Model save
Browse files- README.md +16 -16
- all_results.json +8 -0
- runs/Jan29_08-40-35_d0e85ba8394a/events.out.tfevents.1738140041.d0e85ba8394a.21250.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +1714 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [therealcyberlord/stanford-car-vit-patch16](https://huggingface.co/therealcyberlord/stanford-car-vit-patch16) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 1.4404
|
| 37 |
- Accuracy: 0.5412
|
|
|
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -54,11 +54,11 @@ More information needed
|
|
| 54 |
|
| 55 |
The following hyperparameters were used during training:
|
| 56 |
- learning_rate: 0.001
|
| 57 |
-
- train_batch_size:
|
| 58 |
-
- eval_batch_size:
|
| 59 |
- seed: 42
|
| 60 |
- gradient_accumulation_steps: 4
|
| 61 |
-
- total_train_batch_size:
|
| 62 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
- lr_scheduler_warmup_ratio: 0.1
|
|
@@ -66,18 +66,18 @@ The following hyperparameters were used during training:
|
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 70 |
-
|
| 71 |
-
| 16.0903 | 0.9967 | 226 | 3.4455 |
|
| 72 |
-
| 11.5438 | 1.9967 | 452 | 2.4033 |
|
| 73 |
-
| 9.5963 | 2.9967 | 678 | 2.0761 |
|
| 74 |
-
| 8.3873 | 3.9967 | 904 | 1.8921 |
|
| 75 |
-
| 7.3127 | 4.9967 | 1130 | 1.7535 |
|
| 76 |
-
| 6.2178 | 5.9967 | 1356 | 1.6533 |
|
| 77 |
-
| 5.4619 | 6.9967 | 1582 | 1.5859 |
|
| 78 |
-
| 4.618 | 7.9967 | 1808 | 1.5253 |
|
| 79 |
-
| 3.9349 | 8.9967 | 2034 | 1.4693 |
|
| 80 |
-
| 3.4667 | 9.9967 | 2260 | 1.4404 |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [therealcyberlord/stanford-car-vit-patch16](https://huggingface.co/therealcyberlord/stanford-car-vit-patch16) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
|
|
|
| 36 |
- Accuracy: 0.5412
|
| 37 |
+
- Loss: 1.4404
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 54 |
|
| 55 |
The following hyperparameters were used during training:
|
| 56 |
- learning_rate: 0.001
|
| 57 |
+
- train_batch_size: 128
|
| 58 |
+
- eval_batch_size: 128
|
| 59 |
- seed: 42
|
| 60 |
- gradient_accumulation_steps: 4
|
| 61 |
+
- total_train_batch_size: 512
|
| 62 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 70 |
+
|:-------------:|:------:|:----:|:--------:|:---------------:|
|
| 71 |
+
| 16.0903 | 0.9967 | 226 | 0.1969 | 3.4455 |
|
| 72 |
+
| 11.5438 | 1.9967 | 452 | 0.2992 | 2.4033 |
|
| 73 |
+
| 9.5963 | 2.9967 | 678 | 0.3492 | 2.0761 |
|
| 74 |
+
| 8.3873 | 3.9967 | 904 | 0.3934 | 1.8921 |
|
| 75 |
+
| 7.3127 | 4.9967 | 1130 | 0.4288 | 1.7535 |
|
| 76 |
+
| 6.2178 | 5.9967 | 1356 | 0.4609 | 1.6533 |
|
| 77 |
+
| 5.4619 | 6.9967 | 1582 | 0.4856 | 1.5859 |
|
| 78 |
+
| 4.618 | 7.9967 | 1808 | 0.5129 | 1.5253 |
|
| 79 |
+
| 3.9349 | 8.9967 | 2034 | 0.5315 | 1.4693 |
|
| 80 |
+
| 3.4667 | 9.9967 | 2260 | 0.5412 | 1.4404 |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.996692392502757,
|
| 3 |
+
"total_flos": 1.8565430446260014e+20,
|
| 4 |
+
"train_loss": 8.705859319298668,
|
| 5 |
+
"train_runtime": 25889.9118,
|
| 6 |
+
"train_samples_per_second": 89.633,
|
| 7 |
+
"train_steps_per_second": 0.087
|
| 8 |
+
}
|
runs/Jan29_08-40-35_d0e85ba8394a/events.out.tfevents.1738140041.d0e85ba8394a.21250.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebc231b261860717c5deddb997d56642121b05af893772bed16490b126ee856f
|
| 3 |
+
size 251249
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.996692392502757,
|
| 3 |
+
"total_flos": 1.8565430446260014e+20,
|
| 4 |
+
"train_loss": 8.705859319298668,
|
| 5 |
+
"train_runtime": 25889.9118,
|
| 6 |
+
"train_samples_per_second": 89.633,
|
| 7 |
+
"train_steps_per_second": 0.087
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.541167345355827,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Inventariado_Mobiliario_Urbano/cars_brand_model/cmmy/checkpoint-2260",
|
| 4 |
+
"epoch": 9.996692392502757,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2260,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.044101433296582136,
|
| 13 |
+
"grad_norm": 4.8150153160095215,
|
| 14 |
+
"learning_rate": 4.424778761061947e-05,
|
| 15 |
+
"loss": 33.4771,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08820286659316427,
|
| 20 |
+
"grad_norm": 4.733597278594971,
|
| 21 |
+
"learning_rate": 8.849557522123894e-05,
|
| 22 |
+
"loss": 33.1339,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13230429988974643,
|
| 27 |
+
"grad_norm": 4.442318439483643,
|
| 28 |
+
"learning_rate": 0.00013274336283185842,
|
| 29 |
+
"loss": 32.4884,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.17640573318632854,
|
| 34 |
+
"grad_norm": 4.178449630737305,
|
| 35 |
+
"learning_rate": 0.00017699115044247788,
|
| 36 |
+
"loss": 31.6444,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2205071664829107,
|
| 41 |
+
"grad_norm": 4.139791965484619,
|
| 42 |
+
"learning_rate": 0.00022123893805309737,
|
| 43 |
+
"loss": 30.7515,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26460859977949286,
|
| 48 |
+
"grad_norm": 4.265659332275391,
|
| 49 |
+
"learning_rate": 0.00026548672566371683,
|
| 50 |
+
"loss": 29.8171,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.308710033076075,
|
| 55 |
+
"grad_norm": 4.5766921043396,
|
| 56 |
+
"learning_rate": 0.00030973451327433627,
|
| 57 |
+
"loss": 28.6353,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3528114663726571,
|
| 62 |
+
"grad_norm": 5.000542640686035,
|
| 63 |
+
"learning_rate": 0.00035398230088495576,
|
| 64 |
+
"loss": 27.6647,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.39691289966923926,
|
| 69 |
+
"grad_norm": 4.588747501373291,
|
| 70 |
+
"learning_rate": 0.00039823008849557525,
|
| 71 |
+
"loss": 26.439,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4410143329658214,
|
| 76 |
+
"grad_norm": 5.457170486450195,
|
| 77 |
+
"learning_rate": 0.00044247787610619474,
|
| 78 |
+
"loss": 25.3025,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.48511576626240355,
|
| 83 |
+
"grad_norm": 5.326786518096924,
|
| 84 |
+
"learning_rate": 0.0004867256637168142,
|
| 85 |
+
"loss": 24.4399,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5292171995589857,
|
| 90 |
+
"grad_norm": 5.408795356750488,
|
| 91 |
+
"learning_rate": 0.0005309734513274337,
|
| 92 |
+
"loss": 23.267,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5733186328555678,
|
| 97 |
+
"grad_norm": 5.888697624206543,
|
| 98 |
+
"learning_rate": 0.0005752212389380532,
|
| 99 |
+
"loss": 22.239,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.61742006615215,
|
| 104 |
+
"grad_norm": 6.699647903442383,
|
| 105 |
+
"learning_rate": 0.0006194690265486725,
|
| 106 |
+
"loss": 21.443,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6615214994487321,
|
| 111 |
+
"grad_norm": 5.940579891204834,
|
| 112 |
+
"learning_rate": 0.0006637168141592921,
|
| 113 |
+
"loss": 20.2496,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7056229327453142,
|
| 118 |
+
"grad_norm": 6.729783058166504,
|
| 119 |
+
"learning_rate": 0.0007079646017699115,
|
| 120 |
+
"loss": 19.7215,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7497243660418964,
|
| 125 |
+
"grad_norm": 7.232001781463623,
|
| 126 |
+
"learning_rate": 0.0007522123893805309,
|
| 127 |
+
"loss": 18.8327,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7938257993384785,
|
| 132 |
+
"grad_norm": 6.139113426208496,
|
| 133 |
+
"learning_rate": 0.0007964601769911505,
|
| 134 |
+
"loss": 18.3153,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8379272326350606,
|
| 139 |
+
"grad_norm": 6.233616828918457,
|
| 140 |
+
"learning_rate": 0.0008407079646017699,
|
| 141 |
+
"loss": 17.7032,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8820286659316428,
|
| 146 |
+
"grad_norm": 6.897170543670654,
|
| 147 |
+
"learning_rate": 0.0008849557522123895,
|
| 148 |
+
"loss": 16.9044,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9261300992282249,
|
| 153 |
+
"grad_norm": 6.186814785003662,
|
| 154 |
+
"learning_rate": 0.0009292035398230089,
|
| 155 |
+
"loss": 16.6313,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9702315325248071,
|
| 160 |
+
"grad_norm": 6.237786293029785,
|
| 161 |
+
"learning_rate": 0.0009734513274336283,
|
| 162 |
+
"loss": 16.0903,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9966923925027563,
|
| 167 |
+
"eval_accuracy": 0.19693620321892574,
|
| 168 |
+
"eval_loss": 3.4455316066741943,
|
| 169 |
+
"eval_runtime": 157.5981,
|
| 170 |
+
"eval_samples_per_second": 163.612,
|
| 171 |
+
"eval_steps_per_second": 0.641,
|
| 172 |
+
"step": 226
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.017640573318633,
|
| 176 |
+
"grad_norm": 5.7300639152526855,
|
| 177 |
+
"learning_rate": 0.0009980334316617503,
|
| 178 |
+
"loss": 16.2564,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.061742006615215,
|
| 183 |
+
"grad_norm": 6.365210056304932,
|
| 184 |
+
"learning_rate": 0.000993117010816126,
|
| 185 |
+
"loss": 14.7841,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.1058434399117971,
|
| 190 |
+
"grad_norm": 6.162064552307129,
|
| 191 |
+
"learning_rate": 0.0009882005899705015,
|
| 192 |
+
"loss": 14.7691,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.1499448732083792,
|
| 197 |
+
"grad_norm": 6.440285682678223,
|
| 198 |
+
"learning_rate": 0.0009832841691248771,
|
| 199 |
+
"loss": 14.1738,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.1940463065049614,
|
| 204 |
+
"grad_norm": 5.520109176635742,
|
| 205 |
+
"learning_rate": 0.0009783677482792527,
|
| 206 |
+
"loss": 14.0754,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.2381477398015435,
|
| 211 |
+
"grad_norm": 6.146816730499268,
|
| 212 |
+
"learning_rate": 0.0009734513274336283,
|
| 213 |
+
"loss": 13.9686,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.2822491730981258,
|
| 218 |
+
"grad_norm": 5.696677207946777,
|
| 219 |
+
"learning_rate": 0.000968534906588004,
|
| 220 |
+
"loss": 13.6213,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.326350606394708,
|
| 225 |
+
"grad_norm": 5.706403732299805,
|
| 226 |
+
"learning_rate": 0.0009636184857423795,
|
| 227 |
+
"loss": 13.2106,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.37045203969129,
|
| 232 |
+
"grad_norm": 6.3477067947387695,
|
| 233 |
+
"learning_rate": 0.0009587020648967551,
|
| 234 |
+
"loss": 13.1036,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.4145534729878722,
|
| 239 |
+
"grad_norm": 6.014346599578857,
|
| 240 |
+
"learning_rate": 0.0009537856440511307,
|
| 241 |
+
"loss": 13.0983,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.4586549062844543,
|
| 246 |
+
"grad_norm": 5.742127895355225,
|
| 247 |
+
"learning_rate": 0.0009488692232055063,
|
| 248 |
+
"loss": 12.6127,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.5027563395810364,
|
| 253 |
+
"grad_norm": 5.869048595428467,
|
| 254 |
+
"learning_rate": 0.0009439528023598821,
|
| 255 |
+
"loss": 12.7718,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.5468577728776185,
|
| 260 |
+
"grad_norm": 5.569489479064941,
|
| 261 |
+
"learning_rate": 0.0009390363815142577,
|
| 262 |
+
"loss": 12.4881,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.5909592061742006,
|
| 267 |
+
"grad_norm": 6.744396686553955,
|
| 268 |
+
"learning_rate": 0.0009341199606686333,
|
| 269 |
+
"loss": 12.3667,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.6350606394707827,
|
| 274 |
+
"grad_norm": 5.721745014190674,
|
| 275 |
+
"learning_rate": 0.0009292035398230089,
|
| 276 |
+
"loss": 12.169,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.6791620727673648,
|
| 281 |
+
"grad_norm": 6.00828742980957,
|
| 282 |
+
"learning_rate": 0.0009242871189773845,
|
| 283 |
+
"loss": 12.163,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.723263506063947,
|
| 288 |
+
"grad_norm": 6.328344345092773,
|
| 289 |
+
"learning_rate": 0.0009193706981317601,
|
| 290 |
+
"loss": 11.9877,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.767364939360529,
|
| 295 |
+
"grad_norm": 5.9762492179870605,
|
| 296 |
+
"learning_rate": 0.0009144542772861358,
|
| 297 |
+
"loss": 11.8959,
|
| 298 |
+
"step": 400
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.8114663726571112,
|
| 302 |
+
"grad_norm": 5.462543487548828,
|
| 303 |
+
"learning_rate": 0.0009095378564405114,
|
| 304 |
+
"loss": 11.8443,
|
| 305 |
+
"step": 410
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.8555678059536935,
|
| 309 |
+
"grad_norm": 5.628457069396973,
|
| 310 |
+
"learning_rate": 0.000904621435594887,
|
| 311 |
+
"loss": 11.7006,
|
| 312 |
+
"step": 420
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.8996692392502756,
|
| 316 |
+
"grad_norm": 5.508877754211426,
|
| 317 |
+
"learning_rate": 0.0008997050147492626,
|
| 318 |
+
"loss": 11.6014,
|
| 319 |
+
"step": 430
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.9437706725468578,
|
| 323 |
+
"grad_norm": 5.510633945465088,
|
| 324 |
+
"learning_rate": 0.0008947885939036382,
|
| 325 |
+
"loss": 11.4442,
|
| 326 |
+
"step": 440
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.9878721058434399,
|
| 330 |
+
"grad_norm": 5.567264080047607,
|
| 331 |
+
"learning_rate": 0.0008898721730580139,
|
| 332 |
+
"loss": 11.5438,
|
| 333 |
+
"step": 450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.9966923925027564,
|
| 337 |
+
"eval_accuracy": 0.299166181888695,
|
| 338 |
+
"eval_loss": 2.4033162593841553,
|
| 339 |
+
"eval_runtime": 157.919,
|
| 340 |
+
"eval_samples_per_second": 163.28,
|
| 341 |
+
"eval_steps_per_second": 0.64,
|
| 342 |
+
"step": 452
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.035281146637266,
|
| 346 |
+
"grad_norm": 5.653784275054932,
|
| 347 |
+
"learning_rate": 0.0008849557522123895,
|
| 348 |
+
"loss": 11.2957,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.079382579933848,
|
| 353 |
+
"grad_norm": 5.515305519104004,
|
| 354 |
+
"learning_rate": 0.0008800393313667651,
|
| 355 |
+
"loss": 10.4382,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.12348401323043,
|
| 360 |
+
"grad_norm": 5.540599346160889,
|
| 361 |
+
"learning_rate": 0.0008751229105211407,
|
| 362 |
+
"loss": 10.2655,
|
| 363 |
+
"step": 480
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.167585446527012,
|
| 367 |
+
"grad_norm": 5.588015079498291,
|
| 368 |
+
"learning_rate": 0.0008702064896755162,
|
| 369 |
+
"loss": 10.4359,
|
| 370 |
+
"step": 490
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.2116868798235942,
|
| 374 |
+
"grad_norm": 5.268083095550537,
|
| 375 |
+
"learning_rate": 0.0008652900688298918,
|
| 376 |
+
"loss": 10.4373,
|
| 377 |
+
"step": 500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.2557883131201764,
|
| 381 |
+
"grad_norm": 5.2158427238464355,
|
| 382 |
+
"learning_rate": 0.0008603736479842675,
|
| 383 |
+
"loss": 10.3617,
|
| 384 |
+
"step": 510
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.2998897464167585,
|
| 388 |
+
"grad_norm": 5.967540264129639,
|
| 389 |
+
"learning_rate": 0.0008554572271386431,
|
| 390 |
+
"loss": 10.343,
|
| 391 |
+
"step": 520
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.3439911797133406,
|
| 395 |
+
"grad_norm": 6.330170154571533,
|
| 396 |
+
"learning_rate": 0.0008505408062930187,
|
| 397 |
+
"loss": 10.3236,
|
| 398 |
+
"step": 530
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.3880926130099227,
|
| 402 |
+
"grad_norm": 5.394957065582275,
|
| 403 |
+
"learning_rate": 0.0008456243854473943,
|
| 404 |
+
"loss": 10.1741,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.432194046306505,
|
| 409 |
+
"grad_norm": 5.637348651885986,
|
| 410 |
+
"learning_rate": 0.0008407079646017699,
|
| 411 |
+
"loss": 10.1634,
|
| 412 |
+
"step": 550
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.476295479603087,
|
| 416 |
+
"grad_norm": 5.205583572387695,
|
| 417 |
+
"learning_rate": 0.0008357915437561455,
|
| 418 |
+
"loss": 10.0739,
|
| 419 |
+
"step": 560
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.5203969128996695,
|
| 423 |
+
"grad_norm": 5.155258655548096,
|
| 424 |
+
"learning_rate": 0.0008308751229105212,
|
| 425 |
+
"loss": 10.1469,
|
| 426 |
+
"step": 570
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.5644983461962516,
|
| 430 |
+
"grad_norm": 5.169893741607666,
|
| 431 |
+
"learning_rate": 0.0008259587020648968,
|
| 432 |
+
"loss": 10.0088,
|
| 433 |
+
"step": 580
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.6085997794928337,
|
| 437 |
+
"grad_norm": 5.327938556671143,
|
| 438 |
+
"learning_rate": 0.0008210422812192724,
|
| 439 |
+
"loss": 9.9356,
|
| 440 |
+
"step": 590
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.652701212789416,
|
| 444 |
+
"grad_norm": 5.036328315734863,
|
| 445 |
+
"learning_rate": 0.000816125860373648,
|
| 446 |
+
"loss": 9.8759,
|
| 447 |
+
"step": 600
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.696802646085998,
|
| 451 |
+
"grad_norm": 5.075291633605957,
|
| 452 |
+
"learning_rate": 0.0008112094395280236,
|
| 453 |
+
"loss": 9.8351,
|
| 454 |
+
"step": 610
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.74090407938258,
|
| 458 |
+
"grad_norm": 5.24298620223999,
|
| 459 |
+
"learning_rate": 0.0008062930186823992,
|
| 460 |
+
"loss": 9.6878,
|
| 461 |
+
"step": 620
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.785005512679162,
|
| 465 |
+
"grad_norm": 4.871809005737305,
|
| 466 |
+
"learning_rate": 0.0008013765978367749,
|
| 467 |
+
"loss": 9.9713,
|
| 468 |
+
"step": 630
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.8291069459757443,
|
| 472 |
+
"grad_norm": 4.931336879730225,
|
| 473 |
+
"learning_rate": 0.0007964601769911505,
|
| 474 |
+
"loss": 9.8542,
|
| 475 |
+
"step": 640
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.8732083792723264,
|
| 479 |
+
"grad_norm": 5.142650127410889,
|
| 480 |
+
"learning_rate": 0.0007915437561455261,
|
| 481 |
+
"loss": 9.8176,
|
| 482 |
+
"step": 650
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.9173098125689085,
|
| 486 |
+
"grad_norm": 5.100261211395264,
|
| 487 |
+
"learning_rate": 0.0007866273352999017,
|
| 488 |
+
"loss": 9.5995,
|
| 489 |
+
"step": 660
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.9614112458654906,
|
| 493 |
+
"grad_norm": 4.906562805175781,
|
| 494 |
+
"learning_rate": 0.0007817109144542773,
|
| 495 |
+
"loss": 9.5963,
|
| 496 |
+
"step": 670
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.9966923925027564,
|
| 500 |
+
"eval_accuracy": 0.3491564863292612,
|
| 501 |
+
"eval_loss": 2.0761232376098633,
|
| 502 |
+
"eval_runtime": 157.9952,
|
| 503 |
+
"eval_samples_per_second": 163.201,
|
| 504 |
+
"eval_steps_per_second": 0.639,
|
| 505 |
+
"step": 678
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.0088202866593163,
|
| 509 |
+
"grad_norm": 4.665123462677002,
|
| 510 |
+
"learning_rate": 0.000776794493608653,
|
| 511 |
+
"loss": 9.8294,
|
| 512 |
+
"step": 680
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.0529217199558984,
|
| 516 |
+
"grad_norm": 5.142998695373535,
|
| 517 |
+
"learning_rate": 0.0007718780727630286,
|
| 518 |
+
"loss": 8.6602,
|
| 519 |
+
"step": 690
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.0970231532524806,
|
| 523 |
+
"grad_norm": 4.909497261047363,
|
| 524 |
+
"learning_rate": 0.0007669616519174042,
|
| 525 |
+
"loss": 8.5178,
|
| 526 |
+
"step": 700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.1411245865490627,
|
| 530 |
+
"grad_norm": 4.914758682250977,
|
| 531 |
+
"learning_rate": 0.0007620452310717798,
|
| 532 |
+
"loss": 8.5225,
|
| 533 |
+
"step": 710
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 3.185226019845645,
|
| 537 |
+
"grad_norm": 4.778907299041748,
|
| 538 |
+
"learning_rate": 0.0007571288102261554,
|
| 539 |
+
"loss": 8.6442,
|
| 540 |
+
"step": 720
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.2293274531422274,
|
| 544 |
+
"grad_norm": 4.7863240242004395,
|
| 545 |
+
"learning_rate": 0.0007522123893805309,
|
| 546 |
+
"loss": 8.6121,
|
| 547 |
+
"step": 730
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.2734288864388095,
|
| 551 |
+
"grad_norm": 4.866987228393555,
|
| 552 |
+
"learning_rate": 0.0007472959685349066,
|
| 553 |
+
"loss": 8.6773,
|
| 554 |
+
"step": 740
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.3175303197353916,
|
| 558 |
+
"grad_norm": 4.968977451324463,
|
| 559 |
+
"learning_rate": 0.0007423795476892822,
|
| 560 |
+
"loss": 8.6663,
|
| 561 |
+
"step": 750
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.3616317530319737,
|
| 565 |
+
"grad_norm": 4.805993556976318,
|
| 566 |
+
"learning_rate": 0.0007374631268436578,
|
| 567 |
+
"loss": 8.6653,
|
| 568 |
+
"step": 760
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.405733186328556,
|
| 572 |
+
"grad_norm": 4.871044635772705,
|
| 573 |
+
"learning_rate": 0.0007325467059980334,
|
| 574 |
+
"loss": 8.5913,
|
| 575 |
+
"step": 770
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.449834619625138,
|
| 579 |
+
"grad_norm": 5.305060863494873,
|
| 580 |
+
"learning_rate": 0.000727630285152409,
|
| 581 |
+
"loss": 8.4683,
|
| 582 |
+
"step": 780
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.49393605292172,
|
| 586 |
+
"grad_norm": 4.906181812286377,
|
| 587 |
+
"learning_rate": 0.0007227138643067846,
|
| 588 |
+
"loss": 8.5715,
|
| 589 |
+
"step": 790
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.538037486218302,
|
| 593 |
+
"grad_norm": 4.955236434936523,
|
| 594 |
+
"learning_rate": 0.0007177974434611603,
|
| 595 |
+
"loss": 8.5461,
|
| 596 |
+
"step": 800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.5821389195148843,
|
| 600 |
+
"grad_norm": 4.7065863609313965,
|
| 601 |
+
"learning_rate": 0.0007128810226155359,
|
| 602 |
+
"loss": 8.5517,
|
| 603 |
+
"step": 810
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.6262403528114664,
|
| 607 |
+
"grad_norm": 4.8048930168151855,
|
| 608 |
+
"learning_rate": 0.0007079646017699115,
|
| 609 |
+
"loss": 8.6689,
|
| 610 |
+
"step": 820
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.6703417861080485,
|
| 614 |
+
"grad_norm": 5.108726978302002,
|
| 615 |
+
"learning_rate": 0.0007030481809242871,
|
| 616 |
+
"loss": 8.4989,
|
| 617 |
+
"step": 830
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.7144432194046306,
|
| 621 |
+
"grad_norm": 4.784049034118652,
|
| 622 |
+
"learning_rate": 0.0006981317600786627,
|
| 623 |
+
"loss": 8.5436,
|
| 624 |
+
"step": 840
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.7585446527012127,
|
| 628 |
+
"grad_norm": 4.953752517700195,
|
| 629 |
+
"learning_rate": 0.0006932153392330383,
|
| 630 |
+
"loss": 8.3707,
|
| 631 |
+
"step": 850
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 3.802646085997795,
|
| 635 |
+
"grad_norm": 4.866833686828613,
|
| 636 |
+
"learning_rate": 0.000688298918387414,
|
| 637 |
+
"loss": 8.5086,
|
| 638 |
+
"step": 860
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.846747519294377,
|
| 642 |
+
"grad_norm": 4.966568946838379,
|
| 643 |
+
"learning_rate": 0.0006833824975417896,
|
| 644 |
+
"loss": 8.3376,
|
| 645 |
+
"step": 870
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.890848952590959,
|
| 649 |
+
"grad_norm": 4.906131744384766,
|
| 650 |
+
"learning_rate": 0.0006784660766961652,
|
| 651 |
+
"loss": 8.3634,
|
| 652 |
+
"step": 880
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.934950385887541,
|
| 656 |
+
"grad_norm": 4.776595115661621,
|
| 657 |
+
"learning_rate": 0.0006735496558505408,
|
| 658 |
+
"loss": 8.3092,
|
| 659 |
+
"step": 890
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.9790518191841233,
|
| 663 |
+
"grad_norm": 4.59867525100708,
|
| 664 |
+
"learning_rate": 0.0006686332350049164,
|
| 665 |
+
"loss": 8.3873,
|
| 666 |
+
"step": 900
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.9966923925027564,
|
| 670 |
+
"eval_accuracy": 0.3934458018227652,
|
| 671 |
+
"eval_loss": 1.892139196395874,
|
| 672 |
+
"eval_runtime": 157.998,
|
| 673 |
+
"eval_samples_per_second": 163.198,
|
| 674 |
+
"eval_steps_per_second": 0.639,
|
| 675 |
+
"step": 904
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.0264608599779494,
|
| 679 |
+
"grad_norm": 4.579000473022461,
|
| 680 |
+
"learning_rate": 0.0006637168141592921,
|
| 681 |
+
"loss": 8.0129,
|
| 682 |
+
"step": 910
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.070562293274532,
|
| 686 |
+
"grad_norm": 4.628970623016357,
|
| 687 |
+
"learning_rate": 0.0006588003933136677,
|
| 688 |
+
"loss": 7.3258,
|
| 689 |
+
"step": 920
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.114663726571114,
|
| 693 |
+
"grad_norm": 4.4933953285217285,
|
| 694 |
+
"learning_rate": 0.0006538839724680433,
|
| 695 |
+
"loss": 7.3052,
|
| 696 |
+
"step": 930
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 4.158765159867696,
|
| 700 |
+
"grad_norm": 4.572768211364746,
|
| 701 |
+
"learning_rate": 0.0006489675516224189,
|
| 702 |
+
"loss": 7.3455,
|
| 703 |
+
"step": 940
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 4.202866593164278,
|
| 707 |
+
"grad_norm": 4.468959331512451,
|
| 708 |
+
"learning_rate": 0.0006440511307767945,
|
| 709 |
+
"loss": 7.3741,
|
| 710 |
+
"step": 950
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.24696802646086,
|
| 714 |
+
"grad_norm": 4.594937324523926,
|
| 715 |
+
"learning_rate": 0.00063913470993117,
|
| 716 |
+
"loss": 7.3599,
|
| 717 |
+
"step": 960
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 4.291069459757442,
|
| 721 |
+
"grad_norm": 4.6465935707092285,
|
| 722 |
+
"learning_rate": 0.0006342182890855457,
|
| 723 |
+
"loss": 7.3735,
|
| 724 |
+
"step": 970
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 4.335170893054024,
|
| 728 |
+
"grad_norm": 4.683464527130127,
|
| 729 |
+
"learning_rate": 0.0006293018682399213,
|
| 730 |
+
"loss": 7.447,
|
| 731 |
+
"step": 980
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 4.379272326350606,
|
| 735 |
+
"grad_norm": 4.466670989990234,
|
| 736 |
+
"learning_rate": 0.0006243854473942969,
|
| 737 |
+
"loss": 7.4649,
|
| 738 |
+
"step": 990
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 4.4233737596471885,
|
| 742 |
+
"grad_norm": 4.653200149536133,
|
| 743 |
+
"learning_rate": 0.0006194690265486725,
|
| 744 |
+
"loss": 7.3462,
|
| 745 |
+
"step": 1000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 4.467475192943771,
|
| 749 |
+
"grad_norm": 4.518767356872559,
|
| 750 |
+
"learning_rate": 0.0006145526057030481,
|
| 751 |
+
"loss": 7.2768,
|
| 752 |
+
"step": 1010
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 4.511576626240353,
|
| 756 |
+
"grad_norm": 4.512480735778809,
|
| 757 |
+
"learning_rate": 0.0006096361848574237,
|
| 758 |
+
"loss": 7.306,
|
| 759 |
+
"step": 1020
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 4.555678059536935,
|
| 763 |
+
"grad_norm": 4.512141704559326,
|
| 764 |
+
"learning_rate": 0.0006047197640117994,
|
| 765 |
+
"loss": 7.3665,
|
| 766 |
+
"step": 1030
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 4.599779492833517,
|
| 770 |
+
"grad_norm": 4.769530773162842,
|
| 771 |
+
"learning_rate": 0.000599803343166175,
|
| 772 |
+
"loss": 7.4248,
|
| 773 |
+
"step": 1040
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 4.643880926130099,
|
| 777 |
+
"grad_norm": 4.538891792297363,
|
| 778 |
+
"learning_rate": 0.0005948869223205506,
|
| 779 |
+
"loss": 7.3548,
|
| 780 |
+
"step": 1050
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 4.687982359426681,
|
| 784 |
+
"grad_norm": 4.579529762268066,
|
| 785 |
+
"learning_rate": 0.0005899705014749262,
|
| 786 |
+
"loss": 7.1825,
|
| 787 |
+
"step": 1060
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 4.732083792723263,
|
| 791 |
+
"grad_norm": 4.407522201538086,
|
| 792 |
+
"learning_rate": 0.0005850540806293018,
|
| 793 |
+
"loss": 7.3086,
|
| 794 |
+
"step": 1070
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 4.776185226019845,
|
| 798 |
+
"grad_norm": 4.507376194000244,
|
| 799 |
+
"learning_rate": 0.0005801376597836774,
|
| 800 |
+
"loss": 7.4489,
|
| 801 |
+
"step": 1080
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.8202866593164275,
|
| 805 |
+
"grad_norm": 4.580904960632324,
|
| 806 |
+
"learning_rate": 0.0005752212389380532,
|
| 807 |
+
"loss": 7.2829,
|
| 808 |
+
"step": 1090
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.86438809261301,
|
| 812 |
+
"grad_norm": 4.334172248840332,
|
| 813 |
+
"learning_rate": 0.0005703048180924288,
|
| 814 |
+
"loss": 7.3591,
|
| 815 |
+
"step": 1100
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.908489525909592,
|
| 819 |
+
"grad_norm": 4.6015095710754395,
|
| 820 |
+
"learning_rate": 0.0005653883972468044,
|
| 821 |
+
"loss": 7.3586,
|
| 822 |
+
"step": 1110
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 4.952590959206174,
|
| 826 |
+
"grad_norm": 4.470212936401367,
|
| 827 |
+
"learning_rate": 0.00056047197640118,
|
| 828 |
+
"loss": 7.3276,
|
| 829 |
+
"step": 1120
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.996692392502756,
|
| 833 |
+
"grad_norm": 4.509373664855957,
|
| 834 |
+
"learning_rate": 0.0005555555555555556,
|
| 835 |
+
"loss": 7.3127,
|
| 836 |
+
"step": 1130
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.996692392502756,
|
| 840 |
+
"eval_accuracy": 0.42877642039945707,
|
| 841 |
+
"eval_loss": 1.7534652948379517,
|
| 842 |
+
"eval_runtime": 157.6275,
|
| 843 |
+
"eval_samples_per_second": 163.582,
|
| 844 |
+
"eval_steps_per_second": 0.641,
|
| 845 |
+
"step": 1130
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 5.044101433296582,
|
| 849 |
+
"grad_norm": 4.370789527893066,
|
| 850 |
+
"learning_rate": 0.0005506391347099313,
|
| 851 |
+
"loss": 6.6219,
|
| 852 |
+
"step": 1140
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 5.088202866593164,
|
| 856 |
+
"grad_norm": 4.587760925292969,
|
| 857 |
+
"learning_rate": 0.0005457227138643069,
|
| 858 |
+
"loss": 6.382,
|
| 859 |
+
"step": 1150
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 5.132304299889746,
|
| 863 |
+
"grad_norm": 4.437044143676758,
|
| 864 |
+
"learning_rate": 0.0005408062930186825,
|
| 865 |
+
"loss": 6.3493,
|
| 866 |
+
"step": 1160
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 5.1764057331863285,
|
| 870 |
+
"grad_norm": 4.376111030578613,
|
| 871 |
+
"learning_rate": 0.0005358898721730581,
|
| 872 |
+
"loss": 6.3537,
|
| 873 |
+
"step": 1170
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 5.220507166482911,
|
| 877 |
+
"grad_norm": 4.685988903045654,
|
| 878 |
+
"learning_rate": 0.0005309734513274337,
|
| 879 |
+
"loss": 6.3465,
|
| 880 |
+
"step": 1180
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 5.264608599779493,
|
| 884 |
+
"grad_norm": 4.62017297744751,
|
| 885 |
+
"learning_rate": 0.0005260570304818093,
|
| 886 |
+
"loss": 6.3306,
|
| 887 |
+
"step": 1190
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 5.308710033076075,
|
| 891 |
+
"grad_norm": 4.6863112449646,
|
| 892 |
+
"learning_rate": 0.0005211406096361849,
|
| 893 |
+
"loss": 6.4408,
|
| 894 |
+
"step": 1200
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 5.352811466372657,
|
| 898 |
+
"grad_norm": 4.470117092132568,
|
| 899 |
+
"learning_rate": 0.0005162241887905605,
|
| 900 |
+
"loss": 6.4383,
|
| 901 |
+
"step": 1210
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 5.396912899669239,
|
| 905 |
+
"grad_norm": 4.46852445602417,
|
| 906 |
+
"learning_rate": 0.0005113077679449361,
|
| 907 |
+
"loss": 6.2687,
|
| 908 |
+
"step": 1220
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 5.441014332965821,
|
| 912 |
+
"grad_norm": 4.40092134475708,
|
| 913 |
+
"learning_rate": 0.0005063913470993117,
|
| 914 |
+
"loss": 6.3344,
|
| 915 |
+
"step": 1230
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 5.485115766262403,
|
| 919 |
+
"grad_norm": 4.5052595138549805,
|
| 920 |
+
"learning_rate": 0.0005014749262536873,
|
| 921 |
+
"loss": 6.3289,
|
| 922 |
+
"step": 1240
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 5.529217199558985,
|
| 926 |
+
"grad_norm": 4.2100419998168945,
|
| 927 |
+
"learning_rate": 0.000496558505408063,
|
| 928 |
+
"loss": 6.4074,
|
| 929 |
+
"step": 1250
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 5.5733186328555675,
|
| 933 |
+
"grad_norm": 4.383902549743652,
|
| 934 |
+
"learning_rate": 0.0004916420845624386,
|
| 935 |
+
"loss": 6.3748,
|
| 936 |
+
"step": 1260
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 5.61742006615215,
|
| 940 |
+
"grad_norm": 4.348648548126221,
|
| 941 |
+
"learning_rate": 0.0004867256637168142,
|
| 942 |
+
"loss": 6.2771,
|
| 943 |
+
"step": 1270
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 5.661521499448732,
|
| 947 |
+
"grad_norm": 4.597408294677734,
|
| 948 |
+
"learning_rate": 0.0004818092428711898,
|
| 949 |
+
"loss": 6.4728,
|
| 950 |
+
"step": 1280
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 5.705622932745314,
|
| 954 |
+
"grad_norm": 4.483145236968994,
|
| 955 |
+
"learning_rate": 0.0004768928220255654,
|
| 956 |
+
"loss": 6.3158,
|
| 957 |
+
"step": 1290
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 5.749724366041896,
|
| 961 |
+
"grad_norm": 4.486307144165039,
|
| 962 |
+
"learning_rate": 0.00047197640117994103,
|
| 963 |
+
"loss": 6.3443,
|
| 964 |
+
"step": 1300
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 5.793825799338478,
|
| 968 |
+
"grad_norm": 4.527980804443359,
|
| 969 |
+
"learning_rate": 0.00046705998033431663,
|
| 970 |
+
"loss": 6.306,
|
| 971 |
+
"step": 1310
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 5.83792723263506,
|
| 975 |
+
"grad_norm": 4.423805236816406,
|
| 976 |
+
"learning_rate": 0.00046214355948869223,
|
| 977 |
+
"loss": 6.2912,
|
| 978 |
+
"step": 1320
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 5.882028665931642,
|
| 982 |
+
"grad_norm": 4.3704752922058105,
|
| 983 |
+
"learning_rate": 0.0004572271386430679,
|
| 984 |
+
"loss": 6.2006,
|
| 985 |
+
"step": 1330
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 5.926130099228224,
|
| 989 |
+
"grad_norm": 4.610422611236572,
|
| 990 |
+
"learning_rate": 0.0004523107177974435,
|
| 991 |
+
"loss": 6.2838,
|
| 992 |
+
"step": 1340
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 5.970231532524807,
|
| 996 |
+
"grad_norm": 4.506854057312012,
|
| 997 |
+
"learning_rate": 0.0004473942969518191,
|
| 998 |
+
"loss": 6.2178,
|
| 999 |
+
"step": 1350
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.996692392502756,
|
| 1003 |
+
"eval_accuracy": 0.4608881132441342,
|
| 1004 |
+
"eval_loss": 1.6532503366470337,
|
| 1005 |
+
"eval_runtime": 157.0061,
|
| 1006 |
+
"eval_samples_per_second": 164.229,
|
| 1007 |
+
"eval_steps_per_second": 0.643,
|
| 1008 |
+
"step": 1356
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 6.017640573318633,
|
| 1012 |
+
"grad_norm": 4.212904930114746,
|
| 1013 |
+
"learning_rate": 0.00044247787610619474,
|
| 1014 |
+
"loss": 6.1728,
|
| 1015 |
+
"step": 1360
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 6.061742006615215,
|
| 1019 |
+
"grad_norm": 4.3509931564331055,
|
| 1020 |
+
"learning_rate": 0.00043756145526057034,
|
| 1021 |
+
"loss": 5.4675,
|
| 1022 |
+
"step": 1370
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 6.105843439911797,
|
| 1026 |
+
"grad_norm": 4.346857070922852,
|
| 1027 |
+
"learning_rate": 0.0004326450344149459,
|
| 1028 |
+
"loss": 5.4391,
|
| 1029 |
+
"step": 1380
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 6.149944873208379,
|
| 1033 |
+
"grad_norm": 4.269370079040527,
|
| 1034 |
+
"learning_rate": 0.00042772861356932154,
|
| 1035 |
+
"loss": 5.6166,
|
| 1036 |
+
"step": 1390
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 6.194046306504961,
|
| 1040 |
+
"grad_norm": 4.528676986694336,
|
| 1041 |
+
"learning_rate": 0.00042281219272369714,
|
| 1042 |
+
"loss": 5.4683,
|
| 1043 |
+
"step": 1400
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 6.238147739801543,
|
| 1047 |
+
"grad_norm": 4.301924705505371,
|
| 1048 |
+
"learning_rate": 0.00041789577187807274,
|
| 1049 |
+
"loss": 5.6475,
|
| 1050 |
+
"step": 1410
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 6.282249173098125,
|
| 1054 |
+
"grad_norm": 4.408478736877441,
|
| 1055 |
+
"learning_rate": 0.0004129793510324484,
|
| 1056 |
+
"loss": 5.5012,
|
| 1057 |
+
"step": 1420
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 6.3263506063947075,
|
| 1061 |
+
"grad_norm": 4.205230712890625,
|
| 1062 |
+
"learning_rate": 0.000408062930186824,
|
| 1063 |
+
"loss": 5.4751,
|
| 1064 |
+
"step": 1430
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 6.37045203969129,
|
| 1068 |
+
"grad_norm": 4.417777061462402,
|
| 1069 |
+
"learning_rate": 0.0004031465093411996,
|
| 1070 |
+
"loss": 5.4574,
|
| 1071 |
+
"step": 1440
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 6.414553472987872,
|
| 1075 |
+
"grad_norm": 4.562683582305908,
|
| 1076 |
+
"learning_rate": 0.00039823008849557525,
|
| 1077 |
+
"loss": 5.5681,
|
| 1078 |
+
"step": 1450
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 6.458654906284455,
|
| 1082 |
+
"grad_norm": 4.4911112785339355,
|
| 1083 |
+
"learning_rate": 0.00039331366764995085,
|
| 1084 |
+
"loss": 5.5747,
|
| 1085 |
+
"step": 1460
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 6.502756339581037,
|
| 1089 |
+
"grad_norm": 4.3542890548706055,
|
| 1090 |
+
"learning_rate": 0.0003883972468043265,
|
| 1091 |
+
"loss": 5.4824,
|
| 1092 |
+
"step": 1470
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 6.546857772877619,
|
| 1096 |
+
"grad_norm": 4.291258811950684,
|
| 1097 |
+
"learning_rate": 0.0003834808259587021,
|
| 1098 |
+
"loss": 5.3834,
|
| 1099 |
+
"step": 1480
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 6.590959206174201,
|
| 1103 |
+
"grad_norm": 4.43005895614624,
|
| 1104 |
+
"learning_rate": 0.0003785644051130777,
|
| 1105 |
+
"loss": 5.4797,
|
| 1106 |
+
"step": 1490
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 6.635060639470783,
|
| 1110 |
+
"grad_norm": 4.461911201477051,
|
| 1111 |
+
"learning_rate": 0.0003736479842674533,
|
| 1112 |
+
"loss": 5.5312,
|
| 1113 |
+
"step": 1500
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 6.679162072767365,
|
| 1117 |
+
"grad_norm": 4.246000289916992,
|
| 1118 |
+
"learning_rate": 0.0003687315634218289,
|
| 1119 |
+
"loss": 5.5821,
|
| 1120 |
+
"step": 1510
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 6.723263506063947,
|
| 1124 |
+
"grad_norm": 4.318939685821533,
|
| 1125 |
+
"learning_rate": 0.0003638151425762045,
|
| 1126 |
+
"loss": 5.5103,
|
| 1127 |
+
"step": 1520
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 6.7673649393605295,
|
| 1131 |
+
"grad_norm": 4.241775989532471,
|
| 1132 |
+
"learning_rate": 0.00035889872173058016,
|
| 1133 |
+
"loss": 5.4244,
|
| 1134 |
+
"step": 1530
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 6.811466372657112,
|
| 1138 |
+
"grad_norm": 4.246124267578125,
|
| 1139 |
+
"learning_rate": 0.00035398230088495576,
|
| 1140 |
+
"loss": 5.4415,
|
| 1141 |
+
"step": 1540
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 6.855567805953694,
|
| 1145 |
+
"grad_norm": 4.474425792694092,
|
| 1146 |
+
"learning_rate": 0.00034906588003933136,
|
| 1147 |
+
"loss": 5.4259,
|
| 1148 |
+
"step": 1550
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 6.899669239250276,
|
| 1152 |
+
"grad_norm": 4.427676677703857,
|
| 1153 |
+
"learning_rate": 0.000344149459193707,
|
| 1154 |
+
"loss": 5.4803,
|
| 1155 |
+
"step": 1560
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 6.943770672546858,
|
| 1159 |
+
"grad_norm": 4.402575969696045,
|
| 1160 |
+
"learning_rate": 0.0003392330383480826,
|
| 1161 |
+
"loss": 5.3709,
|
| 1162 |
+
"step": 1570
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 6.98787210584344,
|
| 1166 |
+
"grad_norm": 4.089934349060059,
|
| 1167 |
+
"learning_rate": 0.0003343166175024582,
|
| 1168 |
+
"loss": 5.4619,
|
| 1169 |
+
"step": 1580
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 6.996692392502756,
|
| 1173 |
+
"eval_accuracy": 0.4855923986814039,
|
| 1174 |
+
"eval_loss": 1.5859359502792358,
|
| 1175 |
+
"eval_runtime": 157.4699,
|
| 1176 |
+
"eval_samples_per_second": 163.746,
|
| 1177 |
+
"eval_steps_per_second": 0.641,
|
| 1178 |
+
"step": 1582
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 7.035281146637265,
|
| 1182 |
+
"grad_norm": 4.048954963684082,
|
| 1183 |
+
"learning_rate": 0.00032940019665683387,
|
| 1184 |
+
"loss": 4.9956,
|
| 1185 |
+
"step": 1590
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 7.0793825799338475,
|
| 1189 |
+
"grad_norm": 4.142811298370361,
|
| 1190 |
+
"learning_rate": 0.00032448377581120947,
|
| 1191 |
+
"loss": 4.637,
|
| 1192 |
+
"step": 1600
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 7.12348401323043,
|
| 1196 |
+
"grad_norm": 4.157500267028809,
|
| 1197 |
+
"learning_rate": 0.000319567354965585,
|
| 1198 |
+
"loss": 4.7621,
|
| 1199 |
+
"step": 1610
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 7.167585446527012,
|
| 1203 |
+
"grad_norm": 4.244820594787598,
|
| 1204 |
+
"learning_rate": 0.00031465093411996067,
|
| 1205 |
+
"loss": 4.671,
|
| 1206 |
+
"step": 1620
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 7.211686879823595,
|
| 1210 |
+
"grad_norm": 4.291553497314453,
|
| 1211 |
+
"learning_rate": 0.00030973451327433627,
|
| 1212 |
+
"loss": 4.7641,
|
| 1213 |
+
"step": 1630
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 7.255788313120177,
|
| 1217 |
+
"grad_norm": 4.3009233474731445,
|
| 1218 |
+
"learning_rate": 0.00030481809242871187,
|
| 1219 |
+
"loss": 4.7801,
|
| 1220 |
+
"step": 1640
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 7.299889746416759,
|
| 1224 |
+
"grad_norm": 4.151345729827881,
|
| 1225 |
+
"learning_rate": 0.0002999016715830875,
|
| 1226 |
+
"loss": 4.7008,
|
| 1227 |
+
"step": 1650
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 7.343991179713341,
|
| 1231 |
+
"grad_norm": 4.11318826675415,
|
| 1232 |
+
"learning_rate": 0.0002949852507374631,
|
| 1233 |
+
"loss": 4.5749,
|
| 1234 |
+
"step": 1660
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 7.388092613009923,
|
| 1238 |
+
"grad_norm": 4.272958755493164,
|
| 1239 |
+
"learning_rate": 0.0002900688298918387,
|
| 1240 |
+
"loss": 4.7279,
|
| 1241 |
+
"step": 1670
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 7.432194046306505,
|
| 1245 |
+
"grad_norm": 4.370232105255127,
|
| 1246 |
+
"learning_rate": 0.0002851524090462144,
|
| 1247 |
+
"loss": 4.6739,
|
| 1248 |
+
"step": 1680
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 7.476295479603087,
|
| 1252 |
+
"grad_norm": 4.224992752075195,
|
| 1253 |
+
"learning_rate": 0.00028023598820059,
|
| 1254 |
+
"loss": 4.6791,
|
| 1255 |
+
"step": 1690
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 7.5203969128996695,
|
| 1259 |
+
"grad_norm": 4.131043434143066,
|
| 1260 |
+
"learning_rate": 0.00027531956735496563,
|
| 1261 |
+
"loss": 4.742,
|
| 1262 |
+
"step": 1700
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 7.564498346196252,
|
| 1266 |
+
"grad_norm": 4.325319290161133,
|
| 1267 |
+
"learning_rate": 0.00027040314650934123,
|
| 1268 |
+
"loss": 4.6848,
|
| 1269 |
+
"step": 1710
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 7.608599779492834,
|
| 1273 |
+
"grad_norm": 4.375499248504639,
|
| 1274 |
+
"learning_rate": 0.00026548672566371683,
|
| 1275 |
+
"loss": 4.7289,
|
| 1276 |
+
"step": 1720
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 7.652701212789416,
|
| 1280 |
+
"grad_norm": 4.138423442840576,
|
| 1281 |
+
"learning_rate": 0.00026057030481809243,
|
| 1282 |
+
"loss": 4.7507,
|
| 1283 |
+
"step": 1730
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 7.696802646085998,
|
| 1287 |
+
"grad_norm": 4.30584716796875,
|
| 1288 |
+
"learning_rate": 0.00025565388397246803,
|
| 1289 |
+
"loss": 4.7498,
|
| 1290 |
+
"step": 1740
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 7.74090407938258,
|
| 1294 |
+
"grad_norm": 4.196134567260742,
|
| 1295 |
+
"learning_rate": 0.00025073746312684363,
|
| 1296 |
+
"loss": 4.6912,
|
| 1297 |
+
"step": 1750
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 7.785005512679162,
|
| 1301 |
+
"grad_norm": 4.179983615875244,
|
| 1302 |
+
"learning_rate": 0.0002458210422812193,
|
| 1303 |
+
"loss": 4.6327,
|
| 1304 |
+
"step": 1760
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 7.829106945975744,
|
| 1308 |
+
"grad_norm": 4.482637405395508,
|
| 1309 |
+
"learning_rate": 0.0002409046214355949,
|
| 1310 |
+
"loss": 4.7178,
|
| 1311 |
+
"step": 1770
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 7.873208379272326,
|
| 1315 |
+
"grad_norm": 4.053654670715332,
|
| 1316 |
+
"learning_rate": 0.00023598820058997051,
|
| 1317 |
+
"loss": 4.6353,
|
| 1318 |
+
"step": 1780
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 7.9173098125689085,
|
| 1322 |
+
"grad_norm": 4.109724998474121,
|
| 1323 |
+
"learning_rate": 0.00023107177974434611,
|
| 1324 |
+
"loss": 4.6531,
|
| 1325 |
+
"step": 1790
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 7.961411245865491,
|
| 1329 |
+
"grad_norm": 4.190576553344727,
|
| 1330 |
+
"learning_rate": 0.00022615535889872174,
|
| 1331 |
+
"loss": 4.618,
|
| 1332 |
+
"step": 1800
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 7.996692392502756,
|
| 1336 |
+
"eval_accuracy": 0.5128950940469265,
|
| 1337 |
+
"eval_loss": 1.52533757686615,
|
| 1338 |
+
"eval_runtime": 159.0581,
|
| 1339 |
+
"eval_samples_per_second": 162.111,
|
| 1340 |
+
"eval_steps_per_second": 0.635,
|
| 1341 |
+
"step": 1808
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 8.008820286659317,
|
| 1345 |
+
"grad_norm": 3.9392812252044678,
|
| 1346 |
+
"learning_rate": 0.00022123893805309737,
|
| 1347 |
+
"loss": 4.6935,
|
| 1348 |
+
"step": 1810
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 8.052921719955899,
|
| 1352 |
+
"grad_norm": 3.8019185066223145,
|
| 1353 |
+
"learning_rate": 0.00021632251720747294,
|
| 1354 |
+
"loss": 3.9004,
|
| 1355 |
+
"step": 1820
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 8.097023153252481,
|
| 1359 |
+
"grad_norm": 3.8372962474823,
|
| 1360 |
+
"learning_rate": 0.00021140609636184857,
|
| 1361 |
+
"loss": 4.0764,
|
| 1362 |
+
"step": 1830
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 8.141124586549063,
|
| 1366 |
+
"grad_norm": 4.013173580169678,
|
| 1367 |
+
"learning_rate": 0.0002064896755162242,
|
| 1368 |
+
"loss": 3.921,
|
| 1369 |
+
"step": 1840
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 8.185226019845645,
|
| 1373 |
+
"grad_norm": 4.06724739074707,
|
| 1374 |
+
"learning_rate": 0.0002015732546705998,
|
| 1375 |
+
"loss": 4.1819,
|
| 1376 |
+
"step": 1850
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 8.229327453142227,
|
| 1380 |
+
"grad_norm": 3.967484474182129,
|
| 1381 |
+
"learning_rate": 0.00019665683382497542,
|
| 1382 |
+
"loss": 4.1189,
|
| 1383 |
+
"step": 1860
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 8.27342888643881,
|
| 1387 |
+
"grad_norm": 3.8714957237243652,
|
| 1388 |
+
"learning_rate": 0.00019174041297935105,
|
| 1389 |
+
"loss": 4.0143,
|
| 1390 |
+
"step": 1870
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 8.317530319735392,
|
| 1394 |
+
"grad_norm": 3.9495551586151123,
|
| 1395 |
+
"learning_rate": 0.00018682399213372665,
|
| 1396 |
+
"loss": 4.1982,
|
| 1397 |
+
"step": 1880
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 8.361631753031974,
|
| 1401 |
+
"grad_norm": 4.08094596862793,
|
| 1402 |
+
"learning_rate": 0.00018190757128810225,
|
| 1403 |
+
"loss": 4.0732,
|
| 1404 |
+
"step": 1890
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 8.405733186328556,
|
| 1408 |
+
"grad_norm": 3.997749090194702,
|
| 1409 |
+
"learning_rate": 0.00017699115044247788,
|
| 1410 |
+
"loss": 4.0657,
|
| 1411 |
+
"step": 1900
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 8.449834619625138,
|
| 1415 |
+
"grad_norm": 3.9958107471466064,
|
| 1416 |
+
"learning_rate": 0.0001720747295968535,
|
| 1417 |
+
"loss": 4.0651,
|
| 1418 |
+
"step": 1910
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 8.49393605292172,
|
| 1422 |
+
"grad_norm": 4.039346218109131,
|
| 1423 |
+
"learning_rate": 0.0001671583087512291,
|
| 1424 |
+
"loss": 4.0022,
|
| 1425 |
+
"step": 1920
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 8.538037486218302,
|
| 1429 |
+
"grad_norm": 4.07537317276001,
|
| 1430 |
+
"learning_rate": 0.00016224188790560473,
|
| 1431 |
+
"loss": 4.0364,
|
| 1432 |
+
"step": 1930
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 8.582138919514884,
|
| 1436 |
+
"grad_norm": 3.949800491333008,
|
| 1437 |
+
"learning_rate": 0.00015732546705998033,
|
| 1438 |
+
"loss": 4.0273,
|
| 1439 |
+
"step": 1940
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 8.626240352811466,
|
| 1443 |
+
"grad_norm": 3.9785361289978027,
|
| 1444 |
+
"learning_rate": 0.00015240904621435593,
|
| 1445 |
+
"loss": 4.1008,
|
| 1446 |
+
"step": 1950
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 8.670341786108049,
|
| 1450 |
+
"grad_norm": 4.0533318519592285,
|
| 1451 |
+
"learning_rate": 0.00014749262536873156,
|
| 1452 |
+
"loss": 3.9856,
|
| 1453 |
+
"step": 1960
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 8.71444321940463,
|
| 1457 |
+
"grad_norm": 3.9734625816345215,
|
| 1458 |
+
"learning_rate": 0.0001425762045231072,
|
| 1459 |
+
"loss": 3.9327,
|
| 1460 |
+
"step": 1970
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 8.758544652701213,
|
| 1464 |
+
"grad_norm": 4.144639015197754,
|
| 1465 |
+
"learning_rate": 0.00013765978367748282,
|
| 1466 |
+
"loss": 4.1105,
|
| 1467 |
+
"step": 1980
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 8.802646085997795,
|
| 1471 |
+
"grad_norm": 4.224411487579346,
|
| 1472 |
+
"learning_rate": 0.00013274336283185842,
|
| 1473 |
+
"loss": 4.0302,
|
| 1474 |
+
"step": 1990
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 8.846747519294377,
|
| 1478 |
+
"grad_norm": 4.210290908813477,
|
| 1479 |
+
"learning_rate": 0.00012782694198623402,
|
| 1480 |
+
"loss": 3.9702,
|
| 1481 |
+
"step": 2000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 8.890848952590959,
|
| 1485 |
+
"grad_norm": 3.948779821395874,
|
| 1486 |
+
"learning_rate": 0.00012291052114060964,
|
| 1487 |
+
"loss": 4.0179,
|
| 1488 |
+
"step": 2010
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 8.934950385887541,
|
| 1492 |
+
"grad_norm": 4.020263671875,
|
| 1493 |
+
"learning_rate": 0.00011799410029498526,
|
| 1494 |
+
"loss": 3.9426,
|
| 1495 |
+
"step": 2020
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 8.979051819184123,
|
| 1499 |
+
"grad_norm": 3.9727530479431152,
|
| 1500 |
+
"learning_rate": 0.00011307767944936087,
|
| 1501 |
+
"loss": 3.9349,
|
| 1502 |
+
"step": 2030
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 8.996692392502757,
|
| 1506 |
+
"eval_accuracy": 0.5314717859220477,
|
| 1507 |
+
"eval_loss": 1.4693009853363037,
|
| 1508 |
+
"eval_runtime": 158.202,
|
| 1509 |
+
"eval_samples_per_second": 162.988,
|
| 1510 |
+
"eval_steps_per_second": 0.638,
|
| 1511 |
+
"step": 2034
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 9.026460859977949,
|
| 1515 |
+
"grad_norm": 4.023420333862305,
|
| 1516 |
+
"learning_rate": 0.00010816125860373647,
|
| 1517 |
+
"loss": 4.0029,
|
| 1518 |
+
"step": 2040
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 9.07056229327453,
|
| 1522 |
+
"grad_norm": 3.8481717109680176,
|
| 1523 |
+
"learning_rate": 0.0001032448377581121,
|
| 1524 |
+
"loss": 3.5067,
|
| 1525 |
+
"step": 2050
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 9.114663726571113,
|
| 1529 |
+
"grad_norm": 3.807828187942505,
|
| 1530 |
+
"learning_rate": 9.832841691248771e-05,
|
| 1531 |
+
"loss": 3.5354,
|
| 1532 |
+
"step": 2060
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 9.158765159867695,
|
| 1536 |
+
"grad_norm": 3.808962106704712,
|
| 1537 |
+
"learning_rate": 9.341199606686333e-05,
|
| 1538 |
+
"loss": 3.6032,
|
| 1539 |
+
"step": 2070
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 9.202866593164277,
|
| 1543 |
+
"grad_norm": 3.6250662803649902,
|
| 1544 |
+
"learning_rate": 8.849557522123894e-05,
|
| 1545 |
+
"loss": 3.5225,
|
| 1546 |
+
"step": 2080
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 9.24696802646086,
|
| 1550 |
+
"grad_norm": 3.9860610961914062,
|
| 1551 |
+
"learning_rate": 8.357915437561455e-05,
|
| 1552 |
+
"loss": 3.6428,
|
| 1553 |
+
"step": 2090
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 9.291069459757441,
|
| 1557 |
+
"grad_norm": 3.9992544651031494,
|
| 1558 |
+
"learning_rate": 7.866273352999017e-05,
|
| 1559 |
+
"loss": 3.4771,
|
| 1560 |
+
"step": 2100
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 9.335170893054023,
|
| 1564 |
+
"grad_norm": 3.782989740371704,
|
| 1565 |
+
"learning_rate": 7.374631268436578e-05,
|
| 1566 |
+
"loss": 3.506,
|
| 1567 |
+
"step": 2110
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 9.379272326350605,
|
| 1571 |
+
"grad_norm": 3.9225122928619385,
|
| 1572 |
+
"learning_rate": 6.882989183874141e-05,
|
| 1573 |
+
"loss": 3.4989,
|
| 1574 |
+
"step": 2120
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 9.42337375964719,
|
| 1578 |
+
"grad_norm": 3.853450298309326,
|
| 1579 |
+
"learning_rate": 6.391347099311701e-05,
|
| 1580 |
+
"loss": 3.49,
|
| 1581 |
+
"step": 2130
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 9.467475192943771,
|
| 1585 |
+
"grad_norm": 3.887131452560425,
|
| 1586 |
+
"learning_rate": 5.899705014749263e-05,
|
| 1587 |
+
"loss": 3.5517,
|
| 1588 |
+
"step": 2140
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 9.511576626240354,
|
| 1592 |
+
"grad_norm": 3.7988171577453613,
|
| 1593 |
+
"learning_rate": 5.4080629301868236e-05,
|
| 1594 |
+
"loss": 3.4626,
|
| 1595 |
+
"step": 2150
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 9.555678059536936,
|
| 1599 |
+
"grad_norm": 3.80769419670105,
|
| 1600 |
+
"learning_rate": 4.9164208456243856e-05,
|
| 1601 |
+
"loss": 3.5627,
|
| 1602 |
+
"step": 2160
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 9.599779492833518,
|
| 1606 |
+
"grad_norm": 3.883881092071533,
|
| 1607 |
+
"learning_rate": 4.424778761061947e-05,
|
| 1608 |
+
"loss": 3.5904,
|
| 1609 |
+
"step": 2170
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 9.6438809261301,
|
| 1613 |
+
"grad_norm": 3.729762554168701,
|
| 1614 |
+
"learning_rate": 3.9331366764995083e-05,
|
| 1615 |
+
"loss": 3.5366,
|
| 1616 |
+
"step": 2180
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 9.687982359426682,
|
| 1620 |
+
"grad_norm": 3.7784054279327393,
|
| 1621 |
+
"learning_rate": 3.4414945919370704e-05,
|
| 1622 |
+
"loss": 3.5186,
|
| 1623 |
+
"step": 2190
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 9.732083792723264,
|
| 1627 |
+
"grad_norm": 3.8702545166015625,
|
| 1628 |
+
"learning_rate": 2.9498525073746314e-05,
|
| 1629 |
+
"loss": 3.385,
|
| 1630 |
+
"step": 2200
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 9.776185226019846,
|
| 1634 |
+
"grad_norm": 3.82987380027771,
|
| 1635 |
+
"learning_rate": 2.4582104228121928e-05,
|
| 1636 |
+
"loss": 3.4502,
|
| 1637 |
+
"step": 2210
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 9.820286659316428,
|
| 1641 |
+
"grad_norm": 3.7813146114349365,
|
| 1642 |
+
"learning_rate": 1.9665683382497542e-05,
|
| 1643 |
+
"loss": 3.4203,
|
| 1644 |
+
"step": 2220
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 9.86438809261301,
|
| 1648 |
+
"grad_norm": 3.8914685249328613,
|
| 1649 |
+
"learning_rate": 1.4749262536873157e-05,
|
| 1650 |
+
"loss": 3.5059,
|
| 1651 |
+
"step": 2230
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 9.908489525909593,
|
| 1655 |
+
"grad_norm": 3.8533997535705566,
|
| 1656 |
+
"learning_rate": 9.832841691248771e-06,
|
| 1657 |
+
"loss": 3.483,
|
| 1658 |
+
"step": 2240
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 9.952590959206175,
|
| 1662 |
+
"grad_norm": 3.7153797149658203,
|
| 1663 |
+
"learning_rate": 4.9164208456243854e-06,
|
| 1664 |
+
"loss": 3.5258,
|
| 1665 |
+
"step": 2250
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 9.996692392502757,
|
| 1669 |
+
"grad_norm": 3.670651435852051,
|
| 1670 |
+
"learning_rate": 0.0,
|
| 1671 |
+
"loss": 3.4667,
|
| 1672 |
+
"step": 2260
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 9.996692392502757,
|
| 1676 |
+
"eval_accuracy": 0.541167345355827,
|
| 1677 |
+
"eval_loss": 1.4404356479644775,
|
| 1678 |
+
"eval_runtime": 159.5598,
|
| 1679 |
+
"eval_samples_per_second": 161.601,
|
| 1680 |
+
"eval_steps_per_second": 0.633,
|
| 1681 |
+
"step": 2260
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 9.996692392502757,
|
| 1685 |
+
"step": 2260,
|
| 1686 |
+
"total_flos": 1.8565430446260014e+20,
|
| 1687 |
+
"train_loss": 8.705859319298668,
|
| 1688 |
+
"train_runtime": 25889.9118,
|
| 1689 |
+
"train_samples_per_second": 89.633,
|
| 1690 |
+
"train_steps_per_second": 0.087
|
| 1691 |
+
}
|
| 1692 |
+
],
|
| 1693 |
+
"logging_steps": 10,
|
| 1694 |
+
"max_steps": 2260,
|
| 1695 |
+
"num_input_tokens_seen": 0,
|
| 1696 |
+
"num_train_epochs": 10,
|
| 1697 |
+
"save_steps": 500,
|
| 1698 |
+
"stateful_callbacks": {
|
| 1699 |
+
"TrainerControl": {
|
| 1700 |
+
"args": {
|
| 1701 |
+
"should_epoch_stop": false,
|
| 1702 |
+
"should_evaluate": false,
|
| 1703 |
+
"should_log": false,
|
| 1704 |
+
"should_save": true,
|
| 1705 |
+
"should_training_stop": true
|
| 1706 |
+
},
|
| 1707 |
+
"attributes": {}
|
| 1708 |
+
}
|
| 1709 |
+
},
|
| 1710 |
+
"total_flos": 1.8565430446260014e+20,
|
| 1711 |
+
"train_batch_size": 256,
|
| 1712 |
+
"trial_name": null,
|
| 1713 |
+
"trial_params": null
|
| 1714 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e86ee97e08f747eea8db0b784efda5bfb2453e173b613fed5408bef54109a2e7
|
| 3 |
size 5496
|