Upload 4 files
Browse files- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state (1).json +127 -0
- training_args (1).bin +3 -0
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31eb783d50172b192f343a45701d41cdc4cdedef18c08b3cab6c6ce395503161
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d83cde8dcd8c1d55a89765028f73d5a0a26f3ae49c67d42ae5410a779c0e379c
|
| 3 |
+
size 627
|
trainer_state (1).json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.4065102195306585,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19,
|
| 13 |
+
"learning_rate": 4.8950710741021115e-05,
|
| 14 |
+
"loss": 2.4415,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.38,
|
| 19 |
+
"learning_rate": 4.78993186979561e-05,
|
| 20 |
+
"loss": 1.7099,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.57,
|
| 25 |
+
"learning_rate": 4.684792665489108e-05,
|
| 26 |
+
"loss": 1.4997,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.76,
|
| 31 |
+
"learning_rate": 4.579653461182606e-05,
|
| 32 |
+
"loss": 1.3625,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.95,
|
| 37 |
+
"learning_rate": 4.4745142568761036e-05,
|
| 38 |
+
"loss": 1.2689,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.14,
|
| 43 |
+
"learning_rate": 4.3693750525696025e-05,
|
| 44 |
+
"loss": 1.0546,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.32,
|
| 49 |
+
"learning_rate": 4.264235848263101e-05,
|
| 50 |
+
"loss": 0.9711,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.51,
|
| 55 |
+
"learning_rate": 4.159096643956599e-05,
|
| 56 |
+
"loss": 0.9487,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.7,
|
| 61 |
+
"learning_rate": 4.05416771805871e-05,
|
| 62 |
+
"loss": 0.9202,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.89,
|
| 67 |
+
"learning_rate": 3.949238792160821e-05,
|
| 68 |
+
"loss": 0.8953,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.08,
|
| 73 |
+
"learning_rate": 3.844309866262932e-05,
|
| 74 |
+
"loss": 0.6436,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.27,
|
| 79 |
+
"learning_rate": 3.73917066195643e-05,
|
| 80 |
+
"loss": 0.6361,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.46,
|
| 85 |
+
"learning_rate": 3.6340314576499284e-05,
|
| 86 |
+
"loss": 0.6473,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.65,
|
| 91 |
+
"learning_rate": 3.52910253175204e-05,
|
| 92 |
+
"loss": 0.6383,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.84,
|
| 97 |
+
"learning_rate": 3.423963327445538e-05,
|
| 98 |
+
"loss": 0.6312,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.03,
|
| 103 |
+
"learning_rate": 3.318824123139036e-05,
|
| 104 |
+
"loss": 0.5965,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.22,
|
| 109 |
+
"learning_rate": 3.213684918832535e-05,
|
| 110 |
+
"loss": 0.4106,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.41,
|
| 115 |
+
"learning_rate": 3.1085457145260324e-05,
|
| 116 |
+
"loss": 0.4265,
|
| 117 |
+
"step": 9000
|
| 118 |
+
}
|
| 119 |
+
],
|
| 120 |
+
"logging_steps": 500,
|
| 121 |
+
"max_steps": 23778,
|
| 122 |
+
"num_train_epochs": 9,
|
| 123 |
+
"save_steps": 1000,
|
| 124 |
+
"total_flos": 4.841971331668378e+16,
|
| 125 |
+
"trial_name": null,
|
| 126 |
+
"trial_params": null
|
| 127 |
+
}
|
training_args (1).bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:505116a1dd101c6593ad5d25d5977c6fd401a3d1314c3dfbecd56ca2bf4889a5
|
| 3 |
+
size 4219
|