Commit
•
6fc382a
1
Parent(s):
8554723
Upload 10 files
Browse files- .gitattributes +1 -0
- config.json +42 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +922 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloomz-560m",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "human-produced",
|
| 16 |
+
"1": "machine-generated"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"human-produced": 0,
|
| 21 |
+
"machine-generated": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_epsilon": 1e-05,
|
| 24 |
+
"masked_softmax_fusion": true,
|
| 25 |
+
"model_type": "bloom",
|
| 26 |
+
"n_head": 16,
|
| 27 |
+
"n_inner": null,
|
| 28 |
+
"n_layer": 24,
|
| 29 |
+
"offset_alibi": 100,
|
| 30 |
+
"pad_token_id": 3,
|
| 31 |
+
"pretraining_tp": 1,
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"seq_length": 2048,
|
| 34 |
+
"skip_bias_add": true,
|
| 35 |
+
"skip_bias_add_qkv": false,
|
| 36 |
+
"slow_but_exact": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.26.1",
|
| 39 |
+
"unk_token_id": 0,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 250880
|
| 42 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e61ea2e45edfeec896776af115dabcc98703ee8cc296de762c6e7c1a1defc783
|
| 3 |
+
size 4473979569
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f8c1339fd3044159d03f5d1792c685c645aa011d4a846dd27b56d22cb71fb26
|
| 3 |
+
size 2236965925
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d944d6907131fce4941c1b98753b6c6304e9268438faa750202a7ed282544a4
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19c575370b6179b490f435df9c74d0ea7aabd16f264cf932690c39af9fca6ebb
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa18280d17cb2240255ae226f2e8ce87bc72ae3fb9f7044d0238395b4d8b7a33
|
| 3 |
+
size 14500707
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "bigscience/bloomz-560m",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"padding_side": "left",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"tokenizer_class": "BloomTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,922 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 1750,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9971428571428576e-05,
|
| 13 |
+
"loss": 13.0691,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.9e-05,
|
| 19 |
+
"loss": 14.048,
|
| 20 |
+
"step": 35
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.5,
|
| 25 |
+
"eval_f1": 0.6666666666666666,
|
| 26 |
+
"eval_loss": 7.880705833435059,
|
| 27 |
+
"eval_precision": 0.5,
|
| 28 |
+
"eval_recall": 1.0,
|
| 29 |
+
"eval_runtime": 80.7039,
|
| 30 |
+
"eval_samples_per_second": 37.173,
|
| 31 |
+
"eval_steps_per_second": 4.647,
|
| 32 |
+
"step": 35
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 4.8e-05,
|
| 37 |
+
"loss": 2.2656,
|
| 38 |
+
"step": 70
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_accuracy": 0.5016666666666667,
|
| 43 |
+
"eval_f1": 0.6674082313681868,
|
| 44 |
+
"eval_loss": 3.2190163135528564,
|
| 45 |
+
"eval_precision": 0.5008347245409015,
|
| 46 |
+
"eval_recall": 1.0,
|
| 47 |
+
"eval_runtime": 80.4061,
|
| 48 |
+
"eval_samples_per_second": 37.311,
|
| 49 |
+
"eval_steps_per_second": 4.664,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 4.7e-05,
|
| 55 |
+
"loss": 2.1548,
|
| 56 |
+
"step": 105
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_accuracy": 0.6906666666666667,
|
| 61 |
+
"eval_f1": 0.7371104815864024,
|
| 62 |
+
"eval_loss": 0.5703864097595215,
|
| 63 |
+
"eval_precision": 0.6408866995073892,
|
| 64 |
+
"eval_recall": 0.8673333333333333,
|
| 65 |
+
"eval_runtime": 80.8676,
|
| 66 |
+
"eval_samples_per_second": 37.098,
|
| 67 |
+
"eval_steps_per_second": 4.637,
|
| 68 |
+
"step": 105
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"learning_rate": 4.600000000000001e-05,
|
| 73 |
+
"loss": 1.3819,
|
| 74 |
+
"step": 140
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"eval_accuracy": 0.5,
|
| 79 |
+
"eval_f1": 0.0,
|
| 80 |
+
"eval_loss": 0.9337035417556763,
|
| 81 |
+
"eval_precision": 0.0,
|
| 82 |
+
"eval_recall": 0.0,
|
| 83 |
+
"eval_runtime": 80.5811,
|
| 84 |
+
"eval_samples_per_second": 37.23,
|
| 85 |
+
"eval_steps_per_second": 4.654,
|
| 86 |
+
"step": 140
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 4.5e-05,
|
| 91 |
+
"loss": 1.1309,
|
| 92 |
+
"step": 175
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.1,
|
| 96 |
+
"eval_accuracy": 0.5,
|
| 97 |
+
"eval_f1": 0.6666666666666666,
|
| 98 |
+
"eval_loss": 2.4655497074127197,
|
| 99 |
+
"eval_precision": 0.5,
|
| 100 |
+
"eval_recall": 1.0,
|
| 101 |
+
"eval_runtime": 80.4828,
|
| 102 |
+
"eval_samples_per_second": 37.275,
|
| 103 |
+
"eval_steps_per_second": 4.659,
|
| 104 |
+
"step": 175
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12,
|
| 108 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 109 |
+
"loss": 0.9397,
|
| 110 |
+
"step": 210
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12,
|
| 114 |
+
"eval_accuracy": 0.6686666666666666,
|
| 115 |
+
"eval_f1": 0.7317862924986509,
|
| 116 |
+
"eval_loss": 0.6442784667015076,
|
| 117 |
+
"eval_precision": 0.614687216681777,
|
| 118 |
+
"eval_recall": 0.904,
|
| 119 |
+
"eval_runtime": 80.537,
|
| 120 |
+
"eval_samples_per_second": 37.25,
|
| 121 |
+
"eval_steps_per_second": 4.656,
|
| 122 |
+
"step": 210
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14,
|
| 126 |
+
"learning_rate": 4.3e-05,
|
| 127 |
+
"loss": 0.8193,
|
| 128 |
+
"step": 245
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"eval_accuracy": 0.6676666666666666,
|
| 133 |
+
"eval_f1": 0.7155492154065621,
|
| 134 |
+
"eval_loss": 1.0818308591842651,
|
| 135 |
+
"eval_precision": 0.6254364089775561,
|
| 136 |
+
"eval_recall": 0.836,
|
| 137 |
+
"eval_runtime": 81.1642,
|
| 138 |
+
"eval_samples_per_second": 36.962,
|
| 139 |
+
"eval_steps_per_second": 4.62,
|
| 140 |
+
"step": 245
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 4.2e-05,
|
| 145 |
+
"loss": 0.6235,
|
| 146 |
+
"step": 280
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"eval_accuracy": 0.5413333333333333,
|
| 151 |
+
"eval_f1": 0.685413808870599,
|
| 152 |
+
"eval_loss": 1.136587381362915,
|
| 153 |
+
"eval_precision": 0.5215727209464162,
|
| 154 |
+
"eval_recall": 0.9993333333333333,
|
| 155 |
+
"eval_runtime": 81.1897,
|
| 156 |
+
"eval_samples_per_second": 36.951,
|
| 157 |
+
"eval_steps_per_second": 4.619,
|
| 158 |
+
"step": 280
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18,
|
| 162 |
+
"learning_rate": 4.1e-05,
|
| 163 |
+
"loss": 0.6828,
|
| 164 |
+
"step": 315
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18,
|
| 168 |
+
"eval_accuracy": 0.7913333333333333,
|
| 169 |
+
"eval_f1": 0.7481898632341111,
|
| 170 |
+
"eval_loss": 0.5717737674713135,
|
| 171 |
+
"eval_precision": 0.9432048681541582,
|
| 172 |
+
"eval_recall": 0.62,
|
| 173 |
+
"eval_runtime": 80.6162,
|
| 174 |
+
"eval_samples_per_second": 37.213,
|
| 175 |
+
"eval_steps_per_second": 4.652,
|
| 176 |
+
"step": 315
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2,
|
| 180 |
+
"learning_rate": 4e-05,
|
| 181 |
+
"loss": 0.5375,
|
| 182 |
+
"step": 350
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2,
|
| 186 |
+
"eval_accuracy": 0.6203333333333333,
|
| 187 |
+
"eval_f1": 0.7234765719834911,
|
| 188 |
+
"eval_loss": 1.3898557424545288,
|
| 189 |
+
"eval_precision": 0.5689194348988164,
|
| 190 |
+
"eval_recall": 0.9933333333333333,
|
| 191 |
+
"eval_runtime": 80.8767,
|
| 192 |
+
"eval_samples_per_second": 37.094,
|
| 193 |
+
"eval_steps_per_second": 4.637,
|
| 194 |
+
"step": 350
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.22,
|
| 198 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 199 |
+
"loss": 0.8008,
|
| 200 |
+
"step": 385
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"eval_accuracy": 0.6446666666666667,
|
| 205 |
+
"eval_f1": 0.7352210630899155,
|
| 206 |
+
"eval_loss": 1.3506994247436523,
|
| 207 |
+
"eval_precision": 0.5859065716547902,
|
| 208 |
+
"eval_recall": 0.9866666666666667,
|
| 209 |
+
"eval_runtime": 80.9272,
|
| 210 |
+
"eval_samples_per_second": 37.07,
|
| 211 |
+
"eval_steps_per_second": 4.634,
|
| 212 |
+
"step": 385
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24,
|
| 216 |
+
"learning_rate": 3.8e-05,
|
| 217 |
+
"loss": 0.5408,
|
| 218 |
+
"step": 420
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.24,
|
| 222 |
+
"eval_accuracy": 0.5,
|
| 223 |
+
"eval_f1": 0.6666666666666666,
|
| 224 |
+
"eval_loss": 5.448528289794922,
|
| 225 |
+
"eval_precision": 0.5,
|
| 226 |
+
"eval_recall": 1.0,
|
| 227 |
+
"eval_runtime": 80.3832,
|
| 228 |
+
"eval_samples_per_second": 37.321,
|
| 229 |
+
"eval_steps_per_second": 4.665,
|
| 230 |
+
"step": 420
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.26,
|
| 234 |
+
"learning_rate": 3.7e-05,
|
| 235 |
+
"loss": 1.5679,
|
| 236 |
+
"step": 455
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.26,
|
| 240 |
+
"eval_accuracy": 0.5303333333333333,
|
| 241 |
+
"eval_f1": 0.6804264005443411,
|
| 242 |
+
"eval_loss": 2.9407122135162354,
|
| 243 |
+
"eval_precision": 0.5156411137848058,
|
| 244 |
+
"eval_recall": 1.0,
|
| 245 |
+
"eval_runtime": 80.4322,
|
| 246 |
+
"eval_samples_per_second": 37.298,
|
| 247 |
+
"eval_steps_per_second": 4.662,
|
| 248 |
+
"step": 455
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.28,
|
| 252 |
+
"learning_rate": 3.6e-05,
|
| 253 |
+
"loss": 0.7113,
|
| 254 |
+
"step": 490
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"eval_accuracy": 0.5003333333333333,
|
| 259 |
+
"eval_f1": 0.6668148477439431,
|
| 260 |
+
"eval_loss": 4.913637638092041,
|
| 261 |
+
"eval_precision": 0.5001667222407469,
|
| 262 |
+
"eval_recall": 1.0,
|
| 263 |
+
"eval_runtime": 80.9405,
|
| 264 |
+
"eval_samples_per_second": 37.064,
|
| 265 |
+
"eval_steps_per_second": 4.633,
|
| 266 |
+
"step": 490
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.3,
|
| 270 |
+
"learning_rate": 3.5e-05,
|
| 271 |
+
"loss": 0.5356,
|
| 272 |
+
"step": 525
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.3,
|
| 276 |
+
"eval_accuracy": 0.6223333333333333,
|
| 277 |
+
"eval_f1": 0.724933236222384,
|
| 278 |
+
"eval_loss": 1.4003673791885376,
|
| 279 |
+
"eval_precision": 0.5700649102710958,
|
| 280 |
+
"eval_recall": 0.9953333333333333,
|
| 281 |
+
"eval_runtime": 80.635,
|
| 282 |
+
"eval_samples_per_second": 37.205,
|
| 283 |
+
"eval_steps_per_second": 4.651,
|
| 284 |
+
"step": 525
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.32,
|
| 288 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 289 |
+
"loss": 0.4847,
|
| 290 |
+
"step": 560
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.32,
|
| 294 |
+
"eval_accuracy": 0.5016666666666667,
|
| 295 |
+
"eval_f1": 0.6674082313681868,
|
| 296 |
+
"eval_loss": 6.015239715576172,
|
| 297 |
+
"eval_precision": 0.5008347245409015,
|
| 298 |
+
"eval_recall": 1.0,
|
| 299 |
+
"eval_runtime": 80.7702,
|
| 300 |
+
"eval_samples_per_second": 37.142,
|
| 301 |
+
"eval_steps_per_second": 4.643,
|
| 302 |
+
"step": 560
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.34,
|
| 306 |
+
"learning_rate": 3.3e-05,
|
| 307 |
+
"loss": 0.319,
|
| 308 |
+
"step": 595
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.34,
|
| 312 |
+
"eval_accuracy": 0.8496666666666667,
|
| 313 |
+
"eval_f1": 0.8543752018082015,
|
| 314 |
+
"eval_loss": 0.6166228652000427,
|
| 315 |
+
"eval_precision": 0.828428303068253,
|
| 316 |
+
"eval_recall": 0.882,
|
| 317 |
+
"eval_runtime": 80.8211,
|
| 318 |
+
"eval_samples_per_second": 37.119,
|
| 319 |
+
"eval_steps_per_second": 4.64,
|
| 320 |
+
"step": 595
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.36,
|
| 324 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 325 |
+
"loss": 0.822,
|
| 326 |
+
"step": 630
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.36,
|
| 330 |
+
"eval_accuracy": 0.8383333333333334,
|
| 331 |
+
"eval_f1": 0.820967146548542,
|
| 332 |
+
"eval_loss": 0.41078850626945496,
|
| 333 |
+
"eval_precision": 0.9197684036393714,
|
| 334 |
+
"eval_recall": 0.7413333333333333,
|
| 335 |
+
"eval_runtime": 80.9973,
|
| 336 |
+
"eval_samples_per_second": 37.038,
|
| 337 |
+
"eval_steps_per_second": 4.63,
|
| 338 |
+
"step": 630
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.38,
|
| 342 |
+
"learning_rate": 3.1e-05,
|
| 343 |
+
"loss": 0.4746,
|
| 344 |
+
"step": 665
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.38,
|
| 348 |
+
"eval_accuracy": 0.8246666666666667,
|
| 349 |
+
"eval_f1": 0.830213040671401,
|
| 350 |
+
"eval_loss": 0.3808746337890625,
|
| 351 |
+
"eval_precision": 0.804755944931164,
|
| 352 |
+
"eval_recall": 0.8573333333333333,
|
| 353 |
+
"eval_runtime": 80.4252,
|
| 354 |
+
"eval_samples_per_second": 37.302,
|
| 355 |
+
"eval_steps_per_second": 4.663,
|
| 356 |
+
"step": 665
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.4,
|
| 360 |
+
"learning_rate": 3e-05,
|
| 361 |
+
"loss": 0.2913,
|
| 362 |
+
"step": 700
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.4,
|
| 366 |
+
"eval_accuracy": 0.747,
|
| 367 |
+
"eval_f1": 0.7941415785191213,
|
| 368 |
+
"eval_loss": 0.7681821584701538,
|
| 369 |
+
"eval_precision": 0.6694101508916324,
|
| 370 |
+
"eval_recall": 0.976,
|
| 371 |
+
"eval_runtime": 80.4193,
|
| 372 |
+
"eval_samples_per_second": 37.304,
|
| 373 |
+
"eval_steps_per_second": 4.663,
|
| 374 |
+
"step": 700
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.42,
|
| 378 |
+
"learning_rate": 2.9e-05,
|
| 379 |
+
"loss": 0.3153,
|
| 380 |
+
"step": 735
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.42,
|
| 384 |
+
"eval_accuracy": 0.8356666666666667,
|
| 385 |
+
"eval_f1": 0.8523510032943996,
|
| 386 |
+
"eval_loss": 0.4611086845397949,
|
| 387 |
+
"eval_precision": 0.7737901033170201,
|
| 388 |
+
"eval_recall": 0.9486666666666667,
|
| 389 |
+
"eval_runtime": 80.4421,
|
| 390 |
+
"eval_samples_per_second": 37.294,
|
| 391 |
+
"eval_steps_per_second": 4.662,
|
| 392 |
+
"step": 735
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.44,
|
| 396 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 397 |
+
"loss": 0.4953,
|
| 398 |
+
"step": 770
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.44,
|
| 402 |
+
"eval_accuracy": 0.5146666666666667,
|
| 403 |
+
"eval_f1": 0.6732495511669659,
|
| 404 |
+
"eval_loss": 1.9276390075683594,
|
| 405 |
+
"eval_precision": 0.5074424898511503,
|
| 406 |
+
"eval_recall": 1.0,
|
| 407 |
+
"eval_runtime": 80.6277,
|
| 408 |
+
"eval_samples_per_second": 37.208,
|
| 409 |
+
"eval_steps_per_second": 4.651,
|
| 410 |
+
"step": 770
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.46,
|
| 414 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 415 |
+
"loss": 0.8238,
|
| 416 |
+
"step": 805
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.46,
|
| 420 |
+
"eval_accuracy": 0.8233333333333334,
|
| 421 |
+
"eval_f1": 0.789515488482923,
|
| 422 |
+
"eval_loss": 0.758985698223114,
|
| 423 |
+
"eval_precision": 0.9764243614931237,
|
| 424 |
+
"eval_recall": 0.6626666666666666,
|
| 425 |
+
"eval_runtime": 80.4659,
|
| 426 |
+
"eval_samples_per_second": 37.283,
|
| 427 |
+
"eval_steps_per_second": 4.66,
|
| 428 |
+
"step": 805
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.48,
|
| 432 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 433 |
+
"loss": 0.6315,
|
| 434 |
+
"step": 840
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.48,
|
| 438 |
+
"eval_accuracy": 0.5013333333333333,
|
| 439 |
+
"eval_f1": 0.6672597864768683,
|
| 440 |
+
"eval_loss": 5.900465965270996,
|
| 441 |
+
"eval_precision": 0.5006675567423231,
|
| 442 |
+
"eval_recall": 1.0,
|
| 443 |
+
"eval_runtime": 80.4747,
|
| 444 |
+
"eval_samples_per_second": 37.279,
|
| 445 |
+
"eval_steps_per_second": 4.66,
|
| 446 |
+
"step": 840
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5,
|
| 450 |
+
"learning_rate": 2.5e-05,
|
| 451 |
+
"loss": 0.4659,
|
| 452 |
+
"step": 875
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.5,
|
| 456 |
+
"eval_accuracy": 0.879,
|
| 457 |
+
"eval_f1": 0.875214850464077,
|
| 458 |
+
"eval_loss": 0.2947004735469818,
|
| 459 |
+
"eval_precision": 0.9034776437189496,
|
| 460 |
+
"eval_recall": 0.8486666666666667,
|
| 461 |
+
"eval_runtime": 80.8565,
|
| 462 |
+
"eval_samples_per_second": 37.103,
|
| 463 |
+
"eval_steps_per_second": 4.638,
|
| 464 |
+
"step": 875
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.52,
|
| 468 |
+
"learning_rate": 2.4e-05,
|
| 469 |
+
"loss": 0.2773,
|
| 470 |
+
"step": 910
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.52,
|
| 474 |
+
"eval_accuracy": 0.5133333333333333,
|
| 475 |
+
"eval_f1": 0.672645739910314,
|
| 476 |
+
"eval_loss": 3.5455527305603027,
|
| 477 |
+
"eval_precision": 0.5067567567567568,
|
| 478 |
+
"eval_recall": 1.0,
|
| 479 |
+
"eval_runtime": 80.4994,
|
| 480 |
+
"eval_samples_per_second": 37.267,
|
| 481 |
+
"eval_steps_per_second": 4.658,
|
| 482 |
+
"step": 910
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.54,
|
| 486 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 487 |
+
"loss": 0.371,
|
| 488 |
+
"step": 945
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.54,
|
| 492 |
+
"eval_accuracy": 0.5043333333333333,
|
| 493 |
+
"eval_f1": 0.6685981724983284,
|
| 494 |
+
"eval_loss": 3.9809491634368896,
|
| 495 |
+
"eval_precision": 0.5021760964178105,
|
| 496 |
+
"eval_recall": 1.0,
|
| 497 |
+
"eval_runtime": 80.5845,
|
| 498 |
+
"eval_samples_per_second": 37.228,
|
| 499 |
+
"eval_steps_per_second": 4.654,
|
| 500 |
+
"step": 945
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.56,
|
| 504 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 505 |
+
"loss": 0.4968,
|
| 506 |
+
"step": 980
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.56,
|
| 510 |
+
"eval_accuracy": 0.713,
|
| 511 |
+
"eval_f1": 0.7757228444907528,
|
| 512 |
+
"eval_loss": 1.2047169208526611,
|
| 513 |
+
"eval_precision": 0.6365968362548098,
|
| 514 |
+
"eval_recall": 0.9926666666666667,
|
| 515 |
+
"eval_runtime": 80.9051,
|
| 516 |
+
"eval_samples_per_second": 37.08,
|
| 517 |
+
"eval_steps_per_second": 4.635,
|
| 518 |
+
"step": 980
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.58,
|
| 522 |
+
"learning_rate": 2.1e-05,
|
| 523 |
+
"loss": 0.5577,
|
| 524 |
+
"step": 1015
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.58,
|
| 528 |
+
"eval_accuracy": 0.9123333333333333,
|
| 529 |
+
"eval_f1": 0.9118337244384848,
|
| 530 |
+
"eval_loss": 0.24421826004981995,
|
| 531 |
+
"eval_precision": 0.9170600134861767,
|
| 532 |
+
"eval_recall": 0.9066666666666666,
|
| 533 |
+
"eval_runtime": 80.8404,
|
| 534 |
+
"eval_samples_per_second": 37.11,
|
| 535 |
+
"eval_steps_per_second": 4.639,
|
| 536 |
+
"step": 1015
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.6,
|
| 540 |
+
"learning_rate": 2e-05,
|
| 541 |
+
"loss": 0.2212,
|
| 542 |
+
"step": 1050
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6,
|
| 546 |
+
"eval_accuracy": 0.8366666666666667,
|
| 547 |
+
"eval_f1": 0.8556275780789628,
|
| 548 |
+
"eval_loss": 0.44433295726776123,
|
| 549 |
+
"eval_precision": 0.7666314677930306,
|
| 550 |
+
"eval_recall": 0.968,
|
| 551 |
+
"eval_runtime": 80.4427,
|
| 552 |
+
"eval_samples_per_second": 37.294,
|
| 553 |
+
"eval_steps_per_second": 4.662,
|
| 554 |
+
"step": 1050
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.62,
|
| 558 |
+
"learning_rate": 1.9e-05,
|
| 559 |
+
"loss": 0.2668,
|
| 560 |
+
"step": 1085
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.62,
|
| 564 |
+
"eval_accuracy": 0.56,
|
| 565 |
+
"eval_f1": 0.6943029180176007,
|
| 566 |
+
"eval_loss": 2.2121241092681885,
|
| 567 |
+
"eval_precision": 0.5319375443577005,
|
| 568 |
+
"eval_recall": 0.9993333333333333,
|
| 569 |
+
"eval_runtime": 80.772,
|
| 570 |
+
"eval_samples_per_second": 37.142,
|
| 571 |
+
"eval_steps_per_second": 4.643,
|
| 572 |
+
"step": 1085
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.64,
|
| 576 |
+
"learning_rate": 1.8e-05,
|
| 577 |
+
"loss": 0.2392,
|
| 578 |
+
"step": 1120
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.64,
|
| 582 |
+
"eval_accuracy": 0.617,
|
| 583 |
+
"eval_f1": 0.7223967141821697,
|
| 584 |
+
"eval_loss": 1.7039114236831665,
|
| 585 |
+
"eval_precision": 0.5665024630541872,
|
| 586 |
+
"eval_recall": 0.9966666666666667,
|
| 587 |
+
"eval_runtime": 81.2102,
|
| 588 |
+
"eval_samples_per_second": 36.941,
|
| 589 |
+
"eval_steps_per_second": 4.618,
|
| 590 |
+
"step": 1120
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.66,
|
| 594 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 595 |
+
"loss": 0.4237,
|
| 596 |
+
"step": 1155
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.66,
|
| 600 |
+
"eval_accuracy": 0.5113333333333333,
|
| 601 |
+
"eval_f1": 0.6717420510523958,
|
| 602 |
+
"eval_loss": 3.3159143924713135,
|
| 603 |
+
"eval_precision": 0.5057316250842886,
|
| 604 |
+
"eval_recall": 1.0,
|
| 605 |
+
"eval_runtime": 80.4636,
|
| 606 |
+
"eval_samples_per_second": 37.284,
|
| 607 |
+
"eval_steps_per_second": 4.66,
|
| 608 |
+
"step": 1155
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.68,
|
| 612 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 613 |
+
"loss": 0.4353,
|
| 614 |
+
"step": 1190
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.68,
|
| 618 |
+
"eval_accuracy": 0.82,
|
| 619 |
+
"eval_f1": 0.8432055749128919,
|
| 620 |
+
"eval_loss": 0.5704355239868164,
|
| 621 |
+
"eval_precision": 0.7469135802469136,
|
| 622 |
+
"eval_recall": 0.968,
|
| 623 |
+
"eval_runtime": 80.5065,
|
| 624 |
+
"eval_samples_per_second": 37.264,
|
| 625 |
+
"eval_steps_per_second": 4.658,
|
| 626 |
+
"step": 1190
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7,
|
| 630 |
+
"learning_rate": 1.5e-05,
|
| 631 |
+
"loss": 0.3109,
|
| 632 |
+
"step": 1225
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7,
|
| 636 |
+
"eval_accuracy": 0.6846666666666666,
|
| 637 |
+
"eval_f1": 0.7591649694501018,
|
| 638 |
+
"eval_loss": 1.1700917482376099,
|
| 639 |
+
"eval_precision": 0.6140856672158155,
|
| 640 |
+
"eval_recall": 0.994,
|
| 641 |
+
"eval_runtime": 80.6642,
|
| 642 |
+
"eval_samples_per_second": 37.191,
|
| 643 |
+
"eval_steps_per_second": 4.649,
|
| 644 |
+
"step": 1225
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.72,
|
| 648 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 649 |
+
"loss": 0.2154,
|
| 650 |
+
"step": 1260
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.72,
|
| 654 |
+
"eval_accuracy": 0.817,
|
| 655 |
+
"eval_f1": 0.8419234091563489,
|
| 656 |
+
"eval_loss": 0.48465803265571594,
|
| 657 |
+
"eval_precision": 0.7410035478966042,
|
| 658 |
+
"eval_recall": 0.9746666666666667,
|
| 659 |
+
"eval_runtime": 80.8924,
|
| 660 |
+
"eval_samples_per_second": 37.086,
|
| 661 |
+
"eval_steps_per_second": 4.636,
|
| 662 |
+
"step": 1260
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.74,
|
| 666 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 667 |
+
"loss": 0.2415,
|
| 668 |
+
"step": 1295
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.74,
|
| 672 |
+
"eval_accuracy": 0.8613333333333333,
|
| 673 |
+
"eval_f1": 0.87363304981774,
|
| 674 |
+
"eval_loss": 0.36877182126045227,
|
| 675 |
+
"eval_precision": 0.8024553571428571,
|
| 676 |
+
"eval_recall": 0.9586666666666667,
|
| 677 |
+
"eval_runtime": 80.8409,
|
| 678 |
+
"eval_samples_per_second": 37.11,
|
| 679 |
+
"eval_steps_per_second": 4.639,
|
| 680 |
+
"step": 1295
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.76,
|
| 684 |
+
"learning_rate": 1.2e-05,
|
| 685 |
+
"loss": 0.2014,
|
| 686 |
+
"step": 1330
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.76,
|
| 690 |
+
"eval_accuracy": 0.7543333333333333,
|
| 691 |
+
"eval_f1": 0.8008646311807619,
|
| 692 |
+
"eval_loss": 0.6940145492553711,
|
| 693 |
+
"eval_precision": 0.6733303044070876,
|
| 694 |
+
"eval_recall": 0.988,
|
| 695 |
+
"eval_runtime": 86.2109,
|
| 696 |
+
"eval_samples_per_second": 34.798,
|
| 697 |
+
"eval_steps_per_second": 4.35,
|
| 698 |
+
"step": 1330
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.78,
|
| 702 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 703 |
+
"loss": 0.2165,
|
| 704 |
+
"step": 1365
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.78,
|
| 708 |
+
"eval_accuracy": 0.611,
|
| 709 |
+
"eval_f1": 0.7195385724585437,
|
| 710 |
+
"eval_loss": 1.6025038957595825,
|
| 711 |
+
"eval_precision": 0.5625704622322435,
|
| 712 |
+
"eval_recall": 0.998,
|
| 713 |
+
"eval_runtime": 81.0854,
|
| 714 |
+
"eval_samples_per_second": 36.998,
|
| 715 |
+
"eval_steps_per_second": 4.625,
|
| 716 |
+
"step": 1365
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.8,
|
| 720 |
+
"learning_rate": 1e-05,
|
| 721 |
+
"loss": 0.2487,
|
| 722 |
+
"step": 1400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.8,
|
| 726 |
+
"eval_accuracy": 0.73,
|
| 727 |
+
"eval_f1": 0.7856008470089996,
|
| 728 |
+
"eval_loss": 0.8998059630393982,
|
| 729 |
+
"eval_precision": 0.6514486391571555,
|
| 730 |
+
"eval_recall": 0.9893333333333333,
|
| 731 |
+
"eval_runtime": 80.4427,
|
| 732 |
+
"eval_samples_per_second": 37.294,
|
| 733 |
+
"eval_steps_per_second": 4.662,
|
| 734 |
+
"step": 1400
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.82,
|
| 738 |
+
"learning_rate": 9e-06,
|
| 739 |
+
"loss": 0.2204,
|
| 740 |
+
"step": 1435
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.82,
|
| 744 |
+
"eval_accuracy": 0.8493333333333334,
|
| 745 |
+
"eval_f1": 0.8598884066955982,
|
| 746 |
+
"eval_loss": 0.3596617579460144,
|
| 747 |
+
"eval_precision": 0.8035921205098494,
|
| 748 |
+
"eval_recall": 0.9246666666666666,
|
| 749 |
+
"eval_runtime": 80.5841,
|
| 750 |
+
"eval_samples_per_second": 37.228,
|
| 751 |
+
"eval_steps_per_second": 4.654,
|
| 752 |
+
"step": 1435
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.84,
|
| 756 |
+
"learning_rate": 8.000000000000001e-06,
|
| 757 |
+
"loss": 0.1436,
|
| 758 |
+
"step": 1470
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.84,
|
| 762 |
+
"eval_accuracy": 0.5616666666666666,
|
| 763 |
+
"eval_f1": 0.6951078135868306,
|
| 764 |
+
"eval_loss": 2.4785938262939453,
|
| 765 |
+
"eval_precision": 0.5328830430145752,
|
| 766 |
+
"eval_recall": 0.9993333333333333,
|
| 767 |
+
"eval_runtime": 80.9085,
|
| 768 |
+
"eval_samples_per_second": 37.079,
|
| 769 |
+
"eval_steps_per_second": 4.635,
|
| 770 |
+
"step": 1470
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.86,
|
| 774 |
+
"learning_rate": 7.000000000000001e-06,
|
| 775 |
+
"loss": 0.1431,
|
| 776 |
+
"step": 1505
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.86,
|
| 780 |
+
"eval_accuracy": 0.7606666666666667,
|
| 781 |
+
"eval_f1": 0.8035030103995622,
|
| 782 |
+
"eval_loss": 0.7645860314369202,
|
| 783 |
+
"eval_precision": 0.6815227483751161,
|
| 784 |
+
"eval_recall": 0.9786666666666667,
|
| 785 |
+
"eval_runtime": 80.9077,
|
| 786 |
+
"eval_samples_per_second": 37.079,
|
| 787 |
+
"eval_steps_per_second": 4.635,
|
| 788 |
+
"step": 1505
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.88,
|
| 792 |
+
"learning_rate": 6e-06,
|
| 793 |
+
"loss": 0.2083,
|
| 794 |
+
"step": 1540
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.88,
|
| 798 |
+
"eval_accuracy": 0.645,
|
| 799 |
+
"eval_f1": 0.7372316802368615,
|
| 800 |
+
"eval_loss": 1.5643061399459839,
|
| 801 |
+
"eval_precision": 0.5851938895417156,
|
| 802 |
+
"eval_recall": 0.996,
|
| 803 |
+
"eval_runtime": 80.4452,
|
| 804 |
+
"eval_samples_per_second": 37.292,
|
| 805 |
+
"eval_steps_per_second": 4.662,
|
| 806 |
+
"step": 1540
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.9,
|
| 810 |
+
"learning_rate": 5e-06,
|
| 811 |
+
"loss": 0.218,
|
| 812 |
+
"step": 1575
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.9,
|
| 816 |
+
"eval_accuracy": 0.6816666666666666,
|
| 817 |
+
"eval_f1": 0.7570592724497585,
|
| 818 |
+
"eval_loss": 1.3131792545318604,
|
| 819 |
+
"eval_precision": 0.6120937885643768,
|
| 820 |
+
"eval_recall": 0.992,
|
| 821 |
+
"eval_runtime": 80.8361,
|
| 822 |
+
"eval_samples_per_second": 37.112,
|
| 823 |
+
"eval_steps_per_second": 4.639,
|
| 824 |
+
"step": 1575
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.92,
|
| 828 |
+
"learning_rate": 4.000000000000001e-06,
|
| 829 |
+
"loss": 0.2679,
|
| 830 |
+
"step": 1610
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.92,
|
| 834 |
+
"eval_accuracy": 0.8243333333333334,
|
| 835 |
+
"eval_f1": 0.845771144278607,
|
| 836 |
+
"eval_loss": 0.4741792678833008,
|
| 837 |
+
"eval_precision": 0.7537819509650495,
|
| 838 |
+
"eval_recall": 0.9633333333333334,
|
| 839 |
+
"eval_runtime": 80.8168,
|
| 840 |
+
"eval_samples_per_second": 37.121,
|
| 841 |
+
"eval_steps_per_second": 4.64,
|
| 842 |
+
"step": 1610
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.94,
|
| 846 |
+
"learning_rate": 3e-06,
|
| 847 |
+
"loss": 0.2218,
|
| 848 |
+
"step": 1645
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.94,
|
| 852 |
+
"eval_accuracy": 0.753,
|
| 853 |
+
"eval_f1": 0.7996755879967559,
|
| 854 |
+
"eval_loss": 0.7849438190460205,
|
| 855 |
+
"eval_precision": 0.6725784447476125,
|
| 856 |
+
"eval_recall": 0.986,
|
| 857 |
+
"eval_runtime": 80.4264,
|
| 858 |
+
"eval_samples_per_second": 37.301,
|
| 859 |
+
"eval_steps_per_second": 4.663,
|
| 860 |
+
"step": 1645
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.96,
|
| 864 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 865 |
+
"loss": 0.1489,
|
| 866 |
+
"step": 1680
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.96,
|
| 870 |
+
"eval_accuracy": 0.6353333333333333,
|
| 871 |
+
"eval_f1": 0.7322564855604503,
|
| 872 |
+
"eval_loss": 1.6629990339279175,
|
| 873 |
+
"eval_precision": 0.5784996133023975,
|
| 874 |
+
"eval_recall": 0.9973333333333333,
|
| 875 |
+
"eval_runtime": 80.5542,
|
| 876 |
+
"eval_samples_per_second": 37.242,
|
| 877 |
+
"eval_steps_per_second": 4.655,
|
| 878 |
+
"step": 1680
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.98,
|
| 882 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 883 |
+
"loss": 0.2119,
|
| 884 |
+
"step": 1715
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.98,
|
| 888 |
+
"eval_accuracy": 0.6753333333333333,
|
| 889 |
+
"eval_f1": 0.7536671724835609,
|
| 890 |
+
"eval_loss": 1.2936441898345947,
|
| 891 |
+
"eval_precision": 0.6071719641401793,
|
| 892 |
+
"eval_recall": 0.9933333333333333,
|
| 893 |
+
"eval_runtime": 80.4726,
|
| 894 |
+
"eval_samples_per_second": 37.28,
|
| 895 |
+
"eval_steps_per_second": 4.66,
|
| 896 |
+
"step": 1715
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.0,
|
| 900 |
+
"learning_rate": 0.0,
|
| 901 |
+
"loss": 0.1341,
|
| 902 |
+
"step": 1750
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.0,
|
| 906 |
+
"eval_accuracy": 0.6686666666666666,
|
| 907 |
+
"eval_f1": 0.7500000000000001,
|
| 908 |
+
"eval_loss": 1.3422788381576538,
|
| 909 |
+
"eval_precision": 0.6021809369951535,
|
| 910 |
+
"eval_recall": 0.994,
|
| 911 |
+
"eval_runtime": 80.4399,
|
| 912 |
+
"eval_samples_per_second": 37.295,
|
| 913 |
+
"eval_steps_per_second": 4.662,
|
| 914 |
+
"step": 1750
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"max_steps": 1750,
|
| 918 |
+
"num_train_epochs": 1,
|
| 919 |
+
"total_flos": 1.300198588416e+16,
|
| 920 |
+
"trial_name": null,
|
| 921 |
+
"trial_params": null
|
| 922 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf25998c2d2a78e22dc7450ad504f2cb59548518b1a70670379b2359dcee26c1
|
| 3 |
+
size 3451
|