Commit
•
c3bb20b
1
Parent(s):
c59b59f
Upload 8 files
Browse files- config.json +51 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +26 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1416 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoint-45-finetuned-ucf101-subset/checkpoint-350",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VideoMAEForVideoClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"decoder_hidden_size": 384,
|
| 8 |
+
"decoder_intermediate_size": 1536,
|
| 9 |
+
"decoder_num_attention_heads": 6,
|
| 10 |
+
"decoder_num_hidden_layers": 4,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.0,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Beautiful",
|
| 16 |
+
"1": "Blind",
|
| 17 |
+
"2": "Deaf",
|
| 18 |
+
"3": "Ugly",
|
| 19 |
+
"4": "happy",
|
| 20 |
+
"5": "loud",
|
| 21 |
+
"6": "quiet",
|
| 22 |
+
"7": "sad"
|
| 23 |
+
},
|
| 24 |
+
"image_size": 224,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"Beautiful": 0,
|
| 29 |
+
"Blind": 1,
|
| 30 |
+
"Deaf": 2,
|
| 31 |
+
"Ugly": 3,
|
| 32 |
+
"happy": 4,
|
| 33 |
+
"loud": 5,
|
| 34 |
+
"quiet": 6,
|
| 35 |
+
"sad": 7
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"model_type": "videomae",
|
| 39 |
+
"norm_pix_loss": true,
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_channels": 3,
|
| 42 |
+
"num_frames": 16,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"patch_size": 16,
|
| 45 |
+
"problem_type": "single_label_classification",
|
| 46 |
+
"qkv_bias": true,
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"transformers_version": "4.38.1",
|
| 49 |
+
"tubelet_size": 2,
|
| 50 |
+
"use_mean_pooling": false
|
| 51 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0621591665ef6246ce2adfd4ee62e63c44b34a47afaaa0aca825937fe0236050
|
| 3 |
+
size 344955832
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f054503863c37bce539495bdebbb94328ede0220e09f0bfd657456308e37513
|
| 3 |
+
size 690022458
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_normalize": true,
|
| 8 |
+
"do_rescale": true,
|
| 9 |
+
"do_resize": true,
|
| 10 |
+
"image_mean": [
|
| 11 |
+
0.485,
|
| 12 |
+
0.456,
|
| 13 |
+
0.406
|
| 14 |
+
],
|
| 15 |
+
"image_processor_type": "VideoMAEImageProcessor",
|
| 16 |
+
"image_std": [
|
| 17 |
+
0.229,
|
| 18 |
+
0.224,
|
| 19 |
+
0.225
|
| 20 |
+
],
|
| 21 |
+
"resample": 2,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"shortest_edge": 224
|
| 25 |
+
}
|
| 26 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eab259a586f95f21a54beef8709372bd181d434460ad19104227c63ecbbbde87
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929e339dcc645ea7b93594eb7d40fa276d9868cda045ee046126590d63e5ab79
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1416 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9090909090909091,
|
| 3 |
+
"best_model_checkpoint": "checkpoint-350-4th-march/checkpoint-10",
|
| 4 |
+
"epoch": 89.00555555555556,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"eval_accuracy": 0.7272727272727273,
|
| 14 |
+
"eval_f1": 0.6727272727272727,
|
| 15 |
+
"eval_loss": 0.6355372667312622,
|
| 16 |
+
"eval_precision": 0.6590909090909091,
|
| 17 |
+
"eval_recall": 0.7272727272727273,
|
| 18 |
+
"eval_runtime": 24.4958,
|
| 19 |
+
"eval_samples_per_second": 0.449,
|
| 20 |
+
"eval_steps_per_second": 0.041,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.01,
|
| 25 |
+
"grad_norm": 5.713123321533203,
|
| 26 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 27 |
+
"loss": 0.2306,
|
| 28 |
+
"step": 10
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.01,
|
| 32 |
+
"eval_accuracy": 0.9090909090909091,
|
| 33 |
+
"eval_f1": 0.8787878787878788,
|
| 34 |
+
"eval_loss": 0.5734981894493103,
|
| 35 |
+
"eval_precision": 0.8636363636363636,
|
| 36 |
+
"eval_recall": 0.9090909090909091,
|
| 37 |
+
"eval_runtime": 23.8695,
|
| 38 |
+
"eval_samples_per_second": 0.461,
|
| 39 |
+
"eval_steps_per_second": 0.042,
|
| 40 |
+
"step": 10
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.01,
|
| 44 |
+
"eval_accuracy": 0.8181818181818182,
|
| 45 |
+
"eval_f1": 0.7878787878787878,
|
| 46 |
+
"eval_loss": 0.5388274788856506,
|
| 47 |
+
"eval_precision": 0.7727272727272727,
|
| 48 |
+
"eval_recall": 0.8181818181818182,
|
| 49 |
+
"eval_runtime": 23.9227,
|
| 50 |
+
"eval_samples_per_second": 0.46,
|
| 51 |
+
"eval_steps_per_second": 0.042,
|
| 52 |
+
"step": 15
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.01,
|
| 56 |
+
"grad_norm": 1.6992627382278442,
|
| 57 |
+
"learning_rate": 4.444444444444445e-06,
|
| 58 |
+
"loss": 0.1604,
|
| 59 |
+
"step": 20
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.01,
|
| 63 |
+
"eval_accuracy": 0.8181818181818182,
|
| 64 |
+
"eval_f1": 0.7575757575757577,
|
| 65 |
+
"eval_loss": 0.550200879573822,
|
| 66 |
+
"eval_precision": 0.7272727272727273,
|
| 67 |
+
"eval_recall": 0.8181818181818182,
|
| 68 |
+
"eval_runtime": 24.9639,
|
| 69 |
+
"eval_samples_per_second": 0.441,
|
| 70 |
+
"eval_steps_per_second": 0.04,
|
| 71 |
+
"step": 20
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.01,
|
| 75 |
+
"eval_accuracy": 0.7272727272727273,
|
| 76 |
+
"eval_f1": 0.6727272727272727,
|
| 77 |
+
"eval_loss": 0.6521897912025452,
|
| 78 |
+
"eval_precision": 0.6590909090909091,
|
| 79 |
+
"eval_recall": 0.7272727272727273,
|
| 80 |
+
"eval_runtime": 27.1115,
|
| 81 |
+
"eval_samples_per_second": 0.406,
|
| 82 |
+
"eval_steps_per_second": 0.037,
|
| 83 |
+
"step": 25
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.01,
|
| 87 |
+
"grad_norm": 4.790561199188232,
|
| 88 |
+
"learning_rate": 6.666666666666667e-06,
|
| 89 |
+
"loss": 0.1979,
|
| 90 |
+
"step": 30
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.01,
|
| 94 |
+
"eval_accuracy": 0.7272727272727273,
|
| 95 |
+
"eval_f1": 0.6727272727272727,
|
| 96 |
+
"eval_loss": 0.8280015587806702,
|
| 97 |
+
"eval_precision": 0.6590909090909091,
|
| 98 |
+
"eval_recall": 0.7272727272727273,
|
| 99 |
+
"eval_runtime": 28.3405,
|
| 100 |
+
"eval_samples_per_second": 0.388,
|
| 101 |
+
"eval_steps_per_second": 0.035,
|
| 102 |
+
"step": 30
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 6.01,
|
| 106 |
+
"eval_accuracy": 0.7272727272727273,
|
| 107 |
+
"eval_f1": 0.6727272727272727,
|
| 108 |
+
"eval_loss": 0.6641684174537659,
|
| 109 |
+
"eval_precision": 0.6590909090909091,
|
| 110 |
+
"eval_recall": 0.7272727272727273,
|
| 111 |
+
"eval_runtime": 27.3051,
|
| 112 |
+
"eval_samples_per_second": 0.403,
|
| 113 |
+
"eval_steps_per_second": 0.037,
|
| 114 |
+
"step": 35
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.01,
|
| 118 |
+
"grad_norm": 8.951165199279785,
|
| 119 |
+
"learning_rate": 8.88888888888889e-06,
|
| 120 |
+
"loss": 0.1854,
|
| 121 |
+
"step": 40
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.01,
|
| 125 |
+
"eval_accuracy": 0.8181818181818182,
|
| 126 |
+
"eval_f1": 0.7575757575757577,
|
| 127 |
+
"eval_loss": 0.5681249499320984,
|
| 128 |
+
"eval_precision": 0.7272727272727273,
|
| 129 |
+
"eval_recall": 0.8181818181818182,
|
| 130 |
+
"eval_runtime": 26.9304,
|
| 131 |
+
"eval_samples_per_second": 0.408,
|
| 132 |
+
"eval_steps_per_second": 0.037,
|
| 133 |
+
"step": 40
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 8.01,
|
| 137 |
+
"eval_accuracy": 0.8181818181818182,
|
| 138 |
+
"eval_f1": 0.7727272727272727,
|
| 139 |
+
"eval_loss": 0.5571709275245667,
|
| 140 |
+
"eval_precision": 0.7575757575757577,
|
| 141 |
+
"eval_recall": 0.8181818181818182,
|
| 142 |
+
"eval_runtime": 27.0313,
|
| 143 |
+
"eval_samples_per_second": 0.407,
|
| 144 |
+
"eval_steps_per_second": 0.037,
|
| 145 |
+
"step": 45
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 9.01,
|
| 149 |
+
"grad_norm": 11.677026748657227,
|
| 150 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 151 |
+
"loss": 0.1513,
|
| 152 |
+
"step": 50
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.01,
|
| 156 |
+
"eval_accuracy": 0.7272727272727273,
|
| 157 |
+
"eval_f1": 0.6727272727272727,
|
| 158 |
+
"eval_loss": 0.6411817669868469,
|
| 159 |
+
"eval_precision": 0.6590909090909091,
|
| 160 |
+
"eval_recall": 0.7272727272727273,
|
| 161 |
+
"eval_runtime": 21.8481,
|
| 162 |
+
"eval_samples_per_second": 0.503,
|
| 163 |
+
"eval_steps_per_second": 0.046,
|
| 164 |
+
"step": 50
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.01,
|
| 168 |
+
"eval_accuracy": 0.7272727272727273,
|
| 169 |
+
"eval_f1": 0.6727272727272727,
|
| 170 |
+
"eval_loss": 0.6945109963417053,
|
| 171 |
+
"eval_precision": 0.6590909090909091,
|
| 172 |
+
"eval_recall": 0.7272727272727273,
|
| 173 |
+
"eval_runtime": 20.9102,
|
| 174 |
+
"eval_samples_per_second": 0.526,
|
| 175 |
+
"eval_steps_per_second": 0.048,
|
| 176 |
+
"step": 55
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.01,
|
| 180 |
+
"grad_norm": 4.137542724609375,
|
| 181 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 182 |
+
"loss": 0.1214,
|
| 183 |
+
"step": 60
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 11.01,
|
| 187 |
+
"eval_accuracy": 0.7272727272727273,
|
| 188 |
+
"eval_f1": 0.6515151515151515,
|
| 189 |
+
"eval_loss": 0.7864866852760315,
|
| 190 |
+
"eval_precision": 0.6212121212121212,
|
| 191 |
+
"eval_recall": 0.7272727272727273,
|
| 192 |
+
"eval_runtime": 20.5893,
|
| 193 |
+
"eval_samples_per_second": 0.534,
|
| 194 |
+
"eval_steps_per_second": 0.049,
|
| 195 |
+
"step": 60
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.01,
|
| 199 |
+
"eval_accuracy": 0.7272727272727273,
|
| 200 |
+
"eval_f1": 0.6727272727272727,
|
| 201 |
+
"eval_loss": 0.7256456017494202,
|
| 202 |
+
"eval_precision": 0.6590909090909091,
|
| 203 |
+
"eval_recall": 0.7272727272727273,
|
| 204 |
+
"eval_runtime": 21.3156,
|
| 205 |
+
"eval_samples_per_second": 0.516,
|
| 206 |
+
"eval_steps_per_second": 0.047,
|
| 207 |
+
"step": 65
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 13.01,
|
| 211 |
+
"grad_norm": 3.5624358654022217,
|
| 212 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 213 |
+
"loss": 0.1661,
|
| 214 |
+
"step": 70
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 13.01,
|
| 218 |
+
"eval_accuracy": 0.8181818181818182,
|
| 219 |
+
"eval_f1": 0.7575757575757577,
|
| 220 |
+
"eval_loss": 0.5460242629051208,
|
| 221 |
+
"eval_precision": 0.7272727272727273,
|
| 222 |
+
"eval_recall": 0.8181818181818182,
|
| 223 |
+
"eval_runtime": 21.5745,
|
| 224 |
+
"eval_samples_per_second": 0.51,
|
| 225 |
+
"eval_steps_per_second": 0.046,
|
| 226 |
+
"step": 70
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 14.01,
|
| 230 |
+
"eval_accuracy": 0.8181818181818182,
|
| 231 |
+
"eval_f1": 0.7575757575757577,
|
| 232 |
+
"eval_loss": 0.5317673087120056,
|
| 233 |
+
"eval_precision": 0.7272727272727273,
|
| 234 |
+
"eval_recall": 0.8181818181818182,
|
| 235 |
+
"eval_runtime": 21.1185,
|
| 236 |
+
"eval_samples_per_second": 0.521,
|
| 237 |
+
"eval_steps_per_second": 0.047,
|
| 238 |
+
"step": 75
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 15.01,
|
| 242 |
+
"grad_norm": 1.1072447299957275,
|
| 243 |
+
"learning_rate": 1.777777777777778e-05,
|
| 244 |
+
"loss": 0.1847,
|
| 245 |
+
"step": 80
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 15.01,
|
| 249 |
+
"eval_accuracy": 0.8181818181818182,
|
| 250 |
+
"eval_f1": 0.7727272727272727,
|
| 251 |
+
"eval_loss": 0.5134172439575195,
|
| 252 |
+
"eval_precision": 0.7575757575757577,
|
| 253 |
+
"eval_recall": 0.8181818181818182,
|
| 254 |
+
"eval_runtime": 20.7396,
|
| 255 |
+
"eval_samples_per_second": 0.53,
|
| 256 |
+
"eval_steps_per_second": 0.048,
|
| 257 |
+
"step": 80
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 16.01,
|
| 261 |
+
"eval_accuracy": 0.9090909090909091,
|
| 262 |
+
"eval_f1": 0.8787878787878788,
|
| 263 |
+
"eval_loss": 0.4267767071723938,
|
| 264 |
+
"eval_precision": 0.8636363636363636,
|
| 265 |
+
"eval_recall": 0.9090909090909091,
|
| 266 |
+
"eval_runtime": 20.5432,
|
| 267 |
+
"eval_samples_per_second": 0.535,
|
| 268 |
+
"eval_steps_per_second": 0.049,
|
| 269 |
+
"step": 85
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 17.01,
|
| 273 |
+
"grad_norm": 13.903785705566406,
|
| 274 |
+
"learning_rate": 2e-05,
|
| 275 |
+
"loss": 0.3083,
|
| 276 |
+
"step": 90
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 17.01,
|
| 280 |
+
"eval_accuracy": 0.7272727272727273,
|
| 281 |
+
"eval_f1": 0.6666666666666666,
|
| 282 |
+
"eval_loss": 0.7989960312843323,
|
| 283 |
+
"eval_precision": 0.6363636363636364,
|
| 284 |
+
"eval_recall": 0.7272727272727273,
|
| 285 |
+
"eval_runtime": 20.5742,
|
| 286 |
+
"eval_samples_per_second": 0.535,
|
| 287 |
+
"eval_steps_per_second": 0.049,
|
| 288 |
+
"step": 90
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.01,
|
| 292 |
+
"eval_accuracy": 0.7272727272727273,
|
| 293 |
+
"eval_f1": 0.6666666666666666,
|
| 294 |
+
"eval_loss": 0.8174381256103516,
|
| 295 |
+
"eval_precision": 0.6363636363636364,
|
| 296 |
+
"eval_recall": 0.7272727272727273,
|
| 297 |
+
"eval_runtime": 20.4736,
|
| 298 |
+
"eval_samples_per_second": 0.537,
|
| 299 |
+
"eval_steps_per_second": 0.049,
|
| 300 |
+
"step": 95
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 19.01,
|
| 304 |
+
"grad_norm": 0.5411530137062073,
|
| 305 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 306 |
+
"loss": 0.2193,
|
| 307 |
+
"step": 100
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 19.01,
|
| 311 |
+
"eval_accuracy": 0.7272727272727273,
|
| 312 |
+
"eval_f1": 0.6727272727272727,
|
| 313 |
+
"eval_loss": 0.5629628896713257,
|
| 314 |
+
"eval_precision": 0.6590909090909091,
|
| 315 |
+
"eval_recall": 0.7272727272727273,
|
| 316 |
+
"eval_runtime": 23.091,
|
| 317 |
+
"eval_samples_per_second": 0.476,
|
| 318 |
+
"eval_steps_per_second": 0.043,
|
| 319 |
+
"step": 100
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 20.01,
|
| 323 |
+
"eval_accuracy": 0.8181818181818182,
|
| 324 |
+
"eval_f1": 0.7575757575757577,
|
| 325 |
+
"eval_loss": 0.452359676361084,
|
| 326 |
+
"eval_precision": 0.7272727272727273,
|
| 327 |
+
"eval_recall": 0.8181818181818182,
|
| 328 |
+
"eval_runtime": 22.8931,
|
| 329 |
+
"eval_samples_per_second": 0.48,
|
| 330 |
+
"eval_steps_per_second": 0.044,
|
| 331 |
+
"step": 105
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 21.01,
|
| 335 |
+
"grad_norm": 6.751333713531494,
|
| 336 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 337 |
+
"loss": 0.1367,
|
| 338 |
+
"step": 110
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 21.01,
|
| 342 |
+
"eval_accuracy": 0.8181818181818182,
|
| 343 |
+
"eval_f1": 0.7575757575757577,
|
| 344 |
+
"eval_loss": 0.588365375995636,
|
| 345 |
+
"eval_precision": 0.7272727272727273,
|
| 346 |
+
"eval_recall": 0.8181818181818182,
|
| 347 |
+
"eval_runtime": 22.2164,
|
| 348 |
+
"eval_samples_per_second": 0.495,
|
| 349 |
+
"eval_steps_per_second": 0.045,
|
| 350 |
+
"step": 110
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 22.01,
|
| 354 |
+
"eval_accuracy": 0.7272727272727273,
|
| 355 |
+
"eval_f1": 0.6818181818181818,
|
| 356 |
+
"eval_loss": 0.6520605683326721,
|
| 357 |
+
"eval_precision": 0.6666666666666666,
|
| 358 |
+
"eval_recall": 0.7272727272727273,
|
| 359 |
+
"eval_runtime": 21.6145,
|
| 360 |
+
"eval_samples_per_second": 0.509,
|
| 361 |
+
"eval_steps_per_second": 0.046,
|
| 362 |
+
"step": 115
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 23.01,
|
| 366 |
+
"grad_norm": 2.2240047454833984,
|
| 367 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 368 |
+
"loss": 0.1478,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 23.01,
|
| 373 |
+
"eval_accuracy": 0.8181818181818182,
|
| 374 |
+
"eval_f1": 0.7575757575757577,
|
| 375 |
+
"eval_loss": 0.550651490688324,
|
| 376 |
+
"eval_precision": 0.7272727272727273,
|
| 377 |
+
"eval_recall": 0.8181818181818182,
|
| 378 |
+
"eval_runtime": 22.2994,
|
| 379 |
+
"eval_samples_per_second": 0.493,
|
| 380 |
+
"eval_steps_per_second": 0.045,
|
| 381 |
+
"step": 120
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 24.01,
|
| 385 |
+
"eval_accuracy": 0.8181818181818182,
|
| 386 |
+
"eval_f1": 0.7727272727272727,
|
| 387 |
+
"eval_loss": 0.5914822220802307,
|
| 388 |
+
"eval_precision": 0.7575757575757577,
|
| 389 |
+
"eval_recall": 0.8181818181818182,
|
| 390 |
+
"eval_runtime": 22.4716,
|
| 391 |
+
"eval_samples_per_second": 0.49,
|
| 392 |
+
"eval_steps_per_second": 0.045,
|
| 393 |
+
"step": 125
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 25.01,
|
| 397 |
+
"grad_norm": 2.0005195140838623,
|
| 398 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 399 |
+
"loss": 0.173,
|
| 400 |
+
"step": 130
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.01,
|
| 404 |
+
"eval_accuracy": 0.9090909090909091,
|
| 405 |
+
"eval_f1": 0.8787878787878788,
|
| 406 |
+
"eval_loss": 0.36792269349098206,
|
| 407 |
+
"eval_precision": 0.8636363636363636,
|
| 408 |
+
"eval_recall": 0.9090909090909091,
|
| 409 |
+
"eval_runtime": 22.1546,
|
| 410 |
+
"eval_samples_per_second": 0.497,
|
| 411 |
+
"eval_steps_per_second": 0.045,
|
| 412 |
+
"step": 130
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 26.01,
|
| 416 |
+
"eval_accuracy": 0.8181818181818182,
|
| 417 |
+
"eval_f1": 0.7878787878787878,
|
| 418 |
+
"eval_loss": 0.3868860900402069,
|
| 419 |
+
"eval_precision": 0.7727272727272727,
|
| 420 |
+
"eval_recall": 0.8181818181818182,
|
| 421 |
+
"eval_runtime": 21.2578,
|
| 422 |
+
"eval_samples_per_second": 0.517,
|
| 423 |
+
"eval_steps_per_second": 0.047,
|
| 424 |
+
"step": 135
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 27.01,
|
| 428 |
+
"grad_norm": 7.4427385330200195,
|
| 429 |
+
"learning_rate": 3.111111111111111e-05,
|
| 430 |
+
"loss": 0.2515,
|
| 431 |
+
"step": 140
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 27.01,
|
| 435 |
+
"eval_accuracy": 0.7272727272727273,
|
| 436 |
+
"eval_f1": 0.696969696969697,
|
| 437 |
+
"eval_loss": 0.4347504675388336,
|
| 438 |
+
"eval_precision": 0.6818181818181818,
|
| 439 |
+
"eval_recall": 0.7272727272727273,
|
| 440 |
+
"eval_runtime": 23.2343,
|
| 441 |
+
"eval_samples_per_second": 0.473,
|
| 442 |
+
"eval_steps_per_second": 0.043,
|
| 443 |
+
"step": 140
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 28.01,
|
| 447 |
+
"eval_accuracy": 0.8181818181818182,
|
| 448 |
+
"eval_f1": 0.7727272727272727,
|
| 449 |
+
"eval_loss": 0.5722665786743164,
|
| 450 |
+
"eval_precision": 0.7575757575757577,
|
| 451 |
+
"eval_recall": 0.8181818181818182,
|
| 452 |
+
"eval_runtime": 20.9817,
|
| 453 |
+
"eval_samples_per_second": 0.524,
|
| 454 |
+
"eval_steps_per_second": 0.048,
|
| 455 |
+
"step": 145
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 29.01,
|
| 459 |
+
"grad_norm": 3.472019672393799,
|
| 460 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 461 |
+
"loss": 0.1947,
|
| 462 |
+
"step": 150
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 29.01,
|
| 466 |
+
"eval_accuracy": 0.7272727272727273,
|
| 467 |
+
"eval_f1": 0.6727272727272727,
|
| 468 |
+
"eval_loss": 0.824672520160675,
|
| 469 |
+
"eval_precision": 0.6590909090909091,
|
| 470 |
+
"eval_recall": 0.7272727272727273,
|
| 471 |
+
"eval_runtime": 20.2976,
|
| 472 |
+
"eval_samples_per_second": 0.542,
|
| 473 |
+
"eval_steps_per_second": 0.049,
|
| 474 |
+
"step": 150
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 30.01,
|
| 478 |
+
"eval_accuracy": 0.8181818181818182,
|
| 479 |
+
"eval_f1": 0.7575757575757577,
|
| 480 |
+
"eval_loss": 0.4699678421020508,
|
| 481 |
+
"eval_precision": 0.7272727272727273,
|
| 482 |
+
"eval_recall": 0.8181818181818182,
|
| 483 |
+
"eval_runtime": 19.7939,
|
| 484 |
+
"eval_samples_per_second": 0.556,
|
| 485 |
+
"eval_steps_per_second": 0.051,
|
| 486 |
+
"step": 155
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 31.01,
|
| 490 |
+
"grad_norm": 8.735132217407227,
|
| 491 |
+
"learning_rate": 3.555555555555556e-05,
|
| 492 |
+
"loss": 0.1871,
|
| 493 |
+
"step": 160
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 31.01,
|
| 497 |
+
"eval_accuracy": 0.7272727272727273,
|
| 498 |
+
"eval_f1": 0.6515151515151515,
|
| 499 |
+
"eval_loss": 0.6745826601982117,
|
| 500 |
+
"eval_precision": 0.6212121212121212,
|
| 501 |
+
"eval_recall": 0.7272727272727273,
|
| 502 |
+
"eval_runtime": 21.2096,
|
| 503 |
+
"eval_samples_per_second": 0.519,
|
| 504 |
+
"eval_steps_per_second": 0.047,
|
| 505 |
+
"step": 160
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 32.01,
|
| 509 |
+
"eval_accuracy": 0.7272727272727273,
|
| 510 |
+
"eval_f1": 0.6454545454545454,
|
| 511 |
+
"eval_loss": 1.3604460954666138,
|
| 512 |
+
"eval_precision": 0.606060606060606,
|
| 513 |
+
"eval_recall": 0.7272727272727273,
|
| 514 |
+
"eval_runtime": 20.7259,
|
| 515 |
+
"eval_samples_per_second": 0.531,
|
| 516 |
+
"eval_steps_per_second": 0.048,
|
| 517 |
+
"step": 165
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 33.01,
|
| 521 |
+
"grad_norm": 1.2702025175094604,
|
| 522 |
+
"learning_rate": 3.777777777777778e-05,
|
| 523 |
+
"loss": 0.1651,
|
| 524 |
+
"step": 170
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 33.01,
|
| 528 |
+
"eval_accuracy": 0.7272727272727273,
|
| 529 |
+
"eval_f1": 0.6666666666666666,
|
| 530 |
+
"eval_loss": 0.786778450012207,
|
| 531 |
+
"eval_precision": 0.6363636363636364,
|
| 532 |
+
"eval_recall": 0.7272727272727273,
|
| 533 |
+
"eval_runtime": 22.3289,
|
| 534 |
+
"eval_samples_per_second": 0.493,
|
| 535 |
+
"eval_steps_per_second": 0.045,
|
| 536 |
+
"step": 170
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 34.01,
|
| 540 |
+
"eval_accuracy": 0.8181818181818182,
|
| 541 |
+
"eval_f1": 0.7575757575757577,
|
| 542 |
+
"eval_loss": 0.7492481470108032,
|
| 543 |
+
"eval_precision": 0.7272727272727273,
|
| 544 |
+
"eval_recall": 0.8181818181818182,
|
| 545 |
+
"eval_runtime": 20.2554,
|
| 546 |
+
"eval_samples_per_second": 0.543,
|
| 547 |
+
"eval_steps_per_second": 0.049,
|
| 548 |
+
"step": 175
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 35.01,
|
| 552 |
+
"grad_norm": 1.1660475730895996,
|
| 553 |
+
"learning_rate": 4e-05,
|
| 554 |
+
"loss": 0.1621,
|
| 555 |
+
"step": 180
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 35.01,
|
| 559 |
+
"eval_accuracy": 0.7272727272727273,
|
| 560 |
+
"eval_f1": 0.6727272727272727,
|
| 561 |
+
"eval_loss": 0.707514762878418,
|
| 562 |
+
"eval_precision": 0.6590909090909091,
|
| 563 |
+
"eval_recall": 0.7272727272727273,
|
| 564 |
+
"eval_runtime": 20.9293,
|
| 565 |
+
"eval_samples_per_second": 0.526,
|
| 566 |
+
"eval_steps_per_second": 0.048,
|
| 567 |
+
"step": 180
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 36.01,
|
| 571 |
+
"eval_accuracy": 0.8181818181818182,
|
| 572 |
+
"eval_f1": 0.7727272727272727,
|
| 573 |
+
"eval_loss": 0.5149413347244263,
|
| 574 |
+
"eval_precision": 0.7575757575757577,
|
| 575 |
+
"eval_recall": 0.8181818181818182,
|
| 576 |
+
"eval_runtime": 20.6993,
|
| 577 |
+
"eval_samples_per_second": 0.531,
|
| 578 |
+
"eval_steps_per_second": 0.048,
|
| 579 |
+
"step": 185
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 37.01,
|
| 583 |
+
"grad_norm": 2.7489700317382812,
|
| 584 |
+
"learning_rate": 4.222222222222222e-05,
|
| 585 |
+
"loss": 0.094,
|
| 586 |
+
"step": 190
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 37.01,
|
| 590 |
+
"eval_accuracy": 0.8181818181818182,
|
| 591 |
+
"eval_f1": 0.7575757575757577,
|
| 592 |
+
"eval_loss": 0.6731873750686646,
|
| 593 |
+
"eval_precision": 0.7272727272727273,
|
| 594 |
+
"eval_recall": 0.8181818181818182,
|
| 595 |
+
"eval_runtime": 19.5579,
|
| 596 |
+
"eval_samples_per_second": 0.562,
|
| 597 |
+
"eval_steps_per_second": 0.051,
|
| 598 |
+
"step": 190
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 38.01,
|
| 602 |
+
"eval_accuracy": 0.8181818181818182,
|
| 603 |
+
"eval_f1": 0.7575757575757577,
|
| 604 |
+
"eval_loss": 0.7046161890029907,
|
| 605 |
+
"eval_precision": 0.7272727272727273,
|
| 606 |
+
"eval_recall": 0.8181818181818182,
|
| 607 |
+
"eval_runtime": 20.2638,
|
| 608 |
+
"eval_samples_per_second": 0.543,
|
| 609 |
+
"eval_steps_per_second": 0.049,
|
| 610 |
+
"step": 195
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 39.01,
|
| 614 |
+
"grad_norm": 3.9047691822052,
|
| 615 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 616 |
+
"loss": 0.1494,
|
| 617 |
+
"step": 200
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 39.01,
|
| 621 |
+
"eval_accuracy": 0.8181818181818182,
|
| 622 |
+
"eval_f1": 0.7727272727272727,
|
| 623 |
+
"eval_loss": 0.667763888835907,
|
| 624 |
+
"eval_precision": 0.7575757575757577,
|
| 625 |
+
"eval_recall": 0.8181818181818182,
|
| 626 |
+
"eval_runtime": 21.6759,
|
| 627 |
+
"eval_samples_per_second": 0.507,
|
| 628 |
+
"eval_steps_per_second": 0.046,
|
| 629 |
+
"step": 200
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 40.01,
|
| 633 |
+
"eval_accuracy": 0.8181818181818182,
|
| 634 |
+
"eval_f1": 0.8181818181818182,
|
| 635 |
+
"eval_loss": 0.4195019602775574,
|
| 636 |
+
"eval_precision": 0.8181818181818182,
|
| 637 |
+
"eval_recall": 0.8181818181818182,
|
| 638 |
+
"eval_runtime": 21.8447,
|
| 639 |
+
"eval_samples_per_second": 0.504,
|
| 640 |
+
"eval_steps_per_second": 0.046,
|
| 641 |
+
"step": 205
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 41.01,
|
| 645 |
+
"grad_norm": 20.463916778564453,
|
| 646 |
+
"learning_rate": 4.666666666666667e-05,
|
| 647 |
+
"loss": 0.1819,
|
| 648 |
+
"step": 210
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 41.01,
|
| 652 |
+
"eval_accuracy": 0.8181818181818182,
|
| 653 |
+
"eval_f1": 0.7575757575757577,
|
| 654 |
+
"eval_loss": 0.48133182525634766,
|
| 655 |
+
"eval_precision": 0.7272727272727273,
|
| 656 |
+
"eval_recall": 0.8181818181818182,
|
| 657 |
+
"eval_runtime": 20.7381,
|
| 658 |
+
"eval_samples_per_second": 0.53,
|
| 659 |
+
"eval_steps_per_second": 0.048,
|
| 660 |
+
"step": 210
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 42.01,
|
| 664 |
+
"eval_accuracy": 0.6363636363636364,
|
| 665 |
+
"eval_f1": 0.5757575757575758,
|
| 666 |
+
"eval_loss": 1.2362233400344849,
|
| 667 |
+
"eval_precision": 0.5984848484848485,
|
| 668 |
+
"eval_recall": 0.6363636363636364,
|
| 669 |
+
"eval_runtime": 20.9607,
|
| 670 |
+
"eval_samples_per_second": 0.525,
|
| 671 |
+
"eval_steps_per_second": 0.048,
|
| 672 |
+
"step": 215
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 43.01,
|
| 676 |
+
"grad_norm": 20.663036346435547,
|
| 677 |
+
"learning_rate": 4.888888888888889e-05,
|
| 678 |
+
"loss": 0.3123,
|
| 679 |
+
"step": 220
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 43.01,
|
| 683 |
+
"eval_accuracy": 0.6363636363636364,
|
| 684 |
+
"eval_f1": 0.5848484848484848,
|
| 685 |
+
"eval_loss": 1.2863417863845825,
|
| 686 |
+
"eval_precision": 0.606060606060606,
|
| 687 |
+
"eval_recall": 0.6363636363636364,
|
| 688 |
+
"eval_runtime": 24.9545,
|
| 689 |
+
"eval_samples_per_second": 0.441,
|
| 690 |
+
"eval_steps_per_second": 0.04,
|
| 691 |
+
"step": 220
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 44.01,
|
| 695 |
+
"eval_accuracy": 0.6363636363636364,
|
| 696 |
+
"eval_f1": 0.5696969696969697,
|
| 697 |
+
"eval_loss": 1.4153846502304077,
|
| 698 |
+
"eval_precision": 0.5757575757575757,
|
| 699 |
+
"eval_recall": 0.6363636363636364,
|
| 700 |
+
"eval_runtime": 21.2069,
|
| 701 |
+
"eval_samples_per_second": 0.519,
|
| 702 |
+
"eval_steps_per_second": 0.047,
|
| 703 |
+
"step": 225
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 45.01,
|
| 707 |
+
"grad_norm": 11.3672456741333,
|
| 708 |
+
"learning_rate": 4.962962962962963e-05,
|
| 709 |
+
"loss": 0.3182,
|
| 710 |
+
"step": 230
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 45.01,
|
| 714 |
+
"eval_accuracy": 0.7272727272727273,
|
| 715 |
+
"eval_f1": 0.6818181818181818,
|
| 716 |
+
"eval_loss": 0.6307955384254456,
|
| 717 |
+
"eval_precision": 0.6666666666666666,
|
| 718 |
+
"eval_recall": 0.7272727272727273,
|
| 719 |
+
"eval_runtime": 20.1678,
|
| 720 |
+
"eval_samples_per_second": 0.545,
|
| 721 |
+
"eval_steps_per_second": 0.05,
|
| 722 |
+
"step": 230
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 46.01,
|
| 726 |
+
"eval_accuracy": 0.8181818181818182,
|
| 727 |
+
"eval_f1": 0.7575757575757577,
|
| 728 |
+
"eval_loss": 0.4325122535228729,
|
| 729 |
+
"eval_precision": 0.7272727272727273,
|
| 730 |
+
"eval_recall": 0.8181818181818182,
|
| 731 |
+
"eval_runtime": 21.2567,
|
| 732 |
+
"eval_samples_per_second": 0.517,
|
| 733 |
+
"eval_steps_per_second": 0.047,
|
| 734 |
+
"step": 235
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 47.01,
|
| 738 |
+
"grad_norm": 17.50649642944336,
|
| 739 |
+
"learning_rate": 4.888888888888889e-05,
|
| 740 |
+
"loss": 0.1992,
|
| 741 |
+
"step": 240
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 47.01,
|
| 745 |
+
"eval_accuracy": 0.9090909090909091,
|
| 746 |
+
"eval_f1": 0.8787878787878788,
|
| 747 |
+
"eval_loss": 0.42543408274650574,
|
| 748 |
+
"eval_precision": 0.8636363636363636,
|
| 749 |
+
"eval_recall": 0.9090909090909091,
|
| 750 |
+
"eval_runtime": 20.0391,
|
| 751 |
+
"eval_samples_per_second": 0.549,
|
| 752 |
+
"eval_steps_per_second": 0.05,
|
| 753 |
+
"step": 240
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 48.01,
|
| 757 |
+
"eval_accuracy": 0.8181818181818182,
|
| 758 |
+
"eval_f1": 0.7818181818181817,
|
| 759 |
+
"eval_loss": 0.5966838598251343,
|
| 760 |
+
"eval_precision": 0.8030303030303029,
|
| 761 |
+
"eval_recall": 0.8181818181818182,
|
| 762 |
+
"eval_runtime": 20.4865,
|
| 763 |
+
"eval_samples_per_second": 0.537,
|
| 764 |
+
"eval_steps_per_second": 0.049,
|
| 765 |
+
"step": 245
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 49.01,
|
| 769 |
+
"grad_norm": 10.43728256225586,
|
| 770 |
+
"learning_rate": 4.814814814814815e-05,
|
| 771 |
+
"loss": 0.1887,
|
| 772 |
+
"step": 250
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 49.01,
|
| 776 |
+
"eval_accuracy": 0.9090909090909091,
|
| 777 |
+
"eval_f1": 0.8787878787878788,
|
| 778 |
+
"eval_loss": 0.4350906312465668,
|
| 779 |
+
"eval_precision": 0.8636363636363636,
|
| 780 |
+
"eval_recall": 0.9090909090909091,
|
| 781 |
+
"eval_runtime": 20.3501,
|
| 782 |
+
"eval_samples_per_second": 0.541,
|
| 783 |
+
"eval_steps_per_second": 0.049,
|
| 784 |
+
"step": 250
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 50.01,
|
| 788 |
+
"eval_accuracy": 0.8181818181818182,
|
| 789 |
+
"eval_f1": 0.8181818181818182,
|
| 790 |
+
"eval_loss": 0.5225472450256348,
|
| 791 |
+
"eval_precision": 0.8181818181818182,
|
| 792 |
+
"eval_recall": 0.8181818181818182,
|
| 793 |
+
"eval_runtime": 20.4273,
|
| 794 |
+
"eval_samples_per_second": 0.538,
|
| 795 |
+
"eval_steps_per_second": 0.049,
|
| 796 |
+
"step": 255
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 51.01,
|
| 800 |
+
"grad_norm": 11.036069869995117,
|
| 801 |
+
"learning_rate": 4.740740740740741e-05,
|
| 802 |
+
"loss": 0.2046,
|
| 803 |
+
"step": 260
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 51.01,
|
| 807 |
+
"eval_accuracy": 0.7272727272727273,
|
| 808 |
+
"eval_f1": 0.6818181818181818,
|
| 809 |
+
"eval_loss": 0.6759114861488342,
|
| 810 |
+
"eval_precision": 0.6666666666666667,
|
| 811 |
+
"eval_recall": 0.7272727272727273,
|
| 812 |
+
"eval_runtime": 20.7436,
|
| 813 |
+
"eval_samples_per_second": 0.53,
|
| 814 |
+
"eval_steps_per_second": 0.048,
|
| 815 |
+
"step": 260
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 52.01,
|
| 819 |
+
"eval_accuracy": 0.8181818181818182,
|
| 820 |
+
"eval_f1": 0.7575757575757577,
|
| 821 |
+
"eval_loss": 0.5574895739555359,
|
| 822 |
+
"eval_precision": 0.7272727272727273,
|
| 823 |
+
"eval_recall": 0.8181818181818182,
|
| 824 |
+
"eval_runtime": 20.5552,
|
| 825 |
+
"eval_samples_per_second": 0.535,
|
| 826 |
+
"eval_steps_per_second": 0.049,
|
| 827 |
+
"step": 265
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 53.01,
|
| 831 |
+
"grad_norm": 9.632101058959961,
|
| 832 |
+
"learning_rate": 4.666666666666667e-05,
|
| 833 |
+
"loss": 0.2225,
|
| 834 |
+
"step": 270
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 53.01,
|
| 838 |
+
"eval_accuracy": 0.6363636363636364,
|
| 839 |
+
"eval_f1": 0.5281385281385281,
|
| 840 |
+
"eval_loss": 1.1722840070724487,
|
| 841 |
+
"eval_precision": 0.4818181818181818,
|
| 842 |
+
"eval_recall": 0.6363636363636364,
|
| 843 |
+
"eval_runtime": 25.8215,
|
| 844 |
+
"eval_samples_per_second": 0.426,
|
| 845 |
+
"eval_steps_per_second": 0.039,
|
| 846 |
+
"step": 270
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 54.01,
|
| 850 |
+
"eval_accuracy": 0.7272727272727273,
|
| 851 |
+
"eval_f1": 0.6818181818181818,
|
| 852 |
+
"eval_loss": 0.9067409634590149,
|
| 853 |
+
"eval_precision": 0.6666666666666666,
|
| 854 |
+
"eval_recall": 0.7272727272727273,
|
| 855 |
+
"eval_runtime": 21.6949,
|
| 856 |
+
"eval_samples_per_second": 0.507,
|
| 857 |
+
"eval_steps_per_second": 0.046,
|
| 858 |
+
"step": 275
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 55.01,
|
| 862 |
+
"grad_norm": 18.024147033691406,
|
| 863 |
+
"learning_rate": 4.592592592592593e-05,
|
| 864 |
+
"loss": 0.2867,
|
| 865 |
+
"step": 280
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 55.01,
|
| 869 |
+
"eval_accuracy": 0.9090909090909091,
|
| 870 |
+
"eval_f1": 0.8787878787878788,
|
| 871 |
+
"eval_loss": 0.29047486186027527,
|
| 872 |
+
"eval_precision": 0.8636363636363636,
|
| 873 |
+
"eval_recall": 0.9090909090909091,
|
| 874 |
+
"eval_runtime": 20.839,
|
| 875 |
+
"eval_samples_per_second": 0.528,
|
| 876 |
+
"eval_steps_per_second": 0.048,
|
| 877 |
+
"step": 280
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 56.01,
|
| 881 |
+
"eval_accuracy": 0.7272727272727273,
|
| 882 |
+
"eval_f1": 0.696969696969697,
|
| 883 |
+
"eval_loss": 0.6336184144020081,
|
| 884 |
+
"eval_precision": 0.6818181818181818,
|
| 885 |
+
"eval_recall": 0.7272727272727273,
|
| 886 |
+
"eval_runtime": 22.0174,
|
| 887 |
+
"eval_samples_per_second": 0.5,
|
| 888 |
+
"eval_steps_per_second": 0.045,
|
| 889 |
+
"step": 285
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 57.01,
|
| 893 |
+
"grad_norm": 1.8721508979797363,
|
| 894 |
+
"learning_rate": 4.518518518518519e-05,
|
| 895 |
+
"loss": 0.2137,
|
| 896 |
+
"step": 290
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 57.01,
|
| 900 |
+
"eval_accuracy": 0.8181818181818182,
|
| 901 |
+
"eval_f1": 0.7575757575757577,
|
| 902 |
+
"eval_loss": 0.5004566311836243,
|
| 903 |
+
"eval_precision": 0.7272727272727273,
|
| 904 |
+
"eval_recall": 0.8181818181818182,
|
| 905 |
+
"eval_runtime": 22.896,
|
| 906 |
+
"eval_samples_per_second": 0.48,
|
| 907 |
+
"eval_steps_per_second": 0.044,
|
| 908 |
+
"step": 290
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 58.01,
|
| 912 |
+
"eval_accuracy": 0.8181818181818182,
|
| 913 |
+
"eval_f1": 0.7575757575757577,
|
| 914 |
+
"eval_loss": 0.4470617175102234,
|
| 915 |
+
"eval_precision": 0.7272727272727273,
|
| 916 |
+
"eval_recall": 0.8181818181818182,
|
| 917 |
+
"eval_runtime": 20.6595,
|
| 918 |
+
"eval_samples_per_second": 0.532,
|
| 919 |
+
"eval_steps_per_second": 0.048,
|
| 920 |
+
"step": 295
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 59.01,
|
| 924 |
+
"grad_norm": 1.4810432195663452,
|
| 925 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 926 |
+
"loss": 0.2609,
|
| 927 |
+
"step": 300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 59.01,
|
| 931 |
+
"eval_accuracy": 0.7272727272727273,
|
| 932 |
+
"eval_f1": 0.696969696969697,
|
| 933 |
+
"eval_loss": 0.5465022921562195,
|
| 934 |
+
"eval_precision": 0.6818181818181818,
|
| 935 |
+
"eval_recall": 0.7272727272727273,
|
| 936 |
+
"eval_runtime": 20.8964,
|
| 937 |
+
"eval_samples_per_second": 0.526,
|
| 938 |
+
"eval_steps_per_second": 0.048,
|
| 939 |
+
"step": 300
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 60.01,
|
| 943 |
+
"eval_accuracy": 0.7272727272727273,
|
| 944 |
+
"eval_f1": 0.696969696969697,
|
| 945 |
+
"eval_loss": 0.5460771918296814,
|
| 946 |
+
"eval_precision": 0.6818181818181818,
|
| 947 |
+
"eval_recall": 0.7272727272727273,
|
| 948 |
+
"eval_runtime": 19.8782,
|
| 949 |
+
"eval_samples_per_second": 0.553,
|
| 950 |
+
"eval_steps_per_second": 0.05,
|
| 951 |
+
"step": 305
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 61.01,
|
| 955 |
+
"grad_norm": 10.204845428466797,
|
| 956 |
+
"learning_rate": 4.3703703703703705e-05,
|
| 957 |
+
"loss": 0.1033,
|
| 958 |
+
"step": 310
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 61.01,
|
| 962 |
+
"eval_accuracy": 0.8181818181818182,
|
| 963 |
+
"eval_f1": 0.7727272727272727,
|
| 964 |
+
"eval_loss": 0.46728765964508057,
|
| 965 |
+
"eval_precision": 0.7575757575757577,
|
| 966 |
+
"eval_recall": 0.8181818181818182,
|
| 967 |
+
"eval_runtime": 20.0013,
|
| 968 |
+
"eval_samples_per_second": 0.55,
|
| 969 |
+
"eval_steps_per_second": 0.05,
|
| 970 |
+
"step": 310
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 62.01,
|
| 974 |
+
"eval_accuracy": 0.8181818181818182,
|
| 975 |
+
"eval_f1": 0.7727272727272727,
|
| 976 |
+
"eval_loss": 0.6281985640525818,
|
| 977 |
+
"eval_precision": 0.7575757575757577,
|
| 978 |
+
"eval_recall": 0.8181818181818182,
|
| 979 |
+
"eval_runtime": 20.7864,
|
| 980 |
+
"eval_samples_per_second": 0.529,
|
| 981 |
+
"eval_steps_per_second": 0.048,
|
| 982 |
+
"step": 315
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 63.01,
|
| 986 |
+
"grad_norm": 3.3419110774993896,
|
| 987 |
+
"learning_rate": 4.296296296296296e-05,
|
| 988 |
+
"loss": 0.2027,
|
| 989 |
+
"step": 320
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 63.01,
|
| 993 |
+
"eval_accuracy": 0.6363636363636364,
|
| 994 |
+
"eval_f1": 0.5848484848484848,
|
| 995 |
+
"eval_loss": 1.3454620838165283,
|
| 996 |
+
"eval_precision": 0.606060606060606,
|
| 997 |
+
"eval_recall": 0.6363636363636364,
|
| 998 |
+
"eval_runtime": 20.7754,
|
| 999 |
+
"eval_samples_per_second": 0.529,
|
| 1000 |
+
"eval_steps_per_second": 0.048,
|
| 1001 |
+
"step": 320
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 64.01,
|
| 1005 |
+
"eval_accuracy": 0.6363636363636364,
|
| 1006 |
+
"eval_f1": 0.5848484848484848,
|
| 1007 |
+
"eval_loss": 1.2102134227752686,
|
| 1008 |
+
"eval_precision": 0.606060606060606,
|
| 1009 |
+
"eval_recall": 0.6363636363636364,
|
| 1010 |
+
"eval_runtime": 20.3871,
|
| 1011 |
+
"eval_samples_per_second": 0.54,
|
| 1012 |
+
"eval_steps_per_second": 0.049,
|
| 1013 |
+
"step": 325
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 65.01,
|
| 1017 |
+
"grad_norm": 6.031401634216309,
|
| 1018 |
+
"learning_rate": 4.222222222222222e-05,
|
| 1019 |
+
"loss": 0.2333,
|
| 1020 |
+
"step": 330
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 65.01,
|
| 1024 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1025 |
+
"eval_f1": 0.6606060606060606,
|
| 1026 |
+
"eval_loss": 0.8988341689109802,
|
| 1027 |
+
"eval_precision": 0.6666666666666666,
|
| 1028 |
+
"eval_recall": 0.7272727272727273,
|
| 1029 |
+
"eval_runtime": 19.8751,
|
| 1030 |
+
"eval_samples_per_second": 0.553,
|
| 1031 |
+
"eval_steps_per_second": 0.05,
|
| 1032 |
+
"step": 330
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 66.01,
|
| 1036 |
+
"eval_accuracy": 0.6363636363636364,
|
| 1037 |
+
"eval_f1": 0.5757575757575758,
|
| 1038 |
+
"eval_loss": 1.21355140209198,
|
| 1039 |
+
"eval_precision": 0.5984848484848485,
|
| 1040 |
+
"eval_recall": 0.6363636363636364,
|
| 1041 |
+
"eval_runtime": 21.2698,
|
| 1042 |
+
"eval_samples_per_second": 0.517,
|
| 1043 |
+
"eval_steps_per_second": 0.047,
|
| 1044 |
+
"step": 335
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 67.01,
|
| 1048 |
+
"grad_norm": 1.2481231689453125,
|
| 1049 |
+
"learning_rate": 4.148148148148148e-05,
|
| 1050 |
+
"loss": 0.2014,
|
| 1051 |
+
"step": 340
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 67.01,
|
| 1055 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1056 |
+
"eval_f1": 0.7727272727272727,
|
| 1057 |
+
"eval_loss": 0.7183884978294373,
|
| 1058 |
+
"eval_precision": 0.7575757575757577,
|
| 1059 |
+
"eval_recall": 0.8181818181818182,
|
| 1060 |
+
"eval_runtime": 20.3008,
|
| 1061 |
+
"eval_samples_per_second": 0.542,
|
| 1062 |
+
"eval_steps_per_second": 0.049,
|
| 1063 |
+
"step": 340
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 68.01,
|
| 1067 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1068 |
+
"eval_f1": 0.7878787878787878,
|
| 1069 |
+
"eval_loss": 0.5583562254905701,
|
| 1070 |
+
"eval_precision": 0.7727272727272727,
|
| 1071 |
+
"eval_recall": 0.8181818181818182,
|
| 1072 |
+
"eval_runtime": 22.3248,
|
| 1073 |
+
"eval_samples_per_second": 0.493,
|
| 1074 |
+
"eval_steps_per_second": 0.045,
|
| 1075 |
+
"step": 345
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 69.01,
|
| 1079 |
+
"grad_norm": 1.0424888134002686,
|
| 1080 |
+
"learning_rate": 4.074074074074074e-05,
|
| 1081 |
+
"loss": 0.1532,
|
| 1082 |
+
"step": 350
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 69.01,
|
| 1086 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1087 |
+
"eval_f1": 0.6666666666666666,
|
| 1088 |
+
"eval_loss": 0.9030601382255554,
|
| 1089 |
+
"eval_precision": 0.6363636363636364,
|
| 1090 |
+
"eval_recall": 0.7272727272727273,
|
| 1091 |
+
"eval_runtime": 21.9747,
|
| 1092 |
+
"eval_samples_per_second": 0.501,
|
| 1093 |
+
"eval_steps_per_second": 0.046,
|
| 1094 |
+
"step": 350
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 70.01,
|
| 1098 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1099 |
+
"eval_f1": 0.6515151515151515,
|
| 1100 |
+
"eval_loss": 1.1362484693527222,
|
| 1101 |
+
"eval_precision": 0.6212121212121212,
|
| 1102 |
+
"eval_recall": 0.7272727272727273,
|
| 1103 |
+
"eval_runtime": 21.0027,
|
| 1104 |
+
"eval_samples_per_second": 0.524,
|
| 1105 |
+
"eval_steps_per_second": 0.048,
|
| 1106 |
+
"step": 355
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 71.01,
|
| 1110 |
+
"grad_norm": 13.485044479370117,
|
| 1111 |
+
"learning_rate": 4e-05,
|
| 1112 |
+
"loss": 0.1102,
|
| 1113 |
+
"step": 360
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 71.01,
|
| 1117 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1118 |
+
"eval_f1": 0.6969696969696969,
|
| 1119 |
+
"eval_loss": 0.8755394220352173,
|
| 1120 |
+
"eval_precision": 0.6818181818181818,
|
| 1121 |
+
"eval_recall": 0.7272727272727273,
|
| 1122 |
+
"eval_runtime": 20.8601,
|
| 1123 |
+
"eval_samples_per_second": 0.527,
|
| 1124 |
+
"eval_steps_per_second": 0.048,
|
| 1125 |
+
"step": 360
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 72.01,
|
| 1129 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1130 |
+
"eval_f1": 0.7878787878787878,
|
| 1131 |
+
"eval_loss": 0.7721637487411499,
|
| 1132 |
+
"eval_precision": 0.7727272727272727,
|
| 1133 |
+
"eval_recall": 0.8181818181818182,
|
| 1134 |
+
"eval_runtime": 20.6398,
|
| 1135 |
+
"eval_samples_per_second": 0.533,
|
| 1136 |
+
"eval_steps_per_second": 0.048,
|
| 1137 |
+
"step": 365
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 73.01,
|
| 1141 |
+
"grad_norm": 20.92743492126465,
|
| 1142 |
+
"learning_rate": 3.925925925925926e-05,
|
| 1143 |
+
"loss": 0.2666,
|
| 1144 |
+
"step": 370
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 73.01,
|
| 1148 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1149 |
+
"eval_f1": 0.7878787878787878,
|
| 1150 |
+
"eval_loss": 0.9053316712379456,
|
| 1151 |
+
"eval_precision": 0.7727272727272727,
|
| 1152 |
+
"eval_recall": 0.8181818181818182,
|
| 1153 |
+
"eval_runtime": 20.7791,
|
| 1154 |
+
"eval_samples_per_second": 0.529,
|
| 1155 |
+
"eval_steps_per_second": 0.048,
|
| 1156 |
+
"step": 370
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 74.01,
|
| 1160 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1161 |
+
"eval_f1": 0.7878787878787878,
|
| 1162 |
+
"eval_loss": 0.6602973341941833,
|
| 1163 |
+
"eval_precision": 0.7727272727272727,
|
| 1164 |
+
"eval_recall": 0.8181818181818182,
|
| 1165 |
+
"eval_runtime": 21.2632,
|
| 1166 |
+
"eval_samples_per_second": 0.517,
|
| 1167 |
+
"eval_steps_per_second": 0.047,
|
| 1168 |
+
"step": 375
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 75.01,
|
| 1172 |
+
"grad_norm": 5.458927631378174,
|
| 1173 |
+
"learning_rate": 3.851851851851852e-05,
|
| 1174 |
+
"loss": 0.2473,
|
| 1175 |
+
"step": 380
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 75.01,
|
| 1179 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1180 |
+
"eval_f1": 0.6818181818181818,
|
| 1181 |
+
"eval_loss": 0.5296440720558167,
|
| 1182 |
+
"eval_precision": 0.6666666666666666,
|
| 1183 |
+
"eval_recall": 0.7272727272727273,
|
| 1184 |
+
"eval_runtime": 21.1347,
|
| 1185 |
+
"eval_samples_per_second": 0.52,
|
| 1186 |
+
"eval_steps_per_second": 0.047,
|
| 1187 |
+
"step": 380
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 76.01,
|
| 1191 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1192 |
+
"eval_f1": 0.6818181818181818,
|
| 1193 |
+
"eval_loss": 0.5802969336509705,
|
| 1194 |
+
"eval_precision": 0.6666666666666667,
|
| 1195 |
+
"eval_recall": 0.7272727272727273,
|
| 1196 |
+
"eval_runtime": 21.0086,
|
| 1197 |
+
"eval_samples_per_second": 0.524,
|
| 1198 |
+
"eval_steps_per_second": 0.048,
|
| 1199 |
+
"step": 385
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 77.01,
|
| 1203 |
+
"grad_norm": 6.091598033905029,
|
| 1204 |
+
"learning_rate": 3.777777777777778e-05,
|
| 1205 |
+
"loss": 0.2011,
|
| 1206 |
+
"step": 390
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 77.01,
|
| 1210 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1211 |
+
"eval_f1": 0.6606060606060605,
|
| 1212 |
+
"eval_loss": 0.83270663022995,
|
| 1213 |
+
"eval_precision": 0.6666666666666666,
|
| 1214 |
+
"eval_recall": 0.7272727272727273,
|
| 1215 |
+
"eval_runtime": 21.0559,
|
| 1216 |
+
"eval_samples_per_second": 0.522,
|
| 1217 |
+
"eval_steps_per_second": 0.047,
|
| 1218 |
+
"step": 390
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 78.01,
|
| 1222 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1223 |
+
"eval_f1": 0.7575757575757577,
|
| 1224 |
+
"eval_loss": 0.4885137677192688,
|
| 1225 |
+
"eval_precision": 0.7272727272727273,
|
| 1226 |
+
"eval_recall": 0.8181818181818182,
|
| 1227 |
+
"eval_runtime": 20.5482,
|
| 1228 |
+
"eval_samples_per_second": 0.535,
|
| 1229 |
+
"eval_steps_per_second": 0.049,
|
| 1230 |
+
"step": 395
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 79.01,
|
| 1234 |
+
"grad_norm": 67.30104064941406,
|
| 1235 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 1236 |
+
"loss": 0.299,
|
| 1237 |
+
"step": 400
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 79.01,
|
| 1241 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1242 |
+
"eval_f1": 0.7575757575757577,
|
| 1243 |
+
"eval_loss": 0.46232300996780396,
|
| 1244 |
+
"eval_precision": 0.7272727272727273,
|
| 1245 |
+
"eval_recall": 0.8181818181818182,
|
| 1246 |
+
"eval_runtime": 20.4146,
|
| 1247 |
+
"eval_samples_per_second": 0.539,
|
| 1248 |
+
"eval_steps_per_second": 0.049,
|
| 1249 |
+
"step": 400
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 80.01,
|
| 1253 |
+
"eval_accuracy": 0.9090909090909091,
|
| 1254 |
+
"eval_f1": 0.8787878787878788,
|
| 1255 |
+
"eval_loss": 0.4730096161365509,
|
| 1256 |
+
"eval_precision": 0.8636363636363636,
|
| 1257 |
+
"eval_recall": 0.9090909090909091,
|
| 1258 |
+
"eval_runtime": 20.8428,
|
| 1259 |
+
"eval_samples_per_second": 0.528,
|
| 1260 |
+
"eval_steps_per_second": 0.048,
|
| 1261 |
+
"step": 405
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 81.01,
|
| 1265 |
+
"grad_norm": 3.940727949142456,
|
| 1266 |
+
"learning_rate": 3.62962962962963e-05,
|
| 1267 |
+
"loss": 0.1008,
|
| 1268 |
+
"step": 410
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 81.01,
|
| 1272 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1273 |
+
"eval_f1": 0.7878787878787878,
|
| 1274 |
+
"eval_loss": 0.582288920879364,
|
| 1275 |
+
"eval_precision": 0.7727272727272727,
|
| 1276 |
+
"eval_recall": 0.8181818181818182,
|
| 1277 |
+
"eval_runtime": 20.3701,
|
| 1278 |
+
"eval_samples_per_second": 0.54,
|
| 1279 |
+
"eval_steps_per_second": 0.049,
|
| 1280 |
+
"step": 410
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 82.01,
|
| 1284 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1285 |
+
"eval_f1": 0.8181818181818182,
|
| 1286 |
+
"eval_loss": 0.5622988939285278,
|
| 1287 |
+
"eval_precision": 0.8181818181818182,
|
| 1288 |
+
"eval_recall": 0.8181818181818182,
|
| 1289 |
+
"eval_runtime": 20.3908,
|
| 1290 |
+
"eval_samples_per_second": 0.539,
|
| 1291 |
+
"eval_steps_per_second": 0.049,
|
| 1292 |
+
"step": 415
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 83.01,
|
| 1296 |
+
"grad_norm": 0.6912495493888855,
|
| 1297 |
+
"learning_rate": 3.555555555555556e-05,
|
| 1298 |
+
"loss": 0.1681,
|
| 1299 |
+
"step": 420
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 83.01,
|
| 1303 |
+
"eval_accuracy": 0.9090909090909091,
|
| 1304 |
+
"eval_f1": 0.8787878787878788,
|
| 1305 |
+
"eval_loss": 0.44556429982185364,
|
| 1306 |
+
"eval_precision": 0.8636363636363636,
|
| 1307 |
+
"eval_recall": 0.9090909090909091,
|
| 1308 |
+
"eval_runtime": 20.9116,
|
| 1309 |
+
"eval_samples_per_second": 0.526,
|
| 1310 |
+
"eval_steps_per_second": 0.048,
|
| 1311 |
+
"step": 420
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 84.01,
|
| 1315 |
+
"eval_accuracy": 0.9090909090909091,
|
| 1316 |
+
"eval_f1": 0.8787878787878788,
|
| 1317 |
+
"eval_loss": 0.3800961375236511,
|
| 1318 |
+
"eval_precision": 0.8636363636363636,
|
| 1319 |
+
"eval_recall": 0.9090909090909091,
|
| 1320 |
+
"eval_runtime": 20.9045,
|
| 1321 |
+
"eval_samples_per_second": 0.526,
|
| 1322 |
+
"eval_steps_per_second": 0.048,
|
| 1323 |
+
"step": 425
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 85.01,
|
| 1327 |
+
"grad_norm": 1.7112609148025513,
|
| 1328 |
+
"learning_rate": 3.481481481481482e-05,
|
| 1329 |
+
"loss": 0.1318,
|
| 1330 |
+
"step": 430
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 85.01,
|
| 1334 |
+
"eval_accuracy": 0.9090909090909091,
|
| 1335 |
+
"eval_f1": 0.8787878787878788,
|
| 1336 |
+
"eval_loss": 0.4264180362224579,
|
| 1337 |
+
"eval_precision": 0.8636363636363636,
|
| 1338 |
+
"eval_recall": 0.9090909090909091,
|
| 1339 |
+
"eval_runtime": 20.4232,
|
| 1340 |
+
"eval_samples_per_second": 0.539,
|
| 1341 |
+
"eval_steps_per_second": 0.049,
|
| 1342 |
+
"step": 430
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 86.01,
|
| 1346 |
+
"eval_accuracy": 0.8181818181818182,
|
| 1347 |
+
"eval_f1": 0.8181818181818182,
|
| 1348 |
+
"eval_loss": 0.3410065472126007,
|
| 1349 |
+
"eval_precision": 0.8181818181818182,
|
| 1350 |
+
"eval_recall": 0.8181818181818182,
|
| 1351 |
+
"eval_runtime": 21.0143,
|
| 1352 |
+
"eval_samples_per_second": 0.523,
|
| 1353 |
+
"eval_steps_per_second": 0.048,
|
| 1354 |
+
"step": 435
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 87.01,
|
| 1358 |
+
"grad_norm": 8.220293998718262,
|
| 1359 |
+
"learning_rate": 3.4074074074074077e-05,
|
| 1360 |
+
"loss": 0.1515,
|
| 1361 |
+
"step": 440
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 87.01,
|
| 1365 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1366 |
+
"eval_f1": 0.6818181818181818,
|
| 1367 |
+
"eval_loss": 0.6253748536109924,
|
| 1368 |
+
"eval_precision": 0.6666666666666666,
|
| 1369 |
+
"eval_recall": 0.7272727272727273,
|
| 1370 |
+
"eval_runtime": 20.6136,
|
| 1371 |
+
"eval_samples_per_second": 0.534,
|
| 1372 |
+
"eval_steps_per_second": 0.049,
|
| 1373 |
+
"step": 440
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 88.01,
|
| 1377 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1378 |
+
"eval_f1": 0.6818181818181818,
|
| 1379 |
+
"eval_loss": 0.5382604002952576,
|
| 1380 |
+
"eval_precision": 0.6666666666666666,
|
| 1381 |
+
"eval_recall": 0.7272727272727273,
|
| 1382 |
+
"eval_runtime": 20.2231,
|
| 1383 |
+
"eval_samples_per_second": 0.544,
|
| 1384 |
+
"eval_steps_per_second": 0.049,
|
| 1385 |
+
"step": 445
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 89.01,
|
| 1389 |
+
"grad_norm": 7.24671745300293,
|
| 1390 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1391 |
+
"loss": 0.1379,
|
| 1392 |
+
"step": 450
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 89.01,
|
| 1396 |
+
"eval_accuracy": 0.9090909090909091,
|
| 1397 |
+
"eval_f1": 0.8787878787878788,
|
| 1398 |
+
"eval_loss": 0.26343244314193726,
|
| 1399 |
+
"eval_precision": 0.8636363636363636,
|
| 1400 |
+
"eval_recall": 0.9090909090909091,
|
| 1401 |
+
"eval_runtime": 22.4656,
|
| 1402 |
+
"eval_samples_per_second": 0.49,
|
| 1403 |
+
"eval_steps_per_second": 0.045,
|
| 1404 |
+
"step": 450
|
| 1405 |
+
}
|
| 1406 |
+
],
|
| 1407 |
+
"logging_steps": 10,
|
| 1408 |
+
"max_steps": 900,
|
| 1409 |
+
"num_input_tokens_seen": 0,
|
| 1410 |
+
"num_train_epochs": 9223372036854775807,
|
| 1411 |
+
"save_steps": 500,
|
| 1412 |
+
"total_flos": 8.859993293767311e+18,
|
| 1413 |
+
"train_batch_size": 16,
|
| 1414 |
+
"trial_name": null,
|
| 1415 |
+
"trial_params": null
|
| 1416 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cedbe923c1a1d21530aec0fc175becc3bc90e28a63a747b89f774aad6c66861
|
| 3 |
+
size 4920
|