Upload 8 files
Browse files- config.json +34 -0
- model.safetensors +3 -0
- optimizer-002.pt +3 -0
- preprocessor_config.json +22 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +762 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-large-patch16-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "benign",
|
| 13 |
+
"1": "malignant",
|
| 14 |
+
"2": "normal"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"benign": 0,
|
| 21 |
+
"malignant": 1,
|
| 22 |
+
"normal": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"model_type": "vit",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.38.2"
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64c4a95261002257a92f9846cc25647c5bb43a07e019270f7a361648c3ce3b3c
|
| 3 |
+
size 1213265372
|
optimizer-002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:823ac7b2a83e6142bbf00c0667d6cf819b1ae0aeb302ada9c6b8430abc3c6591
|
| 3 |
+
size 2426765738
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83b61c28272cbf9d5d9437321b135f15aae0e7d3ae86b73db04bec06ed879451
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f820865d11b90edd2dc3d1d4297827aba983623b9bd59f2cde35bb8f14d7a8b
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9358974358974359,
|
| 3 |
+
"best_model_checkpoint": "output-models/checkpoint-470",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1880,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"step": 47,
|
| 14 |
+
"train_accuracy": 0.7072649572649573,
|
| 15 |
+
"train_loss": 0.6782774329185486,
|
| 16 |
+
"train_runtime": 13.5956,
|
| 17 |
+
"train_samples_per_second": 34.423,
|
| 18 |
+
"train_steps_per_second": 8.606
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.0,
|
| 22 |
+
"eval_accuracy": 0.7243589743589743,
|
| 23 |
+
"eval_loss": 0.6180987358093262,
|
| 24 |
+
"eval_runtime": 35.9375,
|
| 25 |
+
"eval_samples_per_second": 4.341,
|
| 26 |
+
"eval_steps_per_second": 1.085,
|
| 27 |
+
"step": 47
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"step": 94,
|
| 32 |
+
"train_accuracy": 0.75,
|
| 33 |
+
"train_loss": 0.5690865516662598,
|
| 34 |
+
"train_runtime": 13.7448,
|
| 35 |
+
"train_samples_per_second": 34.049,
|
| 36 |
+
"train_steps_per_second": 8.512
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.8012820512820513,
|
| 41 |
+
"eval_loss": 0.5130882263183594,
|
| 42 |
+
"eval_runtime": 4.4157,
|
| 43 |
+
"eval_samples_per_second": 35.328,
|
| 44 |
+
"eval_steps_per_second": 8.832,
|
| 45 |
+
"step": 94
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"step": 141,
|
| 50 |
+
"train_accuracy": 0.7350427350427351,
|
| 51 |
+
"train_loss": 0.6460429430007935,
|
| 52 |
+
"train_runtime": 14.0717,
|
| 53 |
+
"train_samples_per_second": 33.258,
|
| 54 |
+
"train_steps_per_second": 8.315
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.8205128205128205,
|
| 59 |
+
"eval_loss": 0.45179083943367004,
|
| 60 |
+
"eval_runtime": 4.8055,
|
| 61 |
+
"eval_samples_per_second": 32.463,
|
| 62 |
+
"eval_steps_per_second": 8.116,
|
| 63 |
+
"step": 141
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.0,
|
| 67 |
+
"step": 188,
|
| 68 |
+
"train_accuracy": 0.8098290598290598,
|
| 69 |
+
"train_loss": 0.39663246273994446,
|
| 70 |
+
"train_runtime": 13.7878,
|
| 71 |
+
"train_samples_per_second": 33.943,
|
| 72 |
+
"train_steps_per_second": 8.486
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.8846153846153846,
|
| 77 |
+
"eval_loss": 0.2980358898639679,
|
| 78 |
+
"eval_runtime": 4.4674,
|
| 79 |
+
"eval_samples_per_second": 34.919,
|
| 80 |
+
"eval_steps_per_second": 8.73,
|
| 81 |
+
"step": 188
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"step": 235,
|
| 86 |
+
"train_accuracy": 0.8632478632478633,
|
| 87 |
+
"train_loss": 0.3636291027069092,
|
| 88 |
+
"train_runtime": 13.58,
|
| 89 |
+
"train_samples_per_second": 34.462,
|
| 90 |
+
"train_steps_per_second": 8.616
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.0,
|
| 94 |
+
"eval_accuracy": 0.8717948717948718,
|
| 95 |
+
"eval_loss": 0.2997760772705078,
|
| 96 |
+
"eval_runtime": 4.9986,
|
| 97 |
+
"eval_samples_per_second": 31.208,
|
| 98 |
+
"eval_steps_per_second": 7.802,
|
| 99 |
+
"step": 235
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.0,
|
| 103 |
+
"step": 282,
|
| 104 |
+
"train_accuracy": 0.8376068376068376,
|
| 105 |
+
"train_loss": 0.4208720922470093,
|
| 106 |
+
"train_runtime": 13.5735,
|
| 107 |
+
"train_samples_per_second": 34.479,
|
| 108 |
+
"train_steps_per_second": 8.62
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.9102564102564102,
|
| 113 |
+
"eval_loss": 0.33183348178863525,
|
| 114 |
+
"eval_runtime": 4.4091,
|
| 115 |
+
"eval_samples_per_second": 35.381,
|
| 116 |
+
"eval_steps_per_second": 8.845,
|
| 117 |
+
"step": 282
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 7.0,
|
| 121 |
+
"step": 329,
|
| 122 |
+
"train_accuracy": 0.8568376068376068,
|
| 123 |
+
"train_loss": 0.32207924127578735,
|
| 124 |
+
"train_runtime": 13.5635,
|
| 125 |
+
"train_samples_per_second": 34.504,
|
| 126 |
+
"train_steps_per_second": 8.626
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 7.0,
|
| 130 |
+
"eval_accuracy": 0.9166666666666666,
|
| 131 |
+
"eval_loss": 0.24086996912956238,
|
| 132 |
+
"eval_runtime": 4.7402,
|
| 133 |
+
"eval_samples_per_second": 32.91,
|
| 134 |
+
"eval_steps_per_second": 8.228,
|
| 135 |
+
"step": 329
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"step": 376,
|
| 140 |
+
"train_accuracy": 0.8846153846153846,
|
| 141 |
+
"train_loss": 0.3257001042366028,
|
| 142 |
+
"train_runtime": 13.9348,
|
| 143 |
+
"train_samples_per_second": 33.585,
|
| 144 |
+
"train_steps_per_second": 8.396
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.0,
|
| 148 |
+
"eval_accuracy": 0.8717948717948718,
|
| 149 |
+
"eval_loss": 0.3424080014228821,
|
| 150 |
+
"eval_runtime": 4.9539,
|
| 151 |
+
"eval_samples_per_second": 31.49,
|
| 152 |
+
"eval_steps_per_second": 7.873,
|
| 153 |
+
"step": 376
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.0,
|
| 157 |
+
"step": 423,
|
| 158 |
+
"train_accuracy": 0.8717948717948718,
|
| 159 |
+
"train_loss": 0.2687961757183075,
|
| 160 |
+
"train_runtime": 13.6829,
|
| 161 |
+
"train_samples_per_second": 34.203,
|
| 162 |
+
"train_steps_per_second": 8.551
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.0,
|
| 166 |
+
"eval_accuracy": 0.9166666666666666,
|
| 167 |
+
"eval_loss": 0.25928938388824463,
|
| 168 |
+
"eval_runtime": 4.4508,
|
| 169 |
+
"eval_samples_per_second": 35.05,
|
| 170 |
+
"eval_steps_per_second": 8.762,
|
| 171 |
+
"step": 423
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 10.0,
|
| 175 |
+
"step": 470,
|
| 176 |
+
"train_accuracy": 0.9102564102564102,
|
| 177 |
+
"train_loss": 0.2113831341266632,
|
| 178 |
+
"train_runtime": 13.44,
|
| 179 |
+
"train_samples_per_second": 34.821,
|
| 180 |
+
"train_steps_per_second": 8.705
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"eval_accuracy": 0.9358974358974359,
|
| 185 |
+
"eval_loss": 0.25084006786346436,
|
| 186 |
+
"eval_runtime": 4.8092,
|
| 187 |
+
"eval_samples_per_second": 32.438,
|
| 188 |
+
"eval_steps_per_second": 8.109,
|
| 189 |
+
"step": 470
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.64,
|
| 193 |
+
"grad_norm": 7.874776840209961,
|
| 194 |
+
"learning_rate": 1.4680851063829789e-05,
|
| 195 |
+
"loss": 0.4595,
|
| 196 |
+
"step": 500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 11.0,
|
| 200 |
+
"step": 517,
|
| 201 |
+
"train_accuracy": 0.8995726495726496,
|
| 202 |
+
"train_loss": 0.25938984751701355,
|
| 203 |
+
"train_runtime": 13.5841,
|
| 204 |
+
"train_samples_per_second": 34.452,
|
| 205 |
+
"train_steps_per_second": 8.613
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 11.0,
|
| 209 |
+
"eval_accuracy": 0.9294871794871795,
|
| 210 |
+
"eval_loss": 0.32409772276878357,
|
| 211 |
+
"eval_runtime": 4.4182,
|
| 212 |
+
"eval_samples_per_second": 35.308,
|
| 213 |
+
"eval_steps_per_second": 8.827,
|
| 214 |
+
"step": 517
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 12.0,
|
| 218 |
+
"step": 564,
|
| 219 |
+
"train_accuracy": 0.8952991452991453,
|
| 220 |
+
"train_loss": 0.26763853430747986,
|
| 221 |
+
"train_runtime": 13.8203,
|
| 222 |
+
"train_samples_per_second": 33.863,
|
| 223 |
+
"train_steps_per_second": 8.466
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 12.0,
|
| 227 |
+
"eval_accuracy": 0.8910256410256411,
|
| 228 |
+
"eval_loss": 0.3308241069316864,
|
| 229 |
+
"eval_runtime": 4.4447,
|
| 230 |
+
"eval_samples_per_second": 35.098,
|
| 231 |
+
"eval_steps_per_second": 8.774,
|
| 232 |
+
"step": 564
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 13.0,
|
| 236 |
+
"step": 611,
|
| 237 |
+
"train_accuracy": 0.9081196581196581,
|
| 238 |
+
"train_loss": 0.23129615187644958,
|
| 239 |
+
"train_runtime": 13.4973,
|
| 240 |
+
"train_samples_per_second": 34.674,
|
| 241 |
+
"train_steps_per_second": 8.668
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 13.0,
|
| 245 |
+
"eval_accuracy": 0.9294871794871795,
|
| 246 |
+
"eval_loss": 0.255931556224823,
|
| 247 |
+
"eval_runtime": 4.6436,
|
| 248 |
+
"eval_samples_per_second": 33.595,
|
| 249 |
+
"eval_steps_per_second": 8.399,
|
| 250 |
+
"step": 611
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 14.0,
|
| 254 |
+
"step": 658,
|
| 255 |
+
"train_accuracy": 0.8846153846153846,
|
| 256 |
+
"train_loss": 0.31185245513916016,
|
| 257 |
+
"train_runtime": 13.5189,
|
| 258 |
+
"train_samples_per_second": 34.618,
|
| 259 |
+
"train_steps_per_second": 8.655
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 14.0,
|
| 263 |
+
"eval_accuracy": 0.9166666666666666,
|
| 264 |
+
"eval_loss": 0.3017214834690094,
|
| 265 |
+
"eval_runtime": 4.6078,
|
| 266 |
+
"eval_samples_per_second": 33.856,
|
| 267 |
+
"eval_steps_per_second": 8.464,
|
| 268 |
+
"step": 658
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 15.0,
|
| 272 |
+
"step": 705,
|
| 273 |
+
"train_accuracy": 0.9166666666666666,
|
| 274 |
+
"train_loss": 0.3007480502128601,
|
| 275 |
+
"train_runtime": 13.4373,
|
| 276 |
+
"train_samples_per_second": 34.829,
|
| 277 |
+
"train_steps_per_second": 8.707
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 15.0,
|
| 281 |
+
"eval_accuracy": 0.9038461538461539,
|
| 282 |
+
"eval_loss": 0.4220944046974182,
|
| 283 |
+
"eval_runtime": 4.9304,
|
| 284 |
+
"eval_samples_per_second": 31.64,
|
| 285 |
+
"eval_steps_per_second": 7.91,
|
| 286 |
+
"step": 705
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 16.0,
|
| 290 |
+
"step": 752,
|
| 291 |
+
"train_accuracy": 0.9188034188034188,
|
| 292 |
+
"train_loss": 0.20939397811889648,
|
| 293 |
+
"train_runtime": 13.6683,
|
| 294 |
+
"train_samples_per_second": 34.24,
|
| 295 |
+
"train_steps_per_second": 8.56
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 16.0,
|
| 299 |
+
"eval_accuracy": 0.9166666666666666,
|
| 300 |
+
"eval_loss": 0.36174264550209045,
|
| 301 |
+
"eval_runtime": 4.4608,
|
| 302 |
+
"eval_samples_per_second": 34.971,
|
| 303 |
+
"eval_steps_per_second": 8.743,
|
| 304 |
+
"step": 752
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 17.0,
|
| 308 |
+
"step": 799,
|
| 309 |
+
"train_accuracy": 0.9209401709401709,
|
| 310 |
+
"train_loss": 0.18879051506519318,
|
| 311 |
+
"train_runtime": 13.7929,
|
| 312 |
+
"train_samples_per_second": 33.931,
|
| 313 |
+
"train_steps_per_second": 8.483
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 17.0,
|
| 317 |
+
"eval_accuracy": 0.9102564102564102,
|
| 318 |
+
"eval_loss": 0.35188791155815125,
|
| 319 |
+
"eval_runtime": 4.7732,
|
| 320 |
+
"eval_samples_per_second": 32.683,
|
| 321 |
+
"eval_steps_per_second": 8.171,
|
| 322 |
+
"step": 799
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 18.0,
|
| 326 |
+
"step": 846,
|
| 327 |
+
"train_accuracy": 0.8952991452991453,
|
| 328 |
+
"train_loss": 0.25016605854034424,
|
| 329 |
+
"train_runtime": 13.3521,
|
| 330 |
+
"train_samples_per_second": 35.051,
|
| 331 |
+
"train_steps_per_second": 8.763
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 18.0,
|
| 335 |
+
"eval_accuracy": 0.9102564102564102,
|
| 336 |
+
"eval_loss": 0.3965354859828949,
|
| 337 |
+
"eval_runtime": 4.3963,
|
| 338 |
+
"eval_samples_per_second": 35.485,
|
| 339 |
+
"eval_steps_per_second": 8.871,
|
| 340 |
+
"step": 846
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 19.0,
|
| 344 |
+
"step": 893,
|
| 345 |
+
"train_accuracy": 0.9209401709401709,
|
| 346 |
+
"train_loss": 0.1891285479068756,
|
| 347 |
+
"train_runtime": 13.4884,
|
| 348 |
+
"train_samples_per_second": 34.696,
|
| 349 |
+
"train_steps_per_second": 8.674
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 19.0,
|
| 353 |
+
"eval_accuracy": 0.9038461538461539,
|
| 354 |
+
"eval_loss": 0.31604066491127014,
|
| 355 |
+
"eval_runtime": 5.1415,
|
| 356 |
+
"eval_samples_per_second": 30.341,
|
| 357 |
+
"eval_steps_per_second": 7.585,
|
| 358 |
+
"step": 893
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 20.0,
|
| 362 |
+
"step": 940,
|
| 363 |
+
"train_accuracy": 0.9401709401709402,
|
| 364 |
+
"train_loss": 0.1873449832201004,
|
| 365 |
+
"train_runtime": 13.9057,
|
| 366 |
+
"train_samples_per_second": 33.655,
|
| 367 |
+
"train_steps_per_second": 8.414
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 20.0,
|
| 371 |
+
"eval_accuracy": 0.9294871794871795,
|
| 372 |
+
"eval_loss": 0.3332672119140625,
|
| 373 |
+
"eval_runtime": 4.9421,
|
| 374 |
+
"eval_samples_per_second": 31.565,
|
| 375 |
+
"eval_steps_per_second": 7.891,
|
| 376 |
+
"step": 940
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 21.0,
|
| 380 |
+
"step": 987,
|
| 381 |
+
"train_accuracy": 0.9230769230769231,
|
| 382 |
+
"train_loss": 0.18881197273731232,
|
| 383 |
+
"train_runtime": 13.5338,
|
| 384 |
+
"train_samples_per_second": 34.58,
|
| 385 |
+
"train_steps_per_second": 8.645
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 21.0,
|
| 389 |
+
"eval_accuracy": 0.8910256410256411,
|
| 390 |
+
"eval_loss": 0.3720751404762268,
|
| 391 |
+
"eval_runtime": 4.8223,
|
| 392 |
+
"eval_samples_per_second": 32.35,
|
| 393 |
+
"eval_steps_per_second": 8.088,
|
| 394 |
+
"step": 987
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 21.28,
|
| 398 |
+
"grad_norm": 5.682499408721924,
|
| 399 |
+
"learning_rate": 9.361702127659576e-06,
|
| 400 |
+
"loss": 0.2485,
|
| 401 |
+
"step": 1000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 22.0,
|
| 405 |
+
"step": 1034,
|
| 406 |
+
"train_accuracy": 0.9444444444444444,
|
| 407 |
+
"train_loss": 0.1338244080543518,
|
| 408 |
+
"train_runtime": 13.6664,
|
| 409 |
+
"train_samples_per_second": 34.245,
|
| 410 |
+
"train_steps_per_second": 8.561
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 22.0,
|
| 414 |
+
"eval_accuracy": 0.9166666666666666,
|
| 415 |
+
"eval_loss": 0.3777410686016083,
|
| 416 |
+
"eval_runtime": 4.3337,
|
| 417 |
+
"eval_samples_per_second": 35.997,
|
| 418 |
+
"eval_steps_per_second": 8.999,
|
| 419 |
+
"step": 1034
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 23.0,
|
| 423 |
+
"step": 1081,
|
| 424 |
+
"train_accuracy": 0.9252136752136753,
|
| 425 |
+
"train_loss": 0.18711484968662262,
|
| 426 |
+
"train_runtime": 13.702,
|
| 427 |
+
"train_samples_per_second": 34.155,
|
| 428 |
+
"train_steps_per_second": 8.539
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 23.0,
|
| 432 |
+
"eval_accuracy": 0.9038461538461539,
|
| 433 |
+
"eval_loss": 0.3984796702861786,
|
| 434 |
+
"eval_runtime": 4.5267,
|
| 435 |
+
"eval_samples_per_second": 34.462,
|
| 436 |
+
"eval_steps_per_second": 8.616,
|
| 437 |
+
"step": 1081
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 24.0,
|
| 441 |
+
"step": 1128,
|
| 442 |
+
"train_accuracy": 0.9444444444444444,
|
| 443 |
+
"train_loss": 0.161672905087471,
|
| 444 |
+
"train_runtime": 13.9523,
|
| 445 |
+
"train_samples_per_second": 33.543,
|
| 446 |
+
"train_steps_per_second": 8.386
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 24.0,
|
| 450 |
+
"eval_accuracy": 0.9230769230769231,
|
| 451 |
+
"eval_loss": 0.38641923666000366,
|
| 452 |
+
"eval_runtime": 5.1128,
|
| 453 |
+
"eval_samples_per_second": 30.511,
|
| 454 |
+
"eval_steps_per_second": 7.628,
|
| 455 |
+
"step": 1128
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 25.0,
|
| 459 |
+
"step": 1175,
|
| 460 |
+
"train_accuracy": 0.9444444444444444,
|
| 461 |
+
"train_loss": 0.17891307175159454,
|
| 462 |
+
"train_runtime": 13.7483,
|
| 463 |
+
"train_samples_per_second": 34.041,
|
| 464 |
+
"train_steps_per_second": 8.51
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 25.0,
|
| 468 |
+
"eval_accuracy": 0.9230769230769231,
|
| 469 |
+
"eval_loss": 0.42098188400268555,
|
| 470 |
+
"eval_runtime": 5.0358,
|
| 471 |
+
"eval_samples_per_second": 30.978,
|
| 472 |
+
"eval_steps_per_second": 7.745,
|
| 473 |
+
"step": 1175
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 26.0,
|
| 477 |
+
"step": 1222,
|
| 478 |
+
"train_accuracy": 0.9572649572649573,
|
| 479 |
+
"train_loss": 0.10899731516838074,
|
| 480 |
+
"train_runtime": 14.0913,
|
| 481 |
+
"train_samples_per_second": 33.212,
|
| 482 |
+
"train_steps_per_second": 8.303
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 26.0,
|
| 486 |
+
"eval_accuracy": 0.9038461538461539,
|
| 487 |
+
"eval_loss": 0.4160342216491699,
|
| 488 |
+
"eval_runtime": 4.7918,
|
| 489 |
+
"eval_samples_per_second": 32.555,
|
| 490 |
+
"eval_steps_per_second": 8.139,
|
| 491 |
+
"step": 1222
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 27.0,
|
| 495 |
+
"step": 1269,
|
| 496 |
+
"train_accuracy": 0.938034188034188,
|
| 497 |
+
"train_loss": 0.16018715500831604,
|
| 498 |
+
"train_runtime": 13.888,
|
| 499 |
+
"train_samples_per_second": 33.698,
|
| 500 |
+
"train_steps_per_second": 8.425
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 27.0,
|
| 504 |
+
"eval_accuracy": 0.9102564102564102,
|
| 505 |
+
"eval_loss": 0.39854034781455994,
|
| 506 |
+
"eval_runtime": 4.8553,
|
| 507 |
+
"eval_samples_per_second": 32.13,
|
| 508 |
+
"eval_steps_per_second": 8.032,
|
| 509 |
+
"step": 1269
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 28.0,
|
| 513 |
+
"step": 1316,
|
| 514 |
+
"train_accuracy": 0.9444444444444444,
|
| 515 |
+
"train_loss": 0.14988763630390167,
|
| 516 |
+
"train_runtime": 13.7687,
|
| 517 |
+
"train_samples_per_second": 33.99,
|
| 518 |
+
"train_steps_per_second": 8.498
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 28.0,
|
| 522 |
+
"eval_accuracy": 0.9102564102564102,
|
| 523 |
+
"eval_loss": 0.40767335891723633,
|
| 524 |
+
"eval_runtime": 4.434,
|
| 525 |
+
"eval_samples_per_second": 35.182,
|
| 526 |
+
"eval_steps_per_second": 8.796,
|
| 527 |
+
"step": 1316
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 29.0,
|
| 531 |
+
"step": 1363,
|
| 532 |
+
"train_accuracy": 0.9316239316239316,
|
| 533 |
+
"train_loss": 0.17876969277858734,
|
| 534 |
+
"train_runtime": 13.3686,
|
| 535 |
+
"train_samples_per_second": 35.008,
|
| 536 |
+
"train_steps_per_second": 8.752
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 29.0,
|
| 540 |
+
"eval_accuracy": 0.8782051282051282,
|
| 541 |
+
"eval_loss": 0.6035234928131104,
|
| 542 |
+
"eval_runtime": 4.8916,
|
| 543 |
+
"eval_samples_per_second": 31.891,
|
| 544 |
+
"eval_steps_per_second": 7.973,
|
| 545 |
+
"step": 1363
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 30.0,
|
| 549 |
+
"step": 1410,
|
| 550 |
+
"train_accuracy": 0.9572649572649573,
|
| 551 |
+
"train_loss": 0.12170404940843582,
|
| 552 |
+
"train_runtime": 13.3084,
|
| 553 |
+
"train_samples_per_second": 35.166,
|
| 554 |
+
"train_steps_per_second": 8.791
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 30.0,
|
| 558 |
+
"eval_accuracy": 0.9230769230769231,
|
| 559 |
+
"eval_loss": 0.3604837954044342,
|
| 560 |
+
"eval_runtime": 4.5664,
|
| 561 |
+
"eval_samples_per_second": 34.163,
|
| 562 |
+
"eval_steps_per_second": 8.541,
|
| 563 |
+
"step": 1410
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 31.0,
|
| 567 |
+
"step": 1457,
|
| 568 |
+
"train_accuracy": 0.9444444444444444,
|
| 569 |
+
"train_loss": 0.17193935811519623,
|
| 570 |
+
"train_runtime": 13.3567,
|
| 571 |
+
"train_samples_per_second": 35.039,
|
| 572 |
+
"train_steps_per_second": 8.76
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 31.0,
|
| 576 |
+
"eval_accuracy": 0.9038461538461539,
|
| 577 |
+
"eval_loss": 0.42400404810905457,
|
| 578 |
+
"eval_runtime": 4.3974,
|
| 579 |
+
"eval_samples_per_second": 35.475,
|
| 580 |
+
"eval_steps_per_second": 8.869,
|
| 581 |
+
"step": 1457
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 31.91,
|
| 585 |
+
"grad_norm": 0.40821418166160583,
|
| 586 |
+
"learning_rate": 4.042553191489362e-06,
|
| 587 |
+
"loss": 0.1715,
|
| 588 |
+
"step": 1500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 32.0,
|
| 592 |
+
"step": 1504,
|
| 593 |
+
"train_accuracy": 0.9551282051282052,
|
| 594 |
+
"train_loss": 0.15071353316307068,
|
| 595 |
+
"train_runtime": 13.338,
|
| 596 |
+
"train_samples_per_second": 35.088,
|
| 597 |
+
"train_steps_per_second": 8.772
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 32.0,
|
| 601 |
+
"eval_accuracy": 0.9166666666666666,
|
| 602 |
+
"eval_loss": 0.3800322711467743,
|
| 603 |
+
"eval_runtime": 4.4234,
|
| 604 |
+
"eval_samples_per_second": 35.267,
|
| 605 |
+
"eval_steps_per_second": 8.817,
|
| 606 |
+
"step": 1504
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 33.0,
|
| 610 |
+
"step": 1551,
|
| 611 |
+
"train_accuracy": 0.9423076923076923,
|
| 612 |
+
"train_loss": 0.15298214554786682,
|
| 613 |
+
"train_runtime": 13.6206,
|
| 614 |
+
"train_samples_per_second": 34.36,
|
| 615 |
+
"train_steps_per_second": 8.59
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 33.0,
|
| 619 |
+
"eval_accuracy": 0.9038461538461539,
|
| 620 |
+
"eval_loss": 0.42538413405418396,
|
| 621 |
+
"eval_runtime": 4.5076,
|
| 622 |
+
"eval_samples_per_second": 34.608,
|
| 623 |
+
"eval_steps_per_second": 8.652,
|
| 624 |
+
"step": 1551
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 34.0,
|
| 628 |
+
"step": 1598,
|
| 629 |
+
"train_accuracy": 0.9615384615384616,
|
| 630 |
+
"train_loss": 0.09072276204824448,
|
| 631 |
+
"train_runtime": 13.7151,
|
| 632 |
+
"train_samples_per_second": 34.123,
|
| 633 |
+
"train_steps_per_second": 8.531
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 34.0,
|
| 637 |
+
"eval_accuracy": 0.9230769230769231,
|
| 638 |
+
"eval_loss": 0.41397902369499207,
|
| 639 |
+
"eval_runtime": 4.448,
|
| 640 |
+
"eval_samples_per_second": 35.072,
|
| 641 |
+
"eval_steps_per_second": 8.768,
|
| 642 |
+
"step": 1598
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 35.0,
|
| 646 |
+
"step": 1645,
|
| 647 |
+
"train_accuracy": 0.9594017094017094,
|
| 648 |
+
"train_loss": 0.15199129283428192,
|
| 649 |
+
"train_runtime": 13.6214,
|
| 650 |
+
"train_samples_per_second": 34.358,
|
| 651 |
+
"train_steps_per_second": 8.589
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 35.0,
|
| 655 |
+
"eval_accuracy": 0.9230769230769231,
|
| 656 |
+
"eval_loss": 0.39104607701301575,
|
| 657 |
+
"eval_runtime": 4.4304,
|
| 658 |
+
"eval_samples_per_second": 35.211,
|
| 659 |
+
"eval_steps_per_second": 8.803,
|
| 660 |
+
"step": 1645
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 36.0,
|
| 664 |
+
"step": 1692,
|
| 665 |
+
"train_accuracy": 0.9594017094017094,
|
| 666 |
+
"train_loss": 0.134719118475914,
|
| 667 |
+
"train_runtime": 13.9053,
|
| 668 |
+
"train_samples_per_second": 33.656,
|
| 669 |
+
"train_steps_per_second": 8.414
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 36.0,
|
| 673 |
+
"eval_accuracy": 0.9102564102564102,
|
| 674 |
+
"eval_loss": 0.4161369204521179,
|
| 675 |
+
"eval_runtime": 4.6871,
|
| 676 |
+
"eval_samples_per_second": 33.283,
|
| 677 |
+
"eval_steps_per_second": 8.321,
|
| 678 |
+
"step": 1692
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 37.0,
|
| 682 |
+
"step": 1739,
|
| 683 |
+
"train_accuracy": 0.9529914529914529,
|
| 684 |
+
"train_loss": 0.16535791754722595,
|
| 685 |
+
"train_runtime": 14.0143,
|
| 686 |
+
"train_samples_per_second": 33.394,
|
| 687 |
+
"train_steps_per_second": 8.349
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 37.0,
|
| 691 |
+
"eval_accuracy": 0.9102564102564102,
|
| 692 |
+
"eval_loss": 0.43847039341926575,
|
| 693 |
+
"eval_runtime": 4.8404,
|
| 694 |
+
"eval_samples_per_second": 32.229,
|
| 695 |
+
"eval_steps_per_second": 8.057,
|
| 696 |
+
"step": 1739
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 38.0,
|
| 700 |
+
"step": 1786,
|
| 701 |
+
"train_accuracy": 0.9487179487179487,
|
| 702 |
+
"train_loss": 0.11996147781610489,
|
| 703 |
+
"train_runtime": 14.1086,
|
| 704 |
+
"train_samples_per_second": 33.171,
|
| 705 |
+
"train_steps_per_second": 8.293
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 38.0,
|
| 709 |
+
"eval_accuracy": 0.9166666666666666,
|
| 710 |
+
"eval_loss": 0.41302695870399475,
|
| 711 |
+
"eval_runtime": 4.7702,
|
| 712 |
+
"eval_samples_per_second": 32.703,
|
| 713 |
+
"eval_steps_per_second": 8.176,
|
| 714 |
+
"step": 1786
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 39.0,
|
| 718 |
+
"step": 1833,
|
| 719 |
+
"train_accuracy": 0.9529914529914529,
|
| 720 |
+
"train_loss": 0.17013560235500336,
|
| 721 |
+
"train_runtime": 13.8197,
|
| 722 |
+
"train_samples_per_second": 33.865,
|
| 723 |
+
"train_steps_per_second": 8.466
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 39.0,
|
| 727 |
+
"eval_accuracy": 0.9166666666666666,
|
| 728 |
+
"eval_loss": 0.4181523323059082,
|
| 729 |
+
"eval_runtime": 5.0402,
|
| 730 |
+
"eval_samples_per_second": 30.951,
|
| 731 |
+
"eval_steps_per_second": 7.738,
|
| 732 |
+
"step": 1833
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 40.0,
|
| 736 |
+
"step": 1880,
|
| 737 |
+
"train_accuracy": 0.9551282051282052,
|
| 738 |
+
"train_loss": 0.11466003954410553,
|
| 739 |
+
"train_runtime": 13.6881,
|
| 740 |
+
"train_samples_per_second": 34.19,
|
| 741 |
+
"train_steps_per_second": 8.548
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 40.0,
|
| 745 |
+
"eval_accuracy": 0.9166666666666666,
|
| 746 |
+
"eval_loss": 0.4133930802345276,
|
| 747 |
+
"eval_runtime": 4.7653,
|
| 748 |
+
"eval_samples_per_second": 32.736,
|
| 749 |
+
"eval_steps_per_second": 8.184,
|
| 750 |
+
"step": 1880
|
| 751 |
+
}
|
| 752 |
+
],
|
| 753 |
+
"logging_steps": 500,
|
| 754 |
+
"max_steps": 1880,
|
| 755 |
+
"num_input_tokens_seen": 0,
|
| 756 |
+
"num_train_epochs": 40,
|
| 757 |
+
"save_steps": 500,
|
| 758 |
+
"total_flos": 5.128065177052447e+18,
|
| 759 |
+
"train_batch_size": 10,
|
| 760 |
+
"trial_name": null,
|
| 761 |
+
"trial_params": null
|
| 762 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52687b65f9d6d4c07e09fec56b9cef39541528f990e60ca9175a8537158d8089
|
| 3 |
+
size 4856
|