Commit
•
bd54712
1
Parent(s):
9a1e2b3
End of training
Browse files- README.md +16 -34
- all_results.json +11 -11
- config.json +6 -6
- eval_results.json +6 -6
- model.safetensors +1 -1
- runs/Nov27_12-28-41_16acc937f5e0/events.out.tfevents.1701088245.16acc937f5e0.1657.0 +3 -0
- runs/Nov27_12-28-41_16acc937f5e0/events.out.tfevents.1701089588.16acc937f5e0.1657.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +1522 -292
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,26 +3,11 @@ license: apache-2.0
|
|
| 3 |
base_model: facebook/convnextv2-tiny-1k-224
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
datasets:
|
| 7 |
-
- beans
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: convnextv2-tiny-1k-224-finetuned-beans
|
| 12 |
-
results:
|
| 13 |
-
- task:
|
| 14 |
-
name: Image Classification
|
| 15 |
-
type: image-classification
|
| 16 |
-
dataset:
|
| 17 |
-
name: beans
|
| 18 |
-
type: beans
|
| 19 |
-
config: default
|
| 20 |
-
split: validation
|
| 21 |
-
args: default
|
| 22 |
-
metrics:
|
| 23 |
-
- name: Accuracy
|
| 24 |
-
type: accuracy
|
| 25 |
-
value: 0.8120300751879699
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -30,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
|
| 31 |
# convnextv2-tiny-1k-224-finetuned-beans
|
| 32 |
|
| 33 |
-
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -53,30 +38,27 @@ More information needed
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 5e-05
|
| 56 |
-
- train_batch_size:
|
| 57 |
-
- eval_batch_size:
|
| 58 |
- seed: 42
|
| 59 |
-
- gradient_accumulation_steps: 4
|
| 60 |
-
- total_train_batch_size: 16
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
- num_epochs: 10
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|
|
|
|
| 3 |
base_model: facebook/convnextv2-tiny-1k-224
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: convnextv2-tiny-1k-224-finetuned-beans
|
| 10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
# convnextv2-tiny-1k-224-finetuned-beans
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.9837
|
| 21 |
+
- Accuracy: 0.6381
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 6
|
| 42 |
+
- eval_batch_size: 6
|
| 43 |
- seed: 42
|
|
|
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
|
|
|
| 46 |
- num_epochs: 10
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.7177 | 1.0 | 269 | 0.6939 | 0.5224 |
|
| 53 |
+
| 0.6132 | 2.0 | 538 | 0.6692 | 0.6101 |
|
| 54 |
+
| 0.642 | 3.0 | 807 | 0.6729 | 0.5951 |
|
| 55 |
+
| 0.6431 | 4.0 | 1076 | 0.6700 | 0.5690 |
|
| 56 |
+
| 0.5081 | 5.0 | 1345 | 0.7537 | 0.6213 |
|
| 57 |
+
| 0.4114 | 6.0 | 1614 | 0.9249 | 0.6175 |
|
| 58 |
+
| 0.3991 | 7.0 | 1883 | 0.9837 | 0.6381 |
|
| 59 |
+
| 0.2194 | 8.0 | 2152 | 1.4350 | 0.5802 |
|
| 60 |
+
| 0.0834 | 9.0 | 2421 | 1.3808 | 0.6138 |
|
| 61 |
+
| 0.15 | 10.0 | 2690 | 1.3277 | 0.6306 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos": 1.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6380597014925373,
|
| 4 |
+
"eval_loss": 0.9836869835853577,
|
| 5 |
+
"eval_runtime": 5.9923,
|
| 6 |
+
"eval_samples_per_second": 89.448,
|
| 7 |
+
"eval_steps_per_second": 15.019,
|
| 8 |
+
"total_flos": 1.2914180359776e+18,
|
| 9 |
+
"train_loss": 0.42039277555774135,
|
| 10 |
+
"train_runtime": 1313.1112,
|
| 11 |
+
"train_samples_per_second": 12.253,
|
| 12 |
+
"train_steps_per_second": 2.049
|
| 13 |
}
|
config.json
CHANGED
|
@@ -18,16 +18,16 @@
|
|
| 18 |
768
|
| 19 |
],
|
| 20 |
"id2label": {
|
| 21 |
-
"0": "
|
| 22 |
-
"1": "
|
| 23 |
-
"2": "
|
| 24 |
},
|
| 25 |
"image_size": 224,
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
"label2id": {
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
},
|
| 32 |
"layer_norm_eps": 1e-12,
|
| 33 |
"model_type": "convnextv2",
|
|
|
|
| 18 |
768
|
| 19 |
],
|
| 20 |
"id2label": {
|
| 21 |
+
"0": "belly",
|
| 22 |
+
"1": "notbelly",
|
| 23 |
+
"2": "unclear"
|
| 24 |
},
|
| 25 |
"image_size": 224,
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
"label2id": {
|
| 28 |
+
"belly": 0,
|
| 29 |
+
"notbelly": 1,
|
| 30 |
+
"unclear": 2
|
| 31 |
},
|
| 32 |
"layer_norm_eps": 1e-12,
|
| 33 |
"model_type": "convnextv2",
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6380597014925373,
|
| 4 |
+
"eval_loss": 0.9836869835853577,
|
| 5 |
+
"eval_runtime": 5.9923,
|
| 6 |
+
"eval_samples_per_second": 89.448,
|
| 7 |
+
"eval_steps_per_second": 15.019
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 111498892
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e47f72089b3850f761b4783e7814004e6839b0fe261dabff73d7db1d3e7c6f5
|
| 3 |
size 111498892
|
runs/Nov27_12-28-41_16acc937f5e0/events.out.tfevents.1701088245.16acc937f5e0.1657.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6900dd4345fc64fd4440a3057e7da97109a7324304ae9bdf6ff4c1688257d279
|
| 3 |
+
size 50235
|
runs/Nov27_12-28-41_16acc937f5e0/events.out.tfevents.1701089588.16acc937f5e0.1657.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a58a1c2fa288612755cc1193b51e1252b17e43f984c1b4a38a79eadd8519f206
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.2914180359776e+18,
|
| 4 |
+
"train_loss": 0.42039277555774135,
|
| 5 |
+
"train_runtime": 1313.1112,
|
| 6 |
+
"train_samples_per_second": 12.253,
|
| 7 |
+
"train_steps_per_second": 2.049
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,502 +1,1732 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "convnextv2-tiny-1k-224-finetuned-beans/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 4.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"eval_runtime": 1.5242,
|
| 52 |
-
"eval_samples_per_second": 87.261,
|
| 53 |
-
"eval_steps_per_second": 22.307,
|
| 54 |
-
"step": 64
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 1.08,
|
| 58 |
-
"learning_rate": 4.947916666666667e-05,
|
| 59 |
-
"loss": 0.1219,
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"learning_rate": 4.
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"learning_rate": 4.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"learning_rate": 4.
|
| 77 |
-
"loss": 0.
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
-
"epoch":
|
| 82 |
-
"learning_rate": 4.
|
| 83 |
-
"loss": 0.
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch":
|
| 88 |
-
"learning_rate": 4.
|
| 89 |
-
"loss": 0.
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"epoch":
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
"eval_runtime": 1.9031,
|
| 97 |
-
"eval_samples_per_second": 69.885,
|
| 98 |
-
"eval_steps_per_second": 17.865,
|
| 99 |
-
"step": 129
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 2.01,
|
| 103 |
-
"learning_rate": 4.4270833333333337e-05,
|
| 104 |
-
"loss": 0.088,
|
| 105 |
"step": 130
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate": 4.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 140
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate": 4.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 150
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate": 4.
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 160
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate": 4.
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 170
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 190
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"eval_runtime": 1.5091,
|
| 148 |
-
"eval_samples_per_second": 88.131,
|
| 149 |
-
"eval_steps_per_second": 22.53,
|
| 150 |
-
"step": 194
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 3.09,
|
| 154 |
-
"learning_rate": 3.8194444444444444e-05,
|
| 155 |
-
"loss": 0.0369,
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 210
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch":
|
| 166 |
-
"learning_rate":
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 220
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch":
|
| 172 |
-
"learning_rate":
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 230
|
| 175 |
},
|
| 176 |
{
|
| 177 |
-
"epoch":
|
| 178 |
-
"learning_rate":
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 240
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"learning_rate":
|
| 185 |
-
"loss": 0.
|
| 186 |
"step": 250
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch":
|
| 190 |
-
"
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"eval_samples_per_second": 89.625,
|
| 194 |
-
"eval_steps_per_second": 22.912,
|
| 195 |
-
"step": 259
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
|
|
|
|
|
|
|
|
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 280
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 290
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 300
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 310
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 320
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
"eval_runtime": 1.8151,
|
| 244 |
-
"eval_samples_per_second": 73.275,
|
| 245 |
-
"eval_steps_per_second": 18.732,
|
| 246 |
-
"step": 323
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 5.1,
|
| 250 |
-
"learning_rate": 2.6909722222222222e-05,
|
| 251 |
-
"loss": 0.0005,
|
| 252 |
"step": 330
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch":
|
| 256 |
-
"learning_rate":
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 340
|
| 259 |
},
|
| 260 |
{
|
| 261 |
-
"epoch":
|
| 262 |
-
"learning_rate":
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 350
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"epoch":
|
| 268 |
-
"learning_rate":
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 360
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"epoch":
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 370
|
| 277 |
},
|
| 278 |
{
|
| 279 |
-
"epoch":
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 380
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"
|
| 287 |
-
"
|
| 288 |
-
"eval_runtime": 2.1559,
|
| 289 |
-
"eval_samples_per_second": 61.691,
|
| 290 |
-
"eval_steps_per_second": 15.771,
|
| 291 |
-
"step": 388
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 6.02,
|
| 295 |
-
"learning_rate": 2.170138888888889e-05,
|
| 296 |
-
"loss": 0.001,
|
| 297 |
"step": 390
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch":
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 400
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"learning_rate":
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 410
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch":
|
| 313 |
-
"learning_rate":
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 420
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch": 6
|
| 319 |
-
"learning_rate":
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 430
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch":
|
| 325 |
-
"learning_rate":
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 440
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch":
|
| 331 |
-
"learning_rate":
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 450
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch":
|
| 337 |
-
"
|
| 338 |
-
"
|
| 339 |
-
"eval_runtime": 1.5163,
|
| 340 |
-
"eval_samples_per_second": 87.716,
|
| 341 |
-
"eval_steps_per_second": 22.424,
|
| 342 |
-
"step": 453
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 7.1,
|
| 346 |
-
"learning_rate": 1.5625e-05,
|
| 347 |
-
"loss": 0.0003,
|
| 348 |
"step": 460
|
| 349 |
},
|
| 350 |
{
|
| 351 |
-
"epoch":
|
| 352 |
-
"learning_rate":
|
| 353 |
-
"loss": 0.
|
| 354 |
"step": 470
|
| 355 |
},
|
| 356 |
{
|
| 357 |
-
"epoch":
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 480
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch":
|
| 364 |
-
"learning_rate":
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 490
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch":
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 500
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch":
|
| 376 |
-
"learning_rate":
|
| 377 |
-
"loss": 0.
|
| 378 |
"step": 510
|
| 379 |
},
|
| 380 |
{
|
| 381 |
-
"epoch":
|
| 382 |
-
"
|
| 383 |
-
"
|
| 384 |
-
"eval_runtime": 1.5209,
|
| 385 |
-
"eval_samples_per_second": 87.448,
|
| 386 |
-
"eval_steps_per_second": 22.355,
|
| 387 |
-
"step": 518
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 8.03,
|
| 391 |
-
"learning_rate": 1.0416666666666668e-05,
|
| 392 |
-
"loss": 0.0002,
|
| 393 |
"step": 520
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch":
|
| 397 |
-
"learning_rate":
|
| 398 |
-
"loss": 0.
|
| 399 |
"step": 530
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch":
|
| 403 |
-
"
|
| 404 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
"step": 540
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch":
|
| 409 |
-
"learning_rate":
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 550
|
| 412 |
},
|
| 413 |
{
|
| 414 |
-
"epoch":
|
| 415 |
-
"learning_rate":
|
| 416 |
-
"loss": 0.
|
| 417 |
"step": 560
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"epoch":
|
| 421 |
-
"learning_rate":
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 570
|
| 424 |
},
|
| 425 |
{
|
| 426 |
-
"epoch":
|
| 427 |
-
"learning_rate":
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 580
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"
|
| 434 |
-
"
|
| 435 |
-
"eval_runtime": 2.0107,
|
| 436 |
-
"eval_samples_per_second": 66.147,
|
| 437 |
-
"eval_steps_per_second": 16.91,
|
| 438 |
-
"step": 582
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 9.11,
|
| 442 |
-
"learning_rate": 4.340277777777778e-06,
|
| 443 |
-
"loss": 0.0002,
|
| 444 |
"step": 590
|
| 445 |
},
|
| 446 |
{
|
| 447 |
-
"epoch":
|
| 448 |
-
"learning_rate": 3.
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 600
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch":
|
| 454 |
-
"learning_rate":
|
| 455 |
-
"loss": 0.
|
| 456 |
"step": 610
|
| 457 |
},
|
| 458 |
{
|
| 459 |
-
"epoch":
|
| 460 |
-
"learning_rate":
|
| 461 |
-
"loss": 0.
|
| 462 |
"step": 620
|
| 463 |
},
|
| 464 |
{
|
| 465 |
-
"epoch":
|
| 466 |
-
"learning_rate":
|
| 467 |
-
"loss": 0.
|
| 468 |
"step": 630
|
| 469 |
},
|
| 470 |
{
|
| 471 |
-
"epoch":
|
| 472 |
-
"learning_rate":
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 640
|
| 475 |
},
|
| 476 |
{
|
| 477 |
-
"epoch":
|
| 478 |
-
"
|
| 479 |
-
"
|
| 480 |
-
"
|
| 481 |
-
|
| 482 |
-
|
| 483 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch":
|
| 487 |
-
"
|
| 488 |
-
"
|
| 489 |
-
"
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 493 |
}
|
| 494 |
],
|
| 495 |
"logging_steps": 10,
|
| 496 |
-
"max_steps":
|
| 497 |
"num_train_epochs": 10,
|
| 498 |
"save_steps": 500,
|
| 499 |
-
"total_flos": 1.
|
| 500 |
"trial_name": null,
|
| 501 |
"trial_params": null
|
| 502 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6380597014925373,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-tiny-1k-224-finetuned-beans/checkpoint-1883",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2690,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 4.9814126394052045e-05,
|
| 14 |
+
"loss": 0.8864,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 4.962825278810409e-05,
|
| 20 |
+
"loss": 0.7181,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 4.944237918215613e-05,
|
| 26 |
+
"loss": 0.731,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 4.925650557620818e-05,
|
| 32 |
+
"loss": 0.8049,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 4.907063197026023e-05,
|
| 38 |
+
"loss": 0.7471,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.22,
|
| 43 |
+
"learning_rate": 4.8884758364312274e-05,
|
| 44 |
+
"loss": 0.7461,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"learning_rate": 4.869888475836432e-05,
|
| 50 |
+
"loss": 0.7432,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.3,
|
| 55 |
+
"learning_rate": 4.851301115241636e-05,
|
| 56 |
+
"loss": 0.726,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.33,
|
| 61 |
+
"learning_rate": 4.83271375464684e-05,
|
| 62 |
+
"loss": 0.6687,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.37,
|
| 67 |
+
"learning_rate": 4.8141263940520446e-05,
|
| 68 |
+
"loss": 0.7631,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.41,
|
| 73 |
+
"learning_rate": 4.795539033457249e-05,
|
| 74 |
+
"loss": 0.7284,
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.45,
|
| 79 |
+
"learning_rate": 4.776951672862454e-05,
|
| 80 |
+
"loss": 0.7516,
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.48,
|
| 85 |
+
"learning_rate": 4.758364312267658e-05,
|
| 86 |
+
"loss": 0.7579,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.52,
|
| 91 |
+
"learning_rate": 4.739776951672863e-05,
|
| 92 |
+
"loss": 0.723,
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.56,
|
| 97 |
+
"learning_rate": 4.7211895910780675e-05,
|
| 98 |
+
"loss": 0.7566,
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.59,
|
| 103 |
+
"learning_rate": 4.702602230483272e-05,
|
| 104 |
+
"loss": 0.7669,
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.63,
|
| 109 |
+
"learning_rate": 4.684014869888476e-05,
|
| 110 |
+
"loss": 0.9366,
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.67,
|
| 115 |
+
"learning_rate": 4.6654275092936804e-05,
|
| 116 |
+
"loss": 0.6604,
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.71,
|
| 121 |
+
"learning_rate": 4.646840148698885e-05,
|
| 122 |
+
"loss": 0.6656,
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.74,
|
| 127 |
+
"learning_rate": 4.6282527881040897e-05,
|
| 128 |
+
"loss": 0.7292,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.78,
|
| 133 |
+
"learning_rate": 4.609665427509294e-05,
|
| 134 |
+
"loss": 0.7268,
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.82,
|
| 139 |
+
"learning_rate": 4.591078066914498e-05,
|
| 140 |
+
"loss": 0.6916,
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.86,
|
| 145 |
+
"learning_rate": 4.5724907063197026e-05,
|
| 146 |
+
"loss": 0.8112,
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.89,
|
| 151 |
+
"learning_rate": 4.5539033457249075e-05,
|
| 152 |
+
"loss": 0.7209,
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.93,
|
| 157 |
+
"learning_rate": 4.535315985130112e-05,
|
| 158 |
+
"loss": 0.7132,
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.97,
|
| 163 |
+
"learning_rate": 4.516728624535316e-05,
|
| 164 |
+
"loss": 0.7177,
|
| 165 |
+
"step": 260
|
|
|
|
|
|
|
|
|
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"eval_accuracy": 0.5223880597014925,
|
| 170 |
+
"eval_loss": 0.6938973665237427,
|
| 171 |
+
"eval_runtime": 5.6738,
|
| 172 |
+
"eval_samples_per_second": 94.47,
|
| 173 |
+
"eval_steps_per_second": 15.863,
|
| 174 |
+
"step": 269
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 1.0,
|
| 178 |
+
"learning_rate": 4.4981412639405204e-05,
|
| 179 |
+
"loss": 0.6926,
|
| 180 |
"step": 270
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"epoch": 1.04,
|
| 184 |
+
"learning_rate": 4.4795539033457254e-05,
|
| 185 |
+
"loss": 0.7133,
|
| 186 |
"step": 280
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 1.08,
|
| 190 |
+
"learning_rate": 4.46096654275093e-05,
|
| 191 |
+
"loss": 0.7041,
|
| 192 |
"step": 290
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 1.12,
|
| 196 |
+
"learning_rate": 4.442379182156134e-05,
|
| 197 |
+
"loss": 0.6854,
|
| 198 |
"step": 300
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 1.15,
|
| 202 |
+
"learning_rate": 4.423791821561338e-05,
|
| 203 |
+
"loss": 0.749,
|
| 204 |
"step": 310
|
| 205 |
},
|
| 206 |
{
|
| 207 |
+
"epoch": 1.19,
|
| 208 |
+
"learning_rate": 4.4052044609665426e-05,
|
| 209 |
+
"loss": 0.6899,
|
| 210 |
"step": 320
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"epoch": 1.23,
|
| 214 |
+
"learning_rate": 4.3866171003717476e-05,
|
| 215 |
+
"loss": 0.6929,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
"step": 330
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 1.26,
|
| 220 |
+
"learning_rate": 4.368029739776952e-05,
|
| 221 |
+
"loss": 0.6526,
|
| 222 |
"step": 340
|
| 223 |
},
|
| 224 |
{
|
| 225 |
+
"epoch": 1.3,
|
| 226 |
+
"learning_rate": 4.349442379182156e-05,
|
| 227 |
+
"loss": 0.6927,
|
| 228 |
"step": 350
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 1.34,
|
| 232 |
+
"learning_rate": 4.330855018587361e-05,
|
| 233 |
+
"loss": 0.6877,
|
| 234 |
"step": 360
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 1.38,
|
| 238 |
+
"learning_rate": 4.3122676579925655e-05,
|
| 239 |
+
"loss": 0.6808,
|
| 240 |
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 1.41,
|
| 244 |
+
"learning_rate": 4.29368029739777e-05,
|
| 245 |
+
"loss": 0.6482,
|
| 246 |
"step": 380
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 1.45,
|
| 250 |
+
"learning_rate": 4.275092936802974e-05,
|
| 251 |
+
"loss": 0.7385,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
"step": 390
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 1.49,
|
| 256 |
+
"learning_rate": 4.2565055762081784e-05,
|
| 257 |
+
"loss": 0.7002,
|
| 258 |
"step": 400
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"epoch": 1.52,
|
| 262 |
+
"learning_rate": 4.237918215613383e-05,
|
| 263 |
+
"loss": 0.6465,
|
| 264 |
"step": 410
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"epoch": 1.56,
|
| 268 |
+
"learning_rate": 4.219330855018588e-05,
|
| 269 |
+
"loss": 0.7034,
|
| 270 |
"step": 420
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 1.6,
|
| 274 |
+
"learning_rate": 4.200743494423792e-05,
|
| 275 |
+
"loss": 0.6164,
|
| 276 |
"step": 430
|
| 277 |
},
|
| 278 |
{
|
| 279 |
+
"epoch": 1.64,
|
| 280 |
+
"learning_rate": 4.182156133828997e-05,
|
| 281 |
+
"loss": 0.7048,
|
| 282 |
"step": 440
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 1.67,
|
| 286 |
+
"learning_rate": 4.163568773234201e-05,
|
| 287 |
+
"loss": 0.7023,
|
| 288 |
"step": 450
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 1.71,
|
| 292 |
+
"learning_rate": 4.1449814126394056e-05,
|
| 293 |
+
"loss": 0.6443,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 294 |
"step": 460
|
| 295 |
},
|
| 296 |
{
|
| 297 |
+
"epoch": 1.75,
|
| 298 |
+
"learning_rate": 4.12639405204461e-05,
|
| 299 |
+
"loss": 0.8055,
|
| 300 |
"step": 470
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"epoch": 1.78,
|
| 304 |
+
"learning_rate": 4.107806691449814e-05,
|
| 305 |
+
"loss": 0.6772,
|
| 306 |
"step": 480
|
| 307 |
},
|
| 308 |
{
|
| 309 |
+
"epoch": 1.82,
|
| 310 |
+
"learning_rate": 4.0892193308550185e-05,
|
| 311 |
+
"loss": 0.6921,
|
| 312 |
"step": 490
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"epoch": 1.86,
|
| 316 |
+
"learning_rate": 4.070631970260223e-05,
|
| 317 |
+
"loss": 0.7103,
|
| 318 |
"step": 500
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 1.9,
|
| 322 |
+
"learning_rate": 4.052044609665428e-05,
|
| 323 |
+
"loss": 0.6161,
|
| 324 |
"step": 510
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 1.93,
|
| 328 |
+
"learning_rate": 4.033457249070633e-05,
|
| 329 |
+
"loss": 0.6699,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 330 |
"step": 520
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 1.97,
|
| 334 |
+
"learning_rate": 4.014869888475837e-05,
|
| 335 |
+
"loss": 0.6132,
|
| 336 |
"step": 530
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"epoch": 2.0,
|
| 340 |
+
"eval_accuracy": 0.6100746268656716,
|
| 341 |
+
"eval_loss": 0.6691508293151855,
|
| 342 |
+
"eval_runtime": 5.6707,
|
| 343 |
+
"eval_samples_per_second": 94.522,
|
| 344 |
+
"eval_steps_per_second": 15.871,
|
| 345 |
+
"step": 538
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.01,
|
| 349 |
+
"learning_rate": 3.996282527881041e-05,
|
| 350 |
+
"loss": 0.5673,
|
| 351 |
"step": 540
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 2.04,
|
| 355 |
+
"learning_rate": 3.9776951672862456e-05,
|
| 356 |
+
"loss": 0.6385,
|
| 357 |
"step": 550
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 2.08,
|
| 361 |
+
"learning_rate": 3.95910780669145e-05,
|
| 362 |
+
"loss": 0.5089,
|
| 363 |
"step": 560
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 2.12,
|
| 367 |
+
"learning_rate": 3.940520446096654e-05,
|
| 368 |
+
"loss": 0.5526,
|
| 369 |
"step": 570
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 2.16,
|
| 373 |
+
"learning_rate": 3.9219330855018585e-05,
|
| 374 |
+
"loss": 0.5757,
|
| 375 |
"step": 580
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 2.19,
|
| 379 |
+
"learning_rate": 3.9033457249070635e-05,
|
| 380 |
+
"loss": 0.6253,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 381 |
"step": 590
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 2.23,
|
| 385 |
+
"learning_rate": 3.884758364312268e-05,
|
| 386 |
+
"loss": 0.7398,
|
| 387 |
"step": 600
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 2.27,
|
| 391 |
+
"learning_rate": 3.866171003717473e-05,
|
| 392 |
+
"loss": 0.7099,
|
| 393 |
"step": 610
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 2.3,
|
| 397 |
+
"learning_rate": 3.847583643122677e-05,
|
| 398 |
+
"loss": 0.5023,
|
| 399 |
"step": 620
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 2.34,
|
| 403 |
+
"learning_rate": 3.8289962825278814e-05,
|
| 404 |
+
"loss": 0.5528,
|
| 405 |
"step": 630
|
| 406 |
},
|
| 407 |
{
|
| 408 |
+
"epoch": 2.38,
|
| 409 |
+
"learning_rate": 3.810408921933086e-05,
|
| 410 |
+
"loss": 0.662,
|
| 411 |
"step": 640
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 2.42,
|
| 415 |
+
"learning_rate": 3.79182156133829e-05,
|
| 416 |
+
"loss": 0.512,
|
| 417 |
+
"step": 650
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.45,
|
| 421 |
+
"learning_rate": 3.773234200743494e-05,
|
| 422 |
+
"loss": 0.5331,
|
| 423 |
+
"step": 660
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.49,
|
| 427 |
+
"learning_rate": 3.754646840148699e-05,
|
| 428 |
+
"loss": 0.412,
|
| 429 |
+
"step": 670
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.53,
|
| 433 |
+
"learning_rate": 3.7360594795539036e-05,
|
| 434 |
+
"loss": 0.5171,
|
| 435 |
+
"step": 680
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.57,
|
| 439 |
+
"learning_rate": 3.717472118959108e-05,
|
| 440 |
+
"loss": 0.3604,
|
| 441 |
+
"step": 690
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.6,
|
| 445 |
+
"learning_rate": 3.698884758364313e-05,
|
| 446 |
+
"loss": 0.7274,
|
| 447 |
+
"step": 700
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.64,
|
| 451 |
+
"learning_rate": 3.680297397769517e-05,
|
| 452 |
+
"loss": 0.6956,
|
| 453 |
+
"step": 710
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.68,
|
| 457 |
+
"learning_rate": 3.6617100371747215e-05,
|
| 458 |
+
"loss": 0.6492,
|
| 459 |
+
"step": 720
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.71,
|
| 463 |
+
"learning_rate": 3.643122676579926e-05,
|
| 464 |
+
"loss": 0.5249,
|
| 465 |
+
"step": 730
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.75,
|
| 469 |
+
"learning_rate": 3.62453531598513e-05,
|
| 470 |
+
"loss": 0.485,
|
| 471 |
+
"step": 740
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.79,
|
| 475 |
+
"learning_rate": 3.6059479553903344e-05,
|
| 476 |
+
"loss": 0.4983,
|
| 477 |
+
"step": 750
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.83,
|
| 481 |
+
"learning_rate": 3.5873605947955393e-05,
|
| 482 |
+
"loss": 0.5527,
|
| 483 |
+
"step": 760
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.86,
|
| 487 |
+
"learning_rate": 3.5687732342007436e-05,
|
| 488 |
+
"loss": 0.474,
|
| 489 |
+
"step": 770
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.9,
|
| 493 |
+
"learning_rate": 3.550185873605948e-05,
|
| 494 |
+
"loss": 0.6361,
|
| 495 |
+
"step": 780
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.94,
|
| 499 |
+
"learning_rate": 3.531598513011153e-05,
|
| 500 |
+
"loss": 0.4852,
|
| 501 |
+
"step": 790
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.97,
|
| 505 |
+
"learning_rate": 3.513011152416357e-05,
|
| 506 |
+
"loss": 0.642,
|
| 507 |
+
"step": 800
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.0,
|
| 511 |
+
"eval_accuracy": 0.5951492537313433,
|
| 512 |
+
"eval_loss": 0.6728847622871399,
|
| 513 |
+
"eval_runtime": 7.6109,
|
| 514 |
+
"eval_samples_per_second": 70.425,
|
| 515 |
+
"eval_steps_per_second": 11.825,
|
| 516 |
+
"step": 807
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 3.01,
|
| 520 |
+
"learning_rate": 3.4944237918215615e-05,
|
| 521 |
+
"loss": 0.447,
|
| 522 |
+
"step": 810
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 3.05,
|
| 526 |
+
"learning_rate": 3.475836431226766e-05,
|
| 527 |
+
"loss": 0.4809,
|
| 528 |
+
"step": 820
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.09,
|
| 532 |
+
"learning_rate": 3.45724907063197e-05,
|
| 533 |
+
"loss": 0.4529,
|
| 534 |
+
"step": 830
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.12,
|
| 538 |
+
"learning_rate": 3.438661710037175e-05,
|
| 539 |
+
"loss": 0.4244,
|
| 540 |
+
"step": 840
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.16,
|
| 544 |
+
"learning_rate": 3.4200743494423794e-05,
|
| 545 |
+
"loss": 0.4605,
|
| 546 |
+
"step": 850
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.2,
|
| 550 |
+
"learning_rate": 3.401486988847584e-05,
|
| 551 |
+
"loss": 0.636,
|
| 552 |
+
"step": 860
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 3.23,
|
| 556 |
+
"learning_rate": 3.382899628252788e-05,
|
| 557 |
+
"loss": 0.4105,
|
| 558 |
+
"step": 870
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 3.27,
|
| 562 |
+
"learning_rate": 3.364312267657992e-05,
|
| 563 |
+
"loss": 0.4607,
|
| 564 |
+
"step": 880
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 3.31,
|
| 568 |
+
"learning_rate": 3.345724907063197e-05,
|
| 569 |
+
"loss": 0.3694,
|
| 570 |
+
"step": 890
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.35,
|
| 574 |
+
"learning_rate": 3.3271375464684016e-05,
|
| 575 |
+
"loss": 0.3316,
|
| 576 |
+
"step": 900
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.38,
|
| 580 |
+
"learning_rate": 3.308550185873606e-05,
|
| 581 |
+
"loss": 0.3896,
|
| 582 |
+
"step": 910
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.42,
|
| 586 |
+
"learning_rate": 3.289962825278811e-05,
|
| 587 |
+
"loss": 0.6064,
|
| 588 |
+
"step": 920
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 3.46,
|
| 592 |
+
"learning_rate": 3.271375464684015e-05,
|
| 593 |
+
"loss": 0.4522,
|
| 594 |
+
"step": 930
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.49,
|
| 598 |
+
"learning_rate": 3.2527881040892195e-05,
|
| 599 |
+
"loss": 0.2951,
|
| 600 |
+
"step": 940
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.53,
|
| 604 |
+
"learning_rate": 3.234200743494424e-05,
|
| 605 |
+
"loss": 0.3321,
|
| 606 |
+
"step": 950
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 3.57,
|
| 610 |
+
"learning_rate": 3.215613382899628e-05,
|
| 611 |
+
"loss": 0.3755,
|
| 612 |
+
"step": 960
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 3.61,
|
| 616 |
+
"learning_rate": 3.1970260223048324e-05,
|
| 617 |
+
"loss": 0.4872,
|
| 618 |
+
"step": 970
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.64,
|
| 622 |
+
"learning_rate": 3.1784386617100374e-05,
|
| 623 |
+
"loss": 0.7994,
|
| 624 |
+
"step": 980
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.68,
|
| 628 |
+
"learning_rate": 3.1598513011152417e-05,
|
| 629 |
+
"loss": 0.4673,
|
| 630 |
+
"step": 990
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 3.72,
|
| 634 |
+
"learning_rate": 3.1412639405204466e-05,
|
| 635 |
+
"loss": 0.3712,
|
| 636 |
+
"step": 1000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 3.75,
|
| 640 |
+
"learning_rate": 3.122676579925651e-05,
|
| 641 |
+
"loss": 0.4688,
|
| 642 |
+
"step": 1010
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 3.79,
|
| 646 |
+
"learning_rate": 3.104089219330855e-05,
|
| 647 |
+
"loss": 0.4393,
|
| 648 |
+
"step": 1020
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.83,
|
| 652 |
+
"learning_rate": 3.0855018587360595e-05,
|
| 653 |
+
"loss": 0.4471,
|
| 654 |
+
"step": 1030
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.87,
|
| 658 |
+
"learning_rate": 3.066914498141264e-05,
|
| 659 |
+
"loss": 0.5707,
|
| 660 |
+
"step": 1040
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.9,
|
| 664 |
+
"learning_rate": 3.0483271375464685e-05,
|
| 665 |
+
"loss": 0.4092,
|
| 666 |
+
"step": 1050
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.94,
|
| 670 |
+
"learning_rate": 3.0297397769516728e-05,
|
| 671 |
+
"loss": 0.6516,
|
| 672 |
+
"step": 1060
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.98,
|
| 676 |
+
"learning_rate": 3.0111524163568778e-05,
|
| 677 |
+
"loss": 0.6431,
|
| 678 |
+
"step": 1070
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 4.0,
|
| 682 |
+
"eval_accuracy": 0.5690298507462687,
|
| 683 |
+
"eval_loss": 0.6699710488319397,
|
| 684 |
+
"eval_runtime": 4.8825,
|
| 685 |
+
"eval_samples_per_second": 109.78,
|
| 686 |
+
"eval_steps_per_second": 18.433,
|
| 687 |
+
"step": 1076
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 4.01,
|
| 691 |
+
"learning_rate": 2.992565055762082e-05,
|
| 692 |
+
"loss": 0.4114,
|
| 693 |
+
"step": 1080
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 4.05,
|
| 697 |
+
"learning_rate": 2.9739776951672864e-05,
|
| 698 |
+
"loss": 0.3278,
|
| 699 |
+
"step": 1090
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 4.09,
|
| 703 |
+
"learning_rate": 2.955390334572491e-05,
|
| 704 |
+
"loss": 0.282,
|
| 705 |
+
"step": 1100
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.13,
|
| 709 |
+
"learning_rate": 2.9368029739776953e-05,
|
| 710 |
+
"loss": 0.4411,
|
| 711 |
+
"step": 1110
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.16,
|
| 715 |
+
"learning_rate": 2.9182156133828996e-05,
|
| 716 |
+
"loss": 0.3877,
|
| 717 |
+
"step": 1120
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 4.2,
|
| 721 |
+
"learning_rate": 2.8996282527881043e-05,
|
| 722 |
+
"loss": 0.3529,
|
| 723 |
+
"step": 1130
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.24,
|
| 727 |
+
"learning_rate": 2.8810408921933086e-05,
|
| 728 |
+
"loss": 0.4784,
|
| 729 |
+
"step": 1140
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.28,
|
| 733 |
+
"learning_rate": 2.862453531598513e-05,
|
| 734 |
+
"loss": 0.3331,
|
| 735 |
+
"step": 1150
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.31,
|
| 739 |
+
"learning_rate": 2.843866171003718e-05,
|
| 740 |
+
"loss": 0.333,
|
| 741 |
+
"step": 1160
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 4.35,
|
| 745 |
+
"learning_rate": 2.825278810408922e-05,
|
| 746 |
+
"loss": 0.229,
|
| 747 |
+
"step": 1170
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.39,
|
| 751 |
+
"learning_rate": 2.8066914498141268e-05,
|
| 752 |
+
"loss": 0.4836,
|
| 753 |
+
"step": 1180
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.42,
|
| 757 |
+
"learning_rate": 2.788104089219331e-05,
|
| 758 |
+
"loss": 0.3867,
|
| 759 |
+
"step": 1190
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 4.46,
|
| 763 |
+
"learning_rate": 2.7695167286245354e-05,
|
| 764 |
+
"loss": 0.4889,
|
| 765 |
+
"step": 1200
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.5,
|
| 769 |
+
"learning_rate": 2.75092936802974e-05,
|
| 770 |
+
"loss": 0.3486,
|
| 771 |
+
"step": 1210
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 4.54,
|
| 775 |
+
"learning_rate": 2.7323420074349443e-05,
|
| 776 |
+
"loss": 0.5418,
|
| 777 |
+
"step": 1220
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 4.57,
|
| 781 |
+
"learning_rate": 2.7137546468401486e-05,
|
| 782 |
+
"loss": 0.5474,
|
| 783 |
+
"step": 1230
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.61,
|
| 787 |
+
"learning_rate": 2.695167286245353e-05,
|
| 788 |
+
"loss": 0.2895,
|
| 789 |
+
"step": 1240
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 4.65,
|
| 793 |
+
"learning_rate": 2.6765799256505576e-05,
|
| 794 |
+
"loss": 0.4961,
|
| 795 |
+
"step": 1250
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 4.68,
|
| 799 |
+
"learning_rate": 2.6579925650557625e-05,
|
| 800 |
+
"loss": 0.4748,
|
| 801 |
+
"step": 1260
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.72,
|
| 805 |
+
"learning_rate": 2.639405204460967e-05,
|
| 806 |
+
"loss": 0.4066,
|
| 807 |
+
"step": 1270
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.76,
|
| 811 |
+
"learning_rate": 2.620817843866171e-05,
|
| 812 |
+
"loss": 0.2847,
|
| 813 |
+
"step": 1280
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.8,
|
| 817 |
+
"learning_rate": 2.6022304832713758e-05,
|
| 818 |
+
"loss": 0.2828,
|
| 819 |
+
"step": 1290
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.83,
|
| 823 |
+
"learning_rate": 2.58364312267658e-05,
|
| 824 |
+
"loss": 0.3473,
|
| 825 |
+
"step": 1300
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.87,
|
| 829 |
+
"learning_rate": 2.5650557620817844e-05,
|
| 830 |
+
"loss": 0.4106,
|
| 831 |
+
"step": 1310
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 4.91,
|
| 835 |
+
"learning_rate": 2.5464684014869887e-05,
|
| 836 |
+
"loss": 0.5531,
|
| 837 |
+
"step": 1320
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.94,
|
| 841 |
+
"learning_rate": 2.5278810408921933e-05,
|
| 842 |
+
"loss": 0.537,
|
| 843 |
+
"step": 1330
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.98,
|
| 847 |
+
"learning_rate": 2.5092936802973976e-05,
|
| 848 |
+
"loss": 0.5081,
|
| 849 |
+
"step": 1340
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 5.0,
|
| 853 |
+
"eval_accuracy": 0.621268656716418,
|
| 854 |
+
"eval_loss": 0.7537009716033936,
|
| 855 |
+
"eval_runtime": 4.9189,
|
| 856 |
+
"eval_samples_per_second": 108.968,
|
| 857 |
+
"eval_steps_per_second": 18.297,
|
| 858 |
+
"step": 1345
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 5.02,
|
| 862 |
+
"learning_rate": 2.4907063197026023e-05,
|
| 863 |
+
"loss": 0.1346,
|
| 864 |
+
"step": 1350
|
| 865 |
},
|
| 866 |
{
|
| 867 |
+
"epoch": 5.06,
|
| 868 |
+
"learning_rate": 2.4721189591078066e-05,
|
| 869 |
+
"loss": 0.2534,
|
| 870 |
+
"step": 1360
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 5.09,
|
| 874 |
+
"learning_rate": 2.4535315985130116e-05,
|
| 875 |
+
"loss": 0.396,
|
| 876 |
+
"step": 1370
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 5.13,
|
| 880 |
+
"learning_rate": 2.434944237918216e-05,
|
| 881 |
+
"loss": 0.336,
|
| 882 |
+
"step": 1380
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 5.17,
|
| 886 |
+
"learning_rate": 2.41635687732342e-05,
|
| 887 |
+
"loss": 0.2851,
|
| 888 |
+
"step": 1390
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 5.2,
|
| 892 |
+
"learning_rate": 2.3977695167286245e-05,
|
| 893 |
+
"loss": 0.3815,
|
| 894 |
+
"step": 1400
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 5.24,
|
| 898 |
+
"learning_rate": 2.379182156133829e-05,
|
| 899 |
+
"loss": 0.2494,
|
| 900 |
+
"step": 1410
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 5.28,
|
| 904 |
+
"learning_rate": 2.3605947955390337e-05,
|
| 905 |
+
"loss": 0.2749,
|
| 906 |
+
"step": 1420
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 5.32,
|
| 910 |
+
"learning_rate": 2.342007434944238e-05,
|
| 911 |
+
"loss": 0.3111,
|
| 912 |
+
"step": 1430
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 5.35,
|
| 916 |
+
"learning_rate": 2.3234200743494423e-05,
|
| 917 |
+
"loss": 0.5944,
|
| 918 |
+
"step": 1440
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 5.39,
|
| 922 |
+
"learning_rate": 2.304832713754647e-05,
|
| 923 |
+
"loss": 0.2278,
|
| 924 |
+
"step": 1450
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 5.43,
|
| 928 |
+
"learning_rate": 2.2862453531598513e-05,
|
| 929 |
+
"loss": 0.3026,
|
| 930 |
+
"step": 1460
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.46,
|
| 934 |
+
"learning_rate": 2.267657992565056e-05,
|
| 935 |
+
"loss": 0.1595,
|
| 936 |
+
"step": 1470
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 5.5,
|
| 940 |
+
"learning_rate": 2.2490706319702602e-05,
|
| 941 |
+
"loss": 0.2316,
|
| 942 |
+
"step": 1480
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 5.54,
|
| 946 |
+
"learning_rate": 2.230483271375465e-05,
|
| 947 |
+
"loss": 0.3516,
|
| 948 |
+
"step": 1490
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 5.58,
|
| 952 |
+
"learning_rate": 2.211895910780669e-05,
|
| 953 |
+
"loss": 0.4393,
|
| 954 |
+
"step": 1500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 5.61,
|
| 958 |
+
"learning_rate": 2.1933085501858738e-05,
|
| 959 |
+
"loss": 0.2632,
|
| 960 |
+
"step": 1510
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 5.65,
|
| 964 |
+
"learning_rate": 2.174721189591078e-05,
|
| 965 |
+
"loss": 0.2464,
|
| 966 |
+
"step": 1520
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 5.69,
|
| 970 |
+
"learning_rate": 2.1561338289962827e-05,
|
| 971 |
+
"loss": 0.3096,
|
| 972 |
+
"step": 1530
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 5.72,
|
| 976 |
+
"learning_rate": 2.137546468401487e-05,
|
| 977 |
+
"loss": 0.6077,
|
| 978 |
+
"step": 1540
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 5.76,
|
| 982 |
+
"learning_rate": 2.1189591078066913e-05,
|
| 983 |
+
"loss": 0.338,
|
| 984 |
+
"step": 1550
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 5.8,
|
| 988 |
+
"learning_rate": 2.100371747211896e-05,
|
| 989 |
+
"loss": 0.5448,
|
| 990 |
+
"step": 1560
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 5.84,
|
| 994 |
+
"learning_rate": 2.0817843866171006e-05,
|
| 995 |
+
"loss": 0.4206,
|
| 996 |
+
"step": 1570
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 5.87,
|
| 1000 |
+
"learning_rate": 2.063197026022305e-05,
|
| 1001 |
+
"loss": 0.2484,
|
| 1002 |
+
"step": 1580
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 5.91,
|
| 1006 |
+
"learning_rate": 2.0446096654275092e-05,
|
| 1007 |
+
"loss": 0.2526,
|
| 1008 |
+
"step": 1590
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.95,
|
| 1012 |
+
"learning_rate": 2.026022304832714e-05,
|
| 1013 |
+
"loss": 0.304,
|
| 1014 |
+
"step": 1600
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.99,
|
| 1018 |
+
"learning_rate": 2.0074349442379185e-05,
|
| 1019 |
+
"loss": 0.4114,
|
| 1020 |
+
"step": 1610
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 6.0,
|
| 1024 |
+
"eval_accuracy": 0.6175373134328358,
|
| 1025 |
+
"eval_loss": 0.9249094724655151,
|
| 1026 |
+
"eval_runtime": 4.9293,
|
| 1027 |
+
"eval_samples_per_second": 108.739,
|
| 1028 |
+
"eval_steps_per_second": 18.258,
|
| 1029 |
+
"step": 1614
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 6.02,
|
| 1033 |
+
"learning_rate": 1.9888475836431228e-05,
|
| 1034 |
+
"loss": 0.2368,
|
| 1035 |
+
"step": 1620
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 6.06,
|
| 1039 |
+
"learning_rate": 1.970260223048327e-05,
|
| 1040 |
+
"loss": 0.4407,
|
| 1041 |
+
"step": 1630
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 6.1,
|
| 1045 |
+
"learning_rate": 1.9516728624535318e-05,
|
| 1046 |
+
"loss": 0.2919,
|
| 1047 |
+
"step": 1640
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 6.13,
|
| 1051 |
+
"learning_rate": 1.9330855018587364e-05,
|
| 1052 |
+
"loss": 0.448,
|
| 1053 |
+
"step": 1650
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 6.17,
|
| 1057 |
+
"learning_rate": 1.9144981412639407e-05,
|
| 1058 |
+
"loss": 0.1191,
|
| 1059 |
+
"step": 1660
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 6.21,
|
| 1063 |
+
"learning_rate": 1.895910780669145e-05,
|
| 1064 |
+
"loss": 0.0392,
|
| 1065 |
+
"step": 1670
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 6.25,
|
| 1069 |
+
"learning_rate": 1.8773234200743496e-05,
|
| 1070 |
+
"loss": 0.1173,
|
| 1071 |
+
"step": 1680
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 6.28,
|
| 1075 |
+
"learning_rate": 1.858736059479554e-05,
|
| 1076 |
+
"loss": 0.563,
|
| 1077 |
+
"step": 1690
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 6.32,
|
| 1081 |
+
"learning_rate": 1.8401486988847586e-05,
|
| 1082 |
+
"loss": 0.0517,
|
| 1083 |
+
"step": 1700
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 6.36,
|
| 1087 |
+
"learning_rate": 1.821561338289963e-05,
|
| 1088 |
+
"loss": 0.2913,
|
| 1089 |
+
"step": 1710
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 6.39,
|
| 1093 |
+
"learning_rate": 1.8029739776951672e-05,
|
| 1094 |
+
"loss": 0.4507,
|
| 1095 |
+
"step": 1720
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 6.43,
|
| 1099 |
+
"learning_rate": 1.7843866171003718e-05,
|
| 1100 |
+
"loss": 0.5469,
|
| 1101 |
+
"step": 1730
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 6.47,
|
| 1105 |
+
"learning_rate": 1.7657992565055765e-05,
|
| 1106 |
+
"loss": 0.4643,
|
| 1107 |
+
"step": 1740
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 6.51,
|
| 1111 |
+
"learning_rate": 1.7472118959107808e-05,
|
| 1112 |
+
"loss": 0.1686,
|
| 1113 |
+
"step": 1750
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 6.54,
|
| 1117 |
+
"learning_rate": 1.728624535315985e-05,
|
| 1118 |
+
"loss": 0.0685,
|
| 1119 |
+
"step": 1760
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 6.58,
|
| 1123 |
+
"learning_rate": 1.7100371747211897e-05,
|
| 1124 |
+
"loss": 0.3367,
|
| 1125 |
+
"step": 1770
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 6.62,
|
| 1129 |
+
"learning_rate": 1.691449814126394e-05,
|
| 1130 |
+
"loss": 0.1368,
|
| 1131 |
+
"step": 1780
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 6.65,
|
| 1135 |
+
"learning_rate": 1.6728624535315986e-05,
|
| 1136 |
+
"loss": 0.2455,
|
| 1137 |
+
"step": 1790
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 6.69,
|
| 1141 |
+
"learning_rate": 1.654275092936803e-05,
|
| 1142 |
+
"loss": 0.3655,
|
| 1143 |
+
"step": 1800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 6.73,
|
| 1147 |
+
"learning_rate": 1.6356877323420076e-05,
|
| 1148 |
+
"loss": 0.3373,
|
| 1149 |
+
"step": 1810
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.77,
|
| 1153 |
+
"learning_rate": 1.617100371747212e-05,
|
| 1154 |
+
"loss": 0.3152,
|
| 1155 |
+
"step": 1820
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 6.8,
|
| 1159 |
+
"learning_rate": 1.5985130111524162e-05,
|
| 1160 |
+
"loss": 0.5365,
|
| 1161 |
+
"step": 1830
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 6.84,
|
| 1165 |
+
"learning_rate": 1.5799256505576208e-05,
|
| 1166 |
+
"loss": 0.1659,
|
| 1167 |
+
"step": 1840
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 6.88,
|
| 1171 |
+
"learning_rate": 1.5613382899628255e-05,
|
| 1172 |
+
"loss": 0.3763,
|
| 1173 |
+
"step": 1850
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 6.91,
|
| 1177 |
+
"learning_rate": 1.5427509293680298e-05,
|
| 1178 |
+
"loss": 0.4083,
|
| 1179 |
+
"step": 1860
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 6.95,
|
| 1183 |
+
"learning_rate": 1.5241635687732342e-05,
|
| 1184 |
+
"loss": 0.2691,
|
| 1185 |
+
"step": 1870
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 6.99,
|
| 1189 |
+
"learning_rate": 1.5055762081784389e-05,
|
| 1190 |
+
"loss": 0.3991,
|
| 1191 |
+
"step": 1880
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 7.0,
|
| 1195 |
+
"eval_accuracy": 0.6380597014925373,
|
| 1196 |
+
"eval_loss": 0.9836869835853577,
|
| 1197 |
+
"eval_runtime": 4.8663,
|
| 1198 |
+
"eval_samples_per_second": 110.145,
|
| 1199 |
+
"eval_steps_per_second": 18.495,
|
| 1200 |
+
"step": 1883
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 7.03,
|
| 1204 |
+
"learning_rate": 1.4869888475836432e-05,
|
| 1205 |
+
"loss": 0.2571,
|
| 1206 |
+
"step": 1890
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 7.06,
|
| 1210 |
+
"learning_rate": 1.4684014869888477e-05,
|
| 1211 |
+
"loss": 0.1307,
|
| 1212 |
+
"step": 1900
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 7.1,
|
| 1216 |
+
"learning_rate": 1.4498141263940521e-05,
|
| 1217 |
+
"loss": 0.1222,
|
| 1218 |
+
"step": 1910
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 7.14,
|
| 1222 |
+
"learning_rate": 1.4312267657992564e-05,
|
| 1223 |
+
"loss": 0.276,
|
| 1224 |
+
"step": 1920
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 7.17,
|
| 1228 |
+
"learning_rate": 1.412639405204461e-05,
|
| 1229 |
+
"loss": 0.5438,
|
| 1230 |
+
"step": 1930
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 7.21,
|
| 1234 |
+
"learning_rate": 1.3940520446096655e-05,
|
| 1235 |
+
"loss": 0.1835,
|
| 1236 |
+
"step": 1940
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 7.25,
|
| 1240 |
+
"learning_rate": 1.37546468401487e-05,
|
| 1241 |
+
"loss": 0.136,
|
| 1242 |
+
"step": 1950
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 7.29,
|
| 1246 |
+
"learning_rate": 1.3568773234200743e-05,
|
| 1247 |
+
"loss": 0.3315,
|
| 1248 |
+
"step": 1960
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 7.32,
|
| 1252 |
+
"learning_rate": 1.3382899628252788e-05,
|
| 1253 |
+
"loss": 0.3154,
|
| 1254 |
+
"step": 1970
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 7.36,
|
| 1258 |
+
"learning_rate": 1.3197026022304834e-05,
|
| 1259 |
+
"loss": 0.1583,
|
| 1260 |
+
"step": 1980
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 7.4,
|
| 1264 |
+
"learning_rate": 1.3011152416356879e-05,
|
| 1265 |
+
"loss": 0.3539,
|
| 1266 |
+
"step": 1990
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 7.43,
|
| 1270 |
+
"learning_rate": 1.2825278810408922e-05,
|
| 1271 |
+
"loss": 0.2128,
|
| 1272 |
+
"step": 2000
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 7.47,
|
| 1276 |
+
"learning_rate": 1.2639405204460967e-05,
|
| 1277 |
+
"loss": 0.2219,
|
| 1278 |
+
"step": 2010
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 7.51,
|
| 1282 |
+
"learning_rate": 1.2453531598513011e-05,
|
| 1283 |
+
"loss": 0.1671,
|
| 1284 |
+
"step": 2020
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 7.55,
|
| 1288 |
+
"learning_rate": 1.2267657992565058e-05,
|
| 1289 |
+
"loss": 0.1404,
|
| 1290 |
+
"step": 2030
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 7.58,
|
| 1294 |
+
"learning_rate": 1.20817843866171e-05,
|
| 1295 |
+
"loss": 0.1204,
|
| 1296 |
+
"step": 2040
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 7.62,
|
| 1300 |
+
"learning_rate": 1.1895910780669145e-05,
|
| 1301 |
+
"loss": 0.1877,
|
| 1302 |
+
"step": 2050
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 7.66,
|
| 1306 |
+
"learning_rate": 1.171003717472119e-05,
|
| 1307 |
+
"loss": 0.2447,
|
| 1308 |
+
"step": 2060
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 7.7,
|
| 1312 |
+
"learning_rate": 1.1524163568773235e-05,
|
| 1313 |
+
"loss": 0.2406,
|
| 1314 |
+
"step": 2070
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 7.73,
|
| 1318 |
+
"learning_rate": 1.133828996282528e-05,
|
| 1319 |
+
"loss": 0.0305,
|
| 1320 |
+
"step": 2080
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 7.77,
|
| 1324 |
+
"learning_rate": 1.1152416356877324e-05,
|
| 1325 |
+
"loss": 0.4781,
|
| 1326 |
+
"step": 2090
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 7.81,
|
| 1330 |
+
"learning_rate": 1.0966542750929369e-05,
|
| 1331 |
+
"loss": 0.6367,
|
| 1332 |
+
"step": 2100
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 7.84,
|
| 1336 |
+
"learning_rate": 1.0780669144981414e-05,
|
| 1337 |
+
"loss": 0.2427,
|
| 1338 |
+
"step": 2110
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 7.88,
|
| 1342 |
+
"learning_rate": 1.0594795539033457e-05,
|
| 1343 |
+
"loss": 0.359,
|
| 1344 |
+
"step": 2120
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 7.92,
|
| 1348 |
+
"learning_rate": 1.0408921933085503e-05,
|
| 1349 |
+
"loss": 0.3237,
|
| 1350 |
+
"step": 2130
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 7.96,
|
| 1354 |
+
"learning_rate": 1.0223048327137546e-05,
|
| 1355 |
+
"loss": 0.161,
|
| 1356 |
+
"step": 2140
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 7.99,
|
| 1360 |
+
"learning_rate": 1.0037174721189593e-05,
|
| 1361 |
+
"loss": 0.2194,
|
| 1362 |
+
"step": 2150
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 8.0,
|
| 1366 |
+
"eval_accuracy": 0.5802238805970149,
|
| 1367 |
+
"eval_loss": 1.4350043535232544,
|
| 1368 |
+
"eval_runtime": 5.1084,
|
| 1369 |
+
"eval_samples_per_second": 104.925,
|
| 1370 |
+
"eval_steps_per_second": 17.618,
|
| 1371 |
+
"step": 2152
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 8.03,
|
| 1375 |
+
"learning_rate": 9.851301115241636e-06,
|
| 1376 |
+
"loss": 0.304,
|
| 1377 |
+
"step": 2160
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 8.07,
|
| 1381 |
+
"learning_rate": 9.665427509293682e-06,
|
| 1382 |
+
"loss": 0.4776,
|
| 1383 |
+
"step": 2170
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 8.1,
|
| 1387 |
+
"learning_rate": 9.479553903345725e-06,
|
| 1388 |
+
"loss": 0.113,
|
| 1389 |
+
"step": 2180
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 8.14,
|
| 1393 |
+
"learning_rate": 9.29368029739777e-06,
|
| 1394 |
+
"loss": 0.3168,
|
| 1395 |
+
"step": 2190
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 8.18,
|
| 1399 |
+
"learning_rate": 9.107806691449814e-06,
|
| 1400 |
+
"loss": 0.2094,
|
| 1401 |
+
"step": 2200
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 8.22,
|
| 1405 |
+
"learning_rate": 8.921933085501859e-06,
|
| 1406 |
+
"loss": 0.1155,
|
| 1407 |
+
"step": 2210
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 8.25,
|
| 1411 |
+
"learning_rate": 8.736059479553904e-06,
|
| 1412 |
+
"loss": 0.1741,
|
| 1413 |
+
"step": 2220
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 8.29,
|
| 1417 |
+
"learning_rate": 8.550185873605949e-06,
|
| 1418 |
+
"loss": 0.3574,
|
| 1419 |
+
"step": 2230
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 8.33,
|
| 1423 |
+
"learning_rate": 8.364312267657993e-06,
|
| 1424 |
+
"loss": 0.1843,
|
| 1425 |
+
"step": 2240
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 8.36,
|
| 1429 |
+
"learning_rate": 8.178438661710038e-06,
|
| 1430 |
+
"loss": 0.4902,
|
| 1431 |
+
"step": 2250
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 8.4,
|
| 1435 |
+
"learning_rate": 7.992565055762081e-06,
|
| 1436 |
+
"loss": 0.3588,
|
| 1437 |
+
"step": 2260
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 8.44,
|
| 1441 |
+
"learning_rate": 7.806691449814127e-06,
|
| 1442 |
+
"loss": 0.2261,
|
| 1443 |
+
"step": 2270
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 8.48,
|
| 1447 |
+
"learning_rate": 7.620817843866171e-06,
|
| 1448 |
+
"loss": 0.2937,
|
| 1449 |
+
"step": 2280
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 8.51,
|
| 1453 |
+
"learning_rate": 7.434944237918216e-06,
|
| 1454 |
+
"loss": 0.1844,
|
| 1455 |
+
"step": 2290
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 8.55,
|
| 1459 |
+
"learning_rate": 7.249070631970261e-06,
|
| 1460 |
+
"loss": 0.1538,
|
| 1461 |
+
"step": 2300
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 8.59,
|
| 1465 |
+
"learning_rate": 7.063197026022305e-06,
|
| 1466 |
+
"loss": 0.0564,
|
| 1467 |
+
"step": 2310
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 8.62,
|
| 1471 |
+
"learning_rate": 6.87732342007435e-06,
|
| 1472 |
+
"loss": 0.0752,
|
| 1473 |
+
"step": 2320
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 8.66,
|
| 1477 |
+
"learning_rate": 6.691449814126394e-06,
|
| 1478 |
+
"loss": 0.2735,
|
| 1479 |
+
"step": 2330
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 8.7,
|
| 1483 |
+
"learning_rate": 6.5055762081784395e-06,
|
| 1484 |
+
"loss": 0.1708,
|
| 1485 |
+
"step": 2340
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 8.74,
|
| 1489 |
+
"learning_rate": 6.319702602230483e-06,
|
| 1490 |
+
"loss": 0.1134,
|
| 1491 |
+
"step": 2350
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 8.77,
|
| 1495 |
+
"learning_rate": 6.133828996282529e-06,
|
| 1496 |
+
"loss": 0.3347,
|
| 1497 |
+
"step": 2360
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 8.81,
|
| 1501 |
+
"learning_rate": 5.947955390334573e-06,
|
| 1502 |
+
"loss": 0.0905,
|
| 1503 |
+
"step": 2370
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 8.85,
|
| 1507 |
+
"learning_rate": 5.7620817843866174e-06,
|
| 1508 |
+
"loss": 0.6311,
|
| 1509 |
+
"step": 2380
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 8.88,
|
| 1513 |
+
"learning_rate": 5.576208178438662e-06,
|
| 1514 |
+
"loss": 0.1654,
|
| 1515 |
+
"step": 2390
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 8.92,
|
| 1519 |
+
"learning_rate": 5.390334572490707e-06,
|
| 1520 |
+
"loss": 0.4053,
|
| 1521 |
+
"step": 2400
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 8.96,
|
| 1525 |
+
"learning_rate": 5.2044609665427516e-06,
|
| 1526 |
+
"loss": 0.0912,
|
| 1527 |
+
"step": 2410
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 9.0,
|
| 1531 |
+
"learning_rate": 5.018587360594796e-06,
|
| 1532 |
+
"loss": 0.0834,
|
| 1533 |
+
"step": 2420
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 9.0,
|
| 1537 |
+
"eval_accuracy": 0.6138059701492538,
|
| 1538 |
+
"eval_loss": 1.3807860612869263,
|
| 1539 |
+
"eval_runtime": 5.3599,
|
| 1540 |
+
"eval_samples_per_second": 100.002,
|
| 1541 |
+
"eval_steps_per_second": 16.791,
|
| 1542 |
+
"step": 2421
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 9.03,
|
| 1546 |
+
"learning_rate": 4.832713754646841e-06,
|
| 1547 |
+
"loss": 0.0566,
|
| 1548 |
+
"step": 2430
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 9.07,
|
| 1552 |
+
"learning_rate": 4.646840148698885e-06,
|
| 1553 |
+
"loss": 0.3705,
|
| 1554 |
+
"step": 2440
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 9.11,
|
| 1558 |
+
"learning_rate": 4.4609665427509296e-06,
|
| 1559 |
+
"loss": 0.2529,
|
| 1560 |
+
"step": 2450
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 9.14,
|
| 1564 |
+
"learning_rate": 4.275092936802974e-06,
|
| 1565 |
+
"loss": 0.0952,
|
| 1566 |
+
"step": 2460
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 9.18,
|
| 1570 |
+
"learning_rate": 4.089219330855019e-06,
|
| 1571 |
+
"loss": 0.1959,
|
| 1572 |
+
"step": 2470
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 9.22,
|
| 1576 |
+
"learning_rate": 3.903345724907064e-06,
|
| 1577 |
+
"loss": 0.2592,
|
| 1578 |
+
"step": 2480
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 9.26,
|
| 1582 |
+
"learning_rate": 3.717472118959108e-06,
|
| 1583 |
+
"loss": 0.1467,
|
| 1584 |
+
"step": 2490
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 9.29,
|
| 1588 |
+
"learning_rate": 3.5315985130111527e-06,
|
| 1589 |
+
"loss": 0.3126,
|
| 1590 |
+
"step": 2500
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 9.33,
|
| 1594 |
+
"learning_rate": 3.345724907063197e-06,
|
| 1595 |
+
"loss": 0.1853,
|
| 1596 |
+
"step": 2510
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 9.37,
|
| 1600 |
+
"learning_rate": 3.1598513011152417e-06,
|
| 1601 |
+
"loss": 0.3267,
|
| 1602 |
+
"step": 2520
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 9.41,
|
| 1606 |
+
"learning_rate": 2.9739776951672864e-06,
|
| 1607 |
+
"loss": 0.1253,
|
| 1608 |
+
"step": 2530
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 9.44,
|
| 1612 |
+
"learning_rate": 2.788104089219331e-06,
|
| 1613 |
+
"loss": 0.0585,
|
| 1614 |
+
"step": 2540
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 9.48,
|
| 1618 |
+
"learning_rate": 2.6022304832713758e-06,
|
| 1619 |
+
"loss": 0.3812,
|
| 1620 |
+
"step": 2550
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 9.52,
|
| 1624 |
+
"learning_rate": 2.4163568773234205e-06,
|
| 1625 |
+
"loss": 0.136,
|
| 1626 |
+
"step": 2560
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 9.55,
|
| 1630 |
+
"learning_rate": 2.2304832713754648e-06,
|
| 1631 |
+
"loss": 0.1899,
|
| 1632 |
+
"step": 2570
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 9.59,
|
| 1636 |
+
"learning_rate": 2.0446096654275095e-06,
|
| 1637 |
+
"loss": 0.3092,
|
| 1638 |
+
"step": 2580
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 9.63,
|
| 1642 |
+
"learning_rate": 1.858736059479554e-06,
|
| 1643 |
+
"loss": 0.2287,
|
| 1644 |
+
"step": 2590
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 9.67,
|
| 1648 |
+
"learning_rate": 1.6728624535315985e-06,
|
| 1649 |
+
"loss": 0.1593,
|
| 1650 |
+
"step": 2600
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 9.7,
|
| 1654 |
+
"learning_rate": 1.4869888475836432e-06,
|
| 1655 |
+
"loss": 0.0521,
|
| 1656 |
+
"step": 2610
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 9.74,
|
| 1660 |
+
"learning_rate": 1.3011152416356879e-06,
|
| 1661 |
+
"loss": 0.5016,
|
| 1662 |
+
"step": 2620
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 9.78,
|
| 1666 |
+
"learning_rate": 1.1152416356877324e-06,
|
| 1667 |
+
"loss": 0.1367,
|
| 1668 |
+
"step": 2630
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 9.81,
|
| 1672 |
+
"learning_rate": 9.29368029739777e-07,
|
| 1673 |
+
"loss": 0.4205,
|
| 1674 |
+
"step": 2640
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 9.85,
|
| 1678 |
+
"learning_rate": 7.434944237918216e-07,
|
| 1679 |
+
"loss": 0.1077,
|
| 1680 |
+
"step": 2650
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 9.89,
|
| 1684 |
+
"learning_rate": 5.576208178438662e-07,
|
| 1685 |
+
"loss": 0.4551,
|
| 1686 |
+
"step": 2660
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 9.93,
|
| 1690 |
+
"learning_rate": 3.717472118959108e-07,
|
| 1691 |
+
"loss": 0.0785,
|
| 1692 |
+
"step": 2670
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 9.96,
|
| 1696 |
+
"learning_rate": 1.858736059479554e-07,
|
| 1697 |
+
"loss": 0.1772,
|
| 1698 |
+
"step": 2680
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 10.0,
|
| 1702 |
+
"learning_rate": 0.0,
|
| 1703 |
+
"loss": 0.15,
|
| 1704 |
+
"step": 2690
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 10.0,
|
| 1708 |
+
"eval_accuracy": 0.6305970149253731,
|
| 1709 |
+
"eval_loss": 1.3277170658111572,
|
| 1710 |
+
"eval_runtime": 5.7368,
|
| 1711 |
+
"eval_samples_per_second": 93.432,
|
| 1712 |
+
"eval_steps_per_second": 15.688,
|
| 1713 |
+
"step": 2690
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 10.0,
|
| 1717 |
+
"step": 2690,
|
| 1718 |
+
"total_flos": 1.2914180359776e+18,
|
| 1719 |
+
"train_loss": 0.42039277555774135,
|
| 1720 |
+
"train_runtime": 1313.1112,
|
| 1721 |
+
"train_samples_per_second": 12.253,
|
| 1722 |
+
"train_steps_per_second": 2.049
|
| 1723 |
}
|
| 1724 |
],
|
| 1725 |
"logging_steps": 10,
|
| 1726 |
+
"max_steps": 2690,
|
| 1727 |
"num_train_epochs": 10,
|
| 1728 |
"save_steps": 500,
|
| 1729 |
+
"total_flos": 1.2914180359776e+18,
|
| 1730 |
"trial_name": null,
|
| 1731 |
"trial_params": null
|
| 1732 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e7712d30879c47a02ba18e78212f82e0d53ff113df54ba5bddc8d99b93d913d
|
| 3 |
size 4600
|