Commit
•
eee473d
1
Parent(s):
fe6579e
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-1b7",
|
| 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": 2048,
|
| 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": 2,
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"seq_length": 4096,
|
| 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:a85dbb75d64e272fc99265afe2229374fa09a0eae1c610fab743059e05ec29ed
|
| 3 |
+
size 13779559309
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49e47901f5c69f6f27f67d3f7b67c176a31eef4c987f7edf40fa1bbac40a295c
|
| 3 |
+
size 6889753481
|
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 sha256:1d94bffac577c2182cd3b6680df4b0ff46f4c0a0b7ff9c866be7458145e68e80
|
| 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-1b7",
|
| 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": 2188,
|
| 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": 4.997714808043876e-05,
|
| 13 |
+
"loss": 6.9866,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.9017367458866546e-05,
|
| 19 |
+
"loss": 3.9852,
|
| 20 |
+
"step": 43
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.5429333333333334,
|
| 25 |
+
"eval_f1": 0.6712696586114307,
|
| 26 |
+
"eval_loss": 1.4847679138183594,
|
| 27 |
+
"eval_precision": 0.5241090146750524,
|
| 28 |
+
"eval_recall": 0.9333333333333333,
|
| 29 |
+
"eval_runtime": 305.136,
|
| 30 |
+
"eval_samples_per_second": 12.29,
|
| 31 |
+
"eval_steps_per_second": 1.537,
|
| 32 |
+
"step": 43
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 4.8034734917733096e-05,
|
| 37 |
+
"loss": 2.6079,
|
| 38 |
+
"step": 86
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_accuracy": 0.5717333333333333,
|
| 43 |
+
"eval_f1": 0.6556603773584906,
|
| 44 |
+
"eval_loss": 0.8047523498535156,
|
| 45 |
+
"eval_precision": 0.5482251703119397,
|
| 46 |
+
"eval_recall": 0.8154666666666667,
|
| 47 |
+
"eval_runtime": 305.1856,
|
| 48 |
+
"eval_samples_per_second": 12.288,
|
| 49 |
+
"eval_steps_per_second": 1.537,
|
| 50 |
+
"step": 86
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 4.705210237659964e-05,
|
| 55 |
+
"loss": 1.0141,
|
| 56 |
+
"step": 129
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_accuracy": 0.5896,
|
| 61 |
+
"eval_f1": 0.6892792247122956,
|
| 62 |
+
"eval_loss": 0.7188379764556885,
|
| 63 |
+
"eval_precision": 0.5545808966861598,
|
| 64 |
+
"eval_recall": 0.9104,
|
| 65 |
+
"eval_runtime": 305.1209,
|
| 66 |
+
"eval_samples_per_second": 12.29,
|
| 67 |
+
"eval_steps_per_second": 1.537,
|
| 68 |
+
"step": 129
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"learning_rate": 4.606946983546618e-05,
|
| 73 |
+
"loss": 0.8023,
|
| 74 |
+
"step": 172
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"eval_accuracy": 0.49733333333333335,
|
| 79 |
+
"eval_f1": 0.11874707807386631,
|
| 80 |
+
"eval_loss": 2.954312801361084,
|
| 81 |
+
"eval_precision": 0.4810606060606061,
|
| 82 |
+
"eval_recall": 0.06773333333333334,
|
| 83 |
+
"eval_runtime": 305.0816,
|
| 84 |
+
"eval_samples_per_second": 12.292,
|
| 85 |
+
"eval_steps_per_second": 1.537,
|
| 86 |
+
"step": 172
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 4.5086837294332726e-05,
|
| 91 |
+
"loss": 2.4517,
|
| 92 |
+
"step": 215
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.1,
|
| 96 |
+
"eval_accuracy": 0.6850666666666667,
|
| 97 |
+
"eval_f1": 0.7327449649241911,
|
| 98 |
+
"eval_loss": 0.6679351925849915,
|
| 99 |
+
"eval_precision": 0.6363993710691824,
|
| 100 |
+
"eval_recall": 0.8634666666666667,
|
| 101 |
+
"eval_runtime": 304.8754,
|
| 102 |
+
"eval_samples_per_second": 12.3,
|
| 103 |
+
"eval_steps_per_second": 1.538,
|
| 104 |
+
"step": 215
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12,
|
| 108 |
+
"learning_rate": 4.410420475319927e-05,
|
| 109 |
+
"loss": 1.6579,
|
| 110 |
+
"step": 258
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12,
|
| 114 |
+
"eval_accuracy": 0.8109333333333333,
|
| 115 |
+
"eval_f1": 0.7899259259259258,
|
| 116 |
+
"eval_loss": 0.7148910164833069,
|
| 117 |
+
"eval_precision": 0.8886666666666667,
|
| 118 |
+
"eval_recall": 0.7109333333333333,
|
| 119 |
+
"eval_runtime": 305.6713,
|
| 120 |
+
"eval_samples_per_second": 12.268,
|
| 121 |
+
"eval_steps_per_second": 1.534,
|
| 122 |
+
"step": 258
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14,
|
| 126 |
+
"learning_rate": 4.312157221206581e-05,
|
| 127 |
+
"loss": 1.3412,
|
| 128 |
+
"step": 301
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"eval_accuracy": 0.4938666666666667,
|
| 133 |
+
"eval_f1": 0.6546579330422125,
|
| 134 |
+
"eval_loss": 3.249486207962036,
|
| 135 |
+
"eval_precision": 0.4968240817453742,
|
| 136 |
+
"eval_recall": 0.9594666666666667,
|
| 137 |
+
"eval_runtime": 304.7083,
|
| 138 |
+
"eval_samples_per_second": 12.307,
|
| 139 |
+
"eval_steps_per_second": 1.539,
|
| 140 |
+
"step": 301
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 4.213893967093236e-05,
|
| 145 |
+
"loss": 1.6235,
|
| 146 |
+
"step": 344
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"eval_accuracy": 0.8013333333333333,
|
| 151 |
+
"eval_f1": 0.797719250610915,
|
| 152 |
+
"eval_loss": 0.4983011782169342,
|
| 153 |
+
"eval_precision": 0.8125,
|
| 154 |
+
"eval_recall": 0.7834666666666666,
|
| 155 |
+
"eval_runtime": 304.8657,
|
| 156 |
+
"eval_samples_per_second": 12.3,
|
| 157 |
+
"eval_steps_per_second": 1.538,
|
| 158 |
+
"step": 344
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18,
|
| 162 |
+
"learning_rate": 4.1156307129798905e-05,
|
| 163 |
+
"loss": 0.7822,
|
| 164 |
+
"step": 387
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18,
|
| 168 |
+
"eval_accuracy": 0.856,
|
| 169 |
+
"eval_f1": 0.8429319371727749,
|
| 170 |
+
"eval_loss": 0.8706910014152527,
|
| 171 |
+
"eval_precision": 0.927063339731286,
|
| 172 |
+
"eval_recall": 0.7728,
|
| 173 |
+
"eval_runtime": 305.1415,
|
| 174 |
+
"eval_samples_per_second": 12.289,
|
| 175 |
+
"eval_steps_per_second": 1.537,
|
| 176 |
+
"step": 387
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2,
|
| 180 |
+
"learning_rate": 4.017367458866545e-05,
|
| 181 |
+
"loss": 1.0922,
|
| 182 |
+
"step": 430
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2,
|
| 186 |
+
"eval_accuracy": 0.8034666666666667,
|
| 187 |
+
"eval_f1": 0.7738570113531757,
|
| 188 |
+
"eval_loss": 0.667508602142334,
|
| 189 |
+
"eval_precision": 0.9111271676300579,
|
| 190 |
+
"eval_recall": 0.6725333333333333,
|
| 191 |
+
"eval_runtime": 305.5394,
|
| 192 |
+
"eval_samples_per_second": 12.273,
|
| 193 |
+
"eval_steps_per_second": 1.535,
|
| 194 |
+
"step": 430
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.22,
|
| 198 |
+
"learning_rate": 3.919104204753199e-05,
|
| 199 |
+
"loss": 0.5747,
|
| 200 |
+
"step": 473
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"eval_accuracy": 0.88,
|
| 205 |
+
"eval_f1": 0.8822605965463108,
|
| 206 |
+
"eval_loss": 0.4237947165966034,
|
| 207 |
+
"eval_precision": 0.8659476117103235,
|
| 208 |
+
"eval_recall": 0.8992,
|
| 209 |
+
"eval_runtime": 305.7145,
|
| 210 |
+
"eval_samples_per_second": 12.266,
|
| 211 |
+
"eval_steps_per_second": 1.534,
|
| 212 |
+
"step": 473
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24,
|
| 216 |
+
"learning_rate": 3.820840950639854e-05,
|
| 217 |
+
"loss": 0.5248,
|
| 218 |
+
"step": 516
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.24,
|
| 222 |
+
"eval_accuracy": 0.8424,
|
| 223 |
+
"eval_f1": 0.8570737605804112,
|
| 224 |
+
"eval_loss": 1.081692099571228,
|
| 225 |
+
"eval_precision": 0.784070796460177,
|
| 226 |
+
"eval_recall": 0.9450666666666667,
|
| 227 |
+
"eval_runtime": 305.0927,
|
| 228 |
+
"eval_samples_per_second": 12.291,
|
| 229 |
+
"eval_steps_per_second": 1.537,
|
| 230 |
+
"step": 516
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.26,
|
| 234 |
+
"learning_rate": 3.7225776965265085e-05,
|
| 235 |
+
"loss": 0.6488,
|
| 236 |
+
"step": 559
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.26,
|
| 240 |
+
"eval_accuracy": 0.8365333333333334,
|
| 241 |
+
"eval_f1": 0.8115585613280049,
|
| 242 |
+
"eval_loss": 0.5578557252883911,
|
| 243 |
+
"eval_precision": 0.9579100145137881,
|
| 244 |
+
"eval_recall": 0.704,
|
| 245 |
+
"eval_runtime": 305.0779,
|
| 246 |
+
"eval_samples_per_second": 12.292,
|
| 247 |
+
"eval_steps_per_second": 1.537,
|
| 248 |
+
"step": 559
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.28,
|
| 252 |
+
"learning_rate": 3.624314442413163e-05,
|
| 253 |
+
"loss": 0.9679,
|
| 254 |
+
"step": 602
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"eval_accuracy": 0.6829333333333333,
|
| 259 |
+
"eval_f1": 0.5987175160310497,
|
| 260 |
+
"eval_loss": 0.9434438943862915,
|
| 261 |
+
"eval_precision": 0.8152573529411765,
|
| 262 |
+
"eval_recall": 0.4730666666666667,
|
| 263 |
+
"eval_runtime": 304.9674,
|
| 264 |
+
"eval_samples_per_second": 12.296,
|
| 265 |
+
"eval_steps_per_second": 1.538,
|
| 266 |
+
"step": 602
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.29,
|
| 270 |
+
"learning_rate": 3.526051188299818e-05,
|
| 271 |
+
"loss": 0.4584,
|
| 272 |
+
"step": 645
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.29,
|
| 276 |
+
"eval_accuracy": 0.8458666666666667,
|
| 277 |
+
"eval_f1": 0.8547008547008548,
|
| 278 |
+
"eval_loss": 0.44859734177589417,
|
| 279 |
+
"eval_precision": 0.8083689966714218,
|
| 280 |
+
"eval_recall": 0.9066666666666666,
|
| 281 |
+
"eval_runtime": 304.9696,
|
| 282 |
+
"eval_samples_per_second": 12.296,
|
| 283 |
+
"eval_steps_per_second": 1.538,
|
| 284 |
+
"step": 645
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.31,
|
| 288 |
+
"learning_rate": 3.4277879341864715e-05,
|
| 289 |
+
"loss": 0.418,
|
| 290 |
+
"step": 688
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.31,
|
| 294 |
+
"eval_accuracy": 0.8901333333333333,
|
| 295 |
+
"eval_f1": 0.892931392931393,
|
| 296 |
+
"eval_loss": 0.5646004676818848,
|
| 297 |
+
"eval_precision": 0.8707551951343132,
|
| 298 |
+
"eval_recall": 0.9162666666666667,
|
| 299 |
+
"eval_runtime": 304.779,
|
| 300 |
+
"eval_samples_per_second": 12.304,
|
| 301 |
+
"eval_steps_per_second": 1.539,
|
| 302 |
+
"step": 688
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.33,
|
| 306 |
+
"learning_rate": 3.329524680073126e-05,
|
| 307 |
+
"loss": 0.5809,
|
| 308 |
+
"step": 731
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.33,
|
| 312 |
+
"eval_accuracy": 0.8773333333333333,
|
| 313 |
+
"eval_f1": 0.8847117794486216,
|
| 314 |
+
"eval_loss": 0.4200115501880646,
|
| 315 |
+
"eval_precision": 0.83451536643026,
|
| 316 |
+
"eval_recall": 0.9413333333333334,
|
| 317 |
+
"eval_runtime": 304.7969,
|
| 318 |
+
"eval_samples_per_second": 12.303,
|
| 319 |
+
"eval_steps_per_second": 1.539,
|
| 320 |
+
"step": 731
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.35,
|
| 324 |
+
"learning_rate": 3.231261425959781e-05,
|
| 325 |
+
"loss": 0.4702,
|
| 326 |
+
"step": 774
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.35,
|
| 330 |
+
"eval_accuracy": 0.7117333333333333,
|
| 331 |
+
"eval_f1": 0.7615265828369733,
|
| 332 |
+
"eval_loss": 0.5946761965751648,
|
| 333 |
+
"eval_precision": 0.6493604213694507,
|
| 334 |
+
"eval_recall": 0.9205333333333333,
|
| 335 |
+
"eval_runtime": 304.8632,
|
| 336 |
+
"eval_samples_per_second": 12.301,
|
| 337 |
+
"eval_steps_per_second": 1.538,
|
| 338 |
+
"step": 774
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.37,
|
| 342 |
+
"learning_rate": 3.132998171846435e-05,
|
| 343 |
+
"loss": 0.3684,
|
| 344 |
+
"step": 817
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.37,
|
| 348 |
+
"eval_accuracy": 0.8965333333333333,
|
| 349 |
+
"eval_f1": 0.8914381645215446,
|
| 350 |
+
"eval_loss": 0.30674976110458374,
|
| 351 |
+
"eval_precision": 0.9376103590347263,
|
| 352 |
+
"eval_recall": 0.8496,
|
| 353 |
+
"eval_runtime": 304.8468,
|
| 354 |
+
"eval_samples_per_second": 12.301,
|
| 355 |
+
"eval_steps_per_second": 1.538,
|
| 356 |
+
"step": 817
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.39,
|
| 360 |
+
"learning_rate": 3.03473491773309e-05,
|
| 361 |
+
"loss": 0.5431,
|
| 362 |
+
"step": 860
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.39,
|
| 366 |
+
"eval_accuracy": 0.8762666666666666,
|
| 367 |
+
"eval_f1": 0.8831234256926952,
|
| 368 |
+
"eval_loss": 0.8089134693145752,
|
| 369 |
+
"eval_precision": 0.8367541766109785,
|
| 370 |
+
"eval_recall": 0.9349333333333333,
|
| 371 |
+
"eval_runtime": 304.976,
|
| 372 |
+
"eval_samples_per_second": 12.296,
|
| 373 |
+
"eval_steps_per_second": 1.538,
|
| 374 |
+
"step": 860
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.41,
|
| 378 |
+
"learning_rate": 2.9364716636197442e-05,
|
| 379 |
+
"loss": 0.4287,
|
| 380 |
+
"step": 903
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.41,
|
| 384 |
+
"eval_accuracy": 0.8466666666666667,
|
| 385 |
+
"eval_f1": 0.822366388631449,
|
| 386 |
+
"eval_loss": 0.49679452180862427,
|
| 387 |
+
"eval_precision": 0.9772393538913363,
|
| 388 |
+
"eval_recall": 0.7098666666666666,
|
| 389 |
+
"eval_runtime": 306.5019,
|
| 390 |
+
"eval_samples_per_second": 12.235,
|
| 391 |
+
"eval_steps_per_second": 1.53,
|
| 392 |
+
"step": 903
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.43,
|
| 396 |
+
"learning_rate": 2.838208409506399e-05,
|
| 397 |
+
"loss": 0.4942,
|
| 398 |
+
"step": 946
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.43,
|
| 402 |
+
"eval_accuracy": 0.9157333333333333,
|
| 403 |
+
"eval_f1": 0.9138025095471904,
|
| 404 |
+
"eval_loss": 0.23615875840187073,
|
| 405 |
+
"eval_precision": 0.9352317141261864,
|
| 406 |
+
"eval_recall": 0.8933333333333333,
|
| 407 |
+
"eval_runtime": 305.2275,
|
| 408 |
+
"eval_samples_per_second": 12.286,
|
| 409 |
+
"eval_steps_per_second": 1.537,
|
| 410 |
+
"step": 946
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.45,
|
| 414 |
+
"learning_rate": 2.739945155393053e-05,
|
| 415 |
+
"loss": 0.3997,
|
| 416 |
+
"step": 989
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.45,
|
| 420 |
+
"eval_accuracy": 0.8874666666666666,
|
| 421 |
+
"eval_f1": 0.8867418142780461,
|
| 422 |
+
"eval_loss": 0.6193059086799622,
|
| 423 |
+
"eval_precision": 0.8924905456509995,
|
| 424 |
+
"eval_recall": 0.8810666666666667,
|
| 425 |
+
"eval_runtime": 304.7962,
|
| 426 |
+
"eval_samples_per_second": 12.303,
|
| 427 |
+
"eval_steps_per_second": 1.539,
|
| 428 |
+
"step": 989
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.47,
|
| 432 |
+
"learning_rate": 2.641681901279708e-05,
|
| 433 |
+
"loss": 0.3862,
|
| 434 |
+
"step": 1032
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.47,
|
| 438 |
+
"eval_accuracy": 0.8712,
|
| 439 |
+
"eval_f1": 0.8817625458996328,
|
| 440 |
+
"eval_loss": 0.6541677713394165,
|
| 441 |
+
"eval_precision": 0.8149321266968326,
|
| 442 |
+
"eval_recall": 0.9605333333333334,
|
| 443 |
+
"eval_runtime": 305.7101,
|
| 444 |
+
"eval_samples_per_second": 12.267,
|
| 445 |
+
"eval_steps_per_second": 1.534,
|
| 446 |
+
"step": 1032
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.49,
|
| 450 |
+
"learning_rate": 2.5434186471663625e-05,
|
| 451 |
+
"loss": 0.4199,
|
| 452 |
+
"step": 1075
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.49,
|
| 456 |
+
"eval_accuracy": 0.8778666666666667,
|
| 457 |
+
"eval_f1": 0.8674768518518517,
|
| 458 |
+
"eval_loss": 0.5205650329589844,
|
| 459 |
+
"eval_precision": 0.948134092346616,
|
| 460 |
+
"eval_recall": 0.7994666666666667,
|
| 461 |
+
"eval_runtime": 306.2355,
|
| 462 |
+
"eval_samples_per_second": 12.245,
|
| 463 |
+
"eval_steps_per_second": 1.532,
|
| 464 |
+
"step": 1075
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.51,
|
| 468 |
+
"learning_rate": 2.4451553930530165e-05,
|
| 469 |
+
"loss": 0.4922,
|
| 470 |
+
"step": 1118
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.51,
|
| 474 |
+
"eval_accuracy": 0.8664,
|
| 475 |
+
"eval_f1": 0.8587538765153652,
|
| 476 |
+
"eval_loss": 0.3552885353565216,
|
| 477 |
+
"eval_precision": 0.9108851674641149,
|
| 478 |
+
"eval_recall": 0.8122666666666667,
|
| 479 |
+
"eval_runtime": 305.1994,
|
| 480 |
+
"eval_samples_per_second": 12.287,
|
| 481 |
+
"eval_steps_per_second": 1.537,
|
| 482 |
+
"step": 1118
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.53,
|
| 486 |
+
"learning_rate": 2.346892138939671e-05,
|
| 487 |
+
"loss": 0.3303,
|
| 488 |
+
"step": 1161
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.53,
|
| 492 |
+
"eval_accuracy": 0.9082666666666667,
|
| 493 |
+
"eval_f1": 0.9038569032979319,
|
| 494 |
+
"eval_loss": 0.38709646463394165,
|
| 495 |
+
"eval_precision": 0.9495008807985907,
|
| 496 |
+
"eval_recall": 0.8624,
|
| 497 |
+
"eval_runtime": 305.1281,
|
| 498 |
+
"eval_samples_per_second": 12.29,
|
| 499 |
+
"eval_steps_per_second": 1.537,
|
| 500 |
+
"step": 1161
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.55,
|
| 504 |
+
"learning_rate": 2.2486288848263255e-05,
|
| 505 |
+
"loss": 0.2829,
|
| 506 |
+
"step": 1204
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.55,
|
| 510 |
+
"eval_accuracy": 0.9104,
|
| 511 |
+
"eval_f1": 0.9114391143911439,
|
| 512 |
+
"eval_loss": 0.3015682101249695,
|
| 513 |
+
"eval_precision": 0.900990099009901,
|
| 514 |
+
"eval_recall": 0.9221333333333334,
|
| 515 |
+
"eval_runtime": 305.3174,
|
| 516 |
+
"eval_samples_per_second": 12.282,
|
| 517 |
+
"eval_steps_per_second": 1.536,
|
| 518 |
+
"step": 1204
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.57,
|
| 522 |
+
"learning_rate": 2.1503656307129798e-05,
|
| 523 |
+
"loss": 0.5477,
|
| 524 |
+
"step": 1247
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.57,
|
| 528 |
+
"eval_accuracy": 0.8509333333333333,
|
| 529 |
+
"eval_f1": 0.8479738917595866,
|
| 530 |
+
"eval_loss": 0.5632778406143188,
|
| 531 |
+
"eval_precision": 0.865149833518313,
|
| 532 |
+
"eval_recall": 0.8314666666666667,
|
| 533 |
+
"eval_runtime": 305.058,
|
| 534 |
+
"eval_samples_per_second": 12.293,
|
| 535 |
+
"eval_steps_per_second": 1.537,
|
| 536 |
+
"step": 1247
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.59,
|
| 540 |
+
"learning_rate": 2.0521023765996345e-05,
|
| 541 |
+
"loss": 0.4431,
|
| 542 |
+
"step": 1290
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.59,
|
| 546 |
+
"eval_accuracy": 0.9082666666666667,
|
| 547 |
+
"eval_f1": 0.9050248481501934,
|
| 548 |
+
"eval_loss": 0.42895591259002686,
|
| 549 |
+
"eval_precision": 0.9381797366914711,
|
| 550 |
+
"eval_recall": 0.8741333333333333,
|
| 551 |
+
"eval_runtime": 305.0347,
|
| 552 |
+
"eval_samples_per_second": 12.294,
|
| 553 |
+
"eval_steps_per_second": 1.538,
|
| 554 |
+
"step": 1290
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.61,
|
| 558 |
+
"learning_rate": 1.953839122486289e-05,
|
| 559 |
+
"loss": 0.3335,
|
| 560 |
+
"step": 1333
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.61,
|
| 564 |
+
"eval_accuracy": 0.9069333333333334,
|
| 565 |
+
"eval_f1": 0.90008588605783,
|
| 566 |
+
"eval_loss": 0.32379406690597534,
|
| 567 |
+
"eval_precision": 0.9715698393077874,
|
| 568 |
+
"eval_recall": 0.8384,
|
| 569 |
+
"eval_runtime": 306.6476,
|
| 570 |
+
"eval_samples_per_second": 12.229,
|
| 571 |
+
"eval_steps_per_second": 1.529,
|
| 572 |
+
"step": 1333
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.63,
|
| 576 |
+
"learning_rate": 1.8555758683729435e-05,
|
| 577 |
+
"loss": 0.3255,
|
| 578 |
+
"step": 1376
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.63,
|
| 582 |
+
"eval_accuracy": 0.9152,
|
| 583 |
+
"eval_f1": 0.9159619450317126,
|
| 584 |
+
"eval_loss": 0.3898433446884155,
|
| 585 |
+
"eval_precision": 0.9078051335777895,
|
| 586 |
+
"eval_recall": 0.9242666666666667,
|
| 587 |
+
"eval_runtime": 305.4671,
|
| 588 |
+
"eval_samples_per_second": 12.276,
|
| 589 |
+
"eval_steps_per_second": 1.535,
|
| 590 |
+
"step": 1376
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.65,
|
| 594 |
+
"learning_rate": 1.7573126142595978e-05,
|
| 595 |
+
"loss": 0.3103,
|
| 596 |
+
"step": 1419
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.65,
|
| 600 |
+
"eval_accuracy": 0.9189333333333334,
|
| 601 |
+
"eval_f1": 0.9140271493212669,
|
| 602 |
+
"eval_loss": 0.25054827332496643,
|
| 603 |
+
"eval_precision": 0.9729078868151716,
|
| 604 |
+
"eval_recall": 0.8618666666666667,
|
| 605 |
+
"eval_runtime": 304.9946,
|
| 606 |
+
"eval_samples_per_second": 12.295,
|
| 607 |
+
"eval_steps_per_second": 1.538,
|
| 608 |
+
"step": 1419
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.67,
|
| 612 |
+
"learning_rate": 1.659049360146252e-05,
|
| 613 |
+
"loss": 0.2878,
|
| 614 |
+
"step": 1462
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.67,
|
| 618 |
+
"eval_accuracy": 0.9208,
|
| 619 |
+
"eval_f1": 0.9207788743664976,
|
| 620 |
+
"eval_loss": 0.29952123761177063,
|
| 621 |
+
"eval_precision": 0.9210245464247598,
|
| 622 |
+
"eval_recall": 0.9205333333333333,
|
| 623 |
+
"eval_runtime": 304.6679,
|
| 624 |
+
"eval_samples_per_second": 12.308,
|
| 625 |
+
"eval_steps_per_second": 1.539,
|
| 626 |
+
"step": 1462
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.69,
|
| 630 |
+
"learning_rate": 1.5607861060329068e-05,
|
| 631 |
+
"loss": 0.3426,
|
| 632 |
+
"step": 1505
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.69,
|
| 636 |
+
"eval_accuracy": 0.9248,
|
| 637 |
+
"eval_f1": 0.9255936675461741,
|
| 638 |
+
"eval_loss": 0.3102300763130188,
|
| 639 |
+
"eval_precision": 0.9159268929503916,
|
| 640 |
+
"eval_recall": 0.9354666666666667,
|
| 641 |
+
"eval_runtime": 305.1368,
|
| 642 |
+
"eval_samples_per_second": 12.29,
|
| 643 |
+
"eval_steps_per_second": 1.537,
|
| 644 |
+
"step": 1505
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.71,
|
| 648 |
+
"learning_rate": 1.4625228519195613e-05,
|
| 649 |
+
"loss": 0.2799,
|
| 650 |
+
"step": 1548
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.71,
|
| 654 |
+
"eval_accuracy": 0.9226666666666666,
|
| 655 |
+
"eval_f1": 0.9236440231700894,
|
| 656 |
+
"eval_loss": 0.32980650663375854,
|
| 657 |
+
"eval_precision": 0.9121164846593863,
|
| 658 |
+
"eval_recall": 0.9354666666666667,
|
| 659 |
+
"eval_runtime": 305.2653,
|
| 660 |
+
"eval_samples_per_second": 12.284,
|
| 661 |
+
"eval_steps_per_second": 1.536,
|
| 662 |
+
"step": 1548
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.73,
|
| 666 |
+
"learning_rate": 1.3642595978062158e-05,
|
| 667 |
+
"loss": 0.4076,
|
| 668 |
+
"step": 1591
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.73,
|
| 672 |
+
"eval_accuracy": 0.9277333333333333,
|
| 673 |
+
"eval_f1": 0.9256515775034294,
|
| 674 |
+
"eval_loss": 0.29825451970100403,
|
| 675 |
+
"eval_precision": 0.9531073446327684,
|
| 676 |
+
"eval_recall": 0.8997333333333334,
|
| 677 |
+
"eval_runtime": 304.9271,
|
| 678 |
+
"eval_samples_per_second": 12.298,
|
| 679 |
+
"eval_steps_per_second": 1.538,
|
| 680 |
+
"step": 1591
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.75,
|
| 684 |
+
"learning_rate": 1.2659963436928701e-05,
|
| 685 |
+
"loss": 0.2303,
|
| 686 |
+
"step": 1634
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.75,
|
| 690 |
+
"eval_accuracy": 0.9168,
|
| 691 |
+
"eval_f1": 0.9147540983606557,
|
| 692 |
+
"eval_loss": 0.27176761627197266,
|
| 693 |
+
"eval_precision": 0.9378151260504202,
|
| 694 |
+
"eval_recall": 0.8928,
|
| 695 |
+
"eval_runtime": 305.6751,
|
| 696 |
+
"eval_samples_per_second": 12.268,
|
| 697 |
+
"eval_steps_per_second": 1.534,
|
| 698 |
+
"step": 1634
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.77,
|
| 702 |
+
"learning_rate": 1.1677330895795248e-05,
|
| 703 |
+
"loss": 0.2793,
|
| 704 |
+
"step": 1677
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.77,
|
| 708 |
+
"eval_accuracy": 0.9229333333333334,
|
| 709 |
+
"eval_f1": 0.9229949373834265,
|
| 710 |
+
"eval_loss": 0.34073972702026367,
|
| 711 |
+
"eval_precision": 0.9222577209797657,
|
| 712 |
+
"eval_recall": 0.9237333333333333,
|
| 713 |
+
"eval_runtime": 305.4396,
|
| 714 |
+
"eval_samples_per_second": 12.277,
|
| 715 |
+
"eval_steps_per_second": 1.535,
|
| 716 |
+
"step": 1677
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.79,
|
| 720 |
+
"learning_rate": 1.0694698354661791e-05,
|
| 721 |
+
"loss": 0.226,
|
| 722 |
+
"step": 1720
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.79,
|
| 726 |
+
"eval_accuracy": 0.9290666666666667,
|
| 727 |
+
"eval_f1": 0.9279132791327913,
|
| 728 |
+
"eval_loss": 0.34017863869667053,
|
| 729 |
+
"eval_precision": 0.9432506887052342,
|
| 730 |
+
"eval_recall": 0.9130666666666667,
|
| 731 |
+
"eval_runtime": 304.4994,
|
| 732 |
+
"eval_samples_per_second": 12.315,
|
| 733 |
+
"eval_steps_per_second": 1.54,
|
| 734 |
+
"step": 1720
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.81,
|
| 738 |
+
"learning_rate": 9.712065813528338e-06,
|
| 739 |
+
"loss": 0.5583,
|
| 740 |
+
"step": 1763
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.81,
|
| 744 |
+
"eval_accuracy": 0.92,
|
| 745 |
+
"eval_f1": 0.9220779220779222,
|
| 746 |
+
"eval_loss": 0.26789960265159607,
|
| 747 |
+
"eval_precision": 0.8987341772151899,
|
| 748 |
+
"eval_recall": 0.9466666666666667,
|
| 749 |
+
"eval_runtime": 304.5833,
|
| 750 |
+
"eval_samples_per_second": 12.312,
|
| 751 |
+
"eval_steps_per_second": 1.54,
|
| 752 |
+
"step": 1763
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.83,
|
| 756 |
+
"learning_rate": 8.729433272394881e-06,
|
| 757 |
+
"loss": 0.2609,
|
| 758 |
+
"step": 1806
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.83,
|
| 762 |
+
"eval_accuracy": 0.9293333333333333,
|
| 763 |
+
"eval_f1": 0.928436402916554,
|
| 764 |
+
"eval_loss": 0.3069748878479004,
|
| 765 |
+
"eval_precision": 0.9403719912472648,
|
| 766 |
+
"eval_recall": 0.9168,
|
| 767 |
+
"eval_runtime": 305.3926,
|
| 768 |
+
"eval_samples_per_second": 12.279,
|
| 769 |
+
"eval_steps_per_second": 1.536,
|
| 770 |
+
"step": 1806
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.85,
|
| 774 |
+
"learning_rate": 7.746800731261426e-06,
|
| 775 |
+
"loss": 0.3392,
|
| 776 |
+
"step": 1849
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.85,
|
| 780 |
+
"eval_accuracy": 0.9309333333333333,
|
| 781 |
+
"eval_f1": 0.928748280605227,
|
| 782 |
+
"eval_loss": 0.24878720939159393,
|
| 783 |
+
"eval_precision": 0.9590909090909091,
|
| 784 |
+
"eval_recall": 0.9002666666666667,
|
| 785 |
+
"eval_runtime": 305.0861,
|
| 786 |
+
"eval_samples_per_second": 12.292,
|
| 787 |
+
"eval_steps_per_second": 1.537,
|
| 788 |
+
"step": 1849
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.86,
|
| 792 |
+
"learning_rate": 6.764168190127972e-06,
|
| 793 |
+
"loss": 0.3378,
|
| 794 |
+
"step": 1892
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.86,
|
| 798 |
+
"eval_accuracy": 0.9272,
|
| 799 |
+
"eval_f1": 0.9248554913294799,
|
| 800 |
+
"eval_loss": 0.2940199077129364,
|
| 801 |
+
"eval_precision": 0.9556313993174061,
|
| 802 |
+
"eval_recall": 0.896,
|
| 803 |
+
"eval_runtime": 304.8472,
|
| 804 |
+
"eval_samples_per_second": 12.301,
|
| 805 |
+
"eval_steps_per_second": 1.538,
|
| 806 |
+
"step": 1892
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.88,
|
| 810 |
+
"learning_rate": 5.781535648994515e-06,
|
| 811 |
+
"loss": 0.2271,
|
| 812 |
+
"step": 1935
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.88,
|
| 816 |
+
"eval_accuracy": 0.9349333333333333,
|
| 817 |
+
"eval_f1": 0.934654525977504,
|
| 818 |
+
"eval_loss": 0.23414117097854614,
|
| 819 |
+
"eval_precision": 0.9386767079074771,
|
| 820 |
+
"eval_recall": 0.9306666666666666,
|
| 821 |
+
"eval_runtime": 304.8432,
|
| 822 |
+
"eval_samples_per_second": 12.301,
|
| 823 |
+
"eval_steps_per_second": 1.538,
|
| 824 |
+
"step": 1935
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.9,
|
| 828 |
+
"learning_rate": 4.798903107861061e-06,
|
| 829 |
+
"loss": 0.4284,
|
| 830 |
+
"step": 1978
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.9,
|
| 834 |
+
"eval_accuracy": 0.9325333333333333,
|
| 835 |
+
"eval_f1": 0.9310438811665304,
|
| 836 |
+
"eval_loss": 0.30585160851478577,
|
| 837 |
+
"eval_precision": 0.9520624303232998,
|
| 838 |
+
"eval_recall": 0.9109333333333334,
|
| 839 |
+
"eval_runtime": 304.8244,
|
| 840 |
+
"eval_samples_per_second": 12.302,
|
| 841 |
+
"eval_steps_per_second": 1.539,
|
| 842 |
+
"step": 1978
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.92,
|
| 846 |
+
"learning_rate": 3.816270566727605e-06,
|
| 847 |
+
"loss": 0.2887,
|
| 848 |
+
"step": 2021
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.92,
|
| 852 |
+
"eval_accuracy": 0.9341333333333334,
|
| 853 |
+
"eval_f1": 0.9327158812312721,
|
| 854 |
+
"eval_loss": 0.27199041843414307,
|
| 855 |
+
"eval_precision": 0.9532293986636972,
|
| 856 |
+
"eval_recall": 0.9130666666666667,
|
| 857 |
+
"eval_runtime": 305.2967,
|
| 858 |
+
"eval_samples_per_second": 12.283,
|
| 859 |
+
"eval_steps_per_second": 1.536,
|
| 860 |
+
"step": 2021
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.94,
|
| 864 |
+
"learning_rate": 2.83363802559415e-06,
|
| 865 |
+
"loss": 0.2287,
|
| 866 |
+
"step": 2064
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.94,
|
| 870 |
+
"eval_accuracy": 0.9362666666666667,
|
| 871 |
+
"eval_f1": 0.9355273806312382,
|
| 872 |
+
"eval_loss": 0.3032676577568054,
|
| 873 |
+
"eval_precision": 0.9465065502183406,
|
| 874 |
+
"eval_recall": 0.9248,
|
| 875 |
+
"eval_runtime": 305.4791,
|
| 876 |
+
"eval_samples_per_second": 12.276,
|
| 877 |
+
"eval_steps_per_second": 1.535,
|
| 878 |
+
"step": 2064
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.96,
|
| 882 |
+
"learning_rate": 1.851005484460695e-06,
|
| 883 |
+
"loss": 0.3379,
|
| 884 |
+
"step": 2107
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.96,
|
| 888 |
+
"eval_accuracy": 0.9362666666666667,
|
| 889 |
+
"eval_f1": 0.9354577369700243,
|
| 890 |
+
"eval_loss": 0.25949496030807495,
|
| 891 |
+
"eval_precision": 0.9474835886214442,
|
| 892 |
+
"eval_recall": 0.9237333333333333,
|
| 893 |
+
"eval_runtime": 305.1987,
|
| 894 |
+
"eval_samples_per_second": 12.287,
|
| 895 |
+
"eval_steps_per_second": 1.537,
|
| 896 |
+
"step": 2107
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.98,
|
| 900 |
+
"learning_rate": 8.683729433272396e-07,
|
| 901 |
+
"loss": 0.2405,
|
| 902 |
+
"step": 2150
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.98,
|
| 906 |
+
"eval_accuracy": 0.9354666666666667,
|
| 907 |
+
"eval_f1": 0.9345238095238096,
|
| 908 |
+
"eval_loss": 0.2737696170806885,
|
| 909 |
+
"eval_precision": 0.9483800109829764,
|
| 910 |
+
"eval_recall": 0.9210666666666667,
|
| 911 |
+
"eval_runtime": 304.727,
|
| 912 |
+
"eval_samples_per_second": 12.306,
|
| 913 |
+
"eval_steps_per_second": 1.539,
|
| 914 |
+
"step": 2150
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"max_steps": 2188,
|
| 918 |
+
"num_train_epochs": 1,
|
| 919 |
+
"total_flos": 6.497491746816e+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 sha256:37ee409cc674da36a57ac4c9c0992b866257aa1147ccbdeec0e7e20912b47bd7
|
| 3 |
+
size 3451
|