pranaydeeps
commited on
Commit
•
1f78c04
1
Parent(s):
4835db8
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +108 -0
- all_results.json +17 -0
- config.json +139 -0
- eval_results.json +12 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +21 -0
- train_results.json +8 -0
- trainer_state.json +565 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: pos_final_xlm_de
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# pos_final_xlm_de
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0580
|
23 |
+
- Precision: 0.9895
|
24 |
+
- Recall: 0.9894
|
25 |
+
- F1: 0.9894
|
26 |
+
- Accuracy: 0.9901
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 5e-05
|
46 |
+
- train_batch_size: 256
|
47 |
+
- eval_batch_size: 256
|
48 |
+
- seed: 42
|
49 |
+
- gradient_accumulation_steps: 4
|
50 |
+
- total_train_batch_size: 1024
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_steps: 500
|
54 |
+
- num_epochs: 40.0
|
55 |
+
- mixed_precision_training: Native AMP
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
61 |
+
| No log | 0.99 | 128 | 0.3828 | 0.9159 | 0.9106 | 0.9133 | 0.9196 |
|
62 |
+
| No log | 1.99 | 256 | 0.0659 | 0.9810 | 0.9812 | 0.9811 | 0.9824 |
|
63 |
+
| No log | 2.99 | 384 | 0.0447 | 0.9857 | 0.9857 | 0.9857 | 0.9865 |
|
64 |
+
| 0.7525 | 3.99 | 512 | 0.0388 | 0.9870 | 0.9871 | 0.9871 | 0.9878 |
|
65 |
+
| 0.7525 | 4.99 | 640 | 0.0373 | 0.9871 | 0.9875 | 0.9873 | 0.9881 |
|
66 |
+
| 0.7525 | 5.99 | 768 | 0.0354 | 0.9880 | 0.9882 | 0.9881 | 0.9889 |
|
67 |
+
| 0.7525 | 6.99 | 896 | 0.0350 | 0.9883 | 0.9885 | 0.9884 | 0.9891 |
|
68 |
+
| 0.0318 | 7.99 | 1024 | 0.0354 | 0.9884 | 0.9886 | 0.9885 | 0.9891 |
|
69 |
+
| 0.0318 | 8.99 | 1152 | 0.0356 | 0.9888 | 0.9888 | 0.9888 | 0.9894 |
|
70 |
+
| 0.0318 | 9.99 | 1280 | 0.0367 | 0.9888 | 0.9889 | 0.9888 | 0.9895 |
|
71 |
+
| 0.0318 | 10.99 | 1408 | 0.0370 | 0.9887 | 0.9888 | 0.9887 | 0.9894 |
|
72 |
+
| 0.0205 | 11.99 | 1536 | 0.0370 | 0.9889 | 0.9891 | 0.9890 | 0.9896 |
|
73 |
+
| 0.0205 | 12.99 | 1664 | 0.0388 | 0.9888 | 0.9889 | 0.9888 | 0.9895 |
|
74 |
+
| 0.0205 | 13.99 | 1792 | 0.0397 | 0.9890 | 0.9891 | 0.9890 | 0.9897 |
|
75 |
+
| 0.0205 | 14.99 | 1920 | 0.0403 | 0.9891 | 0.9891 | 0.9891 | 0.9897 |
|
76 |
+
| 0.0146 | 15.99 | 2048 | 0.0413 | 0.9891 | 0.9891 | 0.9891 | 0.9897 |
|
77 |
+
| 0.0146 | 16.99 | 2176 | 0.0423 | 0.9891 | 0.9891 | 0.9891 | 0.9898 |
|
78 |
+
| 0.0146 | 17.99 | 2304 | 0.0429 | 0.9891 | 0.9891 | 0.9891 | 0.9897 |
|
79 |
+
| 0.0146 | 18.99 | 2432 | 0.0443 | 0.9893 | 0.9894 | 0.9893 | 0.9899 |
|
80 |
+
| 0.0103 | 19.99 | 2560 | 0.0457 | 0.9890 | 0.9889 | 0.9890 | 0.9896 |
|
81 |
+
| 0.0103 | 20.99 | 2688 | 0.0455 | 0.9891 | 0.9892 | 0.9891 | 0.9898 |
|
82 |
+
| 0.0103 | 21.99 | 2816 | 0.0468 | 0.9891 | 0.9892 | 0.9891 | 0.9898 |
|
83 |
+
| 0.0103 | 22.99 | 2944 | 0.0491 | 0.9891 | 0.9892 | 0.9892 | 0.9898 |
|
84 |
+
| 0.0073 | 23.99 | 3072 | 0.0495 | 0.9894 | 0.9894 | 0.9894 | 0.9900 |
|
85 |
+
| 0.0073 | 24.99 | 3200 | 0.0503 | 0.9892 | 0.9892 | 0.9892 | 0.9898 |
|
86 |
+
| 0.0073 | 25.99 | 3328 | 0.0519 | 0.9892 | 0.9892 | 0.9892 | 0.9898 |
|
87 |
+
| 0.0073 | 26.99 | 3456 | 0.0522 | 0.9892 | 0.9893 | 0.9892 | 0.9899 |
|
88 |
+
| 0.0052 | 27.99 | 3584 | 0.0526 | 0.9892 | 0.9892 | 0.9892 | 0.9899 |
|
89 |
+
| 0.0052 | 28.99 | 3712 | 0.0535 | 0.9892 | 0.9892 | 0.9892 | 0.9899 |
|
90 |
+
| 0.0052 | 29.99 | 3840 | 0.0544 | 0.9894 | 0.9894 | 0.9894 | 0.9900 |
|
91 |
+
| 0.0052 | 30.99 | 3968 | 0.0548 | 0.9893 | 0.9894 | 0.9894 | 0.9900 |
|
92 |
+
| 0.0038 | 31.99 | 4096 | 0.0563 | 0.9892 | 0.9892 | 0.9892 | 0.9899 |
|
93 |
+
| 0.0038 | 32.99 | 4224 | 0.0562 | 0.9894 | 0.9894 | 0.9894 | 0.9900 |
|
94 |
+
| 0.0038 | 33.99 | 4352 | 0.0577 | 0.9891 | 0.9892 | 0.9892 | 0.9898 |
|
95 |
+
| 0.0038 | 34.99 | 4480 | 0.0580 | 0.9895 | 0.9894 | 0.9894 | 0.9901 |
|
96 |
+
| 0.003 | 35.99 | 4608 | 0.0581 | 0.9893 | 0.9894 | 0.9894 | 0.9900 |
|
97 |
+
| 0.003 | 36.99 | 4736 | 0.0585 | 0.9893 | 0.9893 | 0.9893 | 0.9899 |
|
98 |
+
| 0.003 | 37.99 | 4864 | 0.0586 | 0.9893 | 0.9894 | 0.9893 | 0.9900 |
|
99 |
+
| 0.003 | 38.99 | 4992 | 0.0588 | 0.9893 | 0.9894 | 0.9894 | 0.9900 |
|
100 |
+
| 0.0024 | 39.99 | 5120 | 0.0589 | 0.9894 | 0.9894 | 0.9894 | 0.9900 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.25.1
|
106 |
+
- Pytorch 1.12.0
|
107 |
+
- Datasets 2.18.0
|
108 |
+
- Tokenizers 0.13.2
|
all_results.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 39.99,
|
3 |
+
"eval_accuracy": 0.9900658187453014,
|
4 |
+
"eval_f1": 0.9894462659525121,
|
5 |
+
"eval_loss": 0.05798300728201866,
|
6 |
+
"eval_precision": 0.989465880076756,
|
7 |
+
"eval_recall": 0.9894266526058723,
|
8 |
+
"eval_runtime": 18.9966,
|
9 |
+
"eval_samples": 437,
|
10 |
+
"eval_samples_per_second": 771.139,
|
11 |
+
"eval_steps_per_second": 3.053,
|
12 |
+
"train_loss": 0.08320926361484453,
|
13 |
+
"train_runtime": 4249.1875,
|
14 |
+
"train_samples": 131833,
|
15 |
+
"train_samples_per_second": 1241.018,
|
16 |
+
"train_steps_per_second": 1.205
|
17 |
+
}
|
config.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"finetuning_task": "pos",
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "ART",
|
16 |
+
"1": "PWAV",
|
17 |
+
"2": "PIAT",
|
18 |
+
"3": "ADV",
|
19 |
+
"4": "KON",
|
20 |
+
"5": "VAPP",
|
21 |
+
"6": "ITJ",
|
22 |
+
"7": "$,",
|
23 |
+
"8": "PPOSAT",
|
24 |
+
"9": "VAINF",
|
25 |
+
"10": "PRELAT",
|
26 |
+
"11": "FM",
|
27 |
+
"12": "VVPP",
|
28 |
+
"13": "PWS",
|
29 |
+
"14": "VVIZU",
|
30 |
+
"15": "ADJD",
|
31 |
+
"16": "APZR",
|
32 |
+
"17": "NN",
|
33 |
+
"18": "TRUNC",
|
34 |
+
"19": "PTKA",
|
35 |
+
"20": "PROAV",
|
36 |
+
"21": "CARD",
|
37 |
+
"22": "PDS",
|
38 |
+
"23": "VMINF",
|
39 |
+
"24": "PRELS",
|
40 |
+
"25": "VVIMP",
|
41 |
+
"26": "PPOSS",
|
42 |
+
"27": "PDAT",
|
43 |
+
"28": "KOKOM",
|
44 |
+
"29": "PTKANT",
|
45 |
+
"30": "APPRART",
|
46 |
+
"31": "KOUI",
|
47 |
+
"32": "PIS",
|
48 |
+
"33": "PPER",
|
49 |
+
"34": "VVINF",
|
50 |
+
"35": "APPR",
|
51 |
+
"36": "KOUS",
|
52 |
+
"37": "PTKNEG",
|
53 |
+
"38": "PRF",
|
54 |
+
"39": "PWAT",
|
55 |
+
"40": "APPO",
|
56 |
+
"41": "$.",
|
57 |
+
"42": "$(",
|
58 |
+
"43": "PTKVZ",
|
59 |
+
"44": "VMFIN",
|
60 |
+
"45": "VMPP",
|
61 |
+
"46": "XY",
|
62 |
+
"47": "VAIMP",
|
63 |
+
"48": "ADJA",
|
64 |
+
"49": "VVFIN",
|
65 |
+
"50": "NE",
|
66 |
+
"51": "VAFIN",
|
67 |
+
"52": "PTKZU"
|
68 |
+
},
|
69 |
+
"initializer_range": 0.02,
|
70 |
+
"intermediate_size": 3072,
|
71 |
+
"label2id": {
|
72 |
+
"$(": 42,
|
73 |
+
"$,": 7,
|
74 |
+
"$.": 41,
|
75 |
+
"ADJA": 48,
|
76 |
+
"ADJD": 15,
|
77 |
+
"ADV": 3,
|
78 |
+
"APPO": 40,
|
79 |
+
"APPR": 35,
|
80 |
+
"APPRART": 30,
|
81 |
+
"APZR": 16,
|
82 |
+
"ART": 0,
|
83 |
+
"CARD": 21,
|
84 |
+
"FM": 11,
|
85 |
+
"ITJ": 6,
|
86 |
+
"KOKOM": 28,
|
87 |
+
"KON": 4,
|
88 |
+
"KOUI": 31,
|
89 |
+
"KOUS": 36,
|
90 |
+
"NE": 50,
|
91 |
+
"NN": 17,
|
92 |
+
"PDAT": 27,
|
93 |
+
"PDS": 22,
|
94 |
+
"PIAT": 2,
|
95 |
+
"PIS": 32,
|
96 |
+
"PPER": 33,
|
97 |
+
"PPOSAT": 8,
|
98 |
+
"PPOSS": 26,
|
99 |
+
"PRELAT": 10,
|
100 |
+
"PRELS": 24,
|
101 |
+
"PRF": 38,
|
102 |
+
"PROAV": 20,
|
103 |
+
"PTKA": 19,
|
104 |
+
"PTKANT": 29,
|
105 |
+
"PTKNEG": 37,
|
106 |
+
"PTKVZ": 43,
|
107 |
+
"PTKZU": 52,
|
108 |
+
"PWAT": 39,
|
109 |
+
"PWAV": 1,
|
110 |
+
"PWS": 13,
|
111 |
+
"TRUNC": 18,
|
112 |
+
"VAFIN": 51,
|
113 |
+
"VAIMP": 47,
|
114 |
+
"VAINF": 9,
|
115 |
+
"VAPP": 5,
|
116 |
+
"VMFIN": 44,
|
117 |
+
"VMINF": 23,
|
118 |
+
"VMPP": 45,
|
119 |
+
"VVFIN": 49,
|
120 |
+
"VVIMP": 25,
|
121 |
+
"VVINF": 34,
|
122 |
+
"VVIZU": 14,
|
123 |
+
"VVPP": 12,
|
124 |
+
"XY": 46
|
125 |
+
},
|
126 |
+
"layer_norm_eps": 1e-05,
|
127 |
+
"max_position_embeddings": 514,
|
128 |
+
"model_type": "xlm-roberta",
|
129 |
+
"num_attention_heads": 12,
|
130 |
+
"num_hidden_layers": 12,
|
131 |
+
"output_past": true,
|
132 |
+
"pad_token_id": 1,
|
133 |
+
"position_embedding_type": "absolute",
|
134 |
+
"torch_dtype": "float32",
|
135 |
+
"transformers_version": "4.25.1",
|
136 |
+
"type_vocab_size": 1,
|
137 |
+
"use_cache": true,
|
138 |
+
"vocab_size": 250002
|
139 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 39.99,
|
3 |
+
"eval_accuracy": 0.9900658187453014,
|
4 |
+
"eval_f1": 0.9894462659525121,
|
5 |
+
"eval_loss": 0.05798300728201866,
|
6 |
+
"eval_precision": 0.989465880076756,
|
7 |
+
"eval_recall": 0.9894266526058723,
|
8 |
+
"eval_runtime": 18.9966,
|
9 |
+
"eval_samples": 437,
|
10 |
+
"eval_samples_per_second": 771.139,
|
11 |
+
"eval_steps_per_second": 3.053
|
12 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a350051c0c5aa4a2de0ad5428149141a07bea1a180f07e9ed68a1598404b51b
|
3 |
+
size 1110046321
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
|
3 |
+
size 17082758
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "xlm-roberta-base",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"token": null,
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 39.99,
|
3 |
+
"train_loss": 0.08320926361484453,
|
4 |
+
"train_runtime": 4249.1875,
|
5 |
+
"train_samples": 131833,
|
6 |
+
"train_samples_per_second": 1241.018,
|
7 |
+
"train_steps_per_second": 1.205
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,565 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9894462659525121,
|
3 |
+
"best_model_checkpoint": "models/pos_final_xlm_de/checkpoint-4480",
|
4 |
+
"epoch": 39.994174757281556,
|
5 |
+
"global_step": 5120,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.99,
|
12 |
+
"eval_accuracy": 0.9195868301139938,
|
13 |
+
"eval_f1": 0.9132772848631359,
|
14 |
+
"eval_loss": 0.3827908933162689,
|
15 |
+
"eval_precision": 0.9159339498123846,
|
16 |
+
"eval_recall": 0.9106359866475313,
|
17 |
+
"eval_runtime": 21.0552,
|
18 |
+
"eval_samples_per_second": 695.744,
|
19 |
+
"eval_steps_per_second": 2.755,
|
20 |
+
"step": 128
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.99,
|
24 |
+
"eval_accuracy": 0.982432992221421,
|
25 |
+
"eval_f1": 0.9811226512328548,
|
26 |
+
"eval_loss": 0.06585212051868439,
|
27 |
+
"eval_precision": 0.9810370934113413,
|
28 |
+
"eval_recall": 0.9812082239789405,
|
29 |
+
"eval_runtime": 20.8303,
|
30 |
+
"eval_samples_per_second": 703.256,
|
31 |
+
"eval_steps_per_second": 2.784,
|
32 |
+
"step": 256
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.99,
|
36 |
+
"eval_accuracy": 0.9865217324598413,
|
37 |
+
"eval_f1": 0.9856564607376338,
|
38 |
+
"eval_loss": 0.04468955472111702,
|
39 |
+
"eval_precision": 0.9856525531240089,
|
40 |
+
"eval_recall": 0.9856603683822421,
|
41 |
+
"eval_runtime": 22.0421,
|
42 |
+
"eval_samples_per_second": 664.592,
|
43 |
+
"eval_steps_per_second": 2.631,
|
44 |
+
"step": 384
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.9,
|
48 |
+
"learning_rate": 4.9800000000000004e-05,
|
49 |
+
"loss": 0.7525,
|
50 |
+
"step": 500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.99,
|
54 |
+
"eval_accuracy": 0.9877989843354454,
|
55 |
+
"eval_f1": 0.9870567994418368,
|
56 |
+
"eval_loss": 0.038840390741825104,
|
57 |
+
"eval_precision": 0.986986371960646,
|
58 |
+
"eval_recall": 0.9871272369746034,
|
59 |
+
"eval_runtime": 19.2442,
|
60 |
+
"eval_samples_per_second": 761.216,
|
61 |
+
"eval_steps_per_second": 3.014,
|
62 |
+
"step": 512
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.99,
|
66 |
+
"eval_accuracy": 0.9880904892680158,
|
67 |
+
"eval_f1": 0.987278301765262,
|
68 |
+
"eval_loss": 0.03728002309799194,
|
69 |
+
"eval_precision": 0.9870924532264904,
|
70 |
+
"eval_recall": 0.9874642202998755,
|
71 |
+
"eval_runtime": 19.7895,
|
72 |
+
"eval_samples_per_second": 740.24,
|
73 |
+
"eval_steps_per_second": 2.931,
|
74 |
+
"step": 640
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.99,
|
78 |
+
"eval_accuracy": 0.9888691142852759,
|
79 |
+
"eval_f1": 0.9881274230760082,
|
80 |
+
"eval_loss": 0.03543518856167793,
|
81 |
+
"eval_precision": 0.9880334223857051,
|
82 |
+
"eval_recall": 0.9882214416543106,
|
83 |
+
"eval_runtime": 20.2566,
|
84 |
+
"eval_samples_per_second": 723.172,
|
85 |
+
"eval_steps_per_second": 2.863,
|
86 |
+
"step": 768
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 6.99,
|
90 |
+
"eval_accuracy": 0.9891414412617561,
|
91 |
+
"eval_f1": 0.9883990811231861,
|
92 |
+
"eval_loss": 0.03501536697149277,
|
93 |
+
"eval_precision": 0.988295262217043,
|
94 |
+
"eval_recall": 0.9885029218436556,
|
95 |
+
"eval_runtime": 20.0491,
|
96 |
+
"eval_samples_per_second": 730.658,
|
97 |
+
"eval_steps_per_second": 2.893,
|
98 |
+
"step": 896
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.81,
|
102 |
+
"learning_rate": 4.462121212121213e-05,
|
103 |
+
"loss": 0.0318,
|
104 |
+
"step": 1000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.99,
|
108 |
+
"eval_accuracy": 0.9890839073934856,
|
109 |
+
"eval_f1": 0.9884860173195352,
|
110 |
+
"eval_loss": 0.03539884835481644,
|
111 |
+
"eval_precision": 0.9884056936962649,
|
112 |
+
"eval_recall": 0.988566353999001,
|
113 |
+
"eval_runtime": 19.1691,
|
114 |
+
"eval_samples_per_second": 764.201,
|
115 |
+
"eval_steps_per_second": 3.026,
|
116 |
+
"step": 1024
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.99,
|
120 |
+
"eval_accuracy": 0.989383083508492,
|
121 |
+
"eval_f1": 0.9887981223821485,
|
122 |
+
"eval_loss": 0.03559485822916031,
|
123 |
+
"eval_precision": 0.9888118431120679,
|
124 |
+
"eval_recall": 0.9887844020330006,
|
125 |
+
"eval_runtime": 19.05,
|
126 |
+
"eval_samples_per_second": 768.977,
|
127 |
+
"eval_steps_per_second": 3.045,
|
128 |
+
"step": 1152
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.99,
|
132 |
+
"eval_accuracy": 0.9894904800625969,
|
133 |
+
"eval_f1": 0.9888288531140862,
|
134 |
+
"eval_loss": 0.036680448800325394,
|
135 |
+
"eval_precision": 0.9887543801233569,
|
136 |
+
"eval_recall": 0.9889033373242732,
|
137 |
+
"eval_runtime": 20.8166,
|
138 |
+
"eval_samples_per_second": 703.718,
|
139 |
+
"eval_steps_per_second": 2.786,
|
140 |
+
"step": 1280
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.99,
|
144 |
+
"eval_accuracy": 0.9893677411436199,
|
145 |
+
"eval_f1": 0.9887373190775782,
|
146 |
+
"eval_loss": 0.03701608628034592,
|
147 |
+
"eval_precision": 0.9886942043922937,
|
148 |
+
"eval_recall": 0.9887804375232915,
|
149 |
+
"eval_runtime": 19.5262,
|
150 |
+
"eval_samples_per_second": 750.222,
|
151 |
+
"eval_steps_per_second": 2.97,
|
152 |
+
"step": 1408
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 11.71,
|
156 |
+
"learning_rate": 3.9209956709956716e-05,
|
157 |
+
"loss": 0.0205,
|
158 |
+
"step": 1500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 11.99,
|
162 |
+
"eval_accuracy": 0.9896170545727918,
|
163 |
+
"eval_f1": 0.9890034963648904,
|
164 |
+
"eval_loss": 0.03703853860497475,
|
165 |
+
"eval_precision": 0.9889094123336214,
|
166 |
+
"eval_recall": 0.9890975983000182,
|
167 |
+
"eval_runtime": 18.6632,
|
168 |
+
"eval_samples_per_second": 784.912,
|
169 |
+
"eval_steps_per_second": 3.108,
|
170 |
+
"step": 1536
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 12.99,
|
174 |
+
"eval_accuracy": 0.9894828088801608,
|
175 |
+
"eval_f1": 0.9888483647175421,
|
176 |
+
"eval_loss": 0.03879130259156227,
|
177 |
+
"eval_precision": 0.9888013256059176,
|
178 |
+
"eval_recall": 0.9888954083048549,
|
179 |
+
"eval_runtime": 18.564,
|
180 |
+
"eval_samples_per_second": 789.109,
|
181 |
+
"eval_steps_per_second": 3.124,
|
182 |
+
"step": 1664
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 13.99,
|
186 |
+
"eval_accuracy": 0.9896592460761902,
|
187 |
+
"eval_f1": 0.989038521766364,
|
188 |
+
"eval_loss": 0.03970788046717644,
|
189 |
+
"eval_precision": 0.9890032348090828,
|
190 |
+
"eval_recall": 0.9890738112417637,
|
191 |
+
"eval_runtime": 19.0522,
|
192 |
+
"eval_samples_per_second": 768.889,
|
193 |
+
"eval_steps_per_second": 3.044,
|
194 |
+
"step": 1792
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 14.99,
|
198 |
+
"eval_accuracy": 0.9896784240322803,
|
199 |
+
"eval_f1": 0.989059827026727,
|
200 |
+
"eval_loss": 0.040303945541381836,
|
201 |
+
"eval_precision": 0.989069630064266,
|
202 |
+
"eval_recall": 0.9890500241835092,
|
203 |
+
"eval_runtime": 18.8982,
|
204 |
+
"eval_samples_per_second": 775.155,
|
205 |
+
"eval_steps_per_second": 3.069,
|
206 |
+
"step": 1920
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 15.62,
|
210 |
+
"learning_rate": 3.3798701298701305e-05,
|
211 |
+
"loss": 0.0146,
|
212 |
+
"step": 2000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 15.99,
|
216 |
+
"eval_accuracy": 0.9897052731708066,
|
217 |
+
"eval_f1": 0.9891171188315472,
|
218 |
+
"eval_loss": 0.04127529263496399,
|
219 |
+
"eval_precision": 0.9891445699061152,
|
220 |
+
"eval_recall": 0.9890896692806,
|
221 |
+
"eval_runtime": 18.6421,
|
222 |
+
"eval_samples_per_second": 785.8,
|
223 |
+
"eval_steps_per_second": 3.111,
|
224 |
+
"step": 2048
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 16.99,
|
228 |
+
"eval_accuracy": 0.989758971447859,
|
229 |
+
"eval_f1": 0.9890990835617984,
|
230 |
+
"eval_loss": 0.04227915033698082,
|
231 |
+
"eval_precision": 0.9891441825426719,
|
232 |
+
"eval_recall": 0.9890539886932183,
|
233 |
+
"eval_runtime": 18.5222,
|
234 |
+
"eval_samples_per_second": 790.89,
|
235 |
+
"eval_steps_per_second": 3.131,
|
236 |
+
"step": 2176
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 17.99,
|
240 |
+
"eval_accuracy": 0.9897436290829869,
|
241 |
+
"eval_f1": 0.9891194678073816,
|
242 |
+
"eval_loss": 0.04291819408535957,
|
243 |
+
"eval_precision": 0.9891135858167388,
|
244 |
+
"eval_recall": 0.9891253498679818,
|
245 |
+
"eval_runtime": 19.3021,
|
246 |
+
"eval_samples_per_second": 758.935,
|
247 |
+
"eval_steps_per_second": 3.005,
|
248 |
+
"step": 2304
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 18.99,
|
252 |
+
"eval_accuracy": 0.9899277374614524,
|
253 |
+
"eval_f1": 0.9893141089045129,
|
254 |
+
"eval_loss": 0.04433906078338623,
|
255 |
+
"eval_precision": 0.9892729298062706,
|
256 |
+
"eval_recall": 0.9893552914311087,
|
257 |
+
"eval_runtime": 20.0023,
|
258 |
+
"eval_samples_per_second": 732.367,
|
259 |
+
"eval_steps_per_second": 2.9,
|
260 |
+
"step": 2432
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 19.53,
|
264 |
+
"learning_rate": 2.838744588744589e-05,
|
265 |
+
"loss": 0.0103,
|
266 |
+
"step": 2500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 19.99,
|
270 |
+
"eval_accuracy": 0.9895978766167017,
|
271 |
+
"eval_f1": 0.9889502105288197,
|
272 |
+
"eval_loss": 0.04566018655896187,
|
273 |
+
"eval_precision": 0.9890129497315686,
|
274 |
+
"eval_recall": 0.9888874792854367,
|
275 |
+
"eval_runtime": 18.9384,
|
276 |
+
"eval_samples_per_second": 773.508,
|
277 |
+
"eval_steps_per_second": 3.063,
|
278 |
+
"step": 2560
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 20.99,
|
282 |
+
"eval_accuracy": 0.9898049985424754,
|
283 |
+
"eval_f1": 0.9891496101074732,
|
284 |
+
"eval_loss": 0.04549423232674599,
|
285 |
+
"eval_precision": 0.9891064774439071,
|
286 |
+
"eval_recall": 0.9891927465330362,
|
287 |
+
"eval_runtime": 18.8835,
|
288 |
+
"eval_samples_per_second": 775.757,
|
289 |
+
"eval_steps_per_second": 3.071,
|
290 |
+
"step": 2688
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 21.99,
|
294 |
+
"eval_accuracy": 0.9897704782215131,
|
295 |
+
"eval_f1": 0.9891315336173181,
|
296 |
+
"eval_loss": 0.04684610292315483,
|
297 |
+
"eval_precision": 0.989109966739214,
|
298 |
+
"eval_recall": 0.9891531014359454,
|
299 |
+
"eval_runtime": 18.9876,
|
300 |
+
"eval_samples_per_second": 771.504,
|
301 |
+
"eval_steps_per_second": 3.055,
|
302 |
+
"step": 2816
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 22.99,
|
306 |
+
"eval_accuracy": 0.9898471900458736,
|
307 |
+
"eval_f1": 0.9891676858093711,
|
308 |
+
"eval_loss": 0.049145638942718506,
|
309 |
+
"eval_precision": 0.9891029884528939,
|
310 |
+
"eval_recall": 0.9892323916301271,
|
311 |
+
"eval_runtime": 18.5499,
|
312 |
+
"eval_samples_per_second": 789.708,
|
313 |
+
"eval_steps_per_second": 3.127,
|
314 |
+
"step": 2944
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 23.43,
|
318 |
+
"learning_rate": 2.2976190476190476e-05,
|
319 |
+
"loss": 0.0073,
|
320 |
+
"step": 3000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 23.99,
|
324 |
+
"eval_accuracy": 0.9899622577824145,
|
325 |
+
"eval_f1": 0.9894013665041952,
|
326 |
+
"eval_loss": 0.04954079911112785,
|
327 |
+
"eval_precision": 0.9893562619667725,
|
328 |
+
"eval_recall": 0.9894464751544176,
|
329 |
+
"eval_runtime": 19.048,
|
330 |
+
"eval_samples_per_second": 769.056,
|
331 |
+
"eval_steps_per_second": 3.045,
|
332 |
+
"step": 3072
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 24.99,
|
336 |
+
"eval_accuracy": 0.9897858205863852,
|
337 |
+
"eval_f1": 0.9891747989478087,
|
338 |
+
"eval_loss": 0.05031678453087807,
|
339 |
+
"eval_precision": 0.9891846031248885,
|
340 |
+
"eval_recall": 0.9891649949650727,
|
341 |
+
"eval_runtime": 18.6731,
|
342 |
+
"eval_samples_per_second": 784.498,
|
343 |
+
"eval_steps_per_second": 3.106,
|
344 |
+
"step": 3200
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 25.99,
|
348 |
+
"eval_accuracy": 0.9898126697249114,
|
349 |
+
"eval_f1": 0.9892364414843007,
|
350 |
+
"eval_loss": 0.05185426026582718,
|
351 |
+
"eval_precision": 0.9892285979337303,
|
352 |
+
"eval_recall": 0.9892442851592543,
|
353 |
+
"eval_runtime": 19.572,
|
354 |
+
"eval_samples_per_second": 748.468,
|
355 |
+
"eval_steps_per_second": 2.963,
|
356 |
+
"step": 3328
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 26.99,
|
360 |
+
"eval_accuracy": 0.9898548612283097,
|
361 |
+
"eval_f1": 0.9892308576661506,
|
362 |
+
"eval_loss": 0.05215698853135109,
|
363 |
+
"eval_precision": 0.9891896820331485,
|
364 |
+
"eval_recall": 0.989272036727218,
|
365 |
+
"eval_runtime": 19.399,
|
366 |
+
"eval_samples_per_second": 755.14,
|
367 |
+
"eval_steps_per_second": 2.99,
|
368 |
+
"step": 3456
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 27.34,
|
372 |
+
"learning_rate": 1.7564935064935065e-05,
|
373 |
+
"loss": 0.0052,
|
374 |
+
"step": 3500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 27.99,
|
378 |
+
"eval_accuracy": 0.9898702035931819,
|
379 |
+
"eval_f1": 0.9892028504316283,
|
380 |
+
"eval_loss": 0.05260332301259041,
|
381 |
+
"eval_precision": 0.9891852033919135,
|
382 |
+
"eval_recall": 0.9892204981009999,
|
383 |
+
"eval_runtime": 19.6509,
|
384 |
+
"eval_samples_per_second": 745.461,
|
385 |
+
"eval_steps_per_second": 2.952,
|
386 |
+
"step": 3584
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 28.99,
|
390 |
+
"eval_accuracy": 0.9898663680019638,
|
391 |
+
"eval_f1": 0.9891989716326818,
|
392 |
+
"eval_loss": 0.05352339521050453,
|
393 |
+
"eval_precision": 0.9891734819683569,
|
394 |
+
"eval_recall": 0.989224462610709,
|
395 |
+
"eval_runtime": 19.4431,
|
396 |
+
"eval_samples_per_second": 753.429,
|
397 |
+
"eval_steps_per_second": 2.983,
|
398 |
+
"step": 3712
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 29.99,
|
402 |
+
"eval_accuracy": 0.9900121204682489,
|
403 |
+
"eval_f1": 0.9893592137553174,
|
404 |
+
"eval_loss": 0.054358094930648804,
|
405 |
+
"eval_precision": 0.9893631361106265,
|
406 |
+
"eval_recall": 0.9893552914311087,
|
407 |
+
"eval_runtime": 18.4688,
|
408 |
+
"eval_samples_per_second": 793.177,
|
409 |
+
"eval_steps_per_second": 3.14,
|
410 |
+
"step": 3840
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 30.99,
|
414 |
+
"eval_accuracy": 0.9899660933736326,
|
415 |
+
"eval_f1": 0.9893714865647028,
|
416 |
+
"eval_loss": 0.05478381738066673,
|
417 |
+
"eval_precision": 0.989340109572098,
|
418 |
+
"eval_recall": 0.9894028655476177,
|
419 |
+
"eval_runtime": 18.761,
|
420 |
+
"eval_samples_per_second": 780.821,
|
421 |
+
"eval_steps_per_second": 3.092,
|
422 |
+
"step": 3968
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 31.25,
|
426 |
+
"learning_rate": 1.2153679653679655e-05,
|
427 |
+
"loss": 0.0038,
|
428 |
+
"step": 4000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 31.99,
|
432 |
+
"eval_accuracy": 0.9898702035931819,
|
433 |
+
"eval_f1": 0.989232477006026,
|
434 |
+
"eval_loss": 0.05625994876027107,
|
435 |
+
"eval_precision": 0.9892246334868896,
|
436 |
+
"eval_recall": 0.9892403206495453,
|
437 |
+
"eval_runtime": 19.3617,
|
438 |
+
"eval_samples_per_second": 756.597,
|
439 |
+
"eval_steps_per_second": 2.996,
|
440 |
+
"step": 4096
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 32.99,
|
444 |
+
"eval_accuracy": 0.9900466407892112,
|
445 |
+
"eval_f1": 0.9894185977362381,
|
446 |
+
"eval_loss": 0.05615779384970665,
|
447 |
+
"eval_precision": 0.9894303656950744,
|
448 |
+
"eval_recall": 0.9894068300573268,
|
449 |
+
"eval_runtime": 18.6932,
|
450 |
+
"eval_samples_per_second": 783.655,
|
451 |
+
"eval_steps_per_second": 3.103,
|
452 |
+
"step": 4224
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 33.99,
|
456 |
+
"eval_accuracy": 0.9898318476810015,
|
457 |
+
"eval_f1": 0.989171306638546,
|
458 |
+
"eval_loss": 0.057734012603759766,
|
459 |
+
"eval_precision": 0.9891379754613387,
|
460 |
+
"eval_recall": 0.9892046400621635,
|
461 |
+
"eval_runtime": 18.8622,
|
462 |
+
"eval_samples_per_second": 776.632,
|
463 |
+
"eval_steps_per_second": 3.075,
|
464 |
+
"step": 4352
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 34.99,
|
468 |
+
"eval_accuracy": 0.9900658187453014,
|
469 |
+
"eval_f1": 0.9894462659525121,
|
470 |
+
"eval_loss": 0.05798300728201866,
|
471 |
+
"eval_precision": 0.989465880076756,
|
472 |
+
"eval_recall": 0.9894266526058723,
|
473 |
+
"eval_runtime": 19.4979,
|
474 |
+
"eval_samples_per_second": 751.311,
|
475 |
+
"eval_steps_per_second": 2.975,
|
476 |
+
"step": 4480
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 35.16,
|
480 |
+
"learning_rate": 6.742424242424243e-06,
|
481 |
+
"loss": 0.003,
|
482 |
+
"step": 4500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 35.99,
|
486 |
+
"eval_accuracy": 0.9899776001472868,
|
487 |
+
"eval_f1": 0.9893636842960725,
|
488 |
+
"eval_loss": 0.05809687077999115,
|
489 |
+
"eval_precision": 0.9893205422976294,
|
490 |
+
"eval_recall": 0.9894068300573268,
|
491 |
+
"eval_runtime": 19.0851,
|
492 |
+
"eval_samples_per_second": 767.563,
|
493 |
+
"eval_steps_per_second": 3.039,
|
494 |
+
"step": 4608
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 36.99,
|
498 |
+
"eval_accuracy": 0.989889381549272,
|
499 |
+
"eval_f1": 0.9892901530063094,
|
500 |
+
"eval_loss": 0.058496102690696716,
|
501 |
+
"eval_precision": 0.9892646609924242,
|
502 |
+
"eval_recall": 0.9893156463340179,
|
503 |
+
"eval_runtime": 19.0831,
|
504 |
+
"eval_samples_per_second": 767.642,
|
505 |
+
"eval_steps_per_second": 3.039,
|
506 |
+
"step": 4736
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 37.99,
|
510 |
+
"eval_accuracy": 0.9899699289648506,
|
511 |
+
"eval_f1": 0.9893475735699306,
|
512 |
+
"eval_loss": 0.05856472626328468,
|
513 |
+
"eval_precision": 0.9893279629570898,
|
514 |
+
"eval_recall": 0.989367184960236,
|
515 |
+
"eval_runtime": 19.3383,
|
516 |
+
"eval_samples_per_second": 757.512,
|
517 |
+
"eval_steps_per_second": 2.999,
|
518 |
+
"step": 4864
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 38.99,
|
522 |
+
"eval_accuracy": 0.9899737645560687,
|
523 |
+
"eval_f1": 0.9893515802159814,
|
524 |
+
"eval_loss": 0.05881791561841965,
|
525 |
+
"eval_precision": 0.9893280475718533,
|
526 |
+
"eval_recall": 0.9893751139796542,
|
527 |
+
"eval_runtime": 19.2023,
|
528 |
+
"eval_samples_per_second": 762.879,
|
529 |
+
"eval_steps_per_second": 3.02,
|
530 |
+
"step": 4992
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 39.06,
|
534 |
+
"learning_rate": 1.3311688311688312e-06,
|
535 |
+
"loss": 0.0024,
|
536 |
+
"step": 5000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 39.99,
|
540 |
+
"eval_accuracy": 0.9899891069209408,
|
541 |
+
"eval_f1": 0.9893752824668374,
|
542 |
+
"eval_loss": 0.058905407786369324,
|
543 |
+
"eval_precision": 0.9893595934127796,
|
544 |
+
"eval_recall": 0.9893909720184905,
|
545 |
+
"eval_runtime": 18.6772,
|
546 |
+
"eval_samples_per_second": 784.326,
|
547 |
+
"eval_steps_per_second": 3.105,
|
548 |
+
"step": 5120
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 39.99,
|
552 |
+
"step": 5120,
|
553 |
+
"total_flos": 3.2246769193641984e+17,
|
554 |
+
"train_loss": 0.08320926361484453,
|
555 |
+
"train_runtime": 4249.1875,
|
556 |
+
"train_samples_per_second": 1241.018,
|
557 |
+
"train_steps_per_second": 1.205
|
558 |
+
}
|
559 |
+
],
|
560 |
+
"max_steps": 5120,
|
561 |
+
"num_train_epochs": 40,
|
562 |
+
"total_flos": 3.2246769193641984e+17,
|
563 |
+
"trial_name": null,
|
564 |
+
"trial_params": null
|
565 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf69f2cdb60730064aaa3d1b29fee1e13e162d0afe04f46a7ba422163b930418
|
3 |
+
size 3439
|