Commit
·
28d8247
1
Parent(s):
f486069
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 sha256:02327efcf7b09ce4e6f4076861caabbc5a9ba706287ac7c9fa1c5d245d41a288
|
| 3 |
+
size 13779559309
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e1843985d65d92cb4cafa4d4d876cf38216612b9052b535a1d4997eb573d80a
|
| 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 sha256:19c575370b6179b490f435df9c74d0ea7aabd16f264cf932690c39af9fca6ebb
|
| 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-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": 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": 3.1194,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.9e-05,
|
| 19 |
+
"loss": 3.222,
|
| 20 |
+
"step": 35
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.5,
|
| 25 |
+
"eval_f1": 0.0,
|
| 26 |
+
"eval_loss": 0.6869668960571289,
|
| 27 |
+
"eval_precision": 0.0,
|
| 28 |
+
"eval_recall": 0.0,
|
| 29 |
+
"eval_runtime": 240.1814,
|
| 30 |
+
"eval_samples_per_second": 12.491,
|
| 31 |
+
"eval_steps_per_second": 1.561,
|
| 32 |
+
"step": 35
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 4.8e-05,
|
| 37 |
+
"loss": 1.7052,
|
| 38 |
+
"step": 70
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_accuracy": 0.5,
|
| 43 |
+
"eval_f1": 0.0,
|
| 44 |
+
"eval_loss": 2.0989105701446533,
|
| 45 |
+
"eval_precision": 0.0,
|
| 46 |
+
"eval_recall": 0.0,
|
| 47 |
+
"eval_runtime": 240.275,
|
| 48 |
+
"eval_samples_per_second": 12.486,
|
| 49 |
+
"eval_steps_per_second": 1.561,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 4.7e-05,
|
| 55 |
+
"loss": 1.4622,
|
| 56 |
+
"step": 105
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_accuracy": 0.5,
|
| 61 |
+
"eval_f1": 0.6666666666666666,
|
| 62 |
+
"eval_loss": 0.706234872341156,
|
| 63 |
+
"eval_precision": 0.5,
|
| 64 |
+
"eval_recall": 1.0,
|
| 65 |
+
"eval_runtime": 240.4103,
|
| 66 |
+
"eval_samples_per_second": 12.479,
|
| 67 |
+
"eval_steps_per_second": 1.56,
|
| 68 |
+
"step": 105
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"learning_rate": 4.600000000000001e-05,
|
| 73 |
+
"loss": 0.9345,
|
| 74 |
+
"step": 140
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"eval_accuracy": 0.514,
|
| 79 |
+
"eval_f1": 0.6729475100942127,
|
| 80 |
+
"eval_loss": 0.7361006140708923,
|
| 81 |
+
"eval_precision": 0.5070993914807302,
|
| 82 |
+
"eval_recall": 1.0,
|
| 83 |
+
"eval_runtime": 240.3366,
|
| 84 |
+
"eval_samples_per_second": 12.482,
|
| 85 |
+
"eval_steps_per_second": 1.56,
|
| 86 |
+
"step": 140
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 4.5e-05,
|
| 91 |
+
"loss": 1.3471,
|
| 92 |
+
"step": 175
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.1,
|
| 96 |
+
"eval_accuracy": 0.5063333333333333,
|
| 97 |
+
"eval_f1": 0.6693458361241348,
|
| 98 |
+
"eval_loss": 0.7378450632095337,
|
| 99 |
+
"eval_precision": 0.5031889895938234,
|
| 100 |
+
"eval_recall": 0.9993333333333333,
|
| 101 |
+
"eval_runtime": 240.3903,
|
| 102 |
+
"eval_samples_per_second": 12.48,
|
| 103 |
+
"eval_steps_per_second": 1.56,
|
| 104 |
+
"step": 175
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12,
|
| 108 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 109 |
+
"loss": 1.0776,
|
| 110 |
+
"step": 210
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12,
|
| 114 |
+
"eval_accuracy": 0.502,
|
| 115 |
+
"eval_f1": 0.6675567423230975,
|
| 116 |
+
"eval_loss": 1.2094249725341797,
|
| 117 |
+
"eval_precision": 0.501002004008016,
|
| 118 |
+
"eval_recall": 1.0,
|
| 119 |
+
"eval_runtime": 241.2524,
|
| 120 |
+
"eval_samples_per_second": 12.435,
|
| 121 |
+
"eval_steps_per_second": 1.554,
|
| 122 |
+
"step": 210
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14,
|
| 126 |
+
"learning_rate": 4.3e-05,
|
| 127 |
+
"loss": 0.7897,
|
| 128 |
+
"step": 245
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"eval_accuracy": 0.818,
|
| 133 |
+
"eval_f1": 0.8189655172413793,
|
| 134 |
+
"eval_loss": 0.42468851804733276,
|
| 135 |
+
"eval_precision": 0.8146437994722955,
|
| 136 |
+
"eval_recall": 0.8233333333333334,
|
| 137 |
+
"eval_runtime": 240.4771,
|
| 138 |
+
"eval_samples_per_second": 12.475,
|
| 139 |
+
"eval_steps_per_second": 1.559,
|
| 140 |
+
"step": 245
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 4.2e-05,
|
| 145 |
+
"loss": 0.8229,
|
| 146 |
+
"step": 280
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"eval_accuracy": 0.6603333333333333,
|
| 151 |
+
"eval_f1": 0.7405143875732112,
|
| 152 |
+
"eval_loss": 0.7496446967124939,
|
| 153 |
+
"eval_precision": 0.5990935311083643,
|
| 154 |
+
"eval_recall": 0.9693333333333334,
|
| 155 |
+
"eval_runtime": 241.2847,
|
| 156 |
+
"eval_samples_per_second": 12.433,
|
| 157 |
+
"eval_steps_per_second": 1.554,
|
| 158 |
+
"step": 280
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18,
|
| 162 |
+
"learning_rate": 4.1e-05,
|
| 163 |
+
"loss": 0.8056,
|
| 164 |
+
"step": 315
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18,
|
| 168 |
+
"eval_accuracy": 0.653,
|
| 169 |
+
"eval_f1": 0.7400749063670412,
|
| 170 |
+
"eval_loss": 0.7388193607330322,
|
| 171 |
+
"eval_precision": 0.5916167664670658,
|
| 172 |
+
"eval_recall": 0.988,
|
| 173 |
+
"eval_runtime": 240.4851,
|
| 174 |
+
"eval_samples_per_second": 12.475,
|
| 175 |
+
"eval_steps_per_second": 1.559,
|
| 176 |
+
"step": 315
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2,
|
| 180 |
+
"learning_rate": 4e-05,
|
| 181 |
+
"loss": 0.831,
|
| 182 |
+
"step": 350
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2,
|
| 186 |
+
"eval_accuracy": 0.7976666666666666,
|
| 187 |
+
"eval_f1": 0.7876880027981812,
|
| 188 |
+
"eval_loss": 0.45541757345199585,
|
| 189 |
+
"eval_precision": 0.8285504047093452,
|
| 190 |
+
"eval_recall": 0.7506666666666667,
|
| 191 |
+
"eval_runtime": 240.8878,
|
| 192 |
+
"eval_samples_per_second": 12.454,
|
| 193 |
+
"eval_steps_per_second": 1.557,
|
| 194 |
+
"step": 350
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.22,
|
| 198 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 199 |
+
"loss": 0.3693,
|
| 200 |
+
"step": 385
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"eval_accuracy": 0.764,
|
| 205 |
+
"eval_f1": 0.7972508591065293,
|
| 206 |
+
"eval_loss": 0.567838191986084,
|
| 207 |
+
"eval_precision": 0.6987951807228916,
|
| 208 |
+
"eval_recall": 0.928,
|
| 209 |
+
"eval_runtime": 240.8981,
|
| 210 |
+
"eval_samples_per_second": 12.453,
|
| 211 |
+
"eval_steps_per_second": 1.557,
|
| 212 |
+
"step": 385
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24,
|
| 216 |
+
"learning_rate": 3.8e-05,
|
| 217 |
+
"loss": 0.7178,
|
| 218 |
+
"step": 420
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.24,
|
| 222 |
+
"eval_accuracy": 0.8273333333333334,
|
| 223 |
+
"eval_f1": 0.832579185520362,
|
| 224 |
+
"eval_loss": 0.4122844934463501,
|
| 225 |
+
"eval_precision": 0.8080301129234629,
|
| 226 |
+
"eval_recall": 0.8586666666666667,
|
| 227 |
+
"eval_runtime": 240.7253,
|
| 228 |
+
"eval_samples_per_second": 12.462,
|
| 229 |
+
"eval_steps_per_second": 1.558,
|
| 230 |
+
"step": 420
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.26,
|
| 234 |
+
"learning_rate": 3.7e-05,
|
| 235 |
+
"loss": 0.5769,
|
| 236 |
+
"step": 455
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.26,
|
| 240 |
+
"eval_accuracy": 0.8406666666666667,
|
| 241 |
+
"eval_f1": 0.8505315822388994,
|
| 242 |
+
"eval_loss": 0.3792554438114166,
|
| 243 |
+
"eval_precision": 0.800942285041225,
|
| 244 |
+
"eval_recall": 0.9066666666666666,
|
| 245 |
+
"eval_runtime": 240.7257,
|
| 246 |
+
"eval_samples_per_second": 12.462,
|
| 247 |
+
"eval_steps_per_second": 1.558,
|
| 248 |
+
"step": 455
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.28,
|
| 252 |
+
"learning_rate": 3.6e-05,
|
| 253 |
+
"loss": 0.5896,
|
| 254 |
+
"step": 490
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"eval_accuracy": 0.6713333333333333,
|
| 259 |
+
"eval_f1": 0.7512613521695257,
|
| 260 |
+
"eval_loss": 0.8622921705245972,
|
| 261 |
+
"eval_precision": 0.604301948051948,
|
| 262 |
+
"eval_recall": 0.9926666666666667,
|
| 263 |
+
"eval_runtime": 240.7579,
|
| 264 |
+
"eval_samples_per_second": 12.461,
|
| 265 |
+
"eval_steps_per_second": 1.558,
|
| 266 |
+
"step": 490
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.3,
|
| 270 |
+
"learning_rate": 3.5e-05,
|
| 271 |
+
"loss": 0.4586,
|
| 272 |
+
"step": 525
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.3,
|
| 276 |
+
"eval_accuracy": 0.8066666666666666,
|
| 277 |
+
"eval_f1": 0.791816223977028,
|
| 278 |
+
"eval_loss": 0.5524763464927673,
|
| 279 |
+
"eval_precision": 0.8576982892690513,
|
| 280 |
+
"eval_recall": 0.7353333333333333,
|
| 281 |
+
"eval_runtime": 241.0103,
|
| 282 |
+
"eval_samples_per_second": 12.448,
|
| 283 |
+
"eval_steps_per_second": 1.556,
|
| 284 |
+
"step": 525
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.32,
|
| 288 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 289 |
+
"loss": 0.5359,
|
| 290 |
+
"step": 560
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.32,
|
| 294 |
+
"eval_accuracy": 0.5066666666666667,
|
| 295 |
+
"eval_f1": 0.6696428571428572,
|
| 296 |
+
"eval_loss": 2.7870869636535645,
|
| 297 |
+
"eval_precision": 0.5033557046979866,
|
| 298 |
+
"eval_recall": 1.0,
|
| 299 |
+
"eval_runtime": 240.5172,
|
| 300 |
+
"eval_samples_per_second": 12.473,
|
| 301 |
+
"eval_steps_per_second": 1.559,
|
| 302 |
+
"step": 560
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.34,
|
| 306 |
+
"learning_rate": 3.3e-05,
|
| 307 |
+
"loss": 0.4746,
|
| 308 |
+
"step": 595
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.34,
|
| 312 |
+
"eval_accuracy": 0.728,
|
| 313 |
+
"eval_f1": 0.7827476038338658,
|
| 314 |
+
"eval_loss": 0.8008346557617188,
|
| 315 |
+
"eval_precision": 0.651595744680851,
|
| 316 |
+
"eval_recall": 0.98,
|
| 317 |
+
"eval_runtime": 241.3279,
|
| 318 |
+
"eval_samples_per_second": 12.431,
|
| 319 |
+
"eval_steps_per_second": 1.554,
|
| 320 |
+
"step": 595
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.36,
|
| 324 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 325 |
+
"loss": 0.4525,
|
| 326 |
+
"step": 630
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.36,
|
| 330 |
+
"eval_accuracy": 0.819,
|
| 331 |
+
"eval_f1": 0.831104199066874,
|
| 332 |
+
"eval_loss": 0.4293590486049652,
|
| 333 |
+
"eval_precision": 0.7790087463556852,
|
| 334 |
+
"eval_recall": 0.8906666666666667,
|
| 335 |
+
"eval_runtime": 240.4794,
|
| 336 |
+
"eval_samples_per_second": 12.475,
|
| 337 |
+
"eval_steps_per_second": 1.559,
|
| 338 |
+
"step": 630
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.38,
|
| 342 |
+
"learning_rate": 3.1e-05,
|
| 343 |
+
"loss": 0.5492,
|
| 344 |
+
"step": 665
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.38,
|
| 348 |
+
"eval_accuracy": 0.8193333333333334,
|
| 349 |
+
"eval_f1": 0.7991104521868051,
|
| 350 |
+
"eval_loss": 0.6366798281669617,
|
| 351 |
+
"eval_precision": 0.8998330550918197,
|
| 352 |
+
"eval_recall": 0.7186666666666667,
|
| 353 |
+
"eval_runtime": 240.7182,
|
| 354 |
+
"eval_samples_per_second": 12.463,
|
| 355 |
+
"eval_steps_per_second": 1.558,
|
| 356 |
+
"step": 665
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.4,
|
| 360 |
+
"learning_rate": 3e-05,
|
| 361 |
+
"loss": 0.3315,
|
| 362 |
+
"step": 700
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.4,
|
| 366 |
+
"eval_accuracy": 0.8446666666666667,
|
| 367 |
+
"eval_f1": 0.8411724608043626,
|
| 368 |
+
"eval_loss": 0.44469600915908813,
|
| 369 |
+
"eval_precision": 0.8605299860529986,
|
| 370 |
+
"eval_recall": 0.8226666666666667,
|
| 371 |
+
"eval_runtime": 240.3073,
|
| 372 |
+
"eval_samples_per_second": 12.484,
|
| 373 |
+
"eval_steps_per_second": 1.561,
|
| 374 |
+
"step": 700
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.42,
|
| 378 |
+
"learning_rate": 2.9e-05,
|
| 379 |
+
"loss": 0.5122,
|
| 380 |
+
"step": 735
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.42,
|
| 384 |
+
"eval_accuracy": 0.723,
|
| 385 |
+
"eval_f1": 0.7735077677841373,
|
| 386 |
+
"eval_loss": 0.7516367435455322,
|
| 387 |
+
"eval_precision": 0.6542185338865837,
|
| 388 |
+
"eval_recall": 0.946,
|
| 389 |
+
"eval_runtime": 240.4309,
|
| 390 |
+
"eval_samples_per_second": 12.478,
|
| 391 |
+
"eval_steps_per_second": 1.56,
|
| 392 |
+
"step": 735
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.44,
|
| 396 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 397 |
+
"loss": 0.4712,
|
| 398 |
+
"step": 770
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.44,
|
| 402 |
+
"eval_accuracy": 0.7073333333333334,
|
| 403 |
+
"eval_f1": 0.7701570680628271,
|
| 404 |
+
"eval_loss": 0.7024486660957336,
|
| 405 |
+
"eval_precision": 0.634051724137931,
|
| 406 |
+
"eval_recall": 0.9806666666666667,
|
| 407 |
+
"eval_runtime": 240.5793,
|
| 408 |
+
"eval_samples_per_second": 12.47,
|
| 409 |
+
"eval_steps_per_second": 1.559,
|
| 410 |
+
"step": 770
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.46,
|
| 414 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 415 |
+
"loss": 0.5167,
|
| 416 |
+
"step": 805
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.46,
|
| 420 |
+
"eval_accuracy": 0.637,
|
| 421 |
+
"eval_f1": 0.7323666748586877,
|
| 422 |
+
"eval_loss": 1.0258432626724243,
|
| 423 |
+
"eval_precision": 0.5799922148695991,
|
| 424 |
+
"eval_recall": 0.9933333333333333,
|
| 425 |
+
"eval_runtime": 240.5552,
|
| 426 |
+
"eval_samples_per_second": 12.471,
|
| 427 |
+
"eval_steps_per_second": 1.559,
|
| 428 |
+
"step": 805
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.48,
|
| 432 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 433 |
+
"loss": 0.3025,
|
| 434 |
+
"step": 840
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.48,
|
| 438 |
+
"eval_accuracy": 0.7826666666666666,
|
| 439 |
+
"eval_f1": 0.8170594837261503,
|
| 440 |
+
"eval_loss": 0.5468646883964539,
|
| 441 |
+
"eval_precision": 0.7054263565891473,
|
| 442 |
+
"eval_recall": 0.9706666666666667,
|
| 443 |
+
"eval_runtime": 240.9803,
|
| 444 |
+
"eval_samples_per_second": 12.449,
|
| 445 |
+
"eval_steps_per_second": 1.556,
|
| 446 |
+
"step": 840
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5,
|
| 450 |
+
"learning_rate": 2.5e-05,
|
| 451 |
+
"loss": 0.3937,
|
| 452 |
+
"step": 875
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.5,
|
| 456 |
+
"eval_accuracy": 0.7956666666666666,
|
| 457 |
+
"eval_f1": 0.8233938346297897,
|
| 458 |
+
"eval_loss": 0.5975732207298279,
|
| 459 |
+
"eval_precision": 0.7250126839167935,
|
| 460 |
+
"eval_recall": 0.9526666666666667,
|
| 461 |
+
"eval_runtime": 240.6768,
|
| 462 |
+
"eval_samples_per_second": 12.465,
|
| 463 |
+
"eval_steps_per_second": 1.558,
|
| 464 |
+
"step": 875
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.52,
|
| 468 |
+
"learning_rate": 2.4e-05,
|
| 469 |
+
"loss": 0.3635,
|
| 470 |
+
"step": 910
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.52,
|
| 474 |
+
"eval_accuracy": 0.7516666666666667,
|
| 475 |
+
"eval_f1": 0.7974993204675184,
|
| 476 |
+
"eval_loss": 0.681395411491394,
|
| 477 |
+
"eval_precision": 0.6732446076181735,
|
| 478 |
+
"eval_recall": 0.978,
|
| 479 |
+
"eval_runtime": 243.1168,
|
| 480 |
+
"eval_samples_per_second": 12.34,
|
| 481 |
+
"eval_steps_per_second": 1.542,
|
| 482 |
+
"step": 910
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.54,
|
| 486 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 487 |
+
"loss": 0.3354,
|
| 488 |
+
"step": 945
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.54,
|
| 492 |
+
"eval_accuracy": 0.6006666666666667,
|
| 493 |
+
"eval_f1": 0.7139446036294174,
|
| 494 |
+
"eval_loss": 1.097399115562439,
|
| 495 |
+
"eval_precision": 0.5561755952380952,
|
| 496 |
+
"eval_recall": 0.9966666666666667,
|
| 497 |
+
"eval_runtime": 240.1778,
|
| 498 |
+
"eval_samples_per_second": 12.491,
|
| 499 |
+
"eval_steps_per_second": 1.561,
|
| 500 |
+
"step": 945
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.56,
|
| 504 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 505 |
+
"loss": 0.2047,
|
| 506 |
+
"step": 980
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.56,
|
| 510 |
+
"eval_accuracy": 0.5143333333333333,
|
| 511 |
+
"eval_f1": 0.6729517396184064,
|
| 512 |
+
"eval_loss": 1.91347074508667,
|
| 513 |
+
"eval_precision": 0.5072758037225042,
|
| 514 |
+
"eval_recall": 0.9993333333333333,
|
| 515 |
+
"eval_runtime": 240.5169,
|
| 516 |
+
"eval_samples_per_second": 12.473,
|
| 517 |
+
"eval_steps_per_second": 1.559,
|
| 518 |
+
"step": 980
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.58,
|
| 522 |
+
"learning_rate": 2.1e-05,
|
| 523 |
+
"loss": 0.4875,
|
| 524 |
+
"step": 1015
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.58,
|
| 528 |
+
"eval_accuracy": 0.8083333333333333,
|
| 529 |
+
"eval_f1": 0.833574529667149,
|
| 530 |
+
"eval_loss": 0.5008577704429626,
|
| 531 |
+
"eval_precision": 0.7365728900255755,
|
| 532 |
+
"eval_recall": 0.96,
|
| 533 |
+
"eval_runtime": 240.1154,
|
| 534 |
+
"eval_samples_per_second": 12.494,
|
| 535 |
+
"eval_steps_per_second": 1.562,
|
| 536 |
+
"step": 1015
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.6,
|
| 540 |
+
"learning_rate": 2e-05,
|
| 541 |
+
"loss": 0.2811,
|
| 542 |
+
"step": 1050
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6,
|
| 546 |
+
"eval_accuracy": 0.8413333333333334,
|
| 547 |
+
"eval_f1": 0.8487928843710293,
|
| 548 |
+
"eval_loss": 0.3812311887741089,
|
| 549 |
+
"eval_precision": 0.8106796116504854,
|
| 550 |
+
"eval_recall": 0.8906666666666667,
|
| 551 |
+
"eval_runtime": 240.4478,
|
| 552 |
+
"eval_samples_per_second": 12.477,
|
| 553 |
+
"eval_steps_per_second": 1.56,
|
| 554 |
+
"step": 1050
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.62,
|
| 558 |
+
"learning_rate": 1.9e-05,
|
| 559 |
+
"loss": 0.2227,
|
| 560 |
+
"step": 1085
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.62,
|
| 564 |
+
"eval_accuracy": 0.8606666666666667,
|
| 565 |
+
"eval_f1": 0.862137203166227,
|
| 566 |
+
"eval_loss": 0.36810368299484253,
|
| 567 |
+
"eval_precision": 0.8531331592689295,
|
| 568 |
+
"eval_recall": 0.8713333333333333,
|
| 569 |
+
"eval_runtime": 240.5301,
|
| 570 |
+
"eval_samples_per_second": 12.472,
|
| 571 |
+
"eval_steps_per_second": 1.559,
|
| 572 |
+
"step": 1085
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.64,
|
| 576 |
+
"learning_rate": 1.8e-05,
|
| 577 |
+
"loss": 0.3917,
|
| 578 |
+
"step": 1120
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.64,
|
| 582 |
+
"eval_accuracy": 0.8543333333333333,
|
| 583 |
+
"eval_f1": 0.8612257859637981,
|
| 584 |
+
"eval_loss": 0.4265972375869751,
|
| 585 |
+
"eval_precision": 0.8223165554881746,
|
| 586 |
+
"eval_recall": 0.904,
|
| 587 |
+
"eval_runtime": 241.0329,
|
| 588 |
+
"eval_samples_per_second": 12.446,
|
| 589 |
+
"eval_steps_per_second": 1.556,
|
| 590 |
+
"step": 1120
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.66,
|
| 594 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 595 |
+
"loss": 0.3635,
|
| 596 |
+
"step": 1155
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.66,
|
| 600 |
+
"eval_accuracy": 0.6436666666666667,
|
| 601 |
+
"eval_f1": 0.736374845869297,
|
| 602 |
+
"eval_loss": 1.1040711402893066,
|
| 603 |
+
"eval_precision": 0.5843444227005871,
|
| 604 |
+
"eval_recall": 0.9953333333333333,
|
| 605 |
+
"eval_runtime": 240.5878,
|
| 606 |
+
"eval_samples_per_second": 12.469,
|
| 607 |
+
"eval_steps_per_second": 1.559,
|
| 608 |
+
"step": 1155
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.68,
|
| 612 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 613 |
+
"loss": 0.4145,
|
| 614 |
+
"step": 1190
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.68,
|
| 618 |
+
"eval_accuracy": 0.8136666666666666,
|
| 619 |
+
"eval_f1": 0.8390440541318746,
|
| 620 |
+
"eval_loss": 0.5226981043815613,
|
| 621 |
+
"eval_precision": 0.7384693360364927,
|
| 622 |
+
"eval_recall": 0.9713333333333334,
|
| 623 |
+
"eval_runtime": 240.5513,
|
| 624 |
+
"eval_samples_per_second": 12.471,
|
| 625 |
+
"eval_steps_per_second": 1.559,
|
| 626 |
+
"step": 1190
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7,
|
| 630 |
+
"learning_rate": 1.5e-05,
|
| 631 |
+
"loss": 0.4154,
|
| 632 |
+
"step": 1225
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7,
|
| 636 |
+
"eval_accuracy": 0.6573333333333333,
|
| 637 |
+
"eval_f1": 0.7438963627304432,
|
| 638 |
+
"eval_loss": 0.8615061640739441,
|
| 639 |
+
"eval_precision": 0.5938743038981702,
|
| 640 |
+
"eval_recall": 0.9953333333333333,
|
| 641 |
+
"eval_runtime": 241.311,
|
| 642 |
+
"eval_samples_per_second": 12.432,
|
| 643 |
+
"eval_steps_per_second": 1.554,
|
| 644 |
+
"step": 1225
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.72,
|
| 648 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 649 |
+
"loss": 0.2322,
|
| 650 |
+
"step": 1260
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.72,
|
| 654 |
+
"eval_accuracy": 0.627,
|
| 655 |
+
"eval_f1": 0.7275383491599707,
|
| 656 |
+
"eval_loss": 1.0941112041473389,
|
| 657 |
+
"eval_precision": 0.57307249712313,
|
| 658 |
+
"eval_recall": 0.996,
|
| 659 |
+
"eval_runtime": 240.2621,
|
| 660 |
+
"eval_samples_per_second": 12.486,
|
| 661 |
+
"eval_steps_per_second": 1.561,
|
| 662 |
+
"step": 1260
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.74,
|
| 666 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 667 |
+
"loss": 0.3221,
|
| 668 |
+
"step": 1295
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.74,
|
| 672 |
+
"eval_accuracy": 0.722,
|
| 673 |
+
"eval_f1": 0.7807570977917981,
|
| 674 |
+
"eval_loss": 0.7642508149147034,
|
| 675 |
+
"eval_precision": 0.64453125,
|
| 676 |
+
"eval_recall": 0.99,
|
| 677 |
+
"eval_runtime": 240.1026,
|
| 678 |
+
"eval_samples_per_second": 12.495,
|
| 679 |
+
"eval_steps_per_second": 1.562,
|
| 680 |
+
"step": 1295
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.76,
|
| 684 |
+
"learning_rate": 1.2e-05,
|
| 685 |
+
"loss": 0.2182,
|
| 686 |
+
"step": 1330
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.76,
|
| 690 |
+
"eval_accuracy": 0.8256666666666667,
|
| 691 |
+
"eval_f1": 0.847477398658501,
|
| 692 |
+
"eval_loss": 0.4936087727546692,
|
| 693 |
+
"eval_precision": 0.7532400207361327,
|
| 694 |
+
"eval_recall": 0.9686666666666667,
|
| 695 |
+
"eval_runtime": 240.5209,
|
| 696 |
+
"eval_samples_per_second": 12.473,
|
| 697 |
+
"eval_steps_per_second": 1.559,
|
| 698 |
+
"step": 1330
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.78,
|
| 702 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 703 |
+
"loss": 0.2608,
|
| 704 |
+
"step": 1365
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.78,
|
| 708 |
+
"eval_accuracy": 0.7696666666666667,
|
| 709 |
+
"eval_f1": 0.8104252400548698,
|
| 710 |
+
"eval_loss": 0.6222155690193176,
|
| 711 |
+
"eval_precision": 0.6885780885780886,
|
| 712 |
+
"eval_recall": 0.9846666666666667,
|
| 713 |
+
"eval_runtime": 242.2988,
|
| 714 |
+
"eval_samples_per_second": 12.381,
|
| 715 |
+
"eval_steps_per_second": 1.548,
|
| 716 |
+
"step": 1365
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.8,
|
| 720 |
+
"learning_rate": 1e-05,
|
| 721 |
+
"loss": 0.3251,
|
| 722 |
+
"step": 1400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.8,
|
| 726 |
+
"eval_accuracy": 0.8256666666666667,
|
| 727 |
+
"eval_f1": 0.8467623791385878,
|
| 728 |
+
"eval_loss": 0.4772394299507141,
|
| 729 |
+
"eval_precision": 0.7553580763199164,
|
| 730 |
+
"eval_recall": 0.9633333333333334,
|
| 731 |
+
"eval_runtime": 240.46,
|
| 732 |
+
"eval_samples_per_second": 12.476,
|
| 733 |
+
"eval_steps_per_second": 1.56,
|
| 734 |
+
"step": 1400
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.82,
|
| 738 |
+
"learning_rate": 9e-06,
|
| 739 |
+
"loss": 0.1763,
|
| 740 |
+
"step": 1435
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.82,
|
| 744 |
+
"eval_accuracy": 0.7433333333333333,
|
| 745 |
+
"eval_f1": 0.7941176470588235,
|
| 746 |
+
"eval_loss": 0.6803577542304993,
|
| 747 |
+
"eval_precision": 0.6629464285714286,
|
| 748 |
+
"eval_recall": 0.99,
|
| 749 |
+
"eval_runtime": 240.563,
|
| 750 |
+
"eval_samples_per_second": 12.471,
|
| 751 |
+
"eval_steps_per_second": 1.559,
|
| 752 |
+
"step": 1435
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.84,
|
| 756 |
+
"learning_rate": 8.000000000000001e-06,
|
| 757 |
+
"loss": 0.2904,
|
| 758 |
+
"step": 1470
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.84,
|
| 762 |
+
"eval_accuracy": 0.7246666666666667,
|
| 763 |
+
"eval_f1": 0.7827459231983166,
|
| 764 |
+
"eval_loss": 0.727342426776886,
|
| 765 |
+
"eval_precision": 0.6463944396177237,
|
| 766 |
+
"eval_recall": 0.992,
|
| 767 |
+
"eval_runtime": 241.4946,
|
| 768 |
+
"eval_samples_per_second": 12.423,
|
| 769 |
+
"eval_steps_per_second": 1.553,
|
| 770 |
+
"step": 1470
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.86,
|
| 774 |
+
"learning_rate": 7.000000000000001e-06,
|
| 775 |
+
"loss": 0.2758,
|
| 776 |
+
"step": 1505
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.86,
|
| 780 |
+
"eval_accuracy": 0.689,
|
| 781 |
+
"eval_f1": 0.7615640173779707,
|
| 782 |
+
"eval_loss": 0.8572436571121216,
|
| 783 |
+
"eval_precision": 0.6174886033982594,
|
| 784 |
+
"eval_recall": 0.9933333333333333,
|
| 785 |
+
"eval_runtime": 240.6981,
|
| 786 |
+
"eval_samples_per_second": 12.464,
|
| 787 |
+
"eval_steps_per_second": 1.558,
|
| 788 |
+
"step": 1505
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.88,
|
| 792 |
+
"learning_rate": 6e-06,
|
| 793 |
+
"loss": 0.3054,
|
| 794 |
+
"step": 1540
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.88,
|
| 798 |
+
"eval_accuracy": 0.6446666666666667,
|
| 799 |
+
"eval_f1": 0.7369200394866732,
|
| 800 |
+
"eval_loss": 0.9957032799720764,
|
| 801 |
+
"eval_precision": 0.5850313479623824,
|
| 802 |
+
"eval_recall": 0.9953333333333333,
|
| 803 |
+
"eval_runtime": 240.6892,
|
| 804 |
+
"eval_samples_per_second": 12.464,
|
| 805 |
+
"eval_steps_per_second": 1.558,
|
| 806 |
+
"step": 1540
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.9,
|
| 810 |
+
"learning_rate": 5e-06,
|
| 811 |
+
"loss": 0.2433,
|
| 812 |
+
"step": 1575
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.9,
|
| 816 |
+
"eval_accuracy": 0.7466666666666667,
|
| 817 |
+
"eval_f1": 0.7960279119699409,
|
| 818 |
+
"eval_loss": 0.6531896591186523,
|
| 819 |
+
"eval_precision": 0.6662174303683738,
|
| 820 |
+
"eval_recall": 0.9886666666666667,
|
| 821 |
+
"eval_runtime": 242.6474,
|
| 822 |
+
"eval_samples_per_second": 12.364,
|
| 823 |
+
"eval_steps_per_second": 1.545,
|
| 824 |
+
"step": 1575
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.92,
|
| 828 |
+
"learning_rate": 4.000000000000001e-06,
|
| 829 |
+
"loss": 0.2869,
|
| 830 |
+
"step": 1610
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.92,
|
| 834 |
+
"eval_accuracy": 0.816,
|
| 835 |
+
"eval_f1": 0.8410138248847926,
|
| 836 |
+
"eval_loss": 0.45964765548706055,
|
| 837 |
+
"eval_precision": 0.7403651115618661,
|
| 838 |
+
"eval_recall": 0.9733333333333334,
|
| 839 |
+
"eval_runtime": 240.842,
|
| 840 |
+
"eval_samples_per_second": 12.456,
|
| 841 |
+
"eval_steps_per_second": 1.557,
|
| 842 |
+
"step": 1610
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.94,
|
| 846 |
+
"learning_rate": 3e-06,
|
| 847 |
+
"loss": 0.119,
|
| 848 |
+
"step": 1645
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.94,
|
| 852 |
+
"eval_accuracy": 0.727,
|
| 853 |
+
"eval_f1": 0.7838479809976248,
|
| 854 |
+
"eval_loss": 0.7068488001823425,
|
| 855 |
+
"eval_precision": 0.6487549148099607,
|
| 856 |
+
"eval_recall": 0.99,
|
| 857 |
+
"eval_runtime": 240.4825,
|
| 858 |
+
"eval_samples_per_second": 12.475,
|
| 859 |
+
"eval_steps_per_second": 1.559,
|
| 860 |
+
"step": 1645
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.96,
|
| 864 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 865 |
+
"loss": 0.2153,
|
| 866 |
+
"step": 1680
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.96,
|
| 870 |
+
"eval_accuracy": 0.7513333333333333,
|
| 871 |
+
"eval_f1": 0.7988133764832793,
|
| 872 |
+
"eval_loss": 0.6478840112686157,
|
| 873 |
+
"eval_precision": 0.6707427536231884,
|
| 874 |
+
"eval_recall": 0.9873333333333333,
|
| 875 |
+
"eval_runtime": 240.4615,
|
| 876 |
+
"eval_samples_per_second": 12.476,
|
| 877 |
+
"eval_steps_per_second": 1.56,
|
| 878 |
+
"step": 1680
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.98,
|
| 882 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 883 |
+
"loss": 0.2594,
|
| 884 |
+
"step": 1715
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.98,
|
| 888 |
+
"eval_accuracy": 0.7313333333333333,
|
| 889 |
+
"eval_f1": 0.7866596082583377,
|
| 890 |
+
"eval_loss": 0.6965696811676025,
|
| 891 |
+
"eval_precision": 0.6523266022827041,
|
| 892 |
+
"eval_recall": 0.9906666666666667,
|
| 893 |
+
"eval_runtime": 240.2996,
|
| 894 |
+
"eval_samples_per_second": 12.484,
|
| 895 |
+
"eval_steps_per_second": 1.561,
|
| 896 |
+
"step": 1715
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.0,
|
| 900 |
+
"learning_rate": 0.0,
|
| 901 |
+
"loss": 0.2108,
|
| 902 |
+
"step": 1750
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.0,
|
| 906 |
+
"eval_accuracy": 0.7433333333333333,
|
| 907 |
+
"eval_f1": 0.7938972162740899,
|
| 908 |
+
"eval_loss": 0.6547001004219055,
|
| 909 |
+
"eval_precision": 0.6632379248658319,
|
| 910 |
+
"eval_recall": 0.9886666666666667,
|
| 911 |
+
"eval_runtime": 240.3896,
|
| 912 |
+
"eval_samples_per_second": 12.48,
|
| 913 |
+
"eval_steps_per_second": 1.56,
|
| 914 |
+
"step": 1750
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"max_steps": 1750,
|
| 918 |
+
"num_train_epochs": 1,
|
| 919 |
+
"total_flos": 5.1979933974528e+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:c8f5066a1aa6c965aa1838458494222c8e72724c8035db925110310fd8b651fd
|
| 3 |
+
size 3451
|