|
| 126 |
+
"trial_params": null
|
| 127 |
+
}
|