Model save
Browse files- README.md +24 -11
- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Apr26_01-09-42_fe7d46d3b18e/events.out.tfevents.1714093804.fe7d46d3b18e.21275.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +704 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -43,20 +43,33 @@ The following hyperparameters were used during training:
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.3787
|
| 21 |
+
- Accuracy: 0.9076
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 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 |
+
| 0.7236 | 0.4651 | 100 | 0.6396 | 0.8102 |
|
| 53 |
+
| 0.7243 | 0.9302 | 200 | 0.5124 | 0.8333 |
|
| 54 |
+
| 0.4288 | 1.3953 | 300 | 0.4514 | 0.8630 |
|
| 55 |
+
| 0.5744 | 1.8605 | 400 | 0.6154 | 0.8102 |
|
| 56 |
+
| 0.4077 | 2.3256 | 500 | 0.4612 | 0.8614 |
|
| 57 |
+
| 0.496 | 2.7907 | 600 | 0.4359 | 0.8729 |
|
| 58 |
+
| 0.3446 | 3.2558 | 700 | 0.4276 | 0.8696 |
|
| 59 |
+
| 0.3347 | 3.7209 | 800 | 0.4259 | 0.8795 |
|
| 60 |
+
| 0.3868 | 4.1860 | 900 | 0.4642 | 0.8548 |
|
| 61 |
+
| 0.36 | 4.6512 | 1000 | 0.4242 | 0.8696 |
|
| 62 |
+
| 0.295 | 5.1163 | 1100 | 0.4204 | 0.8812 |
|
| 63 |
+
| 0.2342 | 5.5814 | 1200 | 0.3933 | 0.8911 |
|
| 64 |
+
| 0.1629 | 6.0465 | 1300 | 0.3634 | 0.8977 |
|
| 65 |
+
| 0.2041 | 6.5116 | 1400 | 0.4007 | 0.8911 |
|
| 66 |
+
| 0.1668 | 6.9767 | 1500 | 0.3843 | 0.8927 |
|
| 67 |
+
| 0.0976 | 7.4419 | 1600 | 0.4062 | 0.8927 |
|
| 68 |
+
| 0.1275 | 7.9070 | 1700 | 0.3861 | 0.8894 |
|
| 69 |
+
| 0.1063 | 8.3721 | 1800 | 0.4011 | 0.8911 |
|
| 70 |
+
| 0.1658 | 8.8372 | 1900 | 0.3840 | 0.9043 |
|
| 71 |
+
| 0.1 | 9.3023 | 2000 | 0.3873 | 0.9010 |
|
| 72 |
+
| 0.1045 | 9.7674 | 2100 | 0.3787 | 0.9076 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.0638481718004941e+18,
|
| 4 |
+
"train_loss": 0.4333847167880036,
|
| 5 |
+
"train_runtime": 591.3634,
|
| 6 |
+
"train_samples_per_second": 23.214,
|
| 7 |
+
"train_steps_per_second": 1.454
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343236280
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26e215444bbd66d8ee275069d4f23c942f375f29a375e9b90a1b9b075b93c014
|
| 3 |
size 343236280
|
runs/Apr26_01-09-42_fe7d46d3b18e/events.out.tfevents.1714093804.fe7d46d3b18e.21275.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d56bc83735dab2375b59c81c968ce11821ba7e686a5cf1bc4685725a1917639
|
| 3 |
+
size 57302
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.0638481718004941e+18,
|
| 4 |
+
"train_loss": 0.4333847167880036,
|
| 5 |
+
"train_runtime": 591.3634,
|
| 6 |
+
"train_samples_per_second": 23.214,
|
| 7 |
+
"train_steps_per_second": 1.454
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,704 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.33891761302948,
|
| 3 |
+
"best_model_checkpoint": "finetuned-electrical-images/checkpoint-600",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 860,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.046511627906976744,
|
| 13 |
+
"grad_norm": 2.072422742843628,
|
| 14 |
+
"learning_rate": 0.00019767441860465116,
|
| 15 |
+
"loss": 1.5929,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09302325581395349,
|
| 20 |
+
"grad_norm": 2.2486143112182617,
|
| 21 |
+
"learning_rate": 0.00019534883720930232,
|
| 22 |
+
"loss": 1.2056,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13953488372093023,
|
| 27 |
+
"grad_norm": 2.1311681270599365,
|
| 28 |
+
"learning_rate": 0.0001930232558139535,
|
| 29 |
+
"loss": 1.0947,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18604651162790697,
|
| 34 |
+
"grad_norm": 2.3108925819396973,
|
| 35 |
+
"learning_rate": 0.00019069767441860466,
|
| 36 |
+
"loss": 0.965,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.23255813953488372,
|
| 41 |
+
"grad_norm": 2.6261141300201416,
|
| 42 |
+
"learning_rate": 0.00018837209302325584,
|
| 43 |
+
"loss": 0.7767,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27906976744186046,
|
| 48 |
+
"grad_norm": 4.883328914642334,
|
| 49 |
+
"learning_rate": 0.000186046511627907,
|
| 50 |
+
"loss": 0.8164,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.32558139534883723,
|
| 55 |
+
"grad_norm": 2.2796030044555664,
|
| 56 |
+
"learning_rate": 0.00018372093023255815,
|
| 57 |
+
"loss": 0.8293,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.37209302325581395,
|
| 62 |
+
"grad_norm": 2.7582902908325195,
|
| 63 |
+
"learning_rate": 0.0001813953488372093,
|
| 64 |
+
"loss": 0.7748,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4186046511627907,
|
| 69 |
+
"grad_norm": 3.0205562114715576,
|
| 70 |
+
"learning_rate": 0.00017906976744186048,
|
| 71 |
+
"loss": 0.8204,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.46511627906976744,
|
| 76 |
+
"grad_norm": 1.5362632274627686,
|
| 77 |
+
"learning_rate": 0.00017674418604651164,
|
| 78 |
+
"loss": 0.7151,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.46511627906976744,
|
| 83 |
+
"eval_accuracy": 0.8201320132013201,
|
| 84 |
+
"eval_loss": 0.5808877348899841,
|
| 85 |
+
"eval_runtime": 7.6253,
|
| 86 |
+
"eval_samples_per_second": 79.472,
|
| 87 |
+
"eval_steps_per_second": 9.967,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.5116279069767442,
|
| 92 |
+
"grad_norm": 3.7735097408294678,
|
| 93 |
+
"learning_rate": 0.0001744186046511628,
|
| 94 |
+
"loss": 0.523,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.5581395348837209,
|
| 99 |
+
"grad_norm": 5.240425109863281,
|
| 100 |
+
"learning_rate": 0.00017209302325581395,
|
| 101 |
+
"loss": 0.5818,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.6046511627906976,
|
| 106 |
+
"grad_norm": 3.7434163093566895,
|
| 107 |
+
"learning_rate": 0.0001697674418604651,
|
| 108 |
+
"loss": 0.7063,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.6511627906976745,
|
| 113 |
+
"grad_norm": 1.7690590620040894,
|
| 114 |
+
"learning_rate": 0.00016744186046511629,
|
| 115 |
+
"loss": 0.7594,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.6976744186046512,
|
| 120 |
+
"grad_norm": 3.7053258419036865,
|
| 121 |
+
"learning_rate": 0.00016511627906976747,
|
| 122 |
+
"loss": 0.5997,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.7441860465116279,
|
| 127 |
+
"grad_norm": 4.870126247406006,
|
| 128 |
+
"learning_rate": 0.00016279069767441862,
|
| 129 |
+
"loss": 0.5614,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.7906976744186046,
|
| 134 |
+
"grad_norm": 2.533661365509033,
|
| 135 |
+
"learning_rate": 0.00016046511627906978,
|
| 136 |
+
"loss": 0.4965,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.8372093023255814,
|
| 141 |
+
"grad_norm": 3.910142660140991,
|
| 142 |
+
"learning_rate": 0.00015813953488372093,
|
| 143 |
+
"loss": 0.5525,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.8837209302325582,
|
| 148 |
+
"grad_norm": 3.5800535678863525,
|
| 149 |
+
"learning_rate": 0.0001558139534883721,
|
| 150 |
+
"loss": 0.5458,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.9302325581395349,
|
| 155 |
+
"grad_norm": 1.315317153930664,
|
| 156 |
+
"learning_rate": 0.00015348837209302327,
|
| 157 |
+
"loss": 0.6882,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.9302325581395349,
|
| 162 |
+
"eval_accuracy": 0.8498349834983498,
|
| 163 |
+
"eval_loss": 0.4638592302799225,
|
| 164 |
+
"eval_runtime": 7.9986,
|
| 165 |
+
"eval_samples_per_second": 75.764,
|
| 166 |
+
"eval_steps_per_second": 9.502,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.9767441860465116,
|
| 171 |
+
"grad_norm": 3.7220730781555176,
|
| 172 |
+
"learning_rate": 0.00015116279069767442,
|
| 173 |
+
"loss": 0.5207,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.0232558139534884,
|
| 178 |
+
"grad_norm": 4.103209018707275,
|
| 179 |
+
"learning_rate": 0.00014883720930232558,
|
| 180 |
+
"loss": 0.5282,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.069767441860465,
|
| 185 |
+
"grad_norm": 2.3725953102111816,
|
| 186 |
+
"learning_rate": 0.00014651162790697673,
|
| 187 |
+
"loss": 0.4849,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.1162790697674418,
|
| 192 |
+
"grad_norm": 2.339578151702881,
|
| 193 |
+
"learning_rate": 0.00014418604651162791,
|
| 194 |
+
"loss": 0.3707,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1627906976744187,
|
| 199 |
+
"grad_norm": 2.8100476264953613,
|
| 200 |
+
"learning_rate": 0.0001418604651162791,
|
| 201 |
+
"loss": 0.3821,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.2093023255813953,
|
| 206 |
+
"grad_norm": 2.1530966758728027,
|
| 207 |
+
"learning_rate": 0.00013953488372093025,
|
| 208 |
+
"loss": 0.4797,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.255813953488372,
|
| 213 |
+
"grad_norm": 1.164758324623108,
|
| 214 |
+
"learning_rate": 0.0001372093023255814,
|
| 215 |
+
"loss": 0.4341,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.302325581395349,
|
| 220 |
+
"grad_norm": 1.5009866952896118,
|
| 221 |
+
"learning_rate": 0.00013488372093023256,
|
| 222 |
+
"loss": 0.4527,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.3488372093023255,
|
| 227 |
+
"grad_norm": 2.4176268577575684,
|
| 228 |
+
"learning_rate": 0.00013255813953488372,
|
| 229 |
+
"loss": 0.3878,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3953488372093024,
|
| 234 |
+
"grad_norm": 4.717296123504639,
|
| 235 |
+
"learning_rate": 0.0001302325581395349,
|
| 236 |
+
"loss": 0.3897,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.3953488372093024,
|
| 241 |
+
"eval_accuracy": 0.8465346534653465,
|
| 242 |
+
"eval_loss": 0.47040635347366333,
|
| 243 |
+
"eval_runtime": 8.212,
|
| 244 |
+
"eval_samples_per_second": 73.794,
|
| 245 |
+
"eval_steps_per_second": 9.255,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.441860465116279,
|
| 250 |
+
"grad_norm": 1.026237964630127,
|
| 251 |
+
"learning_rate": 0.00012790697674418605,
|
| 252 |
+
"loss": 0.3683,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.4883720930232558,
|
| 257 |
+
"grad_norm": 2.894584894180298,
|
| 258 |
+
"learning_rate": 0.0001255813953488372,
|
| 259 |
+
"loss": 0.4968,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.5348837209302326,
|
| 264 |
+
"grad_norm": 1.6250619888305664,
|
| 265 |
+
"learning_rate": 0.00012325581395348836,
|
| 266 |
+
"loss": 0.4784,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.5813953488372094,
|
| 271 |
+
"grad_norm": 2.221461296081543,
|
| 272 |
+
"learning_rate": 0.00012093023255813953,
|
| 273 |
+
"loss": 0.5513,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.627906976744186,
|
| 278 |
+
"grad_norm": 6.982600688934326,
|
| 279 |
+
"learning_rate": 0.00011860465116279071,
|
| 280 |
+
"loss": 0.5509,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.6744186046511627,
|
| 285 |
+
"grad_norm": 2.3711423873901367,
|
| 286 |
+
"learning_rate": 0.00011627906976744187,
|
| 287 |
+
"loss": 0.4542,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.7209302325581395,
|
| 292 |
+
"grad_norm": 2.340607166290283,
|
| 293 |
+
"learning_rate": 0.00011395348837209304,
|
| 294 |
+
"loss": 0.3822,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.7674418604651163,
|
| 299 |
+
"grad_norm": 3.709766387939453,
|
| 300 |
+
"learning_rate": 0.00011162790697674419,
|
| 301 |
+
"loss": 0.4252,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.8139534883720931,
|
| 306 |
+
"grad_norm": 3.5805418491363525,
|
| 307 |
+
"learning_rate": 0.00010930232558139534,
|
| 308 |
+
"loss": 0.6467,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.8604651162790697,
|
| 313 |
+
"grad_norm": 2.1463587284088135,
|
| 314 |
+
"learning_rate": 0.00010697674418604651,
|
| 315 |
+
"loss": 0.4909,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.8604651162790697,
|
| 320 |
+
"eval_accuracy": 0.8448844884488449,
|
| 321 |
+
"eval_loss": 0.5023446083068848,
|
| 322 |
+
"eval_runtime": 8.1791,
|
| 323 |
+
"eval_samples_per_second": 74.091,
|
| 324 |
+
"eval_steps_per_second": 9.292,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.9069767441860463,
|
| 329 |
+
"grad_norm": 3.8787500858306885,
|
| 330 |
+
"learning_rate": 0.00010465116279069768,
|
| 331 |
+
"loss": 0.485,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.9534883720930232,
|
| 336 |
+
"grad_norm": 3.9055089950561523,
|
| 337 |
+
"learning_rate": 0.00010232558139534885,
|
| 338 |
+
"loss": 0.4737,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.0,
|
| 343 |
+
"grad_norm": 1.440263032913208,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 0.35,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.046511627906977,
|
| 350 |
+
"grad_norm": 1.907047986984253,
|
| 351 |
+
"learning_rate": 9.767441860465116e-05,
|
| 352 |
+
"loss": 0.3646,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.0930232558139537,
|
| 357 |
+
"grad_norm": 2.902924060821533,
|
| 358 |
+
"learning_rate": 9.534883720930233e-05,
|
| 359 |
+
"loss": 0.3787,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.13953488372093,
|
| 364 |
+
"grad_norm": 2.807384729385376,
|
| 365 |
+
"learning_rate": 9.30232558139535e-05,
|
| 366 |
+
"loss": 0.3122,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.186046511627907,
|
| 371 |
+
"grad_norm": 1.7866243124008179,
|
| 372 |
+
"learning_rate": 9.069767441860465e-05,
|
| 373 |
+
"loss": 0.3379,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.2325581395348837,
|
| 378 |
+
"grad_norm": 6.933365821838379,
|
| 379 |
+
"learning_rate": 8.837209302325582e-05,
|
| 380 |
+
"loss": 0.3066,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.2790697674418605,
|
| 385 |
+
"grad_norm": 5.515610694885254,
|
| 386 |
+
"learning_rate": 8.604651162790697e-05,
|
| 387 |
+
"loss": 0.2632,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.3255813953488373,
|
| 392 |
+
"grad_norm": 4.792200088500977,
|
| 393 |
+
"learning_rate": 8.372093023255814e-05,
|
| 394 |
+
"loss": 0.2836,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.3255813953488373,
|
| 399 |
+
"eval_accuracy": 0.8745874587458746,
|
| 400 |
+
"eval_loss": 0.41001710295677185,
|
| 401 |
+
"eval_runtime": 8.2547,
|
| 402 |
+
"eval_samples_per_second": 73.413,
|
| 403 |
+
"eval_steps_per_second": 9.207,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.3720930232558137,
|
| 408 |
+
"grad_norm": 4.973999977111816,
|
| 409 |
+
"learning_rate": 8.139534883720931e-05,
|
| 410 |
+
"loss": 0.3589,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.4186046511627906,
|
| 415 |
+
"grad_norm": 2.9822804927825928,
|
| 416 |
+
"learning_rate": 7.906976744186047e-05,
|
| 417 |
+
"loss": 0.2937,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.4651162790697674,
|
| 422 |
+
"grad_norm": 3.735166549682617,
|
| 423 |
+
"learning_rate": 7.674418604651163e-05,
|
| 424 |
+
"loss": 0.3345,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.511627906976744,
|
| 429 |
+
"grad_norm": 3.042361259460449,
|
| 430 |
+
"learning_rate": 7.441860465116279e-05,
|
| 431 |
+
"loss": 0.3717,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.558139534883721,
|
| 436 |
+
"grad_norm": 2.4927892684936523,
|
| 437 |
+
"learning_rate": 7.209302325581396e-05,
|
| 438 |
+
"loss": 0.249,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.604651162790698,
|
| 443 |
+
"grad_norm": 1.5524264574050903,
|
| 444 |
+
"learning_rate": 6.976744186046513e-05,
|
| 445 |
+
"loss": 0.3304,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.6511627906976747,
|
| 450 |
+
"grad_norm": 0.39165279269218445,
|
| 451 |
+
"learning_rate": 6.744186046511628e-05,
|
| 452 |
+
"loss": 0.285,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.697674418604651,
|
| 457 |
+
"grad_norm": 1.6114171743392944,
|
| 458 |
+
"learning_rate": 6.511627906976745e-05,
|
| 459 |
+
"loss": 0.3908,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.744186046511628,
|
| 464 |
+
"grad_norm": 2.375959634780884,
|
| 465 |
+
"learning_rate": 6.27906976744186e-05,
|
| 466 |
+
"loss": 0.2845,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.7906976744186047,
|
| 471 |
+
"grad_norm": 3.077956199645996,
|
| 472 |
+
"learning_rate": 6.0465116279069765e-05,
|
| 473 |
+
"loss": 0.2669,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.7906976744186047,
|
| 478 |
+
"eval_accuracy": 0.8993399339933993,
|
| 479 |
+
"eval_loss": 0.33891761302948,
|
| 480 |
+
"eval_runtime": 8.0736,
|
| 481 |
+
"eval_samples_per_second": 75.059,
|
| 482 |
+
"eval_steps_per_second": 9.413,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.8372093023255816,
|
| 487 |
+
"grad_norm": 1.2785547971725464,
|
| 488 |
+
"learning_rate": 5.8139534883720933e-05,
|
| 489 |
+
"loss": 0.2499,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.883720930232558,
|
| 494 |
+
"grad_norm": 2.2260217666625977,
|
| 495 |
+
"learning_rate": 5.5813953488372095e-05,
|
| 496 |
+
"loss": 0.2065,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.9302325581395348,
|
| 501 |
+
"grad_norm": 2.7635715007781982,
|
| 502 |
+
"learning_rate": 5.348837209302326e-05,
|
| 503 |
+
"loss": 0.3334,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.9767441860465116,
|
| 508 |
+
"grad_norm": 3.221409797668457,
|
| 509 |
+
"learning_rate": 5.1162790697674425e-05,
|
| 510 |
+
"loss": 0.2453,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 3.0232558139534884,
|
| 515 |
+
"grad_norm": 0.77796870470047,
|
| 516 |
+
"learning_rate": 4.883720930232558e-05,
|
| 517 |
+
"loss": 0.2191,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.0697674418604652,
|
| 522 |
+
"grad_norm": 1.0451290607452393,
|
| 523 |
+
"learning_rate": 4.651162790697675e-05,
|
| 524 |
+
"loss": 0.2745,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.116279069767442,
|
| 529 |
+
"grad_norm": 4.356563091278076,
|
| 530 |
+
"learning_rate": 4.418604651162791e-05,
|
| 531 |
+
"loss": 0.2399,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.1627906976744184,
|
| 536 |
+
"grad_norm": 2.47353458404541,
|
| 537 |
+
"learning_rate": 4.186046511627907e-05,
|
| 538 |
+
"loss": 0.3016,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.2093023255813953,
|
| 543 |
+
"grad_norm": 1.1897259950637817,
|
| 544 |
+
"learning_rate": 3.953488372093023e-05,
|
| 545 |
+
"loss": 0.1716,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.255813953488372,
|
| 550 |
+
"grad_norm": 2.9624576568603516,
|
| 551 |
+
"learning_rate": 3.7209302325581394e-05,
|
| 552 |
+
"loss": 0.2304,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.255813953488372,
|
| 557 |
+
"eval_accuracy": 0.8927392739273927,
|
| 558 |
+
"eval_loss": 0.36686915159225464,
|
| 559 |
+
"eval_runtime": 8.0401,
|
| 560 |
+
"eval_samples_per_second": 75.372,
|
| 561 |
+
"eval_steps_per_second": 9.453,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.302325581395349,
|
| 566 |
+
"grad_norm": 0.4115903675556183,
|
| 567 |
+
"learning_rate": 3.488372093023256e-05,
|
| 568 |
+
"loss": 0.2835,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.3488372093023258,
|
| 573 |
+
"grad_norm": 3.0008704662323,
|
| 574 |
+
"learning_rate": 3.2558139534883724e-05,
|
| 575 |
+
"loss": 0.1414,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.395348837209302,
|
| 580 |
+
"grad_norm": 3.6043615341186523,
|
| 581 |
+
"learning_rate": 3.0232558139534883e-05,
|
| 582 |
+
"loss": 0.2309,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.441860465116279,
|
| 587 |
+
"grad_norm": 1.3581503629684448,
|
| 588 |
+
"learning_rate": 2.7906976744186048e-05,
|
| 589 |
+
"loss": 0.3342,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.488372093023256,
|
| 594 |
+
"grad_norm": 1.7710747718811035,
|
| 595 |
+
"learning_rate": 2.5581395348837212e-05,
|
| 596 |
+
"loss": 0.2326,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.5348837209302326,
|
| 601 |
+
"grad_norm": 3.192469835281372,
|
| 602 |
+
"learning_rate": 2.3255813953488374e-05,
|
| 603 |
+
"loss": 0.1234,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.5813953488372094,
|
| 608 |
+
"grad_norm": 0.3328302800655365,
|
| 609 |
+
"learning_rate": 2.0930232558139536e-05,
|
| 610 |
+
"loss": 0.228,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.6279069767441863,
|
| 615 |
+
"grad_norm": 2.4526288509368896,
|
| 616 |
+
"learning_rate": 1.8604651162790697e-05,
|
| 617 |
+
"loss": 0.1601,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.6744186046511627,
|
| 622 |
+
"grad_norm": 1.8664888143539429,
|
| 623 |
+
"learning_rate": 1.6279069767441862e-05,
|
| 624 |
+
"loss": 0.2098,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.7209302325581395,
|
| 629 |
+
"grad_norm": 5.262502193450928,
|
| 630 |
+
"learning_rate": 1.3953488372093024e-05,
|
| 631 |
+
"loss": 0.1523,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.7209302325581395,
|
| 636 |
+
"eval_accuracy": 0.8960396039603961,
|
| 637 |
+
"eval_loss": 0.36768776178359985,
|
| 638 |
+
"eval_runtime": 8.208,
|
| 639 |
+
"eval_samples_per_second": 73.83,
|
| 640 |
+
"eval_steps_per_second": 9.259,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.7674418604651163,
|
| 645 |
+
"grad_norm": 6.241558074951172,
|
| 646 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 647 |
+
"loss": 0.1313,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.813953488372093,
|
| 652 |
+
"grad_norm": 2.1938974857330322,
|
| 653 |
+
"learning_rate": 9.302325581395349e-06,
|
| 654 |
+
"loss": 0.1505,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.8604651162790695,
|
| 659 |
+
"grad_norm": 2.1302292346954346,
|
| 660 |
+
"learning_rate": 6.976744186046512e-06,
|
| 661 |
+
"loss": 0.2306,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.9069767441860463,
|
| 666 |
+
"grad_norm": 10.263894081115723,
|
| 667 |
+
"learning_rate": 4.651162790697674e-06,
|
| 668 |
+
"loss": 0.2138,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.953488372093023,
|
| 673 |
+
"grad_norm": 6.005746364593506,
|
| 674 |
+
"learning_rate": 2.325581395348837e-06,
|
| 675 |
+
"loss": 0.1595,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 4.0,
|
| 680 |
+
"grad_norm": 3.945340156555176,
|
| 681 |
+
"learning_rate": 0.0,
|
| 682 |
+
"loss": 0.2154,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 4.0,
|
| 687 |
+
"step": 860,
|
| 688 |
+
"total_flos": 1.0638481718004941e+18,
|
| 689 |
+
"train_loss": 0.4333847167880036,
|
| 690 |
+
"train_runtime": 591.3634,
|
| 691 |
+
"train_samples_per_second": 23.214,
|
| 692 |
+
"train_steps_per_second": 1.454
|
| 693 |
+
}
|
| 694 |
+
],
|
| 695 |
+
"logging_steps": 10,
|
| 696 |
+
"max_steps": 860,
|
| 697 |
+
"num_input_tokens_seen": 0,
|
| 698 |
+
"num_train_epochs": 4,
|
| 699 |
+
"save_steps": 100,
|
| 700 |
+
"total_flos": 1.0638481718004941e+18,
|
| 701 |
+
"train_batch_size": 16,
|
| 702 |
+
"trial_name": null,
|
| 703 |
+
"trial_params": null
|
| 704 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6891f0f5251ee7f7593096070fd05fa5ee6229f2dcfadc5b6253584dd201d3be
|
| 3 |
size 4984
|