Commit
•
8fad34c
1
Parent(s):
c79d63e
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:e32a063a8f32b5cb332d4aaabe02fd13556a9e495f1c8568008c27d529bdf472
|
3 |
+
size 4473979569
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd9c98fe77474fb3f322e1162d777a45216f35f7d27ca5dd0ddb33462df31a78
|
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 sha256:1d94bffac577c2182cd3b6680df4b0ff46f4c0a0b7ff9c866be7458145e68e80
|
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-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": 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": 5.5906,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 4.9017367458866546e-05,
|
19 |
+
"loss": 3.8301,
|
20 |
+
"step": 43
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"eval_accuracy": 0.7008,
|
25 |
+
"eval_f1": 0.7372365339578454,
|
26 |
+
"eval_loss": 1.7894935607910156,
|
27 |
+
"eval_precision": 0.6572025052192066,
|
28 |
+
"eval_recall": 0.8394666666666667,
|
29 |
+
"eval_runtime": 100.3646,
|
30 |
+
"eval_samples_per_second": 37.364,
|
31 |
+
"eval_steps_per_second": 4.673,
|
32 |
+
"step": 43
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.04,
|
36 |
+
"learning_rate": 4.8034734917733096e-05,
|
37 |
+
"loss": 1.7461,
|
38 |
+
"step": 86
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.04,
|
42 |
+
"eval_accuracy": 0.7669333333333334,
|
43 |
+
"eval_f1": 0.8065515714918104,
|
44 |
+
"eval_loss": 1.6799604892730713,
|
45 |
+
"eval_precision": 0.6893681422625804,
|
46 |
+
"eval_recall": 0.9717333333333333,
|
47 |
+
"eval_runtime": 100.5302,
|
48 |
+
"eval_samples_per_second": 37.302,
|
49 |
+
"eval_steps_per_second": 4.665,
|
50 |
+
"step": 86
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.06,
|
54 |
+
"learning_rate": 4.705210237659964e-05,
|
55 |
+
"loss": 1.5511,
|
56 |
+
"step": 129
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.06,
|
60 |
+
"eval_accuracy": 0.8925333333333333,
|
61 |
+
"eval_f1": 0.8882728028832826,
|
62 |
+
"eval_loss": 0.5680333375930786,
|
63 |
+
"eval_precision": 0.9249422632794457,
|
64 |
+
"eval_recall": 0.8544,
|
65 |
+
"eval_runtime": 100.4817,
|
66 |
+
"eval_samples_per_second": 37.32,
|
67 |
+
"eval_steps_per_second": 4.668,
|
68 |
+
"step": 129
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.08,
|
72 |
+
"learning_rate": 4.606946983546618e-05,
|
73 |
+
"loss": 1.2304,
|
74 |
+
"step": 172
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.08,
|
78 |
+
"eval_accuracy": 0.7061333333333333,
|
79 |
+
"eval_f1": 0.5838368580060423,
|
80 |
+
"eval_loss": 4.393102169036865,
|
81 |
+
"eval_precision": 1.0,
|
82 |
+
"eval_recall": 0.41226666666666667,
|
83 |
+
"eval_runtime": 100.2927,
|
84 |
+
"eval_samples_per_second": 37.391,
|
85 |
+
"eval_steps_per_second": 4.676,
|
86 |
+
"step": 172
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1,
|
90 |
+
"learning_rate": 4.5086837294332726e-05,
|
91 |
+
"loss": 1.6111,
|
92 |
+
"step": 215
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.1,
|
96 |
+
"eval_accuracy": 0.7248,
|
97 |
+
"eval_f1": 0.7810776410691558,
|
98 |
+
"eval_loss": 1.275352954864502,
|
99 |
+
"eval_precision": 0.6484677703416696,
|
100 |
+
"eval_recall": 0.9818666666666667,
|
101 |
+
"eval_runtime": 100.7588,
|
102 |
+
"eval_samples_per_second": 37.218,
|
103 |
+
"eval_steps_per_second": 4.655,
|
104 |
+
"step": 215
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.12,
|
108 |
+
"learning_rate": 4.410420475319927e-05,
|
109 |
+
"loss": 1.1002,
|
110 |
+
"step": 258
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.12,
|
114 |
+
"eval_accuracy": 0.848,
|
115 |
+
"eval_f1": 0.8375142531356898,
|
116 |
+
"eval_loss": 0.5289755463600159,
|
117 |
+
"eval_precision": 0.8995713410900184,
|
118 |
+
"eval_recall": 0.7834666666666666,
|
119 |
+
"eval_runtime": 100.7268,
|
120 |
+
"eval_samples_per_second": 37.229,
|
121 |
+
"eval_steps_per_second": 4.656,
|
122 |
+
"step": 258
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.14,
|
126 |
+
"learning_rate": 4.312157221206581e-05,
|
127 |
+
"loss": 0.6462,
|
128 |
+
"step": 301
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.14,
|
132 |
+
"eval_accuracy": 0.864,
|
133 |
+
"eval_f1": 0.8452669902912622,
|
134 |
+
"eval_loss": 0.6743063926696777,
|
135 |
+
"eval_precision": 0.9802955665024631,
|
136 |
+
"eval_recall": 0.7429333333333333,
|
137 |
+
"eval_runtime": 100.4683,
|
138 |
+
"eval_samples_per_second": 37.325,
|
139 |
+
"eval_steps_per_second": 4.668,
|
140 |
+
"step": 301
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.16,
|
144 |
+
"learning_rate": 4.213893967093236e-05,
|
145 |
+
"loss": 0.6835,
|
146 |
+
"step": 344
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.16,
|
150 |
+
"eval_accuracy": 0.6992,
|
151 |
+
"eval_f1": 0.7657807308970099,
|
152 |
+
"eval_loss": 0.9862114787101746,
|
153 |
+
"eval_precision": 0.6269976198571914,
|
154 |
+
"eval_recall": 0.9834666666666667,
|
155 |
+
"eval_runtime": 100.9462,
|
156 |
+
"eval_samples_per_second": 37.148,
|
157 |
+
"eval_steps_per_second": 4.646,
|
158 |
+
"step": 344
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.18,
|
162 |
+
"learning_rate": 4.1156307129798905e-05,
|
163 |
+
"loss": 0.5506,
|
164 |
+
"step": 387
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.18,
|
168 |
+
"eval_accuracy": 0.7984,
|
169 |
+
"eval_f1": 0.7476635514018691,
|
170 |
+
"eval_loss": 1.4477732181549072,
|
171 |
+
"eval_precision": 0.9991079393398751,
|
172 |
+
"eval_recall": 0.5973333333333334,
|
173 |
+
"eval_runtime": 101.0116,
|
174 |
+
"eval_samples_per_second": 37.124,
|
175 |
+
"eval_steps_per_second": 4.643,
|
176 |
+
"step": 387
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.2,
|
180 |
+
"learning_rate": 4.017367458866545e-05,
|
181 |
+
"loss": 1.0906,
|
182 |
+
"step": 430
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.2,
|
186 |
+
"eval_accuracy": 0.9165333333333333,
|
187 |
+
"eval_f1": 0.9144575020497402,
|
188 |
+
"eval_loss": 0.2948032021522522,
|
189 |
+
"eval_precision": 0.9377802690582959,
|
190 |
+
"eval_recall": 0.8922666666666667,
|
191 |
+
"eval_runtime": 100.9951,
|
192 |
+
"eval_samples_per_second": 37.131,
|
193 |
+
"eval_steps_per_second": 4.644,
|
194 |
+
"step": 430
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.22,
|
198 |
+
"learning_rate": 3.919104204753199e-05,
|
199 |
+
"loss": 0.4459,
|
200 |
+
"step": 473
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.22,
|
204 |
+
"eval_accuracy": 0.9082666666666667,
|
205 |
+
"eval_f1": 0.9078242229367631,
|
206 |
+
"eval_loss": 0.5833027362823486,
|
207 |
+
"eval_precision": 0.9122240172320948,
|
208 |
+
"eval_recall": 0.9034666666666666,
|
209 |
+
"eval_runtime": 100.5094,
|
210 |
+
"eval_samples_per_second": 37.31,
|
211 |
+
"eval_steps_per_second": 4.666,
|
212 |
+
"step": 473
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.24,
|
216 |
+
"learning_rate": 3.820840950639854e-05,
|
217 |
+
"loss": 0.4996,
|
218 |
+
"step": 516
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.24,
|
222 |
+
"eval_accuracy": 0.9210666666666667,
|
223 |
+
"eval_f1": 0.9218172213417856,
|
224 |
+
"eval_loss": 0.6353188157081604,
|
225 |
+
"eval_precision": 0.913134484563056,
|
226 |
+
"eval_recall": 0.9306666666666666,
|
227 |
+
"eval_runtime": 100.6316,
|
228 |
+
"eval_samples_per_second": 37.265,
|
229 |
+
"eval_steps_per_second": 4.661,
|
230 |
+
"step": 516
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.26,
|
234 |
+
"learning_rate": 3.7225776965265085e-05,
|
235 |
+
"loss": 0.4613,
|
236 |
+
"step": 559
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.26,
|
240 |
+
"eval_accuracy": 0.9290666666666667,
|
241 |
+
"eval_f1": 0.926923076923077,
|
242 |
+
"eval_loss": 0.43136465549468994,
|
243 |
+
"eval_precision": 0.9558073654390935,
|
244 |
+
"eval_recall": 0.8997333333333334,
|
245 |
+
"eval_runtime": 100.9532,
|
246 |
+
"eval_samples_per_second": 37.146,
|
247 |
+
"eval_steps_per_second": 4.646,
|
248 |
+
"step": 559
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.28,
|
252 |
+
"learning_rate": 3.624314442413163e-05,
|
253 |
+
"loss": 0.3868,
|
254 |
+
"step": 602
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.28,
|
258 |
+
"eval_accuracy": 0.8997333333333334,
|
259 |
+
"eval_f1": 0.8932424758659853,
|
260 |
+
"eval_loss": 0.6684072017669678,
|
261 |
+
"eval_precision": 0.9550698239222829,
|
262 |
+
"eval_recall": 0.8389333333333333,
|
263 |
+
"eval_runtime": 100.7051,
|
264 |
+
"eval_samples_per_second": 37.237,
|
265 |
+
"eval_steps_per_second": 4.657,
|
266 |
+
"step": 602
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.29,
|
270 |
+
"learning_rate": 3.526051188299818e-05,
|
271 |
+
"loss": 0.3524,
|
272 |
+
"step": 645
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.29,
|
276 |
+
"eval_accuracy": 0.9269333333333334,
|
277 |
+
"eval_f1": 0.9261057173678533,
|
278 |
+
"eval_loss": 0.49305853247642517,
|
279 |
+
"eval_precision": 0.9367157665030006,
|
280 |
+
"eval_recall": 0.9157333333333333,
|
281 |
+
"eval_runtime": 101.0904,
|
282 |
+
"eval_samples_per_second": 37.096,
|
283 |
+
"eval_steps_per_second": 4.639,
|
284 |
+
"step": 645
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.31,
|
288 |
+
"learning_rate": 3.4277879341864715e-05,
|
289 |
+
"loss": 0.4739,
|
290 |
+
"step": 688
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.31,
|
294 |
+
"eval_accuracy": 0.9192,
|
295 |
+
"eval_f1": 0.9207428720899816,
|
296 |
+
"eval_loss": 0.4122666120529175,
|
297 |
+
"eval_precision": 0.9034907597535934,
|
298 |
+
"eval_recall": 0.9386666666666666,
|
299 |
+
"eval_runtime": 101.3837,
|
300 |
+
"eval_samples_per_second": 36.988,
|
301 |
+
"eval_steps_per_second": 4.626,
|
302 |
+
"step": 688
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.33,
|
306 |
+
"learning_rate": 3.329524680073126e-05,
|
307 |
+
"loss": 0.5484,
|
308 |
+
"step": 731
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.33,
|
312 |
+
"eval_accuracy": 0.6853333333333333,
|
313 |
+
"eval_f1": 0.7321833862914208,
|
314 |
+
"eval_loss": 0.6493818759918213,
|
315 |
+
"eval_precision": 0.6372975108652706,
|
316 |
+
"eval_recall": 0.8602666666666666,
|
317 |
+
"eval_runtime": 100.5978,
|
318 |
+
"eval_samples_per_second": 37.277,
|
319 |
+
"eval_steps_per_second": 4.662,
|
320 |
+
"step": 731
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.35,
|
324 |
+
"learning_rate": 3.231261425959781e-05,
|
325 |
+
"loss": 0.4939,
|
326 |
+
"step": 774
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.35,
|
330 |
+
"eval_accuracy": 0.8562666666666666,
|
331 |
+
"eval_f1": 0.8371109096403747,
|
332 |
+
"eval_loss": 0.43780916929244995,
|
333 |
+
"eval_precision": 0.9658298465829847,
|
334 |
+
"eval_recall": 0.7386666666666667,
|
335 |
+
"eval_runtime": 101.7646,
|
336 |
+
"eval_samples_per_second": 36.85,
|
337 |
+
"eval_steps_per_second": 4.609,
|
338 |
+
"step": 774
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.37,
|
342 |
+
"learning_rate": 3.132998171846435e-05,
|
343 |
+
"loss": 0.3646,
|
344 |
+
"step": 817
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.37,
|
348 |
+
"eval_accuracy": 0.9093333333333333,
|
349 |
+
"eval_f1": 0.9018475750577367,
|
350 |
+
"eval_loss": 0.5472243428230286,
|
351 |
+
"eval_precision": 0.9830081812460667,
|
352 |
+
"eval_recall": 0.8330666666666666,
|
353 |
+
"eval_runtime": 100.6656,
|
354 |
+
"eval_samples_per_second": 37.252,
|
355 |
+
"eval_steps_per_second": 4.659,
|
356 |
+
"step": 817
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.39,
|
360 |
+
"learning_rate": 3.03473491773309e-05,
|
361 |
+
"loss": 0.3954,
|
362 |
+
"step": 860
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.39,
|
366 |
+
"eval_accuracy": 0.9216,
|
367 |
+
"eval_f1": 0.9219330855018588,
|
368 |
+
"eval_loss": 0.3911387324333191,
|
369 |
+
"eval_precision": 0.9180327868852459,
|
370 |
+
"eval_recall": 0.9258666666666666,
|
371 |
+
"eval_runtime": 101.1862,
|
372 |
+
"eval_samples_per_second": 37.06,
|
373 |
+
"eval_steps_per_second": 4.635,
|
374 |
+
"step": 860
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.41,
|
378 |
+
"learning_rate": 2.9364716636197442e-05,
|
379 |
+
"loss": 0.3898,
|
380 |
+
"step": 903
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.41,
|
384 |
+
"eval_accuracy": 0.8677333333333334,
|
385 |
+
"eval_f1": 0.8485958485958486,
|
386 |
+
"eval_loss": 0.608423113822937,
|
387 |
+
"eval_precision": 0.9921484653818701,
|
388 |
+
"eval_recall": 0.7413333333333333,
|
389 |
+
"eval_runtime": 100.7786,
|
390 |
+
"eval_samples_per_second": 37.21,
|
391 |
+
"eval_steps_per_second": 4.654,
|
392 |
+
"step": 903
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.43,
|
396 |
+
"learning_rate": 2.838208409506399e-05,
|
397 |
+
"loss": 0.5361,
|
398 |
+
"step": 946
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.43,
|
402 |
+
"eval_accuracy": 0.9045333333333333,
|
403 |
+
"eval_f1": 0.8954439252336449,
|
404 |
+
"eval_loss": 0.5845316648483276,
|
405 |
+
"eval_precision": 0.9896707553260168,
|
406 |
+
"eval_recall": 0.8176,
|
407 |
+
"eval_runtime": 100.5268,
|
408 |
+
"eval_samples_per_second": 37.303,
|
409 |
+
"eval_steps_per_second": 4.665,
|
410 |
+
"step": 946
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.45,
|
414 |
+
"learning_rate": 2.739945155393053e-05,
|
415 |
+
"loss": 0.3488,
|
416 |
+
"step": 989
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.45,
|
420 |
+
"eval_accuracy": 0.9032,
|
421 |
+
"eval_f1": 0.90854119425548,
|
422 |
+
"eval_loss": 0.6275143027305603,
|
423 |
+
"eval_precision": 0.8610315186246418,
|
424 |
+
"eval_recall": 0.9616,
|
425 |
+
"eval_runtime": 100.5257,
|
426 |
+
"eval_samples_per_second": 37.304,
|
427 |
+
"eval_steps_per_second": 4.665,
|
428 |
+
"step": 989
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.47,
|
432 |
+
"learning_rate": 2.641681901279708e-05,
|
433 |
+
"loss": 0.6024,
|
434 |
+
"step": 1032
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.47,
|
438 |
+
"eval_accuracy": 0.7704,
|
439 |
+
"eval_f1": 0.8113910186199343,
|
440 |
+
"eval_loss": 1.486302375793457,
|
441 |
+
"eval_precision": 0.6884758364312268,
|
442 |
+
"eval_recall": 0.9877333333333334,
|
443 |
+
"eval_runtime": 100.9298,
|
444 |
+
"eval_samples_per_second": 37.155,
|
445 |
+
"eval_steps_per_second": 4.647,
|
446 |
+
"step": 1032
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.49,
|
450 |
+
"learning_rate": 2.5434186471663625e-05,
|
451 |
+
"loss": 0.6391,
|
452 |
+
"step": 1075
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.49,
|
456 |
+
"eval_accuracy": 0.9296,
|
457 |
+
"eval_f1": 0.9263803680981595,
|
458 |
+
"eval_loss": 0.47947388887405396,
|
459 |
+
"eval_precision": 0.9707773232028054,
|
460 |
+
"eval_recall": 0.8858666666666667,
|
461 |
+
"eval_runtime": 100.5142,
|
462 |
+
"eval_samples_per_second": 37.308,
|
463 |
+
"eval_steps_per_second": 4.666,
|
464 |
+
"step": 1075
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.51,
|
468 |
+
"learning_rate": 2.4451553930530165e-05,
|
469 |
+
"loss": 0.6603,
|
470 |
+
"step": 1118
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.51,
|
474 |
+
"eval_accuracy": 0.9266666666666666,
|
475 |
+
"eval_f1": 0.9240541286937309,
|
476 |
+
"eval_loss": 0.35503658652305603,
|
477 |
+
"eval_precision": 0.9581901489117984,
|
478 |
+
"eval_recall": 0.8922666666666667,
|
479 |
+
"eval_runtime": 100.9348,
|
480 |
+
"eval_samples_per_second": 37.153,
|
481 |
+
"eval_steps_per_second": 4.647,
|
482 |
+
"step": 1118
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.53,
|
486 |
+
"learning_rate": 2.346892138939671e-05,
|
487 |
+
"loss": 0.3186,
|
488 |
+
"step": 1161
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.53,
|
492 |
+
"eval_accuracy": 0.9317333333333333,
|
493 |
+
"eval_f1": 0.9288493607559756,
|
494 |
+
"eval_loss": 0.4835192561149597,
|
495 |
+
"eval_precision": 0.9698200812536274,
|
496 |
+
"eval_recall": 0.8912,
|
497 |
+
"eval_runtime": 100.4468,
|
498 |
+
"eval_samples_per_second": 37.333,
|
499 |
+
"eval_steps_per_second": 4.669,
|
500 |
+
"step": 1161
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.55,
|
504 |
+
"learning_rate": 2.2486288848263255e-05,
|
505 |
+
"loss": 0.3122,
|
506 |
+
"step": 1204
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.55,
|
510 |
+
"eval_accuracy": 0.9328,
|
511 |
+
"eval_f1": 0.9340314136125655,
|
512 |
+
"eval_loss": 0.31904712319374084,
|
513 |
+
"eval_precision": 0.9172236503856042,
|
514 |
+
"eval_recall": 0.9514666666666667,
|
515 |
+
"eval_runtime": 100.4601,
|
516 |
+
"eval_samples_per_second": 37.328,
|
517 |
+
"eval_steps_per_second": 4.669,
|
518 |
+
"step": 1204
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.57,
|
522 |
+
"learning_rate": 2.1503656307129798e-05,
|
523 |
+
"loss": 0.4917,
|
524 |
+
"step": 1247
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.57,
|
528 |
+
"eval_accuracy": 0.9192,
|
529 |
+
"eval_f1": 0.9151498179781573,
|
530 |
+
"eval_loss": 0.45495307445526123,
|
531 |
+
"eval_precision": 0.9634433962264151,
|
532 |
+
"eval_recall": 0.8714666666666666,
|
533 |
+
"eval_runtime": 100.5501,
|
534 |
+
"eval_samples_per_second": 37.295,
|
535 |
+
"eval_steps_per_second": 4.664,
|
536 |
+
"step": 1247
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.59,
|
540 |
+
"learning_rate": 2.0521023765996345e-05,
|
541 |
+
"loss": 0.448,
|
542 |
+
"step": 1290
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.59,
|
546 |
+
"eval_accuracy": 0.936,
|
547 |
+
"eval_f1": 0.9338113623827909,
|
548 |
+
"eval_loss": 0.18482676148414612,
|
549 |
+
"eval_precision": 0.9668760708166761,
|
550 |
+
"eval_recall": 0.9029333333333334,
|
551 |
+
"eval_runtime": 100.3779,
|
552 |
+
"eval_samples_per_second": 37.359,
|
553 |
+
"eval_steps_per_second": 4.672,
|
554 |
+
"step": 1290
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.61,
|
558 |
+
"learning_rate": 1.953839122486289e-05,
|
559 |
+
"loss": 0.3064,
|
560 |
+
"step": 1333
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.61,
|
564 |
+
"eval_accuracy": 0.9402666666666667,
|
565 |
+
"eval_f1": 0.9405204460966542,
|
566 |
+
"eval_loss": 0.23262375593185425,
|
567 |
+
"eval_precision": 0.9365415124272871,
|
568 |
+
"eval_recall": 0.9445333333333333,
|
569 |
+
"eval_runtime": 101.1761,
|
570 |
+
"eval_samples_per_second": 37.064,
|
571 |
+
"eval_steps_per_second": 4.635,
|
572 |
+
"step": 1333
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.63,
|
576 |
+
"learning_rate": 1.8555758683729435e-05,
|
577 |
+
"loss": 0.2274,
|
578 |
+
"step": 1376
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.63,
|
582 |
+
"eval_accuracy": 0.924,
|
583 |
+
"eval_f1": 0.9256844850065189,
|
584 |
+
"eval_loss": 0.28850072622299194,
|
585 |
+
"eval_precision": 0.9056122448979592,
|
586 |
+
"eval_recall": 0.9466666666666667,
|
587 |
+
"eval_runtime": 100.8319,
|
588 |
+
"eval_samples_per_second": 37.191,
|
589 |
+
"eval_steps_per_second": 4.651,
|
590 |
+
"step": 1376
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.65,
|
594 |
+
"learning_rate": 1.7573126142595978e-05,
|
595 |
+
"loss": 0.3728,
|
596 |
+
"step": 1419
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.65,
|
600 |
+
"eval_accuracy": 0.9301333333333334,
|
601 |
+
"eval_f1": 0.9273433166943982,
|
602 |
+
"eval_loss": 0.29230690002441406,
|
603 |
+
"eval_precision": 0.9659156556903524,
|
604 |
+
"eval_recall": 0.8917333333333334,
|
605 |
+
"eval_runtime": 100.785,
|
606 |
+
"eval_samples_per_second": 37.208,
|
607 |
+
"eval_steps_per_second": 4.653,
|
608 |
+
"step": 1419
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.67,
|
612 |
+
"learning_rate": 1.659049360146252e-05,
|
613 |
+
"loss": 0.5048,
|
614 |
+
"step": 1462
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.67,
|
618 |
+
"eval_accuracy": 0.9464,
|
619 |
+
"eval_f1": 0.9464713715046603,
|
620 |
+
"eval_loss": 0.2164454311132431,
|
621 |
+
"eval_precision": 0.9452127659574469,
|
622 |
+
"eval_recall": 0.9477333333333333,
|
623 |
+
"eval_runtime": 100.7467,
|
624 |
+
"eval_samples_per_second": 37.222,
|
625 |
+
"eval_steps_per_second": 4.655,
|
626 |
+
"step": 1462
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.69,
|
630 |
+
"learning_rate": 1.5607861060329068e-05,
|
631 |
+
"loss": 0.4483,
|
632 |
+
"step": 1505
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.69,
|
636 |
+
"eval_accuracy": 0.9250666666666667,
|
637 |
+
"eval_f1": 0.9274464239607538,
|
638 |
+
"eval_loss": 0.3050013482570648,
|
639 |
+
"eval_precision": 0.8988988988988988,
|
640 |
+
"eval_recall": 0.9578666666666666,
|
641 |
+
"eval_runtime": 100.8928,
|
642 |
+
"eval_samples_per_second": 37.168,
|
643 |
+
"eval_steps_per_second": 4.648,
|
644 |
+
"step": 1505
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.71,
|
648 |
+
"learning_rate": 1.4625228519195613e-05,
|
649 |
+
"loss": 0.3347,
|
650 |
+
"step": 1548
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.71,
|
654 |
+
"eval_accuracy": 0.9466666666666667,
|
655 |
+
"eval_f1": 0.9471179270227393,
|
656 |
+
"eval_loss": 0.22358763217926025,
|
657 |
+
"eval_precision": 0.9391714735186156,
|
658 |
+
"eval_recall": 0.9552,
|
659 |
+
"eval_runtime": 100.8242,
|
660 |
+
"eval_samples_per_second": 37.193,
|
661 |
+
"eval_steps_per_second": 4.652,
|
662 |
+
"step": 1548
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.73,
|
666 |
+
"learning_rate": 1.3642595978062158e-05,
|
667 |
+
"loss": 0.31,
|
668 |
+
"step": 1591
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.73,
|
672 |
+
"eval_accuracy": 0.9386666666666666,
|
673 |
+
"eval_f1": 0.9386011745862254,
|
674 |
+
"eval_loss": 0.18921497464179993,
|
675 |
+
"eval_precision": 0.9396044895777659,
|
676 |
+
"eval_recall": 0.9376,
|
677 |
+
"eval_runtime": 100.5904,
|
678 |
+
"eval_samples_per_second": 37.28,
|
679 |
+
"eval_steps_per_second": 4.662,
|
680 |
+
"step": 1591
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.75,
|
684 |
+
"learning_rate": 1.2659963436928701e-05,
|
685 |
+
"loss": 0.1936,
|
686 |
+
"step": 1634
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.75,
|
690 |
+
"eval_accuracy": 0.9424,
|
691 |
+
"eval_f1": 0.9430079155672824,
|
692 |
+
"eval_loss": 0.24673737585544586,
|
693 |
+
"eval_precision": 0.933159268929504,
|
694 |
+
"eval_recall": 0.9530666666666666,
|
695 |
+
"eval_runtime": 100.7748,
|
696 |
+
"eval_samples_per_second": 37.212,
|
697 |
+
"eval_steps_per_second": 4.654,
|
698 |
+
"step": 1634
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.77,
|
702 |
+
"learning_rate": 1.1677330895795248e-05,
|
703 |
+
"loss": 0.2855,
|
704 |
+
"step": 1677
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.77,
|
708 |
+
"eval_accuracy": 0.9384,
|
709 |
+
"eval_f1": 0.9391304347826087,
|
710 |
+
"eval_loss": 0.37995821237564087,
|
711 |
+
"eval_precision": 0.928125,
|
712 |
+
"eval_recall": 0.9504,
|
713 |
+
"eval_runtime": 100.6345,
|
714 |
+
"eval_samples_per_second": 37.264,
|
715 |
+
"eval_steps_per_second": 4.66,
|
716 |
+
"step": 1677
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.79,
|
720 |
+
"learning_rate": 1.0694698354661791e-05,
|
721 |
+
"loss": 0.2566,
|
722 |
+
"step": 1720
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.79,
|
726 |
+
"eval_accuracy": 0.9370666666666667,
|
727 |
+
"eval_f1": 0.9371671991480297,
|
728 |
+
"eval_loss": 0.38548287749290466,
|
729 |
+
"eval_precision": 0.935672514619883,
|
730 |
+
"eval_recall": 0.9386666666666666,
|
731 |
+
"eval_runtime": 101.0016,
|
732 |
+
"eval_samples_per_second": 37.128,
|
733 |
+
"eval_steps_per_second": 4.643,
|
734 |
+
"step": 1720
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.81,
|
738 |
+
"learning_rate": 9.712065813528338e-06,
|
739 |
+
"loss": 0.2966,
|
740 |
+
"step": 1763
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.81,
|
744 |
+
"eval_accuracy": 0.9512,
|
745 |
+
"eval_f1": 0.950068212824011,
|
746 |
+
"eval_loss": 0.28995445370674133,
|
747 |
+
"eval_precision": 0.9726256983240223,
|
748 |
+
"eval_recall": 0.9285333333333333,
|
749 |
+
"eval_runtime": 100.6179,
|
750 |
+
"eval_samples_per_second": 37.27,
|
751 |
+
"eval_steps_per_second": 4.661,
|
752 |
+
"step": 1763
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.83,
|
756 |
+
"learning_rate": 8.729433272394881e-06,
|
757 |
+
"loss": 0.2485,
|
758 |
+
"step": 1806
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.83,
|
762 |
+
"eval_accuracy": 0.9549333333333333,
|
763 |
+
"eval_f1": 0.9545087483176311,
|
764 |
+
"eval_loss": 0.24945972859859467,
|
765 |
+
"eval_precision": 0.9635869565217391,
|
766 |
+
"eval_recall": 0.9456,
|
767 |
+
"eval_runtime": 100.5538,
|
768 |
+
"eval_samples_per_second": 37.293,
|
769 |
+
"eval_steps_per_second": 4.664,
|
770 |
+
"step": 1806
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.85,
|
774 |
+
"learning_rate": 7.746800731261426e-06,
|
775 |
+
"loss": 0.2553,
|
776 |
+
"step": 1849
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.85,
|
780 |
+
"eval_accuracy": 0.9357333333333333,
|
781 |
+
"eval_f1": 0.9367620047231697,
|
782 |
+
"eval_loss": 0.394607812166214,
|
783 |
+
"eval_precision": 0.922004132231405,
|
784 |
+
"eval_recall": 0.952,
|
785 |
+
"eval_runtime": 100.5784,
|
786 |
+
"eval_samples_per_second": 37.284,
|
787 |
+
"eval_steps_per_second": 4.663,
|
788 |
+
"step": 1849
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.86,
|
792 |
+
"learning_rate": 6.764168190127972e-06,
|
793 |
+
"loss": 0.2719,
|
794 |
+
"step": 1892
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.86,
|
798 |
+
"eval_accuracy": 0.9533333333333334,
|
799 |
+
"eval_f1": 0.9524068534131085,
|
800 |
+
"eval_loss": 0.361551433801651,
|
801 |
+
"eval_precision": 0.9716981132075472,
|
802 |
+
"eval_recall": 0.9338666666666666,
|
803 |
+
"eval_runtime": 100.5791,
|
804 |
+
"eval_samples_per_second": 37.284,
|
805 |
+
"eval_steps_per_second": 4.663,
|
806 |
+
"step": 1892
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.88,
|
810 |
+
"learning_rate": 5.781535648994515e-06,
|
811 |
+
"loss": 0.2925,
|
812 |
+
"step": 1935
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.88,
|
816 |
+
"eval_accuracy": 0.9541333333333334,
|
817 |
+
"eval_f1": 0.9532862574687669,
|
818 |
+
"eval_loss": 0.30848976969718933,
|
819 |
+
"eval_precision": 0.9712230215827338,
|
820 |
+
"eval_recall": 0.936,
|
821 |
+
"eval_runtime": 100.6234,
|
822 |
+
"eval_samples_per_second": 37.268,
|
823 |
+
"eval_steps_per_second": 4.661,
|
824 |
+
"step": 1935
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.9,
|
828 |
+
"learning_rate": 4.798903107861061e-06,
|
829 |
+
"loss": 0.2477,
|
830 |
+
"step": 1978
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.9,
|
834 |
+
"eval_accuracy": 0.9544,
|
835 |
+
"eval_f1": 0.9536710918450284,
|
836 |
+
"eval_loss": 0.28153562545776367,
|
837 |
+
"eval_precision": 0.9691629955947136,
|
838 |
+
"eval_recall": 0.9386666666666666,
|
839 |
+
"eval_runtime": 100.4809,
|
840 |
+
"eval_samples_per_second": 37.321,
|
841 |
+
"eval_steps_per_second": 4.668,
|
842 |
+
"step": 1978
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.92,
|
846 |
+
"learning_rate": 3.816270566727605e-06,
|
847 |
+
"loss": 0.2164,
|
848 |
+
"step": 2021
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.92,
|
852 |
+
"eval_accuracy": 0.9568,
|
853 |
+
"eval_f1": 0.9560499186109603,
|
854 |
+
"eval_loss": 0.24747176468372345,
|
855 |
+
"eval_precision": 0.9729431253451132,
|
856 |
+
"eval_recall": 0.9397333333333333,
|
857 |
+
"eval_runtime": 100.5076,
|
858 |
+
"eval_samples_per_second": 37.311,
|
859 |
+
"eval_steps_per_second": 4.666,
|
860 |
+
"step": 2021
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.94,
|
864 |
+
"learning_rate": 2.83363802559415e-06,
|
865 |
+
"loss": 0.2816,
|
866 |
+
"step": 2064
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.94,
|
870 |
+
"eval_accuracy": 0.9570666666666666,
|
871 |
+
"eval_f1": 0.9563093622795115,
|
872 |
+
"eval_loss": 0.263465017080307,
|
873 |
+
"eval_precision": 0.9734806629834254,
|
874 |
+
"eval_recall": 0.9397333333333333,
|
875 |
+
"eval_runtime": 100.4934,
|
876 |
+
"eval_samples_per_second": 37.316,
|
877 |
+
"eval_steps_per_second": 4.667,
|
878 |
+
"step": 2064
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.96,
|
882 |
+
"learning_rate": 1.851005484460695e-06,
|
883 |
+
"loss": 0.351,
|
884 |
+
"step": 2107
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.96,
|
888 |
+
"eval_accuracy": 0.9573333333333334,
|
889 |
+
"eval_f1": 0.9566160520607375,
|
890 |
+
"eval_loss": 0.23055072128772736,
|
891 |
+
"eval_precision": 0.972972972972973,
|
892 |
+
"eval_recall": 0.9408,
|
893 |
+
"eval_runtime": 100.5497,
|
894 |
+
"eval_samples_per_second": 37.295,
|
895 |
+
"eval_steps_per_second": 4.664,
|
896 |
+
"step": 2107
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.98,
|
900 |
+
"learning_rate": 8.683729433272396e-07,
|
901 |
+
"loss": 0.2591,
|
902 |
+
"step": 2150
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.98,
|
906 |
+
"eval_accuracy": 0.9562666666666667,
|
907 |
+
"eval_f1": 0.955288985823337,
|
908 |
+
"eval_loss": 0.2391371726989746,
|
909 |
+
"eval_precision": 0.9771332961517011,
|
910 |
+
"eval_recall": 0.9344,
|
911 |
+
"eval_runtime": 100.6094,
|
912 |
+
"eval_samples_per_second": 37.273,
|
913 |
+
"eval_steps_per_second": 4.662,
|
914 |
+
"step": 2150
|
915 |
+
}
|
916 |
+
],
|
917 |
+
"max_steps": 2188,
|
918 |
+
"num_train_epochs": 1,
|
919 |
+
"total_flos": 1.62524823552e+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 sha256:1983da0554c54a37764704f64d00f7b12687e75ba40068a5635861ba961f2a1f
|
3 |
+
size 3451
|