Upload 7 files
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +186 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ff9d7bd979f68a4fe58702525d04c0c16f3e9b44b02216fbf2102f130cffe1
|
| 3 |
+
size 33661637
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e46ffb1ef1b7d4061f9f8892541ab0cb47e557733e350b80ff472fb7f2f29faa
|
| 3 |
+
size 16822989
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41d8580f7635059089a007d64bc134302830a39e0142d36d179b3a04077aea76
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f56e2d94fbf475c8ee7bb541a0c78739d0af9b9df1c40b0d2dbe8978e561b1ce
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ea9321a9351156078558d5930b1e4d22d9fefcb1014aef75723c92be857ab9
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7586850523948669,
|
| 3 |
+
"best_model_checkpoint": "experiments/checkpoint-42",
|
| 4 |
+
"epoch": 78.0,
|
| 5 |
+
"global_step": 98,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 4.0,
|
| 12 |
+
"learning_rate": 4.9999999999999996e-05,
|
| 13 |
+
"loss": 0.3998,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 8.0,
|
| 18 |
+
"learning_rate": 9.999999999999999e-05,
|
| 19 |
+
"loss": 0.3916,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 11.0,
|
| 24 |
+
"eval_loss": 1.4091475009918213,
|
| 25 |
+
"eval_runtime": 4.4251,
|
| 26 |
+
"eval_samples_per_second": 2.26,
|
| 27 |
+
"eval_steps_per_second": 0.452,
|
| 28 |
+
"step": 14
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 12.0,
|
| 32 |
+
"learning_rate": 0.00015,
|
| 33 |
+
"loss": 0.3745,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 16.0,
|
| 38 |
+
"learning_rate": 0.00019999999999999998,
|
| 39 |
+
"loss": 0.3387,
|
| 40 |
+
"step": 20
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 20.0,
|
| 44 |
+
"learning_rate": 0.00025,
|
| 45 |
+
"loss": 0.2894,
|
| 46 |
+
"step": 25
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 22.4,
|
| 50 |
+
"eval_loss": 0.8969688415527344,
|
| 51 |
+
"eval_runtime": 4.4836,
|
| 52 |
+
"eval_samples_per_second": 2.23,
|
| 53 |
+
"eval_steps_per_second": 0.446,
|
| 54 |
+
"step": 28
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 24.0,
|
| 58 |
+
"learning_rate": 0.0003,
|
| 59 |
+
"loss": 0.2322,
|
| 60 |
+
"step": 30
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 28.0,
|
| 64 |
+
"learning_rate": 0.00027857142857142854,
|
| 65 |
+
"loss": 0.1964,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 32.0,
|
| 70 |
+
"learning_rate": 0.0002571428571428571,
|
| 71 |
+
"loss": 0.1739,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 34.0,
|
| 76 |
+
"eval_loss": 0.7586850523948669,
|
| 77 |
+
"eval_runtime": 4.4178,
|
| 78 |
+
"eval_samples_per_second": 2.264,
|
| 79 |
+
"eval_steps_per_second": 0.453,
|
| 80 |
+
"step": 42
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 36.0,
|
| 84 |
+
"learning_rate": 0.00023571428571428569,
|
| 85 |
+
"loss": 0.157,
|
| 86 |
+
"step": 45
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 40.0,
|
| 90 |
+
"learning_rate": 0.00021428571428571427,
|
| 91 |
+
"loss": 0.1408,
|
| 92 |
+
"step": 50
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 44.0,
|
| 96 |
+
"learning_rate": 0.00019285714285714286,
|
| 97 |
+
"loss": 0.1264,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 44.8,
|
| 102 |
+
"eval_loss": 0.7922688126564026,
|
| 103 |
+
"eval_runtime": 4.4244,
|
| 104 |
+
"eval_samples_per_second": 2.26,
|
| 105 |
+
"eval_steps_per_second": 0.452,
|
| 106 |
+
"step": 56
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 48.0,
|
| 110 |
+
"learning_rate": 0.0001714285714285714,
|
| 111 |
+
"loss": 0.1134,
|
| 112 |
+
"step": 60
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 52.0,
|
| 116 |
+
"learning_rate": 0.00015,
|
| 117 |
+
"loss": 0.1021,
|
| 118 |
+
"step": 65
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 56.0,
|
| 122 |
+
"learning_rate": 0.00012857142857142855,
|
| 123 |
+
"loss": 0.0893,
|
| 124 |
+
"step": 70
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 56.0,
|
| 128 |
+
"eval_loss": 0.8863828778266907,
|
| 129 |
+
"eval_runtime": 4.4142,
|
| 130 |
+
"eval_samples_per_second": 2.265,
|
| 131 |
+
"eval_steps_per_second": 0.453,
|
| 132 |
+
"step": 70
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 60.0,
|
| 136 |
+
"learning_rate": 0.00010714285714285714,
|
| 137 |
+
"loss": 0.0778,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 64.0,
|
| 142 |
+
"learning_rate": 8.57142857142857e-05,
|
| 143 |
+
"loss": 0.0677,
|
| 144 |
+
"step": 80
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 67.2,
|
| 148 |
+
"eval_loss": 1.0279890298843384,
|
| 149 |
+
"eval_runtime": 4.4181,
|
| 150 |
+
"eval_samples_per_second": 2.263,
|
| 151 |
+
"eval_steps_per_second": 0.453,
|
| 152 |
+
"step": 84
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 68.0,
|
| 156 |
+
"learning_rate": 6.428571428571427e-05,
|
| 157 |
+
"loss": 0.0598,
|
| 158 |
+
"step": 85
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 72.0,
|
| 162 |
+
"learning_rate": 4.285714285714285e-05,
|
| 163 |
+
"loss": 0.0524,
|
| 164 |
+
"step": 90
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 76.0,
|
| 168 |
+
"learning_rate": 2.1428571428571425e-05,
|
| 169 |
+
"loss": 0.0474,
|
| 170 |
+
"step": 95
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 78.0,
|
| 174 |
+
"eval_loss": 1.1172549724578857,
|
| 175 |
+
"eval_runtime": 4.4004,
|
| 176 |
+
"eval_samples_per_second": 2.273,
|
| 177 |
+
"eval_steps_per_second": 0.455,
|
| 178 |
+
"step": 98
|
| 179 |
+
}
|
| 180 |
+
],
|
| 181 |
+
"max_steps": 100,
|
| 182 |
+
"num_train_epochs": 100,
|
| 183 |
+
"total_flos": 6.335270841090048e+16,
|
| 184 |
+
"trial_name": null,
|
| 185 |
+
"trial_params": null
|
| 186 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a730d8bc8fa50a7ac7ab133876f167a354a5dcc0a044229b70f3d06a335eca50
|
| 3 |
+
size 3899
|