End of training
Browse files- README.md +5 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +530 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# vit-base-beans
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 17 |
|
| 18 |
# vit-base-beans
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0644
|
| 23 |
+
- Accuracy: 0.9925
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9924812030075187,
|
| 4 |
+
"eval_loss": 0.06443430483341217,
|
| 5 |
+
"eval_runtime": 1.7605,
|
| 6 |
+
"eval_samples_per_second": 75.545,
|
| 7 |
+
"eval_steps_per_second": 9.656,
|
| 8 |
+
"train_loss": 0.21938713550567626,
|
| 9 |
+
"train_runtime": 203.0056,
|
| 10 |
+
"train_samples_per_second": 25.467,
|
| 11 |
+
"train_steps_per_second": 3.202
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9924812030075187,
|
| 4 |
+
"eval_loss": 0.06443430483341217,
|
| 5 |
+
"eval_runtime": 1.7605,
|
| 6 |
+
"eval_samples_per_second": 75.545,
|
| 7 |
+
"eval_steps_per_second": 9.656
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.21938713550567626,
|
| 4 |
+
"train_runtime": 203.0056,
|
| 5 |
+
"train_samples_per_second": 25.467,
|
| 6 |
+
"train_steps_per_second": 3.202
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,530 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.06443430483341217,
|
| 3 |
+
"best_model_checkpoint": "./beans_outputs/checkpoint-520",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 650,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 2.198350429534912,
|
| 14 |
+
"learning_rate": 1.9692307692307696e-05,
|
| 15 |
+
"loss": 1.0245,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15,
|
| 20 |
+
"grad_norm": 1.8455473184585571,
|
| 21 |
+
"learning_rate": 1.9384615384615386e-05,
|
| 22 |
+
"loss": 0.9453,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.23,
|
| 27 |
+
"grad_norm": 2.1065616607666016,
|
| 28 |
+
"learning_rate": 1.907692307692308e-05,
|
| 29 |
+
"loss": 0.8403,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.31,
|
| 34 |
+
"grad_norm": 2.614351749420166,
|
| 35 |
+
"learning_rate": 1.876923076923077e-05,
|
| 36 |
+
"loss": 0.6945,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.38,
|
| 41 |
+
"grad_norm": 4.106573104858398,
|
| 42 |
+
"learning_rate": 1.8461538461538465e-05,
|
| 43 |
+
"loss": 0.6607,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46,
|
| 48 |
+
"grad_norm": 2.129425048828125,
|
| 49 |
+
"learning_rate": 1.8153846153846155e-05,
|
| 50 |
+
"loss": 0.5811,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.54,
|
| 55 |
+
"grad_norm": 1.8207303285598755,
|
| 56 |
+
"learning_rate": 1.784615384615385e-05,
|
| 57 |
+
"loss": 0.5191,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.62,
|
| 62 |
+
"grad_norm": 1.2188501358032227,
|
| 63 |
+
"learning_rate": 1.753846153846154e-05,
|
| 64 |
+
"loss": 0.3937,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.69,
|
| 69 |
+
"grad_norm": 2.4855401515960693,
|
| 70 |
+
"learning_rate": 1.7230769230769234e-05,
|
| 71 |
+
"loss": 0.3523,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.77,
|
| 76 |
+
"grad_norm": 2.9041554927825928,
|
| 77 |
+
"learning_rate": 1.6923076923076924e-05,
|
| 78 |
+
"loss": 0.3669,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.85,
|
| 83 |
+
"grad_norm": 1.978524923324585,
|
| 84 |
+
"learning_rate": 1.6615384615384618e-05,
|
| 85 |
+
"loss": 0.3324,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.92,
|
| 90 |
+
"grad_norm": 2.6394453048706055,
|
| 91 |
+
"learning_rate": 1.630769230769231e-05,
|
| 92 |
+
"loss": 0.2456,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"grad_norm": 11.733540534973145,
|
| 98 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 99 |
+
"loss": 0.2826,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0,
|
| 104 |
+
"eval_accuracy": 0.9624060150375939,
|
| 105 |
+
"eval_loss": 0.21461370587348938,
|
| 106 |
+
"eval_runtime": 1.7023,
|
| 107 |
+
"eval_samples_per_second": 78.132,
|
| 108 |
+
"eval_steps_per_second": 9.987,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.08,
|
| 113 |
+
"grad_norm": 1.2605695724487305,
|
| 114 |
+
"learning_rate": 1.5692307692307693e-05,
|
| 115 |
+
"loss": 0.1986,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.15,
|
| 120 |
+
"grad_norm": 3.18729829788208,
|
| 121 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 122 |
+
"loss": 0.2255,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.23,
|
| 127 |
+
"grad_norm": 1.4626598358154297,
|
| 128 |
+
"learning_rate": 1.5076923076923078e-05,
|
| 129 |
+
"loss": 0.205,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.31,
|
| 134 |
+
"grad_norm": 0.5206894278526306,
|
| 135 |
+
"learning_rate": 1.4769230769230772e-05,
|
| 136 |
+
"loss": 0.2284,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.38,
|
| 141 |
+
"grad_norm": 0.6028104424476624,
|
| 142 |
+
"learning_rate": 1.4461538461538462e-05,
|
| 143 |
+
"loss": 0.2141,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.46,
|
| 148 |
+
"grad_norm": 3.1314830780029297,
|
| 149 |
+
"learning_rate": 1.4153846153846156e-05,
|
| 150 |
+
"loss": 0.1602,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.54,
|
| 155 |
+
"grad_norm": 0.4666638672351837,
|
| 156 |
+
"learning_rate": 1.3846153846153847e-05,
|
| 157 |
+
"loss": 0.259,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.62,
|
| 162 |
+
"grad_norm": 1.2395788431167603,
|
| 163 |
+
"learning_rate": 1.353846153846154e-05,
|
| 164 |
+
"loss": 0.1841,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.69,
|
| 169 |
+
"grad_norm": 2.4894907474517822,
|
| 170 |
+
"learning_rate": 1.3230769230769231e-05,
|
| 171 |
+
"loss": 0.2117,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.77,
|
| 176 |
+
"grad_norm": 1.910448670387268,
|
| 177 |
+
"learning_rate": 1.2923076923076925e-05,
|
| 178 |
+
"loss": 0.1682,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.85,
|
| 183 |
+
"grad_norm": 4.8757429122924805,
|
| 184 |
+
"learning_rate": 1.2615384615384616e-05,
|
| 185 |
+
"loss": 0.2634,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.92,
|
| 190 |
+
"grad_norm": 0.37920522689819336,
|
| 191 |
+
"learning_rate": 1.230769230769231e-05,
|
| 192 |
+
"loss": 0.1402,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.0,
|
| 197 |
+
"grad_norm": 0.3483049273490906,
|
| 198 |
+
"learning_rate": 1.2e-05,
|
| 199 |
+
"loss": 0.1306,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.0,
|
| 204 |
+
"eval_accuracy": 0.9699248120300752,
|
| 205 |
+
"eval_loss": 0.12822628021240234,
|
| 206 |
+
"eval_runtime": 1.6876,
|
| 207 |
+
"eval_samples_per_second": 78.81,
|
| 208 |
+
"eval_steps_per_second": 10.073,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.08,
|
| 213 |
+
"grad_norm": 0.4993837773799896,
|
| 214 |
+
"learning_rate": 1.1692307692307694e-05,
|
| 215 |
+
"loss": 0.0933,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.15,
|
| 220 |
+
"grad_norm": 0.33854740858078003,
|
| 221 |
+
"learning_rate": 1.1384615384615385e-05,
|
| 222 |
+
"loss": 0.1407,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.23,
|
| 227 |
+
"grad_norm": 6.487577438354492,
|
| 228 |
+
"learning_rate": 1.1076923076923079e-05,
|
| 229 |
+
"loss": 0.1207,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.31,
|
| 234 |
+
"grad_norm": 7.572403430938721,
|
| 235 |
+
"learning_rate": 1.076923076923077e-05,
|
| 236 |
+
"loss": 0.139,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.38,
|
| 241 |
+
"grad_norm": 4.639190196990967,
|
| 242 |
+
"learning_rate": 1.0461538461538463e-05,
|
| 243 |
+
"loss": 0.1735,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.46,
|
| 248 |
+
"grad_norm": 0.31310051679611206,
|
| 249 |
+
"learning_rate": 1.0153846153846154e-05,
|
| 250 |
+
"loss": 0.1563,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.54,
|
| 255 |
+
"grad_norm": 6.506566047668457,
|
| 256 |
+
"learning_rate": 9.846153846153848e-06,
|
| 257 |
+
"loss": 0.185,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.62,
|
| 262 |
+
"grad_norm": 1.2759567499160767,
|
| 263 |
+
"learning_rate": 9.53846153846154e-06,
|
| 264 |
+
"loss": 0.0761,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.69,
|
| 269 |
+
"grad_norm": 0.34429147839546204,
|
| 270 |
+
"learning_rate": 9.230769230769232e-06,
|
| 271 |
+
"loss": 0.1355,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.77,
|
| 276 |
+
"grad_norm": 9.9702787399292,
|
| 277 |
+
"learning_rate": 8.923076923076925e-06,
|
| 278 |
+
"loss": 0.1176,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.85,
|
| 283 |
+
"grad_norm": 0.3892934024333954,
|
| 284 |
+
"learning_rate": 8.615384615384617e-06,
|
| 285 |
+
"loss": 0.1507,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.92,
|
| 290 |
+
"grad_norm": 1.1851181983947754,
|
| 291 |
+
"learning_rate": 8.307692307692309e-06,
|
| 292 |
+
"loss": 0.1324,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.0,
|
| 297 |
+
"grad_norm": 0.29040664434432983,
|
| 298 |
+
"learning_rate": 8.000000000000001e-06,
|
| 299 |
+
"loss": 0.1451,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.0,
|
| 304 |
+
"eval_accuracy": 0.9774436090225563,
|
| 305 |
+
"eval_loss": 0.09662821888923645,
|
| 306 |
+
"eval_runtime": 1.7019,
|
| 307 |
+
"eval_samples_per_second": 78.15,
|
| 308 |
+
"eval_steps_per_second": 9.989,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.08,
|
| 313 |
+
"grad_norm": 2.813366174697876,
|
| 314 |
+
"learning_rate": 7.692307692307694e-06,
|
| 315 |
+
"loss": 0.1365,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.15,
|
| 320 |
+
"grad_norm": 6.747802257537842,
|
| 321 |
+
"learning_rate": 7.384615384615386e-06,
|
| 322 |
+
"loss": 0.1604,
|
| 323 |
+
"step": 410
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.23,
|
| 327 |
+
"grad_norm": 8.719525337219238,
|
| 328 |
+
"learning_rate": 7.076923076923078e-06,
|
| 329 |
+
"loss": 0.1448,
|
| 330 |
+
"step": 420
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.31,
|
| 334 |
+
"grad_norm": 0.23202432692050934,
|
| 335 |
+
"learning_rate": 6.76923076923077e-06,
|
| 336 |
+
"loss": 0.0717,
|
| 337 |
+
"step": 430
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.38,
|
| 341 |
+
"grad_norm": 4.157703399658203,
|
| 342 |
+
"learning_rate": 6.461538461538463e-06,
|
| 343 |
+
"loss": 0.1157,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.46,
|
| 348 |
+
"grad_norm": 12.880057334899902,
|
| 349 |
+
"learning_rate": 6.153846153846155e-06,
|
| 350 |
+
"loss": 0.0834,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.54,
|
| 355 |
+
"grad_norm": 5.217643737792969,
|
| 356 |
+
"learning_rate": 5.846153846153847e-06,
|
| 357 |
+
"loss": 0.0972,
|
| 358 |
+
"step": 460
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.62,
|
| 362 |
+
"grad_norm": 8.088122367858887,
|
| 363 |
+
"learning_rate": 5.538461538461539e-06,
|
| 364 |
+
"loss": 0.0788,
|
| 365 |
+
"step": 470
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.69,
|
| 369 |
+
"grad_norm": 0.22004778683185577,
|
| 370 |
+
"learning_rate": 5.230769230769232e-06,
|
| 371 |
+
"loss": 0.0884,
|
| 372 |
+
"step": 480
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.77,
|
| 376 |
+
"grad_norm": 0.21302741765975952,
|
| 377 |
+
"learning_rate": 4.923076923076924e-06,
|
| 378 |
+
"loss": 0.0752,
|
| 379 |
+
"step": 490
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.85,
|
| 383 |
+
"grad_norm": 0.8432028889656067,
|
| 384 |
+
"learning_rate": 4.615384615384616e-06,
|
| 385 |
+
"loss": 0.1344,
|
| 386 |
+
"step": 500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.92,
|
| 390 |
+
"grad_norm": 0.21321173012256622,
|
| 391 |
+
"learning_rate": 4.307692307692308e-06,
|
| 392 |
+
"loss": 0.1274,
|
| 393 |
+
"step": 510
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.0,
|
| 397 |
+
"grad_norm": 0.3039676249027252,
|
| 398 |
+
"learning_rate": 4.000000000000001e-06,
|
| 399 |
+
"loss": 0.0785,
|
| 400 |
+
"step": 520
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.0,
|
| 404 |
+
"eval_accuracy": 0.9924812030075187,
|
| 405 |
+
"eval_loss": 0.06443430483341217,
|
| 406 |
+
"eval_runtime": 1.7085,
|
| 407 |
+
"eval_samples_per_second": 77.845,
|
| 408 |
+
"eval_steps_per_second": 9.95,
|
| 409 |
+
"step": 520
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.08,
|
| 413 |
+
"grad_norm": 8.200630187988281,
|
| 414 |
+
"learning_rate": 3.692307692307693e-06,
|
| 415 |
+
"loss": 0.1003,
|
| 416 |
+
"step": 530
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.15,
|
| 420 |
+
"grad_norm": 1.6478914022445679,
|
| 421 |
+
"learning_rate": 3.384615384615385e-06,
|
| 422 |
+
"loss": 0.1675,
|
| 423 |
+
"step": 540
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.23,
|
| 427 |
+
"grad_norm": 0.3463890254497528,
|
| 428 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 429 |
+
"loss": 0.1522,
|
| 430 |
+
"step": 550
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 4.31,
|
| 434 |
+
"grad_norm": 1.3014988899230957,
|
| 435 |
+
"learning_rate": 2.7692307692307697e-06,
|
| 436 |
+
"loss": 0.0504,
|
| 437 |
+
"step": 560
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.38,
|
| 441 |
+
"grad_norm": 0.3259345591068268,
|
| 442 |
+
"learning_rate": 2.461538461538462e-06,
|
| 443 |
+
"loss": 0.1332,
|
| 444 |
+
"step": 570
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 4.46,
|
| 448 |
+
"grad_norm": 0.2652953565120697,
|
| 449 |
+
"learning_rate": 2.153846153846154e-06,
|
| 450 |
+
"loss": 0.0824,
|
| 451 |
+
"step": 580
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 4.54,
|
| 455 |
+
"grad_norm": 8.841487884521484,
|
| 456 |
+
"learning_rate": 1.8461538461538465e-06,
|
| 457 |
+
"loss": 0.0709,
|
| 458 |
+
"step": 590
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.62,
|
| 462 |
+
"grad_norm": 1.8583545684814453,
|
| 463 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 464 |
+
"loss": 0.0921,
|
| 465 |
+
"step": 600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.69,
|
| 469 |
+
"grad_norm": 5.223345756530762,
|
| 470 |
+
"learning_rate": 1.230769230769231e-06,
|
| 471 |
+
"loss": 0.0869,
|
| 472 |
+
"step": 610
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 4.77,
|
| 476 |
+
"grad_norm": 0.26816922426223755,
|
| 477 |
+
"learning_rate": 9.230769230769232e-07,
|
| 478 |
+
"loss": 0.0808,
|
| 479 |
+
"step": 620
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.85,
|
| 483 |
+
"grad_norm": 0.2151552438735962,
|
| 484 |
+
"learning_rate": 6.153846153846155e-07,
|
| 485 |
+
"loss": 0.0662,
|
| 486 |
+
"step": 630
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 4.92,
|
| 490 |
+
"grad_norm": 0.23172561824321747,
|
| 491 |
+
"learning_rate": 3.0769230769230774e-07,
|
| 492 |
+
"loss": 0.0783,
|
| 493 |
+
"step": 640
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 5.0,
|
| 497 |
+
"grad_norm": 0.5893689393997192,
|
| 498 |
+
"learning_rate": 0.0,
|
| 499 |
+
"loss": 0.1125,
|
| 500 |
+
"step": 650
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.0,
|
| 504 |
+
"eval_accuracy": 0.9774436090225563,
|
| 505 |
+
"eval_loss": 0.07952458411455154,
|
| 506 |
+
"eval_runtime": 1.7098,
|
| 507 |
+
"eval_samples_per_second": 77.786,
|
| 508 |
+
"eval_steps_per_second": 9.943,
|
| 509 |
+
"step": 650
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.0,
|
| 513 |
+
"step": 650,
|
| 514 |
+
"total_flos": 4.006371770595533e+17,
|
| 515 |
+
"train_loss": 0.21938713550567626,
|
| 516 |
+
"train_runtime": 203.0056,
|
| 517 |
+
"train_samples_per_second": 25.467,
|
| 518 |
+
"train_steps_per_second": 3.202
|
| 519 |
+
}
|
| 520 |
+
],
|
| 521 |
+
"logging_steps": 10,
|
| 522 |
+
"max_steps": 650,
|
| 523 |
+
"num_input_tokens_seen": 0,
|
| 524 |
+
"num_train_epochs": 5,
|
| 525 |
+
"save_steps": 500,
|
| 526 |
+
"total_flos": 4.006371770595533e+17,
|
| 527 |
+
"train_batch_size": 8,
|
| 528 |
+
"trial_name": null,
|
| 529 |
+
"trial_params": null
|
| 530 |
+
}
|