Upload 8 files
Browse files- config.json +34 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +798 -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": "calcificaciones",
|
| 13 |
+
"1": "masas",
|
| 14 |
+
"2": "no_encontrado"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"calcificaciones": 0,
|
| 21 |
+
"masas": 1,
|
| 22 |
+
"no_encontrado": 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": "4.45.1"
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10b0782e374d9537f21dd2c122bf3722f292e6e2c171e16ccde56cea965bcb0d
|
| 3 |
+
size 1213265372
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d6de43352acbfe72d0cb1676cf10eeeb4519111c291d231b24be87a7a4a1645
|
| 3 |
+
size 503940154
|
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": "ViTImageProcessorFast",
|
| 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 sha256:3ce3a3c05ac42196e5ce20babc07ba298e3f4439fa1b4712cb2e14c382e65881
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0edc849a55daef37f3913f72b0ae54d705cb645843af555e57da8ec176190095
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,798 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6901677250862122,
|
| 3 |
+
"best_model_checkpoint": "SavedModels/ViT-large-patch16-224_B/checkpoint-1128",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7520,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.26595744680851063,
|
| 13 |
+
"grad_norm": 16.918853759765625,
|
| 14 |
+
"learning_rate": 0.0002920212765957447,
|
| 15 |
+
"loss": 1.0273,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5319148936170213,
|
| 20 |
+
"grad_norm": 8.12959098815918,
|
| 21 |
+
"learning_rate": 0.00028404255319148934,
|
| 22 |
+
"loss": 0.8052,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7978723404255319,
|
| 27 |
+
"grad_norm": 4.803711891174316,
|
| 28 |
+
"learning_rate": 0.00027606382978723404,
|
| 29 |
+
"loss": 0.7818,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"eval_accuracy": 0.6693333333333333,
|
| 35 |
+
"eval_f1": 0.6679277175440698,
|
| 36 |
+
"eval_loss": 0.7451461553573608,
|
| 37 |
+
"eval_precision": 0.6665516663433287,
|
| 38 |
+
"eval_recall": 0.6708336668000534,
|
| 39 |
+
"eval_runtime": 34.5448,
|
| 40 |
+
"eval_samples_per_second": 21.711,
|
| 41 |
+
"eval_steps_per_second": 2.721,
|
| 42 |
+
"step": 376
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.0638297872340425,
|
| 46 |
+
"grad_norm": 5.264636516571045,
|
| 47 |
+
"learning_rate": 0.0002680851063829787,
|
| 48 |
+
"loss": 0.7518,
|
| 49 |
+
"step": 400
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.3297872340425532,
|
| 53 |
+
"grad_norm": 6.721948146820068,
|
| 54 |
+
"learning_rate": 0.0002601063829787234,
|
| 55 |
+
"loss": 0.7153,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.5957446808510638,
|
| 60 |
+
"grad_norm": 5.855480670928955,
|
| 61 |
+
"learning_rate": 0.00025212765957446806,
|
| 62 |
+
"loss": 0.6854,
|
| 63 |
+
"step": 600
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.8617021276595744,
|
| 67 |
+
"grad_norm": 5.206683158874512,
|
| 68 |
+
"learning_rate": 0.0002441489361702127,
|
| 69 |
+
"loss": 0.6975,
|
| 70 |
+
"step": 700
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.0,
|
| 74 |
+
"eval_accuracy": 0.652,
|
| 75 |
+
"eval_f1": 0.6527448850868924,
|
| 76 |
+
"eval_loss": 0.737027108669281,
|
| 77 |
+
"eval_precision": 0.6598586784457597,
|
| 78 |
+
"eval_recall": 0.6519173002534348,
|
| 79 |
+
"eval_runtime": 34.5417,
|
| 80 |
+
"eval_samples_per_second": 21.713,
|
| 81 |
+
"eval_steps_per_second": 2.721,
|
| 82 |
+
"step": 752
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.127659574468085,
|
| 86 |
+
"grad_norm": 6.592344760894775,
|
| 87 |
+
"learning_rate": 0.00023617021276595742,
|
| 88 |
+
"loss": 0.6174,
|
| 89 |
+
"step": 800
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.393617021276596,
|
| 93 |
+
"grad_norm": 4.732657432556152,
|
| 94 |
+
"learning_rate": 0.0002281914893617021,
|
| 95 |
+
"loss": 0.644,
|
| 96 |
+
"step": 900
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.6595744680851063,
|
| 100 |
+
"grad_norm": 5.618279933929443,
|
| 101 |
+
"learning_rate": 0.00022021276595744679,
|
| 102 |
+
"loss": 0.6098,
|
| 103 |
+
"step": 1000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.925531914893617,
|
| 107 |
+
"grad_norm": 4.702358245849609,
|
| 108 |
+
"learning_rate": 0.0002122340425531915,
|
| 109 |
+
"loss": 0.5934,
|
| 110 |
+
"step": 1100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.0,
|
| 114 |
+
"eval_accuracy": 0.6826666666666666,
|
| 115 |
+
"eval_f1": 0.6716423210919009,
|
| 116 |
+
"eval_loss": 0.6901677250862122,
|
| 117 |
+
"eval_precision": 0.680882951010493,
|
| 118 |
+
"eval_recall": 0.6834541816726691,
|
| 119 |
+
"eval_runtime": 35.1911,
|
| 120 |
+
"eval_samples_per_second": 21.312,
|
| 121 |
+
"eval_steps_per_second": 2.671,
|
| 122 |
+
"step": 1128
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.1914893617021276,
|
| 126 |
+
"grad_norm": 4.94950008392334,
|
| 127 |
+
"learning_rate": 0.00020425531914893615,
|
| 128 |
+
"loss": 0.4998,
|
| 129 |
+
"step": 1200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.4574468085106385,
|
| 133 |
+
"grad_norm": 4.887601375579834,
|
| 134 |
+
"learning_rate": 0.00019627659574468083,
|
| 135 |
+
"loss": 0.5384,
|
| 136 |
+
"step": 1300
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.723404255319149,
|
| 140 |
+
"grad_norm": 5.762096881866455,
|
| 141 |
+
"learning_rate": 0.0001882978723404255,
|
| 142 |
+
"loss": 0.5035,
|
| 143 |
+
"step": 1400
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.9893617021276597,
|
| 147 |
+
"grad_norm": 5.000032424926758,
|
| 148 |
+
"learning_rate": 0.0001803191489361702,
|
| 149 |
+
"loss": 0.4943,
|
| 150 |
+
"step": 1500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.0,
|
| 154 |
+
"eval_accuracy": 0.68,
|
| 155 |
+
"eval_f1": 0.6607042226524314,
|
| 156 |
+
"eval_loss": 0.7506471872329712,
|
| 157 |
+
"eval_precision": 0.6727589541740554,
|
| 158 |
+
"eval_recall": 0.6823892223556088,
|
| 159 |
+
"eval_runtime": 34.4906,
|
| 160 |
+
"eval_samples_per_second": 21.745,
|
| 161 |
+
"eval_steps_per_second": 2.725,
|
| 162 |
+
"step": 1504
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.25531914893617,
|
| 166 |
+
"grad_norm": 7.737178325653076,
|
| 167 |
+
"learning_rate": 0.0001723404255319149,
|
| 168 |
+
"loss": 0.3581,
|
| 169 |
+
"step": 1600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.5212765957446805,
|
| 173 |
+
"grad_norm": 5.353149890899658,
|
| 174 |
+
"learning_rate": 0.00016436170212765956,
|
| 175 |
+
"loss": 0.3857,
|
| 176 |
+
"step": 1700
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.787234042553192,
|
| 180 |
+
"grad_norm": 5.475671768188477,
|
| 181 |
+
"learning_rate": 0.00015638297872340426,
|
| 182 |
+
"loss": 0.3625,
|
| 183 |
+
"step": 1800
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.0,
|
| 187 |
+
"eval_accuracy": 0.6693333333333333,
|
| 188 |
+
"eval_f1": 0.6583454266829142,
|
| 189 |
+
"eval_loss": 0.9006826281547546,
|
| 190 |
+
"eval_precision": 0.6655033443649184,
|
| 191 |
+
"eval_recall": 0.6717070828331333,
|
| 192 |
+
"eval_runtime": 34.3021,
|
| 193 |
+
"eval_samples_per_second": 21.865,
|
| 194 |
+
"eval_steps_per_second": 2.74,
|
| 195 |
+
"step": 1880
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 5.053191489361702,
|
| 199 |
+
"grad_norm": 8.006985664367676,
|
| 200 |
+
"learning_rate": 0.00014840425531914892,
|
| 201 |
+
"loss": 0.3767,
|
| 202 |
+
"step": 1900
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 5.319148936170213,
|
| 206 |
+
"grad_norm": 8.51475715637207,
|
| 207 |
+
"learning_rate": 0.0001404255319148936,
|
| 208 |
+
"loss": 0.2824,
|
| 209 |
+
"step": 2000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.585106382978723,
|
| 213 |
+
"grad_norm": 8.186362266540527,
|
| 214 |
+
"learning_rate": 0.00013244680851063828,
|
| 215 |
+
"loss": 0.2434,
|
| 216 |
+
"step": 2100
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.851063829787234,
|
| 220 |
+
"grad_norm": 6.735799312591553,
|
| 221 |
+
"learning_rate": 0.00012446808510638296,
|
| 222 |
+
"loss": 0.2717,
|
| 223 |
+
"step": 2200
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 6.0,
|
| 227 |
+
"eval_accuracy": 0.6586666666666666,
|
| 228 |
+
"eval_f1": 0.6614425775783358,
|
| 229 |
+
"eval_loss": 1.0333963632583618,
|
| 230 |
+
"eval_precision": 0.6652982915561002,
|
| 231 |
+
"eval_recall": 0.6589942643724156,
|
| 232 |
+
"eval_runtime": 34.3254,
|
| 233 |
+
"eval_samples_per_second": 21.85,
|
| 234 |
+
"eval_steps_per_second": 2.738,
|
| 235 |
+
"step": 2256
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 6.117021276595745,
|
| 239 |
+
"grad_norm": 6.987758636474609,
|
| 240 |
+
"learning_rate": 0.00011648936170212764,
|
| 241 |
+
"loss": 0.2191,
|
| 242 |
+
"step": 2300
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.382978723404255,
|
| 246 |
+
"grad_norm": 8.753083229064941,
|
| 247 |
+
"learning_rate": 0.00010851063829787234,
|
| 248 |
+
"loss": 0.1532,
|
| 249 |
+
"step": 2400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.648936170212766,
|
| 253 |
+
"grad_norm": 6.87877082824707,
|
| 254 |
+
"learning_rate": 0.00010053191489361702,
|
| 255 |
+
"loss": 0.172,
|
| 256 |
+
"step": 2500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 6.914893617021277,
|
| 260 |
+
"grad_norm": 8.248693466186523,
|
| 261 |
+
"learning_rate": 9.25531914893617e-05,
|
| 262 |
+
"loss": 0.188,
|
| 263 |
+
"step": 2600
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 7.0,
|
| 267 |
+
"eval_accuracy": 0.648,
|
| 268 |
+
"eval_f1": 0.6480604224938936,
|
| 269 |
+
"eval_loss": 1.3646624088287354,
|
| 270 |
+
"eval_precision": 0.6474310419368785,
|
| 271 |
+
"eval_recall": 0.6488264639189009,
|
| 272 |
+
"eval_runtime": 34.2754,
|
| 273 |
+
"eval_samples_per_second": 21.882,
|
| 274 |
+
"eval_steps_per_second": 2.742,
|
| 275 |
+
"step": 2632
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.180851063829787,
|
| 279 |
+
"grad_norm": 9.565648078918457,
|
| 280 |
+
"learning_rate": 8.457446808510637e-05,
|
| 281 |
+
"loss": 0.1344,
|
| 282 |
+
"step": 2700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.446808510638298,
|
| 286 |
+
"grad_norm": 10.819112777709961,
|
| 287 |
+
"learning_rate": 7.659574468085105e-05,
|
| 288 |
+
"loss": 0.0791,
|
| 289 |
+
"step": 2800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.712765957446808,
|
| 293 |
+
"grad_norm": 11.498022079467773,
|
| 294 |
+
"learning_rate": 6.861702127659574e-05,
|
| 295 |
+
"loss": 0.0917,
|
| 296 |
+
"step": 2900
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.9787234042553195,
|
| 300 |
+
"grad_norm": 10.500368118286133,
|
| 301 |
+
"learning_rate": 6.063829787234042e-05,
|
| 302 |
+
"loss": 0.0966,
|
| 303 |
+
"step": 3000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.0,
|
| 307 |
+
"eval_accuracy": 0.6506666666666666,
|
| 308 |
+
"eval_f1": 0.6510622640996298,
|
| 309 |
+
"eval_loss": 1.7121126651763916,
|
| 310 |
+
"eval_precision": 0.6518027984453844,
|
| 311 |
+
"eval_recall": 0.6519786581299186,
|
| 312 |
+
"eval_runtime": 34.2979,
|
| 313 |
+
"eval_samples_per_second": 21.867,
|
| 314 |
+
"eval_steps_per_second": 2.741,
|
| 315 |
+
"step": 3008
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.24468085106383,
|
| 319 |
+
"grad_norm": 10.034985542297363,
|
| 320 |
+
"learning_rate": 5.26595744680851e-05,
|
| 321 |
+
"loss": 0.0589,
|
| 322 |
+
"step": 3100
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 8.51063829787234,
|
| 326 |
+
"grad_norm": 8.84762954711914,
|
| 327 |
+
"learning_rate": 4.468085106382978e-05,
|
| 328 |
+
"loss": 0.0444,
|
| 329 |
+
"step": 3200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 8.77659574468085,
|
| 333 |
+
"grad_norm": 8.717729568481445,
|
| 334 |
+
"learning_rate": 3.670212765957446e-05,
|
| 335 |
+
"loss": 0.0492,
|
| 336 |
+
"step": 3300
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 9.0,
|
| 340 |
+
"eval_accuracy": 0.664,
|
| 341 |
+
"eval_f1": 0.6634717422597086,
|
| 342 |
+
"eval_loss": 2.092434883117676,
|
| 343 |
+
"eval_precision": 0.6624493384142015,
|
| 344 |
+
"eval_recall": 0.6648558089902628,
|
| 345 |
+
"eval_runtime": 34.1372,
|
| 346 |
+
"eval_samples_per_second": 21.97,
|
| 347 |
+
"eval_steps_per_second": 2.754,
|
| 348 |
+
"step": 3384
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 9.042553191489361,
|
| 352 |
+
"grad_norm": 10.311498641967773,
|
| 353 |
+
"learning_rate": 2.8723404255319147e-05,
|
| 354 |
+
"loss": 0.0461,
|
| 355 |
+
"step": 3400
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 9.308510638297872,
|
| 359 |
+
"grad_norm": 9.477750778198242,
|
| 360 |
+
"learning_rate": 2.0744680851063828e-05,
|
| 361 |
+
"loss": 0.0215,
|
| 362 |
+
"step": 3500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 9.574468085106384,
|
| 366 |
+
"grad_norm": 10.069836616516113,
|
| 367 |
+
"learning_rate": 1.276595744680851e-05,
|
| 368 |
+
"loss": 0.0275,
|
| 369 |
+
"step": 3600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.840425531914894,
|
| 373 |
+
"grad_norm": 9.309320449829102,
|
| 374 |
+
"learning_rate": 4.7872340425531906e-06,
|
| 375 |
+
"loss": 0.0198,
|
| 376 |
+
"step": 3700
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 10.0,
|
| 380 |
+
"eval_accuracy": 0.6733333333333333,
|
| 381 |
+
"eval_f1": 0.671461456478878,
|
| 382 |
+
"eval_loss": 2.349191427230835,
|
| 383 |
+
"eval_precision": 0.6697804784739011,
|
| 384 |
+
"eval_recall": 0.6742686407896491,
|
| 385 |
+
"eval_runtime": 34.2831,
|
| 386 |
+
"eval_samples_per_second": 21.877,
|
| 387 |
+
"eval_steps_per_second": 2.742,
|
| 388 |
+
"step": 3760
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 10.106382978723405,
|
| 392 |
+
"grad_norm": 4.254685878753662,
|
| 393 |
+
"learning_rate": 0.00014840425531914892,
|
| 394 |
+
"loss": 0.1783,
|
| 395 |
+
"step": 3800
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 10.372340425531915,
|
| 399 |
+
"grad_norm": 6.5849409103393555,
|
| 400 |
+
"learning_rate": 0.00014441489361702127,
|
| 401 |
+
"loss": 0.4254,
|
| 402 |
+
"step": 3900
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 10.638297872340425,
|
| 406 |
+
"grad_norm": 6.008872985839844,
|
| 407 |
+
"learning_rate": 0.0001404255319148936,
|
| 408 |
+
"loss": 0.3892,
|
| 409 |
+
"step": 4000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 10.904255319148936,
|
| 413 |
+
"grad_norm": 4.886096000671387,
|
| 414 |
+
"learning_rate": 0.00013643617021276593,
|
| 415 |
+
"loss": 0.3308,
|
| 416 |
+
"step": 4100
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 11.0,
|
| 420 |
+
"eval_accuracy": 0.6413333333333333,
|
| 421 |
+
"eval_f1": 0.6379586335182581,
|
| 422 |
+
"eval_loss": 1.2812837362289429,
|
| 423 |
+
"eval_precision": 0.6360221570265966,
|
| 424 |
+
"eval_recall": 0.6426586634653862,
|
| 425 |
+
"eval_runtime": 34.4135,
|
| 426 |
+
"eval_samples_per_second": 21.794,
|
| 427 |
+
"eval_steps_per_second": 2.731,
|
| 428 |
+
"step": 4136
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 11.170212765957446,
|
| 432 |
+
"grad_norm": 8.697183609008789,
|
| 433 |
+
"learning_rate": 0.00013244680851063828,
|
| 434 |
+
"loss": 0.3418,
|
| 435 |
+
"step": 4200
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 11.436170212765958,
|
| 439 |
+
"grad_norm": 1.831715703010559,
|
| 440 |
+
"learning_rate": 0.00012845744680851063,
|
| 441 |
+
"loss": 0.2892,
|
| 442 |
+
"step": 4300
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 11.702127659574469,
|
| 446 |
+
"grad_norm": 5.119130611419678,
|
| 447 |
+
"learning_rate": 0.00012446808510638296,
|
| 448 |
+
"loss": 0.2597,
|
| 449 |
+
"step": 4400
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 11.96808510638298,
|
| 453 |
+
"grad_norm": 4.450387001037598,
|
| 454 |
+
"learning_rate": 0.00012047872340425532,
|
| 455 |
+
"loss": 0.2468,
|
| 456 |
+
"step": 4500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 12.0,
|
| 460 |
+
"eval_accuracy": 0.6693333333333333,
|
| 461 |
+
"eval_f1": 0.6644005202701936,
|
| 462 |
+
"eval_loss": 1.343381404876709,
|
| 463 |
+
"eval_precision": 0.6702673209494008,
|
| 464 |
+
"eval_recall": 0.6696177137521676,
|
| 465 |
+
"eval_runtime": 34.1977,
|
| 466 |
+
"eval_samples_per_second": 21.931,
|
| 467 |
+
"eval_steps_per_second": 2.749,
|
| 468 |
+
"step": 4512
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 12.23404255319149,
|
| 472 |
+
"grad_norm": 0.5507918000221252,
|
| 473 |
+
"learning_rate": 0.00011648936170212764,
|
| 474 |
+
"loss": 0.161,
|
| 475 |
+
"step": 4600
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 12.5,
|
| 479 |
+
"grad_norm": 3.424229621887207,
|
| 480 |
+
"learning_rate": 0.0001125,
|
| 481 |
+
"loss": 0.1698,
|
| 482 |
+
"step": 4700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 12.76595744680851,
|
| 486 |
+
"grad_norm": 10.304464340209961,
|
| 487 |
+
"learning_rate": 0.00010851063829787234,
|
| 488 |
+
"loss": 0.1992,
|
| 489 |
+
"step": 4800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 13.0,
|
| 493 |
+
"eval_accuracy": 0.6773333333333333,
|
| 494 |
+
"eval_f1": 0.6757724702487522,
|
| 495 |
+
"eval_loss": 1.5172154903411865,
|
| 496 |
+
"eval_precision": 0.6749943823114556,
|
| 497 |
+
"eval_recall": 0.6780813658796853,
|
| 498 |
+
"eval_runtime": 34.5579,
|
| 499 |
+
"eval_samples_per_second": 21.703,
|
| 500 |
+
"eval_steps_per_second": 2.72,
|
| 501 |
+
"step": 4888
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 13.03191489361702,
|
| 505 |
+
"grad_norm": 0.58838951587677,
|
| 506 |
+
"learning_rate": 0.00010452127659574466,
|
| 507 |
+
"loss": 0.153,
|
| 508 |
+
"step": 4900
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 13.297872340425531,
|
| 512 |
+
"grad_norm": 4.339015007019043,
|
| 513 |
+
"learning_rate": 0.00010053191489361702,
|
| 514 |
+
"loss": 0.0729,
|
| 515 |
+
"step": 5000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 13.563829787234042,
|
| 519 |
+
"grad_norm": 5.353603839874268,
|
| 520 |
+
"learning_rate": 9.654255319148935e-05,
|
| 521 |
+
"loss": 0.1182,
|
| 522 |
+
"step": 5100
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 13.829787234042554,
|
| 526 |
+
"grad_norm": 0.11711510270833969,
|
| 527 |
+
"learning_rate": 9.25531914893617e-05,
|
| 528 |
+
"loss": 0.1391,
|
| 529 |
+
"step": 5200
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 14.0,
|
| 533 |
+
"eval_accuracy": 0.688,
|
| 534 |
+
"eval_f1": 0.6861192542213884,
|
| 535 |
+
"eval_loss": 1.8793449401855469,
|
| 536 |
+
"eval_precision": 0.6887025095519409,
|
| 537 |
+
"eval_recall": 0.6882689075630252,
|
| 538 |
+
"eval_runtime": 35.0719,
|
| 539 |
+
"eval_samples_per_second": 21.385,
|
| 540 |
+
"eval_steps_per_second": 2.68,
|
| 541 |
+
"step": 5264
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 14.095744680851064,
|
| 545 |
+
"grad_norm": 16.545928955078125,
|
| 546 |
+
"learning_rate": 8.856382978723404e-05,
|
| 547 |
+
"loss": 0.0919,
|
| 548 |
+
"step": 5300
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 14.361702127659575,
|
| 552 |
+
"grad_norm": 0.11285369098186493,
|
| 553 |
+
"learning_rate": 8.457446808510637e-05,
|
| 554 |
+
"loss": 0.0724,
|
| 555 |
+
"step": 5400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 14.627659574468085,
|
| 559 |
+
"grad_norm": 1.0866966247558594,
|
| 560 |
+
"learning_rate": 8.058510638297872e-05,
|
| 561 |
+
"loss": 0.0615,
|
| 562 |
+
"step": 5500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 14.893617021276595,
|
| 566 |
+
"grad_norm": 0.0466451533138752,
|
| 567 |
+
"learning_rate": 7.659574468085105e-05,
|
| 568 |
+
"loss": 0.062,
|
| 569 |
+
"step": 5600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 15.0,
|
| 573 |
+
"eval_accuracy": 0.6826666666666666,
|
| 574 |
+
"eval_f1": 0.6784899933134545,
|
| 575 |
+
"eval_loss": 2.1949727535247803,
|
| 576 |
+
"eval_precision": 0.6780378052909217,
|
| 577 |
+
"eval_recall": 0.6832503668133919,
|
| 578 |
+
"eval_runtime": 34.2882,
|
| 579 |
+
"eval_samples_per_second": 21.873,
|
| 580 |
+
"eval_steps_per_second": 2.741,
|
| 581 |
+
"step": 5640
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 15.159574468085106,
|
| 585 |
+
"grad_norm": 1.6346490383148193,
|
| 586 |
+
"learning_rate": 7.26063829787234e-05,
|
| 587 |
+
"loss": 0.0477,
|
| 588 |
+
"step": 5700
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 15.425531914893616,
|
| 592 |
+
"grad_norm": 0.004013681318610907,
|
| 593 |
+
"learning_rate": 6.861702127659574e-05,
|
| 594 |
+
"loss": 0.0484,
|
| 595 |
+
"step": 5800
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 15.691489361702128,
|
| 599 |
+
"grad_norm": 0.6463019847869873,
|
| 600 |
+
"learning_rate": 6.462765957446807e-05,
|
| 601 |
+
"loss": 0.0389,
|
| 602 |
+
"step": 5900
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 15.957446808510639,
|
| 606 |
+
"grad_norm": 0.4977071285247803,
|
| 607 |
+
"learning_rate": 6.063829787234042e-05,
|
| 608 |
+
"loss": 0.0392,
|
| 609 |
+
"step": 6000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 16.0,
|
| 613 |
+
"eval_accuracy": 0.6626666666666666,
|
| 614 |
+
"eval_f1": 0.6599147266673199,
|
| 615 |
+
"eval_loss": 2.2853217124938965,
|
| 616 |
+
"eval_precision": 0.6593416101537274,
|
| 617 |
+
"eval_recall": 0.6640821661998133,
|
| 618 |
+
"eval_runtime": 34.2142,
|
| 619 |
+
"eval_samples_per_second": 21.921,
|
| 620 |
+
"eval_steps_per_second": 2.747,
|
| 621 |
+
"step": 6016
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 16.22340425531915,
|
| 625 |
+
"grad_norm": 0.18373289704322815,
|
| 626 |
+
"learning_rate": 5.6648936170212766e-05,
|
| 627 |
+
"loss": 0.035,
|
| 628 |
+
"step": 6100
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 16.48936170212766,
|
| 632 |
+
"grad_norm": 11.437871932983398,
|
| 633 |
+
"learning_rate": 5.26595744680851e-05,
|
| 634 |
+
"loss": 0.0323,
|
| 635 |
+
"step": 6200
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 16.75531914893617,
|
| 639 |
+
"grad_norm": 0.04929669201374054,
|
| 640 |
+
"learning_rate": 4.867021276595744e-05,
|
| 641 |
+
"loss": 0.0286,
|
| 642 |
+
"step": 6300
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 17.0,
|
| 646 |
+
"eval_accuracy": 0.6706666666666666,
|
| 647 |
+
"eval_f1": 0.6665467903773287,
|
| 648 |
+
"eval_loss": 2.356433153152466,
|
| 649 |
+
"eval_precision": 0.6646925224621034,
|
| 650 |
+
"eval_recall": 0.6718655462184874,
|
| 651 |
+
"eval_runtime": 34.2754,
|
| 652 |
+
"eval_samples_per_second": 21.882,
|
| 653 |
+
"eval_steps_per_second": 2.742,
|
| 654 |
+
"step": 6392
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 17.02127659574468,
|
| 658 |
+
"grad_norm": 0.003023180877789855,
|
| 659 |
+
"learning_rate": 4.468085106382978e-05,
|
| 660 |
+
"loss": 0.0232,
|
| 661 |
+
"step": 6400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 17.28723404255319,
|
| 665 |
+
"grad_norm": 0.009346798993647099,
|
| 666 |
+
"learning_rate": 4.069148936170212e-05,
|
| 667 |
+
"loss": 0.0195,
|
| 668 |
+
"step": 6500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 17.5531914893617,
|
| 672 |
+
"grad_norm": 0.0396982878446579,
|
| 673 |
+
"learning_rate": 3.670212765957446e-05,
|
| 674 |
+
"loss": 0.02,
|
| 675 |
+
"step": 6600
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 17.819148936170212,
|
| 679 |
+
"grad_norm": 0.014023613184690475,
|
| 680 |
+
"learning_rate": 3.271276595744681e-05,
|
| 681 |
+
"loss": 0.025,
|
| 682 |
+
"step": 6700
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 18.0,
|
| 686 |
+
"eval_accuracy": 0.676,
|
| 687 |
+
"eval_f1": 0.6721775597644245,
|
| 688 |
+
"eval_loss": 2.5857865810394287,
|
| 689 |
+
"eval_precision": 0.6713915090790397,
|
| 690 |
+
"eval_recall": 0.6767165532879819,
|
| 691 |
+
"eval_runtime": 34.2491,
|
| 692 |
+
"eval_samples_per_second": 21.898,
|
| 693 |
+
"eval_steps_per_second": 2.745,
|
| 694 |
+
"step": 6768
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 18.085106382978722,
|
| 698 |
+
"grad_norm": 0.47041425108909607,
|
| 699 |
+
"learning_rate": 2.8723404255319147e-05,
|
| 700 |
+
"loss": 0.0202,
|
| 701 |
+
"step": 6800
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 18.351063829787233,
|
| 705 |
+
"grad_norm": 0.06168466433882713,
|
| 706 |
+
"learning_rate": 2.4734042553191484e-05,
|
| 707 |
+
"loss": 0.019,
|
| 708 |
+
"step": 6900
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 18.617021276595743,
|
| 712 |
+
"grad_norm": 0.0014604219468310475,
|
| 713 |
+
"learning_rate": 2.0744680851063828e-05,
|
| 714 |
+
"loss": 0.0178,
|
| 715 |
+
"step": 7000
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 18.882978723404257,
|
| 719 |
+
"grad_norm": 0.0028070323169231415,
|
| 720 |
+
"learning_rate": 1.675531914893617e-05,
|
| 721 |
+
"loss": 0.0214,
|
| 722 |
+
"step": 7100
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 19.0,
|
| 726 |
+
"eval_accuracy": 0.668,
|
| 727 |
+
"eval_f1": 0.6658631291530153,
|
| 728 |
+
"eval_loss": 2.6788387298583984,
|
| 729 |
+
"eval_precision": 0.6642259414225942,
|
| 730 |
+
"eval_recall": 0.6688787515006003,
|
| 731 |
+
"eval_runtime": 34.249,
|
| 732 |
+
"eval_samples_per_second": 21.898,
|
| 733 |
+
"eval_steps_per_second": 2.745,
|
| 734 |
+
"step": 7144
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 19.148936170212767,
|
| 738 |
+
"grad_norm": 0.0015123536577448249,
|
| 739 |
+
"learning_rate": 1.276595744680851e-05,
|
| 740 |
+
"loss": 0.0204,
|
| 741 |
+
"step": 7200
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 19.414893617021278,
|
| 745 |
+
"grad_norm": 0.0018817168893292546,
|
| 746 |
+
"learning_rate": 8.77659574468085e-06,
|
| 747 |
+
"loss": 0.0141,
|
| 748 |
+
"step": 7300
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 19.680851063829788,
|
| 752 |
+
"grad_norm": 0.6008268594741821,
|
| 753 |
+
"learning_rate": 4.7872340425531906e-06,
|
| 754 |
+
"loss": 0.0203,
|
| 755 |
+
"step": 7400
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 19.9468085106383,
|
| 759 |
+
"grad_norm": 1.0317440032958984,
|
| 760 |
+
"learning_rate": 7.978723404255318e-07,
|
| 761 |
+
"loss": 0.0155,
|
| 762 |
+
"step": 7500
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 20.0,
|
| 766 |
+
"eval_accuracy": 0.672,
|
| 767 |
+
"eval_f1": 0.6695170440310667,
|
| 768 |
+
"eval_loss": 2.725527048110962,
|
| 769 |
+
"eval_precision": 0.66779120407287,
|
| 770 |
+
"eval_recall": 0.6728787515006003,
|
| 771 |
+
"eval_runtime": 34.5602,
|
| 772 |
+
"eval_samples_per_second": 21.701,
|
| 773 |
+
"eval_steps_per_second": 2.72,
|
| 774 |
+
"step": 7520
|
| 775 |
+
}
|
| 776 |
+
],
|
| 777 |
+
"logging_steps": 100,
|
| 778 |
+
"max_steps": 7520,
|
| 779 |
+
"num_input_tokens_seen": 0,
|
| 780 |
+
"num_train_epochs": 20,
|
| 781 |
+
"save_steps": 500,
|
| 782 |
+
"stateful_callbacks": {
|
| 783 |
+
"TrainerControl": {
|
| 784 |
+
"args": {
|
| 785 |
+
"should_epoch_stop": false,
|
| 786 |
+
"should_evaluate": false,
|
| 787 |
+
"should_log": false,
|
| 788 |
+
"should_save": true,
|
| 789 |
+
"should_training_stop": true
|
| 790 |
+
},
|
| 791 |
+
"attributes": {}
|
| 792 |
+
}
|
| 793 |
+
},
|
| 794 |
+
"total_flos": 3.288864877974981e+19,
|
| 795 |
+
"train_batch_size": 16,
|
| 796 |
+
"trial_name": null,
|
| 797 |
+
"trial_params": null
|
| 798 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d6161a2d7c96f418e5516fcd350adef0b7734e918251a4c3ab6e45395587780
|
| 3 |
+
size 5240
|