Training in progress, step 15200
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Jan04_20-37-14_vorace/events.out.tfevents.1704401907.vorace.1537045.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +708 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_loss": 3.3253096312547563,
|
| 4 |
+
"train_runtime": 44962.3834,
|
| 5 |
+
"train_samples": 43798,
|
| 6 |
+
"train_samples_per_second": 14.612,
|
| 7 |
+
"train_steps_per_second": 0.365
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2322279712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7672da5bd09cf427bc66613581a71b449bbc210ad010a9367fe7492cdb60f19
|
| 3 |
size 2322279712
|
runs/Jan04_20-37-14_vorace/events.out.tfevents.1704401907.vorace.1537045.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83336ed20a20bcf3e49a097cf65553b0523e13c87e33668c7a97a761d0625edb
|
| 3 |
+
size 26259
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_loss": 3.3253096312547563,
|
| 4 |
+
"train_runtime": 44962.3834,
|
| 5 |
+
"train_samples": 43798,
|
| 6 |
+
"train_samples_per_second": 14.612,
|
| 7 |
+
"train_steps_per_second": 0.365
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,708 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 300,
|
| 6 |
+
"global_step": 16425,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.27,
|
| 13 |
+
"eval_loss": 7.266334533691406,
|
| 14 |
+
"eval_runtime": 325.0132,
|
| 15 |
+
"eval_samples_per_second": 33.952,
|
| 16 |
+
"eval_steps_per_second": 1.061,
|
| 17 |
+
"eval_wer": 1.0,
|
| 18 |
+
"step": 300
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.46,
|
| 22 |
+
"learning_rate": 7.14420628442998e-05,
|
| 23 |
+
"loss": 10.5256,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.55,
|
| 28 |
+
"eval_loss": 3.0892837047576904,
|
| 29 |
+
"eval_runtime": 316.7833,
|
| 30 |
+
"eval_samples_per_second": 34.835,
|
| 31 |
+
"eval_steps_per_second": 1.089,
|
| 32 |
+
"eval_wer": 1.0,
|
| 33 |
+
"step": 600
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.82,
|
| 37 |
+
"eval_loss": 3.061225652694702,
|
| 38 |
+
"eval_runtime": 483.1327,
|
| 39 |
+
"eval_samples_per_second": 22.841,
|
| 40 |
+
"eval_steps_per_second": 0.714,
|
| 41 |
+
"eval_wer": 1.0,
|
| 42 |
+
"step": 900
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.91,
|
| 46 |
+
"learning_rate": 0.0001434602713566988,
|
| 47 |
+
"loss": 2.9795,
|
| 48 |
+
"step": 1000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.1,
|
| 52 |
+
"eval_loss": 2.9936766624450684,
|
| 53 |
+
"eval_runtime": 320.3828,
|
| 54 |
+
"eval_samples_per_second": 34.443,
|
| 55 |
+
"eval_steps_per_second": 1.077,
|
| 56 |
+
"eval_wer": 1.0,
|
| 57 |
+
"step": 1200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.37,
|
| 61 |
+
"learning_rate": 0.0002154784798690978,
|
| 62 |
+
"loss": 2.9564,
|
| 63 |
+
"step": 1500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.37,
|
| 67 |
+
"eval_loss": 3.242413282394409,
|
| 68 |
+
"eval_runtime": 328.1378,
|
| 69 |
+
"eval_samples_per_second": 33.629,
|
| 70 |
+
"eval_steps_per_second": 1.051,
|
| 71 |
+
"eval_wer": 1.0,
|
| 72 |
+
"step": 1500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.64,
|
| 76 |
+
"eval_loss": 3.2866387367248535,
|
| 77 |
+
"eval_runtime": 325.8189,
|
| 78 |
+
"eval_samples_per_second": 33.869,
|
| 79 |
+
"eval_steps_per_second": 1.059,
|
| 80 |
+
"eval_wer": 1.0,
|
| 81 |
+
"step": 1800
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.83,
|
| 85 |
+
"learning_rate": 0.0002874966883814968,
|
| 86 |
+
"loss": 3.1552,
|
| 87 |
+
"step": 2000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.92,
|
| 91 |
+
"eval_loss": 3.6338589191436768,
|
| 92 |
+
"eval_runtime": 322.0052,
|
| 93 |
+
"eval_samples_per_second": 34.27,
|
| 94 |
+
"eval_steps_per_second": 1.071,
|
| 95 |
+
"eval_wer": 1.0,
|
| 96 |
+
"step": 2100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.19,
|
| 100 |
+
"eval_loss": 3.1184866428375244,
|
| 101 |
+
"eval_runtime": 316.2742,
|
| 102 |
+
"eval_samples_per_second": 34.891,
|
| 103 |
+
"eval_steps_per_second": 1.091,
|
| 104 |
+
"eval_wer": 1.0,
|
| 105 |
+
"step": 2400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.28,
|
| 109 |
+
"learning_rate": 0.00035951489689389575,
|
| 110 |
+
"loss": 3.2079,
|
| 111 |
+
"step": 2500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.47,
|
| 115 |
+
"eval_loss": 3.183176040649414,
|
| 116 |
+
"eval_runtime": 316.7437,
|
| 117 |
+
"eval_samples_per_second": 34.839,
|
| 118 |
+
"eval_steps_per_second": 1.089,
|
| 119 |
+
"eval_wer": 1.0,
|
| 120 |
+
"step": 2700
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.74,
|
| 124 |
+
"learning_rate": 0.00043153310540629475,
|
| 125 |
+
"loss": 3.1275,
|
| 126 |
+
"step": 3000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.74,
|
| 130 |
+
"eval_loss": 3.3952367305755615,
|
| 131 |
+
"eval_runtime": 319.4373,
|
| 132 |
+
"eval_samples_per_second": 34.545,
|
| 133 |
+
"eval_steps_per_second": 1.08,
|
| 134 |
+
"eval_wer": 1.0,
|
| 135 |
+
"step": 3000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.01,
|
| 139 |
+
"eval_loss": 3.2981579303741455,
|
| 140 |
+
"eval_runtime": 327.568,
|
| 141 |
+
"eval_samples_per_second": 33.688,
|
| 142 |
+
"eval_steps_per_second": 1.053,
|
| 143 |
+
"eval_wer": 1.0,
|
| 144 |
+
"step": 3300
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.2,
|
| 148 |
+
"learning_rate": 0.0005035513139186939,
|
| 149 |
+
"loss": 3.0987,
|
| 150 |
+
"step": 3500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.29,
|
| 154 |
+
"eval_loss": 3.103595733642578,
|
| 155 |
+
"eval_runtime": 327.3342,
|
| 156 |
+
"eval_samples_per_second": 33.712,
|
| 157 |
+
"eval_steps_per_second": 1.054,
|
| 158 |
+
"eval_wer": 1.0,
|
| 159 |
+
"step": 3600
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.56,
|
| 163 |
+
"eval_loss": 3.1222941875457764,
|
| 164 |
+
"eval_runtime": 312.8357,
|
| 165 |
+
"eval_samples_per_second": 35.274,
|
| 166 |
+
"eval_steps_per_second": 1.103,
|
| 167 |
+
"eval_wer": 1.0,
|
| 168 |
+
"step": 3900
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.65,
|
| 172 |
+
"learning_rate": 0.0005755695224310928,
|
| 173 |
+
"loss": 2.9301,
|
| 174 |
+
"step": 4000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.84,
|
| 178 |
+
"eval_loss": 3.114525556564331,
|
| 179 |
+
"eval_runtime": 308.5965,
|
| 180 |
+
"eval_samples_per_second": 35.759,
|
| 181 |
+
"eval_steps_per_second": 1.118,
|
| 182 |
+
"eval_wer": 1.0,
|
| 183 |
+
"step": 4200
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.11,
|
| 187 |
+
"learning_rate": 0.0006475877309434917,
|
| 188 |
+
"loss": 2.9197,
|
| 189 |
+
"step": 4500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.11,
|
| 193 |
+
"eval_loss": 3.0324432849884033,
|
| 194 |
+
"eval_runtime": 308.9122,
|
| 195 |
+
"eval_samples_per_second": 35.722,
|
| 196 |
+
"eval_steps_per_second": 1.117,
|
| 197 |
+
"eval_wer": 1.0,
|
| 198 |
+
"step": 4500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.38,
|
| 202 |
+
"eval_loss": 2.999401807785034,
|
| 203 |
+
"eval_runtime": 308.612,
|
| 204 |
+
"eval_samples_per_second": 35.757,
|
| 205 |
+
"eval_steps_per_second": 1.118,
|
| 206 |
+
"eval_wer": 1.9598550067965563,
|
| 207 |
+
"step": 4800
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.57,
|
| 211 |
+
"learning_rate": 0.0007196059394558908,
|
| 212 |
+
"loss": 2.9023,
|
| 213 |
+
"step": 5000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.66,
|
| 217 |
+
"eval_loss": 2.991722822189331,
|
| 218 |
+
"eval_runtime": 309.103,
|
| 219 |
+
"eval_samples_per_second": 35.7,
|
| 220 |
+
"eval_steps_per_second": 1.116,
|
| 221 |
+
"eval_wer": 1.8240144993203444,
|
| 222 |
+
"step": 5100
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.93,
|
| 226 |
+
"eval_loss": 2.9946165084838867,
|
| 227 |
+
"eval_runtime": 308.4148,
|
| 228 |
+
"eval_samples_per_second": 35.78,
|
| 229 |
+
"eval_steps_per_second": 1.119,
|
| 230 |
+
"eval_wer": 1.958948799275034,
|
| 231 |
+
"step": 5400
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.02,
|
| 235 |
+
"learning_rate": 0.0006889164121067909,
|
| 236 |
+
"loss": 2.9007,
|
| 237 |
+
"step": 5500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 5.21,
|
| 241 |
+
"eval_loss": 3.195502519607544,
|
| 242 |
+
"eval_runtime": 308.3861,
|
| 243 |
+
"eval_samples_per_second": 35.783,
|
| 244 |
+
"eval_steps_per_second": 1.119,
|
| 245 |
+
"eval_wer": 1.0,
|
| 246 |
+
"step": 5700
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.48,
|
| 250 |
+
"learning_rate": 0.0006574616321963427,
|
| 251 |
+
"loss": 3.1887,
|
| 252 |
+
"step": 6000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.48,
|
| 256 |
+
"eval_loss": 3.1901698112487793,
|
| 257 |
+
"eval_runtime": 308.4713,
|
| 258 |
+
"eval_samples_per_second": 35.773,
|
| 259 |
+
"eval_steps_per_second": 1.118,
|
| 260 |
+
"eval_wer": 1.0,
|
| 261 |
+
"step": 6000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.75,
|
| 265 |
+
"eval_loss": 3.167245864868164,
|
| 266 |
+
"eval_runtime": 308.5576,
|
| 267 |
+
"eval_samples_per_second": 35.763,
|
| 268 |
+
"eval_steps_per_second": 1.118,
|
| 269 |
+
"eval_wer": 1.0,
|
| 270 |
+
"step": 6300
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.94,
|
| 274 |
+
"learning_rate": 0.0006259438166548115,
|
| 275 |
+
"loss": 3.135,
|
| 276 |
+
"step": 6500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 6.03,
|
| 280 |
+
"eval_loss": 3.2076234817504883,
|
| 281 |
+
"eval_runtime": 308.784,
|
| 282 |
+
"eval_samples_per_second": 35.737,
|
| 283 |
+
"eval_steps_per_second": 1.117,
|
| 284 |
+
"eval_wer": 1.0,
|
| 285 |
+
"step": 6600
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.3,
|
| 289 |
+
"eval_loss": 3.212040424346924,
|
| 290 |
+
"eval_runtime": 309.3257,
|
| 291 |
+
"eval_samples_per_second": 35.674,
|
| 292 |
+
"eval_steps_per_second": 1.115,
|
| 293 |
+
"eval_wer": 1.0,
|
| 294 |
+
"step": 6900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.39,
|
| 298 |
+
"learning_rate": 0.0005944260011132802,
|
| 299 |
+
"loss": 3.1482,
|
| 300 |
+
"step": 7000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 6.58,
|
| 304 |
+
"eval_loss": 3.1832025051116943,
|
| 305 |
+
"eval_runtime": 308.2925,
|
| 306 |
+
"eval_samples_per_second": 35.794,
|
| 307 |
+
"eval_steps_per_second": 1.119,
|
| 308 |
+
"eval_wer": 1.0,
|
| 309 |
+
"step": 7200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.85,
|
| 313 |
+
"learning_rate": 0.0005629081855717488,
|
| 314 |
+
"loss": 3.1546,
|
| 315 |
+
"step": 7500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.85,
|
| 319 |
+
"eval_loss": 3.1799111366271973,
|
| 320 |
+
"eval_runtime": 308.7059,
|
| 321 |
+
"eval_samples_per_second": 35.746,
|
| 322 |
+
"eval_steps_per_second": 1.118,
|
| 323 |
+
"eval_wer": 1.0,
|
| 324 |
+
"step": 7500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.12,
|
| 328 |
+
"eval_loss": 3.2451581954956055,
|
| 329 |
+
"eval_runtime": 307.3881,
|
| 330 |
+
"eval_samples_per_second": 35.899,
|
| 331 |
+
"eval_steps_per_second": 1.122,
|
| 332 |
+
"eval_wer": 1.0,
|
| 333 |
+
"step": 7800
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 7.31,
|
| 337 |
+
"learning_rate": 0.0005313903700302176,
|
| 338 |
+
"loss": 3.1567,
|
| 339 |
+
"step": 8000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.4,
|
| 343 |
+
"eval_loss": 3.2318718433380127,
|
| 344 |
+
"eval_runtime": 308.2983,
|
| 345 |
+
"eval_samples_per_second": 35.793,
|
| 346 |
+
"eval_steps_per_second": 1.119,
|
| 347 |
+
"eval_wer": 1.0,
|
| 348 |
+
"step": 8100
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 7.67,
|
| 352 |
+
"eval_loss": 3.222830057144165,
|
| 353 |
+
"eval_runtime": 308.3145,
|
| 354 |
+
"eval_samples_per_second": 35.791,
|
| 355 |
+
"eval_steps_per_second": 1.119,
|
| 356 |
+
"eval_wer": 1.0,
|
| 357 |
+
"step": 8400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 7.76,
|
| 361 |
+
"learning_rate": 0.0004998725544886862,
|
| 362 |
+
"loss": 3.1719,
|
| 363 |
+
"step": 8500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 7.95,
|
| 367 |
+
"eval_loss": 3.2054970264434814,
|
| 368 |
+
"eval_runtime": 308.0159,
|
| 369 |
+
"eval_samples_per_second": 35.826,
|
| 370 |
+
"eval_steps_per_second": 1.12,
|
| 371 |
+
"eval_wer": 1.0,
|
| 372 |
+
"step": 8700
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 8.22,
|
| 376 |
+
"learning_rate": 0.00046835473894715497,
|
| 377 |
+
"loss": 3.168,
|
| 378 |
+
"step": 9000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 8.22,
|
| 382 |
+
"eval_loss": 3.2552778720855713,
|
| 383 |
+
"eval_runtime": 303.2884,
|
| 384 |
+
"eval_samples_per_second": 36.385,
|
| 385 |
+
"eval_steps_per_second": 1.138,
|
| 386 |
+
"eval_wer": 1.0,
|
| 387 |
+
"step": 9000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.49,
|
| 391 |
+
"eval_loss": 3.197523593902588,
|
| 392 |
+
"eval_runtime": 305.1147,
|
| 393 |
+
"eval_samples_per_second": 36.167,
|
| 394 |
+
"eval_steps_per_second": 1.131,
|
| 395 |
+
"eval_wer": 1.0,
|
| 396 |
+
"step": 9300
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.68,
|
| 400 |
+
"learning_rate": 0.0004368369234056237,
|
| 401 |
+
"loss": 3.1643,
|
| 402 |
+
"step": 9500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.77,
|
| 406 |
+
"eval_loss": 3.2445874214172363,
|
| 407 |
+
"eval_runtime": 303.4296,
|
| 408 |
+
"eval_samples_per_second": 36.368,
|
| 409 |
+
"eval_steps_per_second": 1.137,
|
| 410 |
+
"eval_wer": 1.0,
|
| 411 |
+
"step": 9600
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 9.04,
|
| 415 |
+
"eval_loss": 3.2781076431274414,
|
| 416 |
+
"eval_runtime": 305.7237,
|
| 417 |
+
"eval_samples_per_second": 36.095,
|
| 418 |
+
"eval_steps_per_second": 1.128,
|
| 419 |
+
"eval_wer": 1.0,
|
| 420 |
+
"step": 9900
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 9.13,
|
| 424 |
+
"learning_rate": 0.0004053191078640924,
|
| 425 |
+
"loss": 3.169,
|
| 426 |
+
"step": 10000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 9.32,
|
| 430 |
+
"eval_loss": 3.2596964836120605,
|
| 431 |
+
"eval_runtime": 306.6385,
|
| 432 |
+
"eval_samples_per_second": 35.987,
|
| 433 |
+
"eval_steps_per_second": 1.125,
|
| 434 |
+
"eval_wer": 1.0,
|
| 435 |
+
"step": 10200
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 9.59,
|
| 439 |
+
"learning_rate": 0.00037380129232256106,
|
| 440 |
+
"loss": 3.1789,
|
| 441 |
+
"step": 10500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 9.59,
|
| 445 |
+
"eval_loss": 3.2585501670837402,
|
| 446 |
+
"eval_runtime": 307.6539,
|
| 447 |
+
"eval_samples_per_second": 35.868,
|
| 448 |
+
"eval_steps_per_second": 1.121,
|
| 449 |
+
"eval_wer": 1.0,
|
| 450 |
+
"step": 10500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 9.86,
|
| 454 |
+
"eval_loss": 3.2689764499664307,
|
| 455 |
+
"eval_runtime": 307.738,
|
| 456 |
+
"eval_samples_per_second": 35.858,
|
| 457 |
+
"eval_steps_per_second": 1.121,
|
| 458 |
+
"eval_wer": 1.0,
|
| 459 |
+
"step": 10800
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.05,
|
| 463 |
+
"learning_rate": 0.0003422834767810298,
|
| 464 |
+
"loss": 3.1701,
|
| 465 |
+
"step": 11000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 10.14,
|
| 469 |
+
"eval_loss": 3.273723602294922,
|
| 470 |
+
"eval_runtime": 308.5346,
|
| 471 |
+
"eval_samples_per_second": 35.766,
|
| 472 |
+
"eval_steps_per_second": 1.118,
|
| 473 |
+
"eval_wer": 1.0,
|
| 474 |
+
"step": 11100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.41,
|
| 478 |
+
"eval_loss": 3.273848533630371,
|
| 479 |
+
"eval_runtime": 308.8614,
|
| 480 |
+
"eval_samples_per_second": 35.728,
|
| 481 |
+
"eval_steps_per_second": 1.117,
|
| 482 |
+
"eval_wer": 1.0,
|
| 483 |
+
"step": 11400
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 10.5,
|
| 487 |
+
"learning_rate": 0.00031076566123949855,
|
| 488 |
+
"loss": 3.1698,
|
| 489 |
+
"step": 11500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 10.68,
|
| 493 |
+
"eval_loss": 3.2595293521881104,
|
| 494 |
+
"eval_runtime": 308.7628,
|
| 495 |
+
"eval_samples_per_second": 35.739,
|
| 496 |
+
"eval_steps_per_second": 1.117,
|
| 497 |
+
"eval_wer": 1.0,
|
| 498 |
+
"step": 11700
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 10.96,
|
| 502 |
+
"learning_rate": 0.00027924784569796727,
|
| 503 |
+
"loss": 3.1595,
|
| 504 |
+
"step": 12000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 10.96,
|
| 508 |
+
"eval_loss": 3.2467362880706787,
|
| 509 |
+
"eval_runtime": 308.3094,
|
| 510 |
+
"eval_samples_per_second": 35.792,
|
| 511 |
+
"eval_steps_per_second": 1.119,
|
| 512 |
+
"eval_wer": 1.0,
|
| 513 |
+
"step": 12000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 11.23,
|
| 517 |
+
"eval_loss": 3.252420663833618,
|
| 518 |
+
"eval_runtime": 309.0904,
|
| 519 |
+
"eval_samples_per_second": 35.702,
|
| 520 |
+
"eval_steps_per_second": 1.116,
|
| 521 |
+
"eval_wer": 1.0,
|
| 522 |
+
"step": 12300
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 11.42,
|
| 526 |
+
"learning_rate": 0.00024773003015643593,
|
| 527 |
+
"loss": 3.15,
|
| 528 |
+
"step": 12500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 11.51,
|
| 532 |
+
"eval_loss": 3.2327377796173096,
|
| 533 |
+
"eval_runtime": 308.9397,
|
| 534 |
+
"eval_samples_per_second": 35.719,
|
| 535 |
+
"eval_steps_per_second": 1.117,
|
| 536 |
+
"eval_wer": 1.0,
|
| 537 |
+
"step": 12600
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 11.78,
|
| 541 |
+
"eval_loss": 3.219557046890259,
|
| 542 |
+
"eval_runtime": 309.2594,
|
| 543 |
+
"eval_samples_per_second": 35.682,
|
| 544 |
+
"eval_steps_per_second": 1.116,
|
| 545 |
+
"eval_wer": 1.0,
|
| 546 |
+
"step": 12900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 11.87,
|
| 550 |
+
"learning_rate": 0.00021621221461490465,
|
| 551 |
+
"loss": 3.1444,
|
| 552 |
+
"step": 13000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 12.05,
|
| 556 |
+
"eval_loss": 3.1942968368530273,
|
| 557 |
+
"eval_runtime": 309.871,
|
| 558 |
+
"eval_samples_per_second": 35.612,
|
| 559 |
+
"eval_steps_per_second": 1.113,
|
| 560 |
+
"eval_wer": 1.0,
|
| 561 |
+
"step": 13200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 12.33,
|
| 565 |
+
"learning_rate": 0.00018469439907337336,
|
| 566 |
+
"loss": 3.132,
|
| 567 |
+
"step": 13500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 12.33,
|
| 571 |
+
"eval_loss": 3.191138744354248,
|
| 572 |
+
"eval_runtime": 309.3206,
|
| 573 |
+
"eval_samples_per_second": 35.675,
|
| 574 |
+
"eval_steps_per_second": 1.115,
|
| 575 |
+
"eval_wer": 1.0,
|
| 576 |
+
"step": 13500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 12.6,
|
| 580 |
+
"eval_loss": 3.207465648651123,
|
| 581 |
+
"eval_runtime": 309.5517,
|
| 582 |
+
"eval_samples_per_second": 35.648,
|
| 583 |
+
"eval_steps_per_second": 1.115,
|
| 584 |
+
"eval_wer": 1.0,
|
| 585 |
+
"step": 13800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 12.79,
|
| 589 |
+
"learning_rate": 0.00015323961916292511,
|
| 590 |
+
"loss": 3.1153,
|
| 591 |
+
"step": 14000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 12.88,
|
| 595 |
+
"eval_loss": 3.1938300132751465,
|
| 596 |
+
"eval_runtime": 310.0376,
|
| 597 |
+
"eval_samples_per_second": 35.592,
|
| 598 |
+
"eval_steps_per_second": 1.113,
|
| 599 |
+
"eval_wer": 1.0,
|
| 600 |
+
"step": 14100
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 13.15,
|
| 604 |
+
"eval_loss": 3.1638731956481934,
|
| 605 |
+
"eval_runtime": 308.9592,
|
| 606 |
+
"eval_samples_per_second": 35.717,
|
| 607 |
+
"eval_steps_per_second": 1.117,
|
| 608 |
+
"eval_wer": 1.0,
|
| 609 |
+
"step": 14400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.24,
|
| 613 |
+
"learning_rate": 0.00012172180362139385,
|
| 614 |
+
"loss": 3.1039,
|
| 615 |
+
"step": 14500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 13.42,
|
| 619 |
+
"eval_loss": 3.15146803855896,
|
| 620 |
+
"eval_runtime": 308.6922,
|
| 621 |
+
"eval_samples_per_second": 35.748,
|
| 622 |
+
"eval_steps_per_second": 1.118,
|
| 623 |
+
"eval_wer": 1.0,
|
| 624 |
+
"step": 14700
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 13.7,
|
| 628 |
+
"learning_rate": 9.020398807986256e-05,
|
| 629 |
+
"loss": 3.0839,
|
| 630 |
+
"step": 15000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 13.7,
|
| 634 |
+
"eval_loss": 3.153453826904297,
|
| 635 |
+
"eval_runtime": 309.1197,
|
| 636 |
+
"eval_samples_per_second": 35.698,
|
| 637 |
+
"eval_steps_per_second": 1.116,
|
| 638 |
+
"eval_wer": 1.0,
|
| 639 |
+
"step": 15000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 13.97,
|
| 643 |
+
"eval_loss": 3.130723237991333,
|
| 644 |
+
"eval_runtime": 309.6167,
|
| 645 |
+
"eval_samples_per_second": 35.641,
|
| 646 |
+
"eval_steps_per_second": 1.114,
|
| 647 |
+
"eval_wer": 1.0,
|
| 648 |
+
"step": 15300
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 14.16,
|
| 652 |
+
"learning_rate": 5.8686172538331265e-05,
|
| 653 |
+
"loss": 3.0632,
|
| 654 |
+
"step": 15500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 14.25,
|
| 658 |
+
"eval_loss": 3.1138317584991455,
|
| 659 |
+
"eval_runtime": 309.4562,
|
| 660 |
+
"eval_samples_per_second": 35.659,
|
| 661 |
+
"eval_steps_per_second": 1.115,
|
| 662 |
+
"eval_wer": 1.0,
|
| 663 |
+
"step": 15600
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 14.52,
|
| 667 |
+
"eval_loss": 3.128912925720215,
|
| 668 |
+
"eval_runtime": 309.4874,
|
| 669 |
+
"eval_samples_per_second": 35.656,
|
| 670 |
+
"eval_steps_per_second": 1.115,
|
| 671 |
+
"eval_wer": 1.0,
|
| 672 |
+
"step": 15900
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 14.61,
|
| 676 |
+
"learning_rate": 2.7168356996799972e-05,
|
| 677 |
+
"loss": 3.0518,
|
| 678 |
+
"step": 16000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 14.79,
|
| 682 |
+
"eval_loss": 3.081491708755493,
|
| 683 |
+
"eval_runtime": 308.8218,
|
| 684 |
+
"eval_samples_per_second": 35.733,
|
| 685 |
+
"eval_steps_per_second": 1.117,
|
| 686 |
+
"eval_wer": 1.0,
|
| 687 |
+
"step": 16200
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 15.0,
|
| 691 |
+
"step": 16425,
|
| 692 |
+
"total_flos": 6.442470243808035e+19,
|
| 693 |
+
"train_loss": 3.3253096312547563,
|
| 694 |
+
"train_runtime": 44962.3834,
|
| 695 |
+
"train_samples_per_second": 14.612,
|
| 696 |
+
"train_steps_per_second": 0.365
|
| 697 |
+
}
|
| 698 |
+
],
|
| 699 |
+
"logging_steps": 500,
|
| 700 |
+
"max_steps": 16425,
|
| 701 |
+
"num_input_tokens_seen": 0,
|
| 702 |
+
"num_train_epochs": 15,
|
| 703 |
+
"save_steps": 400,
|
| 704 |
+
"total_flos": 6.442470243808035e+19,
|
| 705 |
+
"train_batch_size": 20,
|
| 706 |
+
"trial_name": null,
|
| 707 |
+
"trial_params": null
|
| 708 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3c53562aa99723a8907e8c35881be65f8d75203d3001a36991a6ebba0d8857
|
| 3 |
size 4728
|