Hugging Face's logo

pavlichenko
/
flan-t5-base-comma-correction

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
pavlichenko commited on
Commit
fff8277
·
1 Parent(s): 2bf5d18

Training in progress, step 500

Browse files
Files changed (20) hide show
  1. README.md +68 -0
  2. all_results.json +20 -0
  3. config.json +62 -0
  4. emissions.csv +4 -0
  5. eval_results.json +15 -0
  6. generation_config.json +6 -0
  7. model.safetensors +3 -0
  8. runs/Nov11_23-24-10_d4ab1870bfb3/events.out.tfevents.1699745064.d4ab1870bfb3.7.0 +3 -0
  9. runs/Nov11_23-24-10_d4ab1870bfb3/events.out.tfevents.1699746934.d4ab1870bfb3.7.1 +3 -0
  10. runs/Nov12_02-03-01_1b9b6608cd90/events.out.tfevents.1699754596.1b9b6608cd90.7.0 +3 -0
  11. runs/Nov12_02-03-01_1b9b6608cd90/events.out.tfevents.1699756470.1b9b6608cd90.7.1 +3 -0
  12. runs/Nov12_03-16-29_92dce217e2b6/events.out.tfevents.1699759004.92dce217e2b6.8.0 +3 -0
  13. runs/Nov12_03-47-40_4c37345259d2/events.out.tfevents.1699760878.4c37345259d2.9.0 +3 -0
  14. special_tokens_map.json +107 -0
  15. spiece.model +3 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +938 -0
  18. train_results.json +8 -0
  19. trainer_state.json +3955 -0
  20. training_args.bin +3 -0
README.md CHANGED
@@ -1,3 +1,71 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/flan-t5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ model-index:
11
+ - name: flan-t5-base-comma-correction
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
+ # flan-t5-base-comma-correction
19
+
20
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0492
23
+ - Gen Len: 39.5298
24
+ - Em Ic: 0.9334
25
+ - Em: 0.6384
26
+ - Precision: 0.9141
27
+ - Recall: 0.8575
28
+ - F1: 0.8248
29
+ - Levinstein Ratio: 0.9955
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 2e-05
49
+ - train_batch_size: 64
50
+ - eval_batch_size: 64
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: cosine
54
+ - lr_scheduler_warmup_steps: 200
55
+ - num_epochs: 3.0
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Gen Len | Em Ic | Em | Precision | Recall | F1 | Levinstein Ratio |
60
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:------:|:------:|:----------------:|
61
+ | 0.042 | 1.0 | 2159 | 0.0500 | 39.4971 | 0.9328 | 0.6256 | 0.9175 | 0.8452 | 0.8165 | 0.9954 |
62
+ | 0.0342 | 2.0 | 4318 | 0.0492 | 39.5158 | 0.9334 | 0.6361 | 0.9159 | 0.8546 | 0.8229 | 0.9955 |
63
+ | 0.0346 | 3.0 | 6477 | 0.0492 | 39.5298 | 0.9334 | 0.6384 | 0.9141 | 0.8575 | 0.8248 | 0.9955 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.35.0
69
+ - Pytorch 2.1.0+cu118
70
+ - Datasets 2.14.6
71
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_em": 0.6384,
4
+ "eval_em_ic": 0.9334,
5
+ "eval_f1": 0.8248,
6
+ "eval_gen_len": 39.5298,
7
+ "eval_levinstein_ratio": 0.9955,
8
+ "eval_loss": 0.04924384132027626,
9
+ "eval_precision": 0.9141,
10
+ "eval_recall": 0.8575,
11
+ "eval_runtime": 166.7446,
12
+ "eval_samples": 1712,
13
+ "eval_samples_per_second": 10.267,
14
+ "eval_steps_per_second": 0.162,
15
+ "train_loss": 0.04666397547913275,
16
+ "train_runtime": 1704.3592,
17
+ "train_samples": 138142,
18
+ "train_samples_per_second": 243.156,
19
+ "train_steps_per_second": 3.8
20
+ }
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.35.0",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
emissions.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
2
+ 2023-11-11T23:52:47,66d0e133-76c1-4ec5-8629-8771379933d8,codecarbon,1702.4160313606262,0.0475393601463552,0.12925329022935073,USA,USA,Virginia,Y,azure,eastus
3
+ 2023-11-12T02:31:40,952a0139-b3b1-4bf6-a253-c07ec4fc724e,codecarbon,1704.3497834205627,0.047007517862861795,0.12780728075818867,USA,USA,Virginia,Y,azure,eastus
4
+ 2023-11-12T03:46:01,121545f5-d3d6-4150-980a-91245b875481,codecarbon,1756.9844217300415,0.04688993191807487,0.12748757998389035,USA,USA,Virginia,Y,azure,eastus
eval_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_em": 0.6384,
4
+ "eval_em_ic": 0.9334,
5
+ "eval_f1": 0.8248,
6
+ "eval_gen_len": 39.5298,
7
+ "eval_levinstein_ratio": 0.9955,
8
+ "eval_loss": 0.04924384132027626,
9
+ "eval_precision": 0.9141,
10
+ "eval_recall": 0.8575,
11
+ "eval_runtime": 166.7446,
12
+ "eval_samples": 1712,
13
+ "eval_samples_per_second": 10.267,
14
+ "eval_steps_per_second": 0.162
15
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.35.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e03dc0a02c235c5084c2c39c86f0b8aa050ea29f6d862d9925279a2c0493ce48
3
+ size 990345064
runs/Nov11_23-24-10_d4ab1870bfb3/events.out.tfevents.1699745064.d4ab1870bfb3.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf69f52dc4021b985dd164ee11e2c610c6741e9618bc3a9e7dacb1818ff32c1b
3
+ size 109036
runs/Nov11_23-24-10_d4ab1870bfb3/events.out.tfevents.1699746934.d4ab1870bfb3.7.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8e9388cb669a447d9f3fe0a0335e3d1a1a7018855f13b287da3414ca54b7d8
3
+ size 714
runs/Nov12_02-03-01_1b9b6608cd90/events.out.tfevents.1699754596.1b9b6608cd90.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361bacf66bd965b37ec60f8996991184cbd1ad7f2b5e8d74d0caf1f3ca5155b4
3
+ size 109036
runs/Nov12_02-03-01_1b9b6608cd90/events.out.tfevents.1699756470.1b9b6608cd90.7.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e7649801a41246ce307f3f6b1ac5c4db45c6e183cb5381cea657833b34b72f
3
+ size 714
runs/Nov12_03-16-29_92dce217e2b6/events.out.tfevents.1699759004.92dce217e2b6.8.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee686b7b9c703bfa53d677fe93438bea7e83c4c7c1c53ad3382e0d273d86a73
3
+ size 109074
runs/Nov12_03-47-40_4c37345259d2/events.out.tfevents.1699760878.4c37345259d2.9.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9095ee517a101d5369540d4d632d87b3c62b2ec08289ed6ebf680140090d6dbe
3
+ size 13113
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<extra_id_99>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<extra_id_98>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<extra_id_97>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<extra_id_96>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<extra_id_95>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<extra_id_94>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<extra_id_93>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<extra_id_92>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<extra_id_91>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<extra_id_90>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<extra_id_89>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<extra_id_88>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<extra_id_87>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<extra_id_86>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<extra_id_85>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<extra_id_84>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<extra_id_83>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<extra_id_82>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<extra_id_81>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<extra_id_80>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<extra_id_79>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<extra_id_78>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32022": {
204
+ "content": "<extra_id_77>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32023": {
212
+ "content": "<extra_id_76>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32024": {
220
+ "content": "<extra_id_75>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32025": {
228
+ "content": "<extra_id_74>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32026": {
236
+ "content": "<extra_id_73>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32027": {
244
+ "content": "<extra_id_72>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32028": {
252
+ "content": "<extra_id_71>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32029": {
260
+ "content": "<extra_id_70>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32030": {
268
+ "content": "<extra_id_69>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32031": {
276
+ "content": "<extra_id_68>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32032": {
284
+ "content": "<extra_id_67>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32033": {
292
+ "content": "<extra_id_66>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32034": {
300
+ "content": "<extra_id_65>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32035": {
308
+ "content": "<extra_id_64>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32036": {
316
+ "content": "<extra_id_63>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32037": {
324
+ "content": "<extra_id_62>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32038": {
332
+ "content": "<extra_id_61>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32039": {
340
+ "content": "<extra_id_60>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32040": {
348
+ "content": "<extra_id_59>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32041": {
356
+ "content": "<extra_id_58>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32042": {
364
+ "content": "<extra_id_57>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32043": {
372
+ "content": "<extra_id_56>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32044": {
380
+ "content": "<extra_id_55>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32045": {
388
+ "content": "<extra_id_54>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32046": {
396
+ "content": "<extra_id_53>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32047": {
404
+ "content": "<extra_id_52>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32048": {
412
+ "content": "<extra_id_51>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32049": {
420
+ "content": "<extra_id_50>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32050": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32051": {
436
+ "content": "<extra_id_48>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32052": {
444
+ "content": "<extra_id_47>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32053": {
452
+ "content": "<extra_id_46>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32054": {
460
+ "content": "<extra_id_45>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32055": {
468
+ "content": "<extra_id_44>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32056": {
476
+ "content": "<extra_id_43>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32057": {
484
+ "content": "<extra_id_42>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32058": {
492
+ "content": "<extra_id_41>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32059": {
500
+ "content": "<extra_id_40>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32060": {
508
+ "content": "<extra_id_39>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32061": {
516
+ "content": "<extra_id_38>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32062": {
524
+ "content": "<extra_id_37>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32063": {
532
+ "content": "<extra_id_36>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32064": {
540
+ "content": "<extra_id_35>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32065": {
548
+ "content": "<extra_id_34>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32066": {
556
+ "content": "<extra_id_33>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32067": {
564
+ "content": "<extra_id_32>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32068": {
572
+ "content": "<extra_id_31>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32069": {
580
+ "content": "<extra_id_30>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32070": {
588
+ "content": "<extra_id_29>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32071": {
596
+ "content": "<extra_id_28>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32072": {
604
+ "content": "<extra_id_27>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32073": {
612
+ "content": "<extra_id_26>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32074": {
620
+ "content": "<extra_id_25>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32075": {
628
+ "content": "<extra_id_24>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32076": {
636
+ "content": "<extra_id_23>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32077": {
644
+ "content": "<extra_id_22>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32078": {
652
+ "content": "<extra_id_21>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32079": {
660
+ "content": "<extra_id_20>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32080": {
668
+ "content": "<extra_id_19>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32081": {
676
+ "content": "<extra_id_18>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32082": {
684
+ "content": "<extra_id_17>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32083": {
692
+ "content": "<extra_id_16>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32084": {
700
+ "content": "<extra_id_15>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32085": {
708
+ "content": "<extra_id_14>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32086": {
716
+ "content": "<extra_id_13>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32087": {
724
+ "content": "<extra_id_12>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32088": {
732
+ "content": "<extra_id_11>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32089": {
740
+ "content": "<extra_id_10>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32090": {
748
+ "content": "<extra_id_9>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32091": {
756
+ "content": "<extra_id_8>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32092": {
764
+ "content": "<extra_id_7>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32093": {
772
+ "content": "<extra_id_6>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32094": {
780
+ "content": "<extra_id_5>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32095": {
788
+ "content": "<extra_id_4>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32096": {
796
+ "content": "<extra_id_3>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32097": {
804
+ "content": "<extra_id_2>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32098": {
812
+ "content": "<extra_id_1>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32099": {
820
+ "content": "<extra_id_0>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
+ "additional_special_tokens": [
829
+ "<extra_id_0>",
830
+ "<extra_id_1>",
831
+ "<extra_id_2>",
832
+ "<extra_id_3>",
833
+ "<extra_id_4>",
834
+ "<extra_id_5>",
835
+ "<extra_id_6>",
836
+ "<extra_id_7>",
837
+ "<extra_id_8>",
838
+ "<extra_id_9>",
839
+ "<extra_id_10>",
840
+ "<extra_id_11>",
841
+ "<extra_id_12>",
842
+ "<extra_id_13>",
843
+ "<extra_id_14>",
844
+ "<extra_id_15>",
845
+ "<extra_id_16>",
846
+ "<extra_id_17>",
847
+ "<extra_id_18>",
848
+ "<extra_id_19>",
849
+ "<extra_id_20>",
850
+ "<extra_id_21>",
851
+ "<extra_id_22>",
852
+ "<extra_id_23>",
853
+ "<extra_id_24>",
854
+ "<extra_id_25>",
855
+ "<extra_id_26>",
856
+ "<extra_id_27>",
857
+ "<extra_id_28>",
858
+ "<extra_id_29>",
859
+ "<extra_id_30>",
860
+ "<extra_id_31>",
861
+ "<extra_id_32>",
862
+ "<extra_id_33>",
863
+ "<extra_id_34>",
864
+ "<extra_id_35>",
865
+ "<extra_id_36>",
866
+ "<extra_id_37>",
867
+ "<extra_id_38>",
868
+ "<extra_id_39>",
869
+ "<extra_id_40>",
870
+ "<extra_id_41>",
871
+ "<extra_id_42>",
872
+ "<extra_id_43>",
873
+ "<extra_id_44>",
874
+ "<extra_id_45>",
875
+ "<extra_id_46>",
876
+ "<extra_id_47>",
877
+ "<extra_id_48>",
878
+ "<extra_id_49>",
879
+ "<extra_id_50>",
880
+ "<extra_id_51>",
881
+ "<extra_id_52>",
882
+ "<extra_id_53>",
883
+ "<extra_id_54>",
884
+ "<extra_id_55>",
885
+ "<extra_id_56>",
886
+ "<extra_id_57>",
887
+ "<extra_id_58>",
888
+ "<extra_id_59>",
889
+ "<extra_id_60>",
890
+ "<extra_id_61>",
891
+ "<extra_id_62>",
892
+ "<extra_id_63>",
893
+ "<extra_id_64>",
894
+ "<extra_id_65>",
895
+ "<extra_id_66>",
896
+ "<extra_id_67>",
897
+ "<extra_id_68>",
898
+ "<extra_id_69>",
899
+ "<extra_id_70>",
900
+ "<extra_id_71>",
901
+ "<extra_id_72>",
902
+ "<extra_id_73>",
903
+ "<extra_id_74>",
904
+ "<extra_id_75>",
905
+ "<extra_id_76>",
906
+ "<extra_id_77>",
907
+ "<extra_id_78>",
908
+ "<extra_id_79>",
909
+ "<extra_id_80>",
910
+ "<extra_id_81>",
911
+ "<extra_id_82>",
912
+ "<extra_id_83>",
913
+ "<extra_id_84>",
914
+ "<extra_id_85>",
915
+ "<extra_id_86>",
916
+ "<extra_id_87>",
917
+ "<extra_id_88>",
918
+ "<extra_id_89>",
919
+ "<extra_id_90>",
920
+ "<extra_id_91>",
921
+ "<extra_id_92>",
922
+ "<extra_id_93>",
923
+ "<extra_id_94>",
924
+ "<extra_id_95>",
925
+ "<extra_id_96>",
926
+ "<extra_id_97>",
927
+ "<extra_id_98>",
928
+ "<extra_id_99>"
929
+ ],
930
+ "clean_up_tokenization_spaces": true,
931
+ "eos_token": "</s>",
932
+ "extra_ids": 100,
933
+ "model_max_length": 512,
934
+ "pad_token": "<pad>",
935
+ "sp_model_kwargs": {},
936
+ "tokenizer_class": "T5Tokenizer",
937
+ "unk_token": "<unk>"
938
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.04666397547913275,
4
+ "train_runtime": 1704.3592,
5
+ "train_samples": 138142,
6
+ "train_samples_per_second": 243.156,
7
+ "train_steps_per_second": 3.8
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,3955 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6477,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.0000000000000002e-06,
14
+ "loss": 0.5967,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.0000000000000003e-06,
20
+ "loss": 0.5579,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 3e-06,
26
+ "loss": 0.5271,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4.000000000000001e-06,
32
+ "loss": 0.4947,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 5e-06,
38
+ "loss": 0.4531,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 6e-06,
44
+ "loss": 0.4091,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 7e-06,
50
+ "loss": 0.3732,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 8.000000000000001e-06,
56
+ "loss": 0.3181,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 9e-06,
62
+ "loss": 0.2763,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.05,
67
+ "learning_rate": 1e-05,
68
+ "loss": 0.2419,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 1.1000000000000001e-05,
74
+ "loss": 0.2118,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.06,
79
+ "learning_rate": 1.2e-05,
80
+ "loss": 0.1898,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 1.3000000000000001e-05,
86
+ "loss": 0.1659,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 1.4e-05,
92
+ "loss": 0.1456,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "learning_rate": 1.5000000000000002e-05,
98
+ "loss": 0.1309,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.07,
103
+ "learning_rate": 1.6000000000000003e-05,
104
+ "loss": 0.1123,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.08,
109
+ "learning_rate": 1.7e-05,
110
+ "loss": 0.1133,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.08,
115
+ "learning_rate": 1.8e-05,
116
+ "loss": 0.1069,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.09,
121
+ "learning_rate": 1.9e-05,
122
+ "loss": 0.0919,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.09,
127
+ "learning_rate": 2e-05,
128
+ "loss": 0.0874,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "learning_rate": 1.9999874753792008e-05,
134
+ "loss": 0.0889,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.1,
139
+ "learning_rate": 1.999949901830535e-05,
140
+ "loss": 0.0802,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.11,
145
+ "learning_rate": 1.9998872802951915e-05,
146
+ "loss": 0.0804,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.11,
151
+ "learning_rate": 1.999799612341792e-05,
152
+ "loss": 0.0744,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.12,
157
+ "learning_rate": 1.999686900166353e-05,
158
+ "loss": 0.0751,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.12,
163
+ "learning_rate": 1.9995491465922284e-05,
164
+ "loss": 0.0746,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.13,
169
+ "learning_rate": 1.9993863550700413e-05,
170
+ "loss": 0.0721,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.13,
175
+ "learning_rate": 1.999198529677595e-05,
176
+ "loss": 0.0714,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.13,
181
+ "learning_rate": 1.9989856751197742e-05,
182
+ "loss": 0.0658,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.14,
187
+ "learning_rate": 1.998747796728423e-05,
188
+ "loss": 0.069,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.14,
193
+ "learning_rate": 1.998484900462216e-05,
194
+ "loss": 0.0647,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.15,
199
+ "learning_rate": 1.9981969929065044e-05,
200
+ "loss": 0.0712,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.15,
205
+ "learning_rate": 1.997884081273154e-05,
206
+ "loss": 0.0592,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.16,
211
+ "learning_rate": 1.9975461734003646e-05,
212
+ "loss": 0.0723,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.16,
217
+ "learning_rate": 1.9971832777524717e-05,
218
+ "loss": 0.0636,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.17,
223
+ "learning_rate": 1.996795403419736e-05,
224
+ "loss": 0.062,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.17,
229
+ "learning_rate": 1.9963825601181152e-05,
230
+ "loss": 0.0629,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.18,
235
+ "learning_rate": 1.9959447581890218e-05,
236
+ "loss": 0.0577,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.18,
241
+ "learning_rate": 1.995482008599061e-05,
242
+ "loss": 0.0611,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.19,
247
+ "learning_rate": 1.9949943229397597e-05,
248
+ "loss": 0.0657,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.19,
253
+ "learning_rate": 1.994481713427274e-05,
254
+ "loss": 0.0542,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.19,
259
+ "learning_rate": 1.9939441929020823e-05,
260
+ "loss": 0.0522,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.2,
265
+ "learning_rate": 1.993381774828668e-05,
266
+ "loss": 0.0562,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.2,
271
+ "learning_rate": 1.992794473295175e-05,
272
+ "loss": 0.0608,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.21,
277
+ "learning_rate": 1.9921823030130635e-05,
278
+ "loss": 0.0653,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.21,
283
+ "learning_rate": 1.9915452793167335e-05,
284
+ "loss": 0.0623,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.22,
289
+ "learning_rate": 1.9908834181631455e-05,
290
+ "loss": 0.0593,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.22,
295
+ "learning_rate": 1.99019673613142e-05,
296
+ "loss": 0.0534,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.23,
301
+ "learning_rate": 1.9894852504224206e-05,
302
+ "loss": 0.0536,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.23,
307
+ "learning_rate": 1.988748978858325e-05,
308
+ "loss": 0.058,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.24,
313
+ "learning_rate": 1.9879879398821775e-05,
314
+ "loss": 0.0573,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 0.24,
319
+ "learning_rate": 1.9872021525574274e-05,
320
+ "loss": 0.0589,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 0.25,
325
+ "learning_rate": 1.9863916365674506e-05,
326
+ "loss": 0.0589,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 0.25,
331
+ "learning_rate": 1.985556412215059e-05,
332
+ "loss": 0.0604,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 0.25,
337
+ "learning_rate": 1.9846965004219883e-05,
338
+ "loss": 0.0512,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 0.26,
343
+ "learning_rate": 1.983811922728377e-05,
344
+ "loss": 0.0571,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 0.26,
349
+ "learning_rate": 1.9829027012922257e-05,
350
+ "loss": 0.0599,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 0.27,
355
+ "learning_rate": 1.981968858888841e-05,
356
+ "loss": 0.0493,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 0.27,
361
+ "learning_rate": 1.9810104189102683e-05,
362
+ "loss": 0.0483,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 0.28,
367
+ "learning_rate": 1.9800274053647014e-05,
368
+ "loss": 0.0478,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 0.28,
373
+ "learning_rate": 1.979019842875884e-05,
374
+ "loss": 0.0542,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 0.29,
379
+ "learning_rate": 1.977987756682492e-05,
380
+ "loss": 0.0494,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 0.29,
385
+ "learning_rate": 1.9769311726375026e-05,
386
+ "loss": 0.0503,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 0.3,
391
+ "learning_rate": 1.975850117207544e-05,
392
+ "loss": 0.0549,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 0.3,
397
+ "learning_rate": 1.9747446174722357e-05,
398
+ "loss": 0.0442,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 0.31,
403
+ "learning_rate": 1.9736147011235073e-05,
404
+ "loss": 0.0498,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 0.31,
409
+ "learning_rate": 1.972460396464906e-05,
410
+ "loss": 0.0528,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 0.31,
415
+ "learning_rate": 1.9712817324108885e-05,
416
+ "loss": 0.0552,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 0.32,
421
+ "learning_rate": 1.9700787384860957e-05,
422
+ "loss": 0.0508,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 0.32,
427
+ "learning_rate": 1.9688514448246124e-05,
428
+ "loss": 0.0555,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 0.33,
433
+ "learning_rate": 1.9675998821692145e-05,
434
+ "loss": 0.0523,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 0.33,
439
+ "learning_rate": 1.9663240818705968e-05,
440
+ "loss": 0.0513,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 0.34,
445
+ "learning_rate": 1.96502407588659e-05,
446
+ "loss": 0.0502,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 0.34,
451
+ "learning_rate": 1.9636998967813577e-05,
452
+ "loss": 0.0509,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 0.35,
457
+ "learning_rate": 1.9623515777245822e-05,
458
+ "loss": 0.0526,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 0.35,
463
+ "learning_rate": 1.9609791524906333e-05,
464
+ "loss": 0.0513,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 0.36,
469
+ "learning_rate": 1.959582655457722e-05,
470
+ "loss": 0.0508,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 0.36,
475
+ "learning_rate": 1.9581621216070403e-05,
476
+ "loss": 0.0429,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 0.37,
481
+ "learning_rate": 1.956717586521884e-05,
482
+ "loss": 0.0491,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 0.37,
487
+ "learning_rate": 1.9552490863867607e-05,
488
+ "loss": 0.05,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 0.38,
493
+ "learning_rate": 1.953756657986486e-05,
494
+ "loss": 0.0463,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 0.38,
499
+ "learning_rate": 1.9522403387052586e-05,
500
+ "loss": 0.0529,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 0.38,
505
+ "learning_rate": 1.9507001665257265e-05,
506
+ "loss": 0.048,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 0.39,
511
+ "learning_rate": 1.9491361800280355e-05,
512
+ "loss": 0.0508,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 0.39,
517
+ "learning_rate": 1.947548418388861e-05,
518
+ "loss": 0.0476,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 0.4,
523
+ "learning_rate": 1.9459369213804276e-05,
524
+ "loss": 0.0393,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 0.4,
529
+ "learning_rate": 1.9443017293695132e-05,
530
+ "loss": 0.0549,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 0.41,
535
+ "learning_rate": 1.9426428833164376e-05,
536
+ "loss": 0.0515,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 0.41,
541
+ "learning_rate": 1.9409604247740368e-05,
542
+ "loss": 0.0488,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 0.42,
547
+ "learning_rate": 1.9392543958866208e-05,
548
+ "loss": 0.0522,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 0.42,
553
+ "learning_rate": 1.9375248393889198e-05,
554
+ "loss": 0.0445,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 0.43,
559
+ "learning_rate": 1.9357717986050115e-05,
560
+ "loss": 0.0499,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 0.43,
565
+ "learning_rate": 1.9339953174472388e-05,
566
+ "loss": 0.0467,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 0.44,
571
+ "learning_rate": 1.9321954404151074e-05,
572
+ "loss": 0.0409,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 0.44,
577
+ "learning_rate": 1.930372212594172e-05,
578
+ "loss": 0.0465,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 0.44,
583
+ "learning_rate": 1.928525679654906e-05,
584
+ "loss": 0.0477,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 0.45,
589
+ "learning_rate": 1.92665588785156e-05,
590
+ "loss": 0.0503,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 0.45,
595
+ "learning_rate": 1.9247628840210004e-05,
596
+ "loss": 0.0445,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 0.46,
601
+ "learning_rate": 1.922846715581537e-05,
602
+ "loss": 0.0511,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 0.46,
607
+ "learning_rate": 1.9209074305317367e-05,
608
+ "loss": 0.0438,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 0.47,
613
+ "learning_rate": 1.9189450774492188e-05,
614
+ "loss": 0.0407,
615
+ "step": 1010
616
+ },
617
+ {
618
+ "epoch": 0.47,
619
+ "learning_rate": 1.9169597054894398e-05,
620
+ "loss": 0.0428,
621
+ "step": 1020
622
+ },
623
+ {
624
+ "epoch": 0.48,
625
+ "learning_rate": 1.9149513643844616e-05,
626
+ "loss": 0.0471,
627
+ "step": 1030
628
+ },
629
+ {
630
+ "epoch": 0.48,
631
+ "learning_rate": 1.912920104441706e-05,
632
+ "loss": 0.0432,
633
+ "step": 1040
634
+ },
635
+ {
636
+ "epoch": 0.49,
637
+ "learning_rate": 1.9108659765426937e-05,
638
+ "loss": 0.0441,
639
+ "step": 1050
640
+ },
641
+ {
642
+ "epoch": 0.49,
643
+ "learning_rate": 1.9087890321417707e-05,
644
+ "loss": 0.0506,
645
+ "step": 1060
646
+ },
647
+ {
648
+ "epoch": 0.5,
649
+ "learning_rate": 1.9066893232648197e-05,
650
+ "loss": 0.0439,
651
+ "step": 1070
652
+ },
653
+ {
654
+ "epoch": 0.5,
655
+ "learning_rate": 1.904566902507955e-05,
656
+ "loss": 0.0423,
657
+ "step": 1080
658
+ },
659
+ {
660
+ "epoch": 0.5,
661
+ "learning_rate": 1.902421823036207e-05,
662
+ "loss": 0.047,
663
+ "step": 1090
664
+ },
665
+ {
666
+ "epoch": 0.51,
667
+ "learning_rate": 1.90025413858219e-05,
668
+ "loss": 0.0442,
669
+ "step": 1100
670
+ },
671
+ {
672
+ "epoch": 0.51,
673
+ "learning_rate": 1.8980639034447552e-05,
674
+ "loss": 0.0447,
675
+ "step": 1110
676
+ },
677
+ {
678
+ "epoch": 0.52,
679
+ "learning_rate": 1.895851172487632e-05,
680
+ "loss": 0.0464,
681
+ "step": 1120
682
+ },
683
+ {
684
+ "epoch": 0.52,
685
+ "learning_rate": 1.8936160011380525e-05,
686
+ "loss": 0.0458,
687
+ "step": 1130
688
+ },
689
+ {
690
+ "epoch": 0.53,
691
+ "learning_rate": 1.891358445385364e-05,
692
+ "loss": 0.0457,
693
+ "step": 1140
694
+ },
695
+ {
696
+ "epoch": 0.53,
697
+ "learning_rate": 1.889078561779626e-05,
698
+ "loss": 0.0478,
699
+ "step": 1150
700
+ },
701
+ {
702
+ "epoch": 0.54,
703
+ "learning_rate": 1.8867764074301934e-05,
704
+ "loss": 0.0499,
705
+ "step": 1160
706
+ },
707
+ {
708
+ "epoch": 0.54,
709
+ "learning_rate": 1.8844520400042873e-05,
710
+ "loss": 0.0517,
711
+ "step": 1170
712
+ },
713
+ {
714
+ "epoch": 0.55,
715
+ "learning_rate": 1.8821055177255483e-05,
716
+ "loss": 0.0434,
717
+ "step": 1180
718
+ },
719
+ {
720
+ "epoch": 0.55,
721
+ "learning_rate": 1.879736899372581e-05,
722
+ "loss": 0.0391,
723
+ "step": 1190
724
+ },
725
+ {
726
+ "epoch": 0.56,
727
+ "learning_rate": 1.8773462442774772e-05,
728
+ "loss": 0.0412,
729
+ "step": 1200
730
+ },
731
+ {
732
+ "epoch": 0.56,
733
+ "learning_rate": 1.874933612324335e-05,
734
+ "loss": 0.0487,
735
+ "step": 1210
736
+ },
737
+ {
738
+ "epoch": 0.57,
739
+ "learning_rate": 1.8724990639477546e-05,
740
+ "loss": 0.0429,
741
+ "step": 1220
742
+ },
743
+ {
744
+ "epoch": 0.57,
745
+ "learning_rate": 1.8700426601313266e-05,
746
+ "loss": 0.0427,
747
+ "step": 1230
748
+ },
749
+ {
750
+ "epoch": 0.57,
751
+ "learning_rate": 1.867564462406104e-05,
752
+ "loss": 0.0468,
753
+ "step": 1240
754
+ },
755
+ {
756
+ "epoch": 0.58,
757
+ "learning_rate": 1.86506453284906e-05,
758
+ "loss": 0.0417,
759
+ "step": 1250
760
+ },
761
+ {
762
+ "epoch": 0.58,
763
+ "learning_rate": 1.862542934081534e-05,
764
+ "loss": 0.0399,
765
+ "step": 1260
766
+ },
767
+ {
768
+ "epoch": 0.59,
769
+ "learning_rate": 1.859999729267663e-05,
770
+ "loss": 0.046,
771
+ "step": 1270
772
+ },
773
+ {
774
+ "epoch": 0.59,
775
+ "learning_rate": 1.8574349821127986e-05,
776
+ "loss": 0.0409,
777
+ "step": 1280
778
+ },
779
+ {
780
+ "epoch": 0.6,
781
+ "learning_rate": 1.854848756861912e-05,
782
+ "loss": 0.048,
783
+ "step": 1290
784
+ },
785
+ {
786
+ "epoch": 0.6,
787
+ "learning_rate": 1.8522411182979846e-05,
788
+ "loss": 0.0411,
789
+ "step": 1300
790
+ },
791
+ {
792
+ "epoch": 0.61,
793
+ "learning_rate": 1.8496121317403843e-05,
794
+ "loss": 0.04,
795
+ "step": 1310
796
+ },
797
+ {
798
+ "epoch": 0.61,
799
+ "learning_rate": 1.8469618630432307e-05,
800
+ "loss": 0.0455,
801
+ "step": 1320
802
+ },
803
+ {
804
+ "epoch": 0.62,
805
+ "learning_rate": 1.844290378593745e-05,
806
+ "loss": 0.0452,
807
+ "step": 1330
808
+ },
809
+ {
810
+ "epoch": 0.62,
811
+ "learning_rate": 1.8415977453105864e-05,
812
+ "loss": 0.0378,
813
+ "step": 1340
814
+ },
815
+ {
816
+ "epoch": 0.63,
817
+ "learning_rate": 1.8388840306421763e-05,
818
+ "loss": 0.0396,
819
+ "step": 1350
820
+ },
821
+ {
822
+ "epoch": 0.63,
823
+ "learning_rate": 1.8361493025650097e-05,
824
+ "loss": 0.0434,
825
+ "step": 1360
826
+ },
827
+ {
828
+ "epoch": 0.63,
829
+ "learning_rate": 1.8333936295819504e-05,
830
+ "loss": 0.0402,
831
+ "step": 1370
832
+ },
833
+ {
834
+ "epoch": 0.64,
835
+ "learning_rate": 1.8306170807205162e-05,
836
+ "loss": 0.0402,
837
+ "step": 1380
838
+ },
839
+ {
840
+ "epoch": 0.64,
841
+ "learning_rate": 1.8278197255311515e-05,
842
+ "loss": 0.0377,
843
+ "step": 1390
844
+ },
845
+ {
846
+ "epoch": 0.65,
847
+ "learning_rate": 1.825001634085482e-05,
848
+ "loss": 0.0389,
849
+ "step": 1400
850
+ },
851
+ {
852
+ "epoch": 0.65,
853
+ "learning_rate": 1.8221628769745604e-05,
854
+ "loss": 0.0442,
855
+ "step": 1410
856
+ },
857
+ {
858
+ "epoch": 0.66,
859
+ "learning_rate": 1.8193035253071004e-05,
860
+ "loss": 0.0428,
861
+ "step": 1420
862
+ },
863
+ {
864
+ "epoch": 0.66,
865
+ "learning_rate": 1.8164236507076917e-05,
866
+ "loss": 0.0398,
867
+ "step": 1430
868
+ },
869
+ {
870
+ "epoch": 0.67,
871
+ "learning_rate": 1.8135233253150097e-05,
872
+ "loss": 0.0383,
873
+ "step": 1440
874
+ },
875
+ {
876
+ "epoch": 0.67,
877
+ "learning_rate": 1.810602621780006e-05,
878
+ "loss": 0.0405,
879
+ "step": 1450
880
+ },
881
+ {
882
+ "epoch": 0.68,
883
+ "learning_rate": 1.807661613264088e-05,
884
+ "loss": 0.0379,
885
+ "step": 1460
886
+ },
887
+ {
888
+ "epoch": 0.68,
889
+ "learning_rate": 1.80470037343729e-05,
890
+ "loss": 0.0473,
891
+ "step": 1470
892
+ },
893
+ {
894
+ "epoch": 0.69,
895
+ "learning_rate": 1.8017189764764226e-05,
896
+ "loss": 0.0398,
897
+ "step": 1480
898
+ },
899
+ {
900
+ "epoch": 0.69,
901
+ "learning_rate": 1.7987174970632197e-05,
902
+ "loss": 0.0406,
903
+ "step": 1490
904
+ },
905
+ {
906
+ "epoch": 0.69,
907
+ "learning_rate": 1.795696010382463e-05,
908
+ "loss": 0.0406,
909
+ "step": 1500
910
+ },
911
+ {
912
+ "epoch": 0.7,
913
+ "learning_rate": 1.7926545921201038e-05,
914
+ "loss": 0.0444,
915
+ "step": 1510
916
+ },
917
+ {
918
+ "epoch": 0.7,
919
+ "learning_rate": 1.789593318461362e-05,
920
+ "loss": 0.0461,
921
+ "step": 1520
922
+ },
923
+ {
924
+ "epoch": 0.71,
925
+ "learning_rate": 1.7865122660888207e-05,
926
+ "loss": 0.0471,
927
+ "step": 1530
928
+ },
929
+ {
930
+ "epoch": 0.71,
931
+ "learning_rate": 1.7834115121805063e-05,
932
+ "loss": 0.0424,
933
+ "step": 1540
934
+ },
935
+ {
936
+ "epoch": 0.72,
937
+ "learning_rate": 1.780291134407952e-05,
938
+ "loss": 0.0488,
939
+ "step": 1550
940
+ },
941
+ {
942
+ "epoch": 0.72,
943
+ "learning_rate": 1.7771512109342545e-05,
944
+ "loss": 0.0412,
945
+ "step": 1560
946
+ },
947
+ {
948
+ "epoch": 0.73,
949
+ "learning_rate": 1.7739918204121153e-05,
950
+ "loss": 0.0409,
951
+ "step": 1570
952
+ },
953
+ {
954
+ "epoch": 0.73,
955
+ "learning_rate": 1.7708130419818713e-05,
956
+ "loss": 0.0421,
957
+ "step": 1580
958
+ },
959
+ {
960
+ "epoch": 0.74,
961
+ "learning_rate": 1.767614955269511e-05,
962
+ "loss": 0.039,
963
+ "step": 1590
964
+ },
965
+ {
966
+ "epoch": 0.74,
967
+ "learning_rate": 1.7643976403846817e-05,
968
+ "loss": 0.0422,
969
+ "step": 1600
970
+ },
971
+ {
972
+ "epoch": 0.75,
973
+ "learning_rate": 1.7611611779186804e-05,
974
+ "loss": 0.0393,
975
+ "step": 1610
976
+ },
977
+ {
978
+ "epoch": 0.75,
979
+ "learning_rate": 1.757905648942438e-05,
980
+ "loss": 0.0426,
981
+ "step": 1620
982
+ },
983
+ {
984
+ "epoch": 0.75,
985
+ "learning_rate": 1.7546311350044865e-05,
986
+ "loss": 0.0417,
987
+ "step": 1630
988
+ },
989
+ {
990
+ "epoch": 0.76,
991
+ "learning_rate": 1.751337718128916e-05,
992
+ "loss": 0.0433,
993
+ "step": 1640
994
+ },
995
+ {
996
+ "epoch": 0.76,
997
+ "learning_rate": 1.748025480813322e-05,
998
+ "loss": 0.0412,
999
+ "step": 1650
1000
+ },
1001
+ {
1002
+ "epoch": 0.77,
1003
+ "learning_rate": 1.7446945060267367e-05,
1004
+ "loss": 0.0446,
1005
+ "step": 1660
1006
+ },
1007
+ {
1008
+ "epoch": 0.77,
1009
+ "learning_rate": 1.7413448772075532e-05,
1010
+ "loss": 0.0423,
1011
+ "step": 1670
1012
+ },
1013
+ {
1014
+ "epoch": 0.78,
1015
+ "learning_rate": 1.7379766782614323e-05,
1016
+ "loss": 0.0396,
1017
+ "step": 1680
1018
+ },
1019
+ {
1020
+ "epoch": 0.78,
1021
+ "learning_rate": 1.734589993559203e-05,
1022
+ "loss": 0.0391,
1023
+ "step": 1690
1024
+ },
1025
+ {
1026
+ "epoch": 0.79,
1027
+ "learning_rate": 1.7311849079347495e-05,
1028
+ "loss": 0.0376,
1029
+ "step": 1700
1030
+ },
1031
+ {
1032
+ "epoch": 0.79,
1033
+ "learning_rate": 1.7277615066828836e-05,
1034
+ "loss": 0.0405,
1035
+ "step": 1710
1036
+ },
1037
+ {
1038
+ "epoch": 0.8,
1039
+ "learning_rate": 1.7243198755572104e-05,
1040
+ "loss": 0.0424,
1041
+ "step": 1720
1042
+ },
1043
+ {
1044
+ "epoch": 0.8,
1045
+ "learning_rate": 1.7208601007679796e-05,
1046
+ "loss": 0.0406,
1047
+ "step": 1730
1048
+ },
1049
+ {
1050
+ "epoch": 0.81,
1051
+ "learning_rate": 1.7173822689799256e-05,
1052
+ "loss": 0.0382,
1053
+ "step": 1740
1054
+ },
1055
+ {
1056
+ "epoch": 0.81,
1057
+ "learning_rate": 1.7138864673100974e-05,
1058
+ "loss": 0.0402,
1059
+ "step": 1750
1060
+ },
1061
+ {
1062
+ "epoch": 0.82,
1063
+ "learning_rate": 1.7103727833256757e-05,
1064
+ "loss": 0.0453,
1065
+ "step": 1760
1066
+ },
1067
+ {
1068
+ "epoch": 0.82,
1069
+ "learning_rate": 1.706841305041779e-05,
1070
+ "loss": 0.0404,
1071
+ "step": 1770
1072
+ },
1073
+ {
1074
+ "epoch": 0.82,
1075
+ "learning_rate": 1.7032921209192603e-05,
1076
+ "loss": 0.0445,
1077
+ "step": 1780
1078
+ },
1079
+ {
1080
+ "epoch": 0.83,
1081
+ "learning_rate": 1.6997253198624905e-05,
1082
+ "loss": 0.0424,
1083
+ "step": 1790
1084
+ },
1085
+ {
1086
+ "epoch": 0.83,
1087
+ "learning_rate": 1.69614099121713e-05,
1088
+ "loss": 0.0378,
1089
+ "step": 1800
1090
+ },
1091
+ {
1092
+ "epoch": 0.84,
1093
+ "learning_rate": 1.6925392247678943e-05,
1094
+ "loss": 0.0447,
1095
+ "step": 1810
1096
+ },
1097
+ {
1098
+ "epoch": 0.84,
1099
+ "learning_rate": 1.688920110736301e-05,
1100
+ "loss": 0.0413,
1101
+ "step": 1820
1102
+ },
1103
+ {
1104
+ "epoch": 0.85,
1105
+ "learning_rate": 1.6852837397784108e-05,
1106
+ "loss": 0.0385,
1107
+ "step": 1830
1108
+ },
1109
+ {
1110
+ "epoch": 0.85,
1111
+ "learning_rate": 1.6816302029825594e-05,
1112
+ "loss": 0.0389,
1113
+ "step": 1840
1114
+ },
1115
+ {
1116
+ "epoch": 0.86,
1117
+ "learning_rate": 1.677959591867073e-05,
1118
+ "loss": 0.0393,
1119
+ "step": 1850
1120
+ },
1121
+ {
1122
+ "epoch": 0.86,
1123
+ "learning_rate": 1.6742719983779752e-05,
1124
+ "loss": 0.0401,
1125
+ "step": 1860
1126
+ },
1127
+ {
1128
+ "epoch": 0.87,
1129
+ "learning_rate": 1.670567514886687e-05,
1130
+ "loss": 0.0409,
1131
+ "step": 1870
1132
+ },
1133
+ {
1134
+ "epoch": 0.87,
1135
+ "learning_rate": 1.6668462341877098e-05,
1136
+ "loss": 0.0421,
1137
+ "step": 1880
1138
+ },
1139
+ {
1140
+ "epoch": 0.88,
1141
+ "learning_rate": 1.6631082494963037e-05,
1142
+ "loss": 0.0415,
1143
+ "step": 1890
1144
+ },
1145
+ {
1146
+ "epoch": 0.88,
1147
+ "learning_rate": 1.6593536544461494e-05,
1148
+ "loss": 0.0421,
1149
+ "step": 1900
1150
+ },
1151
+ {
1152
+ "epoch": 0.88,
1153
+ "learning_rate": 1.655582543087006e-05,
1154
+ "loss": 0.0419,
1155
+ "step": 1910
1156
+ },
1157
+ {
1158
+ "epoch": 0.89,
1159
+ "learning_rate": 1.651795009882353e-05,
1160
+ "loss": 0.0451,
1161
+ "step": 1920
1162
+ },
1163
+ {
1164
+ "epoch": 0.89,
1165
+ "learning_rate": 1.6479911497070245e-05,
1166
+ "loss": 0.0422,
1167
+ "step": 1930
1168
+ },
1169
+ {
1170
+ "epoch": 0.9,
1171
+ "learning_rate": 1.644171057844833e-05,
1172
+ "loss": 0.0438,
1173
+ "step": 1940
1174
+ },
1175
+ {
1176
+ "epoch": 0.9,
1177
+ "learning_rate": 1.6403348299861827e-05,
1178
+ "loss": 0.0396,
1179
+ "step": 1950
1180
+ },
1181
+ {
1182
+ "epoch": 0.91,
1183
+ "learning_rate": 1.636482562225672e-05,
1184
+ "loss": 0.0377,
1185
+ "step": 1960
1186
+ },
1187
+ {
1188
+ "epoch": 0.91,
1189
+ "learning_rate": 1.6326143510596865e-05,
1190
+ "loss": 0.0362,
1191
+ "step": 1970
1192
+ },
1193
+ {
1194
+ "epoch": 0.92,
1195
+ "learning_rate": 1.6287302933839826e-05,
1196
+ "loss": 0.0442,
1197
+ "step": 1980
1198
+ },
1199
+ {
1200
+ "epoch": 0.92,
1201
+ "learning_rate": 1.6248304864912592e-05,
1202
+ "loss": 0.0397,
1203
+ "step": 1990
1204
+ },
1205
+ {
1206
+ "epoch": 0.93,
1207
+ "learning_rate": 1.6209150280687217e-05,
1208
+ "loss": 0.0389,
1209
+ "step": 2000
1210
+ },
1211
+ {
1212
+ "epoch": 0.93,
1213
+ "learning_rate": 1.6169840161956333e-05,
1214
+ "loss": 0.0382,
1215
+ "step": 2010
1216
+ },
1217
+ {
1218
+ "epoch": 0.94,
1219
+ "learning_rate": 1.6130375493408613e-05,
1220
+ "loss": 0.0435,
1221
+ "step": 2020
1222
+ },
1223
+ {
1224
+ "epoch": 0.94,
1225
+ "learning_rate": 1.609075726360406e-05,
1226
+ "loss": 0.0399,
1227
+ "step": 2030
1228
+ },
1229
+ {
1230
+ "epoch": 0.94,
1231
+ "learning_rate": 1.6050986464949298e-05,
1232
+ "loss": 0.042,
1233
+ "step": 2040
1234
+ },
1235
+ {
1236
+ "epoch": 0.95,
1237
+ "learning_rate": 1.601106409367266e-05,
1238
+ "loss": 0.0394,
1239
+ "step": 2050
1240
+ },
1241
+ {
1242
+ "epoch": 0.95,
1243
+ "learning_rate": 1.5970991149799276e-05,
1244
+ "loss": 0.0399,
1245
+ "step": 2060
1246
+ },
1247
+ {
1248
+ "epoch": 0.96,
1249
+ "learning_rate": 1.5930768637125995e-05,
1250
+ "loss": 0.0424,
1251
+ "step": 2070
1252
+ },
1253
+ {
1254
+ "epoch": 0.96,
1255
+ "learning_rate": 1.5890397563196257e-05,
1256
+ "loss": 0.0416,
1257
+ "step": 2080
1258
+ },
1259
+ {
1260
+ "epoch": 0.97,
1261
+ "learning_rate": 1.5849878939274844e-05,
1262
+ "loss": 0.0426,
1263
+ "step": 2090
1264
+ },
1265
+ {
1266
+ "epoch": 0.97,
1267
+ "learning_rate": 1.580921378032256e-05,
1268
+ "loss": 0.0376,
1269
+ "step": 2100
1270
+ },
1271
+ {
1272
+ "epoch": 0.98,
1273
+ "learning_rate": 1.5768403104970792e-05,
1274
+ "loss": 0.0433,
1275
+ "step": 2110
1276
+ },
1277
+ {
1278
+ "epoch": 0.98,
1279
+ "learning_rate": 1.572744793549601e-05,
1280
+ "loss": 0.038,
1281
+ "step": 2120
1282
+ },
1283
+ {
1284
+ "epoch": 0.99,
1285
+ "learning_rate": 1.5686349297794148e-05,
1286
+ "loss": 0.0412,
1287
+ "step": 2130
1288
+ },
1289
+ {
1290
+ "epoch": 0.99,
1291
+ "learning_rate": 1.564510822135491e-05,
1292
+ "loss": 0.0383,
1293
+ "step": 2140
1294
+ },
1295
+ {
1296
+ "epoch": 1.0,
1297
+ "learning_rate": 1.5603725739235983e-05,
1298
+ "loss": 0.042,
1299
+ "step": 2150
1300
+ },
1301
+ {
1302
+ "epoch": 1.0,
1303
+ "eval_em": 0.6256,
1304
+ "eval_em_ic": 0.9328,
1305
+ "eval_f1": 0.8165,
1306
+ "eval_gen_len": 39.4971,
1307
+ "eval_levinstein_ratio": 0.9954,
1308
+ "eval_loss": 0.050038907676935196,
1309
+ "eval_precision": 0.9175,
1310
+ "eval_recall": 0.8452,
1311
+ "eval_runtime": 167.7461,
1312
+ "eval_samples_per_second": 10.206,
1313
+ "eval_steps_per_second": 0.161,
1314
+ "step": 2159
1315
+ },
1316
+ {
1317
+ "epoch": 1.0,
1318
+ "learning_rate": 1.556220288803716e-05,
1319
+ "loss": 0.0385,
1320
+ "step": 2160
1321
+ },
1322
+ {
1323
+ "epoch": 1.01,
1324
+ "learning_rate": 1.5520540707874373e-05,
1325
+ "loss": 0.0375,
1326
+ "step": 2170
1327
+ },
1328
+ {
1329
+ "epoch": 1.01,
1330
+ "learning_rate": 1.5478740242353644e-05,
1331
+ "loss": 0.0375,
1332
+ "step": 2180
1333
+ },
1334
+ {
1335
+ "epoch": 1.01,
1336
+ "learning_rate": 1.543680253854492e-05,
1337
+ "loss": 0.0374,
1338
+ "step": 2190
1339
+ },
1340
+ {
1341
+ "epoch": 1.02,
1342
+ "learning_rate": 1.5394728646955884e-05,
1343
+ "loss": 0.0407,
1344
+ "step": 2200
1345
+ },
1346
+ {
1347
+ "epoch": 1.02,
1348
+ "learning_rate": 1.535251962150562e-05,
1349
+ "loss": 0.0422,
1350
+ "step": 2210
1351
+ },
1352
+ {
1353
+ "epoch": 1.03,
1354
+ "learning_rate": 1.5310176519498187e-05,
1355
+ "loss": 0.0356,
1356
+ "step": 2220
1357
+ },
1358
+ {
1359
+ "epoch": 1.03,
1360
+ "learning_rate": 1.5267700401596185e-05,
1361
+ "loss": 0.0408,
1362
+ "step": 2230
1363
+ },
1364
+ {
1365
+ "epoch": 1.04,
1366
+ "learning_rate": 1.522509233179415e-05,
1367
+ "loss": 0.0383,
1368
+ "step": 2240
1369
+ },
1370
+ {
1371
+ "epoch": 1.04,
1372
+ "learning_rate": 1.5182353377391925e-05,
1373
+ "loss": 0.0386,
1374
+ "step": 2250
1375
+ },
1376
+ {
1377
+ "epoch": 1.05,
1378
+ "learning_rate": 1.5139484608967901e-05,
1379
+ "loss": 0.0381,
1380
+ "step": 2260
1381
+ },
1382
+ {
1383
+ "epoch": 1.05,
1384
+ "learning_rate": 1.5096487100352208e-05,
1385
+ "loss": 0.0404,
1386
+ "step": 2270
1387
+ },
1388
+ {
1389
+ "epoch": 1.06,
1390
+ "learning_rate": 1.5053361928599837e-05,
1391
+ "loss": 0.0364,
1392
+ "step": 2280
1393
+ },
1394
+ {
1395
+ "epoch": 1.06,
1396
+ "learning_rate": 1.5010110173963633e-05,
1397
+ "loss": 0.0388,
1398
+ "step": 2290
1399
+ },
1400
+ {
1401
+ "epoch": 1.07,
1402
+ "learning_rate": 1.496673291986724e-05,
1403
+ "loss": 0.0405,
1404
+ "step": 2300
1405
+ },
1406
+ {
1407
+ "epoch": 1.07,
1408
+ "learning_rate": 1.4923231252877983e-05,
1409
+ "loss": 0.0353,
1410
+ "step": 2310
1411
+ },
1412
+ {
1413
+ "epoch": 1.07,
1414
+ "learning_rate": 1.4879606262679625e-05,
1415
+ "loss": 0.0388,
1416
+ "step": 2320
1417
+ },
1418
+ {
1419
+ "epoch": 1.08,
1420
+ "learning_rate": 1.4835859042045088e-05,
1421
+ "loss": 0.0404,
1422
+ "step": 2330
1423
+ },
1424
+ {
1425
+ "epoch": 1.08,
1426
+ "learning_rate": 1.4791990686809068e-05,
1427
+ "loss": 0.0373,
1428
+ "step": 2340
1429
+ },
1430
+ {
1431
+ "epoch": 1.09,
1432
+ "learning_rate": 1.4748002295840593e-05,
1433
+ "loss": 0.0382,
1434
+ "step": 2350
1435
+ },
1436
+ {
1437
+ "epoch": 1.09,
1438
+ "learning_rate": 1.4703894971015503e-05,
1439
+ "loss": 0.0347,
1440
+ "step": 2360
1441
+ },
1442
+ {
1443
+ "epoch": 1.1,
1444
+ "learning_rate": 1.4659669817188824e-05,
1445
+ "loss": 0.0388,
1446
+ "step": 2370
1447
+ },
1448
+ {
1449
+ "epoch": 1.1,
1450
+ "learning_rate": 1.4615327942167125e-05,
1451
+ "loss": 0.0342,
1452
+ "step": 2380
1453
+ },
1454
+ {
1455
+ "epoch": 1.11,
1456
+ "learning_rate": 1.4570870456680745e-05,
1457
+ "loss": 0.0389,
1458
+ "step": 2390
1459
+ },
1460
+ {
1461
+ "epoch": 1.11,
1462
+ "learning_rate": 1.452629847435598e-05,
1463
+ "loss": 0.0373,
1464
+ "step": 2400
1465
+ },
1466
+ {
1467
+ "epoch": 1.12,
1468
+ "learning_rate": 1.4481613111687182e-05,
1469
+ "loss": 0.0348,
1470
+ "step": 2410
1471
+ },
1472
+ {
1473
+ "epoch": 1.12,
1474
+ "learning_rate": 1.4436815488008798e-05,
1475
+ "loss": 0.0418,
1476
+ "step": 2420
1477
+ },
1478
+ {
1479
+ "epoch": 1.13,
1480
+ "learning_rate": 1.4391906725467324e-05,
1481
+ "loss": 0.0362,
1482
+ "step": 2430
1483
+ },
1484
+ {
1485
+ "epoch": 1.13,
1486
+ "learning_rate": 1.4346887948993206e-05,
1487
+ "loss": 0.0426,
1488
+ "step": 2440
1489
+ },
1490
+ {
1491
+ "epoch": 1.13,
1492
+ "learning_rate": 1.430176028627265e-05,
1493
+ "loss": 0.0379,
1494
+ "step": 2450
1495
+ },
1496
+ {
1497
+ "epoch": 1.14,
1498
+ "learning_rate": 1.4256524867719386e-05,
1499
+ "loss": 0.0352,
1500
+ "step": 2460
1501
+ },
1502
+ {
1503
+ "epoch": 1.14,
1504
+ "learning_rate": 1.4211182826446334e-05,
1505
+ "loss": 0.0356,
1506
+ "step": 2470
1507
+ },
1508
+ {
1509
+ "epoch": 1.15,
1510
+ "learning_rate": 1.4165735298237251e-05,
1511
+ "loss": 0.0369,
1512
+ "step": 2480
1513
+ },
1514
+ {
1515
+ "epoch": 1.15,
1516
+ "learning_rate": 1.412018342151824e-05,
1517
+ "loss": 0.0333,
1518
+ "step": 2490
1519
+ },
1520
+ {
1521
+ "epoch": 1.16,
1522
+ "learning_rate": 1.4074528337329276e-05,
1523
+ "loss": 0.0333,
1524
+ "step": 2500
1525
+ },
1526
+ {
1527
+ "epoch": 1.16,
1528
+ "learning_rate": 1.4028771189295593e-05,
1529
+ "loss": 0.04,
1530
+ "step": 2510
1531
+ },
1532
+ {
1533
+ "epoch": 1.17,
1534
+ "learning_rate": 1.3982913123599038e-05,
1535
+ "loss": 0.0372,
1536
+ "step": 2520
1537
+ },
1538
+ {
1539
+ "epoch": 1.17,
1540
+ "learning_rate": 1.3936955288949383e-05,
1541
+ "loss": 0.0405,
1542
+ "step": 2530
1543
+ },
1544
+ {
1545
+ "epoch": 1.18,
1546
+ "learning_rate": 1.3890898836555532e-05,
1547
+ "loss": 0.0368,
1548
+ "step": 2540
1549
+ },
1550
+ {
1551
+ "epoch": 1.18,
1552
+ "learning_rate": 1.3844744920096691e-05,
1553
+ "loss": 0.0378,
1554
+ "step": 2550
1555
+ },
1556
+ {
1557
+ "epoch": 1.19,
1558
+ "learning_rate": 1.3798494695693456e-05,
1559
+ "loss": 0.0357,
1560
+ "step": 2560
1561
+ },
1562
+ {
1563
+ "epoch": 1.19,
1564
+ "learning_rate": 1.375214932187888e-05,
1565
+ "loss": 0.0343,
1566
+ "step": 2570
1567
+ },
1568
+ {
1569
+ "epoch": 1.19,
1570
+ "learning_rate": 1.3705709959569422e-05,
1571
+ "loss": 0.0322,
1572
+ "step": 2580
1573
+ },
1574
+ {
1575
+ "epoch": 1.2,
1576
+ "learning_rate": 1.3659177772035896e-05,
1577
+ "loss": 0.041,
1578
+ "step": 2590
1579
+ },
1580
+ {
1581
+ "epoch": 1.2,
1582
+ "learning_rate": 1.3612553924874305e-05,
1583
+ "loss": 0.0351,
1584
+ "step": 2600
1585
+ },
1586
+ {
1587
+ "epoch": 1.21,
1588
+ "learning_rate": 1.356583958597666e-05,
1589
+ "loss": 0.0372,
1590
+ "step": 2610
1591
+ },
1592
+ {
1593
+ "epoch": 1.21,
1594
+ "learning_rate": 1.3519035925501722e-05,
1595
+ "loss": 0.0375,
1596
+ "step": 2620
1597
+ },
1598
+ {
1599
+ "epoch": 1.22,
1600
+ "learning_rate": 1.3472144115845694e-05,
1601
+ "loss": 0.0344,
1602
+ "step": 2630
1603
+ },
1604
+ {
1605
+ "epoch": 1.22,
1606
+ "learning_rate": 1.3425165331612839e-05,
1607
+ "loss": 0.0388,
1608
+ "step": 2640
1609
+ },
1610
+ {
1611
+ "epoch": 1.23,
1612
+ "learning_rate": 1.337810074958608e-05,
1613
+ "loss": 0.0429,
1614
+ "step": 2650
1615
+ },
1616
+ {
1617
+ "epoch": 1.23,
1618
+ "learning_rate": 1.33309515486975e-05,
1619
+ "loss": 0.0351,
1620
+ "step": 2660
1621
+ },
1622
+ {
1623
+ "epoch": 1.24,
1624
+ "learning_rate": 1.3283718909998822e-05,
1625
+ "loss": 0.0412,
1626
+ "step": 2670
1627
+ },
1628
+ {
1629
+ "epoch": 1.24,
1630
+ "learning_rate": 1.323640401663182e-05,
1631
+ "loss": 0.0411,
1632
+ "step": 2680
1633
+ },
1634
+ {
1635
+ "epoch": 1.25,
1636
+ "learning_rate": 1.31890080537987e-05,
1637
+ "loss": 0.0376,
1638
+ "step": 2690
1639
+ },
1640
+ {
1641
+ "epoch": 1.25,
1642
+ "learning_rate": 1.3141532208732381e-05,
1643
+ "loss": 0.0348,
1644
+ "step": 2700
1645
+ },
1646
+ {
1647
+ "epoch": 1.26,
1648
+ "learning_rate": 1.3093977670666772e-05,
1649
+ "loss": 0.0411,
1650
+ "step": 2710
1651
+ },
1652
+ {
1653
+ "epoch": 1.26,
1654
+ "learning_rate": 1.304634563080699e-05,
1655
+ "loss": 0.0359,
1656
+ "step": 2720
1657
+ },
1658
+ {
1659
+ "epoch": 1.26,
1660
+ "learning_rate": 1.2998637282299507e-05,
1661
+ "loss": 0.0414,
1662
+ "step": 2730
1663
+ },
1664
+ {
1665
+ "epoch": 1.27,
1666
+ "learning_rate": 1.2950853820202274e-05,
1667
+ "loss": 0.0377,
1668
+ "step": 2740
1669
+ },
1670
+ {
1671
+ "epoch": 1.27,
1672
+ "learning_rate": 1.2902996441454775e-05,
1673
+ "loss": 0.035,
1674
+ "step": 2750
1675
+ },
1676
+ {
1677
+ "epoch": 1.28,
1678
+ "learning_rate": 1.2855066344848055e-05,
1679
+ "loss": 0.0352,
1680
+ "step": 2760
1681
+ },
1682
+ {
1683
+ "epoch": 1.28,
1684
+ "learning_rate": 1.2807064730994685e-05,
1685
+ "loss": 0.0371,
1686
+ "step": 2770
1687
+ },
1688
+ {
1689
+ "epoch": 1.29,
1690
+ "learning_rate": 1.275899280229868e-05,
1691
+ "loss": 0.0371,
1692
+ "step": 2780
1693
+ },
1694
+ {
1695
+ "epoch": 1.29,
1696
+ "learning_rate": 1.2710851762925403e-05,
1697
+ "loss": 0.0357,
1698
+ "step": 2790
1699
+ },
1700
+ {
1701
+ "epoch": 1.3,
1702
+ "learning_rate": 1.2662642818771377e-05,
1703
+ "loss": 0.0382,
1704
+ "step": 2800
1705
+ },
1706
+ {
1707
+ "epoch": 1.3,
1708
+ "learning_rate": 1.2614367177434094e-05,
1709
+ "loss": 0.0403,
1710
+ "step": 2810
1711
+ },
1712
+ {
1713
+ "epoch": 1.31,
1714
+ "learning_rate": 1.2566026048181756e-05,
1715
+ "loss": 0.0365,
1716
+ "step": 2820
1717
+ },
1718
+ {
1719
+ "epoch": 1.31,
1720
+ "learning_rate": 1.2517620641922986e-05,
1721
+ "loss": 0.0406,
1722
+ "step": 2830
1723
+ },
1724
+ {
1725
+ "epoch": 1.32,
1726
+ "learning_rate": 1.2469152171176503e-05,
1727
+ "loss": 0.0445,
1728
+ "step": 2840
1729
+ },
1730
+ {
1731
+ "epoch": 1.32,
1732
+ "learning_rate": 1.2420621850040741e-05,
1733
+ "loss": 0.0375,
1734
+ "step": 2850
1735
+ },
1736
+ {
1737
+ "epoch": 1.32,
1738
+ "learning_rate": 1.2372030894163437e-05,
1739
+ "loss": 0.0401,
1740
+ "step": 2860
1741
+ },
1742
+ {
1743
+ "epoch": 1.33,
1744
+ "learning_rate": 1.2323380520711185e-05,
1745
+ "loss": 0.0345,
1746
+ "step": 2870
1747
+ },
1748
+ {
1749
+ "epoch": 1.33,
1750
+ "learning_rate": 1.2274671948338947e-05,
1751
+ "loss": 0.0341,
1752
+ "step": 2880
1753
+ },
1754
+ {
1755
+ "epoch": 1.34,
1756
+ "learning_rate": 1.2225906397159518e-05,
1757
+ "loss": 0.0367,
1758
+ "step": 2890
1759
+ },
1760
+ {
1761
+ "epoch": 1.34,
1762
+ "learning_rate": 1.2177085088712965e-05,
1763
+ "loss": 0.0385,
1764
+ "step": 2900
1765
+ },
1766
+ {
1767
+ "epoch": 1.35,
1768
+ "learning_rate": 1.2128209245936045e-05,
1769
+ "loss": 0.0376,
1770
+ "step": 2910
1771
+ },
1772
+ {
1773
+ "epoch": 1.35,
1774
+ "learning_rate": 1.2079280093131554e-05,
1775
+ "loss": 0.0334,
1776
+ "step": 2920
1777
+ },
1778
+ {
1779
+ "epoch": 1.36,
1780
+ "learning_rate": 1.2030298855937654e-05,
1781
+ "loss": 0.0353,
1782
+ "step": 2930
1783
+ },
1784
+ {
1785
+ "epoch": 1.36,
1786
+ "learning_rate": 1.1981266761297196e-05,
1787
+ "loss": 0.0368,
1788
+ "step": 2940
1789
+ },
1790
+ {
1791
+ "epoch": 1.37,
1792
+ "learning_rate": 1.1932185037426964e-05,
1793
+ "loss": 0.0405,
1794
+ "step": 2950
1795
+ },
1796
+ {
1797
+ "epoch": 1.37,
1798
+ "learning_rate": 1.1883054913786915e-05,
1799
+ "loss": 0.0341,
1800
+ "step": 2960
1801
+ },
1802
+ {
1803
+ "epoch": 1.38,
1804
+ "learning_rate": 1.1833877621049386e-05,
1805
+ "loss": 0.0387,
1806
+ "step": 2970
1807
+ },
1808
+ {
1809
+ "epoch": 1.38,
1810
+ "learning_rate": 1.1784654391068264e-05,
1811
+ "loss": 0.0354,
1812
+ "step": 2980
1813
+ },
1814
+ {
1815
+ "epoch": 1.38,
1816
+ "learning_rate": 1.1735386456848134e-05,
1817
+ "loss": 0.0399,
1818
+ "step": 2990
1819
+ },
1820
+ {
1821
+ "epoch": 1.39,
1822
+ "learning_rate": 1.1686075052513378e-05,
1823
+ "loss": 0.0326,
1824
+ "step": 3000
1825
+ },
1826
+ {
1827
+ "epoch": 1.39,
1828
+ "learning_rate": 1.1636721413277274e-05,
1829
+ "loss": 0.0379,
1830
+ "step": 3010
1831
+ },
1832
+ {
1833
+ "epoch": 1.4,
1834
+ "learning_rate": 1.1587326775411061e-05,
1835
+ "loss": 0.0382,
1836
+ "step": 3020
1837
+ },
1838
+ {
1839
+ "epoch": 1.4,
1840
+ "learning_rate": 1.1537892376212956e-05,
1841
+ "loss": 0.0371,
1842
+ "step": 3030
1843
+ },
1844
+ {
1845
+ "epoch": 1.41,
1846
+ "learning_rate": 1.1488419453977166e-05,
1847
+ "loss": 0.0365,
1848
+ "step": 3040
1849
+ },
1850
+ {
1851
+ "epoch": 1.41,
1852
+ "learning_rate": 1.143890924796287e-05,
1853
+ "loss": 0.0361,
1854
+ "step": 3050
1855
+ },
1856
+ {
1857
+ "epoch": 1.42,
1858
+ "learning_rate": 1.1389362998363187e-05,
1859
+ "loss": 0.0366,
1860
+ "step": 3060
1861
+ },
1862
+ {
1863
+ "epoch": 1.42,
1864
+ "learning_rate": 1.133978194627409e-05,
1865
+ "loss": 0.0368,
1866
+ "step": 3070
1867
+ },
1868
+ {
1869
+ "epoch": 1.43,
1870
+ "learning_rate": 1.1290167333663326e-05,
1871
+ "loss": 0.0375,
1872
+ "step": 3080
1873
+ },
1874
+ {
1875
+ "epoch": 1.43,
1876
+ "learning_rate": 1.124052040333932e-05,
1877
+ "loss": 0.0338,
1878
+ "step": 3090
1879
+ },
1880
+ {
1881
+ "epoch": 1.44,
1882
+ "learning_rate": 1.1190842398920026e-05,
1883
+ "loss": 0.041,
1884
+ "step": 3100
1885
+ },
1886
+ {
1887
+ "epoch": 1.44,
1888
+ "learning_rate": 1.1141134564801775e-05,
1889
+ "loss": 0.034,
1890
+ "step": 3110
1891
+ },
1892
+ {
1893
+ "epoch": 1.45,
1894
+ "learning_rate": 1.109139814612811e-05,
1895
+ "loss": 0.038,
1896
+ "step": 3120
1897
+ },
1898
+ {
1899
+ "epoch": 1.45,
1900
+ "learning_rate": 1.1041634388758601e-05,
1901
+ "loss": 0.0397,
1902
+ "step": 3130
1903
+ },
1904
+ {
1905
+ "epoch": 1.45,
1906
+ "learning_rate": 1.0991844539237635e-05,
1907
+ "loss": 0.0326,
1908
+ "step": 3140
1909
+ },
1910
+ {
1911
+ "epoch": 1.46,
1912
+ "learning_rate": 1.0942029844763177e-05,
1913
+ "loss": 0.0377,
1914
+ "step": 3150
1915
+ },
1916
+ {
1917
+ "epoch": 1.46,
1918
+ "learning_rate": 1.0892191553155543e-05,
1919
+ "loss": 0.0361,
1920
+ "step": 3160
1921
+ },
1922
+ {
1923
+ "epoch": 1.47,
1924
+ "learning_rate": 1.0842330912826138e-05,
1925
+ "loss": 0.0343,
1926
+ "step": 3170
1927
+ },
1928
+ {
1929
+ "epoch": 1.47,
1930
+ "learning_rate": 1.0792449172746197e-05,
1931
+ "loss": 0.0384,
1932
+ "step": 3180
1933
+ },
1934
+ {
1935
+ "epoch": 1.48,
1936
+ "learning_rate": 1.0742547582415473e-05,
1937
+ "loss": 0.0336,
1938
+ "step": 3190
1939
+ },
1940
+ {
1941
+ "epoch": 1.48,
1942
+ "learning_rate": 1.0692627391830954e-05,
1943
+ "loss": 0.0339,
1944
+ "step": 3200
1945
+ },
1946
+ {
1947
+ "epoch": 1.49,
1948
+ "learning_rate": 1.0642689851455561e-05,
1949
+ "loss": 0.0369,
1950
+ "step": 3210
1951
+ },
1952
+ {
1953
+ "epoch": 1.49,
1954
+ "learning_rate": 1.0592736212186808e-05,
1955
+ "loss": 0.0338,
1956
+ "step": 3220
1957
+ },
1958
+ {
1959
+ "epoch": 1.5,
1960
+ "learning_rate": 1.0542767725325471e-05,
1961
+ "loss": 0.0346,
1962
+ "step": 3230
1963
+ },
1964
+ {
1965
+ "epoch": 1.5,
1966
+ "learning_rate": 1.0492785642544248e-05,
1967
+ "loss": 0.0349,
1968
+ "step": 3240
1969
+ },
1970
+ {
1971
+ "epoch": 1.51,
1972
+ "learning_rate": 1.0442791215856409e-05,
1973
+ "loss": 0.0402,
1974
+ "step": 3250
1975
+ },
1976
+ {
1977
+ "epoch": 1.51,
1978
+ "learning_rate": 1.0392785697584428e-05,
1979
+ "loss": 0.039,
1980
+ "step": 3260
1981
+ },
1982
+ {
1983
+ "epoch": 1.51,
1984
+ "learning_rate": 1.0342770340328609e-05,
1985
+ "loss": 0.0414,
1986
+ "step": 3270
1987
+ },
1988
+ {
1989
+ "epoch": 1.52,
1990
+ "learning_rate": 1.0292746396935727e-05,
1991
+ "loss": 0.0358,
1992
+ "step": 3280
1993
+ },
1994
+ {
1995
+ "epoch": 1.52,
1996
+ "learning_rate": 1.0242715120467616e-05,
1997
+ "loss": 0.0377,
1998
+ "step": 3290
1999
+ },
2000
+ {
2001
+ "epoch": 1.53,
2002
+ "learning_rate": 1.0192677764169817e-05,
2003
+ "loss": 0.0347,
2004
+ "step": 3300
2005
+ },
2006
+ {
2007
+ "epoch": 1.53,
2008
+ "learning_rate": 1.0142635581440148e-05,
2009
+ "loss": 0.0316,
2010
+ "step": 3310
2011
+ },
2012
+ {
2013
+ "epoch": 1.54,
2014
+ "learning_rate": 1.009258982579734e-05,
2015
+ "loss": 0.0404,
2016
+ "step": 3320
2017
+ },
2018
+ {
2019
+ "epoch": 1.54,
2020
+ "learning_rate": 1.004254175084962e-05,
2021
+ "loss": 0.0368,
2022
+ "step": 3330
2023
+ },
2024
+ {
2025
+ "epoch": 1.55,
2026
+ "learning_rate": 9.992492610263299e-06,
2027
+ "loss": 0.037,
2028
+ "step": 3340
2029
+ },
2030
+ {
2031
+ "epoch": 1.55,
2032
+ "learning_rate": 9.942443657731405e-06,
2033
+ "loss": 0.0338,
2034
+ "step": 3350
2035
+ },
2036
+ {
2037
+ "epoch": 1.56,
2038
+ "learning_rate": 9.892396146942228e-06,
2039
+ "loss": 0.0384,
2040
+ "step": 3360
2041
+ },
2042
+ {
2043
+ "epoch": 1.56,
2044
+ "learning_rate": 9.842351331547964e-06,
2045
+ "loss": 0.0398,
2046
+ "step": 3370
2047
+ },
2048
+ {
2049
+ "epoch": 1.57,
2050
+ "learning_rate": 9.792310465133284e-06,
2051
+ "loss": 0.0346,
2052
+ "step": 3380
2053
+ },
2054
+ {
2055
+ "epoch": 1.57,
2056
+ "learning_rate": 9.74227480118394e-06,
2057
+ "loss": 0.0342,
2058
+ "step": 3390
2059
+ },
2060
+ {
2061
+ "epoch": 1.57,
2062
+ "learning_rate": 9.692245593055368e-06,
2063
+ "loss": 0.039,
2064
+ "step": 3400
2065
+ },
2066
+ {
2067
+ "epoch": 1.58,
2068
+ "learning_rate": 9.64222409394129e-06,
2069
+ "loss": 0.0363,
2070
+ "step": 3410
2071
+ },
2072
+ {
2073
+ "epoch": 1.58,
2074
+ "learning_rate": 9.592211556842319e-06,
2075
+ "loss": 0.0359,
2076
+ "step": 3420
2077
+ },
2078
+ {
2079
+ "epoch": 1.59,
2080
+ "learning_rate": 9.542209234534581e-06,
2081
+ "loss": 0.0378,
2082
+ "step": 3430
2083
+ },
2084
+ {
2085
+ "epoch": 1.59,
2086
+ "learning_rate": 9.492218379538331e-06,
2087
+ "loss": 0.0317,
2088
+ "step": 3440
2089
+ },
2090
+ {
2091
+ "epoch": 1.6,
2092
+ "learning_rate": 9.442240244086573e-06,
2093
+ "loss": 0.0369,
2094
+ "step": 3450
2095
+ },
2096
+ {
2097
+ "epoch": 1.6,
2098
+ "learning_rate": 9.392276080093693e-06,
2099
+ "loss": 0.0387,
2100
+ "step": 3460
2101
+ },
2102
+ {
2103
+ "epoch": 1.61,
2104
+ "learning_rate": 9.342327139124107e-06,
2105
+ "loss": 0.0345,
2106
+ "step": 3470
2107
+ },
2108
+ {
2109
+ "epoch": 1.61,
2110
+ "learning_rate": 9.292394672360906e-06,
2111
+ "loss": 0.0343,
2112
+ "step": 3480
2113
+ },
2114
+ {
2115
+ "epoch": 1.62,
2116
+ "learning_rate": 9.242479930574515e-06,
2117
+ "loss": 0.0389,
2118
+ "step": 3490
2119
+ },
2120
+ {
2121
+ "epoch": 1.62,
2122
+ "learning_rate": 9.192584164091358e-06,
2123
+ "loss": 0.035,
2124
+ "step": 3500
2125
+ },
2126
+ {
2127
+ "epoch": 1.63,
2128
+ "learning_rate": 9.142708622762545e-06,
2129
+ "loss": 0.0357,
2130
+ "step": 3510
2131
+ },
2132
+ {
2133
+ "epoch": 1.63,
2134
+ "learning_rate": 9.092854555932561e-06,
2135
+ "loss": 0.035,
2136
+ "step": 3520
2137
+ },
2138
+ {
2139
+ "epoch": 1.64,
2140
+ "learning_rate": 9.043023212407971e-06,
2141
+ "loss": 0.0373,
2142
+ "step": 3530
2143
+ },
2144
+ {
2145
+ "epoch": 1.64,
2146
+ "learning_rate": 8.993215840426138e-06,
2147
+ "loss": 0.0334,
2148
+ "step": 3540
2149
+ },
2150
+ {
2151
+ "epoch": 1.64,
2152
+ "learning_rate": 8.94343368762396e-06,
2153
+ "loss": 0.0366,
2154
+ "step": 3550
2155
+ },
2156
+ {
2157
+ "epoch": 1.65,
2158
+ "learning_rate": 8.893678001006601e-06,
2159
+ "loss": 0.0377,
2160
+ "step": 3560
2161
+ },
2162
+ {
2163
+ "epoch": 1.65,
2164
+ "learning_rate": 8.843950026916283e-06,
2165
+ "loss": 0.0295,
2166
+ "step": 3570
2167
+ },
2168
+ {
2169
+ "epoch": 1.66,
2170
+ "learning_rate": 8.794251011001038e-06,
2171
+ "loss": 0.0358,
2172
+ "step": 3580
2173
+ },
2174
+ {
2175
+ "epoch": 1.66,
2176
+ "learning_rate": 8.744582198183528e-06,
2177
+ "loss": 0.0357,
2178
+ "step": 3590
2179
+ },
2180
+ {
2181
+ "epoch": 1.67,
2182
+ "learning_rate": 8.694944832629844e-06,
2183
+ "loss": 0.0328,
2184
+ "step": 3600
2185
+ },
2186
+ {
2187
+ "epoch": 1.67,
2188
+ "learning_rate": 8.645340157718346e-06,
2189
+ "loss": 0.0377,
2190
+ "step": 3610
2191
+ },
2192
+ {
2193
+ "epoch": 1.68,
2194
+ "learning_rate": 8.59576941600852e-06,
2195
+ "loss": 0.0342,
2196
+ "step": 3620
2197
+ },
2198
+ {
2199
+ "epoch": 1.68,
2200
+ "learning_rate": 8.546233849209856e-06,
2201
+ "loss": 0.0402,
2202
+ "step": 3630
2203
+ },
2204
+ {
2205
+ "epoch": 1.69,
2206
+ "learning_rate": 8.49673469815073e-06,
2207
+ "loss": 0.0378,
2208
+ "step": 3640
2209
+ },
2210
+ {
2211
+ "epoch": 1.69,
2212
+ "learning_rate": 8.447273202747337e-06,
2213
+ "loss": 0.0388,
2214
+ "step": 3650
2215
+ },
2216
+ {
2217
+ "epoch": 1.7,
2218
+ "learning_rate": 8.397850601972625e-06,
2219
+ "loss": 0.0372,
2220
+ "step": 3660
2221
+ },
2222
+ {
2223
+ "epoch": 1.7,
2224
+ "learning_rate": 8.34846813382526e-06,
2225
+ "loss": 0.0356,
2226
+ "step": 3670
2227
+ },
2228
+ {
2229
+ "epoch": 1.7,
2230
+ "learning_rate": 8.299127035298621e-06,
2231
+ "loss": 0.039,
2232
+ "step": 3680
2233
+ },
2234
+ {
2235
+ "epoch": 1.71,
2236
+ "learning_rate": 8.249828542349802e-06,
2237
+ "loss": 0.0329,
2238
+ "step": 3690
2239
+ },
2240
+ {
2241
+ "epoch": 1.71,
2242
+ "learning_rate": 8.200573889868666e-06,
2243
+ "loss": 0.036,
2244
+ "step": 3700
2245
+ },
2246
+ {
2247
+ "epoch": 1.72,
2248
+ "learning_rate": 8.151364311646902e-06,
2249
+ "loss": 0.0385,
2250
+ "step": 3710
2251
+ },
2252
+ {
2253
+ "epoch": 1.72,
2254
+ "learning_rate": 8.102201040347123e-06,
2255
+ "loss": 0.0361,
2256
+ "step": 3720
2257
+ },
2258
+ {
2259
+ "epoch": 1.73,
2260
+ "learning_rate": 8.053085307471989e-06,
2261
+ "loss": 0.0361,
2262
+ "step": 3730
2263
+ },
2264
+ {
2265
+ "epoch": 1.73,
2266
+ "learning_rate": 8.004018343333366e-06,
2267
+ "loss": 0.0309,
2268
+ "step": 3740
2269
+ },
2270
+ {
2271
+ "epoch": 1.74,
2272
+ "learning_rate": 7.955001377021484e-06,
2273
+ "loss": 0.0395,
2274
+ "step": 3750
2275
+ },
2276
+ {
2277
+ "epoch": 1.74,
2278
+ "learning_rate": 7.906035636374177e-06,
2279
+ "loss": 0.034,
2280
+ "step": 3760
2281
+ },
2282
+ {
2283
+ "epoch": 1.75,
2284
+ "learning_rate": 7.857122347946113e-06,
2285
+ "loss": 0.0354,
2286
+ "step": 3770
2287
+ },
2288
+ {
2289
+ "epoch": 1.75,
2290
+ "learning_rate": 7.808262736978074e-06,
2291
+ "loss": 0.0316,
2292
+ "step": 3780
2293
+ },
2294
+ {
2295
+ "epoch": 1.76,
2296
+ "learning_rate": 7.759458027366258e-06,
2297
+ "loss": 0.0374,
2298
+ "step": 3790
2299
+ },
2300
+ {
2301
+ "epoch": 1.76,
2302
+ "learning_rate": 7.710709441631624e-06,
2303
+ "loss": 0.0356,
2304
+ "step": 3800
2305
+ },
2306
+ {
2307
+ "epoch": 1.76,
2308
+ "learning_rate": 7.662018200889276e-06,
2309
+ "loss": 0.041,
2310
+ "step": 3810
2311
+ },
2312
+ {
2313
+ "epoch": 1.77,
2314
+ "learning_rate": 7.6133855248178715e-06,
2315
+ "loss": 0.0342,
2316
+ "step": 3820
2317
+ },
2318
+ {
2319
+ "epoch": 1.77,
2320
+ "learning_rate": 7.564812631629055e-06,
2321
+ "loss": 0.0334,
2322
+ "step": 3830
2323
+ },
2324
+ {
2325
+ "epoch": 1.78,
2326
+ "learning_rate": 7.516300738036972e-06,
2327
+ "loss": 0.0356,
2328
+ "step": 3840
2329
+ },
2330
+ {
2331
+ "epoch": 1.78,
2332
+ "learning_rate": 7.4678510592277576e-06,
2333
+ "loss": 0.0367,
2334
+ "step": 3850
2335
+ },
2336
+ {
2337
+ "epoch": 1.79,
2338
+ "learning_rate": 7.419464808829123e-06,
2339
+ "loss": 0.0311,
2340
+ "step": 3860
2341
+ },
2342
+ {
2343
+ "epoch": 1.79,
2344
+ "learning_rate": 7.3711431988799485e-06,
2345
+ "loss": 0.0398,
2346
+ "step": 3870
2347
+ },
2348
+ {
2349
+ "epoch": 1.8,
2350
+ "learning_rate": 7.322887439799913e-06,
2351
+ "loss": 0.0334,
2352
+ "step": 3880
2353
+ },
2354
+ {
2355
+ "epoch": 1.8,
2356
+ "learning_rate": 7.274698740359184e-06,
2357
+ "loss": 0.04,
2358
+ "step": 3890
2359
+ },
2360
+ {
2361
+ "epoch": 1.81,
2362
+ "learning_rate": 7.22657830764814e-06,
2363
+ "loss": 0.0352,
2364
+ "step": 3900
2365
+ },
2366
+ {
2367
+ "epoch": 1.81,
2368
+ "learning_rate": 7.17852734704712e-06,
2369
+ "loss": 0.0401,
2370
+ "step": 3910
2371
+ },
2372
+ {
2373
+ "epoch": 1.82,
2374
+ "learning_rate": 7.1305470621962495e-06,
2375
+ "loss": 0.0356,
2376
+ "step": 3920
2377
+ },
2378
+ {
2379
+ "epoch": 1.82,
2380
+ "learning_rate": 7.082638654965277e-06,
2381
+ "loss": 0.0357,
2382
+ "step": 3930
2383
+ },
2384
+ {
2385
+ "epoch": 1.82,
2386
+ "learning_rate": 7.034803325423465e-06,
2387
+ "loss": 0.0391,
2388
+ "step": 3940
2389
+ },
2390
+ {
2391
+ "epoch": 1.83,
2392
+ "learning_rate": 6.987042271809541e-06,
2393
+ "loss": 0.0334,
2394
+ "step": 3950
2395
+ },
2396
+ {
2397
+ "epoch": 1.83,
2398
+ "learning_rate": 6.9393566905016775e-06,
2399
+ "loss": 0.0317,
2400
+ "step": 3960
2401
+ },
2402
+ {
2403
+ "epoch": 1.84,
2404
+ "learning_rate": 6.891747775987521e-06,
2405
+ "loss": 0.0347,
2406
+ "step": 3970
2407
+ },
2408
+ {
2409
+ "epoch": 1.84,
2410
+ "learning_rate": 6.844216720834276e-06,
2411
+ "loss": 0.0321,
2412
+ "step": 3980
2413
+ },
2414
+ {
2415
+ "epoch": 1.85,
2416
+ "learning_rate": 6.796764715658821e-06,
2417
+ "loss": 0.0342,
2418
+ "step": 3990
2419
+ },
2420
+ {
2421
+ "epoch": 1.85,
2422
+ "learning_rate": 6.749392949097904e-06,
2423
+ "loss": 0.0385,
2424
+ "step": 4000
2425
+ },
2426
+ {
2427
+ "epoch": 1.86,
2428
+ "learning_rate": 6.702102607778347e-06,
2429
+ "loss": 0.0325,
2430
+ "step": 4010
2431
+ },
2432
+ {
2433
+ "epoch": 1.86,
2434
+ "learning_rate": 6.654894876287335e-06,
2435
+ "loss": 0.0337,
2436
+ "step": 4020
2437
+ },
2438
+ {
2439
+ "epoch": 1.87,
2440
+ "learning_rate": 6.607770937142743e-06,
2441
+ "loss": 0.0383,
2442
+ "step": 4030
2443
+ },
2444
+ {
2445
+ "epoch": 1.87,
2446
+ "learning_rate": 6.560731970763503e-06,
2447
+ "loss": 0.0366,
2448
+ "step": 4040
2449
+ },
2450
+ {
2451
+ "epoch": 1.88,
2452
+ "learning_rate": 6.51377915544005e-06,
2453
+ "loss": 0.0357,
2454
+ "step": 4050
2455
+ },
2456
+ {
2457
+ "epoch": 1.88,
2458
+ "learning_rate": 6.4669136673047985e-06,
2459
+ "loss": 0.0363,
2460
+ "step": 4060
2461
+ },
2462
+ {
2463
+ "epoch": 1.89,
2464
+ "learning_rate": 6.420136680302683e-06,
2465
+ "loss": 0.0401,
2466
+ "step": 4070
2467
+ },
2468
+ {
2469
+ "epoch": 1.89,
2470
+ "learning_rate": 6.373449366161755e-06,
2471
+ "loss": 0.0345,
2472
+ "step": 4080
2473
+ },
2474
+ {
2475
+ "epoch": 1.89,
2476
+ "learning_rate": 6.326852894363824e-06,
2477
+ "loss": 0.04,
2478
+ "step": 4090
2479
+ },
2480
+ {
2481
+ "epoch": 1.9,
2482
+ "learning_rate": 6.280348432115169e-06,
2483
+ "loss": 0.0338,
2484
+ "step": 4100
2485
+ },
2486
+ {
2487
+ "epoch": 1.9,
2488
+ "learning_rate": 6.233937144317302e-06,
2489
+ "loss": 0.0384,
2490
+ "step": 4110
2491
+ },
2492
+ {
2493
+ "epoch": 1.91,
2494
+ "learning_rate": 6.1876201935377835e-06,
2495
+ "loss": 0.038,
2496
+ "step": 4120
2497
+ },
2498
+ {
2499
+ "epoch": 1.91,
2500
+ "learning_rate": 6.1413987399811055e-06,
2501
+ "loss": 0.0406,
2502
+ "step": 4130
2503
+ },
2504
+ {
2505
+ "epoch": 1.92,
2506
+ "learning_rate": 6.0952739414596205e-06,
2507
+ "loss": 0.0334,
2508
+ "step": 4140
2509
+ },
2510
+ {
2511
+ "epoch": 1.92,
2512
+ "learning_rate": 6.049246953364551e-06,
2513
+ "loss": 0.0343,
2514
+ "step": 4150
2515
+ },
2516
+ {
2517
+ "epoch": 1.93,
2518
+ "learning_rate": 6.003318928637045e-06,
2519
+ "loss": 0.0329,
2520
+ "step": 4160
2521
+ },
2522
+ {
2523
+ "epoch": 1.93,
2524
+ "learning_rate": 5.957491017739292e-06,
2525
+ "loss": 0.0405,
2526
+ "step": 4170
2527
+ },
2528
+ {
2529
+ "epoch": 1.94,
2530
+ "learning_rate": 5.911764368625697e-06,
2531
+ "loss": 0.0334,
2532
+ "step": 4180
2533
+ },
2534
+ {
2535
+ "epoch": 1.94,
2536
+ "learning_rate": 5.866140126714146e-06,
2537
+ "loss": 0.0414,
2538
+ "step": 4190
2539
+ },
2540
+ {
2541
+ "epoch": 1.95,
2542
+ "learning_rate": 5.820619434857295e-06,
2543
+ "loss": 0.035,
2544
+ "step": 4200
2545
+ },
2546
+ {
2547
+ "epoch": 1.95,
2548
+ "learning_rate": 5.775203433313956e-06,
2549
+ "loss": 0.0366,
2550
+ "step": 4210
2551
+ },
2552
+ {
2553
+ "epoch": 1.95,
2554
+ "learning_rate": 5.729893259720523e-06,
2555
+ "loss": 0.0312,
2556
+ "step": 4220
2557
+ },
2558
+ {
2559
+ "epoch": 1.96,
2560
+ "learning_rate": 5.684690049062478e-06,
2561
+ "loss": 0.0366,
2562
+ "step": 4230
2563
+ },
2564
+ {
2565
+ "epoch": 1.96,
2566
+ "learning_rate": 5.639594933645969e-06,
2567
+ "loss": 0.0341,
2568
+ "step": 4240
2569
+ },
2570
+ {
2571
+ "epoch": 1.97,
2572
+ "learning_rate": 5.594609043069431e-06,
2573
+ "loss": 0.0318,
2574
+ "step": 4250
2575
+ },
2576
+ {
2577
+ "epoch": 1.97,
2578
+ "learning_rate": 5.549733504195314e-06,
2579
+ "loss": 0.037,
2580
+ "step": 4260
2581
+ },
2582
+ {
2583
+ "epoch": 1.98,
2584
+ "learning_rate": 5.50496944112183e-06,
2585
+ "loss": 0.0347,
2586
+ "step": 4270
2587
+ },
2588
+ {
2589
+ "epoch": 1.98,
2590
+ "learning_rate": 5.460317975154805e-06,
2591
+ "loss": 0.038,
2592
+ "step": 4280
2593
+ },
2594
+ {
2595
+ "epoch": 1.99,
2596
+ "learning_rate": 5.415780224779605e-06,
2597
+ "loss": 0.0318,
2598
+ "step": 4290
2599
+ },
2600
+ {
2601
+ "epoch": 1.99,
2602
+ "learning_rate": 5.371357305633098e-06,
2603
+ "loss": 0.0336,
2604
+ "step": 4300
2605
+ },
2606
+ {
2607
+ "epoch": 2.0,
2608
+ "learning_rate": 5.327050330475712e-06,
2609
+ "loss": 0.0342,
2610
+ "step": 4310
2611
+ },
2612
+ {
2613
+ "epoch": 2.0,
2614
+ "eval_em": 0.6361,
2615
+ "eval_em_ic": 0.9334,
2616
+ "eval_f1": 0.8229,
2617
+ "eval_gen_len": 39.5158,
2618
+ "eval_levinstein_ratio": 0.9955,
2619
+ "eval_loss": 0.049182891845703125,
2620
+ "eval_precision": 0.9159,
2621
+ "eval_recall": 0.8546,
2622
+ "eval_runtime": 166.2957,
2623
+ "eval_samples_per_second": 10.295,
2624
+ "eval_steps_per_second": 0.162,
2625
+ "step": 4318
2626
+ },
2627
+ {
2628
+ "epoch": 2.0,
2629
+ "learning_rate": 5.282860409163584e-06,
2630
+ "loss": 0.0371,
2631
+ "step": 4320
2632
+ },
2633
+ {
2634
+ "epoch": 2.01,
2635
+ "learning_rate": 5.238788648620714e-06,
2636
+ "loss": 0.0321,
2637
+ "step": 4330
2638
+ },
2639
+ {
2640
+ "epoch": 2.01,
2641
+ "learning_rate": 5.194836152811292e-06,
2642
+ "loss": 0.0366,
2643
+ "step": 4340
2644
+ },
2645
+ {
2646
+ "epoch": 2.01,
2647
+ "learning_rate": 5.1510040227120005e-06,
2648
+ "loss": 0.0413,
2649
+ "step": 4350
2650
+ },
2651
+ {
2652
+ "epoch": 2.02,
2653
+ "learning_rate": 5.107293356284451e-06,
2654
+ "loss": 0.0342,
2655
+ "step": 4360
2656
+ },
2657
+ {
2658
+ "epoch": 2.02,
2659
+ "learning_rate": 5.063705248447697e-06,
2660
+ "loss": 0.0354,
2661
+ "step": 4370
2662
+ },
2663
+ {
2664
+ "epoch": 2.03,
2665
+ "learning_rate": 5.0202407910507755e-06,
2666
+ "loss": 0.0337,
2667
+ "step": 4380
2668
+ },
2669
+ {
2670
+ "epoch": 2.03,
2671
+ "learning_rate": 4.976901072845379e-06,
2672
+ "loss": 0.0323,
2673
+ "step": 4390
2674
+ },
2675
+ {
2676
+ "epoch": 2.04,
2677
+ "learning_rate": 4.933687179458588e-06,
2678
+ "loss": 0.0353,
2679
+ "step": 4400
2680
+ },
2681
+ {
2682
+ "epoch": 2.04,
2683
+ "learning_rate": 4.890600193365654e-06,
2684
+ "loss": 0.0328,
2685
+ "step": 4410
2686
+ },
2687
+ {
2688
+ "epoch": 2.05,
2689
+ "learning_rate": 4.847641193862901e-06,
2690
+ "loss": 0.032,
2691
+ "step": 4420
2692
+ },
2693
+ {
2694
+ "epoch": 2.05,
2695
+ "learning_rate": 4.804811257040685e-06,
2696
+ "loss": 0.0345,
2697
+ "step": 4430
2698
+ },
2699
+ {
2700
+ "epoch": 2.06,
2701
+ "learning_rate": 4.7621114557564405e-06,
2702
+ "loss": 0.0339,
2703
+ "step": 4440
2704
+ },
2705
+ {
2706
+ "epoch": 2.06,
2707
+ "learning_rate": 4.719542859607812e-06,
2708
+ "loss": 0.0344,
2709
+ "step": 4450
2710
+ },
2711
+ {
2712
+ "epoch": 2.07,
2713
+ "learning_rate": 4.677106534905844e-06,
2714
+ "loss": 0.0432,
2715
+ "step": 4460
2716
+ },
2717
+ {
2718
+ "epoch": 2.07,
2719
+ "learning_rate": 4.6348035446482845e-06,
2720
+ "loss": 0.0331,
2721
+ "step": 4470
2722
+ },
2723
+ {
2724
+ "epoch": 2.08,
2725
+ "learning_rate": 4.592634948492965e-06,
2726
+ "loss": 0.0346,
2727
+ "step": 4480
2728
+ },
2729
+ {
2730
+ "epoch": 2.08,
2731
+ "learning_rate": 4.550601802731231e-06,
2732
+ "loss": 0.0345,
2733
+ "step": 4490
2734
+ },
2735
+ {
2736
+ "epoch": 2.08,
2737
+ "learning_rate": 4.508705160261506e-06,
2738
+ "loss": 0.0302,
2739
+ "step": 4500
2740
+ },
2741
+ {
2742
+ "epoch": 2.09,
2743
+ "learning_rate": 4.466946070562915e-06,
2744
+ "loss": 0.0368,
2745
+ "step": 4510
2746
+ },
2747
+ {
2748
+ "epoch": 2.09,
2749
+ "learning_rate": 4.425325579668982e-06,
2750
+ "loss": 0.0356,
2751
+ "step": 4520
2752
+ },
2753
+ {
2754
+ "epoch": 2.1,
2755
+ "learning_rate": 4.383844730141438e-06,
2756
+ "loss": 0.0343,
2757
+ "step": 4530
2758
+ },
2759
+ {
2760
+ "epoch": 2.1,
2761
+ "learning_rate": 4.342504561044105e-06,
2762
+ "loss": 0.0391,
2763
+ "step": 4540
2764
+ },
2765
+ {
2766
+ "epoch": 2.11,
2767
+ "learning_rate": 4.301306107916862e-06,
2768
+ "loss": 0.0377,
2769
+ "step": 4550
2770
+ },
2771
+ {
2772
+ "epoch": 2.11,
2773
+ "learning_rate": 4.260250402749725e-06,
2774
+ "loss": 0.0338,
2775
+ "step": 4560
2776
+ },
2777
+ {
2778
+ "epoch": 2.12,
2779
+ "learning_rate": 4.219338473956964e-06,
2780
+ "loss": 0.0339,
2781
+ "step": 4570
2782
+ },
2783
+ {
2784
+ "epoch": 2.12,
2785
+ "learning_rate": 4.178571346351366e-06,
2786
+ "loss": 0.0323,
2787
+ "step": 4580
2788
+ },
2789
+ {
2790
+ "epoch": 2.13,
2791
+ "learning_rate": 4.137950041118568e-06,
2792
+ "loss": 0.0323,
2793
+ "step": 4590
2794
+ },
2795
+ {
2796
+ "epoch": 2.13,
2797
+ "learning_rate": 4.097475575791454e-06,
2798
+ "loss": 0.0366,
2799
+ "step": 4600
2800
+ },
2801
+ {
2802
+ "epoch": 2.14,
2803
+ "learning_rate": 4.057148964224684e-06,
2804
+ "loss": 0.0322,
2805
+ "step": 4610
2806
+ },
2807
+ {
2808
+ "epoch": 2.14,
2809
+ "learning_rate": 4.016971216569294e-06,
2810
+ "loss": 0.0348,
2811
+ "step": 4620
2812
+ },
2813
+ {
2814
+ "epoch": 2.14,
2815
+ "learning_rate": 3.976943339247391e-06,
2816
+ "loss": 0.0343,
2817
+ "step": 4630
2818
+ },
2819
+ {
2820
+ "epoch": 2.15,
2821
+ "learning_rate": 3.937066334926949e-06,
2822
+ "loss": 0.0346,
2823
+ "step": 4640
2824
+ },
2825
+ {
2826
+ "epoch": 2.15,
2827
+ "learning_rate": 3.897341202496679e-06,
2828
+ "loss": 0.0357,
2829
+ "step": 4650
2830
+ },
2831
+ {
2832
+ "epoch": 2.16,
2833
+ "learning_rate": 3.857768937041021e-06,
2834
+ "loss": 0.0295,
2835
+ "step": 4660
2836
+ },
2837
+ {
2838
+ "epoch": 2.16,
2839
+ "learning_rate": 3.818350529815218e-06,
2840
+ "loss": 0.0347,
2841
+ "step": 4670
2842
+ },
2843
+ {
2844
+ "epoch": 2.17,
2845
+ "learning_rate": 3.779086968220472e-06,
2846
+ "loss": 0.0307,
2847
+ "step": 4680
2848
+ },
2849
+ {
2850
+ "epoch": 2.17,
2851
+ "learning_rate": 3.7399792357792207e-06,
2852
+ "loss": 0.033,
2853
+ "step": 4690
2854
+ },
2855
+ {
2856
+ "epoch": 2.18,
2857
+ "learning_rate": 3.7010283121105094e-06,
2858
+ "loss": 0.0341,
2859
+ "step": 4700
2860
+ },
2861
+ {
2862
+ "epoch": 2.18,
2863
+ "learning_rate": 3.662235172905435e-06,
2864
+ "loss": 0.0327,
2865
+ "step": 4710
2866
+ },
2867
+ {
2868
+ "epoch": 2.19,
2869
+ "learning_rate": 3.623600789902704e-06,
2870
+ "loss": 0.0319,
2871
+ "step": 4720
2872
+ },
2873
+ {
2874
+ "epoch": 2.19,
2875
+ "learning_rate": 3.5851261308643204e-06,
2876
+ "loss": 0.0298,
2877
+ "step": 4730
2878
+ },
2879
+ {
2880
+ "epoch": 2.2,
2881
+ "learning_rate": 3.5468121595513073e-06,
2882
+ "loss": 0.0332,
2883
+ "step": 4740
2884
+ },
2885
+ {
2886
+ "epoch": 2.2,
2887
+ "learning_rate": 3.508659835699595e-06,
2888
+ "loss": 0.0364,
2889
+ "step": 4750
2890
+ },
2891
+ {
2892
+ "epoch": 2.2,
2893
+ "learning_rate": 3.4706701149959577e-06,
2894
+ "loss": 0.0363,
2895
+ "step": 4760
2896
+ },
2897
+ {
2898
+ "epoch": 2.21,
2899
+ "learning_rate": 3.4328439490540844e-06,
2900
+ "loss": 0.0384,
2901
+ "step": 4770
2902
+ },
2903
+ {
2904
+ "epoch": 2.21,
2905
+ "learning_rate": 3.3951822853907525e-06,
2906
+ "loss": 0.0327,
2907
+ "step": 4780
2908
+ },
2909
+ {
2910
+ "epoch": 2.22,
2911
+ "learning_rate": 3.3576860674020683e-06,
2912
+ "loss": 0.0317,
2913
+ "step": 4790
2914
+ },
2915
+ {
2916
+ "epoch": 2.22,
2917
+ "learning_rate": 3.3203562343398545e-06,
2918
+ "loss": 0.0347,
2919
+ "step": 4800
2920
+ },
2921
+ {
2922
+ "epoch": 2.23,
2923
+ "learning_rate": 3.283193721288127e-06,
2924
+ "loss": 0.0336,
2925
+ "step": 4810
2926
+ },
2927
+ {
2928
+ "epoch": 2.23,
2929
+ "learning_rate": 3.246199459139643e-06,
2930
+ "loss": 0.0323,
2931
+ "step": 4820
2932
+ },
2933
+ {
2934
+ "epoch": 2.24,
2935
+ "learning_rate": 3.2093743745726147e-06,
2936
+ "loss": 0.0317,
2937
+ "step": 4830
2938
+ },
2939
+ {
2940
+ "epoch": 2.24,
2941
+ "learning_rate": 3.1727193900274866e-06,
2942
+ "loss": 0.0361,
2943
+ "step": 4840
2944
+ },
2945
+ {
2946
+ "epoch": 2.25,
2947
+ "learning_rate": 3.136235423683819e-06,
2948
+ "loss": 0.0359,
2949
+ "step": 4850
2950
+ },
2951
+ {
2952
+ "epoch": 2.25,
2953
+ "learning_rate": 3.0999233894373026e-06,
2954
+ "loss": 0.0336,
2955
+ "step": 4860
2956
+ },
2957
+ {
2958
+ "epoch": 2.26,
2959
+ "learning_rate": 3.0637841968768532e-06,
2960
+ "loss": 0.0375,
2961
+ "step": 4870
2962
+ },
2963
+ {
2964
+ "epoch": 2.26,
2965
+ "learning_rate": 3.027818751261836e-06,
2966
+ "loss": 0.0353,
2967
+ "step": 4880
2968
+ },
2969
+ {
2970
+ "epoch": 2.26,
2971
+ "learning_rate": 2.992027953499391e-06,
2972
+ "loss": 0.032,
2973
+ "step": 4890
2974
+ },
2975
+ {
2976
+ "epoch": 2.27,
2977
+ "learning_rate": 2.95641270012186e-06,
2978
+ "loss": 0.0306,
2979
+ "step": 4900
2980
+ },
2981
+ {
2982
+ "epoch": 2.27,
2983
+ "learning_rate": 2.92097388326432e-06,
2984
+ "loss": 0.0345,
2985
+ "step": 4910
2986
+ },
2987
+ {
2988
+ "epoch": 2.28,
2989
+ "learning_rate": 2.8857123906422644e-06,
2990
+ "loss": 0.0349,
2991
+ "step": 4920
2992
+ },
2993
+ {
2994
+ "epoch": 2.28,
2995
+ "learning_rate": 2.8506291055293358e-06,
2996
+ "loss": 0.0361,
2997
+ "step": 4930
2998
+ },
2999
+ {
3000
+ "epoch": 2.29,
3001
+ "learning_rate": 2.8157249067352254e-06,
3002
+ "loss": 0.0375,
3003
+ "step": 4940
3004
+ },
3005
+ {
3006
+ "epoch": 2.29,
3007
+ "learning_rate": 2.781000668583638e-06,
3008
+ "loss": 0.0402,
3009
+ "step": 4950
3010
+ },
3011
+ {
3012
+ "epoch": 2.3,
3013
+ "learning_rate": 2.7464572608904005e-06,
3014
+ "loss": 0.0361,
3015
+ "step": 4960
3016
+ },
3017
+ {
3018
+ "epoch": 2.3,
3019
+ "learning_rate": 2.7120955489416865e-06,
3020
+ "loss": 0.0325,
3021
+ "step": 4970
3022
+ },
3023
+ {
3024
+ "epoch": 2.31,
3025
+ "learning_rate": 2.677916393472315e-06,
3026
+ "loss": 0.0334,
3027
+ "step": 4980
3028
+ },
3029
+ {
3030
+ "epoch": 2.31,
3031
+ "learning_rate": 2.6439206506442083e-06,
3032
+ "loss": 0.0337,
3033
+ "step": 4990
3034
+ },
3035
+ {
3036
+ "epoch": 2.32,
3037
+ "learning_rate": 2.610109172024948e-06,
3038
+ "loss": 0.0369,
3039
+ "step": 5000
3040
+ },
3041
+ {
3042
+ "epoch": 2.32,
3043
+ "learning_rate": 2.5764828045664238e-06,
3044
+ "loss": 0.0349,
3045
+ "step": 5010
3046
+ },
3047
+ {
3048
+ "epoch": 2.33,
3049
+ "learning_rate": 2.5430423905836365e-06,
3050
+ "loss": 0.0356,
3051
+ "step": 5020
3052
+ },
3053
+ {
3054
+ "epoch": 2.33,
3055
+ "learning_rate": 2.5097887677336043e-06,
3056
+ "loss": 0.0342,
3057
+ "step": 5030
3058
+ },
3059
+ {
3060
+ "epoch": 2.33,
3061
+ "learning_rate": 2.4767227689943506e-06,
3062
+ "loss": 0.0329,
3063
+ "step": 5040
3064
+ },
3065
+ {
3066
+ "epoch": 2.34,
3067
+ "learning_rate": 2.4438452226440734e-06,
3068
+ "loss": 0.0306,
3069
+ "step": 5050
3070
+ },
3071
+ {
3072
+ "epoch": 2.34,
3073
+ "learning_rate": 2.411156952240373e-06,
3074
+ "loss": 0.0314,
3075
+ "step": 5060
3076
+ },
3077
+ {
3078
+ "epoch": 2.35,
3079
+ "learning_rate": 2.3786587765996283e-06,
3080
+ "loss": 0.035,
3081
+ "step": 5070
3082
+ },
3083
+ {
3084
+ "epoch": 2.35,
3085
+ "learning_rate": 2.346351509776498e-06,
3086
+ "loss": 0.0355,
3087
+ "step": 5080
3088
+ },
3089
+ {
3090
+ "epoch": 2.36,
3091
+ "learning_rate": 2.3142359610435105e-06,
3092
+ "loss": 0.0374,
3093
+ "step": 5090
3094
+ },
3095
+ {
3096
+ "epoch": 2.36,
3097
+ "learning_rate": 2.282312934870806e-06,
3098
+ "loss": 0.0338,
3099
+ "step": 5100
3100
+ },
3101
+ {
3102
+ "epoch": 2.37,
3103
+ "learning_rate": 2.2505832309059806e-06,
3104
+ "loss": 0.0327,
3105
+ "step": 5110
3106
+ },
3107
+ {
3108
+ "epoch": 2.37,
3109
+ "learning_rate": 2.2190476439540543e-06,
3110
+ "loss": 0.0347,
3111
+ "step": 5120
3112
+ },
3113
+ {
3114
+ "epoch": 2.38,
3115
+ "learning_rate": 2.1877069639575587e-06,
3116
+ "loss": 0.0383,
3117
+ "step": 5130
3118
+ },
3119
+ {
3120
+ "epoch": 2.38,
3121
+ "learning_rate": 2.1565619759767675e-06,
3122
+ "loss": 0.0359,
3123
+ "step": 5140
3124
+ },
3125
+ {
3126
+ "epoch": 2.39,
3127
+ "learning_rate": 2.1256134601700018e-06,
3128
+ "loss": 0.0288,
3129
+ "step": 5150
3130
+ },
3131
+ {
3132
+ "epoch": 2.39,
3133
+ "learning_rate": 2.0948621917741163e-06,
3134
+ "loss": 0.0336,
3135
+ "step": 5160
3136
+ },
3137
+ {
3138
+ "epoch": 2.39,
3139
+ "learning_rate": 2.0643089410850624e-06,
3140
+ "loss": 0.0304,
3141
+ "step": 5170
3142
+ },
3143
+ {
3144
+ "epoch": 2.4,
3145
+ "learning_rate": 2.033954473438593e-06,
3146
+ "loss": 0.0334,
3147
+ "step": 5180
3148
+ },
3149
+ {
3150
+ "epoch": 2.4,
3151
+ "learning_rate": 2.00379954919111e-06,
3152
+ "loss": 0.0347,
3153
+ "step": 5190
3154
+ },
3155
+ {
3156
+ "epoch": 2.41,
3157
+ "learning_rate": 1.9738449237005895e-06,
3158
+ "loss": 0.034,
3159
+ "step": 5200
3160
+ },
3161
+ {
3162
+ "epoch": 2.41,
3163
+ "learning_rate": 1.9440913473076815e-06,
3164
+ "loss": 0.0302,
3165
+ "step": 5210
3166
+ },
3167
+ {
3168
+ "epoch": 2.42,
3169
+ "learning_rate": 1.914539565316915e-06,
3170
+ "loss": 0.0383,
3171
+ "step": 5220
3172
+ },
3173
+ {
3174
+ "epoch": 2.42,
3175
+ "learning_rate": 1.885190317978015e-06,
3176
+ "loss": 0.0357,
3177
+ "step": 5230
3178
+ },
3179
+ {
3180
+ "epoch": 2.43,
3181
+ "learning_rate": 1.8560443404673644e-06,
3182
+ "loss": 0.0339,
3183
+ "step": 5240
3184
+ },
3185
+ {
3186
+ "epoch": 2.43,
3187
+ "learning_rate": 1.8271023628696027e-06,
3188
+ "loss": 0.0318,
3189
+ "step": 5250
3190
+ },
3191
+ {
3192
+ "epoch": 2.44,
3193
+ "learning_rate": 1.7983651101593126e-06,
3194
+ "loss": 0.0341,
3195
+ "step": 5260
3196
+ },
3197
+ {
3198
+ "epoch": 2.44,
3199
+ "learning_rate": 1.769833302182885e-06,
3200
+ "loss": 0.0316,
3201
+ "step": 5270
3202
+ },
3203
+ {
3204
+ "epoch": 2.45,
3205
+ "learning_rate": 1.7415076536404697e-06,
3206
+ "loss": 0.0299,
3207
+ "step": 5280
3208
+ },
3209
+ {
3210
+ "epoch": 2.45,
3211
+ "learning_rate": 1.7133888740680803e-06,
3212
+ "loss": 0.0302,
3213
+ "step": 5290
3214
+ },
3215
+ {
3216
+ "epoch": 2.45,
3217
+ "learning_rate": 1.6854776678198192e-06,
3218
+ "loss": 0.0326,
3219
+ "step": 5300
3220
+ },
3221
+ {
3222
+ "epoch": 2.46,
3223
+ "learning_rate": 1.6577747340502348e-06,
3224
+ "loss": 0.0323,
3225
+ "step": 5310
3226
+ },
3227
+ {
3228
+ "epoch": 2.46,
3229
+ "learning_rate": 1.6302807666968068e-06,
3230
+ "loss": 0.0342,
3231
+ "step": 5320
3232
+ },
3233
+ {
3234
+ "epoch": 2.47,
3235
+ "learning_rate": 1.6029964544625698e-06,
3236
+ "loss": 0.0333,
3237
+ "step": 5330
3238
+ },
3239
+ {
3240
+ "epoch": 2.47,
3241
+ "learning_rate": 1.5759224807988504e-06,
3242
+ "loss": 0.0367,
3243
+ "step": 5340
3244
+ },
3245
+ {
3246
+ "epoch": 2.48,
3247
+ "learning_rate": 1.5490595238881544e-06,
3248
+ "loss": 0.0349,
3249
+ "step": 5350
3250
+ },
3251
+ {
3252
+ "epoch": 2.48,
3253
+ "learning_rate": 1.5224082566271835e-06,
3254
+ "loss": 0.0363,
3255
+ "step": 5360
3256
+ },
3257
+ {
3258
+ "epoch": 2.49,
3259
+ "learning_rate": 1.4959693466099657e-06,
3260
+ "loss": 0.0301,
3261
+ "step": 5370
3262
+ },
3263
+ {
3264
+ "epoch": 2.49,
3265
+ "learning_rate": 1.4697434561111512e-06,
3266
+ "loss": 0.0379,
3267
+ "step": 5380
3268
+ },
3269
+ {
3270
+ "epoch": 2.5,
3271
+ "learning_rate": 1.443731242069405e-06,
3272
+ "loss": 0.0371,
3273
+ "step": 5390
3274
+ },
3275
+ {
3276
+ "epoch": 2.5,
3277
+ "learning_rate": 1.4179333560709563e-06,
3278
+ "loss": 0.0378,
3279
+ "step": 5400
3280
+ },
3281
+ {
3282
+ "epoch": 2.51,
3283
+ "learning_rate": 1.3923504443332914e-06,
3284
+ "loss": 0.0327,
3285
+ "step": 5410
3286
+ },
3287
+ {
3288
+ "epoch": 2.51,
3289
+ "learning_rate": 1.3669831476889429e-06,
3290
+ "loss": 0.0318,
3291
+ "step": 5420
3292
+ },
3293
+ {
3294
+ "epoch": 2.52,
3295
+ "learning_rate": 1.3418321015694525e-06,
3296
+ "loss": 0.0354,
3297
+ "step": 5430
3298
+ },
3299
+ {
3300
+ "epoch": 2.52,
3301
+ "learning_rate": 1.316897935989454e-06,
3302
+ "loss": 0.0371,
3303
+ "step": 5440
3304
+ },
3305
+ {
3306
+ "epoch": 2.52,
3307
+ "learning_rate": 1.2921812755308839e-06,
3308
+ "loss": 0.0363,
3309
+ "step": 5450
3310
+ },
3311
+ {
3312
+ "epoch": 2.53,
3313
+ "learning_rate": 1.2676827393273405e-06,
3314
+ "loss": 0.0426,
3315
+ "step": 5460
3316
+ },
3317
+ {
3318
+ "epoch": 2.53,
3319
+ "learning_rate": 1.2434029410485771e-06,
3320
+ "loss": 0.0378,
3321
+ "step": 5470
3322
+ },
3323
+ {
3324
+ "epoch": 2.54,
3325
+ "learning_rate": 1.219342488885128e-06,
3326
+ "loss": 0.0297,
3327
+ "step": 5480
3328
+ },
3329
+ {
3330
+ "epoch": 2.54,
3331
+ "learning_rate": 1.1955019855330708e-06,
3332
+ "loss": 0.0341,
3333
+ "step": 5490
3334
+ },
3335
+ {
3336
+ "epoch": 2.55,
3337
+ "learning_rate": 1.1718820281789323e-06,
3338
+ "loss": 0.0327,
3339
+ "step": 5500
3340
+ },
3341
+ {
3342
+ "epoch": 2.55,
3343
+ "learning_rate": 1.148483208484732e-06,
3344
+ "loss": 0.0321,
3345
+ "step": 5510
3346
+ },
3347
+ {
3348
+ "epoch": 2.56,
3349
+ "learning_rate": 1.125306112573159e-06,
3350
+ "loss": 0.0313,
3351
+ "step": 5520
3352
+ },
3353
+ {
3354
+ "epoch": 2.56,
3355
+ "learning_rate": 1.1023513210128878e-06,
3356
+ "loss": 0.0324,
3357
+ "step": 5530
3358
+ },
3359
+ {
3360
+ "epoch": 2.57,
3361
+ "learning_rate": 1.0796194088040358e-06,
3362
+ "loss": 0.0335,
3363
+ "step": 5540
3364
+ },
3365
+ {
3366
+ "epoch": 2.57,
3367
+ "learning_rate": 1.0571109453637674e-06,
3368
+ "loss": 0.0393,
3369
+ "step": 5550
3370
+ },
3371
+ {
3372
+ "epoch": 2.58,
3373
+ "learning_rate": 1.0348264945120202e-06,
3374
+ "loss": 0.0331,
3375
+ "step": 5560
3376
+ },
3377
+ {
3378
+ "epoch": 2.58,
3379
+ "learning_rate": 1.0127666144573845e-06,
3380
+ "loss": 0.0295,
3381
+ "step": 5570
3382
+ },
3383
+ {
3384
+ "epoch": 2.58,
3385
+ "learning_rate": 9.909318577831317e-07,
3386
+ "loss": 0.0347,
3387
+ "step": 5580
3388
+ },
3389
+ {
3390
+ "epoch": 2.59,
3391
+ "learning_rate": 9.693227714333487e-07,
3392
+ "loss": 0.036,
3393
+ "step": 5590
3394
+ },
3395
+ {
3396
+ "epoch": 2.59,
3397
+ "learning_rate": 9.47939896699267e-07,
3398
+ "loss": 0.0334,
3399
+ "step": 5600
3400
+ },
3401
+ {
3402
+ "epoch": 2.6,
3403
+ "learning_rate": 9.267837692056791e-07,
3404
+ "loss": 0.0334,
3405
+ "step": 5610
3406
+ },
3407
+ {
3408
+ "epoch": 2.6,
3409
+ "learning_rate": 9.05854918897533e-07,
3410
+ "loss": 0.0296,
3411
+ "step": 5620
3412
+ },
3413
+ {
3414
+ "epoch": 2.61,
3415
+ "learning_rate": 8.851538700266593e-07,
3416
+ "loss": 0.0309,
3417
+ "step": 5630
3418
+ },
3419
+ {
3420
+ "epoch": 2.61,
3421
+ "learning_rate": 8.646811411386313e-07,
3422
+ "loss": 0.0326,
3423
+ "step": 5640
3424
+ },
3425
+ {
3426
+ "epoch": 2.62,
3427
+ "learning_rate": 8.444372450597782e-07,
3428
+ "loss": 0.032,
3429
+ "step": 5650
3430
+ },
3431
+ {
3432
+ "epoch": 2.62,
3433
+ "learning_rate": 8.244226888843487e-07,
3434
+ "loss": 0.0323,
3435
+ "step": 5660
3436
+ },
3437
+ {
3438
+ "epoch": 2.63,
3439
+ "learning_rate": 8.046379739617915e-07,
3440
+ "loss": 0.0322,
3441
+ "step": 5670
3442
+ },
3443
+ {
3444
+ "epoch": 2.63,
3445
+ "learning_rate": 7.850835958842174e-07,
3446
+ "loss": 0.0349,
3447
+ "step": 5680
3448
+ },
3449
+ {
3450
+ "epoch": 2.64,
3451
+ "learning_rate": 7.657600444739588e-07,
3452
+ "loss": 0.0332,
3453
+ "step": 5690
3454
+ },
3455
+ {
3456
+ "epoch": 2.64,
3457
+ "learning_rate": 7.466678037713271e-07,
3458
+ "loss": 0.0343,
3459
+ "step": 5700
3460
+ },
3461
+ {
3462
+ "epoch": 2.64,
3463
+ "learning_rate": 7.278073520224737e-07,
3464
+ "loss": 0.0356,
3465
+ "step": 5710
3466
+ },
3467
+ {
3468
+ "epoch": 2.65,
3469
+ "learning_rate": 7.091791616674093e-07,
3470
+ "loss": 0.0376,
3471
+ "step": 5720
3472
+ },
3473
+ {
3474
+ "epoch": 2.65,
3475
+ "learning_rate": 6.907836993281736e-07,
3476
+ "loss": 0.0349,
3477
+ "step": 5730
3478
+ },
3479
+ {
3480
+ "epoch": 2.66,
3481
+ "learning_rate": 6.726214257971509e-07,
3482
+ "loss": 0.0335,
3483
+ "step": 5740
3484
+ },
3485
+ {
3486
+ "epoch": 2.66,
3487
+ "learning_rate": 6.546927960255167e-07,
3488
+ "loss": 0.0327,
3489
+ "step": 5750
3490
+ },
3491
+ {
3492
+ "epoch": 2.67,
3493
+ "learning_rate": 6.369982591118473e-07,
3494
+ "loss": 0.0299,
3495
+ "step": 5760
3496
+ },
3497
+ {
3498
+ "epoch": 2.67,
3499
+ "learning_rate": 6.195382582908793e-07,
3500
+ "loss": 0.0356,
3501
+ "step": 5770
3502
+ },
3503
+ {
3504
+ "epoch": 2.68,
3505
+ "learning_rate": 6.023132309223834e-07,
3506
+ "loss": 0.0355,
3507
+ "step": 5780
3508
+ },
3509
+ {
3510
+ "epoch": 2.68,
3511
+ "learning_rate": 5.853236084802372e-07,
3512
+ "loss": 0.0346,
3513
+ "step": 5790
3514
+ },
3515
+ {
3516
+ "epoch": 2.69,
3517
+ "learning_rate": 5.685698165415965e-07,
3518
+ "loss": 0.0329,
3519
+ "step": 5800
3520
+ },
3521
+ {
3522
+ "epoch": 2.69,
3523
+ "learning_rate": 5.520522747762424e-07,
3524
+ "loss": 0.0301,
3525
+ "step": 5810
3526
+ },
3527
+ {
3528
+ "epoch": 2.7,
3529
+ "learning_rate": 5.357713969360712e-07,
3530
+ "loss": 0.0327,
3531
+ "step": 5820
3532
+ },
3533
+ {
3534
+ "epoch": 2.7,
3535
+ "learning_rate": 5.197275908447241e-07,
3536
+ "loss": 0.0313,
3537
+ "step": 5830
3538
+ },
3539
+ {
3540
+ "epoch": 2.7,
3541
+ "learning_rate": 5.039212583873743e-07,
3542
+ "loss": 0.0315,
3543
+ "step": 5840
3544
+ },
3545
+ {
3546
+ "epoch": 2.71,
3547
+ "learning_rate": 4.883527955006662e-07,
3548
+ "loss": 0.0323,
3549
+ "step": 5850
3550
+ },
3551
+ {
3552
+ "epoch": 2.71,
3553
+ "learning_rate": 4.7302259216278625e-07,
3554
+ "loss": 0.0333,
3555
+ "step": 5860
3556
+ },
3557
+ {
3558
+ "epoch": 2.72,
3559
+ "learning_rate": 4.5793103238370053e-07,
3560
+ "loss": 0.0333,
3561
+ "step": 5870
3562
+ },
3563
+ {
3564
+ "epoch": 2.72,
3565
+ "learning_rate": 4.430784941955368e-07,
3566
+ "loss": 0.0291,
3567
+ "step": 5880
3568
+ },
3569
+ {
3570
+ "epoch": 2.73,
3571
+ "learning_rate": 4.2846534964311124e-07,
3572
+ "loss": 0.0323,
3573
+ "step": 5890
3574
+ },
3575
+ {
3576
+ "epoch": 2.73,
3577
+ "learning_rate": 4.1409196477461444e-07,
3578
+ "loss": 0.0353,
3579
+ "step": 5900
3580
+ },
3581
+ {
3582
+ "epoch": 2.74,
3583
+ "learning_rate": 3.999586996324367e-07,
3584
+ "loss": 0.0355,
3585
+ "step": 5910
3586
+ },
3587
+ {
3588
+ "epoch": 2.74,
3589
+ "learning_rate": 3.860659082441476e-07,
3590
+ "loss": 0.0345,
3591
+ "step": 5920
3592
+ },
3593
+ {
3594
+ "epoch": 2.75,
3595
+ "learning_rate": 3.724139386136394e-07,
3596
+ "loss": 0.0336,
3597
+ "step": 5930
3598
+ },
3599
+ {
3600
+ "epoch": 2.75,
3601
+ "learning_rate": 3.5900313271239664e-07,
3602
+ "loss": 0.0316,
3603
+ "step": 5940
3604
+ },
3605
+ {
3606
+ "epoch": 2.76,
3607
+ "learning_rate": 3.4583382647093267e-07,
3608
+ "loss": 0.0322,
3609
+ "step": 5950
3610
+ },
3611
+ {
3612
+ "epoch": 2.76,
3613
+ "learning_rate": 3.329063497703866e-07,
3614
+ "loss": 0.0333,
3615
+ "step": 5960
3616
+ },
3617
+ {
3618
+ "epoch": 2.77,
3619
+ "learning_rate": 3.2022102643424315e-07,
3620
+ "loss": 0.0344,
3621
+ "step": 5970
3622
+ },
3623
+ {
3624
+ "epoch": 2.77,
3625
+ "learning_rate": 3.0777817422023017e-07,
3626
+ "loss": 0.0362,
3627
+ "step": 5980
3628
+ },
3629
+ {
3630
+ "epoch": 2.77,
3631
+ "learning_rate": 2.955781048123607e-07,
3632
+ "loss": 0.0352,
3633
+ "step": 5990
3634
+ },
3635
+ {
3636
+ "epoch": 2.78,
3637
+ "learning_rate": 2.836211238131192e-07,
3638
+ "loss": 0.0336,
3639
+ "step": 6000
3640
+ },
3641
+ {
3642
+ "epoch": 2.78,
3643
+ "learning_rate": 2.7190753073581434e-07,
3644
+ "loss": 0.0338,
3645
+ "step": 6010
3646
+ },
3647
+ {
3648
+ "epoch": 2.79,
3649
+ "learning_rate": 2.604376189970659e-07,
3650
+ "loss": 0.0339,
3651
+ "step": 6020
3652
+ },
3653
+ {
3654
+ "epoch": 2.79,
3655
+ "learning_rate": 2.492116759094654e-07,
3656
+ "loss": 0.0375,
3657
+ "step": 6030
3658
+ },
3659
+ {
3660
+ "epoch": 2.8,
3661
+ "learning_rate": 2.382299826743739e-07,
3662
+ "loss": 0.0344,
3663
+ "step": 6040
3664
+ },
3665
+ {
3666
+ "epoch": 2.8,
3667
+ "learning_rate": 2.2749281437487891e-07,
3668
+ "loss": 0.033,
3669
+ "step": 6050
3670
+ },
3671
+ {
3672
+ "epoch": 2.81,
3673
+ "learning_rate": 2.1700043996890074e-07,
3674
+ "loss": 0.0348,
3675
+ "step": 6060
3676
+ },
3677
+ {
3678
+ "epoch": 2.81,
3679
+ "learning_rate": 2.067531222824648e-07,
3680
+ "loss": 0.0373,
3681
+ "step": 6070
3682
+ },
3683
+ {
3684
+ "epoch": 2.82,
3685
+ "learning_rate": 1.9675111800310341e-07,
3686
+ "loss": 0.0363,
3687
+ "step": 6080
3688
+ },
3689
+ {
3690
+ "epoch": 2.82,
3691
+ "learning_rate": 1.8699467767343993e-07,
3692
+ "loss": 0.0344,
3693
+ "step": 6090
3694
+ },
3695
+ {
3696
+ "epoch": 2.83,
3697
+ "learning_rate": 1.7748404568490696e-07,
3698
+ "loss": 0.0339,
3699
+ "step": 6100
3700
+ },
3701
+ {
3702
+ "epoch": 2.83,
3703
+ "learning_rate": 1.6821946027161917e-07,
3704
+ "loss": 0.0362,
3705
+ "step": 6110
3706
+ },
3707
+ {
3708
+ "epoch": 2.83,
3709
+ "learning_rate": 1.5920115350441913e-07,
3710
+ "loss": 0.0298,
3711
+ "step": 6120
3712
+ },
3713
+ {
3714
+ "epoch": 2.84,
3715
+ "learning_rate": 1.5042935128504965e-07,
3716
+ "loss": 0.0329,
3717
+ "step": 6130
3718
+ },
3719
+ {
3720
+ "epoch": 2.84,
3721
+ "learning_rate": 1.4190427334050294e-07,
3722
+ "loss": 0.0341,
3723
+ "step": 6140
3724
+ },
3725
+ {
3726
+ "epoch": 2.85,
3727
+ "learning_rate": 1.3362613321751815e-07,
3728
+ "loss": 0.0352,
3729
+ "step": 6150
3730
+ },
3731
+ {
3732
+ "epoch": 2.85,
3733
+ "learning_rate": 1.2559513827722582e-07,
3734
+ "loss": 0.0314,
3735
+ "step": 6160
3736
+ },
3737
+ {
3738
+ "epoch": 2.86,
3739
+ "learning_rate": 1.1781148968995959e-07,
3740
+ "loss": 0.0318,
3741
+ "step": 6170
3742
+ },
3743
+ {
3744
+ "epoch": 2.86,
3745
+ "learning_rate": 1.1027538243021274e-07,
3746
+ "loss": 0.0319,
3747
+ "step": 6180
3748
+ },
3749
+ {
3750
+ "epoch": 2.87,
3751
+ "learning_rate": 1.0298700527175521e-07,
3752
+ "loss": 0.0351,
3753
+ "step": 6190
3754
+ },
3755
+ {
3756
+ "epoch": 2.87,
3757
+ "learning_rate": 9.594654078290966e-08,
3758
+ "loss": 0.0388,
3759
+ "step": 6200
3760
+ },
3761
+ {
3762
+ "epoch": 2.88,
3763
+ "learning_rate": 8.915416532197186e-08,
3764
+ "loss": 0.0333,
3765
+ "step": 6210
3766
+ },
3767
+ {
3768
+ "epoch": 2.88,
3769
+ "learning_rate": 8.261004903279413e-08,
3770
+ "loss": 0.0338,
3771
+ "step": 6220
3772
+ },
3773
+ {
3774
+ "epoch": 2.89,
3775
+ "learning_rate": 7.631435584052772e-08,
3776
+ "loss": 0.0313,
3777
+ "step": 6230
3778
+ },
3779
+ {
3780
+ "epoch": 2.89,
3781
+ "learning_rate": 7.026724344751268e-08,
3782
+ "loss": 0.036,
3783
+ "step": 6240
3784
+ },
3785
+ {
3786
+ "epoch": 2.89,
3787
+ "learning_rate": 6.446886332932667e-08,
3788
+ "loss": 0.0309,
3789
+ "step": 6250
3790
+ },
3791
+ {
3792
+ "epoch": 2.9,
3793
+ "learning_rate": 5.89193607309968e-08,
3794
+ "loss": 0.0321,
3795
+ "step": 6260
3796
+ },
3797
+ {
3798
+ "epoch": 2.9,
3799
+ "learning_rate": 5.3618874663351475e-08,
3800
+ "loss": 0.035,
3801
+ "step": 6270
3802
+ },
3803
+ {
3804
+ "epoch": 2.91,
3805
+ "learning_rate": 4.856753789954982e-08,
3806
+ "loss": 0.0327,
3807
+ "step": 6280
3808
+ },
3809
+ {
3810
+ "epoch": 2.91,
3811
+ "learning_rate": 4.376547697174438e-08,
3812
+ "loss": 0.0347,
3813
+ "step": 6290
3814
+ },
3815
+ {
3816
+ "epoch": 2.92,
3817
+ "learning_rate": 3.921281216791917e-08,
3818
+ "loss": 0.0353,
3819
+ "step": 6300
3820
+ },
3821
+ {
3822
+ "epoch": 2.92,
3823
+ "learning_rate": 3.490965752887765e-08,
3824
+ "loss": 0.0337,
3825
+ "step": 6310
3826
+ },
3827
+ {
3828
+ "epoch": 2.93,
3829
+ "learning_rate": 3.0856120845377256e-08,
3830
+ "loss": 0.0335,
3831
+ "step": 6320
3832
+ },
3833
+ {
3834
+ "epoch": 2.93,
3835
+ "learning_rate": 2.7052303655438204e-08,
3836
+ "loss": 0.031,
3837
+ "step": 6330
3838
+ },
3839
+ {
3840
+ "epoch": 2.94,
3841
+ "learning_rate": 2.349830124179775e-08,
3842
+ "loss": 0.0358,
3843
+ "step": 6340
3844
+ },
3845
+ {
3846
+ "epoch": 2.94,
3847
+ "learning_rate": 2.0194202629519876e-08,
3848
+ "loss": 0.0322,
3849
+ "step": 6350
3850
+ },
3851
+ {
3852
+ "epoch": 2.95,
3853
+ "learning_rate": 1.714009058376931e-08,
3854
+ "loss": 0.0308,
3855
+ "step": 6360
3856
+ },
3857
+ {
3858
+ "epoch": 2.95,
3859
+ "learning_rate": 1.4336041607736495e-08,
3860
+ "loss": 0.0344,
3861
+ "step": 6370
3862
+ },
3863
+ {
3864
+ "epoch": 2.96,
3865
+ "learning_rate": 1.1782125940721367e-08,
3866
+ "loss": 0.035,
3867
+ "step": 6380
3868
+ },
3869
+ {
3870
+ "epoch": 2.96,
3871
+ "learning_rate": 9.478407556375857e-09,
3872
+ "loss": 0.0334,
3873
+ "step": 6390
3874
+ },
3875
+ {
3876
+ "epoch": 2.96,
3877
+ "learning_rate": 7.424944161096293e-09,
3878
+ "loss": 0.0306,
3879
+ "step": 6400
3880
+ },
3881
+ {
3882
+ "epoch": 2.97,
3883
+ "learning_rate": 5.621787192583439e-09,
3884
+ "loss": 0.0331,
3885
+ "step": 6410
3886
+ },
3887
+ {
3888
+ "epoch": 2.97,
3889
+ "learning_rate": 4.06898181855353e-09,
3890
+ "loss": 0.0351,
3891
+ "step": 6420
3892
+ },
3893
+ {
3894
+ "epoch": 2.98,
3895
+ "learning_rate": 2.7665669356025105e-09,
3896
+ "loss": 0.0315,
3897
+ "step": 6430
3898
+ },
3899
+ {
3900
+ "epoch": 2.98,
3901
+ "learning_rate": 1.7145751682368094e-09,
3902
+ "loss": 0.0329,
3903
+ "step": 6440
3904
+ },
3905
+ {
3906
+ "epoch": 2.99,
3907
+ "learning_rate": 9.130328680495571e-10,
3908
+ "loss": 0.0354,
3909
+ "step": 6450
3910
+ },
3911
+ {
3912
+ "epoch": 2.99,
3913
+ "learning_rate": 3.6196011306999237e-10,
3914
+ "loss": 0.0296,
3915
+ "step": 6460
3916
+ },
3917
+ {
3918
+ "epoch": 3.0,
3919
+ "learning_rate": 6.137070725165117e-11,
3920
+ "loss": 0.0346,
3921
+ "step": 6470
3922
+ },
3923
+ {
3924
+ "epoch": 3.0,
3925
+ "eval_em": 0.6384,
3926
+ "eval_em_ic": 0.9334,
3927
+ "eval_f1": 0.8248,
3928
+ "eval_gen_len": 39.5298,
3929
+ "eval_levinstein_ratio": 0.9955,
3930
+ "eval_loss": 0.04924384132027626,
3931
+ "eval_precision": 0.9141,
3932
+ "eval_recall": 0.8575,
3933
+ "eval_runtime": 165.9228,
3934
+ "eval_samples_per_second": 10.318,
3935
+ "eval_steps_per_second": 0.163,
3936
+ "step": 6477
3937
+ },
3938
+ {
3939
+ "epoch": 3.0,
3940
+ "step": 6477,
3941
+ "total_flos": 4.332530652023808e+16,
3942
+ "train_loss": 0.04666397547913275,
3943
+ "train_runtime": 1704.3592,
3944
+ "train_samples_per_second": 243.156,
3945
+ "train_steps_per_second": 3.8
3946
+ }
3947
+ ],
3948
+ "logging_steps": 10,
3949
+ "max_steps": 6477,
3950
+ "num_train_epochs": 3,
3951
+ "save_steps": 500,
3952
+ "total_flos": 4.332530652023808e+16,
3953
+ "trial_name": null,
3954
+ "trial_params": null
3955
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321429d5dff9029ec3df0d255a189e657bcfe66b81c4f1af3a72daa77c778ef5
3
+ size 4792