Training in progress, epoch 1
Browse files- all_results.json +8 -0
- confusion_matrix.jpg +0 -0
- model.safetensors +1 -1
- runs/Aug11_13-22-52_prod3/events.out.tfevents.1754890678.prod3.730045.1 +3 -0
- runs/Aug11_13-45-55_prod3/events.out.tfevents.1754891163.prod3.753305.0 +3 -0
- test_results.json +8 -0
- trainer_state.json +395 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.142857142857143,
|
| 3 |
+
"eval_accuracy": 0.7804878048780488,
|
| 4 |
+
"eval_loss": 1.077329158782959,
|
| 5 |
+
"eval_runtime": 5.6706,
|
| 6 |
+
"eval_samples_per_second": 14.461,
|
| 7 |
+
"eval_steps_per_second": 3.703
|
| 8 |
+
}
|
confusion_matrix.jpg
CHANGED
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344952716
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c7b5d0cb1d714a52696a8ff0f6dc1293167be17242fb1b444307772c973ad9
|
| 3 |
size 344952716
|
runs/Aug11_13-22-52_prod3/events.out.tfevents.1754890678.prod3.730045.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a72647c4ece89c4638cf84c0ef336f15a835e947a7591c59a84e5e9a6945ec16
|
| 3 |
+
size 411
|
runs/Aug11_13-45-55_prod3/events.out.tfevents.1754891163.prod3.753305.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c2c7e858cddad8e172f12987e7e173a48429d302a8207374e46ace10fec806
|
| 3 |
+
size 8424
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.142857142857143,
|
| 3 |
+
"eval_accuracy": 0.7804878048780488,
|
| 4 |
+
"eval_loss": 1.077329158782959,
|
| 5 |
+
"eval_runtime": 5.6706,
|
| 6 |
+
"eval_samples_per_second": 14.461,
|
| 7 |
+
"eval_steps_per_second": 3.703
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,395 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 230,
|
| 3 |
+
"best_metric": 0.7804878048780488,
|
| 4 |
+
"best_model_checkpoint": "./Models/Matcha_clips_224_fintuned_5/checkpoint-230",
|
| 5 |
+
"epoch": 6.142857142857143,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 805,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.024844720496894408,
|
| 14 |
+
"grad_norm": 11.596962928771973,
|
| 15 |
+
"learning_rate": 1.1728395061728396e-05,
|
| 16 |
+
"loss": 1.6871,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.049689440993788817,
|
| 21 |
+
"grad_norm": 15.900735855102539,
|
| 22 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 23 |
+
"loss": 0.9615,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07453416149068323,
|
| 28 |
+
"grad_norm": 4.670846939086914,
|
| 29 |
+
"learning_rate": 3.6419753086419754e-05,
|
| 30 |
+
"loss": 0.5851,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09937888198757763,
|
| 35 |
+
"grad_norm": 6.628495216369629,
|
| 36 |
+
"learning_rate": 4.876543209876544e-05,
|
| 37 |
+
"loss": 0.3508,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12422360248447205,
|
| 42 |
+
"grad_norm": 10.711517333984375,
|
| 43 |
+
"learning_rate": 4.875690607734807e-05,
|
| 44 |
+
"loss": 0.3922,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.14285714285714285,
|
| 49 |
+
"eval_accuracy": 0.7682926829268293,
|
| 50 |
+
"eval_loss": 0.996225118637085,
|
| 51 |
+
"eval_runtime": 6.4019,
|
| 52 |
+
"eval_samples_per_second": 12.809,
|
| 53 |
+
"eval_steps_per_second": 3.28,
|
| 54 |
+
"step": 115
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.0062111801242235,
|
| 58 |
+
"grad_norm": 0.29712462425231934,
|
| 59 |
+
"learning_rate": 4.737569060773481e-05,
|
| 60 |
+
"loss": 0.1851,
|
| 61 |
+
"step": 120
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.031055900621118,
|
| 65 |
+
"grad_norm": 3.168236494064331,
|
| 66 |
+
"learning_rate": 4.599447513812155e-05,
|
| 67 |
+
"loss": 0.1939,
|
| 68 |
+
"step": 140
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0559006211180124,
|
| 72 |
+
"grad_norm": 0.13498322665691376,
|
| 73 |
+
"learning_rate": 4.461325966850829e-05,
|
| 74 |
+
"loss": 0.3082,
|
| 75 |
+
"step": 160
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.0807453416149069,
|
| 79 |
+
"grad_norm": 0.22494107484817505,
|
| 80 |
+
"learning_rate": 4.323204419889503e-05,
|
| 81 |
+
"loss": 0.0559,
|
| 82 |
+
"step": 180
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.1055900621118013,
|
| 86 |
+
"grad_norm": 0.5178938508033752,
|
| 87 |
+
"learning_rate": 4.1850828729281773e-05,
|
| 88 |
+
"loss": 0.2148,
|
| 89 |
+
"step": 200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.1304347826086956,
|
| 93 |
+
"grad_norm": 0.1849067360162735,
|
| 94 |
+
"learning_rate": 4.046961325966851e-05,
|
| 95 |
+
"loss": 0.208,
|
| 96 |
+
"step": 220
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.1428571428571428,
|
| 100 |
+
"eval_accuracy": 0.7804878048780488,
|
| 101 |
+
"eval_loss": 1.0773290395736694,
|
| 102 |
+
"eval_runtime": 6.2229,
|
| 103 |
+
"eval_samples_per_second": 13.177,
|
| 104 |
+
"eval_steps_per_second": 3.375,
|
| 105 |
+
"step": 230
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.012422360248447,
|
| 109 |
+
"grad_norm": 2.8872368335723877,
|
| 110 |
+
"learning_rate": 3.9088397790055245e-05,
|
| 111 |
+
"loss": 0.1527,
|
| 112 |
+
"step": 240
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.0372670807453415,
|
| 116 |
+
"grad_norm": 0.04912768676877022,
|
| 117 |
+
"learning_rate": 3.770718232044199e-05,
|
| 118 |
+
"loss": 0.0707,
|
| 119 |
+
"step": 260
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.062111801242236,
|
| 123 |
+
"grad_norm": 0.0381060354411602,
|
| 124 |
+
"learning_rate": 3.632596685082873e-05,
|
| 125 |
+
"loss": 0.0086,
|
| 126 |
+
"step": 280
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.0869565217391304,
|
| 130 |
+
"grad_norm": 42.93180465698242,
|
| 131 |
+
"learning_rate": 3.4944751381215476e-05,
|
| 132 |
+
"loss": 0.022,
|
| 133 |
+
"step": 300
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.111801242236025,
|
| 137 |
+
"grad_norm": 9.570910453796387,
|
| 138 |
+
"learning_rate": 3.3563535911602215e-05,
|
| 139 |
+
"loss": 0.0579,
|
| 140 |
+
"step": 320
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.1366459627329193,
|
| 144 |
+
"grad_norm": 0.1904195100069046,
|
| 145 |
+
"learning_rate": 3.218232044198895e-05,
|
| 146 |
+
"loss": 0.0868,
|
| 147 |
+
"step": 340
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.142857142857143,
|
| 151 |
+
"eval_accuracy": 0.7317073170731707,
|
| 152 |
+
"eval_loss": 1.2267667055130005,
|
| 153 |
+
"eval_runtime": 6.118,
|
| 154 |
+
"eval_samples_per_second": 13.403,
|
| 155 |
+
"eval_steps_per_second": 3.432,
|
| 156 |
+
"step": 345
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.018633540372671,
|
| 160 |
+
"grad_norm": 0.011533539742231369,
|
| 161 |
+
"learning_rate": 3.0801104972375693e-05,
|
| 162 |
+
"loss": 0.0023,
|
| 163 |
+
"step": 360
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.0434782608695654,
|
| 167 |
+
"grad_norm": 0.018733657896518707,
|
| 168 |
+
"learning_rate": 2.9419889502762433e-05,
|
| 169 |
+
"loss": 0.0034,
|
| 170 |
+
"step": 380
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.0683229813664594,
|
| 174 |
+
"grad_norm": 0.02364545315504074,
|
| 175 |
+
"learning_rate": 2.8038674033149172e-05,
|
| 176 |
+
"loss": 0.0041,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.093167701863354,
|
| 181 |
+
"grad_norm": 0.011309165507555008,
|
| 182 |
+
"learning_rate": 2.6657458563535914e-05,
|
| 183 |
+
"loss": 0.0014,
|
| 184 |
+
"step": 420
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.1180124223602483,
|
| 188 |
+
"grad_norm": 0.01748155988752842,
|
| 189 |
+
"learning_rate": 2.5276243093922653e-05,
|
| 190 |
+
"loss": 0.0042,
|
| 191 |
+
"step": 440
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.142857142857143,
|
| 195 |
+
"grad_norm": 0.025904180482029915,
|
| 196 |
+
"learning_rate": 2.3895027624309393e-05,
|
| 197 |
+
"loss": 0.0032,
|
| 198 |
+
"step": 460
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.142857142857143,
|
| 202 |
+
"eval_accuracy": 0.7317073170731707,
|
| 203 |
+
"eval_loss": 1.3057693243026733,
|
| 204 |
+
"eval_runtime": 6.2762,
|
| 205 |
+
"eval_samples_per_second": 13.065,
|
| 206 |
+
"eval_steps_per_second": 3.346,
|
| 207 |
+
"step": 460
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.024844720496894,
|
| 211 |
+
"grad_norm": 0.04104848951101303,
|
| 212 |
+
"learning_rate": 2.2513812154696135e-05,
|
| 213 |
+
"loss": 0.0012,
|
| 214 |
+
"step": 480
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 4.049689440993789,
|
| 218 |
+
"grad_norm": 0.013835583813488483,
|
| 219 |
+
"learning_rate": 2.1132596685082874e-05,
|
| 220 |
+
"loss": 0.0009,
|
| 221 |
+
"step": 500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.074534161490683,
|
| 225 |
+
"grad_norm": 0.016223575919866562,
|
| 226 |
+
"learning_rate": 1.9751381215469613e-05,
|
| 227 |
+
"loss": 0.001,
|
| 228 |
+
"step": 520
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.099378881987578,
|
| 232 |
+
"grad_norm": 0.010322828777134418,
|
| 233 |
+
"learning_rate": 1.8370165745856356e-05,
|
| 234 |
+
"loss": 0.0008,
|
| 235 |
+
"step": 540
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 4.124223602484472,
|
| 239 |
+
"grad_norm": 0.012116617523133755,
|
| 240 |
+
"learning_rate": 1.6988950276243095e-05,
|
| 241 |
+
"loss": 0.0014,
|
| 242 |
+
"step": 560
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.142857142857143,
|
| 246 |
+
"eval_accuracy": 0.7317073170731707,
|
| 247 |
+
"eval_loss": 1.3161958456039429,
|
| 248 |
+
"eval_runtime": 6.3153,
|
| 249 |
+
"eval_samples_per_second": 12.984,
|
| 250 |
+
"eval_steps_per_second": 3.325,
|
| 251 |
+
"step": 575
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 5.0062111801242235,
|
| 255 |
+
"grad_norm": 0.012491249479353428,
|
| 256 |
+
"learning_rate": 1.5607734806629834e-05,
|
| 257 |
+
"loss": 0.0008,
|
| 258 |
+
"step": 580
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.031055900621118,
|
| 262 |
+
"grad_norm": 0.040033698081970215,
|
| 263 |
+
"learning_rate": 1.4226519337016575e-05,
|
| 264 |
+
"loss": 0.0007,
|
| 265 |
+
"step": 600
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 5.055900621118012,
|
| 269 |
+
"grad_norm": 0.010547437705099583,
|
| 270 |
+
"learning_rate": 1.2845303867403316e-05,
|
| 271 |
+
"loss": 0.0006,
|
| 272 |
+
"step": 620
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.080745341614906,
|
| 276 |
+
"grad_norm": 0.016931477934122086,
|
| 277 |
+
"learning_rate": 1.1464088397790055e-05,
|
| 278 |
+
"loss": 0.0009,
|
| 279 |
+
"step": 640
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.105590062111801,
|
| 283 |
+
"grad_norm": 0.021733667701482773,
|
| 284 |
+
"learning_rate": 1.0082872928176797e-05,
|
| 285 |
+
"loss": 0.0006,
|
| 286 |
+
"step": 660
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 5.130434782608695,
|
| 290 |
+
"grad_norm": 0.053632985800504684,
|
| 291 |
+
"learning_rate": 8.701657458563537e-06,
|
| 292 |
+
"loss": 0.0007,
|
| 293 |
+
"step": 680
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.142857142857143,
|
| 297 |
+
"eval_accuracy": 0.7317073170731707,
|
| 298 |
+
"eval_loss": 1.3207590579986572,
|
| 299 |
+
"eval_runtime": 6.2982,
|
| 300 |
+
"eval_samples_per_second": 13.02,
|
| 301 |
+
"eval_steps_per_second": 3.334,
|
| 302 |
+
"step": 690
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.012422360248447,
|
| 306 |
+
"grad_norm": 0.01116255484521389,
|
| 307 |
+
"learning_rate": 7.320441988950276e-06,
|
| 308 |
+
"loss": 0.0006,
|
| 309 |
+
"step": 700
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.037267080745342,
|
| 313 |
+
"grad_norm": 0.01857682503759861,
|
| 314 |
+
"learning_rate": 5.939226519337017e-06,
|
| 315 |
+
"loss": 0.0006,
|
| 316 |
+
"step": 720
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.062111801242236,
|
| 320 |
+
"grad_norm": 0.010129285044968128,
|
| 321 |
+
"learning_rate": 4.5580110497237574e-06,
|
| 322 |
+
"loss": 0.0006,
|
| 323 |
+
"step": 740
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.086956521739131,
|
| 327 |
+
"grad_norm": 0.007020850665867329,
|
| 328 |
+
"learning_rate": 3.1767955801104974e-06,
|
| 329 |
+
"loss": 0.0006,
|
| 330 |
+
"step": 760
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 6.111801242236025,
|
| 334 |
+
"grad_norm": 0.009550134651362896,
|
| 335 |
+
"learning_rate": 1.7955801104972376e-06,
|
| 336 |
+
"loss": 0.0006,
|
| 337 |
+
"step": 780
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 6.136645962732919,
|
| 341 |
+
"grad_norm": 0.013940293341875076,
|
| 342 |
+
"learning_rate": 4.143646408839779e-07,
|
| 343 |
+
"loss": 0.0007,
|
| 344 |
+
"step": 800
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.142857142857143,
|
| 348 |
+
"eval_accuracy": 0.7317073170731707,
|
| 349 |
+
"eval_loss": 1.3218822479248047,
|
| 350 |
+
"eval_runtime": 6.2549,
|
| 351 |
+
"eval_samples_per_second": 13.11,
|
| 352 |
+
"eval_steps_per_second": 3.357,
|
| 353 |
+
"step": 805
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 6.142857142857143,
|
| 357 |
+
"step": 805,
|
| 358 |
+
"total_flos": 4.012506890622075e+18,
|
| 359 |
+
"train_loss": 0.1384738716829036,
|
| 360 |
+
"train_runtime": 848.1252,
|
| 361 |
+
"train_samples_per_second": 3.797,
|
| 362 |
+
"train_steps_per_second": 0.949
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.142857142857143,
|
| 366 |
+
"eval_accuracy": 0.7804878048780488,
|
| 367 |
+
"eval_loss": 1.077329158782959,
|
| 368 |
+
"eval_runtime": 5.6706,
|
| 369 |
+
"eval_samples_per_second": 14.461,
|
| 370 |
+
"eval_steps_per_second": 3.703,
|
| 371 |
+
"step": 805
|
| 372 |
+
}
|
| 373 |
+
],
|
| 374 |
+
"logging_steps": 20,
|
| 375 |
+
"max_steps": 805,
|
| 376 |
+
"num_input_tokens_seen": 0,
|
| 377 |
+
"num_train_epochs": 9223372036854775807,
|
| 378 |
+
"save_steps": 500,
|
| 379 |
+
"stateful_callbacks": {
|
| 380 |
+
"TrainerControl": {
|
| 381 |
+
"args": {
|
| 382 |
+
"should_epoch_stop": false,
|
| 383 |
+
"should_evaluate": false,
|
| 384 |
+
"should_log": false,
|
| 385 |
+
"should_save": true,
|
| 386 |
+
"should_training_stop": true
|
| 387 |
+
},
|
| 388 |
+
"attributes": {}
|
| 389 |
+
}
|
| 390 |
+
},
|
| 391 |
+
"total_flos": 4.012506890622075e+18,
|
| 392 |
+
"train_batch_size": 4,
|
| 393 |
+
"trial_name": null,
|
| 394 |
+
"trial_params": null
|
| 395 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acfa06c9a4d7a0d20f474dc00057d5fe4ef6648d6c36d35f2ad4dfe9c51a8a7b
|
| 3 |
size 5368
|