Commit
•
2264ca0
1
Parent(s):
6f17b4b
eye_diabetic
Browse files- README.md +15 -15
- all_results.json +10 -10
- eval_results.json +6 -6
- model.safetensors +1 -1
- runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731636336.108ed13fb04b.30.0 +3 -0
- runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731638410.108ed13fb04b.30.1 +3 -0
- runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731640599.108ed13fb04b.30.2 +3 -0
- runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731642705.108ed13fb04b.30.3 +3 -0
- runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731644665.108ed13fb04b.30.4 +3 -0
- train_results.json +4 -4
- trainer_state.json +566 -566
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -24,10 +24,10 @@ model-index:
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
-
value: 0.
|
| 28 |
- name: F1
|
| 29 |
type: f1
|
| 30 |
-
value: 0.
|
| 31 |
---
|
| 32 |
|
| 33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -37,9 +37,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 37 |
|
| 38 |
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
|
| 39 |
It achieves the following results on the evaluation set:
|
| 40 |
-
- Loss: 0.
|
| 41 |
-
- Accuracy: 0.
|
| 42 |
-
- F1: 0.
|
| 43 |
|
| 44 |
## Model description
|
| 45 |
|
|
@@ -73,16 +73,16 @@ The following hyperparameters were used during training:
|
|
| 73 |
|
| 74 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 75 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
|
| 87 |
|
| 88 |
### Framework versions
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
+
value: 0.968
|
| 28 |
- name: F1
|
| 29 |
type: f1
|
| 30 |
+
value: 0.9678344915175675
|
| 31 |
---
|
| 32 |
|
| 33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 37 |
|
| 38 |
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
|
| 39 |
It achieves the following results on the evaluation set:
|
| 40 |
+
- Loss: 0.2262
|
| 41 |
+
- Accuracy: 0.968
|
| 42 |
+
- F1: 0.9678
|
| 43 |
|
| 44 |
## Model description
|
| 45 |
|
|
|
|
| 73 |
|
| 74 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 75 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 76 |
+
| 0.3853 | 1.0 | 250 | 0.4918 | 0.874 | 0.8729 |
|
| 77 |
+
| 0.5345 | 2.0 | 500 | 0.4390 | 0.878 | 0.8771 |
|
| 78 |
+
| 0.4693 | 3.0 | 750 | 0.3857 | 0.88 | 0.8796 |
|
| 79 |
+
| 0.1933 | 4.0 | 1000 | 0.3444 | 0.894 | 0.8948 |
|
| 80 |
+
| 0.3146 | 5.0 | 1250 | 0.2456 | 0.936 | 0.9362 |
|
| 81 |
+
| 0.1832 | 6.0 | 1500 | 0.3369 | 0.924 | 0.9229 |
|
| 82 |
+
| 0.1407 | 7.0 | 1750 | 0.3425 | 0.946 | 0.9454 |
|
| 83 |
+
| 0.1462 | 8.0 | 2000 | 0.2864 | 0.948 | 0.9476 |
|
| 84 |
+
| 0.0905 | 9.0 | 2250 | 0.2177 | 0.956 | 0.9560 |
|
| 85 |
+
| 0.0859 | 10.0 | 2500 | 0.2262 | 0.968 | 0.9678 |
|
| 86 |
|
| 87 |
|
| 88 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime": 8.
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 14.
|
| 9 |
"total_flos": 4.0857422266368e+18,
|
| 10 |
-
"train_loss": 0.
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples_per_second": 21.
|
| 13 |
-
"train_steps_per_second": 1.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.968,
|
| 4 |
+
"eval_f1": 0.9678344915175675,
|
| 5 |
+
"eval_loss": 0.22622914612293243,
|
| 6 |
+
"eval_runtime": 8.6004,
|
| 7 |
+
"eval_samples_per_second": 58.137,
|
| 8 |
+
"eval_steps_per_second": 14.534,
|
| 9 |
"total_flos": 4.0857422266368e+18,
|
| 10 |
+
"train_loss": 0.24487185467481612,
|
| 11 |
+
"train_runtime": 1824.5027,
|
| 12 |
+
"train_samples_per_second": 21.924,
|
| 13 |
+
"train_steps_per_second": 1.37
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime": 8.
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 14.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.968,
|
| 4 |
+
"eval_f1": 0.9678344915175675,
|
| 5 |
+
"eval_loss": 0.22622914612293243,
|
| 6 |
+
"eval_runtime": 8.6004,
|
| 7 |
+
"eval_samples_per_second": 58.137,
|
| 8 |
+
"eval_steps_per_second": 14.534
|
| 9 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346378372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb08b07361d442c58890188b6121742b12ea0f79c43e8f8ce0aa993a90c71753
|
| 3 |
size 346378372
|
runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731636336.108ed13fb04b.30.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:055307af16e8dae911d16ce803b1c5482c6e9ebf2a46afb489ed8b8ac7c70c78
|
| 3 |
+
size 62160
|
runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731638410.108ed13fb04b.30.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d90f16063c2622fe39bd9bf5f0495117b1e557844dce662124d3212543209981
|
| 3 |
+
size 62226
|
runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731640599.108ed13fb04b.30.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b53fb0ae6722b140f7a356b3798bd2006a4aaeec7e0c23405850af6b62a0dec2
|
| 3 |
+
size 62226
|
runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731642705.108ed13fb04b.30.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f406354f01b53aac47e8d860f6c4218561bfc77e9a804c32aebedc28e5bd6c32
|
| 3 |
+
size 62226
|
runs/Nov15_02-02-31_108ed13fb04b/events.out.tfevents.1731644665.108ed13fb04b.30.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a00a821a9c7ad8228562c188e57eb9f9368bd5b1671571caa759e208d7773f04
|
| 3 |
+
size 457
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 4.0857422266368e+18,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 21.
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 4.0857422266368e+18,
|
| 4 |
+
"train_loss": 0.24487185467481612,
|
| 5 |
+
"train_runtime": 1824.5027,
|
| 6 |
+
"train_samples_per_second": 21.924,
|
| 7 |
+
"train_steps_per_second": 1.37
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "dinov2-base-finetuned-eye/checkpoint-
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2500,
|
|
@@ -10,1862 +10,1862 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 8.000000000000001e-07,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.08,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 1.6000000000000001e-06,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.12,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 2.4000000000000003e-06,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.16,
|
| 34 |
-
"grad_norm":
|
| 35 |
"learning_rate": 3.2000000000000003e-06,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.2,
|
| 41 |
-
"grad_norm":
|
| 42 |
"learning_rate": 4.000000000000001e-06,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.24,
|
| 48 |
-
"grad_norm":
|
| 49 |
"learning_rate": 4.800000000000001e-06,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.28,
|
| 55 |
-
"grad_norm":
|
| 56 |
"learning_rate": 5.600000000000001e-06,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.32,
|
| 62 |
-
"grad_norm":
|
| 63 |
"learning_rate": 6.4000000000000006e-06,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.36,
|
| 69 |
-
"grad_norm":
|
| 70 |
"learning_rate": 7.2000000000000005e-06,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.4,
|
| 76 |
-
"grad_norm":
|
| 77 |
"learning_rate": 8.000000000000001e-06,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.44,
|
| 83 |
-
"grad_norm":
|
| 84 |
"learning_rate": 8.8e-06,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.48,
|
| 90 |
-
"grad_norm":
|
| 91 |
"learning_rate": 9.600000000000001e-06,
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.52,
|
| 97 |
-
"grad_norm":
|
| 98 |
"learning_rate": 1.04e-05,
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.56,
|
| 104 |
-
"grad_norm":
|
| 105 |
"learning_rate": 1.1200000000000001e-05,
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.6,
|
| 111 |
-
"grad_norm":
|
| 112 |
"learning_rate": 1.2e-05,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.64,
|
| 118 |
-
"grad_norm":
|
| 119 |
"learning_rate": 1.2800000000000001e-05,
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.68,
|
| 125 |
-
"grad_norm":
|
| 126 |
"learning_rate": 1.3600000000000002e-05,
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.72,
|
| 132 |
-
"grad_norm":
|
| 133 |
"learning_rate": 1.4400000000000001e-05,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.76,
|
| 139 |
-
"grad_norm":
|
| 140 |
"learning_rate": 1.5200000000000002e-05,
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.8,
|
| 146 |
-
"grad_norm":
|
| 147 |
"learning_rate": 1.6000000000000003e-05,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.84,
|
| 153 |
-
"grad_norm":
|
| 154 |
"learning_rate": 1.6800000000000002e-05,
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.88,
|
| 160 |
-
"grad_norm":
|
| 161 |
"learning_rate": 1.76e-05,
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.92,
|
| 167 |
-
"grad_norm":
|
| 168 |
"learning_rate": 1.8400000000000003e-05,
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.96,
|
| 174 |
-
"grad_norm":
|
| 175 |
"learning_rate": 1.9200000000000003e-05,
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 1.0,
|
| 181 |
-
"grad_norm":
|
| 182 |
"learning_rate": 2e-05,
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 1.0,
|
| 188 |
-
"eval_accuracy": 0.
|
| 189 |
-
"eval_f1": 0.
|
| 190 |
-
"eval_loss": 0.
|
| 191 |
-
"eval_runtime": 8.
|
| 192 |
-
"eval_samples_per_second": 57.
|
| 193 |
-
"eval_steps_per_second": 14.
|
| 194 |
"step": 250
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 1.04,
|
| 198 |
-
"grad_norm":
|
| 199 |
"learning_rate": 1.9911111111111112e-05,
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 260
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 1.08,
|
| 205 |
-
"grad_norm":
|
| 206 |
"learning_rate": 1.9822222222222226e-05,
|
| 207 |
-
"loss": 0.
|
| 208 |
"step": 270
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"epoch": 1.12,
|
| 212 |
-
"grad_norm":
|
| 213 |
"learning_rate": 1.9733333333333336e-05,
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 280
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 1.16,
|
| 219 |
-
"grad_norm":
|
| 220 |
"learning_rate": 1.9644444444444447e-05,
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 290
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 1.2,
|
| 226 |
-
"grad_norm":
|
| 227 |
"learning_rate": 1.9555555555555557e-05,
|
| 228 |
-
"loss": 0.
|
| 229 |
"step": 300
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 1.24,
|
| 233 |
-
"grad_norm":
|
| 234 |
"learning_rate": 1.9466666666666668e-05,
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 310
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 1.28,
|
| 240 |
-
"grad_norm":
|
| 241 |
"learning_rate": 1.9377777777777778e-05,
|
| 242 |
-
"loss": 0.
|
| 243 |
"step": 320
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 1.32,
|
| 247 |
-
"grad_norm":
|
| 248 |
"learning_rate": 1.928888888888889e-05,
|
| 249 |
-
"loss": 0.
|
| 250 |
"step": 330
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 1.3599999999999999,
|
| 254 |
-
"grad_norm":
|
| 255 |
"learning_rate": 1.9200000000000003e-05,
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 340
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 1.4,
|
| 261 |
-
"grad_norm": 44.
|
| 262 |
"learning_rate": 1.9111111111111113e-05,
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 350
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 1.44,
|
| 268 |
-
"grad_norm":
|
| 269 |
"learning_rate": 1.9022222222222223e-05,
|
| 270 |
-
"loss": 0.
|
| 271 |
"step": 360
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 1.48,
|
| 275 |
-
"grad_norm":
|
| 276 |
"learning_rate": 1.8933333333333334e-05,
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 370
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 1.52,
|
| 282 |
-
"grad_norm":
|
| 283 |
"learning_rate": 1.8844444444444444e-05,
|
| 284 |
-
"loss": 0.
|
| 285 |
"step": 380
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 1.56,
|
| 289 |
-
"grad_norm":
|
| 290 |
"learning_rate": 1.8755555555555558e-05,
|
| 291 |
-
"loss": 0.
|
| 292 |
"step": 390
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 1.6,
|
| 296 |
-
"grad_norm":
|
| 297 |
"learning_rate": 1.866666666666667e-05,
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 400
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 1.6400000000000001,
|
| 303 |
-
"grad_norm":
|
| 304 |
"learning_rate": 1.857777777777778e-05,
|
| 305 |
-
"loss": 0.
|
| 306 |
"step": 410
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 1.6800000000000002,
|
| 310 |
-
"grad_norm":
|
| 311 |
"learning_rate": 1.848888888888889e-05,
|
| 312 |
-
"loss": 0.
|
| 313 |
"step": 420
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 1.72,
|
| 317 |
-
"grad_norm":
|
| 318 |
"learning_rate": 1.8400000000000003e-05,
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 430
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 1.76,
|
| 324 |
-
"grad_norm":
|
| 325 |
"learning_rate": 1.8311111111111114e-05,
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 440
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 1.8,
|
| 331 |
-
"grad_norm":
|
| 332 |
"learning_rate": 1.8222222222222224e-05,
|
| 333 |
-
"loss": 0.
|
| 334 |
"step": 450
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 1.8399999999999999,
|
| 338 |
-
"grad_norm":
|
| 339 |
"learning_rate": 1.8133333333333335e-05,
|
| 340 |
-
"loss": 0.
|
| 341 |
"step": 460
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 1.88,
|
| 345 |
-
"grad_norm":
|
| 346 |
"learning_rate": 1.8044444444444445e-05,
|
| 347 |
-
"loss": 0.
|
| 348 |
"step": 470
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 1.92,
|
| 352 |
-
"grad_norm":
|
| 353 |
"learning_rate": 1.7955555555555556e-05,
|
| 354 |
-
"loss": 0.
|
| 355 |
"step": 480
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 1.96,
|
| 359 |
-
"grad_norm":
|
| 360 |
"learning_rate": 1.7866666666666666e-05,
|
| 361 |
-
"loss": 0.
|
| 362 |
"step": 490
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 2.0,
|
| 366 |
-
"grad_norm":
|
| 367 |
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
-
"loss": 0.
|
| 369 |
"step": 500
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 2.0,
|
| 373 |
-
"eval_accuracy": 0.
|
| 374 |
-
"eval_f1": 0.
|
| 375 |
-
"eval_loss": 0.
|
| 376 |
-
"eval_runtime": 8.
|
| 377 |
-
"eval_samples_per_second": 57.
|
| 378 |
-
"eval_steps_per_second": 14.
|
| 379 |
"step": 500
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 2.04,
|
| 383 |
-
"grad_norm":
|
| 384 |
"learning_rate": 1.768888888888889e-05,
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 510
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 2.08,
|
| 390 |
-
"grad_norm":
|
| 391 |
"learning_rate": 1.76e-05,
|
| 392 |
-
"loss": 0.
|
| 393 |
"step": 520
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 2.12,
|
| 397 |
-
"grad_norm":
|
| 398 |
"learning_rate": 1.751111111111111e-05,
|
| 399 |
-
"loss": 0.
|
| 400 |
"step": 530
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 2.16,
|
| 404 |
-
"grad_norm":
|
| 405 |
"learning_rate": 1.7422222222222222e-05,
|
| 406 |
-
"loss": 0.
|
| 407 |
"step": 540
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 2.2,
|
| 411 |
-
"grad_norm":
|
| 412 |
"learning_rate": 1.7333333333333336e-05,
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 550
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 2.24,
|
| 418 |
-
"grad_norm":
|
| 419 |
"learning_rate": 1.7244444444444446e-05,
|
| 420 |
-
"loss": 0.
|
| 421 |
"step": 560
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 2.2800000000000002,
|
| 425 |
-
"grad_norm":
|
| 426 |
"learning_rate": 1.7155555555555557e-05,
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 570
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 2.32,
|
| 432 |
-
"grad_norm":
|
| 433 |
"learning_rate": 1.706666666666667e-05,
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 580
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 2.36,
|
| 439 |
-
"grad_norm":
|
| 440 |
"learning_rate": 1.697777777777778e-05,
|
| 441 |
-
"loss": 0.
|
| 442 |
"step": 590
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 2.4,
|
| 446 |
-
"grad_norm":
|
| 447 |
"learning_rate": 1.688888888888889e-05,
|
| 448 |
-
"loss": 0.
|
| 449 |
"step": 600
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 2.44,
|
| 453 |
-
"grad_norm":
|
| 454 |
"learning_rate": 1.6800000000000002e-05,
|
| 455 |
-
"loss": 0.
|
| 456 |
"step": 610
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 2.48,
|
| 460 |
-
"grad_norm":
|
| 461 |
"learning_rate": 1.6711111111111112e-05,
|
| 462 |
-
"loss": 0.
|
| 463 |
"step": 620
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 2.52,
|
| 467 |
-
"grad_norm":
|
| 468 |
"learning_rate": 1.6622222222222223e-05,
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 630
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 2.56,
|
| 474 |
-
"grad_norm":
|
| 475 |
"learning_rate": 1.6533333333333333e-05,
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 640
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 2.6,
|
| 481 |
-
"grad_norm":
|
| 482 |
"learning_rate": 1.6444444444444444e-05,
|
| 483 |
-
"loss": 0.
|
| 484 |
"step": 650
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 2.64,
|
| 488 |
-
"grad_norm":
|
| 489 |
"learning_rate": 1.6355555555555557e-05,
|
| 490 |
-
"loss": 0.
|
| 491 |
"step": 660
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 2.68,
|
| 495 |
-
"grad_norm":
|
| 496 |
"learning_rate": 1.6266666666666668e-05,
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 670
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 2.7199999999999998,
|
| 502 |
-
"grad_norm":
|
| 503 |
"learning_rate": 1.617777777777778e-05,
|
| 504 |
-
"loss": 0.
|
| 505 |
"step": 680
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 2.76,
|
| 509 |
-
"grad_norm":
|
| 510 |
"learning_rate": 1.608888888888889e-05,
|
| 511 |
-
"loss": 0.
|
| 512 |
"step": 690
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 2.8,
|
| 516 |
-
"grad_norm":
|
| 517 |
"learning_rate": 1.6000000000000003e-05,
|
| 518 |
-
"loss": 0.
|
| 519 |
"step": 700
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 2.84,
|
| 523 |
-
"grad_norm":
|
| 524 |
"learning_rate": 1.5911111111111113e-05,
|
| 525 |
-
"loss": 0.
|
| 526 |
"step": 710
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 2.88,
|
| 530 |
-
"grad_norm":
|
| 531 |
"learning_rate": 1.5822222222222224e-05,
|
| 532 |
-
"loss": 0.
|
| 533 |
"step": 720
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 2.92,
|
| 537 |
-
"grad_norm":
|
| 538 |
"learning_rate": 1.5733333333333334e-05,
|
| 539 |
-
"loss": 0.
|
| 540 |
"step": 730
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 2.96,
|
| 544 |
-
"grad_norm":
|
| 545 |
"learning_rate": 1.5644444444444448e-05,
|
| 546 |
-
"loss": 0.
|
| 547 |
"step": 740
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 3.0,
|
| 551 |
-
"grad_norm":
|
| 552 |
"learning_rate": 1.555555555555556e-05,
|
| 553 |
-
"loss": 0.
|
| 554 |
"step": 750
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 3.0,
|
| 558 |
-
"eval_accuracy": 0.
|
| 559 |
-
"eval_f1": 0.
|
| 560 |
-
"eval_loss": 0.
|
| 561 |
-
"eval_runtime": 8.
|
| 562 |
-
"eval_samples_per_second":
|
| 563 |
-
"eval_steps_per_second": 14.
|
| 564 |
"step": 750
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 3.04,
|
| 568 |
-
"grad_norm":
|
| 569 |
"learning_rate": 1.546666666666667e-05,
|
| 570 |
-
"loss": 0.
|
| 571 |
"step": 760
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 3.08,
|
| 575 |
-
"grad_norm":
|
| 576 |
"learning_rate": 1.537777777777778e-05,
|
| 577 |
-
"loss": 0.
|
| 578 |
"step": 770
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 3.12,
|
| 582 |
-
"grad_norm":
|
| 583 |
"learning_rate": 1.528888888888889e-05,
|
| 584 |
-
"loss": 0.
|
| 585 |
"step": 780
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 3.16,
|
| 589 |
-
"grad_norm":
|
| 590 |
"learning_rate": 1.5200000000000002e-05,
|
| 591 |
-
"loss": 0.
|
| 592 |
"step": 790
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 3.2,
|
| 596 |
-
"grad_norm":
|
| 597 |
"learning_rate": 1.5111111111111112e-05,
|
| 598 |
-
"loss": 0.
|
| 599 |
"step": 800
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 3.24,
|
| 603 |
-
"grad_norm":
|
| 604 |
"learning_rate": 1.5022222222222223e-05,
|
| 605 |
-
"loss": 0.
|
| 606 |
"step": 810
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 3.2800000000000002,
|
| 610 |
-
"grad_norm":
|
| 611 |
"learning_rate": 1.4933333333333335e-05,
|
| 612 |
-
"loss": 0.
|
| 613 |
"step": 820
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 3.32,
|
| 617 |
-
"grad_norm":
|
| 618 |
"learning_rate": 1.4844444444444445e-05,
|
| 619 |
-
"loss": 0.
|
| 620 |
"step": 830
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 3.36,
|
| 624 |
-
"grad_norm":
|
| 625 |
"learning_rate": 1.4755555555555556e-05,
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 840
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 3.4,
|
| 631 |
-
"grad_norm":
|
| 632 |
"learning_rate": 1.4666666666666666e-05,
|
| 633 |
-
"loss": 0.
|
| 634 |
"step": 850
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 3.44,
|
| 638 |
-
"grad_norm":
|
| 639 |
"learning_rate": 1.457777777777778e-05,
|
| 640 |
-
"loss": 0.
|
| 641 |
"step": 860
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 3.48,
|
| 645 |
-
"grad_norm":
|
| 646 |
"learning_rate": 1.448888888888889e-05,
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 870
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 3.52,
|
| 652 |
-
"grad_norm":
|
| 653 |
"learning_rate": 1.4400000000000001e-05,
|
| 654 |
-
"loss": 0.
|
| 655 |
"step": 880
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 3.56,
|
| 659 |
-
"grad_norm":
|
| 660 |
"learning_rate": 1.4311111111111111e-05,
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 890
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 3.6,
|
| 666 |
-
"grad_norm":
|
| 667 |
"learning_rate": 1.4222222222222224e-05,
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 900
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 3.64,
|
| 673 |
-
"grad_norm":
|
| 674 |
"learning_rate": 1.4133333333333334e-05,
|
| 675 |
-
"loss": 0.
|
| 676 |
"step": 910
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 3.68,
|
| 680 |
-
"grad_norm":
|
| 681 |
"learning_rate": 1.4044444444444445e-05,
|
| 682 |
-
"loss": 0.
|
| 683 |
"step": 920
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 3.7199999999999998,
|
| 687 |
-
"grad_norm":
|
| 688 |
"learning_rate": 1.3955555555555558e-05,
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 930
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 3.76,
|
| 694 |
-
"grad_norm":
|
| 695 |
"learning_rate": 1.3866666666666669e-05,
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 940
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 3.8,
|
| 701 |
-
"grad_norm":
|
| 702 |
"learning_rate": 1.377777777777778e-05,
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 950
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 3.84,
|
| 708 |
-
"grad_norm":
|
| 709 |
"learning_rate": 1.368888888888889e-05,
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 960
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 3.88,
|
| 715 |
-
"grad_norm":
|
| 716 |
"learning_rate": 1.3600000000000002e-05,
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 970
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 3.92,
|
| 722 |
-
"grad_norm":
|
| 723 |
"learning_rate": 1.3511111111111112e-05,
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 980
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 3.96,
|
| 729 |
-
"grad_norm":
|
| 730 |
"learning_rate": 1.3422222222222223e-05,
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 990
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 4.0,
|
| 736 |
-
"grad_norm":
|
| 737 |
"learning_rate": 1.3333333333333333e-05,
|
| 738 |
-
"loss": 0.
|
| 739 |
"step": 1000
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 4.0,
|
| 743 |
-
"eval_accuracy": 0.
|
| 744 |
-
"eval_f1": 0.
|
| 745 |
-
"eval_loss": 0.
|
| 746 |
-
"eval_runtime": 8.
|
| 747 |
-
"eval_samples_per_second":
|
| 748 |
-
"eval_steps_per_second": 14.
|
| 749 |
"step": 1000
|
| 750 |
},
|
| 751 |
{
|
| 752 |
"epoch": 4.04,
|
| 753 |
-
"grad_norm":
|
| 754 |
"learning_rate": 1.3244444444444447e-05,
|
| 755 |
-
"loss": 0.
|
| 756 |
"step": 1010
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"epoch": 4.08,
|
| 760 |
-
"grad_norm":
|
| 761 |
"learning_rate": 1.3155555555555558e-05,
|
| 762 |
-
"loss": 0.
|
| 763 |
"step": 1020
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 4.12,
|
| 767 |
-
"grad_norm":
|
| 768 |
"learning_rate": 1.3066666666666668e-05,
|
| 769 |
-
"loss": 0.
|
| 770 |
"step": 1030
|
| 771 |
},
|
| 772 |
{
|
| 773 |
"epoch": 4.16,
|
| 774 |
-
"grad_norm":
|
| 775 |
"learning_rate": 1.2977777777777779e-05,
|
| 776 |
-
"loss": 0.
|
| 777 |
"step": 1040
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 4.2,
|
| 781 |
-
"grad_norm":
|
| 782 |
"learning_rate": 1.288888888888889e-05,
|
| 783 |
-
"loss": 0.
|
| 784 |
"step": 1050
|
| 785 |
},
|
| 786 |
{
|
| 787 |
"epoch": 4.24,
|
| 788 |
-
"grad_norm":
|
| 789 |
"learning_rate": 1.2800000000000001e-05,
|
| 790 |
-
"loss": 0.
|
| 791 |
"step": 1060
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 4.28,
|
| 795 |
-
"grad_norm":
|
| 796 |
"learning_rate": 1.2711111111111112e-05,
|
| 797 |
-
"loss": 0.
|
| 798 |
"step": 1070
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 4.32,
|
| 802 |
-
"grad_norm":
|
| 803 |
"learning_rate": 1.2622222222222222e-05,
|
| 804 |
-
"loss": 0.
|
| 805 |
"step": 1080
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"epoch": 4.36,
|
| 809 |
-
"grad_norm":
|
| 810 |
"learning_rate": 1.2533333333333336e-05,
|
| 811 |
-
"loss": 0.
|
| 812 |
"step": 1090
|
| 813 |
},
|
| 814 |
{
|
| 815 |
"epoch": 4.4,
|
| 816 |
-
"grad_norm":
|
| 817 |
"learning_rate": 1.2444444444444446e-05,
|
| 818 |
-
"loss": 0.
|
| 819 |
"step": 1100
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 4.44,
|
| 823 |
-
"grad_norm":
|
| 824 |
"learning_rate": 1.2355555555555557e-05,
|
| 825 |
-
"loss": 0.
|
| 826 |
"step": 1110
|
| 827 |
},
|
| 828 |
{
|
| 829 |
"epoch": 4.48,
|
| 830 |
-
"grad_norm":
|
| 831 |
"learning_rate": 1.2266666666666667e-05,
|
| 832 |
-
"loss": 0.
|
| 833 |
"step": 1120
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 4.52,
|
| 837 |
-
"grad_norm":
|
| 838 |
"learning_rate": 1.217777777777778e-05,
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 1130
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 4.5600000000000005,
|
| 844 |
-
"grad_norm":
|
| 845 |
"learning_rate": 1.208888888888889e-05,
|
| 846 |
-
"loss": 0.
|
| 847 |
"step": 1140
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 4.6,
|
| 851 |
-
"grad_norm":
|
| 852 |
"learning_rate": 1.2e-05,
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 1150
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 4.64,
|
| 858 |
-
"grad_norm":
|
| 859 |
"learning_rate": 1.191111111111111e-05,
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1160
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 4.68,
|
| 865 |
-
"grad_norm":
|
| 866 |
"learning_rate": 1.1822222222222225e-05,
|
| 867 |
-
"loss": 0.
|
| 868 |
"step": 1170
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"epoch": 4.72,
|
| 872 |
-
"grad_norm":
|
| 873 |
"learning_rate": 1.1733333333333335e-05,
|
| 874 |
-
"loss": 0.
|
| 875 |
"step": 1180
|
| 876 |
},
|
| 877 |
{
|
| 878 |
"epoch": 4.76,
|
| 879 |
-
"grad_norm":
|
| 880 |
"learning_rate": 1.1644444444444446e-05,
|
| 881 |
-
"loss": 0.
|
| 882 |
"step": 1190
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"epoch": 4.8,
|
| 886 |
-
"grad_norm":
|
| 887 |
"learning_rate": 1.1555555555555556e-05,
|
| 888 |
-
"loss": 0.
|
| 889 |
"step": 1200
|
| 890 |
},
|
| 891 |
{
|
| 892 |
"epoch": 4.84,
|
| 893 |
-
"grad_norm":
|
| 894 |
"learning_rate": 1.1466666666666668e-05,
|
| 895 |
-
"loss": 0.
|
| 896 |
"step": 1210
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 4.88,
|
| 900 |
-
"grad_norm":
|
| 901 |
"learning_rate": 1.1377777777777779e-05,
|
| 902 |
-
"loss": 0.
|
| 903 |
"step": 1220
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 4.92,
|
| 907 |
-
"grad_norm":
|
| 908 |
"learning_rate": 1.1288888888888889e-05,
|
| 909 |
-
"loss": 0.
|
| 910 |
"step": 1230
|
| 911 |
},
|
| 912 |
{
|
| 913 |
"epoch": 4.96,
|
| 914 |
-
"grad_norm":
|
| 915 |
"learning_rate": 1.1200000000000001e-05,
|
| 916 |
-
"loss": 0.
|
| 917 |
"step": 1240
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 5.0,
|
| 921 |
-
"grad_norm":
|
| 922 |
"learning_rate": 1.1111111111111113e-05,
|
| 923 |
-
"loss": 0.
|
| 924 |
"step": 1250
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 5.0,
|
| 928 |
-
"eval_accuracy": 0.
|
| 929 |
-
"eval_f1": 0.
|
| 930 |
-
"eval_loss": 0.
|
| 931 |
-
"eval_runtime": 8.
|
| 932 |
-
"eval_samples_per_second":
|
| 933 |
-
"eval_steps_per_second": 14.
|
| 934 |
"step": 1250
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 5.04,
|
| 938 |
-
"grad_norm":
|
| 939 |
"learning_rate": 1.1022222222222224e-05,
|
| 940 |
-
"loss": 0.
|
| 941 |
"step": 1260
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 5.08,
|
| 945 |
-
"grad_norm":
|
| 946 |
"learning_rate": 1.0933333333333334e-05,
|
| 947 |
-
"loss": 0.
|
| 948 |
"step": 1270
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 5.12,
|
| 952 |
-
"grad_norm":
|
| 953 |
"learning_rate": 1.0844444444444446e-05,
|
| 954 |
-
"loss": 0.
|
| 955 |
"step": 1280
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 5.16,
|
| 959 |
-
"grad_norm":
|
| 960 |
"learning_rate": 1.0755555555555557e-05,
|
| 961 |
-
"loss": 0.
|
| 962 |
"step": 1290
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 5.2,
|
| 966 |
-
"grad_norm":
|
| 967 |
"learning_rate": 1.0666666666666667e-05,
|
| 968 |
-
"loss": 0.
|
| 969 |
"step": 1300
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 5.24,
|
| 973 |
-
"grad_norm":
|
| 974 |
"learning_rate": 1.0577777777777778e-05,
|
| 975 |
-
"loss": 0.
|
| 976 |
"step": 1310
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 5.28,
|
| 980 |
-
"grad_norm":
|
| 981 |
"learning_rate": 1.048888888888889e-05,
|
| 982 |
-
"loss": 0.
|
| 983 |
"step": 1320
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 5.32,
|
| 987 |
-
"grad_norm":
|
| 988 |
"learning_rate": 1.04e-05,
|
| 989 |
-
"loss": 0.
|
| 990 |
"step": 1330
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 5.36,
|
| 994 |
-
"grad_norm":
|
| 995 |
"learning_rate": 1.0311111111111113e-05,
|
| 996 |
-
"loss": 0.
|
| 997 |
"step": 1340
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
"epoch": 5.4,
|
| 1001 |
-
"grad_norm":
|
| 1002 |
"learning_rate": 1.0222222222222223e-05,
|
| 1003 |
-
"loss": 0.
|
| 1004 |
"step": 1350
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 5.44,
|
| 1008 |
-
"grad_norm":
|
| 1009 |
"learning_rate": 1.0133333333333335e-05,
|
| 1010 |
-
"loss": 0.
|
| 1011 |
"step": 1360
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 5.48,
|
| 1015 |
-
"grad_norm":
|
| 1016 |
"learning_rate": 1.0044444444444446e-05,
|
| 1017 |
-
"loss": 0.
|
| 1018 |
"step": 1370
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
"epoch": 5.52,
|
| 1022 |
-
"grad_norm":
|
| 1023 |
"learning_rate": 9.955555555555556e-06,
|
| 1024 |
-
"loss": 0.
|
| 1025 |
"step": 1380
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 5.5600000000000005,
|
| 1029 |
-
"grad_norm":
|
| 1030 |
"learning_rate": 9.866666666666668e-06,
|
| 1031 |
-
"loss": 0.
|
| 1032 |
"step": 1390
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
"epoch": 5.6,
|
| 1036 |
-
"grad_norm":
|
| 1037 |
"learning_rate": 9.777777777777779e-06,
|
| 1038 |
-
"loss": 0.
|
| 1039 |
"step": 1400
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
"epoch": 5.64,
|
| 1043 |
-
"grad_norm":
|
| 1044 |
"learning_rate": 9.688888888888889e-06,
|
| 1045 |
-
"loss": 0.
|
| 1046 |
"step": 1410
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
"epoch": 5.68,
|
| 1050 |
-
"grad_norm":
|
| 1051 |
"learning_rate": 9.600000000000001e-06,
|
| 1052 |
-
"loss": 0.
|
| 1053 |
"step": 1420
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 5.72,
|
| 1057 |
-
"grad_norm":
|
| 1058 |
"learning_rate": 9.511111111111112e-06,
|
| 1059 |
-
"loss": 0.
|
| 1060 |
"step": 1430
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
"epoch": 5.76,
|
| 1064 |
-
"grad_norm":
|
| 1065 |
"learning_rate": 9.422222222222222e-06,
|
| 1066 |
-
"loss": 0.
|
| 1067 |
"step": 1440
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
"epoch": 5.8,
|
| 1071 |
-
"grad_norm":
|
| 1072 |
"learning_rate": 9.333333333333334e-06,
|
| 1073 |
-
"loss": 0.
|
| 1074 |
"step": 1450
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
"epoch": 5.84,
|
| 1078 |
-
"grad_norm":
|
| 1079 |
"learning_rate": 9.244444444444445e-06,
|
| 1080 |
-
"loss": 0.
|
| 1081 |
"step": 1460
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
"epoch": 5.88,
|
| 1085 |
-
"grad_norm":
|
| 1086 |
"learning_rate": 9.155555555555557e-06,
|
| 1087 |
-
"loss": 0.
|
| 1088 |
"step": 1470
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
"epoch": 5.92,
|
| 1092 |
-
"grad_norm":
|
| 1093 |
"learning_rate": 9.066666666666667e-06,
|
| 1094 |
-
"loss": 0.
|
| 1095 |
"step": 1480
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 5.96,
|
| 1099 |
-
"grad_norm":
|
| 1100 |
"learning_rate": 8.977777777777778e-06,
|
| 1101 |
-
"loss": 0.
|
| 1102 |
"step": 1490
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
"epoch": 6.0,
|
| 1106 |
-
"grad_norm":
|
| 1107 |
"learning_rate": 8.888888888888888e-06,
|
| 1108 |
-
"loss": 0.
|
| 1109 |
"step": 1500
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
"epoch": 6.0,
|
| 1113 |
-
"eval_accuracy": 0.
|
| 1114 |
-
"eval_f1": 0.
|
| 1115 |
-
"eval_loss": 0.
|
| 1116 |
-
"eval_runtime": 8.
|
| 1117 |
-
"eval_samples_per_second":
|
| 1118 |
-
"eval_steps_per_second": 14.
|
| 1119 |
"step": 1500
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 6.04,
|
| 1123 |
-
"grad_norm":
|
| 1124 |
"learning_rate": 8.8e-06,
|
| 1125 |
-
"loss": 0.
|
| 1126 |
"step": 1510
|
| 1127 |
},
|
| 1128 |
{
|
| 1129 |
"epoch": 6.08,
|
| 1130 |
-
"grad_norm":
|
| 1131 |
"learning_rate": 8.711111111111111e-06,
|
| 1132 |
-
"loss": 0.
|
| 1133 |
"step": 1520
|
| 1134 |
},
|
| 1135 |
{
|
| 1136 |
"epoch": 6.12,
|
| 1137 |
-
"grad_norm":
|
| 1138 |
"learning_rate": 8.622222222222223e-06,
|
| 1139 |
-
"loss": 0.
|
| 1140 |
"step": 1530
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 6.16,
|
| 1144 |
-
"grad_norm":
|
| 1145 |
"learning_rate": 8.533333333333335e-06,
|
| 1146 |
-
"loss": 0.
|
| 1147 |
"step": 1540
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
"epoch": 6.2,
|
| 1151 |
-
"grad_norm":
|
| 1152 |
"learning_rate": 8.444444444444446e-06,
|
| 1153 |
-
"loss": 0.
|
| 1154 |
"step": 1550
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 6.24,
|
| 1158 |
-
"grad_norm":
|
| 1159 |
"learning_rate": 8.355555555555556e-06,
|
| 1160 |
-
"loss": 0.
|
| 1161 |
"step": 1560
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 6.28,
|
| 1165 |
-
"grad_norm":
|
| 1166 |
"learning_rate": 8.266666666666667e-06,
|
| 1167 |
-
"loss": 0.
|
| 1168 |
"step": 1570
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
"epoch": 6.32,
|
| 1172 |
-
"grad_norm":
|
| 1173 |
"learning_rate": 8.177777777777779e-06,
|
| 1174 |
-
"loss": 0.
|
| 1175 |
"step": 1580
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
"epoch": 6.36,
|
| 1179 |
-
"grad_norm":
|
| 1180 |
"learning_rate": 8.08888888888889e-06,
|
| 1181 |
-
"loss": 0.
|
| 1182 |
"step": 1590
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 6.4,
|
| 1186 |
-
"grad_norm":
|
| 1187 |
"learning_rate": 8.000000000000001e-06,
|
| 1188 |
-
"loss": 0.
|
| 1189 |
"step": 1600
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 6.44,
|
| 1193 |
-
"grad_norm":
|
| 1194 |
"learning_rate": 7.911111111111112e-06,
|
| 1195 |
-
"loss": 0.
|
| 1196 |
"step": 1610
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
"epoch": 6.48,
|
| 1200 |
-
"grad_norm":
|
| 1201 |
"learning_rate": 7.822222222222224e-06,
|
| 1202 |
-
"loss": 0.
|
| 1203 |
"step": 1620
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 6.52,
|
| 1207 |
-
"grad_norm":
|
| 1208 |
"learning_rate": 7.733333333333334e-06,
|
| 1209 |
-
"loss": 0.
|
| 1210 |
"step": 1630
|
| 1211 |
},
|
| 1212 |
{
|
| 1213 |
"epoch": 6.5600000000000005,
|
| 1214 |
-
"grad_norm":
|
| 1215 |
"learning_rate": 7.644444444444445e-06,
|
| 1216 |
-
"loss": 0.
|
| 1217 |
"step": 1640
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 6.6,
|
| 1221 |
-
"grad_norm":
|
| 1222 |
"learning_rate": 7.555555555555556e-06,
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"step": 1650
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 6.64,
|
| 1228 |
-
"grad_norm":
|
| 1229 |
"learning_rate": 7.4666666666666675e-06,
|
| 1230 |
-
"loss": 0.
|
| 1231 |
"step": 1660
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
"epoch": 6.68,
|
| 1235 |
-
"grad_norm":
|
| 1236 |
"learning_rate": 7.377777777777778e-06,
|
| 1237 |
-
"loss": 0.
|
| 1238 |
"step": 1670
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
"epoch": 6.72,
|
| 1242 |
-
"grad_norm":
|
| 1243 |
"learning_rate": 7.28888888888889e-06,
|
| 1244 |
-
"loss": 0.
|
| 1245 |
"step": 1680
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 6.76,
|
| 1249 |
-
"grad_norm":
|
| 1250 |
"learning_rate": 7.2000000000000005e-06,
|
| 1251 |
-
"loss": 0.
|
| 1252 |
"step": 1690
|
| 1253 |
},
|
| 1254 |
{
|
| 1255 |
"epoch": 6.8,
|
| 1256 |
-
"grad_norm":
|
| 1257 |
"learning_rate": 7.111111111111112e-06,
|
| 1258 |
-
"loss": 0.
|
| 1259 |
"step": 1700
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 6.84,
|
| 1263 |
-
"grad_norm":
|
| 1264 |
"learning_rate": 7.022222222222222e-06,
|
| 1265 |
-
"loss": 0.
|
| 1266 |
"step": 1710
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
"epoch": 6.88,
|
| 1270 |
-
"grad_norm":
|
| 1271 |
"learning_rate": 6.9333333333333344e-06,
|
| 1272 |
-
"loss": 0.
|
| 1273 |
"step": 1720
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 6.92,
|
| 1277 |
-
"grad_norm":
|
| 1278 |
"learning_rate": 6.844444444444445e-06,
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"step": 1730
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 6.96,
|
| 1284 |
-
"grad_norm":
|
| 1285 |
"learning_rate": 6.755555555555556e-06,
|
| 1286 |
-
"loss": 0.
|
| 1287 |
"step": 1740
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 7.0,
|
| 1291 |
-
"grad_norm":
|
| 1292 |
"learning_rate": 6.666666666666667e-06,
|
| 1293 |
-
"loss": 0.
|
| 1294 |
"step": 1750
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
"epoch": 7.0,
|
| 1298 |
-
"eval_accuracy": 0.
|
| 1299 |
-
"eval_f1": 0.
|
| 1300 |
-
"eval_loss": 0.
|
| 1301 |
-
"eval_runtime": 8.
|
| 1302 |
-
"eval_samples_per_second":
|
| 1303 |
-
"eval_steps_per_second": 14.
|
| 1304 |
"step": 1750
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 7.04,
|
| 1308 |
-
"grad_norm":
|
| 1309 |
"learning_rate": 6.577777777777779e-06,
|
| 1310 |
-
"loss": 0.
|
| 1311 |
"step": 1760
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 7.08,
|
| 1315 |
-
"grad_norm":
|
| 1316 |
"learning_rate": 6.488888888888889e-06,
|
| 1317 |
-
"loss": 0.
|
| 1318 |
"step": 1770
|
| 1319 |
},
|
| 1320 |
{
|
| 1321 |
"epoch": 7.12,
|
| 1322 |
-
"grad_norm":
|
| 1323 |
"learning_rate": 6.4000000000000006e-06,
|
| 1324 |
-
"loss": 0.
|
| 1325 |
"step": 1780
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 7.16,
|
| 1329 |
-
"grad_norm":
|
| 1330 |
"learning_rate": 6.311111111111111e-06,
|
| 1331 |
-
"loss": 0.
|
| 1332 |
"step": 1790
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 7.2,
|
| 1336 |
-
"grad_norm":
|
| 1337 |
"learning_rate": 6.222222222222223e-06,
|
| 1338 |
-
"loss": 0.
|
| 1339 |
"step": 1800
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
"epoch": 7.24,
|
| 1343 |
-
"grad_norm":
|
| 1344 |
"learning_rate": 6.133333333333334e-06,
|
| 1345 |
-
"loss": 0.
|
| 1346 |
"step": 1810
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 7.28,
|
| 1350 |
-
"grad_norm":
|
| 1351 |
"learning_rate": 6.044444444444445e-06,
|
| 1352 |
-
"loss": 0.
|
| 1353 |
"step": 1820
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 7.32,
|
| 1357 |
-
"grad_norm":
|
| 1358 |
"learning_rate": 5.955555555555555e-06,
|
| 1359 |
-
"loss": 0.
|
| 1360 |
"step": 1830
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 7.36,
|
| 1364 |
-
"grad_norm":
|
| 1365 |
"learning_rate": 5.8666666666666675e-06,
|
| 1366 |
-
"loss": 0.
|
| 1367 |
"step": 1840
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 7.4,
|
| 1371 |
-
"grad_norm":
|
| 1372 |
"learning_rate": 5.777777777777778e-06,
|
| 1373 |
-
"loss": 0.
|
| 1374 |
"step": 1850
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 7.44,
|
| 1378 |
-
"grad_norm":
|
| 1379 |
"learning_rate": 5.688888888888889e-06,
|
| 1380 |
-
"loss": 0.
|
| 1381 |
"step": 1860
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 7.48,
|
| 1385 |
-
"grad_norm":
|
| 1386 |
"learning_rate": 5.600000000000001e-06,
|
| 1387 |
-
"loss": 0.
|
| 1388 |
"step": 1870
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 7.52,
|
| 1392 |
-
"grad_norm":
|
| 1393 |
"learning_rate": 5.511111111111112e-06,
|
| 1394 |
-
"loss": 0.
|
| 1395 |
"step": 1880
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 7.5600000000000005,
|
| 1399 |
-
"grad_norm":
|
| 1400 |
"learning_rate": 5.422222222222223e-06,
|
| 1401 |
-
"loss": 0.
|
| 1402 |
"step": 1890
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 7.6,
|
| 1406 |
-
"grad_norm":
|
| 1407 |
"learning_rate": 5.333333333333334e-06,
|
| 1408 |
-
"loss": 0.
|
| 1409 |
"step": 1900
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 7.64,
|
| 1413 |
-
"grad_norm":
|
| 1414 |
"learning_rate": 5.244444444444445e-06,
|
| 1415 |
-
"loss": 0.
|
| 1416 |
"step": 1910
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 7.68,
|
| 1420 |
-
"grad_norm":
|
| 1421 |
"learning_rate": 5.155555555555556e-06,
|
| 1422 |
-
"loss": 0.
|
| 1423 |
"step": 1920
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 7.72,
|
| 1427 |
-
"grad_norm":
|
| 1428 |
"learning_rate": 5.0666666666666676e-06,
|
| 1429 |
-
"loss": 0.
|
| 1430 |
"step": 1930
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 7.76,
|
| 1434 |
-
"grad_norm":
|
| 1435 |
"learning_rate": 4.977777777777778e-06,
|
| 1436 |
-
"loss": 0.
|
| 1437 |
"step": 1940
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 7.8,
|
| 1441 |
-
"grad_norm":
|
| 1442 |
"learning_rate": 4.888888888888889e-06,
|
| 1443 |
-
"loss": 0.
|
| 1444 |
"step": 1950
|
| 1445 |
},
|
| 1446 |
{
|
| 1447 |
"epoch": 7.84,
|
| 1448 |
-
"grad_norm": 5.
|
| 1449 |
"learning_rate": 4.800000000000001e-06,
|
| 1450 |
-
"loss": 0.
|
| 1451 |
"step": 1960
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
"epoch": 7.88,
|
| 1455 |
-
"grad_norm":
|
| 1456 |
"learning_rate": 4.711111111111111e-06,
|
| 1457 |
-
"loss": 0.
|
| 1458 |
"step": 1970
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 7.92,
|
| 1462 |
-
"grad_norm":
|
| 1463 |
"learning_rate": 4.622222222222222e-06,
|
| 1464 |
-
"loss": 0.
|
| 1465 |
"step": 1980
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 7.96,
|
| 1469 |
-
"grad_norm":
|
| 1470 |
"learning_rate": 4.533333333333334e-06,
|
| 1471 |
-
"loss": 0.
|
| 1472 |
"step": 1990
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 8.0,
|
| 1476 |
-
"grad_norm":
|
| 1477 |
"learning_rate": 4.444444444444444e-06,
|
| 1478 |
-
"loss": 0.
|
| 1479 |
"step": 2000
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 8.0,
|
| 1483 |
-
"eval_accuracy": 0.
|
| 1484 |
-
"eval_f1": 0.
|
| 1485 |
-
"eval_loss": 0.
|
| 1486 |
-
"eval_runtime": 8.
|
| 1487 |
-
"eval_samples_per_second": 57.
|
| 1488 |
-
"eval_steps_per_second": 14.
|
| 1489 |
"step": 2000
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
"epoch": 8.04,
|
| 1493 |
-
"grad_norm":
|
| 1494 |
"learning_rate": 4.3555555555555555e-06,
|
| 1495 |
-
"loss": 0.
|
| 1496 |
"step": 2010
|
| 1497 |
},
|
| 1498 |
{
|
| 1499 |
"epoch": 8.08,
|
| 1500 |
-
"grad_norm":
|
| 1501 |
"learning_rate": 4.266666666666668e-06,
|
| 1502 |
-
"loss": 0.
|
| 1503 |
"step": 2020
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 8.12,
|
| 1507 |
-
"grad_norm":
|
| 1508 |
"learning_rate": 4.177777777777778e-06,
|
| 1509 |
-
"loss": 0.
|
| 1510 |
"step": 2030
|
| 1511 |
},
|
| 1512 |
{
|
| 1513 |
"epoch": 8.16,
|
| 1514 |
-
"grad_norm":
|
| 1515 |
"learning_rate": 4.088888888888889e-06,
|
| 1516 |
-
"loss": 0.
|
| 1517 |
"step": 2040
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 8.2,
|
| 1521 |
-
"grad_norm":
|
| 1522 |
"learning_rate": 4.000000000000001e-06,
|
| 1523 |
-
"loss": 0.
|
| 1524 |
"step": 2050
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 8.24,
|
| 1528 |
-
"grad_norm":
|
| 1529 |
"learning_rate": 3.911111111111112e-06,
|
| 1530 |
-
"loss": 0.
|
| 1531 |
"step": 2060
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 8.28,
|
| 1535 |
-
"grad_norm":
|
| 1536 |
"learning_rate": 3.8222222222222224e-06,
|
| 1537 |
-
"loss": 0.
|
| 1538 |
"step": 2070
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 8.32,
|
| 1542 |
-
"grad_norm":
|
| 1543 |
"learning_rate": 3.7333333333333337e-06,
|
| 1544 |
-
"loss": 0.
|
| 1545 |
"step": 2080
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 8.36,
|
| 1549 |
-
"grad_norm":
|
| 1550 |
"learning_rate": 3.644444444444445e-06,
|
| 1551 |
-
"loss": 0.
|
| 1552 |
"step": 2090
|
| 1553 |
},
|
| 1554 |
{
|
| 1555 |
"epoch": 8.4,
|
| 1556 |
-
"grad_norm":
|
| 1557 |
"learning_rate": 3.555555555555556e-06,
|
| 1558 |
-
"loss": 0.
|
| 1559 |
"step": 2100
|
| 1560 |
},
|
| 1561 |
{
|
| 1562 |
"epoch": 8.44,
|
| 1563 |
-
"grad_norm":
|
| 1564 |
"learning_rate": 3.4666666666666672e-06,
|
| 1565 |
-
"loss": 0.
|
| 1566 |
"step": 2110
|
| 1567 |
},
|
| 1568 |
{
|
| 1569 |
"epoch": 8.48,
|
| 1570 |
-
"grad_norm":
|
| 1571 |
"learning_rate": 3.377777777777778e-06,
|
| 1572 |
-
"loss": 0.
|
| 1573 |
"step": 2120
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 8.52,
|
| 1577 |
-
"grad_norm":
|
| 1578 |
"learning_rate": 3.2888888888888894e-06,
|
| 1579 |
-
"loss": 0.
|
| 1580 |
"step": 2130
|
| 1581 |
},
|
| 1582 |
{
|
| 1583 |
"epoch": 8.56,
|
| 1584 |
-
"grad_norm":
|
| 1585 |
"learning_rate": 3.2000000000000003e-06,
|
| 1586 |
-
"loss": 0.
|
| 1587 |
"step": 2140
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
"epoch": 8.6,
|
| 1591 |
-
"grad_norm":
|
| 1592 |
"learning_rate": 3.1111111111111116e-06,
|
| 1593 |
-
"loss": 0.
|
| 1594 |
"step": 2150
|
| 1595 |
},
|
| 1596 |
{
|
| 1597 |
"epoch": 8.64,
|
| 1598 |
-
"grad_norm":
|
| 1599 |
"learning_rate": 3.0222222222222225e-06,
|
| 1600 |
-
"loss": 0.
|
| 1601 |
"step": 2160
|
| 1602 |
},
|
| 1603 |
{
|
| 1604 |
"epoch": 8.68,
|
| 1605 |
-
"grad_norm":
|
| 1606 |
"learning_rate": 2.9333333333333338e-06,
|
| 1607 |
-
"loss": 0.
|
| 1608 |
"step": 2170
|
| 1609 |
},
|
| 1610 |
{
|
| 1611 |
"epoch": 8.72,
|
| 1612 |
-
"grad_norm":
|
| 1613 |
"learning_rate": 2.8444444444444446e-06,
|
| 1614 |
-
"loss": 0.
|
| 1615 |
"step": 2180
|
| 1616 |
},
|
| 1617 |
{
|
| 1618 |
"epoch": 8.76,
|
| 1619 |
-
"grad_norm":
|
| 1620 |
"learning_rate": 2.755555555555556e-06,
|
| 1621 |
-
"loss": 0.
|
| 1622 |
"step": 2190
|
| 1623 |
},
|
| 1624 |
{
|
| 1625 |
"epoch": 8.8,
|
| 1626 |
-
"grad_norm":
|
| 1627 |
"learning_rate": 2.666666666666667e-06,
|
| 1628 |
-
"loss": 0.
|
| 1629 |
"step": 2200
|
| 1630 |
},
|
| 1631 |
{
|
| 1632 |
"epoch": 8.84,
|
| 1633 |
-
"grad_norm":
|
| 1634 |
"learning_rate": 2.577777777777778e-06,
|
| 1635 |
-
"loss": 0.
|
| 1636 |
"step": 2210
|
| 1637 |
},
|
| 1638 |
{
|
| 1639 |
"epoch": 8.88,
|
| 1640 |
-
"grad_norm":
|
| 1641 |
"learning_rate": 2.488888888888889e-06,
|
| 1642 |
-
"loss": 0.
|
| 1643 |
"step": 2220
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 8.92,
|
| 1647 |
-
"grad_norm":
|
| 1648 |
"learning_rate": 2.4000000000000003e-06,
|
| 1649 |
-
"loss": 0.
|
| 1650 |
"step": 2230
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 8.96,
|
| 1654 |
-
"grad_norm":
|
| 1655 |
"learning_rate": 2.311111111111111e-06,
|
| 1656 |
-
"loss": 0.
|
| 1657 |
"step": 2240
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
"epoch": 9.0,
|
| 1661 |
-
"grad_norm":
|
| 1662 |
"learning_rate": 2.222222222222222e-06,
|
| 1663 |
-
"loss": 0.
|
| 1664 |
"step": 2250
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 9.0,
|
| 1668 |
-
"eval_accuracy": 0.
|
| 1669 |
-
"eval_f1": 0.
|
| 1670 |
-
"eval_loss": 0.
|
| 1671 |
-
"eval_runtime": 8.
|
| 1672 |
-
"eval_samples_per_second":
|
| 1673 |
-
"eval_steps_per_second": 14.
|
| 1674 |
"step": 2250
|
| 1675 |
},
|
| 1676 |
{
|
| 1677 |
"epoch": 9.04,
|
| 1678 |
-
"grad_norm":
|
| 1679 |
"learning_rate": 2.133333333333334e-06,
|
| 1680 |
-
"loss": 0.
|
| 1681 |
"step": 2260
|
| 1682 |
},
|
| 1683 |
{
|
| 1684 |
"epoch": 9.08,
|
| 1685 |
-
"grad_norm":
|
| 1686 |
"learning_rate": 2.0444444444444447e-06,
|
| 1687 |
-
"loss": 0.
|
| 1688 |
"step": 2270
|
| 1689 |
},
|
| 1690 |
{
|
| 1691 |
"epoch": 9.12,
|
| 1692 |
-
"grad_norm":
|
| 1693 |
"learning_rate": 1.955555555555556e-06,
|
| 1694 |
-
"loss": 0.
|
| 1695 |
"step": 2280
|
| 1696 |
},
|
| 1697 |
{
|
| 1698 |
"epoch": 9.16,
|
| 1699 |
-
"grad_norm":
|
| 1700 |
"learning_rate": 1.8666666666666669e-06,
|
| 1701 |
-
"loss": 0.
|
| 1702 |
"step": 2290
|
| 1703 |
},
|
| 1704 |
{
|
| 1705 |
"epoch": 9.2,
|
| 1706 |
-
"grad_norm":
|
| 1707 |
"learning_rate": 1.777777777777778e-06,
|
| 1708 |
-
"loss": 0.
|
| 1709 |
"step": 2300
|
| 1710 |
},
|
| 1711 |
{
|
| 1712 |
"epoch": 9.24,
|
| 1713 |
-
"grad_norm":
|
| 1714 |
"learning_rate": 1.688888888888889e-06,
|
| 1715 |
-
"loss": 0.
|
| 1716 |
"step": 2310
|
| 1717 |
},
|
| 1718 |
{
|
| 1719 |
"epoch": 9.28,
|
| 1720 |
-
"grad_norm":
|
| 1721 |
"learning_rate": 1.6000000000000001e-06,
|
| 1722 |
-
"loss": 0.
|
| 1723 |
"step": 2320
|
| 1724 |
},
|
| 1725 |
{
|
| 1726 |
"epoch": 9.32,
|
| 1727 |
-
"grad_norm":
|
| 1728 |
"learning_rate": 1.5111111111111112e-06,
|
| 1729 |
-
"loss": 0.
|
| 1730 |
"step": 2330
|
| 1731 |
},
|
| 1732 |
{
|
| 1733 |
"epoch": 9.36,
|
| 1734 |
-
"grad_norm":
|
| 1735 |
"learning_rate": 1.4222222222222223e-06,
|
| 1736 |
-
"loss": 0.
|
| 1737 |
"step": 2340
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
"epoch": 9.4,
|
| 1741 |
-
"grad_norm":
|
| 1742 |
"learning_rate": 1.3333333333333334e-06,
|
| 1743 |
-
"loss": 0.
|
| 1744 |
"step": 2350
|
| 1745 |
},
|
| 1746 |
{
|
| 1747 |
"epoch": 9.44,
|
| 1748 |
-
"grad_norm": 0.
|
| 1749 |
"learning_rate": 1.2444444444444445e-06,
|
| 1750 |
-
"loss": 0.
|
| 1751 |
"step": 2360
|
| 1752 |
},
|
| 1753 |
{
|
| 1754 |
"epoch": 9.48,
|
| 1755 |
-
"grad_norm":
|
| 1756 |
"learning_rate": 1.1555555555555556e-06,
|
| 1757 |
-
"loss": 0.
|
| 1758 |
"step": 2370
|
| 1759 |
},
|
| 1760 |
{
|
| 1761 |
"epoch": 9.52,
|
| 1762 |
-
"grad_norm":
|
| 1763 |
"learning_rate": 1.066666666666667e-06,
|
| 1764 |
-
"loss": 0.
|
| 1765 |
"step": 2380
|
| 1766 |
},
|
| 1767 |
{
|
| 1768 |
"epoch": 9.56,
|
| 1769 |
-
"grad_norm":
|
| 1770 |
"learning_rate": 9.77777777777778e-07,
|
| 1771 |
-
"loss": 0.
|
| 1772 |
"step": 2390
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 9.6,
|
| 1776 |
-
"grad_norm":
|
| 1777 |
"learning_rate": 8.88888888888889e-07,
|
| 1778 |
-
"loss": 0.
|
| 1779 |
"step": 2400
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 9.64,
|
| 1783 |
-
"grad_norm":
|
| 1784 |
"learning_rate": 8.000000000000001e-07,
|
| 1785 |
-
"loss": 0.
|
| 1786 |
"step": 2410
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
"epoch": 9.68,
|
| 1790 |
-
"grad_norm":
|
| 1791 |
"learning_rate": 7.111111111111112e-07,
|
| 1792 |
-
"loss": 0.
|
| 1793 |
"step": 2420
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
"epoch": 9.72,
|
| 1797 |
-
"grad_norm":
|
| 1798 |
"learning_rate": 6.222222222222223e-07,
|
| 1799 |
-
"loss": 0.
|
| 1800 |
"step": 2430
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 9.76,
|
| 1804 |
-
"grad_norm":
|
| 1805 |
"learning_rate": 5.333333333333335e-07,
|
| 1806 |
-
"loss": 0.
|
| 1807 |
"step": 2440
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 9.8,
|
| 1811 |
-
"grad_norm":
|
| 1812 |
"learning_rate": 4.444444444444445e-07,
|
| 1813 |
-
"loss": 0.
|
| 1814 |
"step": 2450
|
| 1815 |
},
|
| 1816 |
{
|
| 1817 |
"epoch": 9.84,
|
| 1818 |
-
"grad_norm":
|
| 1819 |
"learning_rate": 3.555555555555556e-07,
|
| 1820 |
-
"loss": 0.
|
| 1821 |
"step": 2460
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 9.88,
|
| 1825 |
-
"grad_norm":
|
| 1826 |
"learning_rate": 2.666666666666667e-07,
|
| 1827 |
-
"loss": 0.
|
| 1828 |
"step": 2470
|
| 1829 |
},
|
| 1830 |
{
|
| 1831 |
"epoch": 9.92,
|
| 1832 |
-
"grad_norm":
|
| 1833 |
"learning_rate": 1.777777777777778e-07,
|
| 1834 |
-
"loss": 0.
|
| 1835 |
"step": 2480
|
| 1836 |
},
|
| 1837 |
{
|
| 1838 |
"epoch": 9.96,
|
| 1839 |
-
"grad_norm":
|
| 1840 |
"learning_rate": 8.88888888888889e-08,
|
| 1841 |
-
"loss": 0.
|
| 1842 |
"step": 2490
|
| 1843 |
},
|
| 1844 |
{
|
| 1845 |
"epoch": 10.0,
|
| 1846 |
-
"grad_norm":
|
| 1847 |
"learning_rate": 0.0,
|
| 1848 |
-
"loss": 0.
|
| 1849 |
"step": 2500
|
| 1850 |
},
|
| 1851 |
{
|
| 1852 |
"epoch": 10.0,
|
| 1853 |
-
"eval_accuracy": 0.
|
| 1854 |
-
"eval_f1": 0.
|
| 1855 |
-
"eval_loss": 0.
|
| 1856 |
-
"eval_runtime": 8.
|
| 1857 |
-
"eval_samples_per_second":
|
| 1858 |
-
"eval_steps_per_second": 14.
|
| 1859 |
"step": 2500
|
| 1860 |
},
|
| 1861 |
{
|
| 1862 |
"epoch": 10.0,
|
| 1863 |
"step": 2500,
|
| 1864 |
"total_flos": 4.0857422266368e+18,
|
| 1865 |
-
"train_loss": 0.
|
| 1866 |
-
"train_runtime":
|
| 1867 |
-
"train_samples_per_second": 21.
|
| 1868 |
-
"train_steps_per_second": 1.
|
| 1869 |
}
|
| 1870 |
],
|
| 1871 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.968,
|
| 3 |
+
"best_model_checkpoint": "dinov2-base-finetuned-eye/checkpoint-2500",
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2500,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 25.091054916381836,
|
| 14 |
"learning_rate": 8.000000000000001e-07,
|
| 15 |
+
"loss": 0.2386,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 6.266851425170898,
|
| 21 |
"learning_rate": 1.6000000000000001e-06,
|
| 22 |
+
"loss": 0.0581,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 107.60309600830078,
|
| 28 |
"learning_rate": 2.4000000000000003e-06,
|
| 29 |
+
"loss": 0.2613,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 4.244115352630615,
|
| 35 |
"learning_rate": 3.2000000000000003e-06,
|
| 36 |
+
"loss": 0.0925,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 55.03916931152344,
|
| 42 |
"learning_rate": 4.000000000000001e-06,
|
| 43 |
+
"loss": 0.2499,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 104.31927490234375,
|
| 49 |
"learning_rate": 4.800000000000001e-06,
|
| 50 |
+
"loss": 0.2216,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 43.71086120605469,
|
| 56 |
"learning_rate": 5.600000000000001e-06,
|
| 57 |
+
"loss": 0.1194,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 10.551958084106445,
|
| 63 |
"learning_rate": 6.4000000000000006e-06,
|
| 64 |
+
"loss": 0.098,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 25.248905181884766,
|
| 70 |
"learning_rate": 7.2000000000000005e-06,
|
| 71 |
+
"loss": 0.2751,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 12.814699172973633,
|
| 77 |
"learning_rate": 8.000000000000001e-06,
|
| 78 |
+
"loss": 0.2384,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 59.77313995361328,
|
| 84 |
"learning_rate": 8.8e-06,
|
| 85 |
+
"loss": 0.2072,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 74.56177520751953,
|
| 91 |
"learning_rate": 9.600000000000001e-06,
|
| 92 |
+
"loss": 0.3489,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 33.88791275024414,
|
| 98 |
"learning_rate": 1.04e-05,
|
| 99 |
+
"loss": 0.1099,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 33.14435958862305,
|
| 105 |
"learning_rate": 1.1200000000000001e-05,
|
| 106 |
+
"loss": 0.1244,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 100.65065002441406,
|
| 112 |
"learning_rate": 1.2e-05,
|
| 113 |
+
"loss": 0.4129,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 86.43379974365234,
|
| 119 |
"learning_rate": 1.2800000000000001e-05,
|
| 120 |
+
"loss": 0.2088,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 2.185288429260254,
|
| 126 |
"learning_rate": 1.3600000000000002e-05,
|
| 127 |
+
"loss": 0.2778,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 55.72468185424805,
|
| 133 |
"learning_rate": 1.4400000000000001e-05,
|
| 134 |
+
"loss": 0.2935,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 33.43989181518555,
|
| 140 |
"learning_rate": 1.5200000000000002e-05,
|
| 141 |
+
"loss": 0.3813,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 62.71244430541992,
|
| 147 |
"learning_rate": 1.6000000000000003e-05,
|
| 148 |
+
"loss": 0.2892,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 19.36113739013672,
|
| 154 |
"learning_rate": 1.6800000000000002e-05,
|
| 155 |
+
"loss": 0.2822,
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 56.82246017456055,
|
| 161 |
"learning_rate": 1.76e-05,
|
| 162 |
+
"loss": 0.3083,
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 609.8956909179688,
|
| 168 |
"learning_rate": 1.8400000000000003e-05,
|
| 169 |
+
"loss": 0.4352,
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 21.06277847290039,
|
| 175 |
"learning_rate": 1.9200000000000003e-05,
|
| 176 |
+
"loss": 0.4511,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 13.084687232971191,
|
| 182 |
"learning_rate": 2e-05,
|
| 183 |
+
"loss": 0.3853,
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 1.0,
|
| 188 |
+
"eval_accuracy": 0.874,
|
| 189 |
+
"eval_f1": 0.8728784694592093,
|
| 190 |
+
"eval_loss": 0.4917781352996826,
|
| 191 |
+
"eval_runtime": 8.6219,
|
| 192 |
+
"eval_samples_per_second": 57.992,
|
| 193 |
+
"eval_steps_per_second": 14.498,
|
| 194 |
"step": 250
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 1.04,
|
| 198 |
+
"grad_norm": 52.16224670410156,
|
| 199 |
"learning_rate": 1.9911111111111112e-05,
|
| 200 |
+
"loss": 0.2854,
|
| 201 |
"step": 260
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 1.08,
|
| 205 |
+
"grad_norm": 56.812461853027344,
|
| 206 |
"learning_rate": 1.9822222222222226e-05,
|
| 207 |
+
"loss": 0.3914,
|
| 208 |
"step": 270
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"epoch": 1.12,
|
| 212 |
+
"grad_norm": 76.50477600097656,
|
| 213 |
"learning_rate": 1.9733333333333336e-05,
|
| 214 |
+
"loss": 0.433,
|
| 215 |
"step": 280
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 1.16,
|
| 219 |
+
"grad_norm": 54.315757751464844,
|
| 220 |
"learning_rate": 1.9644444444444447e-05,
|
| 221 |
+
"loss": 0.3325,
|
| 222 |
"step": 290
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 1.2,
|
| 226 |
+
"grad_norm": 26.856290817260742,
|
| 227 |
"learning_rate": 1.9555555555555557e-05,
|
| 228 |
+
"loss": 0.3577,
|
| 229 |
"step": 300
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 1.24,
|
| 233 |
+
"grad_norm": 7.286658763885498,
|
| 234 |
"learning_rate": 1.9466666666666668e-05,
|
| 235 |
+
"loss": 0.3507,
|
| 236 |
"step": 310
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 1.28,
|
| 240 |
+
"grad_norm": 88.7168960571289,
|
| 241 |
"learning_rate": 1.9377777777777778e-05,
|
| 242 |
+
"loss": 0.3419,
|
| 243 |
"step": 320
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 1.32,
|
| 247 |
+
"grad_norm": 10.988639831542969,
|
| 248 |
"learning_rate": 1.928888888888889e-05,
|
| 249 |
+
"loss": 0.3714,
|
| 250 |
"step": 330
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 1.3599999999999999,
|
| 254 |
+
"grad_norm": 58.80833435058594,
|
| 255 |
"learning_rate": 1.9200000000000003e-05,
|
| 256 |
+
"loss": 0.3088,
|
| 257 |
"step": 340
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 1.4,
|
| 261 |
+
"grad_norm": 44.44467544555664,
|
| 262 |
"learning_rate": 1.9111111111111113e-05,
|
| 263 |
+
"loss": 0.3212,
|
| 264 |
"step": 350
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 1.44,
|
| 268 |
+
"grad_norm": 25.056461334228516,
|
| 269 |
"learning_rate": 1.9022222222222223e-05,
|
| 270 |
+
"loss": 0.4266,
|
| 271 |
"step": 360
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 1.48,
|
| 275 |
+
"grad_norm": 76.53874969482422,
|
| 276 |
"learning_rate": 1.8933333333333334e-05,
|
| 277 |
+
"loss": 0.3125,
|
| 278 |
"step": 370
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 1.52,
|
| 282 |
+
"grad_norm": 57.03301239013672,
|
| 283 |
"learning_rate": 1.8844444444444444e-05,
|
| 284 |
+
"loss": 0.4589,
|
| 285 |
"step": 380
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 1.56,
|
| 289 |
+
"grad_norm": 49.278892517089844,
|
| 290 |
"learning_rate": 1.8755555555555558e-05,
|
| 291 |
+
"loss": 0.3832,
|
| 292 |
"step": 390
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 1.6,
|
| 296 |
+
"grad_norm": 56.22084045410156,
|
| 297 |
"learning_rate": 1.866666666666667e-05,
|
| 298 |
+
"loss": 0.2668,
|
| 299 |
"step": 400
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 1.6400000000000001,
|
| 303 |
+
"grad_norm": 70.71886444091797,
|
| 304 |
"learning_rate": 1.857777777777778e-05,
|
| 305 |
+
"loss": 0.3858,
|
| 306 |
"step": 410
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 1.6800000000000002,
|
| 310 |
+
"grad_norm": 55.63289260864258,
|
| 311 |
"learning_rate": 1.848888888888889e-05,
|
| 312 |
+
"loss": 0.3321,
|
| 313 |
"step": 420
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 1.72,
|
| 317 |
+
"grad_norm": 54.63759231567383,
|
| 318 |
"learning_rate": 1.8400000000000003e-05,
|
| 319 |
+
"loss": 0.356,
|
| 320 |
"step": 430
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 1.76,
|
| 324 |
+
"grad_norm": 95.25802612304688,
|
| 325 |
"learning_rate": 1.8311111111111114e-05,
|
| 326 |
+
"loss": 0.2692,
|
| 327 |
"step": 440
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 1.8,
|
| 331 |
+
"grad_norm": 105.18350982666016,
|
| 332 |
"learning_rate": 1.8222222222222224e-05,
|
| 333 |
+
"loss": 0.3576,
|
| 334 |
"step": 450
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 1.8399999999999999,
|
| 338 |
+
"grad_norm": 57.272056579589844,
|
| 339 |
"learning_rate": 1.8133333333333335e-05,
|
| 340 |
+
"loss": 0.5661,
|
| 341 |
"step": 460
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 1.88,
|
| 345 |
+
"grad_norm": 17.590261459350586,
|
| 346 |
"learning_rate": 1.8044444444444445e-05,
|
| 347 |
+
"loss": 0.2745,
|
| 348 |
"step": 470
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 1.92,
|
| 352 |
+
"grad_norm": 41.226783752441406,
|
| 353 |
"learning_rate": 1.7955555555555556e-05,
|
| 354 |
+
"loss": 0.3762,
|
| 355 |
"step": 480
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 1.96,
|
| 359 |
+
"grad_norm": 98.6812973022461,
|
| 360 |
"learning_rate": 1.7866666666666666e-05,
|
| 361 |
+
"loss": 0.2868,
|
| 362 |
"step": 490
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 2.0,
|
| 366 |
+
"grad_norm": 25.974720001220703,
|
| 367 |
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 0.5345,
|
| 369 |
"step": 500
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 2.0,
|
| 373 |
+
"eval_accuracy": 0.878,
|
| 374 |
+
"eval_f1": 0.8770706559649587,
|
| 375 |
+
"eval_loss": 0.4389978051185608,
|
| 376 |
+
"eval_runtime": 8.7088,
|
| 377 |
+
"eval_samples_per_second": 57.413,
|
| 378 |
+
"eval_steps_per_second": 14.353,
|
| 379 |
"step": 500
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 2.04,
|
| 383 |
+
"grad_norm": 37.647239685058594,
|
| 384 |
"learning_rate": 1.768888888888889e-05,
|
| 385 |
+
"loss": 0.3808,
|
| 386 |
"step": 510
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 2.08,
|
| 390 |
+
"grad_norm": 12.569307327270508,
|
| 391 |
"learning_rate": 1.76e-05,
|
| 392 |
+
"loss": 0.2284,
|
| 393 |
"step": 520
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 2.12,
|
| 397 |
+
"grad_norm": 26.684873580932617,
|
| 398 |
"learning_rate": 1.751111111111111e-05,
|
| 399 |
+
"loss": 0.3773,
|
| 400 |
"step": 530
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 2.16,
|
| 404 |
+
"grad_norm": 50.10330581665039,
|
| 405 |
"learning_rate": 1.7422222222222222e-05,
|
| 406 |
+
"loss": 0.3123,
|
| 407 |
"step": 540
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 2.2,
|
| 411 |
+
"grad_norm": 58.362998962402344,
|
| 412 |
"learning_rate": 1.7333333333333336e-05,
|
| 413 |
+
"loss": 0.3619,
|
| 414 |
"step": 550
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 2.24,
|
| 418 |
+
"grad_norm": 38.542510986328125,
|
| 419 |
"learning_rate": 1.7244444444444446e-05,
|
| 420 |
+
"loss": 0.4542,
|
| 421 |
"step": 560
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 2.2800000000000002,
|
| 425 |
+
"grad_norm": 19.456159591674805,
|
| 426 |
"learning_rate": 1.7155555555555557e-05,
|
| 427 |
+
"loss": 0.3001,
|
| 428 |
"step": 570
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 2.32,
|
| 432 |
+
"grad_norm": 49.56319808959961,
|
| 433 |
"learning_rate": 1.706666666666667e-05,
|
| 434 |
+
"loss": 0.2794,
|
| 435 |
"step": 580
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 2.36,
|
| 439 |
+
"grad_norm": 38.250526428222656,
|
| 440 |
"learning_rate": 1.697777777777778e-05,
|
| 441 |
+
"loss": 0.3814,
|
| 442 |
"step": 590
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 2.4,
|
| 446 |
+
"grad_norm": 23.731311798095703,
|
| 447 |
"learning_rate": 1.688888888888889e-05,
|
| 448 |
+
"loss": 0.271,
|
| 449 |
"step": 600
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 2.44,
|
| 453 |
+
"grad_norm": 67.27165985107422,
|
| 454 |
"learning_rate": 1.6800000000000002e-05,
|
| 455 |
+
"loss": 0.268,
|
| 456 |
"step": 610
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 2.48,
|
| 460 |
+
"grad_norm": 55.98159408569336,
|
| 461 |
"learning_rate": 1.6711111111111112e-05,
|
| 462 |
+
"loss": 0.3155,
|
| 463 |
"step": 620
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 2.52,
|
| 467 |
+
"grad_norm": 73.56021881103516,
|
| 468 |
"learning_rate": 1.6622222222222223e-05,
|
| 469 |
+
"loss": 0.335,
|
| 470 |
"step": 630
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 2.56,
|
| 474 |
+
"grad_norm": 34.84354782104492,
|
| 475 |
"learning_rate": 1.6533333333333333e-05,
|
| 476 |
+
"loss": 0.3491,
|
| 477 |
"step": 640
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 2.6,
|
| 481 |
+
"grad_norm": 53.700233459472656,
|
| 482 |
"learning_rate": 1.6444444444444444e-05,
|
| 483 |
+
"loss": 0.2745,
|
| 484 |
"step": 650
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"epoch": 2.64,
|
| 488 |
+
"grad_norm": 91.70999908447266,
|
| 489 |
"learning_rate": 1.6355555555555557e-05,
|
| 490 |
+
"loss": 0.2777,
|
| 491 |
"step": 660
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 2.68,
|
| 495 |
+
"grad_norm": 43.926513671875,
|
| 496 |
"learning_rate": 1.6266666666666668e-05,
|
| 497 |
+
"loss": 0.3612,
|
| 498 |
"step": 670
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 2.7199999999999998,
|
| 502 |
+
"grad_norm": 80.7772216796875,
|
| 503 |
"learning_rate": 1.617777777777778e-05,
|
| 504 |
+
"loss": 0.4634,
|
| 505 |
"step": 680
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 2.76,
|
| 509 |
+
"grad_norm": 41.586029052734375,
|
| 510 |
"learning_rate": 1.608888888888889e-05,
|
| 511 |
+
"loss": 0.5096,
|
| 512 |
"step": 690
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 2.8,
|
| 516 |
+
"grad_norm": 49.59820556640625,
|
| 517 |
"learning_rate": 1.6000000000000003e-05,
|
| 518 |
+
"loss": 0.5235,
|
| 519 |
"step": 700
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 2.84,
|
| 523 |
+
"grad_norm": 30.699186325073242,
|
| 524 |
"learning_rate": 1.5911111111111113e-05,
|
| 525 |
+
"loss": 0.2734,
|
| 526 |
"step": 710
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 2.88,
|
| 530 |
+
"grad_norm": 68.27303314208984,
|
| 531 |
"learning_rate": 1.5822222222222224e-05,
|
| 532 |
+
"loss": 0.2262,
|
| 533 |
"step": 720
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 2.92,
|
| 537 |
+
"grad_norm": 27.952354431152344,
|
| 538 |
"learning_rate": 1.5733333333333334e-05,
|
| 539 |
+
"loss": 0.2699,
|
| 540 |
"step": 730
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 2.96,
|
| 544 |
+
"grad_norm": 66.80079650878906,
|
| 545 |
"learning_rate": 1.5644444444444448e-05,
|
| 546 |
+
"loss": 0.2604,
|
| 547 |
"step": 740
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 3.0,
|
| 551 |
+
"grad_norm": 61.24441146850586,
|
| 552 |
"learning_rate": 1.555555555555556e-05,
|
| 553 |
+
"loss": 0.4693,
|
| 554 |
"step": 750
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 3.0,
|
| 558 |
+
"eval_accuracy": 0.88,
|
| 559 |
+
"eval_f1": 0.8795642760077516,
|
| 560 |
+
"eval_loss": 0.3856970965862274,
|
| 561 |
+
"eval_runtime": 8.5744,
|
| 562 |
+
"eval_samples_per_second": 58.313,
|
| 563 |
+
"eval_steps_per_second": 14.578,
|
| 564 |
"step": 750
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 3.04,
|
| 568 |
+
"grad_norm": 18.007030487060547,
|
| 569 |
"learning_rate": 1.546666666666667e-05,
|
| 570 |
+
"loss": 0.3052,
|
| 571 |
"step": 760
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 3.08,
|
| 575 |
+
"grad_norm": 27.437442779541016,
|
| 576 |
"learning_rate": 1.537777777777778e-05,
|
| 577 |
+
"loss": 0.379,
|
| 578 |
"step": 770
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 3.12,
|
| 582 |
+
"grad_norm": 21.621686935424805,
|
| 583 |
"learning_rate": 1.528888888888889e-05,
|
| 584 |
+
"loss": 0.1708,
|
| 585 |
"step": 780
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 3.16,
|
| 589 |
+
"grad_norm": 43.909889221191406,
|
| 590 |
"learning_rate": 1.5200000000000002e-05,
|
| 591 |
+
"loss": 0.3133,
|
| 592 |
"step": 790
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 3.2,
|
| 596 |
+
"grad_norm": 18.5758056640625,
|
| 597 |
"learning_rate": 1.5111111111111112e-05,
|
| 598 |
+
"loss": 0.2785,
|
| 599 |
"step": 800
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 3.24,
|
| 603 |
+
"grad_norm": 54.679080963134766,
|
| 604 |
"learning_rate": 1.5022222222222223e-05,
|
| 605 |
+
"loss": 0.3306,
|
| 606 |
"step": 810
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 3.2800000000000002,
|
| 610 |
+
"grad_norm": 8.038825988769531,
|
| 611 |
"learning_rate": 1.4933333333333335e-05,
|
| 612 |
+
"loss": 0.3865,
|
| 613 |
"step": 820
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 3.32,
|
| 617 |
+
"grad_norm": 38.3331413269043,
|
| 618 |
"learning_rate": 1.4844444444444445e-05,
|
| 619 |
+
"loss": 0.2825,
|
| 620 |
"step": 830
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 3.36,
|
| 624 |
+
"grad_norm": 33.338321685791016,
|
| 625 |
"learning_rate": 1.4755555555555556e-05,
|
| 626 |
+
"loss": 0.3358,
|
| 627 |
"step": 840
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 3.4,
|
| 631 |
+
"grad_norm": 17.133817672729492,
|
| 632 |
"learning_rate": 1.4666666666666666e-05,
|
| 633 |
+
"loss": 0.2373,
|
| 634 |
"step": 850
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 3.44,
|
| 638 |
+
"grad_norm": 38.80360794067383,
|
| 639 |
"learning_rate": 1.457777777777778e-05,
|
| 640 |
+
"loss": 0.2955,
|
| 641 |
"step": 860
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 3.48,
|
| 645 |
+
"grad_norm": 70.89875030517578,
|
| 646 |
"learning_rate": 1.448888888888889e-05,
|
| 647 |
+
"loss": 0.2965,
|
| 648 |
"step": 870
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 3.52,
|
| 652 |
+
"grad_norm": 21.7913875579834,
|
| 653 |
"learning_rate": 1.4400000000000001e-05,
|
| 654 |
+
"loss": 0.2547,
|
| 655 |
"step": 880
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 3.56,
|
| 659 |
+
"grad_norm": 69.4725570678711,
|
| 660 |
"learning_rate": 1.4311111111111111e-05,
|
| 661 |
+
"loss": 0.3298,
|
| 662 |
"step": 890
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 3.6,
|
| 666 |
+
"grad_norm": 55.30929946899414,
|
| 667 |
"learning_rate": 1.4222222222222224e-05,
|
| 668 |
+
"loss": 0.3039,
|
| 669 |
"step": 900
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 3.64,
|
| 673 |
+
"grad_norm": 14.594221115112305,
|
| 674 |
"learning_rate": 1.4133333333333334e-05,
|
| 675 |
+
"loss": 0.502,
|
| 676 |
"step": 910
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 3.68,
|
| 680 |
+
"grad_norm": 25.05082893371582,
|
| 681 |
"learning_rate": 1.4044444444444445e-05,
|
| 682 |
+
"loss": 0.2026,
|
| 683 |
"step": 920
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 3.7199999999999998,
|
| 687 |
+
"grad_norm": 22.42095947265625,
|
| 688 |
"learning_rate": 1.3955555555555558e-05,
|
| 689 |
+
"loss": 0.3169,
|
| 690 |
"step": 930
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 3.76,
|
| 694 |
+
"grad_norm": 87.3176498413086,
|
| 695 |
"learning_rate": 1.3866666666666669e-05,
|
| 696 |
+
"loss": 0.173,
|
| 697 |
"step": 940
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 3.8,
|
| 701 |
+
"grad_norm": 47.08412170410156,
|
| 702 |
"learning_rate": 1.377777777777778e-05,
|
| 703 |
+
"loss": 0.2126,
|
| 704 |
"step": 950
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 3.84,
|
| 708 |
+
"grad_norm": 26.897066116333008,
|
| 709 |
"learning_rate": 1.368888888888889e-05,
|
| 710 |
+
"loss": 0.3429,
|
| 711 |
"step": 960
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 3.88,
|
| 715 |
+
"grad_norm": 45.889381408691406,
|
| 716 |
"learning_rate": 1.3600000000000002e-05,
|
| 717 |
+
"loss": 0.3655,
|
| 718 |
"step": 970
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 3.92,
|
| 722 |
+
"grad_norm": 72.64950561523438,
|
| 723 |
"learning_rate": 1.3511111111111112e-05,
|
| 724 |
+
"loss": 0.2785,
|
| 725 |
"step": 980
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 3.96,
|
| 729 |
+
"grad_norm": 74.62352752685547,
|
| 730 |
"learning_rate": 1.3422222222222223e-05,
|
| 731 |
+
"loss": 0.2916,
|
| 732 |
"step": 990
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 4.0,
|
| 736 |
+
"grad_norm": 90.89289855957031,
|
| 737 |
"learning_rate": 1.3333333333333333e-05,
|
| 738 |
+
"loss": 0.1933,
|
| 739 |
"step": 1000
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 4.0,
|
| 743 |
+
"eval_accuracy": 0.894,
|
| 744 |
+
"eval_f1": 0.8947502154752695,
|
| 745 |
+
"eval_loss": 0.3444240093231201,
|
| 746 |
+
"eval_runtime": 8.6975,
|
| 747 |
+
"eval_samples_per_second": 57.488,
|
| 748 |
+
"eval_steps_per_second": 14.372,
|
| 749 |
"step": 1000
|
| 750 |
},
|
| 751 |
{
|
| 752 |
"epoch": 4.04,
|
| 753 |
+
"grad_norm": 55.490447998046875,
|
| 754 |
"learning_rate": 1.3244444444444447e-05,
|
| 755 |
+
"loss": 0.1877,
|
| 756 |
"step": 1010
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"epoch": 4.08,
|
| 760 |
+
"grad_norm": 70.09012603759766,
|
| 761 |
"learning_rate": 1.3155555555555558e-05,
|
| 762 |
+
"loss": 0.348,
|
| 763 |
"step": 1020
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 4.12,
|
| 767 |
+
"grad_norm": 74.7720947265625,
|
| 768 |
"learning_rate": 1.3066666666666668e-05,
|
| 769 |
+
"loss": 0.3635,
|
| 770 |
"step": 1030
|
| 771 |
},
|
| 772 |
{
|
| 773 |
"epoch": 4.16,
|
| 774 |
+
"grad_norm": 37.04428482055664,
|
| 775 |
"learning_rate": 1.2977777777777779e-05,
|
| 776 |
+
"loss": 0.3447,
|
| 777 |
"step": 1040
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 4.2,
|
| 781 |
+
"grad_norm": 77.90045928955078,
|
| 782 |
"learning_rate": 1.288888888888889e-05,
|
| 783 |
+
"loss": 0.3281,
|
| 784 |
"step": 1050
|
| 785 |
},
|
| 786 |
{
|
| 787 |
"epoch": 4.24,
|
| 788 |
+
"grad_norm": 92.32732391357422,
|
| 789 |
"learning_rate": 1.2800000000000001e-05,
|
| 790 |
+
"loss": 0.2735,
|
| 791 |
"step": 1060
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 4.28,
|
| 795 |
+
"grad_norm": 44.78059387207031,
|
| 796 |
"learning_rate": 1.2711111111111112e-05,
|
| 797 |
+
"loss": 0.3756,
|
| 798 |
"step": 1070
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 4.32,
|
| 802 |
+
"grad_norm": 28.424644470214844,
|
| 803 |
"learning_rate": 1.2622222222222222e-05,
|
| 804 |
+
"loss": 0.1935,
|
| 805 |
"step": 1080
|
| 806 |
},
|
| 807 |
{
|
| 808 |
"epoch": 4.36,
|
| 809 |
+
"grad_norm": 50.174949645996094,
|
| 810 |
"learning_rate": 1.2533333333333336e-05,
|
| 811 |
+
"loss": 0.3282,
|
| 812 |
"step": 1090
|
| 813 |
},
|
| 814 |
{
|
| 815 |
"epoch": 4.4,
|
| 816 |
+
"grad_norm": 13.964503288269043,
|
| 817 |
"learning_rate": 1.2444444444444446e-05,
|
| 818 |
+
"loss": 0.1625,
|
| 819 |
"step": 1100
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 4.44,
|
| 823 |
+
"grad_norm": 90.46607971191406,
|
| 824 |
"learning_rate": 1.2355555555555557e-05,
|
| 825 |
+
"loss": 0.2342,
|
| 826 |
"step": 1110
|
| 827 |
},
|
| 828 |
{
|
| 829 |
"epoch": 4.48,
|
| 830 |
+
"grad_norm": 2.025235891342163,
|
| 831 |
"learning_rate": 1.2266666666666667e-05,
|
| 832 |
+
"loss": 0.2906,
|
| 833 |
"step": 1120
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 4.52,
|
| 837 |
+
"grad_norm": 36.99541091918945,
|
| 838 |
"learning_rate": 1.217777777777778e-05,
|
| 839 |
+
"loss": 0.2817,
|
| 840 |
"step": 1130
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 4.5600000000000005,
|
| 844 |
+
"grad_norm": 84.70581817626953,
|
| 845 |
"learning_rate": 1.208888888888889e-05,
|
| 846 |
+
"loss": 0.3246,
|
| 847 |
"step": 1140
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 4.6,
|
| 851 |
+
"grad_norm": 27.94813346862793,
|
| 852 |
"learning_rate": 1.2e-05,
|
| 853 |
+
"loss": 0.3587,
|
| 854 |
"step": 1150
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 4.64,
|
| 858 |
+
"grad_norm": 8.473387718200684,
|
| 859 |
"learning_rate": 1.191111111111111e-05,
|
| 860 |
+
"loss": 0.2862,
|
| 861 |
"step": 1160
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 4.68,
|
| 865 |
+
"grad_norm": 42.427734375,
|
| 866 |
"learning_rate": 1.1822222222222225e-05,
|
| 867 |
+
"loss": 0.2924,
|
| 868 |
"step": 1170
|
| 869 |
},
|
| 870 |
{
|
| 871 |
"epoch": 4.72,
|
| 872 |
+
"grad_norm": 65.75909423828125,
|
| 873 |
"learning_rate": 1.1733333333333335e-05,
|
| 874 |
+
"loss": 0.2524,
|
| 875 |
"step": 1180
|
| 876 |
},
|
| 877 |
{
|
| 878 |
"epoch": 4.76,
|
| 879 |
+
"grad_norm": 72.92707061767578,
|
| 880 |
"learning_rate": 1.1644444444444446e-05,
|
| 881 |
+
"loss": 0.2454,
|
| 882 |
"step": 1190
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"epoch": 4.8,
|
| 886 |
+
"grad_norm": 30.95335578918457,
|
| 887 |
"learning_rate": 1.1555555555555556e-05,
|
| 888 |
+
"loss": 0.303,
|
| 889 |
"step": 1200
|
| 890 |
},
|
| 891 |
{
|
| 892 |
"epoch": 4.84,
|
| 893 |
+
"grad_norm": 26.16335678100586,
|
| 894 |
"learning_rate": 1.1466666666666668e-05,
|
| 895 |
+
"loss": 0.3051,
|
| 896 |
"step": 1210
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 4.88,
|
| 900 |
+
"grad_norm": 34.4001350402832,
|
| 901 |
"learning_rate": 1.1377777777777779e-05,
|
| 902 |
+
"loss": 0.1801,
|
| 903 |
"step": 1220
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 4.92,
|
| 907 |
+
"grad_norm": 43.86663818359375,
|
| 908 |
"learning_rate": 1.1288888888888889e-05,
|
| 909 |
+
"loss": 0.168,
|
| 910 |
"step": 1230
|
| 911 |
},
|
| 912 |
{
|
| 913 |
"epoch": 4.96,
|
| 914 |
+
"grad_norm": 0.3658877909183502,
|
| 915 |
"learning_rate": 1.1200000000000001e-05,
|
| 916 |
+
"loss": 0.2493,
|
| 917 |
"step": 1240
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 5.0,
|
| 921 |
+
"grad_norm": 17.853328704833984,
|
| 922 |
"learning_rate": 1.1111111111111113e-05,
|
| 923 |
+
"loss": 0.3146,
|
| 924 |
"step": 1250
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 5.0,
|
| 928 |
+
"eval_accuracy": 0.936,
|
| 929 |
+
"eval_f1": 0.9361975859190919,
|
| 930 |
+
"eval_loss": 0.2456333488225937,
|
| 931 |
+
"eval_runtime": 8.6547,
|
| 932 |
+
"eval_samples_per_second": 57.772,
|
| 933 |
+
"eval_steps_per_second": 14.443,
|
| 934 |
"step": 1250
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 5.04,
|
| 938 |
+
"grad_norm": 28.078502655029297,
|
| 939 |
"learning_rate": 1.1022222222222224e-05,
|
| 940 |
+
"loss": 0.1975,
|
| 941 |
"step": 1260
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 5.08,
|
| 945 |
+
"grad_norm": 30.93500518798828,
|
| 946 |
"learning_rate": 1.0933333333333334e-05,
|
| 947 |
+
"loss": 0.1725,
|
| 948 |
"step": 1270
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 5.12,
|
| 952 |
+
"grad_norm": 36.137969970703125,
|
| 953 |
"learning_rate": 1.0844444444444446e-05,
|
| 954 |
+
"loss": 0.3072,
|
| 955 |
"step": 1280
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 5.16,
|
| 959 |
+
"grad_norm": 38.812007904052734,
|
| 960 |
"learning_rate": 1.0755555555555557e-05,
|
| 961 |
+
"loss": 0.2047,
|
| 962 |
"step": 1290
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 5.2,
|
| 966 |
+
"grad_norm": 62.65950393676758,
|
| 967 |
"learning_rate": 1.0666666666666667e-05,
|
| 968 |
+
"loss": 0.2897,
|
| 969 |
"step": 1300
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 5.24,
|
| 973 |
+
"grad_norm": 69.6206283569336,
|
| 974 |
"learning_rate": 1.0577777777777778e-05,
|
| 975 |
+
"loss": 0.2959,
|
| 976 |
"step": 1310
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 5.28,
|
| 980 |
+
"grad_norm": 53.226375579833984,
|
| 981 |
"learning_rate": 1.048888888888889e-05,
|
| 982 |
+
"loss": 0.3842,
|
| 983 |
"step": 1320
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 5.32,
|
| 987 |
+
"grad_norm": 120.20613098144531,
|
| 988 |
"learning_rate": 1.04e-05,
|
| 989 |
+
"loss": 0.2835,
|
| 990 |
"step": 1330
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 5.36,
|
| 994 |
+
"grad_norm": 19.712247848510742,
|
| 995 |
"learning_rate": 1.0311111111111113e-05,
|
| 996 |
+
"loss": 0.2208,
|
| 997 |
"step": 1340
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
"epoch": 5.4,
|
| 1001 |
+
"grad_norm": 39.82862854003906,
|
| 1002 |
"learning_rate": 1.0222222222222223e-05,
|
| 1003 |
+
"loss": 0.3166,
|
| 1004 |
"step": 1350
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 5.44,
|
| 1008 |
+
"grad_norm": 25.11990737915039,
|
| 1009 |
"learning_rate": 1.0133333333333335e-05,
|
| 1010 |
+
"loss": 0.266,
|
| 1011 |
"step": 1360
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 5.48,
|
| 1015 |
+
"grad_norm": 29.185226440429688,
|
| 1016 |
"learning_rate": 1.0044444444444446e-05,
|
| 1017 |
+
"loss": 0.1907,
|
| 1018 |
"step": 1370
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
"epoch": 5.52,
|
| 1022 |
+
"grad_norm": 51.418678283691406,
|
| 1023 |
"learning_rate": 9.955555555555556e-06,
|
| 1024 |
+
"loss": 0.2762,
|
| 1025 |
"step": 1380
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 5.5600000000000005,
|
| 1029 |
+
"grad_norm": 8.843996047973633,
|
| 1030 |
"learning_rate": 9.866666666666668e-06,
|
| 1031 |
+
"loss": 0.1223,
|
| 1032 |
"step": 1390
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
"epoch": 5.6,
|
| 1036 |
+
"grad_norm": 91.5838851928711,
|
| 1037 |
"learning_rate": 9.777777777777779e-06,
|
| 1038 |
+
"loss": 0.2242,
|
| 1039 |
"step": 1400
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
"epoch": 5.64,
|
| 1043 |
+
"grad_norm": 58.07487869262695,
|
| 1044 |
"learning_rate": 9.688888888888889e-06,
|
| 1045 |
+
"loss": 0.2818,
|
| 1046 |
"step": 1410
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
"epoch": 5.68,
|
| 1050 |
+
"grad_norm": 63.59052658081055,
|
| 1051 |
"learning_rate": 9.600000000000001e-06,
|
| 1052 |
+
"loss": 0.2808,
|
| 1053 |
"step": 1420
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 5.72,
|
| 1057 |
+
"grad_norm": 35.42782974243164,
|
| 1058 |
"learning_rate": 9.511111111111112e-06,
|
| 1059 |
+
"loss": 0.2617,
|
| 1060 |
"step": 1430
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
"epoch": 5.76,
|
| 1064 |
+
"grad_norm": 41.844383239746094,
|
| 1065 |
"learning_rate": 9.422222222222222e-06,
|
| 1066 |
+
"loss": 0.1203,
|
| 1067 |
"step": 1440
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
"epoch": 5.8,
|
| 1071 |
+
"grad_norm": 51.4361457824707,
|
| 1072 |
"learning_rate": 9.333333333333334e-06,
|
| 1073 |
+
"loss": 0.306,
|
| 1074 |
"step": 1450
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
"epoch": 5.84,
|
| 1078 |
+
"grad_norm": 29.05099105834961,
|
| 1079 |
"learning_rate": 9.244444444444445e-06,
|
| 1080 |
+
"loss": 0.4744,
|
| 1081 |
"step": 1460
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
"epoch": 5.88,
|
| 1085 |
+
"grad_norm": 51.445220947265625,
|
| 1086 |
"learning_rate": 9.155555555555557e-06,
|
| 1087 |
+
"loss": 0.3157,
|
| 1088 |
"step": 1470
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
"epoch": 5.92,
|
| 1092 |
+
"grad_norm": 34.62455368041992,
|
| 1093 |
"learning_rate": 9.066666666666667e-06,
|
| 1094 |
+
"loss": 0.22,
|
| 1095 |
"step": 1480
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 5.96,
|
| 1099 |
+
"grad_norm": 12.388022422790527,
|
| 1100 |
"learning_rate": 8.977777777777778e-06,
|
| 1101 |
+
"loss": 0.2072,
|
| 1102 |
"step": 1490
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
"epoch": 6.0,
|
| 1106 |
+
"grad_norm": 9.763510704040527,
|
| 1107 |
"learning_rate": 8.888888888888888e-06,
|
| 1108 |
+
"loss": 0.1832,
|
| 1109 |
"step": 1500
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
"epoch": 6.0,
|
| 1113 |
+
"eval_accuracy": 0.924,
|
| 1114 |
+
"eval_f1": 0.9229000637110923,
|
| 1115 |
+
"eval_loss": 0.3368554711341858,
|
| 1116 |
+
"eval_runtime": 8.557,
|
| 1117 |
+
"eval_samples_per_second": 58.432,
|
| 1118 |
+
"eval_steps_per_second": 14.608,
|
| 1119 |
"step": 1500
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 6.04,
|
| 1123 |
+
"grad_norm": 9.751482963562012,
|
| 1124 |
"learning_rate": 8.8e-06,
|
| 1125 |
+
"loss": 0.2234,
|
| 1126 |
"step": 1510
|
| 1127 |
},
|
| 1128 |
{
|
| 1129 |
"epoch": 6.08,
|
| 1130 |
+
"grad_norm": 3.580552101135254,
|
| 1131 |
"learning_rate": 8.711111111111111e-06,
|
| 1132 |
+
"loss": 0.1233,
|
| 1133 |
"step": 1520
|
| 1134 |
},
|
| 1135 |
{
|
| 1136 |
"epoch": 6.12,
|
| 1137 |
+
"grad_norm": 30.625099182128906,
|
| 1138 |
"learning_rate": 8.622222222222223e-06,
|
| 1139 |
+
"loss": 0.1805,
|
| 1140 |
"step": 1530
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 6.16,
|
| 1144 |
+
"grad_norm": 23.020915985107422,
|
| 1145 |
"learning_rate": 8.533333333333335e-06,
|
| 1146 |
+
"loss": 0.2868,
|
| 1147 |
"step": 1540
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
"epoch": 6.2,
|
| 1151 |
+
"grad_norm": 18.9671630859375,
|
| 1152 |
"learning_rate": 8.444444444444446e-06,
|
| 1153 |
+
"loss": 0.2041,
|
| 1154 |
"step": 1550
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 6.24,
|
| 1158 |
+
"grad_norm": 33.78700256347656,
|
| 1159 |
"learning_rate": 8.355555555555556e-06,
|
| 1160 |
+
"loss": 0.1599,
|
| 1161 |
"step": 1560
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 6.28,
|
| 1165 |
+
"grad_norm": 75.42900848388672,
|
| 1166 |
"learning_rate": 8.266666666666667e-06,
|
| 1167 |
+
"loss": 0.1084,
|
| 1168 |
"step": 1570
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
"epoch": 6.32,
|
| 1172 |
+
"grad_norm": 2.74202299118042,
|
| 1173 |
"learning_rate": 8.177777777777779e-06,
|
| 1174 |
+
"loss": 0.2967,
|
| 1175 |
"step": 1580
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
"epoch": 6.36,
|
| 1179 |
+
"grad_norm": 51.8353157043457,
|
| 1180 |
"learning_rate": 8.08888888888889e-06,
|
| 1181 |
+
"loss": 0.3407,
|
| 1182 |
"step": 1590
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 6.4,
|
| 1186 |
+
"grad_norm": 10.7664213180542,
|
| 1187 |
"learning_rate": 8.000000000000001e-06,
|
| 1188 |
+
"loss": 0.3942,
|
| 1189 |
"step": 1600
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 6.44,
|
| 1193 |
+
"grad_norm": 25.22667694091797,
|
| 1194 |
"learning_rate": 7.911111111111112e-06,
|
| 1195 |
+
"loss": 0.1484,
|
| 1196 |
"step": 1610
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
"epoch": 6.48,
|
| 1200 |
+
"grad_norm": 7.64856481552124,
|
| 1201 |
"learning_rate": 7.822222222222224e-06,
|
| 1202 |
+
"loss": 0.2024,
|
| 1203 |
"step": 1620
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 6.52,
|
| 1207 |
+
"grad_norm": 12.741067886352539,
|
| 1208 |
"learning_rate": 7.733333333333334e-06,
|
| 1209 |
+
"loss": 0.2127,
|
| 1210 |
"step": 1630
|
| 1211 |
},
|
| 1212 |
{
|
| 1213 |
"epoch": 6.5600000000000005,
|
| 1214 |
+
"grad_norm": 33.97446060180664,
|
| 1215 |
"learning_rate": 7.644444444444445e-06,
|
| 1216 |
+
"loss": 0.1763,
|
| 1217 |
"step": 1640
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 6.6,
|
| 1221 |
+
"grad_norm": 22.31916618347168,
|
| 1222 |
"learning_rate": 7.555555555555556e-06,
|
| 1223 |
+
"loss": 0.1481,
|
| 1224 |
"step": 1650
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 6.64,
|
| 1228 |
+
"grad_norm": 31.509164810180664,
|
| 1229 |
"learning_rate": 7.4666666666666675e-06,
|
| 1230 |
+
"loss": 0.2496,
|
| 1231 |
"step": 1660
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
"epoch": 6.68,
|
| 1235 |
+
"grad_norm": 49.01666259765625,
|
| 1236 |
"learning_rate": 7.377777777777778e-06,
|
| 1237 |
+
"loss": 0.1519,
|
| 1238 |
"step": 1670
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
"epoch": 6.72,
|
| 1242 |
+
"grad_norm": 19.280881881713867,
|
| 1243 |
"learning_rate": 7.28888888888889e-06,
|
| 1244 |
+
"loss": 0.2143,
|
| 1245 |
"step": 1680
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 6.76,
|
| 1249 |
+
"grad_norm": 21.911842346191406,
|
| 1250 |
"learning_rate": 7.2000000000000005e-06,
|
| 1251 |
+
"loss": 0.1652,
|
| 1252 |
"step": 1690
|
| 1253 |
},
|
| 1254 |
{
|
| 1255 |
"epoch": 6.8,
|
| 1256 |
+
"grad_norm": 62.79658126831055,
|
| 1257 |
"learning_rate": 7.111111111111112e-06,
|
| 1258 |
+
"loss": 0.1994,
|
| 1259 |
"step": 1700
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 6.84,
|
| 1263 |
+
"grad_norm": 4.01326322555542,
|
| 1264 |
"learning_rate": 7.022222222222222e-06,
|
| 1265 |
+
"loss": 0.1806,
|
| 1266 |
"step": 1710
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
"epoch": 6.88,
|
| 1270 |
+
"grad_norm": 61.08246994018555,
|
| 1271 |
"learning_rate": 6.9333333333333344e-06,
|
| 1272 |
+
"loss": 0.1763,
|
| 1273 |
"step": 1720
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 6.92,
|
| 1277 |
+
"grad_norm": 64.75476837158203,
|
| 1278 |
"learning_rate": 6.844444444444445e-06,
|
| 1279 |
+
"loss": 0.1214,
|
| 1280 |
"step": 1730
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 6.96,
|
| 1284 |
+
"grad_norm": 63.44350051879883,
|
| 1285 |
"learning_rate": 6.755555555555556e-06,
|
| 1286 |
+
"loss": 0.2009,
|
| 1287 |
"step": 1740
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 7.0,
|
| 1291 |
+
"grad_norm": 7.164996147155762,
|
| 1292 |
"learning_rate": 6.666666666666667e-06,
|
| 1293 |
+
"loss": 0.1407,
|
| 1294 |
"step": 1750
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
"epoch": 7.0,
|
| 1298 |
+
"eval_accuracy": 0.946,
|
| 1299 |
+
"eval_f1": 0.9454404643456045,
|
| 1300 |
+
"eval_loss": 0.3425253629684448,
|
| 1301 |
+
"eval_runtime": 8.5243,
|
| 1302 |
+
"eval_samples_per_second": 58.656,
|
| 1303 |
+
"eval_steps_per_second": 14.664,
|
| 1304 |
"step": 1750
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 7.04,
|
| 1308 |
+
"grad_norm": 63.62957763671875,
|
| 1309 |
"learning_rate": 6.577777777777779e-06,
|
| 1310 |
+
"loss": 0.2602,
|
| 1311 |
"step": 1760
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 7.08,
|
| 1315 |
+
"grad_norm": 44.226463317871094,
|
| 1316 |
"learning_rate": 6.488888888888889e-06,
|
| 1317 |
+
"loss": 0.1125,
|
| 1318 |
"step": 1770
|
| 1319 |
},
|
| 1320 |
{
|
| 1321 |
"epoch": 7.12,
|
| 1322 |
+
"grad_norm": 62.62407684326172,
|
| 1323 |
"learning_rate": 6.4000000000000006e-06,
|
| 1324 |
+
"loss": 0.3144,
|
| 1325 |
"step": 1780
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 7.16,
|
| 1329 |
+
"grad_norm": 41.71411895751953,
|
| 1330 |
"learning_rate": 6.311111111111111e-06,
|
| 1331 |
+
"loss": 0.1585,
|
| 1332 |
"step": 1790
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 7.2,
|
| 1336 |
+
"grad_norm": 33.34163284301758,
|
| 1337 |
"learning_rate": 6.222222222222223e-06,
|
| 1338 |
+
"loss": 0.2164,
|
| 1339 |
"step": 1800
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
"epoch": 7.24,
|
| 1343 |
+
"grad_norm": 51.477291107177734,
|
| 1344 |
"learning_rate": 6.133333333333334e-06,
|
| 1345 |
+
"loss": 0.1467,
|
| 1346 |
"step": 1810
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 7.28,
|
| 1350 |
+
"grad_norm": 4.217121601104736,
|
| 1351 |
"learning_rate": 6.044444444444445e-06,
|
| 1352 |
+
"loss": 0.072,
|
| 1353 |
"step": 1820
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 7.32,
|
| 1357 |
+
"grad_norm": 14.78985595703125,
|
| 1358 |
"learning_rate": 5.955555555555555e-06,
|
| 1359 |
+
"loss": 0.1472,
|
| 1360 |
"step": 1830
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 7.36,
|
| 1364 |
+
"grad_norm": 28.724449157714844,
|
| 1365 |
"learning_rate": 5.8666666666666675e-06,
|
| 1366 |
+
"loss": 0.1792,
|
| 1367 |
"step": 1840
|
| 1368 |
},
|
| 1369 |
{
|
| 1370 |
"epoch": 7.4,
|
| 1371 |
+
"grad_norm": 90.70431518554688,
|
| 1372 |
"learning_rate": 5.777777777777778e-06,
|
| 1373 |
+
"loss": 0.263,
|
| 1374 |
"step": 1850
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 7.44,
|
| 1378 |
+
"grad_norm": 46.434898376464844,
|
| 1379 |
"learning_rate": 5.688888888888889e-06,
|
| 1380 |
+
"loss": 0.1768,
|
| 1381 |
"step": 1860
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 7.48,
|
| 1385 |
+
"grad_norm": 13.007624626159668,
|
| 1386 |
"learning_rate": 5.600000000000001e-06,
|
| 1387 |
+
"loss": 0.0883,
|
| 1388 |
"step": 1870
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 7.52,
|
| 1392 |
+
"grad_norm": 18.006866455078125,
|
| 1393 |
"learning_rate": 5.511111111111112e-06,
|
| 1394 |
+
"loss": 0.1935,
|
| 1395 |
"step": 1880
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 7.5600000000000005,
|
| 1399 |
+
"grad_norm": 17.47731590270996,
|
| 1400 |
"learning_rate": 5.422222222222223e-06,
|
| 1401 |
+
"loss": 0.218,
|
| 1402 |
"step": 1890
|
| 1403 |
},
|
| 1404 |
{
|
| 1405 |
"epoch": 7.6,
|
| 1406 |
+
"grad_norm": 55.587310791015625,
|
| 1407 |
"learning_rate": 5.333333333333334e-06,
|
| 1408 |
+
"loss": 0.2225,
|
| 1409 |
"step": 1900
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 7.64,
|
| 1413 |
+
"grad_norm": 32.001670837402344,
|
| 1414 |
"learning_rate": 5.244444444444445e-06,
|
| 1415 |
+
"loss": 0.1861,
|
| 1416 |
"step": 1910
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 7.68,
|
| 1420 |
+
"grad_norm": 55.86604309082031,
|
| 1421 |
"learning_rate": 5.155555555555556e-06,
|
| 1422 |
+
"loss": 0.1404,
|
| 1423 |
"step": 1920
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 7.72,
|
| 1427 |
+
"grad_norm": 89.22872924804688,
|
| 1428 |
"learning_rate": 5.0666666666666676e-06,
|
| 1429 |
+
"loss": 0.162,
|
| 1430 |
"step": 1930
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 7.76,
|
| 1434 |
+
"grad_norm": 0.25738686323165894,
|
| 1435 |
"learning_rate": 4.977777777777778e-06,
|
| 1436 |
+
"loss": 0.2159,
|
| 1437 |
"step": 1940
|
| 1438 |
},
|
| 1439 |
{
|
| 1440 |
"epoch": 7.8,
|
| 1441 |
+
"grad_norm": 48.370277404785156,
|
| 1442 |
"learning_rate": 4.888888888888889e-06,
|
| 1443 |
+
"loss": 0.171,
|
| 1444 |
"step": 1950
|
| 1445 |
},
|
| 1446 |
{
|
| 1447 |
"epoch": 7.84,
|
| 1448 |
+
"grad_norm": 5.000326633453369,
|
| 1449 |
"learning_rate": 4.800000000000001e-06,
|
| 1450 |
+
"loss": 0.2945,
|
| 1451 |
"step": 1960
|
| 1452 |
},
|
| 1453 |
{
|
| 1454 |
"epoch": 7.88,
|
| 1455 |
+
"grad_norm": 7.4195685386657715,
|
| 1456 |
"learning_rate": 4.711111111111111e-06,
|
| 1457 |
+
"loss": 0.0845,
|
| 1458 |
"step": 1970
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 7.92,
|
| 1462 |
+
"grad_norm": 71.77230072021484,
|
| 1463 |
"learning_rate": 4.622222222222222e-06,
|
| 1464 |
+
"loss": 0.1664,
|
| 1465 |
"step": 1980
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 7.96,
|
| 1469 |
+
"grad_norm": 11.938881874084473,
|
| 1470 |
"learning_rate": 4.533333333333334e-06,
|
| 1471 |
+
"loss": 0.1009,
|
| 1472 |
"step": 1990
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 8.0,
|
| 1476 |
+
"grad_norm": 9.97079086303711,
|
| 1477 |
"learning_rate": 4.444444444444444e-06,
|
| 1478 |
+
"loss": 0.1462,
|
| 1479 |
"step": 2000
|
| 1480 |
},
|
| 1481 |
{
|
| 1482 |
"epoch": 8.0,
|
| 1483 |
+
"eval_accuracy": 0.948,
|
| 1484 |
+
"eval_f1": 0.9475735032806624,
|
| 1485 |
+
"eval_loss": 0.2863907516002655,
|
| 1486 |
+
"eval_runtime": 8.7213,
|
| 1487 |
+
"eval_samples_per_second": 57.331,
|
| 1488 |
+
"eval_steps_per_second": 14.333,
|
| 1489 |
"step": 2000
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
"epoch": 8.04,
|
| 1493 |
+
"grad_norm": 46.91502380371094,
|
| 1494 |
"learning_rate": 4.3555555555555555e-06,
|
| 1495 |
+
"loss": 0.1368,
|
| 1496 |
"step": 2010
|
| 1497 |
},
|
| 1498 |
{
|
| 1499 |
"epoch": 8.08,
|
| 1500 |
+
"grad_norm": 12.112004280090332,
|
| 1501 |
"learning_rate": 4.266666666666668e-06,
|
| 1502 |
+
"loss": 0.0635,
|
| 1503 |
"step": 2020
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 8.12,
|
| 1507 |
+
"grad_norm": 11.893278121948242,
|
| 1508 |
"learning_rate": 4.177777777777778e-06,
|
| 1509 |
+
"loss": 0.2191,
|
| 1510 |
"step": 2030
|
| 1511 |
},
|
| 1512 |
{
|
| 1513 |
"epoch": 8.16,
|
| 1514 |
+
"grad_norm": 56.45474624633789,
|
| 1515 |
"learning_rate": 4.088888888888889e-06,
|
| 1516 |
+
"loss": 0.1351,
|
| 1517 |
"step": 2040
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 8.2,
|
| 1521 |
+
"grad_norm": 22.199668884277344,
|
| 1522 |
"learning_rate": 4.000000000000001e-06,
|
| 1523 |
+
"loss": 0.1389,
|
| 1524 |
"step": 2050
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 8.24,
|
| 1528 |
+
"grad_norm": 13.854080200195312,
|
| 1529 |
"learning_rate": 3.911111111111112e-06,
|
| 1530 |
+
"loss": 0.1661,
|
| 1531 |
"step": 2060
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 8.28,
|
| 1535 |
+
"grad_norm": 44.242244720458984,
|
| 1536 |
"learning_rate": 3.8222222222222224e-06,
|
| 1537 |
+
"loss": 0.16,
|
| 1538 |
"step": 2070
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 8.32,
|
| 1542 |
+
"grad_norm": 12.572860717773438,
|
| 1543 |
"learning_rate": 3.7333333333333337e-06,
|
| 1544 |
+
"loss": 0.1411,
|
| 1545 |
"step": 2080
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 8.36,
|
| 1549 |
+
"grad_norm": 21.231435775756836,
|
| 1550 |
"learning_rate": 3.644444444444445e-06,
|
| 1551 |
+
"loss": 0.2252,
|
| 1552 |
"step": 2090
|
| 1553 |
},
|
| 1554 |
{
|
| 1555 |
"epoch": 8.4,
|
| 1556 |
+
"grad_norm": 7.332576274871826,
|
| 1557 |
"learning_rate": 3.555555555555556e-06,
|
| 1558 |
+
"loss": 0.1545,
|
| 1559 |
"step": 2100
|
| 1560 |
},
|
| 1561 |
{
|
| 1562 |
"epoch": 8.44,
|
| 1563 |
+
"grad_norm": 21.509479522705078,
|
| 1564 |
"learning_rate": 3.4666666666666672e-06,
|
| 1565 |
+
"loss": 0.1005,
|
| 1566 |
"step": 2110
|
| 1567 |
},
|
| 1568 |
{
|
| 1569 |
"epoch": 8.48,
|
| 1570 |
+
"grad_norm": 30.77674674987793,
|
| 1571 |
"learning_rate": 3.377777777777778e-06,
|
| 1572 |
+
"loss": 0.1603,
|
| 1573 |
"step": 2120
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 8.52,
|
| 1577 |
+
"grad_norm": 41.59734344482422,
|
| 1578 |
"learning_rate": 3.2888888888888894e-06,
|
| 1579 |
+
"loss": 0.2069,
|
| 1580 |
"step": 2130
|
| 1581 |
},
|
| 1582 |
{
|
| 1583 |
"epoch": 8.56,
|
| 1584 |
+
"grad_norm": 29.843107223510742,
|
| 1585 |
"learning_rate": 3.2000000000000003e-06,
|
| 1586 |
+
"loss": 0.2436,
|
| 1587 |
"step": 2140
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
"epoch": 8.6,
|
| 1591 |
+
"grad_norm": 38.74693298339844,
|
| 1592 |
"learning_rate": 3.1111111111111116e-06,
|
| 1593 |
+
"loss": 0.1175,
|
| 1594 |
"step": 2150
|
| 1595 |
},
|
| 1596 |
{
|
| 1597 |
"epoch": 8.64,
|
| 1598 |
+
"grad_norm": 15.177172660827637,
|
| 1599 |
"learning_rate": 3.0222222222222225e-06,
|
| 1600 |
+
"loss": 0.1125,
|
| 1601 |
"step": 2160
|
| 1602 |
},
|
| 1603 |
{
|
| 1604 |
"epoch": 8.68,
|
| 1605 |
+
"grad_norm": 46.20457077026367,
|
| 1606 |
"learning_rate": 2.9333333333333338e-06,
|
| 1607 |
+
"loss": 0.1392,
|
| 1608 |
"step": 2170
|
| 1609 |
},
|
| 1610 |
{
|
| 1611 |
"epoch": 8.72,
|
| 1612 |
+
"grad_norm": 0.42567014694213867,
|
| 1613 |
"learning_rate": 2.8444444444444446e-06,
|
| 1614 |
+
"loss": 0.1395,
|
| 1615 |
"step": 2180
|
| 1616 |
},
|
| 1617 |
{
|
| 1618 |
"epoch": 8.76,
|
| 1619 |
+
"grad_norm": 60.429443359375,
|
| 1620 |
"learning_rate": 2.755555555555556e-06,
|
| 1621 |
+
"loss": 0.2866,
|
| 1622 |
"step": 2190
|
| 1623 |
},
|
| 1624 |
{
|
| 1625 |
"epoch": 8.8,
|
| 1626 |
+
"grad_norm": 34.261043548583984,
|
| 1627 |
"learning_rate": 2.666666666666667e-06,
|
| 1628 |
+
"loss": 0.2126,
|
| 1629 |
"step": 2200
|
| 1630 |
},
|
| 1631 |
{
|
| 1632 |
"epoch": 8.84,
|
| 1633 |
+
"grad_norm": 24.502214431762695,
|
| 1634 |
"learning_rate": 2.577777777777778e-06,
|
| 1635 |
+
"loss": 0.131,
|
| 1636 |
"step": 2210
|
| 1637 |
},
|
| 1638 |
{
|
| 1639 |
"epoch": 8.88,
|
| 1640 |
+
"grad_norm": 1.0593976974487305,
|
| 1641 |
"learning_rate": 2.488888888888889e-06,
|
| 1642 |
+
"loss": 0.1685,
|
| 1643 |
"step": 2220
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 8.92,
|
| 1647 |
+
"grad_norm": 26.03633689880371,
|
| 1648 |
"learning_rate": 2.4000000000000003e-06,
|
| 1649 |
+
"loss": 0.1013,
|
| 1650 |
"step": 2230
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 8.96,
|
| 1654 |
+
"grad_norm": 0.4252139925956726,
|
| 1655 |
"learning_rate": 2.311111111111111e-06,
|
| 1656 |
+
"loss": 0.1407,
|
| 1657 |
"step": 2240
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
"epoch": 9.0,
|
| 1661 |
+
"grad_norm": 4.702337741851807,
|
| 1662 |
"learning_rate": 2.222222222222222e-06,
|
| 1663 |
+
"loss": 0.0905,
|
| 1664 |
"step": 2250
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 9.0,
|
| 1668 |
+
"eval_accuracy": 0.956,
|
| 1669 |
+
"eval_f1": 0.9559537578342157,
|
| 1670 |
+
"eval_loss": 0.21772001683712006,
|
| 1671 |
+
"eval_runtime": 8.4726,
|
| 1672 |
+
"eval_samples_per_second": 59.014,
|
| 1673 |
+
"eval_steps_per_second": 14.753,
|
| 1674 |
"step": 2250
|
| 1675 |
},
|
| 1676 |
{
|
| 1677 |
"epoch": 9.04,
|
| 1678 |
+
"grad_norm": 0.3719678223133087,
|
| 1679 |
"learning_rate": 2.133333333333334e-06,
|
| 1680 |
+
"loss": 0.1046,
|
| 1681 |
"step": 2260
|
| 1682 |
},
|
| 1683 |
{
|
| 1684 |
"epoch": 9.08,
|
| 1685 |
+
"grad_norm": 84.62899017333984,
|
| 1686 |
"learning_rate": 2.0444444444444447e-06,
|
| 1687 |
+
"loss": 0.0603,
|
| 1688 |
"step": 2270
|
| 1689 |
},
|
| 1690 |
{
|
| 1691 |
"epoch": 9.12,
|
| 1692 |
+
"grad_norm": 52.96356964111328,
|
| 1693 |
"learning_rate": 1.955555555555556e-06,
|
| 1694 |
+
"loss": 0.1158,
|
| 1695 |
"step": 2280
|
| 1696 |
},
|
| 1697 |
{
|
| 1698 |
"epoch": 9.16,
|
| 1699 |
+
"grad_norm": 15.068770408630371,
|
| 1700 |
"learning_rate": 1.8666666666666669e-06,
|
| 1701 |
+
"loss": 0.1248,
|
| 1702 |
"step": 2290
|
| 1703 |
},
|
| 1704 |
{
|
| 1705 |
"epoch": 9.2,
|
| 1706 |
+
"grad_norm": 59.39225769042969,
|
| 1707 |
"learning_rate": 1.777777777777778e-06,
|
| 1708 |
+
"loss": 0.1852,
|
| 1709 |
"step": 2300
|
| 1710 |
},
|
| 1711 |
{
|
| 1712 |
"epoch": 9.24,
|
| 1713 |
+
"grad_norm": 23.1497859954834,
|
| 1714 |
"learning_rate": 1.688888888888889e-06,
|
| 1715 |
+
"loss": 0.143,
|
| 1716 |
"step": 2310
|
| 1717 |
},
|
| 1718 |
{
|
| 1719 |
"epoch": 9.28,
|
| 1720 |
+
"grad_norm": 87.2287368774414,
|
| 1721 |
"learning_rate": 1.6000000000000001e-06,
|
| 1722 |
+
"loss": 0.0571,
|
| 1723 |
"step": 2320
|
| 1724 |
},
|
| 1725 |
{
|
| 1726 |
"epoch": 9.32,
|
| 1727 |
+
"grad_norm": 0.1568875014781952,
|
| 1728 |
"learning_rate": 1.5111111111111112e-06,
|
| 1729 |
+
"loss": 0.0795,
|
| 1730 |
"step": 2330
|
| 1731 |
},
|
| 1732 |
{
|
| 1733 |
"epoch": 9.36,
|
| 1734 |
+
"grad_norm": 33.47188949584961,
|
| 1735 |
"learning_rate": 1.4222222222222223e-06,
|
| 1736 |
+
"loss": 0.2421,
|
| 1737 |
"step": 2340
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
"epoch": 9.4,
|
| 1741 |
+
"grad_norm": 0.5016130805015564,
|
| 1742 |
"learning_rate": 1.3333333333333334e-06,
|
| 1743 |
+
"loss": 0.2073,
|
| 1744 |
"step": 2350
|
| 1745 |
},
|
| 1746 |
{
|
| 1747 |
"epoch": 9.44,
|
| 1748 |
+
"grad_norm": 0.5481801629066467,
|
| 1749 |
"learning_rate": 1.2444444444444445e-06,
|
| 1750 |
+
"loss": 0.114,
|
| 1751 |
"step": 2360
|
| 1752 |
},
|
| 1753 |
{
|
| 1754 |
"epoch": 9.48,
|
| 1755 |
+
"grad_norm": 8.88733196258545,
|
| 1756 |
"learning_rate": 1.1555555555555556e-06,
|
| 1757 |
+
"loss": 0.1705,
|
| 1758 |
"step": 2370
|
| 1759 |
},
|
| 1760 |
{
|
| 1761 |
"epoch": 9.52,
|
| 1762 |
+
"grad_norm": 0.017446085810661316,
|
| 1763 |
"learning_rate": 1.066666666666667e-06,
|
| 1764 |
+
"loss": 0.103,
|
| 1765 |
"step": 2380
|
| 1766 |
},
|
| 1767 |
{
|
| 1768 |
"epoch": 9.56,
|
| 1769 |
+
"grad_norm": 2.8653106689453125,
|
| 1770 |
"learning_rate": 9.77777777777778e-07,
|
| 1771 |
+
"loss": 0.1108,
|
| 1772 |
"step": 2390
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 9.6,
|
| 1776 |
+
"grad_norm": 2.0959718227386475,
|
| 1777 |
"learning_rate": 8.88888888888889e-07,
|
| 1778 |
+
"loss": 0.0365,
|
| 1779 |
"step": 2400
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 9.64,
|
| 1783 |
+
"grad_norm": 9.384411811828613,
|
| 1784 |
"learning_rate": 8.000000000000001e-07,
|
| 1785 |
+
"loss": 0.0692,
|
| 1786 |
"step": 2410
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
"epoch": 9.68,
|
| 1790 |
+
"grad_norm": 78.89244079589844,
|
| 1791 |
"learning_rate": 7.111111111111112e-07,
|
| 1792 |
+
"loss": 0.1545,
|
| 1793 |
"step": 2420
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
"epoch": 9.72,
|
| 1797 |
+
"grad_norm": 20.242263793945312,
|
| 1798 |
"learning_rate": 6.222222222222223e-07,
|
| 1799 |
+
"loss": 0.1993,
|
| 1800 |
"step": 2430
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 9.76,
|
| 1804 |
+
"grad_norm": 1.8956968784332275,
|
| 1805 |
"learning_rate": 5.333333333333335e-07,
|
| 1806 |
+
"loss": 0.0961,
|
| 1807 |
"step": 2440
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 9.8,
|
| 1811 |
+
"grad_norm": 13.430234909057617,
|
| 1812 |
"learning_rate": 4.444444444444445e-07,
|
| 1813 |
+
"loss": 0.1252,
|
| 1814 |
"step": 2450
|
| 1815 |
},
|
| 1816 |
{
|
| 1817 |
"epoch": 9.84,
|
| 1818 |
+
"grad_norm": 13.087069511413574,
|
| 1819 |
"learning_rate": 3.555555555555556e-07,
|
| 1820 |
+
"loss": 0.1547,
|
| 1821 |
"step": 2460
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 9.88,
|
| 1825 |
+
"grad_norm": 11.872249603271484,
|
| 1826 |
"learning_rate": 2.666666666666667e-07,
|
| 1827 |
+
"loss": 0.0899,
|
| 1828 |
"step": 2470
|
| 1829 |
},
|
| 1830 |
{
|
| 1831 |
"epoch": 9.92,
|
| 1832 |
+
"grad_norm": 2.150407314300537,
|
| 1833 |
"learning_rate": 1.777777777777778e-07,
|
| 1834 |
+
"loss": 0.116,
|
| 1835 |
"step": 2480
|
| 1836 |
},
|
| 1837 |
{
|
| 1838 |
"epoch": 9.96,
|
| 1839 |
+
"grad_norm": 5.467511177062988,
|
| 1840 |
"learning_rate": 8.88888888888889e-08,
|
| 1841 |
+
"loss": 0.1912,
|
| 1842 |
"step": 2490
|
| 1843 |
},
|
| 1844 |
{
|
| 1845 |
"epoch": 10.0,
|
| 1846 |
+
"grad_norm": 1.3495206832885742,
|
| 1847 |
"learning_rate": 0.0,
|
| 1848 |
+
"loss": 0.0859,
|
| 1849 |
"step": 2500
|
| 1850 |
},
|
| 1851 |
{
|
| 1852 |
"epoch": 10.0,
|
| 1853 |
+
"eval_accuracy": 0.968,
|
| 1854 |
+
"eval_f1": 0.9678344915175675,
|
| 1855 |
+
"eval_loss": 0.22622914612293243,
|
| 1856 |
+
"eval_runtime": 8.4705,
|
| 1857 |
+
"eval_samples_per_second": 59.028,
|
| 1858 |
+
"eval_steps_per_second": 14.757,
|
| 1859 |
"step": 2500
|
| 1860 |
},
|
| 1861 |
{
|
| 1862 |
"epoch": 10.0,
|
| 1863 |
"step": 2500,
|
| 1864 |
"total_flos": 4.0857422266368e+18,
|
| 1865 |
+
"train_loss": 0.24487185467481612,
|
| 1866 |
+
"train_runtime": 1824.5027,
|
| 1867 |
+
"train_samples_per_second": 21.924,
|
| 1868 |
+
"train_steps_per_second": 1.37
|
| 1869 |
}
|
| 1870 |
],
|
| 1871 |
"logging_steps": 10,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7382e8afcd57b22dcb18368980dfe4ab08e3de6fedc3e500bcf90678b8d48a70
|
| 3 |
size 5240
|