Training in progress, step 400
Browse files- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/pytorch_model.bin +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scaler.pt +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/trainer_state.json +512 -0
- checkpoint-400/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/May07_17-47-06_bc858596195a/events.out.tfevents.1683481716.bc858596195a.2495.0 +2 -2
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0d0c0a02a8fa485ea52b372606064156c19b1db1720b124f713069b3fd7d97a
|
| 3 |
+
size 25279045
|
checkpoint-400/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abbaba667a6f88a1fb00cdf4223a0724abe2247f2481de4170e08f9c68e41ae2
|
| 3 |
+
size 12653389
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d622581499d6ad6f632b305c1f6612f0f5f7af2475bc34aae66217e3791b0f2
|
| 3 |
+
size 14575
|
checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc40a4be6a52cee4d7658df4041e660ffa02b0d8b5bd143bb8bb397f7b71b1a5
|
| 3 |
+
size 557
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e0f6cba5a7eeb044f70b413fb4ddf47d2810e47484fa10b320a6aa206b4a277
|
| 3 |
+
size 627
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,512 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.207701563835144,
|
| 3 |
+
"best_model_checkpoint": "outputs/checkpoint-400",
|
| 4 |
+
"epoch": 0.128,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 1.8184,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.0,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 1.7858,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.0,
|
| 24 |
+
"learning_rate": 3e-05,
|
| 25 |
+
"loss": 1.7218,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 4e-05,
|
| 31 |
+
"loss": 1.7218,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.01,
|
| 36 |
+
"learning_rate": 5e-05,
|
| 37 |
+
"loss": 1.7009,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01,
|
| 42 |
+
"learning_rate": 6e-05,
|
| 43 |
+
"loss": 1.6714,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"learning_rate": 7e-05,
|
| 49 |
+
"loss": 1.6582,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.01,
|
| 54 |
+
"learning_rate": 8e-05,
|
| 55 |
+
"loss": 1.5659,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.01,
|
| 60 |
+
"learning_rate": 9e-05,
|
| 61 |
+
"loss": 1.5343,
|
| 62 |
+
"step": 45
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.02,
|
| 66 |
+
"learning_rate": 0.0001,
|
| 67 |
+
"loss": 1.5252,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.02,
|
| 72 |
+
"learning_rate": 0.00011000000000000002,
|
| 73 |
+
"loss": 1.414,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.02,
|
| 78 |
+
"learning_rate": 0.00012,
|
| 79 |
+
"loss": 1.3919,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02,
|
| 84 |
+
"learning_rate": 0.00013000000000000002,
|
| 85 |
+
"loss": 1.352,
|
| 86 |
+
"step": 65
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.02,
|
| 90 |
+
"learning_rate": 0.00014,
|
| 91 |
+
"loss": 1.3762,
|
| 92 |
+
"step": 70
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.02,
|
| 96 |
+
"learning_rate": 0.00015000000000000001,
|
| 97 |
+
"loss": 1.3238,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.03,
|
| 102 |
+
"learning_rate": 0.00016,
|
| 103 |
+
"loss": 1.3306,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.03,
|
| 108 |
+
"learning_rate": 0.00017,
|
| 109 |
+
"loss": 1.3423,
|
| 110 |
+
"step": 85
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.03,
|
| 114 |
+
"learning_rate": 0.00018,
|
| 115 |
+
"loss": 1.3199,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.03,
|
| 120 |
+
"learning_rate": 0.00019,
|
| 121 |
+
"loss": 1.3506,
|
| 122 |
+
"step": 95
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 1.3315,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.03,
|
| 132 |
+
"learning_rate": 0.0001998921832884097,
|
| 133 |
+
"loss": 1.3142,
|
| 134 |
+
"step": 105
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.04,
|
| 138 |
+
"learning_rate": 0.00019978436657681943,
|
| 139 |
+
"loss": 1.2994,
|
| 140 |
+
"step": 110
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.04,
|
| 144 |
+
"learning_rate": 0.00019967654986522912,
|
| 145 |
+
"loss": 1.2972,
|
| 146 |
+
"step": 115
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.04,
|
| 150 |
+
"learning_rate": 0.00019956873315363883,
|
| 151 |
+
"loss": 1.3135,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.04,
|
| 156 |
+
"learning_rate": 0.00019946091644204851,
|
| 157 |
+
"loss": 1.2903,
|
| 158 |
+
"step": 125
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.04,
|
| 162 |
+
"learning_rate": 0.00019935309973045823,
|
| 163 |
+
"loss": 1.2783,
|
| 164 |
+
"step": 130
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04,
|
| 168 |
+
"learning_rate": 0.00019924528301886794,
|
| 169 |
+
"loss": 1.3044,
|
| 170 |
+
"step": 135
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04,
|
| 174 |
+
"learning_rate": 0.00019913746630727762,
|
| 175 |
+
"loss": 1.2947,
|
| 176 |
+
"step": 140
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.05,
|
| 180 |
+
"learning_rate": 0.00019902964959568736,
|
| 181 |
+
"loss": 1.2759,
|
| 182 |
+
"step": 145
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.05,
|
| 186 |
+
"learning_rate": 0.00019892183288409705,
|
| 187 |
+
"loss": 1.2746,
|
| 188 |
+
"step": 150
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.05,
|
| 192 |
+
"learning_rate": 0.00019881401617250676,
|
| 193 |
+
"loss": 1.2869,
|
| 194 |
+
"step": 155
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.05,
|
| 198 |
+
"learning_rate": 0.00019870619946091644,
|
| 199 |
+
"loss": 1.26,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.05,
|
| 204 |
+
"learning_rate": 0.00019859838274932616,
|
| 205 |
+
"loss": 1.258,
|
| 206 |
+
"step": 165
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.05,
|
| 210 |
+
"learning_rate": 0.00019849056603773587,
|
| 211 |
+
"loss": 1.2649,
|
| 212 |
+
"step": 170
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06,
|
| 216 |
+
"learning_rate": 0.00019838274932614555,
|
| 217 |
+
"loss": 1.2549,
|
| 218 |
+
"step": 175
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.06,
|
| 222 |
+
"learning_rate": 0.00019827493261455526,
|
| 223 |
+
"loss": 1.2859,
|
| 224 |
+
"step": 180
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.06,
|
| 228 |
+
"learning_rate": 0.00019816711590296498,
|
| 229 |
+
"loss": 1.2934,
|
| 230 |
+
"step": 185
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.06,
|
| 234 |
+
"learning_rate": 0.00019805929919137466,
|
| 235 |
+
"loss": 1.3011,
|
| 236 |
+
"step": 190
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.06,
|
| 240 |
+
"learning_rate": 0.00019795148247978437,
|
| 241 |
+
"loss": 1.2304,
|
| 242 |
+
"step": 195
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.06,
|
| 246 |
+
"learning_rate": 0.00019784366576819408,
|
| 247 |
+
"loss": 1.2849,
|
| 248 |
+
"step": 200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.06,
|
| 252 |
+
"eval_loss": 1.2345943450927734,
|
| 253 |
+
"eval_runtime": 710.2534,
|
| 254 |
+
"eval_samples_per_second": 7.04,
|
| 255 |
+
"eval_steps_per_second": 0.88,
|
| 256 |
+
"step": 200
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.07,
|
| 260 |
+
"learning_rate": 0.0001977358490566038,
|
| 261 |
+
"loss": 1.2726,
|
| 262 |
+
"step": 205
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.07,
|
| 266 |
+
"learning_rate": 0.00019762803234501348,
|
| 267 |
+
"loss": 1.2996,
|
| 268 |
+
"step": 210
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.07,
|
| 272 |
+
"learning_rate": 0.0001975202156334232,
|
| 273 |
+
"loss": 1.2456,
|
| 274 |
+
"step": 215
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.07,
|
| 278 |
+
"learning_rate": 0.0001974123989218329,
|
| 279 |
+
"loss": 1.2794,
|
| 280 |
+
"step": 220
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.07,
|
| 284 |
+
"learning_rate": 0.0001973045822102426,
|
| 285 |
+
"loss": 1.2637,
|
| 286 |
+
"step": 225
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.07,
|
| 290 |
+
"learning_rate": 0.0001971967654986523,
|
| 291 |
+
"loss": 1.252,
|
| 292 |
+
"step": 230
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.08,
|
| 296 |
+
"learning_rate": 0.000197088948787062,
|
| 297 |
+
"loss": 1.2492,
|
| 298 |
+
"step": 235
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.08,
|
| 302 |
+
"learning_rate": 0.0001969811320754717,
|
| 303 |
+
"loss": 1.2972,
|
| 304 |
+
"step": 240
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.08,
|
| 308 |
+
"learning_rate": 0.0001968733153638814,
|
| 309 |
+
"loss": 1.3023,
|
| 310 |
+
"step": 245
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.08,
|
| 314 |
+
"learning_rate": 0.00019676549865229112,
|
| 315 |
+
"loss": 1.2682,
|
| 316 |
+
"step": 250
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.08,
|
| 320 |
+
"learning_rate": 0.00019665768194070083,
|
| 321 |
+
"loss": 1.2981,
|
| 322 |
+
"step": 255
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.08,
|
| 326 |
+
"learning_rate": 0.00019654986522911052,
|
| 327 |
+
"loss": 1.3084,
|
| 328 |
+
"step": 260
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.08,
|
| 332 |
+
"learning_rate": 0.00019644204851752023,
|
| 333 |
+
"loss": 1.2666,
|
| 334 |
+
"step": 265
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.09,
|
| 338 |
+
"learning_rate": 0.00019633423180592994,
|
| 339 |
+
"loss": 1.2623,
|
| 340 |
+
"step": 270
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.09,
|
| 344 |
+
"learning_rate": 0.00019622641509433963,
|
| 345 |
+
"loss": 1.2406,
|
| 346 |
+
"step": 275
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.09,
|
| 350 |
+
"learning_rate": 0.00019611859838274934,
|
| 351 |
+
"loss": 1.2623,
|
| 352 |
+
"step": 280
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.09,
|
| 356 |
+
"learning_rate": 0.00019601078167115905,
|
| 357 |
+
"loss": 1.2562,
|
| 358 |
+
"step": 285
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.09,
|
| 362 |
+
"learning_rate": 0.00019590296495956873,
|
| 363 |
+
"loss": 1.2166,
|
| 364 |
+
"step": 290
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.09,
|
| 368 |
+
"learning_rate": 0.00019579514824797845,
|
| 369 |
+
"loss": 1.2931,
|
| 370 |
+
"step": 295
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.1,
|
| 374 |
+
"learning_rate": 0.00019568733153638813,
|
| 375 |
+
"loss": 1.2354,
|
| 376 |
+
"step": 300
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.1,
|
| 380 |
+
"learning_rate": 0.00019557951482479787,
|
| 381 |
+
"loss": 1.2246,
|
| 382 |
+
"step": 305
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.1,
|
| 386 |
+
"learning_rate": 0.00019547169811320755,
|
| 387 |
+
"loss": 1.2236,
|
| 388 |
+
"step": 310
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.1,
|
| 392 |
+
"learning_rate": 0.00019536388140161727,
|
| 393 |
+
"loss": 1.2442,
|
| 394 |
+
"step": 315
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1,
|
| 398 |
+
"learning_rate": 0.00019525606469002698,
|
| 399 |
+
"loss": 1.2779,
|
| 400 |
+
"step": 320
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.1,
|
| 404 |
+
"learning_rate": 0.00019514824797843666,
|
| 405 |
+
"loss": 1.2285,
|
| 406 |
+
"step": 325
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.11,
|
| 410 |
+
"learning_rate": 0.00019504043126684637,
|
| 411 |
+
"loss": 1.2157,
|
| 412 |
+
"step": 330
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.11,
|
| 416 |
+
"learning_rate": 0.00019493261455525606,
|
| 417 |
+
"loss": 1.2405,
|
| 418 |
+
"step": 335
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.11,
|
| 422 |
+
"learning_rate": 0.0001948247978436658,
|
| 423 |
+
"loss": 1.2335,
|
| 424 |
+
"step": 340
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.11,
|
| 428 |
+
"learning_rate": 0.00019471698113207548,
|
| 429 |
+
"loss": 1.2401,
|
| 430 |
+
"step": 345
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.11,
|
| 434 |
+
"learning_rate": 0.00019460916442048517,
|
| 435 |
+
"loss": 1.2521,
|
| 436 |
+
"step": 350
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.11,
|
| 440 |
+
"learning_rate": 0.0001945013477088949,
|
| 441 |
+
"loss": 1.2386,
|
| 442 |
+
"step": 355
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.12,
|
| 446 |
+
"learning_rate": 0.0001943935309973046,
|
| 447 |
+
"loss": 1.2196,
|
| 448 |
+
"step": 360
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.12,
|
| 452 |
+
"learning_rate": 0.0001942857142857143,
|
| 453 |
+
"loss": 1.192,
|
| 454 |
+
"step": 365
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.12,
|
| 458 |
+
"learning_rate": 0.000194177897574124,
|
| 459 |
+
"loss": 1.1964,
|
| 460 |
+
"step": 370
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.12,
|
| 464 |
+
"learning_rate": 0.0001940700808625337,
|
| 465 |
+
"loss": 1.2876,
|
| 466 |
+
"step": 375
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.12,
|
| 470 |
+
"learning_rate": 0.0001939622641509434,
|
| 471 |
+
"loss": 1.2622,
|
| 472 |
+
"step": 380
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.12,
|
| 476 |
+
"learning_rate": 0.0001938544474393531,
|
| 477 |
+
"loss": 1.2183,
|
| 478 |
+
"step": 385
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.12,
|
| 482 |
+
"learning_rate": 0.00019374663072776284,
|
| 483 |
+
"loss": 1.206,
|
| 484 |
+
"step": 390
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.13,
|
| 488 |
+
"learning_rate": 0.00019363881401617252,
|
| 489 |
+
"loss": 1.2697,
|
| 490 |
+
"step": 395
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.13,
|
| 494 |
+
"learning_rate": 0.0001935309973045822,
|
| 495 |
+
"loss": 1.2515,
|
| 496 |
+
"step": 400
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.13,
|
| 500 |
+
"eval_loss": 1.207701563835144,
|
| 501 |
+
"eval_runtime": 709.7794,
|
| 502 |
+
"eval_samples_per_second": 7.044,
|
| 503 |
+
"eval_steps_per_second": 0.881,
|
| 504 |
+
"step": 400
|
| 505 |
+
}
|
| 506 |
+
],
|
| 507 |
+
"max_steps": 9375,
|
| 508 |
+
"num_train_epochs": 3,
|
| 509 |
+
"total_flos": 2.38239419990016e+16,
|
| 510 |
+
"trial_name": null,
|
| 511 |
+
"trial_params": null
|
| 512 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37558cbc88ba261791fbfa1f320a80e38b6c62c51b94e8ff0512ef16db3ba9ad
|
| 3 |
+
size 3963
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12653389
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abbaba667a6f88a1fb00cdf4223a0724abe2247f2481de4170e08f9c68e41ae2
|
| 3 |
size 12653389
|
runs/May07_17-47-06_bc858596195a/events.out.tfevents.1683481716.bc858596195a.2495.0
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 sha256:36ce865e4896a4c5642df27a505af913332ac10545b96cc03968dac864c4f1ca
|
| 3 |
+
size 17282
|