Model save
Browse files- README.md +1 -1
- all_results.json +13 -0
- config.json +8 -10
- eval_results.json +8 -0
- model.safetensors +2 -2
- runs/Dec13_16-35-05_13fe3db568b1/events.out.tfevents.1702485564.13fe3db568b1.2192.1 +3 -0
- runs/Dec13_16-46-11_13fe3db568b1/events.out.tfevents.1702485976.13fe3db568b1.2192.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +358 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 4
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.8812949640287769,
|
| 4 |
+
"eval_loss": 0.4103582799434662,
|
| 5 |
+
"eval_runtime": 15.1855,
|
| 6 |
+
"eval_samples_per_second": 73.228,
|
| 7 |
+
"eval_steps_per_second": 9.153,
|
| 8 |
+
"total_flos": 6.887981879958897e+17,
|
| 9 |
+
"train_loss": 0.8073481788738168,
|
| 10 |
+
"train_runtime": 211.1785,
|
| 11 |
+
"train_samples_per_second": 42.088,
|
| 12 |
+
"train_steps_per_second": 2.633
|
| 13 |
+
}
|
config.json
CHANGED
|
@@ -14,11 +14,10 @@
|
|
| 14 |
"2": "country",
|
| 15 |
"3": "disco",
|
| 16 |
"4": "hiphop",
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "rock"
|
| 22 |
},
|
| 23 |
"image_size": 224,
|
| 24 |
"initializer_range": 0.02,
|
|
@@ -29,11 +28,10 @@
|
|
| 29 |
"country": "2",
|
| 30 |
"disco": "3",
|
| 31 |
"hiphop": "4",
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"rock": "9"
|
| 37 |
},
|
| 38 |
"layer_norm_eps": 1e-12,
|
| 39 |
"model_type": "vit",
|
|
|
|
| 14 |
"2": "country",
|
| 15 |
"3": "disco",
|
| 16 |
"4": "hiphop",
|
| 17 |
+
"5": "metal",
|
| 18 |
+
"6": "pop",
|
| 19 |
+
"7": "reggae",
|
| 20 |
+
"8": "rock"
|
|
|
|
| 21 |
},
|
| 22 |
"image_size": 224,
|
| 23 |
"initializer_range": 0.02,
|
|
|
|
| 28 |
"country": "2",
|
| 29 |
"disco": "3",
|
| 30 |
"hiphop": "4",
|
| 31 |
+
"metal": "5",
|
| 32 |
+
"pop": "6",
|
| 33 |
+
"reggae": "7",
|
| 34 |
+
"rock": "8"
|
|
|
|
| 35 |
},
|
| 36 |
"layer_norm_eps": 1e-12,
|
| 37 |
"model_type": "vit",
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.8812949640287769,
|
| 4 |
+
"eval_loss": 0.4103582799434662,
|
| 5 |
+
"eval_runtime": 15.1855,
|
| 6 |
+
"eval_samples_per_second": 73.228,
|
| 7 |
+
"eval_steps_per_second": 9.153
|
| 8 |
+
}
|
model.safetensors
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 sha256:00b1d2b573d535dfc63daa9455538004fae4c4fb3a4417efbabba67fbfa6b2e3
|
| 3 |
+
size 343245508
|
runs/Dec13_16-35-05_13fe3db568b1/events.out.tfevents.1702485564.13fe3db568b1.2192.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ed95f41aa471731461f250714cd19edb900a0af9896ae2ce78f956d2037eb8
|
| 3 |
+
size 411
|
runs/Dec13_16-46-11_13fe3db568b1/events.out.tfevents.1702485976.13fe3db568b1.2192.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa710440375e94b1a33a74e50ee6042553ad61c680ff877ac2cfb56d8ff12fd
|
| 3 |
+
size 21701
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 6.887981879958897e+17,
|
| 4 |
+
"train_loss": 0.8073481788738168,
|
| 5 |
+
"train_runtime": 211.1785,
|
| 6 |
+
"train_samples_per_second": 42.088,
|
| 7 |
+
"train_steps_per_second": 2.633
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,358 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 3000,
|
| 6 |
+
"global_step": 556,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 0.00019640287769784174,
|
| 14 |
+
"loss": 2.1468,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 0.00019280575539568347,
|
| 20 |
+
"loss": 1.9709,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 0.00018920863309352518,
|
| 26 |
+
"loss": 1.8468,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.14,
|
| 31 |
+
"learning_rate": 0.0001856115107913669,
|
| 32 |
+
"loss": 1.6942,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.18,
|
| 37 |
+
"learning_rate": 0.00018201438848920864,
|
| 38 |
+
"loss": 1.4989,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.22,
|
| 43 |
+
"learning_rate": 0.00017841726618705037,
|
| 44 |
+
"loss": 1.3514,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.25,
|
| 49 |
+
"learning_rate": 0.0001748201438848921,
|
| 50 |
+
"loss": 1.3165,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.29,
|
| 55 |
+
"learning_rate": 0.00017122302158273383,
|
| 56 |
+
"loss": 1.2268,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.32,
|
| 61 |
+
"learning_rate": 0.00016762589928057554,
|
| 62 |
+
"loss": 1.3164,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.36,
|
| 67 |
+
"learning_rate": 0.00016402877697841727,
|
| 68 |
+
"loss": 1.3179,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.4,
|
| 73 |
+
"learning_rate": 0.000160431654676259,
|
| 74 |
+
"loss": 1.2648,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.43,
|
| 79 |
+
"learning_rate": 0.00015683453237410073,
|
| 80 |
+
"loss": 1.178,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.47,
|
| 85 |
+
"learning_rate": 0.00015323741007194246,
|
| 86 |
+
"loss": 1.1558,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5,
|
| 91 |
+
"learning_rate": 0.0001496402877697842,
|
| 92 |
+
"loss": 1.0114,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.54,
|
| 97 |
+
"learning_rate": 0.0001460431654676259,
|
| 98 |
+
"loss": 0.8844,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.58,
|
| 103 |
+
"learning_rate": 0.00014244604316546763,
|
| 104 |
+
"loss": 0.9118,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.61,
|
| 109 |
+
"learning_rate": 0.00013884892086330936,
|
| 110 |
+
"loss": 1.0269,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.65,
|
| 115 |
+
"learning_rate": 0.0001352517985611511,
|
| 116 |
+
"loss": 0.9542,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.68,
|
| 121 |
+
"learning_rate": 0.00013165467625899283,
|
| 122 |
+
"loss": 0.8281,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.72,
|
| 127 |
+
"learning_rate": 0.00012805755395683453,
|
| 128 |
+
"loss": 0.8024,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.76,
|
| 133 |
+
"learning_rate": 0.00012446043165467626,
|
| 134 |
+
"loss": 0.8185,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.79,
|
| 139 |
+
"learning_rate": 0.00012086330935251799,
|
| 140 |
+
"loss": 1.099,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.83,
|
| 145 |
+
"learning_rate": 0.00011726618705035972,
|
| 146 |
+
"loss": 0.8726,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.86,
|
| 151 |
+
"learning_rate": 0.00011366906474820144,
|
| 152 |
+
"loss": 0.7907,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.9,
|
| 157 |
+
"learning_rate": 0.00011007194244604317,
|
| 158 |
+
"loss": 0.9099,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.94,
|
| 163 |
+
"learning_rate": 0.0001064748201438849,
|
| 164 |
+
"loss": 0.7301,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.97,
|
| 169 |
+
"learning_rate": 0.00010287769784172662,
|
| 170 |
+
"loss": 0.772,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.01,
|
| 175 |
+
"learning_rate": 9.928057553956835e-05,
|
| 176 |
+
"loss": 0.7936,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.04,
|
| 181 |
+
"learning_rate": 9.568345323741009e-05,
|
| 182 |
+
"loss": 0.6623,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.08,
|
| 187 |
+
"learning_rate": 9.20863309352518e-05,
|
| 188 |
+
"loss": 0.5091,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.12,
|
| 193 |
+
"learning_rate": 8.848920863309353e-05,
|
| 194 |
+
"loss": 0.4996,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.15,
|
| 199 |
+
"learning_rate": 8.489208633093527e-05,
|
| 200 |
+
"loss": 0.5529,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.19,
|
| 205 |
+
"learning_rate": 8.129496402877698e-05,
|
| 206 |
+
"loss": 0.6094,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.22,
|
| 211 |
+
"learning_rate": 7.769784172661872e-05,
|
| 212 |
+
"loss": 0.4422,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.26,
|
| 217 |
+
"learning_rate": 7.410071942446043e-05,
|
| 218 |
+
"loss": 0.4468,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.29,
|
| 223 |
+
"learning_rate": 7.050359712230215e-05,
|
| 224 |
+
"loss": 0.4673,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.33,
|
| 229 |
+
"learning_rate": 6.690647482014388e-05,
|
| 230 |
+
"loss": 0.4746,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.37,
|
| 235 |
+
"learning_rate": 6.366906474820145e-05,
|
| 236 |
+
"loss": 0.4601,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.4,
|
| 241 |
+
"learning_rate": 6.007194244604317e-05,
|
| 242 |
+
"loss": 0.4793,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.44,
|
| 247 |
+
"learning_rate": 5.64748201438849e-05,
|
| 248 |
+
"loss": 0.5919,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.47,
|
| 253 |
+
"learning_rate": 5.287769784172663e-05,
|
| 254 |
+
"loss": 0.4313,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.51,
|
| 259 |
+
"learning_rate": 4.9280575539568345e-05,
|
| 260 |
+
"loss": 0.4715,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.55,
|
| 265 |
+
"learning_rate": 4.5683453237410076e-05,
|
| 266 |
+
"loss": 0.3263,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.58,
|
| 271 |
+
"learning_rate": 4.20863309352518e-05,
|
| 272 |
+
"loss": 0.4526,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.62,
|
| 277 |
+
"learning_rate": 3.8489208633093525e-05,
|
| 278 |
+
"loss": 0.4379,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.65,
|
| 283 |
+
"learning_rate": 3.489208633093525e-05,
|
| 284 |
+
"loss": 0.5083,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.69,
|
| 289 |
+
"learning_rate": 3.129496402877698e-05,
|
| 290 |
+
"loss": 0.5373,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.73,
|
| 295 |
+
"learning_rate": 2.7697841726618706e-05,
|
| 296 |
+
"loss": 0.3303,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.76,
|
| 301 |
+
"learning_rate": 2.4100719424460434e-05,
|
| 302 |
+
"loss": 0.3214,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.8,
|
| 307 |
+
"learning_rate": 2.050359712230216e-05,
|
| 308 |
+
"loss": 0.4343,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.83,
|
| 313 |
+
"learning_rate": 1.6906474820143887e-05,
|
| 314 |
+
"loss": 0.314,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.87,
|
| 319 |
+
"learning_rate": 1.3309352517985613e-05,
|
| 320 |
+
"loss": 0.3727,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.91,
|
| 325 |
+
"learning_rate": 9.71223021582734e-06,
|
| 326 |
+
"loss": 0.2798,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.94,
|
| 331 |
+
"learning_rate": 6.115107913669065e-06,
|
| 332 |
+
"loss": 0.4031,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.98,
|
| 337 |
+
"learning_rate": 2.5179856115107916e-06,
|
| 338 |
+
"loss": 0.3542,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.0,
|
| 343 |
+
"step": 556,
|
| 344 |
+
"total_flos": 6.887981879958897e+17,
|
| 345 |
+
"train_loss": 0.8073481788738168,
|
| 346 |
+
"train_runtime": 211.1785,
|
| 347 |
+
"train_samples_per_second": 42.088,
|
| 348 |
+
"train_steps_per_second": 2.633
|
| 349 |
+
}
|
| 350 |
+
],
|
| 351 |
+
"logging_steps": 10,
|
| 352 |
+
"max_steps": 556,
|
| 353 |
+
"num_train_epochs": 2,
|
| 354 |
+
"save_steps": 3000,
|
| 355 |
+
"total_flos": 6.887981879958897e+17,
|
| 356 |
+
"trial_name": null,
|
| 357 |
+
"trial_params": null
|
| 358 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40e060b246756e077a5b3f9c838cb6a3db0529d1fa52f148322b678deef99e77
|
| 3 |
size 4536
|