Commit
•
61d963c
1
Parent(s):
e1bfff8
Upload 9 files
Browse files- config.json +60 -0
- optimizer.pt +3 -0
- preprocessor_config.json +29 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1108 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/beit-large-patch16-224-pt22k-ft22k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BeitForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"auxiliary_channels": 256,
|
| 8 |
+
"auxiliary_concat_input": false,
|
| 9 |
+
"auxiliary_loss_weight": 0.4,
|
| 10 |
+
"auxiliary_num_convs": 1,
|
| 11 |
+
"drop_path_rate": 0.1,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.0,
|
| 14 |
+
"hidden_size": 1024,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "adenocarcinoma_left.lower.lobe_T2_N0_M0_Ib",
|
| 17 |
+
"1": "large.cell.carcinoma_left.hilum_T2_N2_M0_IIIa",
|
| 18 |
+
"2": "normal",
|
| 19 |
+
"3": "squamous.cell.carcinoma_left.hilum_T1_N2_M0_IIIa"
|
| 20 |
+
},
|
| 21 |
+
"image_size": 224,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 4096,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"adenocarcinoma_left.lower.lobe_T2_N0_M0_Ib": "0",
|
| 26 |
+
"large.cell.carcinoma_left.hilum_T2_N2_M0_IIIa": "1",
|
| 27 |
+
"normal": "2",
|
| 28 |
+
"squamous.cell.carcinoma_left.hilum_T1_N2_M0_IIIa": "3"
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"layer_scale_init_value": 0.1,
|
| 32 |
+
"model_type": "beit",
|
| 33 |
+
"num_attention_heads": 16,
|
| 34 |
+
"num_channels": 3,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"out_indices": [
|
| 37 |
+
3,
|
| 38 |
+
5,
|
| 39 |
+
7,
|
| 40 |
+
11
|
| 41 |
+
],
|
| 42 |
+
"patch_size": 16,
|
| 43 |
+
"pool_scales": [
|
| 44 |
+
1,
|
| 45 |
+
2,
|
| 46 |
+
3,
|
| 47 |
+
6
|
| 48 |
+
],
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"semantic_loss_ignore_index": 255,
|
| 51 |
+
"torch_dtype": "float32",
|
| 52 |
+
"transformers_version": "4.26.1",
|
| 53 |
+
"use_absolute_position_embeddings": false,
|
| 54 |
+
"use_auxiliary_head": true,
|
| 55 |
+
"use_mask_token": false,
|
| 56 |
+
"use_mean_pooling": true,
|
| 57 |
+
"use_relative_position_bias": true,
|
| 58 |
+
"use_shared_relative_position_bias": false,
|
| 59 |
+
"vocab_size": 8192
|
| 60 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:927f4261a030993944046fbad2c5b771a58a6aab2bd36b291b57958c212b92de
|
| 3 |
+
size 2427535237
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": false,
|
| 7 |
+
"do_normalize": true,
|
| 8 |
+
"do_reduce_labels": false,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"feature_extractor_type": "BeitFeatureExtractor",
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "BeitFeatureExtractor",
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 224,
|
| 27 |
+
"width": 224
|
| 28 |
+
}
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3452a633ab01b1e80f621aa7caef3098cf1520129d3ef739d75670036271bfa
|
| 3 |
+
size 1221249673
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea5dcde6ebbfb5345dd754106a6c61dd1f48e15865fd168adf2072fc6fdb7c1a
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09569add4e9b671967067ab1a4d0204af23543e7aaaaaffacdf9b35cebbfb32c
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24970c5cfd2621fc40030046106702e7e8549dfe171942edd6d026597559f42f
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9508196721311475,
|
| 3 |
+
"best_model_checkpoint": "./vit-LungCancer1/checkpoint-1644",
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"global_step": 1644,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 5.839416058394161e-06,
|
| 13 |
+
"loss": 1.5263,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.15,
|
| 18 |
+
"learning_rate": 1.3138686131386862e-05,
|
| 19 |
+
"loss": 1.2535,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.22,
|
| 24 |
+
"learning_rate": 1.9708029197080295e-05,
|
| 25 |
+
"loss": 1.0549,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.29,
|
| 30 |
+
"learning_rate": 2.7007299270072995e-05,
|
| 31 |
+
"loss": 1.0019,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.36,
|
| 36 |
+
"learning_rate": 3.43065693430657e-05,
|
| 37 |
+
"loss": 0.834,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.44,
|
| 42 |
+
"learning_rate": 4.16058394160584e-05,
|
| 43 |
+
"loss": 0.996,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.51,
|
| 48 |
+
"learning_rate": 4.89051094890511e-05,
|
| 49 |
+
"loss": 0.8396,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.58,
|
| 54 |
+
"learning_rate": 5.6204379562043795e-05,
|
| 55 |
+
"loss": 0.9554,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.66,
|
| 60 |
+
"learning_rate": 6.35036496350365e-05,
|
| 61 |
+
"loss": 0.8082,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.73,
|
| 66 |
+
"learning_rate": 7.080291970802921e-05,
|
| 67 |
+
"loss": 0.9226,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.8,
|
| 72 |
+
"learning_rate": 7.81021897810219e-05,
|
| 73 |
+
"loss": 0.7346,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.88,
|
| 78 |
+
"learning_rate": 8.54014598540146e-05,
|
| 79 |
+
"loss": 1.1845,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.95,
|
| 84 |
+
"learning_rate": 9.27007299270073e-05,
|
| 85 |
+
"loss": 0.8577,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_accuracy": 0.7131147540983607,
|
| 91 |
+
"eval_loss": 0.6326848268508911,
|
| 92 |
+
"eval_runtime": 38.5798,
|
| 93 |
+
"eval_samples_per_second": 3.162,
|
| 94 |
+
"eval_steps_per_second": 0.415,
|
| 95 |
+
"step": 137
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.02,
|
| 99 |
+
"learning_rate": 0.0001,
|
| 100 |
+
"loss": 0.7385,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.09,
|
| 105 |
+
"learning_rate": 0.0001072992700729927,
|
| 106 |
+
"loss": 0.6147,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.17,
|
| 111 |
+
"learning_rate": 0.00011459854014598541,
|
| 112 |
+
"loss": 0.7883,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.24,
|
| 117 |
+
"learning_rate": 0.0001218978102189781,
|
| 118 |
+
"loss": 0.5992,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.31,
|
| 123 |
+
"learning_rate": 0.00012919708029197083,
|
| 124 |
+
"loss": 0.6838,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.39,
|
| 129 |
+
"learning_rate": 0.0001364963503649635,
|
| 130 |
+
"loss": 0.602,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.46,
|
| 135 |
+
"learning_rate": 0.00014306569343065694,
|
| 136 |
+
"loss": 0.7759,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.53,
|
| 141 |
+
"learning_rate": 0.00015036496350364964,
|
| 142 |
+
"loss": 0.8934,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.61,
|
| 147 |
+
"learning_rate": 0.00015766423357664236,
|
| 148 |
+
"loss": 0.7176,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.68,
|
| 153 |
+
"learning_rate": 0.00016496350364963503,
|
| 154 |
+
"loss": 0.5465,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.75,
|
| 159 |
+
"learning_rate": 0.00017226277372262773,
|
| 160 |
+
"loss": 0.456,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.82,
|
| 165 |
+
"learning_rate": 0.00017956204379562045,
|
| 166 |
+
"loss": 1.0494,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.9,
|
| 171 |
+
"learning_rate": 0.0001861313868613139,
|
| 172 |
+
"loss": 0.6576,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.97,
|
| 177 |
+
"learning_rate": 0.00019343065693430656,
|
| 178 |
+
"loss": 0.8688,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.0,
|
| 183 |
+
"eval_accuracy": 0.7377049180327869,
|
| 184 |
+
"eval_loss": 0.6352217197418213,
|
| 185 |
+
"eval_runtime": 2.5417,
|
| 186 |
+
"eval_samples_per_second": 48.0,
|
| 187 |
+
"eval_steps_per_second": 6.295,
|
| 188 |
+
"step": 274
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.04,
|
| 192 |
+
"learning_rate": 0.00019991889699918898,
|
| 193 |
+
"loss": 0.7188,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.12,
|
| 198 |
+
"learning_rate": 0.0001991078669910787,
|
| 199 |
+
"loss": 0.6241,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.19,
|
| 204 |
+
"learning_rate": 0.00019829683698296838,
|
| 205 |
+
"loss": 0.7577,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.26,
|
| 210 |
+
"learning_rate": 0.00019748580697485807,
|
| 211 |
+
"loss": 0.6734,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.34,
|
| 216 |
+
"learning_rate": 0.00019667477696674778,
|
| 217 |
+
"loss": 0.7604,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.41,
|
| 222 |
+
"learning_rate": 0.00019586374695863747,
|
| 223 |
+
"loss": 0.8586,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.48,
|
| 228 |
+
"learning_rate": 0.0001950527169505272,
|
| 229 |
+
"loss": 0.6902,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.55,
|
| 234 |
+
"learning_rate": 0.0001942416869424169,
|
| 235 |
+
"loss": 0.6251,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.63,
|
| 240 |
+
"learning_rate": 0.00019343065693430656,
|
| 241 |
+
"loss": 0.6236,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.7,
|
| 246 |
+
"learning_rate": 0.00019261962692619628,
|
| 247 |
+
"loss": 0.9306,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.77,
|
| 252 |
+
"learning_rate": 0.00019180859691808597,
|
| 253 |
+
"loss": 0.8566,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.85,
|
| 258 |
+
"learning_rate": 0.00019099756690997568,
|
| 259 |
+
"loss": 0.5177,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.92,
|
| 264 |
+
"learning_rate": 0.0001901865369018654,
|
| 265 |
+
"loss": 0.5699,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.99,
|
| 270 |
+
"learning_rate": 0.00018937550689375506,
|
| 271 |
+
"loss": 0.6084,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.0,
|
| 276 |
+
"eval_accuracy": 0.680327868852459,
|
| 277 |
+
"eval_loss": 1.126508355140686,
|
| 278 |
+
"eval_runtime": 2.4124,
|
| 279 |
+
"eval_samples_per_second": 50.573,
|
| 280 |
+
"eval_steps_per_second": 6.632,
|
| 281 |
+
"step": 411
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.07,
|
| 285 |
+
"learning_rate": 0.00018856447688564478,
|
| 286 |
+
"loss": 0.8547,
|
| 287 |
+
"step": 420
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.14,
|
| 291 |
+
"learning_rate": 0.00018775344687753446,
|
| 292 |
+
"loss": 0.9728,
|
| 293 |
+
"step": 430
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.21,
|
| 297 |
+
"learning_rate": 0.00018694241686942418,
|
| 298 |
+
"loss": 0.4814,
|
| 299 |
+
"step": 440
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.28,
|
| 303 |
+
"learning_rate": 0.0001861313868613139,
|
| 304 |
+
"loss": 0.6865,
|
| 305 |
+
"step": 450
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.36,
|
| 309 |
+
"learning_rate": 0.00018532035685320356,
|
| 310 |
+
"loss": 0.2393,
|
| 311 |
+
"step": 460
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.43,
|
| 315 |
+
"learning_rate": 0.00018450932684509327,
|
| 316 |
+
"loss": 0.6487,
|
| 317 |
+
"step": 470
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.5,
|
| 321 |
+
"learning_rate": 0.000183698296836983,
|
| 322 |
+
"loss": 0.9157,
|
| 323 |
+
"step": 480
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.58,
|
| 327 |
+
"learning_rate": 0.00018288726682887268,
|
| 328 |
+
"loss": 0.8132,
|
| 329 |
+
"step": 490
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.65,
|
| 333 |
+
"learning_rate": 0.0001820762368207624,
|
| 334 |
+
"loss": 0.4784,
|
| 335 |
+
"step": 500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.72,
|
| 339 |
+
"learning_rate": 0.00018126520681265205,
|
| 340 |
+
"loss": 0.4648,
|
| 341 |
+
"step": 510
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.8,
|
| 345 |
+
"learning_rate": 0.00018045417680454177,
|
| 346 |
+
"loss": 0.3903,
|
| 347 |
+
"step": 520
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.87,
|
| 351 |
+
"learning_rate": 0.00017964314679643148,
|
| 352 |
+
"loss": 0.5677,
|
| 353 |
+
"step": 530
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.94,
|
| 357 |
+
"learning_rate": 0.00017883211678832117,
|
| 358 |
+
"loss": 0.3922,
|
| 359 |
+
"step": 540
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.0,
|
| 363 |
+
"eval_accuracy": 0.7622950819672131,
|
| 364 |
+
"eval_loss": 0.7107774019241333,
|
| 365 |
+
"eval_runtime": 2.435,
|
| 366 |
+
"eval_samples_per_second": 50.102,
|
| 367 |
+
"eval_steps_per_second": 6.571,
|
| 368 |
+
"step": 548
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.01,
|
| 372 |
+
"learning_rate": 0.0001780210867802109,
|
| 373 |
+
"loss": 0.8354,
|
| 374 |
+
"step": 550
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.09,
|
| 378 |
+
"learning_rate": 0.00017721005677210058,
|
| 379 |
+
"loss": 0.1381,
|
| 380 |
+
"step": 560
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.16,
|
| 384 |
+
"learning_rate": 0.00017639902676399026,
|
| 385 |
+
"loss": 0.5879,
|
| 386 |
+
"step": 570
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.23,
|
| 390 |
+
"learning_rate": 0.00017558799675587998,
|
| 391 |
+
"loss": 0.7096,
|
| 392 |
+
"step": 580
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.31,
|
| 396 |
+
"learning_rate": 0.00017477696674776967,
|
| 397 |
+
"loss": 0.5362,
|
| 398 |
+
"step": 590
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.38,
|
| 402 |
+
"learning_rate": 0.00017396593673965938,
|
| 403 |
+
"loss": 0.4455,
|
| 404 |
+
"step": 600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.45,
|
| 408 |
+
"learning_rate": 0.00017315490673154907,
|
| 409 |
+
"loss": 0.475,
|
| 410 |
+
"step": 610
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.53,
|
| 414 |
+
"learning_rate": 0.00017234387672343876,
|
| 415 |
+
"loss": 0.4872,
|
| 416 |
+
"step": 620
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.6,
|
| 420 |
+
"learning_rate": 0.00017153284671532848,
|
| 421 |
+
"loss": 0.2913,
|
| 422 |
+
"step": 630
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.67,
|
| 426 |
+
"learning_rate": 0.0001707218167072182,
|
| 427 |
+
"loss": 0.1585,
|
| 428 |
+
"step": 640
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.74,
|
| 432 |
+
"learning_rate": 0.00016991078669910788,
|
| 433 |
+
"loss": 0.304,
|
| 434 |
+
"step": 650
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.82,
|
| 438 |
+
"learning_rate": 0.00016909975669099757,
|
| 439 |
+
"loss": 0.2869,
|
| 440 |
+
"step": 660
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.89,
|
| 444 |
+
"learning_rate": 0.00016828872668288726,
|
| 445 |
+
"loss": 0.1741,
|
| 446 |
+
"step": 670
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.96,
|
| 450 |
+
"learning_rate": 0.00016747769667477697,
|
| 451 |
+
"loss": 0.2565,
|
| 452 |
+
"step": 680
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.0,
|
| 456 |
+
"eval_accuracy": 0.7213114754098361,
|
| 457 |
+
"eval_loss": 1.4021536111831665,
|
| 458 |
+
"eval_runtime": 2.5436,
|
| 459 |
+
"eval_samples_per_second": 47.963,
|
| 460 |
+
"eval_steps_per_second": 6.29,
|
| 461 |
+
"step": 685
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.04,
|
| 465 |
+
"learning_rate": 0.0001666666666666667,
|
| 466 |
+
"loss": 0.3661,
|
| 467 |
+
"step": 690
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.11,
|
| 471 |
+
"learning_rate": 0.00016585563665855638,
|
| 472 |
+
"loss": 0.457,
|
| 473 |
+
"step": 700
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.18,
|
| 477 |
+
"learning_rate": 0.00016504460665044607,
|
| 478 |
+
"loss": 0.2173,
|
| 479 |
+
"step": 710
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 5.26,
|
| 483 |
+
"learning_rate": 0.00016423357664233578,
|
| 484 |
+
"loss": 0.226,
|
| 485 |
+
"step": 720
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.33,
|
| 489 |
+
"learning_rate": 0.00016342254663422547,
|
| 490 |
+
"loss": 0.3724,
|
| 491 |
+
"step": 730
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 5.4,
|
| 495 |
+
"learning_rate": 0.00016261151662611518,
|
| 496 |
+
"loss": 0.1765,
|
| 497 |
+
"step": 740
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 5.47,
|
| 501 |
+
"learning_rate": 0.00016180048661800487,
|
| 502 |
+
"loss": 0.4033,
|
| 503 |
+
"step": 750
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 5.55,
|
| 507 |
+
"learning_rate": 0.00016098945660989456,
|
| 508 |
+
"loss": 0.6861,
|
| 509 |
+
"step": 760
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.62,
|
| 513 |
+
"learning_rate": 0.00016017842660178428,
|
| 514 |
+
"loss": 0.4331,
|
| 515 |
+
"step": 770
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 5.69,
|
| 519 |
+
"learning_rate": 0.00015936739659367397,
|
| 520 |
+
"loss": 0.2177,
|
| 521 |
+
"step": 780
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 5.77,
|
| 525 |
+
"learning_rate": 0.00015855636658556368,
|
| 526 |
+
"loss": 0.4115,
|
| 527 |
+
"step": 790
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 5.84,
|
| 531 |
+
"learning_rate": 0.0001577453365774534,
|
| 532 |
+
"loss": 0.4569,
|
| 533 |
+
"step": 800
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.91,
|
| 537 |
+
"learning_rate": 0.00015693430656934306,
|
| 538 |
+
"loss": 0.3108,
|
| 539 |
+
"step": 810
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.99,
|
| 543 |
+
"learning_rate": 0.00015612327656123277,
|
| 544 |
+
"loss": 0.4898,
|
| 545 |
+
"step": 820
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 6.0,
|
| 549 |
+
"eval_accuracy": 0.7213114754098361,
|
| 550 |
+
"eval_loss": 1.002202033996582,
|
| 551 |
+
"eval_runtime": 2.5947,
|
| 552 |
+
"eval_samples_per_second": 47.019,
|
| 553 |
+
"eval_steps_per_second": 6.166,
|
| 554 |
+
"step": 822
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.06,
|
| 558 |
+
"learning_rate": 0.00015531224655312246,
|
| 559 |
+
"loss": 0.2544,
|
| 560 |
+
"step": 830
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.13,
|
| 564 |
+
"learning_rate": 0.00015450121654501218,
|
| 565 |
+
"loss": 0.1688,
|
| 566 |
+
"step": 840
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 6.2,
|
| 570 |
+
"learning_rate": 0.0001536901865369019,
|
| 571 |
+
"loss": 0.2628,
|
| 572 |
+
"step": 850
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 6.28,
|
| 576 |
+
"learning_rate": 0.00015287915652879155,
|
| 577 |
+
"loss": 0.0097,
|
| 578 |
+
"step": 860
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.35,
|
| 582 |
+
"learning_rate": 0.00015206812652068127,
|
| 583 |
+
"loss": 0.5975,
|
| 584 |
+
"step": 870
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.42,
|
| 588 |
+
"learning_rate": 0.00015125709651257096,
|
| 589 |
+
"loss": 0.1515,
|
| 590 |
+
"step": 880
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.5,
|
| 594 |
+
"learning_rate": 0.00015044606650446067,
|
| 595 |
+
"loss": 0.0841,
|
| 596 |
+
"step": 890
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.57,
|
| 600 |
+
"learning_rate": 0.0001496350364963504,
|
| 601 |
+
"loss": 0.12,
|
| 602 |
+
"step": 900
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 6.64,
|
| 606 |
+
"learning_rate": 0.00014882400648824008,
|
| 607 |
+
"loss": 0.0841,
|
| 608 |
+
"step": 910
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 6.72,
|
| 612 |
+
"learning_rate": 0.00014801297648012977,
|
| 613 |
+
"loss": 0.327,
|
| 614 |
+
"step": 920
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 6.79,
|
| 618 |
+
"learning_rate": 0.00014720194647201948,
|
| 619 |
+
"loss": 0.1671,
|
| 620 |
+
"step": 930
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 6.86,
|
| 624 |
+
"learning_rate": 0.00014639091646390917,
|
| 625 |
+
"loss": 0.1677,
|
| 626 |
+
"step": 940
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 6.93,
|
| 630 |
+
"learning_rate": 0.00014557988645579888,
|
| 631 |
+
"loss": 0.325,
|
| 632 |
+
"step": 950
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.0,
|
| 636 |
+
"eval_accuracy": 0.819672131147541,
|
| 637 |
+
"eval_loss": 1.1020625829696655,
|
| 638 |
+
"eval_runtime": 2.5409,
|
| 639 |
+
"eval_samples_per_second": 48.014,
|
| 640 |
+
"eval_steps_per_second": 6.297,
|
| 641 |
+
"step": 959
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 7.01,
|
| 645 |
+
"learning_rate": 0.00014476885644768857,
|
| 646 |
+
"loss": 0.0793,
|
| 647 |
+
"step": 960
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 7.08,
|
| 651 |
+
"learning_rate": 0.00014395782643957826,
|
| 652 |
+
"loss": 0.3219,
|
| 653 |
+
"step": 970
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.15,
|
| 657 |
+
"learning_rate": 0.00014314679643146798,
|
| 658 |
+
"loss": 0.1076,
|
| 659 |
+
"step": 980
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 7.23,
|
| 663 |
+
"learning_rate": 0.00014233576642335767,
|
| 664 |
+
"loss": 0.0561,
|
| 665 |
+
"step": 990
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 7.3,
|
| 669 |
+
"learning_rate": 0.00014152473641524738,
|
| 670 |
+
"loss": 0.034,
|
| 671 |
+
"step": 1000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 7.37,
|
| 675 |
+
"learning_rate": 0.00014071370640713707,
|
| 676 |
+
"loss": 0.0886,
|
| 677 |
+
"step": 1010
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 7.45,
|
| 681 |
+
"learning_rate": 0.00013990267639902676,
|
| 682 |
+
"loss": 0.1077,
|
| 683 |
+
"step": 1020
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 7.52,
|
| 687 |
+
"learning_rate": 0.00013909164639091647,
|
| 688 |
+
"loss": 0.0872,
|
| 689 |
+
"step": 1030
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 7.59,
|
| 693 |
+
"learning_rate": 0.00013828061638280616,
|
| 694 |
+
"loss": 0.0343,
|
| 695 |
+
"step": 1040
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 7.66,
|
| 699 |
+
"learning_rate": 0.00013746958637469588,
|
| 700 |
+
"loss": 0.0941,
|
| 701 |
+
"step": 1050
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 7.74,
|
| 705 |
+
"learning_rate": 0.00013665855636658557,
|
| 706 |
+
"loss": 0.0696,
|
| 707 |
+
"step": 1060
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 7.81,
|
| 711 |
+
"learning_rate": 0.00013584752635847525,
|
| 712 |
+
"loss": 0.0313,
|
| 713 |
+
"step": 1070
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 7.88,
|
| 717 |
+
"learning_rate": 0.00013503649635036497,
|
| 718 |
+
"loss": 0.0473,
|
| 719 |
+
"step": 1080
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 7.96,
|
| 723 |
+
"learning_rate": 0.00013422546634225469,
|
| 724 |
+
"loss": 0.0217,
|
| 725 |
+
"step": 1090
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.0,
|
| 729 |
+
"eval_accuracy": 0.860655737704918,
|
| 730 |
+
"eval_loss": 1.2505751848220825,
|
| 731 |
+
"eval_runtime": 2.4946,
|
| 732 |
+
"eval_samples_per_second": 48.906,
|
| 733 |
+
"eval_steps_per_second": 6.414,
|
| 734 |
+
"step": 1096
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 8.03,
|
| 738 |
+
"learning_rate": 0.00013341443633414437,
|
| 739 |
+
"loss": 0.1985,
|
| 740 |
+
"step": 1100
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 8.1,
|
| 744 |
+
"learning_rate": 0.00013260340632603406,
|
| 745 |
+
"loss": 0.1631,
|
| 746 |
+
"step": 1110
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.18,
|
| 750 |
+
"learning_rate": 0.00013179237631792375,
|
| 751 |
+
"loss": 0.11,
|
| 752 |
+
"step": 1120
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 8.25,
|
| 756 |
+
"learning_rate": 0.00013098134630981347,
|
| 757 |
+
"loss": 0.2332,
|
| 758 |
+
"step": 1130
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 8.32,
|
| 762 |
+
"learning_rate": 0.00013017031630170318,
|
| 763 |
+
"loss": 0.1398,
|
| 764 |
+
"step": 1140
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 8.39,
|
| 768 |
+
"learning_rate": 0.00012935928629359287,
|
| 769 |
+
"loss": 0.0189,
|
| 770 |
+
"step": 1150
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.47,
|
| 774 |
+
"learning_rate": 0.00012854825628548256,
|
| 775 |
+
"loss": 0.1305,
|
| 776 |
+
"step": 1160
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 8.54,
|
| 780 |
+
"learning_rate": 0.00012773722627737227,
|
| 781 |
+
"loss": 0.0954,
|
| 782 |
+
"step": 1170
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 8.61,
|
| 786 |
+
"learning_rate": 0.00012692619626926196,
|
| 787 |
+
"loss": 0.0631,
|
| 788 |
+
"step": 1180
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 8.69,
|
| 792 |
+
"learning_rate": 0.00012611516626115168,
|
| 793 |
+
"loss": 0.0184,
|
| 794 |
+
"step": 1190
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 8.76,
|
| 798 |
+
"learning_rate": 0.00012530413625304137,
|
| 799 |
+
"loss": 0.1647,
|
| 800 |
+
"step": 1200
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 8.83,
|
| 804 |
+
"learning_rate": 0.00012449310624493108,
|
| 805 |
+
"loss": 0.0028,
|
| 806 |
+
"step": 1210
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 8.91,
|
| 810 |
+
"learning_rate": 0.00012368207623682077,
|
| 811 |
+
"loss": 0.0015,
|
| 812 |
+
"step": 1220
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 8.98,
|
| 816 |
+
"learning_rate": 0.00012287104622871046,
|
| 817 |
+
"loss": 0.1405,
|
| 818 |
+
"step": 1230
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.0,
|
| 822 |
+
"eval_accuracy": 0.8770491803278688,
|
| 823 |
+
"eval_loss": 0.6274831295013428,
|
| 824 |
+
"eval_runtime": 2.431,
|
| 825 |
+
"eval_samples_per_second": 50.186,
|
| 826 |
+
"eval_steps_per_second": 6.582,
|
| 827 |
+
"step": 1233
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 9.05,
|
| 831 |
+
"learning_rate": 0.00012206001622060017,
|
| 832 |
+
"loss": 0.1252,
|
| 833 |
+
"step": 1240
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 9.12,
|
| 837 |
+
"learning_rate": 0.00012124898621248988,
|
| 838 |
+
"loss": 0.0605,
|
| 839 |
+
"step": 1250
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.2,
|
| 843 |
+
"learning_rate": 0.00012043795620437956,
|
| 844 |
+
"loss": 0.1781,
|
| 845 |
+
"step": 1260
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 9.27,
|
| 849 |
+
"learning_rate": 0.00011962692619626928,
|
| 850 |
+
"loss": 0.001,
|
| 851 |
+
"step": 1270
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 9.34,
|
| 855 |
+
"learning_rate": 0.00011881589618815895,
|
| 856 |
+
"loss": 0.1232,
|
| 857 |
+
"step": 1280
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 9.42,
|
| 861 |
+
"learning_rate": 0.00011800486618004867,
|
| 862 |
+
"loss": 0.0477,
|
| 863 |
+
"step": 1290
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 9.49,
|
| 867 |
+
"learning_rate": 0.00011719383617193837,
|
| 868 |
+
"loss": 0.0041,
|
| 869 |
+
"step": 1300
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 9.56,
|
| 873 |
+
"learning_rate": 0.00011638280616382806,
|
| 874 |
+
"loss": 0.0205,
|
| 875 |
+
"step": 1310
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 9.64,
|
| 879 |
+
"learning_rate": 0.00011557177615571778,
|
| 880 |
+
"loss": 0.1789,
|
| 881 |
+
"step": 1320
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 9.71,
|
| 885 |
+
"learning_rate": 0.00011476074614760745,
|
| 886 |
+
"loss": 0.0133,
|
| 887 |
+
"step": 1330
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 9.78,
|
| 891 |
+
"learning_rate": 0.00011394971613949717,
|
| 892 |
+
"loss": 0.0806,
|
| 893 |
+
"step": 1340
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 9.85,
|
| 897 |
+
"learning_rate": 0.00011313868613138687,
|
| 898 |
+
"loss": 0.1051,
|
| 899 |
+
"step": 1350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 9.93,
|
| 903 |
+
"learning_rate": 0.00011232765612327656,
|
| 904 |
+
"loss": 0.0284,
|
| 905 |
+
"step": 1360
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 10.0,
|
| 909 |
+
"learning_rate": 0.00011151662611516627,
|
| 910 |
+
"loss": 0.0433,
|
| 911 |
+
"step": 1370
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 10.0,
|
| 915 |
+
"eval_accuracy": 0.9426229508196722,
|
| 916 |
+
"eval_loss": 0.33996063470840454,
|
| 917 |
+
"eval_runtime": 2.4463,
|
| 918 |
+
"eval_samples_per_second": 49.871,
|
| 919 |
+
"eval_steps_per_second": 6.54,
|
| 920 |
+
"step": 1370
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 10.07,
|
| 924 |
+
"learning_rate": 0.00011070559610705597,
|
| 925 |
+
"loss": 0.0784,
|
| 926 |
+
"step": 1380
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 10.15,
|
| 930 |
+
"learning_rate": 0.00010989456609894566,
|
| 931 |
+
"loss": 0.0347,
|
| 932 |
+
"step": 1390
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 10.22,
|
| 936 |
+
"learning_rate": 0.00010908353609083536,
|
| 937 |
+
"loss": 0.019,
|
| 938 |
+
"step": 1400
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 10.29,
|
| 942 |
+
"learning_rate": 0.00010827250608272505,
|
| 943 |
+
"loss": 0.0011,
|
| 944 |
+
"step": 1410
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 10.36,
|
| 948 |
+
"learning_rate": 0.00010746147607461477,
|
| 949 |
+
"loss": 0.0007,
|
| 950 |
+
"step": 1420
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 10.44,
|
| 954 |
+
"learning_rate": 0.00010665044606650447,
|
| 955 |
+
"loss": 0.0015,
|
| 956 |
+
"step": 1430
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 10.51,
|
| 960 |
+
"learning_rate": 0.00010583941605839416,
|
| 961 |
+
"loss": 0.0733,
|
| 962 |
+
"step": 1440
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 10.58,
|
| 966 |
+
"learning_rate": 0.00010502838605028386,
|
| 967 |
+
"loss": 0.4108,
|
| 968 |
+
"step": 1450
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 10.66,
|
| 972 |
+
"learning_rate": 0.00010421735604217358,
|
| 973 |
+
"loss": 0.0772,
|
| 974 |
+
"step": 1460
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 10.73,
|
| 978 |
+
"learning_rate": 0.00010340632603406326,
|
| 979 |
+
"loss": 0.016,
|
| 980 |
+
"step": 1470
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 10.8,
|
| 984 |
+
"learning_rate": 0.00010259529602595297,
|
| 985 |
+
"loss": 0.004,
|
| 986 |
+
"step": 1480
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 10.88,
|
| 990 |
+
"learning_rate": 0.00010178426601784266,
|
| 991 |
+
"loss": 0.1367,
|
| 992 |
+
"step": 1490
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 10.95,
|
| 996 |
+
"learning_rate": 0.00010097323600973236,
|
| 997 |
+
"loss": 0.168,
|
| 998 |
+
"step": 1500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 11.0,
|
| 1002 |
+
"eval_accuracy": 0.8934426229508197,
|
| 1003 |
+
"eval_loss": 0.5016093850135803,
|
| 1004 |
+
"eval_runtime": 2.4265,
|
| 1005 |
+
"eval_samples_per_second": 50.278,
|
| 1006 |
+
"eval_steps_per_second": 6.594,
|
| 1007 |
+
"step": 1507
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 11.02,
|
| 1011 |
+
"learning_rate": 0.00010016220600162207,
|
| 1012 |
+
"loss": 0.1004,
|
| 1013 |
+
"step": 1510
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 11.09,
|
| 1017 |
+
"learning_rate": 9.935117599351177e-05,
|
| 1018 |
+
"loss": 0.0006,
|
| 1019 |
+
"step": 1520
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 11.17,
|
| 1023 |
+
"learning_rate": 9.854014598540146e-05,
|
| 1024 |
+
"loss": 0.0111,
|
| 1025 |
+
"step": 1530
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 11.24,
|
| 1029 |
+
"learning_rate": 9.772911597729116e-05,
|
| 1030 |
+
"loss": 0.0278,
|
| 1031 |
+
"step": 1540
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 11.31,
|
| 1035 |
+
"learning_rate": 9.691808596918087e-05,
|
| 1036 |
+
"loss": 0.0631,
|
| 1037 |
+
"step": 1550
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 11.39,
|
| 1041 |
+
"learning_rate": 9.610705596107057e-05,
|
| 1042 |
+
"loss": 0.0002,
|
| 1043 |
+
"step": 1560
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 11.46,
|
| 1047 |
+
"learning_rate": 9.529602595296027e-05,
|
| 1048 |
+
"loss": 0.0013,
|
| 1049 |
+
"step": 1570
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 11.53,
|
| 1053 |
+
"learning_rate": 9.448499594484996e-05,
|
| 1054 |
+
"loss": 0.0008,
|
| 1055 |
+
"step": 1580
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 11.61,
|
| 1059 |
+
"learning_rate": 9.367396593673966e-05,
|
| 1060 |
+
"loss": 0.0001,
|
| 1061 |
+
"step": 1590
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 11.68,
|
| 1065 |
+
"learning_rate": 9.286293592862936e-05,
|
| 1066 |
+
"loss": 0.0001,
|
| 1067 |
+
"step": 1600
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 11.75,
|
| 1071 |
+
"learning_rate": 9.205190592051907e-05,
|
| 1072 |
+
"loss": 0.0002,
|
| 1073 |
+
"step": 1610
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 11.82,
|
| 1077 |
+
"learning_rate": 9.124087591240877e-05,
|
| 1078 |
+
"loss": 0.0002,
|
| 1079 |
+
"step": 1620
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 11.9,
|
| 1083 |
+
"learning_rate": 9.042984590429846e-05,
|
| 1084 |
+
"loss": 0.0001,
|
| 1085 |
+
"step": 1630
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 11.97,
|
| 1089 |
+
"learning_rate": 8.961881589618817e-05,
|
| 1090 |
+
"loss": 0.0001,
|
| 1091 |
+
"step": 1640
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 12.0,
|
| 1095 |
+
"eval_accuracy": 0.9508196721311475,
|
| 1096 |
+
"eval_loss": 0.2764035761356354,
|
| 1097 |
+
"eval_runtime": 2.435,
|
| 1098 |
+
"eval_samples_per_second": 50.104,
|
| 1099 |
+
"eval_steps_per_second": 6.571,
|
| 1100 |
+
"step": 1644
|
| 1101 |
+
}
|
| 1102 |
+
],
|
| 1103 |
+
"max_steps": 2740,
|
| 1104 |
+
"num_train_epochs": 20,
|
| 1105 |
+
"total_flos": 3.5908878492818473e+18,
|
| 1106 |
+
"trial_name": null,
|
| 1107 |
+
"trial_params": null
|
| 1108 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:243d8174ddf7e15e284ae33c12e86a303a84efe0f28f793d2dd1a14c7fb565cd
|
| 3 |
+
size 3515
|