longcld commited on
Commit
b99e558
1 Parent(s): 63dac24
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<sep>": 250100, "<hl>": 250101}
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "n_positions": 512,
19
+ "num_decoder_layers": 6,
20
+ "num_heads": 8,
21
+ "num_layers": 6,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_num_buckets": 32,
25
+ "task_specific_params": {
26
+ "summarization": {
27
+ "early_stopping": true,
28
+ "length_penalty": 2.0,
29
+ "max_length": 200,
30
+ "min_length": 30,
31
+ "no_repeat_ngram_size": 3,
32
+ "num_beams": 4,
33
+ "prefix": "summarize: "
34
+ },
35
+ "translation_en_to_de": {
36
+ "early_stopping": true,
37
+ "max_length": 300,
38
+ "num_beams": 4,
39
+ "prefix": "translate English to German: "
40
+ },
41
+ "translation_en_to_fr": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to French: "
46
+ },
47
+ "translation_en_to_ro": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to Romanian: "
52
+ }
53
+ },
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.10.0",
56
+ "use_cache": true,
57
+ "vocab_size": 250102
58
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9f6fe010e512320a90ce220ed55a10ff624f259e8a75c32268b9132a34e934
3
+ size 352532601
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e576da7e6d3188bac283997ec40b96be395c180937d3e0cd64a81c475eee7f5a
3
+ size 688496379
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4137b71a9c6c90a0b8880aa5775cd23b0f08ddb88acac61c8656a0072ea5157c
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4fc6a6f383126201b9ed524a41f33bc30e031454336d5411887b80a7f125f0c
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "C:\\Users\\hydra/.cache\\huggingface\\transformers\\bde22e2f08347211bf47b72fb4730b4b9a2e3323a6a1254932cf0fb969eb18cd.b02fba13e4584f40329b20be0bad88c2ef97b5fda7d9f4f69b1cb3a620568a86", "tokenizer_file": null, "name_or_path": "longcld/t5_small_qg_ae_hl", "tokenizer_class": "T5Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,3526 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.3538515843492895,
5
+ "global_step": 58500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 9.989138698816118e-05,
13
+ "loss": 9.1158,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 9.978277397632236e-05,
19
+ "loss": 5.8307,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 9.967416096448356e-05,
25
+ "loss": 5.4251,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 9.956554795264474e-05,
31
+ "loss": 5.2931,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.05,
36
+ "learning_rate": 9.945693494080592e-05,
37
+ "loss": 5.0326,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 9.93483219289671e-05,
43
+ "loss": 4.8397,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.08,
48
+ "learning_rate": 9.923970891712828e-05,
49
+ "loss": 4.9379,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.09,
54
+ "learning_rate": 9.913109590528946e-05,
55
+ "loss": 4.6978,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.1,
60
+ "learning_rate": 9.902248289345064e-05,
61
+ "loss": 4.7727,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.11,
66
+ "learning_rate": 9.891386988161182e-05,
67
+ "loss": 4.5856,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.12,
72
+ "learning_rate": 9.8805256869773e-05,
73
+ "loss": 4.5636,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.13,
78
+ "learning_rate": 9.869664385793419e-05,
79
+ "loss": 4.4165,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.14,
84
+ "learning_rate": 9.858803084609537e-05,
85
+ "loss": 4.4187,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.15,
90
+ "learning_rate": 9.847941783425655e-05,
91
+ "loss": 4.3553,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.16,
96
+ "learning_rate": 9.837080482241773e-05,
97
+ "loss": 4.3312,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.17,
102
+ "learning_rate": 9.826219181057891e-05,
103
+ "loss": 4.3841,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.18,
108
+ "learning_rate": 9.81535787987401e-05,
109
+ "loss": 4.3428,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.2,
114
+ "learning_rate": 9.804496578690128e-05,
115
+ "loss": 4.3044,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.21,
120
+ "learning_rate": 9.793635277506245e-05,
121
+ "loss": 4.2581,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.22,
126
+ "learning_rate": 9.782773976322363e-05,
127
+ "loss": 4.1639,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.23,
132
+ "learning_rate": 9.771912675138481e-05,
133
+ "loss": 4.231,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.24,
138
+ "learning_rate": 9.7610513739546e-05,
139
+ "loss": 4.1087,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.25,
144
+ "learning_rate": 9.750190072770718e-05,
145
+ "loss": 4.2166,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.26,
150
+ "learning_rate": 9.739328771586836e-05,
151
+ "loss": 4.0581,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.27,
156
+ "learning_rate": 9.728467470402954e-05,
157
+ "loss": 4.0475,
158
+ "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.28,
162
+ "learning_rate": 9.717606169219074e-05,
163
+ "loss": 4.0477,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.29,
168
+ "learning_rate": 9.706744868035192e-05,
169
+ "loss": 4.2303,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.3,
174
+ "learning_rate": 9.69588356685131e-05,
175
+ "loss": 4.0649,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.31,
180
+ "learning_rate": 9.685022265667428e-05,
181
+ "loss": 4.0515,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.33,
186
+ "learning_rate": 9.674160964483546e-05,
187
+ "loss": 4.0151,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.34,
192
+ "learning_rate": 9.663299663299664e-05,
193
+ "loss": 3.9701,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.35,
198
+ "learning_rate": 9.652438362115782e-05,
199
+ "loss": 3.8968,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.36,
204
+ "learning_rate": 9.6415770609319e-05,
205
+ "loss": 4.0167,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.37,
210
+ "learning_rate": 9.630715759748018e-05,
211
+ "loss": 4.0087,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.38,
216
+ "learning_rate": 9.619854458564136e-05,
217
+ "loss": 4.0071,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.39,
222
+ "learning_rate": 9.608993157380255e-05,
223
+ "loss": 4.0202,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.4,
228
+ "learning_rate": 9.598131856196373e-05,
229
+ "loss": 4.069,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.41,
234
+ "learning_rate": 9.587270555012491e-05,
235
+ "loss": 3.9612,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.42,
240
+ "learning_rate": 9.576409253828609e-05,
241
+ "loss": 3.8818,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.43,
246
+ "learning_rate": 9.565547952644728e-05,
247
+ "loss": 3.9479,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.45,
252
+ "learning_rate": 9.554686651460846e-05,
253
+ "loss": 3.8681,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.46,
258
+ "learning_rate": 9.543825350276964e-05,
259
+ "loss": 3.8267,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.47,
264
+ "learning_rate": 9.532964049093082e-05,
265
+ "loss": 3.9206,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.48,
270
+ "learning_rate": 9.5221027479092e-05,
271
+ "loss": 3.8918,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.49,
276
+ "learning_rate": 9.511241446725318e-05,
277
+ "loss": 3.7453,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.5,
282
+ "learning_rate": 9.500380145541436e-05,
283
+ "loss": 3.8368,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 0.51,
288
+ "learning_rate": 9.489518844357554e-05,
289
+ "loss": 3.8248,
290
+ "step": 4700
291
+ },
292
+ {
293
+ "epoch": 0.52,
294
+ "learning_rate": 9.478657543173672e-05,
295
+ "loss": 3.8242,
296
+ "step": 4800
297
+ },
298
+ {
299
+ "epoch": 0.53,
300
+ "learning_rate": 9.46779624198979e-05,
301
+ "loss": 3.8506,
302
+ "step": 4900
303
+ },
304
+ {
305
+ "epoch": 0.54,
306
+ "learning_rate": 9.45693494080591e-05,
307
+ "loss": 3.878,
308
+ "step": 5000
309
+ },
310
+ {
311
+ "epoch": 0.55,
312
+ "learning_rate": 9.446073639622027e-05,
313
+ "loss": 3.7932,
314
+ "step": 5100
315
+ },
316
+ {
317
+ "epoch": 0.56,
318
+ "learning_rate": 9.435212338438145e-05,
319
+ "loss": 3.8755,
320
+ "step": 5200
321
+ },
322
+ {
323
+ "epoch": 0.58,
324
+ "learning_rate": 9.424351037254263e-05,
325
+ "loss": 3.7838,
326
+ "step": 5300
327
+ },
328
+ {
329
+ "epoch": 0.59,
330
+ "learning_rate": 9.413489736070383e-05,
331
+ "loss": 3.856,
332
+ "step": 5400
333
+ },
334
+ {
335
+ "epoch": 0.6,
336
+ "learning_rate": 9.402628434886501e-05,
337
+ "loss": 3.6716,
338
+ "step": 5500
339
+ },
340
+ {
341
+ "epoch": 0.61,
342
+ "learning_rate": 9.391767133702617e-05,
343
+ "loss": 3.7467,
344
+ "step": 5600
345
+ },
346
+ {
347
+ "epoch": 0.62,
348
+ "learning_rate": 9.380905832518735e-05,
349
+ "loss": 3.6716,
350
+ "step": 5700
351
+ },
352
+ {
353
+ "epoch": 0.63,
354
+ "learning_rate": 9.370044531334853e-05,
355
+ "loss": 3.6479,
356
+ "step": 5800
357
+ },
358
+ {
359
+ "epoch": 0.64,
360
+ "learning_rate": 9.359183230150973e-05,
361
+ "loss": 3.6937,
362
+ "step": 5900
363
+ },
364
+ {
365
+ "epoch": 0.65,
366
+ "learning_rate": 9.348321928967091e-05,
367
+ "loss": 3.7943,
368
+ "step": 6000
369
+ },
370
+ {
371
+ "epoch": 0.66,
372
+ "learning_rate": 9.337460627783209e-05,
373
+ "loss": 3.6678,
374
+ "step": 6100
375
+ },
376
+ {
377
+ "epoch": 0.67,
378
+ "learning_rate": 9.326599326599327e-05,
379
+ "loss": 3.6824,
380
+ "step": 6200
381
+ },
382
+ {
383
+ "epoch": 0.68,
384
+ "learning_rate": 9.315738025415445e-05,
385
+ "loss": 3.6794,
386
+ "step": 6300
387
+ },
388
+ {
389
+ "epoch": 0.7,
390
+ "learning_rate": 9.304876724231564e-05,
391
+ "loss": 3.7675,
392
+ "step": 6400
393
+ },
394
+ {
395
+ "epoch": 0.71,
396
+ "learning_rate": 9.294015423047682e-05,
397
+ "loss": 3.6341,
398
+ "step": 6500
399
+ },
400
+ {
401
+ "epoch": 0.72,
402
+ "learning_rate": 9.2831541218638e-05,
403
+ "loss": 3.6805,
404
+ "step": 6600
405
+ },
406
+ {
407
+ "epoch": 0.73,
408
+ "learning_rate": 9.272292820679918e-05,
409
+ "loss": 3.6479,
410
+ "step": 6700
411
+ },
412
+ {
413
+ "epoch": 0.74,
414
+ "learning_rate": 9.261431519496036e-05,
415
+ "loss": 3.6145,
416
+ "step": 6800
417
+ },
418
+ {
419
+ "epoch": 0.75,
420
+ "learning_rate": 9.250570218312154e-05,
421
+ "loss": 3.5535,
422
+ "step": 6900
423
+ },
424
+ {
425
+ "epoch": 0.76,
426
+ "learning_rate": 9.239708917128272e-05,
427
+ "loss": 3.6772,
428
+ "step": 7000
429
+ },
430
+ {
431
+ "epoch": 0.77,
432
+ "learning_rate": 9.22884761594439e-05,
433
+ "loss": 3.6542,
434
+ "step": 7100
435
+ },
436
+ {
437
+ "epoch": 0.78,
438
+ "learning_rate": 9.217986314760508e-05,
439
+ "loss": 3.5783,
440
+ "step": 7200
441
+ },
442
+ {
443
+ "epoch": 0.79,
444
+ "learning_rate": 9.207125013576627e-05,
445
+ "loss": 3.5812,
446
+ "step": 7300
447
+ },
448
+ {
449
+ "epoch": 0.8,
450
+ "learning_rate": 9.196263712392745e-05,
451
+ "loss": 3.5677,
452
+ "step": 7400
453
+ },
454
+ {
455
+ "epoch": 0.81,
456
+ "learning_rate": 9.185402411208863e-05,
457
+ "loss": 3.5258,
458
+ "step": 7500
459
+ },
460
+ {
461
+ "epoch": 0.83,
462
+ "learning_rate": 9.174541110024981e-05,
463
+ "loss": 3.618,
464
+ "step": 7600
465
+ },
466
+ {
467
+ "epoch": 0.84,
468
+ "learning_rate": 9.163679808841099e-05,
469
+ "loss": 3.7178,
470
+ "step": 7700
471
+ },
472
+ {
473
+ "epoch": 0.85,
474
+ "learning_rate": 9.152818507657219e-05,
475
+ "loss": 3.6502,
476
+ "step": 7800
477
+ },
478
+ {
479
+ "epoch": 0.86,
480
+ "learning_rate": 9.141957206473337e-05,
481
+ "loss": 3.6745,
482
+ "step": 7900
483
+ },
484
+ {
485
+ "epoch": 0.87,
486
+ "learning_rate": 9.131095905289455e-05,
487
+ "loss": 3.6149,
488
+ "step": 8000
489
+ },
490
+ {
491
+ "epoch": 0.88,
492
+ "learning_rate": 9.120234604105573e-05,
493
+ "loss": 3.5411,
494
+ "step": 8100
495
+ },
496
+ {
497
+ "epoch": 0.89,
498
+ "learning_rate": 9.10937330292169e-05,
499
+ "loss": 3.4925,
500
+ "step": 8200
501
+ },
502
+ {
503
+ "epoch": 0.9,
504
+ "learning_rate": 9.098512001737809e-05,
505
+ "loss": 3.575,
506
+ "step": 8300
507
+ },
508
+ {
509
+ "epoch": 0.91,
510
+ "learning_rate": 9.087650700553927e-05,
511
+ "loss": 3.4702,
512
+ "step": 8400
513
+ },
514
+ {
515
+ "epoch": 0.92,
516
+ "learning_rate": 9.076789399370045e-05,
517
+ "loss": 3.5782,
518
+ "step": 8500
519
+ },
520
+ {
521
+ "epoch": 0.93,
522
+ "learning_rate": 9.065928098186163e-05,
523
+ "loss": 3.6253,
524
+ "step": 8600
525
+ },
526
+ {
527
+ "epoch": 0.94,
528
+ "learning_rate": 9.055066797002282e-05,
529
+ "loss": 3.475,
530
+ "step": 8700
531
+ },
532
+ {
533
+ "epoch": 0.96,
534
+ "learning_rate": 9.0442054958184e-05,
535
+ "loss": 3.5008,
536
+ "step": 8800
537
+ },
538
+ {
539
+ "epoch": 0.97,
540
+ "learning_rate": 9.033344194634518e-05,
541
+ "loss": 3.5272,
542
+ "step": 8900
543
+ },
544
+ {
545
+ "epoch": 0.98,
546
+ "learning_rate": 9.022482893450636e-05,
547
+ "loss": 3.5002,
548
+ "step": 9000
549
+ },
550
+ {
551
+ "epoch": 0.99,
552
+ "learning_rate": 9.011621592266754e-05,
553
+ "loss": 3.611,
554
+ "step": 9100
555
+ },
556
+ {
557
+ "epoch": 1.0,
558
+ "learning_rate": 9.000760291082873e-05,
559
+ "loss": 3.607,
560
+ "step": 9200
561
+ },
562
+ {
563
+ "epoch": 1.01,
564
+ "learning_rate": 8.98989898989899e-05,
565
+ "loss": 3.494,
566
+ "step": 9300
567
+ },
568
+ {
569
+ "epoch": 1.02,
570
+ "learning_rate": 8.979037688715108e-05,
571
+ "loss": 3.542,
572
+ "step": 9400
573
+ },
574
+ {
575
+ "epoch": 1.03,
576
+ "learning_rate": 8.968176387531226e-05,
577
+ "loss": 3.468,
578
+ "step": 9500
579
+ },
580
+ {
581
+ "epoch": 1.04,
582
+ "learning_rate": 8.957315086347344e-05,
583
+ "loss": 3.3716,
584
+ "step": 9600
585
+ },
586
+ {
587
+ "epoch": 1.05,
588
+ "learning_rate": 8.946453785163463e-05,
589
+ "loss": 3.593,
590
+ "step": 9700
591
+ },
592
+ {
593
+ "epoch": 1.06,
594
+ "learning_rate": 8.935592483979581e-05,
595
+ "loss": 3.3818,
596
+ "step": 9800
597
+ },
598
+ {
599
+ "epoch": 1.08,
600
+ "learning_rate": 8.924731182795699e-05,
601
+ "loss": 3.3353,
602
+ "step": 9900
603
+ },
604
+ {
605
+ "epoch": 1.09,
606
+ "learning_rate": 8.913869881611817e-05,
607
+ "loss": 3.4241,
608
+ "step": 10000
609
+ },
610
+ {
611
+ "epoch": 1.1,
612
+ "learning_rate": 8.903008580427936e-05,
613
+ "loss": 3.507,
614
+ "step": 10100
615
+ },
616
+ {
617
+ "epoch": 1.11,
618
+ "learning_rate": 8.892147279244054e-05,
619
+ "loss": 3.4623,
620
+ "step": 10200
621
+ },
622
+ {
623
+ "epoch": 1.12,
624
+ "learning_rate": 8.881285978060172e-05,
625
+ "loss": 3.443,
626
+ "step": 10300
627
+ },
628
+ {
629
+ "epoch": 1.13,
630
+ "learning_rate": 8.87042467687629e-05,
631
+ "loss": 3.4692,
632
+ "step": 10400
633
+ },
634
+ {
635
+ "epoch": 1.14,
636
+ "learning_rate": 8.859563375692408e-05,
637
+ "loss": 3.424,
638
+ "step": 10500
639
+ },
640
+ {
641
+ "epoch": 1.15,
642
+ "learning_rate": 8.848702074508526e-05,
643
+ "loss": 3.3139,
644
+ "step": 10600
645
+ },
646
+ {
647
+ "epoch": 1.16,
648
+ "learning_rate": 8.837840773324644e-05,
649
+ "loss": 3.3319,
650
+ "step": 10700
651
+ },
652
+ {
653
+ "epoch": 1.17,
654
+ "learning_rate": 8.826979472140762e-05,
655
+ "loss": 3.5363,
656
+ "step": 10800
657
+ },
658
+ {
659
+ "epoch": 1.18,
660
+ "learning_rate": 8.81611817095688e-05,
661
+ "loss": 3.4598,
662
+ "step": 10900
663
+ },
664
+ {
665
+ "epoch": 1.19,
666
+ "learning_rate": 8.805256869772998e-05,
667
+ "loss": 3.4883,
668
+ "step": 11000
669
+ },
670
+ {
671
+ "epoch": 1.21,
672
+ "learning_rate": 8.794395568589118e-05,
673
+ "loss": 3.2751,
674
+ "step": 11100
675
+ },
676
+ {
677
+ "epoch": 1.22,
678
+ "learning_rate": 8.783534267405236e-05,
679
+ "loss": 3.3685,
680
+ "step": 11200
681
+ },
682
+ {
683
+ "epoch": 1.23,
684
+ "learning_rate": 8.772672966221354e-05,
685
+ "loss": 3.4111,
686
+ "step": 11300
687
+ },
688
+ {
689
+ "epoch": 1.24,
690
+ "learning_rate": 8.761811665037472e-05,
691
+ "loss": 3.3984,
692
+ "step": 11400
693
+ },
694
+ {
695
+ "epoch": 1.25,
696
+ "learning_rate": 8.750950363853591e-05,
697
+ "loss": 3.4246,
698
+ "step": 11500
699
+ },
700
+ {
701
+ "epoch": 1.26,
702
+ "learning_rate": 8.740089062669709e-05,
703
+ "loss": 3.2751,
704
+ "step": 11600
705
+ },
706
+ {
707
+ "epoch": 1.27,
708
+ "learning_rate": 8.729227761485827e-05,
709
+ "loss": 3.4855,
710
+ "step": 11700
711
+ },
712
+ {
713
+ "epoch": 1.28,
714
+ "learning_rate": 8.718366460301945e-05,
715
+ "loss": 3.4712,
716
+ "step": 11800
717
+ },
718
+ {
719
+ "epoch": 1.29,
720
+ "learning_rate": 8.707505159118062e-05,
721
+ "loss": 3.3221,
722
+ "step": 11900
723
+ },
724
+ {
725
+ "epoch": 1.3,
726
+ "learning_rate": 8.696643857934181e-05,
727
+ "loss": 3.35,
728
+ "step": 12000
729
+ },
730
+ {
731
+ "epoch": 1.31,
732
+ "learning_rate": 8.685782556750299e-05,
733
+ "loss": 3.3502,
734
+ "step": 12100
735
+ },
736
+ {
737
+ "epoch": 1.33,
738
+ "learning_rate": 8.674921255566417e-05,
739
+ "loss": 3.2973,
740
+ "step": 12200
741
+ },
742
+ {
743
+ "epoch": 1.34,
744
+ "learning_rate": 8.664059954382535e-05,
745
+ "loss": 3.3982,
746
+ "step": 12300
747
+ },
748
+ {
749
+ "epoch": 1.35,
750
+ "learning_rate": 8.653198653198653e-05,
751
+ "loss": 3.3566,
752
+ "step": 12400
753
+ },
754
+ {
755
+ "epoch": 1.36,
756
+ "learning_rate": 8.642337352014772e-05,
757
+ "loss": 3.3709,
758
+ "step": 12500
759
+ },
760
+ {
761
+ "epoch": 1.37,
762
+ "learning_rate": 8.63147605083089e-05,
763
+ "loss": 3.4209,
764
+ "step": 12600
765
+ },
766
+ {
767
+ "epoch": 1.38,
768
+ "learning_rate": 8.620614749647008e-05,
769
+ "loss": 3.2738,
770
+ "step": 12700
771
+ },
772
+ {
773
+ "epoch": 1.39,
774
+ "learning_rate": 8.609753448463126e-05,
775
+ "loss": 3.4105,
776
+ "step": 12800
777
+ },
778
+ {
779
+ "epoch": 1.4,
780
+ "learning_rate": 8.598892147279246e-05,
781
+ "loss": 3.2289,
782
+ "step": 12900
783
+ },
784
+ {
785
+ "epoch": 1.41,
786
+ "learning_rate": 8.588030846095362e-05,
787
+ "loss": 3.2912,
788
+ "step": 13000
789
+ },
790
+ {
791
+ "epoch": 1.42,
792
+ "learning_rate": 8.57716954491148e-05,
793
+ "loss": 3.3281,
794
+ "step": 13100
795
+ },
796
+ {
797
+ "epoch": 1.43,
798
+ "learning_rate": 8.566308243727598e-05,
799
+ "loss": 3.4349,
800
+ "step": 13200
801
+ },
802
+ {
803
+ "epoch": 1.44,
804
+ "learning_rate": 8.555446942543716e-05,
805
+ "loss": 3.2977,
806
+ "step": 13300
807
+ },
808
+ {
809
+ "epoch": 1.46,
810
+ "learning_rate": 8.544585641359836e-05,
811
+ "loss": 3.4786,
812
+ "step": 13400
813
+ },
814
+ {
815
+ "epoch": 1.47,
816
+ "learning_rate": 8.533724340175954e-05,
817
+ "loss": 3.2424,
818
+ "step": 13500
819
+ },
820
+ {
821
+ "epoch": 1.48,
822
+ "learning_rate": 8.522863038992072e-05,
823
+ "loss": 3.2443,
824
+ "step": 13600
825
+ },
826
+ {
827
+ "epoch": 1.49,
828
+ "learning_rate": 8.51200173780819e-05,
829
+ "loss": 3.3818,
830
+ "step": 13700
831
+ },
832
+ {
833
+ "epoch": 1.5,
834
+ "learning_rate": 8.501140436624308e-05,
835
+ "loss": 3.3809,
836
+ "step": 13800
837
+ },
838
+ {
839
+ "epoch": 1.51,
840
+ "learning_rate": 8.490279135440427e-05,
841
+ "loss": 3.2922,
842
+ "step": 13900
843
+ },
844
+ {
845
+ "epoch": 1.52,
846
+ "learning_rate": 8.479417834256545e-05,
847
+ "loss": 3.2152,
848
+ "step": 14000
849
+ },
850
+ {
851
+ "epoch": 1.53,
852
+ "learning_rate": 8.468556533072663e-05,
853
+ "loss": 3.3144,
854
+ "step": 14100
855
+ },
856
+ {
857
+ "epoch": 1.54,
858
+ "learning_rate": 8.457695231888781e-05,
859
+ "loss": 3.266,
860
+ "step": 14200
861
+ },
862
+ {
863
+ "epoch": 1.55,
864
+ "learning_rate": 8.446833930704899e-05,
865
+ "loss": 3.3113,
866
+ "step": 14300
867
+ },
868
+ {
869
+ "epoch": 1.56,
870
+ "learning_rate": 8.435972629521017e-05,
871
+ "loss": 3.2186,
872
+ "step": 14400
873
+ },
874
+ {
875
+ "epoch": 1.57,
876
+ "learning_rate": 8.425111328337135e-05,
877
+ "loss": 3.2034,
878
+ "step": 14500
879
+ },
880
+ {
881
+ "epoch": 1.59,
882
+ "learning_rate": 8.414250027153253e-05,
883
+ "loss": 3.2229,
884
+ "step": 14600
885
+ },
886
+ {
887
+ "epoch": 1.6,
888
+ "learning_rate": 8.403388725969371e-05,
889
+ "loss": 3.2563,
890
+ "step": 14700
891
+ },
892
+ {
893
+ "epoch": 1.61,
894
+ "learning_rate": 8.39252742478549e-05,
895
+ "loss": 3.2689,
896
+ "step": 14800
897
+ },
898
+ {
899
+ "epoch": 1.62,
900
+ "learning_rate": 8.381666123601608e-05,
901
+ "loss": 3.1917,
902
+ "step": 14900
903
+ },
904
+ {
905
+ "epoch": 1.63,
906
+ "learning_rate": 8.370804822417726e-05,
907
+ "loss": 3.3305,
908
+ "step": 15000
909
+ },
910
+ {
911
+ "epoch": 1.64,
912
+ "learning_rate": 8.359943521233844e-05,
913
+ "loss": 3.2577,
914
+ "step": 15100
915
+ },
916
+ {
917
+ "epoch": 1.65,
918
+ "learning_rate": 8.349082220049962e-05,
919
+ "loss": 3.3375,
920
+ "step": 15200
921
+ },
922
+ {
923
+ "epoch": 1.66,
924
+ "learning_rate": 8.338220918866081e-05,
925
+ "loss": 3.2056,
926
+ "step": 15300
927
+ },
928
+ {
929
+ "epoch": 1.67,
930
+ "learning_rate": 8.3273596176822e-05,
931
+ "loss": 3.2336,
932
+ "step": 15400
933
+ },
934
+ {
935
+ "epoch": 1.68,
936
+ "learning_rate": 8.316498316498317e-05,
937
+ "loss": 3.2219,
938
+ "step": 15500
939
+ },
940
+ {
941
+ "epoch": 1.69,
942
+ "learning_rate": 8.305637015314434e-05,
943
+ "loss": 3.3085,
944
+ "step": 15600
945
+ },
946
+ {
947
+ "epoch": 1.71,
948
+ "learning_rate": 8.294775714130553e-05,
949
+ "loss": 3.2312,
950
+ "step": 15700
951
+ },
952
+ {
953
+ "epoch": 1.72,
954
+ "learning_rate": 8.283914412946671e-05,
955
+ "loss": 3.2054,
956
+ "step": 15800
957
+ },
958
+ {
959
+ "epoch": 1.73,
960
+ "learning_rate": 8.27305311176279e-05,
961
+ "loss": 3.3518,
962
+ "step": 15900
963
+ },
964
+ {
965
+ "epoch": 1.74,
966
+ "learning_rate": 8.262191810578907e-05,
967
+ "loss": 3.22,
968
+ "step": 16000
969
+ },
970
+ {
971
+ "epoch": 1.75,
972
+ "learning_rate": 8.251330509395025e-05,
973
+ "loss": 3.2564,
974
+ "step": 16100
975
+ },
976
+ {
977
+ "epoch": 1.76,
978
+ "learning_rate": 8.240469208211145e-05,
979
+ "loss": 3.181,
980
+ "step": 16200
981
+ },
982
+ {
983
+ "epoch": 1.77,
984
+ "learning_rate": 8.229607907027263e-05,
985
+ "loss": 3.3038,
986
+ "step": 16300
987
+ },
988
+ {
989
+ "epoch": 1.78,
990
+ "learning_rate": 8.218746605843381e-05,
991
+ "loss": 3.1689,
992
+ "step": 16400
993
+ },
994
+ {
995
+ "epoch": 1.79,
996
+ "learning_rate": 8.207885304659499e-05,
997
+ "loss": 3.2781,
998
+ "step": 16500
999
+ },
1000
+ {
1001
+ "epoch": 1.8,
1002
+ "learning_rate": 8.197024003475617e-05,
1003
+ "loss": 3.1925,
1004
+ "step": 16600
1005
+ },
1006
+ {
1007
+ "epoch": 1.81,
1008
+ "learning_rate": 8.186162702291735e-05,
1009
+ "loss": 3.2514,
1010
+ "step": 16700
1011
+ },
1012
+ {
1013
+ "epoch": 1.82,
1014
+ "learning_rate": 8.175301401107853e-05,
1015
+ "loss": 3.2324,
1016
+ "step": 16800
1017
+ },
1018
+ {
1019
+ "epoch": 1.84,
1020
+ "learning_rate": 8.16444009992397e-05,
1021
+ "loss": 3.1748,
1022
+ "step": 16900
1023
+ },
1024
+ {
1025
+ "epoch": 1.85,
1026
+ "learning_rate": 8.153578798740089e-05,
1027
+ "loss": 3.2089,
1028
+ "step": 17000
1029
+ },
1030
+ {
1031
+ "epoch": 1.86,
1032
+ "learning_rate": 8.142717497556208e-05,
1033
+ "loss": 3.156,
1034
+ "step": 17100
1035
+ },
1036
+ {
1037
+ "epoch": 1.87,
1038
+ "learning_rate": 8.131856196372326e-05,
1039
+ "loss": 3.2313,
1040
+ "step": 17200
1041
+ },
1042
+ {
1043
+ "epoch": 1.88,
1044
+ "learning_rate": 8.120994895188444e-05,
1045
+ "loss": 3.2406,
1046
+ "step": 17300
1047
+ },
1048
+ {
1049
+ "epoch": 1.89,
1050
+ "learning_rate": 8.110133594004562e-05,
1051
+ "loss": 3.2273,
1052
+ "step": 17400
1053
+ },
1054
+ {
1055
+ "epoch": 1.9,
1056
+ "learning_rate": 8.09927229282068e-05,
1057
+ "loss": 3.1781,
1058
+ "step": 17500
1059
+ },
1060
+ {
1061
+ "epoch": 1.91,
1062
+ "learning_rate": 8.088410991636799e-05,
1063
+ "loss": 3.1407,
1064
+ "step": 17600
1065
+ },
1066
+ {
1067
+ "epoch": 1.92,
1068
+ "learning_rate": 8.077549690452917e-05,
1069
+ "loss": 3.1266,
1070
+ "step": 17700
1071
+ },
1072
+ {
1073
+ "epoch": 1.93,
1074
+ "learning_rate": 8.066688389269035e-05,
1075
+ "loss": 3.1861,
1076
+ "step": 17800
1077
+ },
1078
+ {
1079
+ "epoch": 1.94,
1080
+ "learning_rate": 8.055827088085153e-05,
1081
+ "loss": 3.1604,
1082
+ "step": 17900
1083
+ },
1084
+ {
1085
+ "epoch": 1.96,
1086
+ "learning_rate": 8.044965786901271e-05,
1087
+ "loss": 3.1591,
1088
+ "step": 18000
1089
+ },
1090
+ {
1091
+ "epoch": 1.97,
1092
+ "learning_rate": 8.034104485717389e-05,
1093
+ "loss": 3.2045,
1094
+ "step": 18100
1095
+ },
1096
+ {
1097
+ "epoch": 1.98,
1098
+ "learning_rate": 8.023243184533507e-05,
1099
+ "loss": 3.1123,
1100
+ "step": 18200
1101
+ },
1102
+ {
1103
+ "epoch": 1.99,
1104
+ "learning_rate": 8.012381883349625e-05,
1105
+ "loss": 3.2466,
1106
+ "step": 18300
1107
+ },
1108
+ {
1109
+ "epoch": 2.0,
1110
+ "learning_rate": 8.001520582165743e-05,
1111
+ "loss": 3.2711,
1112
+ "step": 18400
1113
+ },
1114
+ {
1115
+ "epoch": 2.01,
1116
+ "learning_rate": 7.990659280981863e-05,
1117
+ "loss": 3.1771,
1118
+ "step": 18500
1119
+ },
1120
+ {
1121
+ "epoch": 2.02,
1122
+ "learning_rate": 7.97979797979798e-05,
1123
+ "loss": 3.1217,
1124
+ "step": 18600
1125
+ },
1126
+ {
1127
+ "epoch": 2.03,
1128
+ "learning_rate": 7.968936678614099e-05,
1129
+ "loss": 3.0909,
1130
+ "step": 18700
1131
+ },
1132
+ {
1133
+ "epoch": 2.04,
1134
+ "learning_rate": 7.958075377430217e-05,
1135
+ "loss": 3.0777,
1136
+ "step": 18800
1137
+ },
1138
+ {
1139
+ "epoch": 2.05,
1140
+ "learning_rate": 7.947214076246335e-05,
1141
+ "loss": 3.1697,
1142
+ "step": 18900
1143
+ },
1144
+ {
1145
+ "epoch": 2.06,
1146
+ "learning_rate": 7.936352775062454e-05,
1147
+ "loss": 3.1588,
1148
+ "step": 19000
1149
+ },
1150
+ {
1151
+ "epoch": 2.07,
1152
+ "learning_rate": 7.925491473878572e-05,
1153
+ "loss": 3.1334,
1154
+ "step": 19100
1155
+ },
1156
+ {
1157
+ "epoch": 2.09,
1158
+ "learning_rate": 7.91463017269469e-05,
1159
+ "loss": 3.1442,
1160
+ "step": 19200
1161
+ },
1162
+ {
1163
+ "epoch": 2.1,
1164
+ "learning_rate": 7.903768871510806e-05,
1165
+ "loss": 3.1633,
1166
+ "step": 19300
1167
+ },
1168
+ {
1169
+ "epoch": 2.11,
1170
+ "learning_rate": 7.892907570326924e-05,
1171
+ "loss": 3.1913,
1172
+ "step": 19400
1173
+ },
1174
+ {
1175
+ "epoch": 2.12,
1176
+ "learning_rate": 7.882046269143044e-05,
1177
+ "loss": 3.1455,
1178
+ "step": 19500
1179
+ },
1180
+ {
1181
+ "epoch": 2.13,
1182
+ "learning_rate": 7.871184967959162e-05,
1183
+ "loss": 3.155,
1184
+ "step": 19600
1185
+ },
1186
+ {
1187
+ "epoch": 2.14,
1188
+ "learning_rate": 7.86032366677528e-05,
1189
+ "loss": 3.2162,
1190
+ "step": 19700
1191
+ },
1192
+ {
1193
+ "epoch": 2.15,
1194
+ "learning_rate": 7.849462365591398e-05,
1195
+ "loss": 3.1831,
1196
+ "step": 19800
1197
+ },
1198
+ {
1199
+ "epoch": 2.16,
1200
+ "learning_rate": 7.838601064407516e-05,
1201
+ "loss": 3.1012,
1202
+ "step": 19900
1203
+ },
1204
+ {
1205
+ "epoch": 2.17,
1206
+ "learning_rate": 7.827739763223635e-05,
1207
+ "loss": 3.1624,
1208
+ "step": 20000
1209
+ },
1210
+ {
1211
+ "epoch": 2.18,
1212
+ "learning_rate": 7.816878462039753e-05,
1213
+ "loss": 3.1208,
1214
+ "step": 20100
1215
+ },
1216
+ {
1217
+ "epoch": 2.19,
1218
+ "learning_rate": 7.806017160855871e-05,
1219
+ "loss": 3.1124,
1220
+ "step": 20200
1221
+ },
1222
+ {
1223
+ "epoch": 2.2,
1224
+ "learning_rate": 7.795155859671989e-05,
1225
+ "loss": 3.125,
1226
+ "step": 20300
1227
+ },
1228
+ {
1229
+ "epoch": 2.22,
1230
+ "learning_rate": 7.784294558488107e-05,
1231
+ "loss": 3.1171,
1232
+ "step": 20400
1233
+ },
1234
+ {
1235
+ "epoch": 2.23,
1236
+ "learning_rate": 7.773433257304225e-05,
1237
+ "loss": 3.1837,
1238
+ "step": 20500
1239
+ },
1240
+ {
1241
+ "epoch": 2.24,
1242
+ "learning_rate": 7.762571956120343e-05,
1243
+ "loss": 3.1093,
1244
+ "step": 20600
1245
+ },
1246
+ {
1247
+ "epoch": 2.25,
1248
+ "learning_rate": 7.751710654936461e-05,
1249
+ "loss": 3.0628,
1250
+ "step": 20700
1251
+ },
1252
+ {
1253
+ "epoch": 2.26,
1254
+ "learning_rate": 7.740849353752579e-05,
1255
+ "loss": 3.0512,
1256
+ "step": 20800
1257
+ },
1258
+ {
1259
+ "epoch": 2.27,
1260
+ "learning_rate": 7.729988052568698e-05,
1261
+ "loss": 3.127,
1262
+ "step": 20900
1263
+ },
1264
+ {
1265
+ "epoch": 2.28,
1266
+ "learning_rate": 7.719126751384816e-05,
1267
+ "loss": 3.1499,
1268
+ "step": 21000
1269
+ },
1270
+ {
1271
+ "epoch": 2.29,
1272
+ "learning_rate": 7.708265450200934e-05,
1273
+ "loss": 3.069,
1274
+ "step": 21100
1275
+ },
1276
+ {
1277
+ "epoch": 2.3,
1278
+ "learning_rate": 7.697404149017052e-05,
1279
+ "loss": 3.206,
1280
+ "step": 21200
1281
+ },
1282
+ {
1283
+ "epoch": 2.31,
1284
+ "learning_rate": 7.68654284783317e-05,
1285
+ "loss": 3.0981,
1286
+ "step": 21300
1287
+ },
1288
+ {
1289
+ "epoch": 2.32,
1290
+ "learning_rate": 7.67568154664929e-05,
1291
+ "loss": 3.1826,
1292
+ "step": 21400
1293
+ },
1294
+ {
1295
+ "epoch": 2.34,
1296
+ "learning_rate": 7.664820245465408e-05,
1297
+ "loss": 3.1654,
1298
+ "step": 21500
1299
+ },
1300
+ {
1301
+ "epoch": 2.35,
1302
+ "learning_rate": 7.653958944281526e-05,
1303
+ "loss": 3.0237,
1304
+ "step": 21600
1305
+ },
1306
+ {
1307
+ "epoch": 2.36,
1308
+ "learning_rate": 7.643097643097644e-05,
1309
+ "loss": 3.1942,
1310
+ "step": 21700
1311
+ },
1312
+ {
1313
+ "epoch": 2.37,
1314
+ "learning_rate": 7.632236341913762e-05,
1315
+ "loss": 3.1073,
1316
+ "step": 21800
1317
+ },
1318
+ {
1319
+ "epoch": 2.38,
1320
+ "learning_rate": 7.62137504072988e-05,
1321
+ "loss": 3.1343,
1322
+ "step": 21900
1323
+ },
1324
+ {
1325
+ "epoch": 2.39,
1326
+ "learning_rate": 7.610513739545998e-05,
1327
+ "loss": 3.1203,
1328
+ "step": 22000
1329
+ },
1330
+ {
1331
+ "epoch": 2.4,
1332
+ "learning_rate": 7.599652438362116e-05,
1333
+ "loss": 3.1676,
1334
+ "step": 22100
1335
+ },
1336
+ {
1337
+ "epoch": 2.41,
1338
+ "learning_rate": 7.588791137178234e-05,
1339
+ "loss": 3.1682,
1340
+ "step": 22200
1341
+ },
1342
+ {
1343
+ "epoch": 2.42,
1344
+ "learning_rate": 7.577929835994353e-05,
1345
+ "loss": 3.0663,
1346
+ "step": 22300
1347
+ },
1348
+ {
1349
+ "epoch": 2.43,
1350
+ "learning_rate": 7.567068534810471e-05,
1351
+ "loss": 3.1309,
1352
+ "step": 22400
1353
+ },
1354
+ {
1355
+ "epoch": 2.44,
1356
+ "learning_rate": 7.556207233626589e-05,
1357
+ "loss": 3.0167,
1358
+ "step": 22500
1359
+ },
1360
+ {
1361
+ "epoch": 2.45,
1362
+ "learning_rate": 7.545345932442707e-05,
1363
+ "loss": 3.1367,
1364
+ "step": 22600
1365
+ },
1366
+ {
1367
+ "epoch": 2.47,
1368
+ "learning_rate": 7.534484631258825e-05,
1369
+ "loss": 3.1597,
1370
+ "step": 22700
1371
+ },
1372
+ {
1373
+ "epoch": 2.48,
1374
+ "learning_rate": 7.523623330074944e-05,
1375
+ "loss": 3.1616,
1376
+ "step": 22800
1377
+ },
1378
+ {
1379
+ "epoch": 2.49,
1380
+ "learning_rate": 7.512762028891062e-05,
1381
+ "loss": 3.0356,
1382
+ "step": 22900
1383
+ },
1384
+ {
1385
+ "epoch": 2.5,
1386
+ "learning_rate": 7.501900727707179e-05,
1387
+ "loss": 3.1821,
1388
+ "step": 23000
1389
+ },
1390
+ {
1391
+ "epoch": 2.51,
1392
+ "learning_rate": 7.491039426523297e-05,
1393
+ "loss": 3.0478,
1394
+ "step": 23100
1395
+ },
1396
+ {
1397
+ "epoch": 2.52,
1398
+ "learning_rate": 7.480178125339416e-05,
1399
+ "loss": 3.116,
1400
+ "step": 23200
1401
+ },
1402
+ {
1403
+ "epoch": 2.53,
1404
+ "learning_rate": 7.469316824155534e-05,
1405
+ "loss": 3.0147,
1406
+ "step": 23300
1407
+ },
1408
+ {
1409
+ "epoch": 2.54,
1410
+ "learning_rate": 7.458455522971652e-05,
1411
+ "loss": 3.1325,
1412
+ "step": 23400
1413
+ },
1414
+ {
1415
+ "epoch": 2.55,
1416
+ "learning_rate": 7.44759422178777e-05,
1417
+ "loss": 2.9355,
1418
+ "step": 23500
1419
+ },
1420
+ {
1421
+ "epoch": 2.56,
1422
+ "learning_rate": 7.436732920603888e-05,
1423
+ "loss": 3.1018,
1424
+ "step": 23600
1425
+ },
1426
+ {
1427
+ "epoch": 2.57,
1428
+ "learning_rate": 7.425871619420008e-05,
1429
+ "loss": 3.1251,
1430
+ "step": 23700
1431
+ },
1432
+ {
1433
+ "epoch": 2.58,
1434
+ "learning_rate": 7.415010318236126e-05,
1435
+ "loss": 3.0988,
1436
+ "step": 23800
1437
+ },
1438
+ {
1439
+ "epoch": 2.6,
1440
+ "learning_rate": 7.404149017052244e-05,
1441
+ "loss": 3.0469,
1442
+ "step": 23900
1443
+ },
1444
+ {
1445
+ "epoch": 2.61,
1446
+ "learning_rate": 7.393287715868362e-05,
1447
+ "loss": 3.0617,
1448
+ "step": 24000
1449
+ },
1450
+ {
1451
+ "epoch": 2.62,
1452
+ "learning_rate": 7.38242641468448e-05,
1453
+ "loss": 3.1484,
1454
+ "step": 24100
1455
+ },
1456
+ {
1457
+ "epoch": 2.63,
1458
+ "learning_rate": 7.371565113500597e-05,
1459
+ "loss": 3.015,
1460
+ "step": 24200
1461
+ },
1462
+ {
1463
+ "epoch": 2.64,
1464
+ "learning_rate": 7.360703812316715e-05,
1465
+ "loss": 3.1561,
1466
+ "step": 24300
1467
+ },
1468
+ {
1469
+ "epoch": 2.65,
1470
+ "learning_rate": 7.349842511132833e-05,
1471
+ "loss": 3.0644,
1472
+ "step": 24400
1473
+ },
1474
+ {
1475
+ "epoch": 2.66,
1476
+ "learning_rate": 7.338981209948951e-05,
1477
+ "loss": 3.017,
1478
+ "step": 24500
1479
+ },
1480
+ {
1481
+ "epoch": 2.67,
1482
+ "learning_rate": 7.328119908765071e-05,
1483
+ "loss": 3.0305,
1484
+ "step": 24600
1485
+ },
1486
+ {
1487
+ "epoch": 2.68,
1488
+ "learning_rate": 7.317258607581189e-05,
1489
+ "loss": 3.1057,
1490
+ "step": 24700
1491
+ },
1492
+ {
1493
+ "epoch": 2.69,
1494
+ "learning_rate": 7.306397306397307e-05,
1495
+ "loss": 3.0648,
1496
+ "step": 24800
1497
+ },
1498
+ {
1499
+ "epoch": 2.7,
1500
+ "learning_rate": 7.295536005213425e-05,
1501
+ "loss": 2.9583,
1502
+ "step": 24900
1503
+ },
1504
+ {
1505
+ "epoch": 2.72,
1506
+ "learning_rate": 7.284674704029543e-05,
1507
+ "loss": 3.0673,
1508
+ "step": 25000
1509
+ },
1510
+ {
1511
+ "epoch": 2.73,
1512
+ "learning_rate": 7.273813402845662e-05,
1513
+ "loss": 3.0524,
1514
+ "step": 25100
1515
+ },
1516
+ {
1517
+ "epoch": 2.74,
1518
+ "learning_rate": 7.26295210166178e-05,
1519
+ "loss": 3.0098,
1520
+ "step": 25200
1521
+ },
1522
+ {
1523
+ "epoch": 2.75,
1524
+ "learning_rate": 7.252090800477898e-05,
1525
+ "loss": 3.0,
1526
+ "step": 25300
1527
+ },
1528
+ {
1529
+ "epoch": 2.76,
1530
+ "learning_rate": 7.241229499294016e-05,
1531
+ "loss": 3.0914,
1532
+ "step": 25400
1533
+ },
1534
+ {
1535
+ "epoch": 2.77,
1536
+ "learning_rate": 7.230368198110134e-05,
1537
+ "loss": 3.0455,
1538
+ "step": 25500
1539
+ },
1540
+ {
1541
+ "epoch": 2.78,
1542
+ "learning_rate": 7.219506896926252e-05,
1543
+ "loss": 3.06,
1544
+ "step": 25600
1545
+ },
1546
+ {
1547
+ "epoch": 2.79,
1548
+ "learning_rate": 7.20864559574237e-05,
1549
+ "loss": 3.0307,
1550
+ "step": 25700
1551
+ },
1552
+ {
1553
+ "epoch": 2.8,
1554
+ "learning_rate": 7.197784294558488e-05,
1555
+ "loss": 3.0215,
1556
+ "step": 25800
1557
+ },
1558
+ {
1559
+ "epoch": 2.81,
1560
+ "learning_rate": 7.186922993374606e-05,
1561
+ "loss": 3.0389,
1562
+ "step": 25900
1563
+ },
1564
+ {
1565
+ "epoch": 2.82,
1566
+ "learning_rate": 7.176061692190725e-05,
1567
+ "loss": 3.0078,
1568
+ "step": 26000
1569
+ },
1570
+ {
1571
+ "epoch": 2.83,
1572
+ "learning_rate": 7.165200391006843e-05,
1573
+ "loss": 2.9979,
1574
+ "step": 26100
1575
+ },
1576
+ {
1577
+ "epoch": 2.85,
1578
+ "learning_rate": 7.154339089822961e-05,
1579
+ "loss": 3.0612,
1580
+ "step": 26200
1581
+ },
1582
+ {
1583
+ "epoch": 2.86,
1584
+ "learning_rate": 7.14347778863908e-05,
1585
+ "loss": 3.0747,
1586
+ "step": 26300
1587
+ },
1588
+ {
1589
+ "epoch": 2.87,
1590
+ "learning_rate": 7.132616487455197e-05,
1591
+ "loss": 3.0439,
1592
+ "step": 26400
1593
+ },
1594
+ {
1595
+ "epoch": 2.88,
1596
+ "learning_rate": 7.121755186271317e-05,
1597
+ "loss": 3.0511,
1598
+ "step": 26500
1599
+ },
1600
+ {
1601
+ "epoch": 2.89,
1602
+ "learning_rate": 7.110893885087435e-05,
1603
+ "loss": 3.0268,
1604
+ "step": 26600
1605
+ },
1606
+ {
1607
+ "epoch": 2.9,
1608
+ "learning_rate": 7.100032583903551e-05,
1609
+ "loss": 3.0712,
1610
+ "step": 26700
1611
+ },
1612
+ {
1613
+ "epoch": 2.91,
1614
+ "learning_rate": 7.089171282719669e-05,
1615
+ "loss": 3.0466,
1616
+ "step": 26800
1617
+ },
1618
+ {
1619
+ "epoch": 2.92,
1620
+ "learning_rate": 7.078309981535787e-05,
1621
+ "loss": 3.0257,
1622
+ "step": 26900
1623
+ },
1624
+ {
1625
+ "epoch": 2.93,
1626
+ "learning_rate": 7.067448680351907e-05,
1627
+ "loss": 3.0384,
1628
+ "step": 27000
1629
+ },
1630
+ {
1631
+ "epoch": 2.94,
1632
+ "learning_rate": 7.056587379168025e-05,
1633
+ "loss": 2.9557,
1634
+ "step": 27100
1635
+ },
1636
+ {
1637
+ "epoch": 2.95,
1638
+ "learning_rate": 7.045726077984143e-05,
1639
+ "loss": 3.0617,
1640
+ "step": 27200
1641
+ },
1642
+ {
1643
+ "epoch": 2.97,
1644
+ "learning_rate": 7.03486477680026e-05,
1645
+ "loss": 3.0958,
1646
+ "step": 27300
1647
+ },
1648
+ {
1649
+ "epoch": 2.98,
1650
+ "learning_rate": 7.02400347561638e-05,
1651
+ "loss": 3.0421,
1652
+ "step": 27400
1653
+ },
1654
+ {
1655
+ "epoch": 2.99,
1656
+ "learning_rate": 7.013142174432498e-05,
1657
+ "loss": 3.0083,
1658
+ "step": 27500
1659
+ },
1660
+ {
1661
+ "epoch": 3.0,
1662
+ "learning_rate": 7.002280873248616e-05,
1663
+ "loss": 3.0199,
1664
+ "step": 27600
1665
+ },
1666
+ {
1667
+ "epoch": 3.01,
1668
+ "learning_rate": 6.991419572064734e-05,
1669
+ "loss": 3.0205,
1670
+ "step": 27700
1671
+ },
1672
+ {
1673
+ "epoch": 3.02,
1674
+ "learning_rate": 6.980558270880852e-05,
1675
+ "loss": 3.0701,
1676
+ "step": 27800
1677
+ },
1678
+ {
1679
+ "epoch": 3.03,
1680
+ "learning_rate": 6.96969696969697e-05,
1681
+ "loss": 2.8957,
1682
+ "step": 27900
1683
+ },
1684
+ {
1685
+ "epoch": 3.04,
1686
+ "learning_rate": 6.958835668513088e-05,
1687
+ "loss": 2.9442,
1688
+ "step": 28000
1689
+ },
1690
+ {
1691
+ "epoch": 3.05,
1692
+ "learning_rate": 6.947974367329206e-05,
1693
+ "loss": 2.9768,
1694
+ "step": 28100
1695
+ },
1696
+ {
1697
+ "epoch": 3.06,
1698
+ "learning_rate": 6.937113066145324e-05,
1699
+ "loss": 3.0057,
1700
+ "step": 28200
1701
+ },
1702
+ {
1703
+ "epoch": 3.07,
1704
+ "learning_rate": 6.926251764961442e-05,
1705
+ "loss": 2.9816,
1706
+ "step": 28300
1707
+ },
1708
+ {
1709
+ "epoch": 3.08,
1710
+ "learning_rate": 6.915390463777561e-05,
1711
+ "loss": 2.9866,
1712
+ "step": 28400
1713
+ },
1714
+ {
1715
+ "epoch": 3.1,
1716
+ "learning_rate": 6.904529162593679e-05,
1717
+ "loss": 3.056,
1718
+ "step": 28500
1719
+ },
1720
+ {
1721
+ "epoch": 3.11,
1722
+ "learning_rate": 6.893667861409797e-05,
1723
+ "loss": 2.9423,
1724
+ "step": 28600
1725
+ },
1726
+ {
1727
+ "epoch": 3.12,
1728
+ "learning_rate": 6.882806560225915e-05,
1729
+ "loss": 2.9433,
1730
+ "step": 28700
1731
+ },
1732
+ {
1733
+ "epoch": 3.13,
1734
+ "learning_rate": 6.871945259042033e-05,
1735
+ "loss": 2.9175,
1736
+ "step": 28800
1737
+ },
1738
+ {
1739
+ "epoch": 3.14,
1740
+ "learning_rate": 6.861083957858153e-05,
1741
+ "loss": 3.0126,
1742
+ "step": 28900
1743
+ },
1744
+ {
1745
+ "epoch": 3.15,
1746
+ "learning_rate": 6.85022265667427e-05,
1747
+ "loss": 2.9797,
1748
+ "step": 29000
1749
+ },
1750
+ {
1751
+ "epoch": 3.16,
1752
+ "learning_rate": 6.839361355490389e-05,
1753
+ "loss": 2.9233,
1754
+ "step": 29100
1755
+ },
1756
+ {
1757
+ "epoch": 3.17,
1758
+ "learning_rate": 6.828500054306506e-05,
1759
+ "loss": 2.953,
1760
+ "step": 29200
1761
+ },
1762
+ {
1763
+ "epoch": 3.18,
1764
+ "learning_rate": 6.817638753122624e-05,
1765
+ "loss": 2.9087,
1766
+ "step": 29300
1767
+ },
1768
+ {
1769
+ "epoch": 3.19,
1770
+ "learning_rate": 6.806777451938742e-05,
1771
+ "loss": 2.951,
1772
+ "step": 29400
1773
+ },
1774
+ {
1775
+ "epoch": 3.2,
1776
+ "learning_rate": 6.79591615075486e-05,
1777
+ "loss": 3.0381,
1778
+ "step": 29500
1779
+ },
1780
+ {
1781
+ "epoch": 3.21,
1782
+ "learning_rate": 6.785054849570978e-05,
1783
+ "loss": 2.9996,
1784
+ "step": 29600
1785
+ },
1786
+ {
1787
+ "epoch": 3.23,
1788
+ "learning_rate": 6.774193548387096e-05,
1789
+ "loss": 2.9855,
1790
+ "step": 29700
1791
+ },
1792
+ {
1793
+ "epoch": 3.24,
1794
+ "learning_rate": 6.763332247203216e-05,
1795
+ "loss": 2.9895,
1796
+ "step": 29800
1797
+ },
1798
+ {
1799
+ "epoch": 3.25,
1800
+ "learning_rate": 6.752470946019334e-05,
1801
+ "loss": 2.9553,
1802
+ "step": 29900
1803
+ },
1804
+ {
1805
+ "epoch": 3.26,
1806
+ "learning_rate": 6.741609644835452e-05,
1807
+ "loss": 3.0319,
1808
+ "step": 30000
1809
+ },
1810
+ {
1811
+ "epoch": 3.27,
1812
+ "learning_rate": 6.73074834365157e-05,
1813
+ "loss": 3.0371,
1814
+ "step": 30100
1815
+ },
1816
+ {
1817
+ "epoch": 3.28,
1818
+ "learning_rate": 6.719887042467688e-05,
1819
+ "loss": 2.9884,
1820
+ "step": 30200
1821
+ },
1822
+ {
1823
+ "epoch": 3.29,
1824
+ "learning_rate": 6.709025741283807e-05,
1825
+ "loss": 2.9377,
1826
+ "step": 30300
1827
+ },
1828
+ {
1829
+ "epoch": 3.3,
1830
+ "learning_rate": 6.698164440099924e-05,
1831
+ "loss": 2.9495,
1832
+ "step": 30400
1833
+ },
1834
+ {
1835
+ "epoch": 3.31,
1836
+ "learning_rate": 6.687303138916042e-05,
1837
+ "loss": 2.9938,
1838
+ "step": 30500
1839
+ },
1840
+ {
1841
+ "epoch": 3.32,
1842
+ "learning_rate": 6.67644183773216e-05,
1843
+ "loss": 2.9422,
1844
+ "step": 30600
1845
+ },
1846
+ {
1847
+ "epoch": 3.33,
1848
+ "learning_rate": 6.665580536548279e-05,
1849
+ "loss": 3.0207,
1850
+ "step": 30700
1851
+ },
1852
+ {
1853
+ "epoch": 3.35,
1854
+ "learning_rate": 6.654719235364397e-05,
1855
+ "loss": 2.8544,
1856
+ "step": 30800
1857
+ },
1858
+ {
1859
+ "epoch": 3.36,
1860
+ "learning_rate": 6.643857934180515e-05,
1861
+ "loss": 2.9468,
1862
+ "step": 30900
1863
+ },
1864
+ {
1865
+ "epoch": 3.37,
1866
+ "learning_rate": 6.632996632996633e-05,
1867
+ "loss": 2.9787,
1868
+ "step": 31000
1869
+ },
1870
+ {
1871
+ "epoch": 3.38,
1872
+ "learning_rate": 6.622135331812751e-05,
1873
+ "loss": 2.9319,
1874
+ "step": 31100
1875
+ },
1876
+ {
1877
+ "epoch": 3.39,
1878
+ "learning_rate": 6.61127403062887e-05,
1879
+ "loss": 2.9638,
1880
+ "step": 31200
1881
+ },
1882
+ {
1883
+ "epoch": 3.4,
1884
+ "learning_rate": 6.600412729444988e-05,
1885
+ "loss": 2.9358,
1886
+ "step": 31300
1887
+ },
1888
+ {
1889
+ "epoch": 3.41,
1890
+ "learning_rate": 6.589551428261106e-05,
1891
+ "loss": 2.979,
1892
+ "step": 31400
1893
+ },
1894
+ {
1895
+ "epoch": 3.42,
1896
+ "learning_rate": 6.578690127077224e-05,
1897
+ "loss": 2.9887,
1898
+ "step": 31500
1899
+ },
1900
+ {
1901
+ "epoch": 3.43,
1902
+ "learning_rate": 6.567828825893342e-05,
1903
+ "loss": 2.8997,
1904
+ "step": 31600
1905
+ },
1906
+ {
1907
+ "epoch": 3.44,
1908
+ "learning_rate": 6.55696752470946e-05,
1909
+ "loss": 2.9228,
1910
+ "step": 31700
1911
+ },
1912
+ {
1913
+ "epoch": 3.45,
1914
+ "learning_rate": 6.546106223525578e-05,
1915
+ "loss": 2.9675,
1916
+ "step": 31800
1917
+ },
1918
+ {
1919
+ "epoch": 3.46,
1920
+ "learning_rate": 6.535244922341696e-05,
1921
+ "loss": 2.8826,
1922
+ "step": 31900
1923
+ },
1924
+ {
1925
+ "epoch": 3.48,
1926
+ "learning_rate": 6.524383621157814e-05,
1927
+ "loss": 3.0264,
1928
+ "step": 32000
1929
+ },
1930
+ {
1931
+ "epoch": 3.49,
1932
+ "learning_rate": 6.513522319973934e-05,
1933
+ "loss": 2.9325,
1934
+ "step": 32100
1935
+ },
1936
+ {
1937
+ "epoch": 3.5,
1938
+ "learning_rate": 6.502661018790052e-05,
1939
+ "loss": 2.9294,
1940
+ "step": 32200
1941
+ },
1942
+ {
1943
+ "epoch": 3.51,
1944
+ "learning_rate": 6.49179971760617e-05,
1945
+ "loss": 2.9156,
1946
+ "step": 32300
1947
+ },
1948
+ {
1949
+ "epoch": 3.52,
1950
+ "learning_rate": 6.480938416422288e-05,
1951
+ "loss": 2.9291,
1952
+ "step": 32400
1953
+ },
1954
+ {
1955
+ "epoch": 3.53,
1956
+ "learning_rate": 6.470077115238406e-05,
1957
+ "loss": 2.9219,
1958
+ "step": 32500
1959
+ },
1960
+ {
1961
+ "epoch": 3.54,
1962
+ "learning_rate": 6.459215814054525e-05,
1963
+ "loss": 3.0269,
1964
+ "step": 32600
1965
+ },
1966
+ {
1967
+ "epoch": 3.55,
1968
+ "learning_rate": 6.448354512870643e-05,
1969
+ "loss": 3.0573,
1970
+ "step": 32700
1971
+ },
1972
+ {
1973
+ "epoch": 3.56,
1974
+ "learning_rate": 6.437493211686761e-05,
1975
+ "loss": 2.979,
1976
+ "step": 32800
1977
+ },
1978
+ {
1979
+ "epoch": 3.57,
1980
+ "learning_rate": 6.426631910502879e-05,
1981
+ "loss": 2.9678,
1982
+ "step": 32900
1983
+ },
1984
+ {
1985
+ "epoch": 3.58,
1986
+ "learning_rate": 6.415770609318996e-05,
1987
+ "loss": 2.8691,
1988
+ "step": 33000
1989
+ },
1990
+ {
1991
+ "epoch": 3.6,
1992
+ "learning_rate": 6.404909308135115e-05,
1993
+ "loss": 3.0819,
1994
+ "step": 33100
1995
+ },
1996
+ {
1997
+ "epoch": 3.61,
1998
+ "learning_rate": 6.394048006951233e-05,
1999
+ "loss": 2.9761,
2000
+ "step": 33200
2001
+ },
2002
+ {
2003
+ "epoch": 3.62,
2004
+ "learning_rate": 6.383186705767351e-05,
2005
+ "loss": 3.0444,
2006
+ "step": 33300
2007
+ },
2008
+ {
2009
+ "epoch": 3.63,
2010
+ "learning_rate": 6.372325404583469e-05,
2011
+ "loss": 2.91,
2012
+ "step": 33400
2013
+ },
2014
+ {
2015
+ "epoch": 3.64,
2016
+ "learning_rate": 6.361464103399588e-05,
2017
+ "loss": 2.9845,
2018
+ "step": 33500
2019
+ },
2020
+ {
2021
+ "epoch": 3.65,
2022
+ "learning_rate": 6.350602802215706e-05,
2023
+ "loss": 2.9298,
2024
+ "step": 33600
2025
+ },
2026
+ {
2027
+ "epoch": 3.66,
2028
+ "learning_rate": 6.339741501031824e-05,
2029
+ "loss": 2.9518,
2030
+ "step": 33700
2031
+ },
2032
+ {
2033
+ "epoch": 3.67,
2034
+ "learning_rate": 6.328880199847942e-05,
2035
+ "loss": 2.9359,
2036
+ "step": 33800
2037
+ },
2038
+ {
2039
+ "epoch": 3.68,
2040
+ "learning_rate": 6.31801889866406e-05,
2041
+ "loss": 2.9675,
2042
+ "step": 33900
2043
+ },
2044
+ {
2045
+ "epoch": 3.69,
2046
+ "learning_rate": 6.30715759748018e-05,
2047
+ "loss": 2.8137,
2048
+ "step": 34000
2049
+ },
2050
+ {
2051
+ "epoch": 3.7,
2052
+ "learning_rate": 6.296296296296296e-05,
2053
+ "loss": 3.0078,
2054
+ "step": 34100
2055
+ },
2056
+ {
2057
+ "epoch": 3.71,
2058
+ "learning_rate": 6.285434995112414e-05,
2059
+ "loss": 3.0557,
2060
+ "step": 34200
2061
+ },
2062
+ {
2063
+ "epoch": 3.73,
2064
+ "learning_rate": 6.274573693928532e-05,
2065
+ "loss": 2.9161,
2066
+ "step": 34300
2067
+ },
2068
+ {
2069
+ "epoch": 3.74,
2070
+ "learning_rate": 6.26371239274465e-05,
2071
+ "loss": 2.9669,
2072
+ "step": 34400
2073
+ },
2074
+ {
2075
+ "epoch": 3.75,
2076
+ "learning_rate": 6.25285109156077e-05,
2077
+ "loss": 2.9938,
2078
+ "step": 34500
2079
+ },
2080
+ {
2081
+ "epoch": 3.76,
2082
+ "learning_rate": 6.241989790376887e-05,
2083
+ "loss": 2.9183,
2084
+ "step": 34600
2085
+ },
2086
+ {
2087
+ "epoch": 3.77,
2088
+ "learning_rate": 6.231128489193005e-05,
2089
+ "loss": 2.9855,
2090
+ "step": 34700
2091
+ },
2092
+ {
2093
+ "epoch": 3.78,
2094
+ "learning_rate": 6.220267188009123e-05,
2095
+ "loss": 2.8912,
2096
+ "step": 34800
2097
+ },
2098
+ {
2099
+ "epoch": 3.79,
2100
+ "learning_rate": 6.209405886825243e-05,
2101
+ "loss": 2.8896,
2102
+ "step": 34900
2103
+ },
2104
+ {
2105
+ "epoch": 3.8,
2106
+ "learning_rate": 6.198544585641361e-05,
2107
+ "loss": 2.953,
2108
+ "step": 35000
2109
+ },
2110
+ {
2111
+ "epoch": 3.81,
2112
+ "learning_rate": 6.187683284457479e-05,
2113
+ "loss": 2.8615,
2114
+ "step": 35100
2115
+ },
2116
+ {
2117
+ "epoch": 3.82,
2118
+ "learning_rate": 6.176821983273597e-05,
2119
+ "loss": 2.9473,
2120
+ "step": 35200
2121
+ },
2122
+ {
2123
+ "epoch": 3.83,
2124
+ "learning_rate": 6.165960682089715e-05,
2125
+ "loss": 2.9928,
2126
+ "step": 35300
2127
+ },
2128
+ {
2129
+ "epoch": 3.84,
2130
+ "learning_rate": 6.155099380905833e-05,
2131
+ "loss": 2.8082,
2132
+ "step": 35400
2133
+ },
2134
+ {
2135
+ "epoch": 3.86,
2136
+ "learning_rate": 6.144238079721951e-05,
2137
+ "loss": 2.9584,
2138
+ "step": 35500
2139
+ },
2140
+ {
2141
+ "epoch": 3.87,
2142
+ "learning_rate": 6.133376778538069e-05,
2143
+ "loss": 2.9186,
2144
+ "step": 35600
2145
+ },
2146
+ {
2147
+ "epoch": 3.88,
2148
+ "learning_rate": 6.122515477354187e-05,
2149
+ "loss": 2.9403,
2150
+ "step": 35700
2151
+ },
2152
+ {
2153
+ "epoch": 3.89,
2154
+ "learning_rate": 6.111654176170305e-05,
2155
+ "loss": 2.8996,
2156
+ "step": 35800
2157
+ },
2158
+ {
2159
+ "epoch": 3.9,
2160
+ "learning_rate": 6.100792874986424e-05,
2161
+ "loss": 3.0083,
2162
+ "step": 35900
2163
+ },
2164
+ {
2165
+ "epoch": 3.91,
2166
+ "learning_rate": 6.089931573802542e-05,
2167
+ "loss": 2.9722,
2168
+ "step": 36000
2169
+ },
2170
+ {
2171
+ "epoch": 3.92,
2172
+ "learning_rate": 6.07907027261866e-05,
2173
+ "loss": 2.8405,
2174
+ "step": 36100
2175
+ },
2176
+ {
2177
+ "epoch": 3.93,
2178
+ "learning_rate": 6.068208971434778e-05,
2179
+ "loss": 2.971,
2180
+ "step": 36200
2181
+ },
2182
+ {
2183
+ "epoch": 3.94,
2184
+ "learning_rate": 6.057347670250897e-05,
2185
+ "loss": 2.9748,
2186
+ "step": 36300
2187
+ },
2188
+ {
2189
+ "epoch": 3.95,
2190
+ "learning_rate": 6.046486369067015e-05,
2191
+ "loss": 2.8846,
2192
+ "step": 36400
2193
+ },
2194
+ {
2195
+ "epoch": 3.96,
2196
+ "learning_rate": 6.0356250678831327e-05,
2197
+ "loss": 2.8576,
2198
+ "step": 36500
2199
+ },
2200
+ {
2201
+ "epoch": 3.98,
2202
+ "learning_rate": 6.0247637666992506e-05,
2203
+ "loss": 2.9272,
2204
+ "step": 36600
2205
+ },
2206
+ {
2207
+ "epoch": 3.99,
2208
+ "learning_rate": 6.0139024655153686e-05,
2209
+ "loss": 2.9479,
2210
+ "step": 36700
2211
+ },
2212
+ {
2213
+ "epoch": 4.0,
2214
+ "learning_rate": 6.003041164331488e-05,
2215
+ "loss": 2.8707,
2216
+ "step": 36800
2217
+ },
2218
+ {
2219
+ "epoch": 4.01,
2220
+ "learning_rate": 5.992179863147605e-05,
2221
+ "loss": 2.9569,
2222
+ "step": 36900
2223
+ },
2224
+ {
2225
+ "epoch": 4.02,
2226
+ "learning_rate": 5.981318561963723e-05,
2227
+ "loss": 2.8839,
2228
+ "step": 37000
2229
+ },
2230
+ {
2231
+ "epoch": 4.03,
2232
+ "learning_rate": 5.970457260779841e-05,
2233
+ "loss": 2.9383,
2234
+ "step": 37100
2235
+ },
2236
+ {
2237
+ "epoch": 4.04,
2238
+ "learning_rate": 5.959595959595959e-05,
2239
+ "loss": 2.9082,
2240
+ "step": 37200
2241
+ },
2242
+ {
2243
+ "epoch": 4.05,
2244
+ "learning_rate": 5.9487346584120786e-05,
2245
+ "loss": 2.8685,
2246
+ "step": 37300
2247
+ },
2248
+ {
2249
+ "epoch": 4.06,
2250
+ "learning_rate": 5.9378733572281966e-05,
2251
+ "loss": 2.8974,
2252
+ "step": 37400
2253
+ },
2254
+ {
2255
+ "epoch": 4.07,
2256
+ "learning_rate": 5.9270120560443146e-05,
2257
+ "loss": 2.9803,
2258
+ "step": 37500
2259
+ },
2260
+ {
2261
+ "epoch": 4.08,
2262
+ "learning_rate": 5.916150754860432e-05,
2263
+ "loss": 2.8538,
2264
+ "step": 37600
2265
+ },
2266
+ {
2267
+ "epoch": 4.09,
2268
+ "learning_rate": 5.905289453676551e-05,
2269
+ "loss": 2.7821,
2270
+ "step": 37700
2271
+ },
2272
+ {
2273
+ "epoch": 4.11,
2274
+ "learning_rate": 5.894428152492669e-05,
2275
+ "loss": 2.8806,
2276
+ "step": 37800
2277
+ },
2278
+ {
2279
+ "epoch": 4.12,
2280
+ "learning_rate": 5.883566851308787e-05,
2281
+ "loss": 2.871,
2282
+ "step": 37900
2283
+ },
2284
+ {
2285
+ "epoch": 4.13,
2286
+ "learning_rate": 5.872705550124905e-05,
2287
+ "loss": 2.954,
2288
+ "step": 38000
2289
+ },
2290
+ {
2291
+ "epoch": 4.14,
2292
+ "learning_rate": 5.861844248941023e-05,
2293
+ "loss": 2.8033,
2294
+ "step": 38100
2295
+ },
2296
+ {
2297
+ "epoch": 4.15,
2298
+ "learning_rate": 5.850982947757142e-05,
2299
+ "loss": 2.8521,
2300
+ "step": 38200
2301
+ },
2302
+ {
2303
+ "epoch": 4.16,
2304
+ "learning_rate": 5.84012164657326e-05,
2305
+ "loss": 2.7813,
2306
+ "step": 38300
2307
+ },
2308
+ {
2309
+ "epoch": 4.17,
2310
+ "learning_rate": 5.829260345389378e-05,
2311
+ "loss": 2.823,
2312
+ "step": 38400
2313
+ },
2314
+ {
2315
+ "epoch": 4.18,
2316
+ "learning_rate": 5.818399044205496e-05,
2317
+ "loss": 2.862,
2318
+ "step": 38500
2319
+ },
2320
+ {
2321
+ "epoch": 4.19,
2322
+ "learning_rate": 5.807537743021614e-05,
2323
+ "loss": 2.8487,
2324
+ "step": 38600
2325
+ },
2326
+ {
2327
+ "epoch": 4.2,
2328
+ "learning_rate": 5.7966764418377325e-05,
2329
+ "loss": 2.8546,
2330
+ "step": 38700
2331
+ },
2332
+ {
2333
+ "epoch": 4.21,
2334
+ "learning_rate": 5.7858151406538505e-05,
2335
+ "loss": 2.9429,
2336
+ "step": 38800
2337
+ },
2338
+ {
2339
+ "epoch": 4.23,
2340
+ "learning_rate": 5.7749538394699685e-05,
2341
+ "loss": 2.9066,
2342
+ "step": 38900
2343
+ },
2344
+ {
2345
+ "epoch": 4.24,
2346
+ "learning_rate": 5.7640925382860865e-05,
2347
+ "loss": 3.0249,
2348
+ "step": 39000
2349
+ },
2350
+ {
2351
+ "epoch": 4.25,
2352
+ "learning_rate": 5.7532312371022045e-05,
2353
+ "loss": 2.8215,
2354
+ "step": 39100
2355
+ },
2356
+ {
2357
+ "epoch": 4.26,
2358
+ "learning_rate": 5.742369935918324e-05,
2359
+ "loss": 2.8526,
2360
+ "step": 39200
2361
+ },
2362
+ {
2363
+ "epoch": 4.27,
2364
+ "learning_rate": 5.731508634734442e-05,
2365
+ "loss": 2.9065,
2366
+ "step": 39300
2367
+ },
2368
+ {
2369
+ "epoch": 4.28,
2370
+ "learning_rate": 5.72064733355056e-05,
2371
+ "loss": 2.8976,
2372
+ "step": 39400
2373
+ },
2374
+ {
2375
+ "epoch": 4.29,
2376
+ "learning_rate": 5.709786032366677e-05,
2377
+ "loss": 2.9547,
2378
+ "step": 39500
2379
+ },
2380
+ {
2381
+ "epoch": 4.3,
2382
+ "learning_rate": 5.6989247311827965e-05,
2383
+ "loss": 2.9062,
2384
+ "step": 39600
2385
+ },
2386
+ {
2387
+ "epoch": 4.31,
2388
+ "learning_rate": 5.6880634299989144e-05,
2389
+ "loss": 2.8824,
2390
+ "step": 39700
2391
+ },
2392
+ {
2393
+ "epoch": 4.32,
2394
+ "learning_rate": 5.6772021288150324e-05,
2395
+ "loss": 2.8768,
2396
+ "step": 39800
2397
+ },
2398
+ {
2399
+ "epoch": 4.33,
2400
+ "learning_rate": 5.6663408276311504e-05,
2401
+ "loss": 2.8265,
2402
+ "step": 39900
2403
+ },
2404
+ {
2405
+ "epoch": 4.34,
2406
+ "learning_rate": 5.6554795264472684e-05,
2407
+ "loss": 2.9223,
2408
+ "step": 40000
2409
+ },
2410
+ {
2411
+ "epoch": 4.36,
2412
+ "learning_rate": 5.644618225263387e-05,
2413
+ "loss": 2.8611,
2414
+ "step": 40100
2415
+ },
2416
+ {
2417
+ "epoch": 4.37,
2418
+ "learning_rate": 5.633756924079505e-05,
2419
+ "loss": 2.8157,
2420
+ "step": 40200
2421
+ },
2422
+ {
2423
+ "epoch": 4.38,
2424
+ "learning_rate": 5.622895622895623e-05,
2425
+ "loss": 2.848,
2426
+ "step": 40300
2427
+ },
2428
+ {
2429
+ "epoch": 4.39,
2430
+ "learning_rate": 5.612034321711741e-05,
2431
+ "loss": 2.8369,
2432
+ "step": 40400
2433
+ },
2434
+ {
2435
+ "epoch": 4.4,
2436
+ "learning_rate": 5.601173020527859e-05,
2437
+ "loss": 2.966,
2438
+ "step": 40500
2439
+ },
2440
+ {
2441
+ "epoch": 4.41,
2442
+ "learning_rate": 5.590311719343978e-05,
2443
+ "loss": 2.9007,
2444
+ "step": 40600
2445
+ },
2446
+ {
2447
+ "epoch": 4.42,
2448
+ "learning_rate": 5.579450418160096e-05,
2449
+ "loss": 2.9092,
2450
+ "step": 40700
2451
+ },
2452
+ {
2453
+ "epoch": 4.43,
2454
+ "learning_rate": 5.568589116976214e-05,
2455
+ "loss": 2.911,
2456
+ "step": 40800
2457
+ },
2458
+ {
2459
+ "epoch": 4.44,
2460
+ "learning_rate": 5.557727815792332e-05,
2461
+ "loss": 2.8352,
2462
+ "step": 40900
2463
+ },
2464
+ {
2465
+ "epoch": 4.45,
2466
+ "learning_rate": 5.546866514608451e-05,
2467
+ "loss": 2.814,
2468
+ "step": 41000
2469
+ },
2470
+ {
2471
+ "epoch": 4.46,
2472
+ "learning_rate": 5.536005213424569e-05,
2473
+ "loss": 2.8483,
2474
+ "step": 41100
2475
+ },
2476
+ {
2477
+ "epoch": 4.47,
2478
+ "learning_rate": 5.525143912240687e-05,
2479
+ "loss": 2.7428,
2480
+ "step": 41200
2481
+ },
2482
+ {
2483
+ "epoch": 4.49,
2484
+ "learning_rate": 5.514282611056805e-05,
2485
+ "loss": 2.7516,
2486
+ "step": 41300
2487
+ },
2488
+ {
2489
+ "epoch": 4.5,
2490
+ "learning_rate": 5.503421309872922e-05,
2491
+ "loss": 2.9075,
2492
+ "step": 41400
2493
+ },
2494
+ {
2495
+ "epoch": 4.51,
2496
+ "learning_rate": 5.4925600086890417e-05,
2497
+ "loss": 2.8721,
2498
+ "step": 41500
2499
+ },
2500
+ {
2501
+ "epoch": 4.52,
2502
+ "learning_rate": 5.4816987075051596e-05,
2503
+ "loss": 2.8518,
2504
+ "step": 41600
2505
+ },
2506
+ {
2507
+ "epoch": 4.53,
2508
+ "learning_rate": 5.4708374063212776e-05,
2509
+ "loss": 2.8708,
2510
+ "step": 41700
2511
+ },
2512
+ {
2513
+ "epoch": 4.54,
2514
+ "learning_rate": 5.4599761051373956e-05,
2515
+ "loss": 2.8379,
2516
+ "step": 41800
2517
+ },
2518
+ {
2519
+ "epoch": 4.55,
2520
+ "learning_rate": 5.4491148039535136e-05,
2521
+ "loss": 2.8438,
2522
+ "step": 41900
2523
+ },
2524
+ {
2525
+ "epoch": 4.56,
2526
+ "learning_rate": 5.438253502769632e-05,
2527
+ "loss": 2.8823,
2528
+ "step": 42000
2529
+ },
2530
+ {
2531
+ "epoch": 4.57,
2532
+ "learning_rate": 5.42739220158575e-05,
2533
+ "loss": 2.8721,
2534
+ "step": 42100
2535
+ },
2536
+ {
2537
+ "epoch": 4.58,
2538
+ "learning_rate": 5.416530900401868e-05,
2539
+ "loss": 2.8483,
2540
+ "step": 42200
2541
+ },
2542
+ {
2543
+ "epoch": 4.59,
2544
+ "learning_rate": 5.405669599217986e-05,
2545
+ "loss": 2.828,
2546
+ "step": 42300
2547
+ },
2548
+ {
2549
+ "epoch": 4.61,
2550
+ "learning_rate": 5.394808298034105e-05,
2551
+ "loss": 2.9338,
2552
+ "step": 42400
2553
+ },
2554
+ {
2555
+ "epoch": 4.62,
2556
+ "learning_rate": 5.383946996850223e-05,
2557
+ "loss": 2.8982,
2558
+ "step": 42500
2559
+ },
2560
+ {
2561
+ "epoch": 4.63,
2562
+ "learning_rate": 5.373085695666341e-05,
2563
+ "loss": 2.8346,
2564
+ "step": 42600
2565
+ },
2566
+ {
2567
+ "epoch": 4.64,
2568
+ "learning_rate": 5.362224394482459e-05,
2569
+ "loss": 2.9424,
2570
+ "step": 42700
2571
+ },
2572
+ {
2573
+ "epoch": 4.65,
2574
+ "learning_rate": 5.351363093298577e-05,
2575
+ "loss": 2.8952,
2576
+ "step": 42800
2577
+ },
2578
+ {
2579
+ "epoch": 4.66,
2580
+ "learning_rate": 5.340501792114696e-05,
2581
+ "loss": 2.8737,
2582
+ "step": 42900
2583
+ },
2584
+ {
2585
+ "epoch": 4.67,
2586
+ "learning_rate": 5.329640490930814e-05,
2587
+ "loss": 2.9484,
2588
+ "step": 43000
2589
+ },
2590
+ {
2591
+ "epoch": 4.68,
2592
+ "learning_rate": 5.318779189746932e-05,
2593
+ "loss": 2.8492,
2594
+ "step": 43100
2595
+ },
2596
+ {
2597
+ "epoch": 4.69,
2598
+ "learning_rate": 5.3079178885630495e-05,
2599
+ "loss": 2.8864,
2600
+ "step": 43200
2601
+ },
2602
+ {
2603
+ "epoch": 4.7,
2604
+ "learning_rate": 5.2970565873791675e-05,
2605
+ "loss": 2.8093,
2606
+ "step": 43300
2607
+ },
2608
+ {
2609
+ "epoch": 4.71,
2610
+ "learning_rate": 5.286195286195287e-05,
2611
+ "loss": 2.7881,
2612
+ "step": 43400
2613
+ },
2614
+ {
2615
+ "epoch": 4.72,
2616
+ "learning_rate": 5.275333985011405e-05,
2617
+ "loss": 2.8584,
2618
+ "step": 43500
2619
+ },
2620
+ {
2621
+ "epoch": 4.74,
2622
+ "learning_rate": 5.264472683827523e-05,
2623
+ "loss": 2.8925,
2624
+ "step": 43600
2625
+ },
2626
+ {
2627
+ "epoch": 4.75,
2628
+ "learning_rate": 5.253611382643641e-05,
2629
+ "loss": 2.7261,
2630
+ "step": 43700
2631
+ },
2632
+ {
2633
+ "epoch": 4.76,
2634
+ "learning_rate": 5.2427500814597595e-05,
2635
+ "loss": 2.8569,
2636
+ "step": 43800
2637
+ },
2638
+ {
2639
+ "epoch": 4.77,
2640
+ "learning_rate": 5.2318887802758775e-05,
2641
+ "loss": 2.8978,
2642
+ "step": 43900
2643
+ },
2644
+ {
2645
+ "epoch": 4.78,
2646
+ "learning_rate": 5.2210274790919955e-05,
2647
+ "loss": 2.9005,
2648
+ "step": 44000
2649
+ },
2650
+ {
2651
+ "epoch": 4.79,
2652
+ "learning_rate": 5.2101661779081135e-05,
2653
+ "loss": 2.8661,
2654
+ "step": 44100
2655
+ },
2656
+ {
2657
+ "epoch": 4.8,
2658
+ "learning_rate": 5.1993048767242315e-05,
2659
+ "loss": 2.9499,
2660
+ "step": 44200
2661
+ },
2662
+ {
2663
+ "epoch": 4.81,
2664
+ "learning_rate": 5.18844357554035e-05,
2665
+ "loss": 2.8969,
2666
+ "step": 44300
2667
+ },
2668
+ {
2669
+ "epoch": 4.82,
2670
+ "learning_rate": 5.177582274356468e-05,
2671
+ "loss": 2.8314,
2672
+ "step": 44400
2673
+ },
2674
+ {
2675
+ "epoch": 4.83,
2676
+ "learning_rate": 5.166720973172586e-05,
2677
+ "loss": 2.8229,
2678
+ "step": 44500
2679
+ },
2680
+ {
2681
+ "epoch": 4.84,
2682
+ "learning_rate": 5.155859671988704e-05,
2683
+ "loss": 2.8463,
2684
+ "step": 44600
2685
+ },
2686
+ {
2687
+ "epoch": 4.85,
2688
+ "learning_rate": 5.144998370804822e-05,
2689
+ "loss": 2.8764,
2690
+ "step": 44700
2691
+ },
2692
+ {
2693
+ "epoch": 4.87,
2694
+ "learning_rate": 5.1341370696209414e-05,
2695
+ "loss": 2.8458,
2696
+ "step": 44800
2697
+ },
2698
+ {
2699
+ "epoch": 4.88,
2700
+ "learning_rate": 5.1232757684370594e-05,
2701
+ "loss": 2.8062,
2702
+ "step": 44900
2703
+ },
2704
+ {
2705
+ "epoch": 4.89,
2706
+ "learning_rate": 5.1124144672531774e-05,
2707
+ "loss": 2.894,
2708
+ "step": 45000
2709
+ },
2710
+ {
2711
+ "epoch": 4.9,
2712
+ "learning_rate": 5.101553166069295e-05,
2713
+ "loss": 2.8546,
2714
+ "step": 45100
2715
+ },
2716
+ {
2717
+ "epoch": 4.91,
2718
+ "learning_rate": 5.090691864885414e-05,
2719
+ "loss": 2.8455,
2720
+ "step": 45200
2721
+ },
2722
+ {
2723
+ "epoch": 4.92,
2724
+ "learning_rate": 5.079830563701532e-05,
2725
+ "loss": 2.8055,
2726
+ "step": 45300
2727
+ },
2728
+ {
2729
+ "epoch": 4.93,
2730
+ "learning_rate": 5.06896926251765e-05,
2731
+ "loss": 2.9081,
2732
+ "step": 45400
2733
+ },
2734
+ {
2735
+ "epoch": 4.94,
2736
+ "learning_rate": 5.058107961333768e-05,
2737
+ "loss": 2.9016,
2738
+ "step": 45500
2739
+ },
2740
+ {
2741
+ "epoch": 4.95,
2742
+ "learning_rate": 5.047246660149886e-05,
2743
+ "loss": 2.88,
2744
+ "step": 45600
2745
+ },
2746
+ {
2747
+ "epoch": 4.96,
2748
+ "learning_rate": 5.036385358966005e-05,
2749
+ "loss": 2.9696,
2750
+ "step": 45700
2751
+ },
2752
+ {
2753
+ "epoch": 4.97,
2754
+ "learning_rate": 5.025524057782123e-05,
2755
+ "loss": 2.8584,
2756
+ "step": 45800
2757
+ },
2758
+ {
2759
+ "epoch": 4.99,
2760
+ "learning_rate": 5.014662756598241e-05,
2761
+ "loss": 2.8707,
2762
+ "step": 45900
2763
+ },
2764
+ {
2765
+ "epoch": 5.0,
2766
+ "learning_rate": 5.003801455414359e-05,
2767
+ "loss": 2.8539,
2768
+ "step": 46000
2769
+ },
2770
+ {
2771
+ "epoch": 5.01,
2772
+ "learning_rate": 4.9929401542304773e-05,
2773
+ "loss": 2.8842,
2774
+ "step": 46100
2775
+ },
2776
+ {
2777
+ "epoch": 5.02,
2778
+ "learning_rate": 4.982078853046595e-05,
2779
+ "loss": 2.7645,
2780
+ "step": 46200
2781
+ },
2782
+ {
2783
+ "epoch": 5.03,
2784
+ "learning_rate": 4.971217551862713e-05,
2785
+ "loss": 2.8499,
2786
+ "step": 46300
2787
+ },
2788
+ {
2789
+ "epoch": 5.04,
2790
+ "learning_rate": 4.960356250678831e-05,
2791
+ "loss": 2.8812,
2792
+ "step": 46400
2793
+ },
2794
+ {
2795
+ "epoch": 5.05,
2796
+ "learning_rate": 4.94949494949495e-05,
2797
+ "loss": 2.7704,
2798
+ "step": 46500
2799
+ },
2800
+ {
2801
+ "epoch": 5.06,
2802
+ "learning_rate": 4.938633648311068e-05,
2803
+ "loss": 2.7921,
2804
+ "step": 46600
2805
+ },
2806
+ {
2807
+ "epoch": 5.07,
2808
+ "learning_rate": 4.927772347127186e-05,
2809
+ "loss": 2.8428,
2810
+ "step": 46700
2811
+ },
2812
+ {
2813
+ "epoch": 5.08,
2814
+ "learning_rate": 4.9169110459433046e-05,
2815
+ "loss": 2.8605,
2816
+ "step": 46800
2817
+ },
2818
+ {
2819
+ "epoch": 5.09,
2820
+ "learning_rate": 4.906049744759422e-05,
2821
+ "loss": 2.7879,
2822
+ "step": 46900
2823
+ },
2824
+ {
2825
+ "epoch": 5.1,
2826
+ "learning_rate": 4.8951884435755406e-05,
2827
+ "loss": 2.846,
2828
+ "step": 47000
2829
+ },
2830
+ {
2831
+ "epoch": 5.12,
2832
+ "learning_rate": 4.8843271423916586e-05,
2833
+ "loss": 2.8179,
2834
+ "step": 47100
2835
+ },
2836
+ {
2837
+ "epoch": 5.13,
2838
+ "learning_rate": 4.873465841207777e-05,
2839
+ "loss": 2.9302,
2840
+ "step": 47200
2841
+ },
2842
+ {
2843
+ "epoch": 5.14,
2844
+ "learning_rate": 4.862604540023895e-05,
2845
+ "loss": 2.7913,
2846
+ "step": 47300
2847
+ },
2848
+ {
2849
+ "epoch": 5.15,
2850
+ "learning_rate": 4.851743238840013e-05,
2851
+ "loss": 2.7173,
2852
+ "step": 47400
2853
+ },
2854
+ {
2855
+ "epoch": 5.16,
2856
+ "learning_rate": 4.840881937656131e-05,
2857
+ "loss": 2.8389,
2858
+ "step": 47500
2859
+ },
2860
+ {
2861
+ "epoch": 5.17,
2862
+ "learning_rate": 4.830020636472249e-05,
2863
+ "loss": 2.6752,
2864
+ "step": 47600
2865
+ },
2866
+ {
2867
+ "epoch": 5.18,
2868
+ "learning_rate": 4.819159335288368e-05,
2869
+ "loss": 2.7911,
2870
+ "step": 47700
2871
+ },
2872
+ {
2873
+ "epoch": 5.19,
2874
+ "learning_rate": 4.808298034104486e-05,
2875
+ "loss": 2.8147,
2876
+ "step": 47800
2877
+ },
2878
+ {
2879
+ "epoch": 5.2,
2880
+ "learning_rate": 4.7974367329206046e-05,
2881
+ "loss": 2.7192,
2882
+ "step": 47900
2883
+ },
2884
+ {
2885
+ "epoch": 5.21,
2886
+ "learning_rate": 4.7865754317367225e-05,
2887
+ "loss": 2.8325,
2888
+ "step": 48000
2889
+ },
2890
+ {
2891
+ "epoch": 5.22,
2892
+ "learning_rate": 4.7757141305528405e-05,
2893
+ "loss": 2.8132,
2894
+ "step": 48100
2895
+ },
2896
+ {
2897
+ "epoch": 5.24,
2898
+ "learning_rate": 4.7648528293689585e-05,
2899
+ "loss": 2.7436,
2900
+ "step": 48200
2901
+ },
2902
+ {
2903
+ "epoch": 5.25,
2904
+ "learning_rate": 4.7539915281850765e-05,
2905
+ "loss": 2.7892,
2906
+ "step": 48300
2907
+ },
2908
+ {
2909
+ "epoch": 5.26,
2910
+ "learning_rate": 4.743130227001195e-05,
2911
+ "loss": 2.7921,
2912
+ "step": 48400
2913
+ },
2914
+ {
2915
+ "epoch": 5.27,
2916
+ "learning_rate": 4.732268925817313e-05,
2917
+ "loss": 2.7845,
2918
+ "step": 48500
2919
+ },
2920
+ {
2921
+ "epoch": 5.28,
2922
+ "learning_rate": 4.721407624633432e-05,
2923
+ "loss": 2.8523,
2924
+ "step": 48600
2925
+ },
2926
+ {
2927
+ "epoch": 5.29,
2928
+ "learning_rate": 4.71054632344955e-05,
2929
+ "loss": 2.8484,
2930
+ "step": 48700
2931
+ },
2932
+ {
2933
+ "epoch": 5.3,
2934
+ "learning_rate": 4.699685022265667e-05,
2935
+ "loss": 2.7924,
2936
+ "step": 48800
2937
+ },
2938
+ {
2939
+ "epoch": 5.31,
2940
+ "learning_rate": 4.688823721081786e-05,
2941
+ "loss": 2.8363,
2942
+ "step": 48900
2943
+ },
2944
+ {
2945
+ "epoch": 5.32,
2946
+ "learning_rate": 4.677962419897904e-05,
2947
+ "loss": 2.7945,
2948
+ "step": 49000
2949
+ },
2950
+ {
2951
+ "epoch": 5.33,
2952
+ "learning_rate": 4.6671011187140225e-05,
2953
+ "loss": 2.8128,
2954
+ "step": 49100
2955
+ },
2956
+ {
2957
+ "epoch": 5.34,
2958
+ "learning_rate": 4.6562398175301405e-05,
2959
+ "loss": 2.8558,
2960
+ "step": 49200
2961
+ },
2962
+ {
2963
+ "epoch": 5.35,
2964
+ "learning_rate": 4.6453785163462584e-05,
2965
+ "loss": 2.838,
2966
+ "step": 49300
2967
+ },
2968
+ {
2969
+ "epoch": 5.37,
2970
+ "learning_rate": 4.6345172151623764e-05,
2971
+ "loss": 2.7965,
2972
+ "step": 49400
2973
+ },
2974
+ {
2975
+ "epoch": 5.38,
2976
+ "learning_rate": 4.6236559139784944e-05,
2977
+ "loss": 2.742,
2978
+ "step": 49500
2979
+ },
2980
+ {
2981
+ "epoch": 5.39,
2982
+ "learning_rate": 4.612794612794613e-05,
2983
+ "loss": 2.6993,
2984
+ "step": 49600
2985
+ },
2986
+ {
2987
+ "epoch": 5.4,
2988
+ "learning_rate": 4.601933311610731e-05,
2989
+ "loss": 2.8197,
2990
+ "step": 49700
2991
+ },
2992
+ {
2993
+ "epoch": 5.41,
2994
+ "learning_rate": 4.59107201042685e-05,
2995
+ "loss": 2.7072,
2996
+ "step": 49800
2997
+ },
2998
+ {
2999
+ "epoch": 5.42,
3000
+ "learning_rate": 4.580210709242968e-05,
3001
+ "loss": 2.8693,
3002
+ "step": 49900
3003
+ },
3004
+ {
3005
+ "epoch": 5.43,
3006
+ "learning_rate": 4.569349408059086e-05,
3007
+ "loss": 2.795,
3008
+ "step": 50000
3009
+ },
3010
+ {
3011
+ "epoch": 5.44,
3012
+ "learning_rate": 4.558488106875204e-05,
3013
+ "loss": 2.8191,
3014
+ "step": 50100
3015
+ },
3016
+ {
3017
+ "epoch": 5.45,
3018
+ "learning_rate": 4.547626805691322e-05,
3019
+ "loss": 2.8621,
3020
+ "step": 50200
3021
+ },
3022
+ {
3023
+ "epoch": 5.46,
3024
+ "learning_rate": 4.5367655045074404e-05,
3025
+ "loss": 2.7651,
3026
+ "step": 50300
3027
+ },
3028
+ {
3029
+ "epoch": 5.47,
3030
+ "learning_rate": 4.5259042033235584e-05,
3031
+ "loss": 2.77,
3032
+ "step": 50400
3033
+ },
3034
+ {
3035
+ "epoch": 5.48,
3036
+ "learning_rate": 4.515042902139677e-05,
3037
+ "loss": 2.8439,
3038
+ "step": 50500
3039
+ },
3040
+ {
3041
+ "epoch": 5.5,
3042
+ "learning_rate": 4.5041816009557944e-05,
3043
+ "loss": 2.7788,
3044
+ "step": 50600
3045
+ },
3046
+ {
3047
+ "epoch": 5.51,
3048
+ "learning_rate": 4.493320299771913e-05,
3049
+ "loss": 2.8328,
3050
+ "step": 50700
3051
+ },
3052
+ {
3053
+ "epoch": 5.52,
3054
+ "learning_rate": 4.482458998588031e-05,
3055
+ "loss": 2.8625,
3056
+ "step": 50800
3057
+ },
3058
+ {
3059
+ "epoch": 5.53,
3060
+ "learning_rate": 4.471597697404149e-05,
3061
+ "loss": 2.8773,
3062
+ "step": 50900
3063
+ },
3064
+ {
3065
+ "epoch": 5.54,
3066
+ "learning_rate": 4.460736396220268e-05,
3067
+ "loss": 2.8209,
3068
+ "step": 51000
3069
+ },
3070
+ {
3071
+ "epoch": 5.55,
3072
+ "learning_rate": 4.449875095036386e-05,
3073
+ "loss": 2.7392,
3074
+ "step": 51100
3075
+ },
3076
+ {
3077
+ "epoch": 5.56,
3078
+ "learning_rate": 4.4390137938525037e-05,
3079
+ "loss": 2.7048,
3080
+ "step": 51200
3081
+ },
3082
+ {
3083
+ "epoch": 5.57,
3084
+ "learning_rate": 4.4281524926686216e-05,
3085
+ "loss": 2.8771,
3086
+ "step": 51300
3087
+ },
3088
+ {
3089
+ "epoch": 5.58,
3090
+ "learning_rate": 4.41729119148474e-05,
3091
+ "loss": 2.7526,
3092
+ "step": 51400
3093
+ },
3094
+ {
3095
+ "epoch": 5.59,
3096
+ "learning_rate": 4.406429890300858e-05,
3097
+ "loss": 2.7457,
3098
+ "step": 51500
3099
+ },
3100
+ {
3101
+ "epoch": 5.6,
3102
+ "learning_rate": 4.395568589116976e-05,
3103
+ "loss": 2.8338,
3104
+ "step": 51600
3105
+ },
3106
+ {
3107
+ "epoch": 5.62,
3108
+ "learning_rate": 4.384707287933095e-05,
3109
+ "loss": 2.8154,
3110
+ "step": 51700
3111
+ },
3112
+ {
3113
+ "epoch": 5.63,
3114
+ "learning_rate": 4.373845986749213e-05,
3115
+ "loss": 2.7648,
3116
+ "step": 51800
3117
+ },
3118
+ {
3119
+ "epoch": 5.64,
3120
+ "learning_rate": 4.362984685565331e-05,
3121
+ "loss": 2.81,
3122
+ "step": 51900
3123
+ },
3124
+ {
3125
+ "epoch": 5.65,
3126
+ "learning_rate": 4.352123384381449e-05,
3127
+ "loss": 2.742,
3128
+ "step": 52000
3129
+ },
3130
+ {
3131
+ "epoch": 5.66,
3132
+ "learning_rate": 4.3412620831975676e-05,
3133
+ "loss": 2.7741,
3134
+ "step": 52100
3135
+ },
3136
+ {
3137
+ "epoch": 5.67,
3138
+ "learning_rate": 4.3304007820136856e-05,
3139
+ "loss": 2.7733,
3140
+ "step": 52200
3141
+ },
3142
+ {
3143
+ "epoch": 5.68,
3144
+ "learning_rate": 4.3195394808298036e-05,
3145
+ "loss": 2.8178,
3146
+ "step": 52300
3147
+ },
3148
+ {
3149
+ "epoch": 5.69,
3150
+ "learning_rate": 4.308678179645922e-05,
3151
+ "loss": 2.8433,
3152
+ "step": 52400
3153
+ },
3154
+ {
3155
+ "epoch": 5.7,
3156
+ "learning_rate": 4.2978168784620396e-05,
3157
+ "loss": 2.8015,
3158
+ "step": 52500
3159
+ },
3160
+ {
3161
+ "epoch": 5.71,
3162
+ "learning_rate": 4.286955577278158e-05,
3163
+ "loss": 2.8093,
3164
+ "step": 52600
3165
+ },
3166
+ {
3167
+ "epoch": 5.72,
3168
+ "learning_rate": 4.276094276094276e-05,
3169
+ "loss": 2.8235,
3170
+ "step": 52700
3171
+ },
3172
+ {
3173
+ "epoch": 5.73,
3174
+ "learning_rate": 4.265232974910394e-05,
3175
+ "loss": 2.7772,
3176
+ "step": 52800
3177
+ },
3178
+ {
3179
+ "epoch": 5.75,
3180
+ "learning_rate": 4.254371673726513e-05,
3181
+ "loss": 2.7632,
3182
+ "step": 52900
3183
+ },
3184
+ {
3185
+ "epoch": 5.76,
3186
+ "learning_rate": 4.243510372542631e-05,
3187
+ "loss": 2.9062,
3188
+ "step": 53000
3189
+ },
3190
+ {
3191
+ "epoch": 5.77,
3192
+ "learning_rate": 4.232649071358749e-05,
3193
+ "loss": 2.7796,
3194
+ "step": 53100
3195
+ },
3196
+ {
3197
+ "epoch": 5.78,
3198
+ "learning_rate": 4.221787770174867e-05,
3199
+ "loss": 2.7974,
3200
+ "step": 53200
3201
+ },
3202
+ {
3203
+ "epoch": 5.79,
3204
+ "learning_rate": 4.2109264689909855e-05,
3205
+ "loss": 2.8285,
3206
+ "step": 53300
3207
+ },
3208
+ {
3209
+ "epoch": 5.8,
3210
+ "learning_rate": 4.2000651678071035e-05,
3211
+ "loss": 2.8202,
3212
+ "step": 53400
3213
+ },
3214
+ {
3215
+ "epoch": 5.81,
3216
+ "learning_rate": 4.1892038666232215e-05,
3217
+ "loss": 2.8093,
3218
+ "step": 53500
3219
+ },
3220
+ {
3221
+ "epoch": 5.82,
3222
+ "learning_rate": 4.17834256543934e-05,
3223
+ "loss": 2.8685,
3224
+ "step": 53600
3225
+ },
3226
+ {
3227
+ "epoch": 5.83,
3228
+ "learning_rate": 4.167481264255458e-05,
3229
+ "loss": 2.8321,
3230
+ "step": 53700
3231
+ },
3232
+ {
3233
+ "epoch": 5.84,
3234
+ "learning_rate": 4.156619963071576e-05,
3235
+ "loss": 2.6883,
3236
+ "step": 53800
3237
+ },
3238
+ {
3239
+ "epoch": 5.85,
3240
+ "learning_rate": 4.145758661887694e-05,
3241
+ "loss": 2.7624,
3242
+ "step": 53900
3243
+ },
3244
+ {
3245
+ "epoch": 5.87,
3246
+ "learning_rate": 4.134897360703813e-05,
3247
+ "loss": 2.8609,
3248
+ "step": 54000
3249
+ },
3250
+ {
3251
+ "epoch": 5.88,
3252
+ "learning_rate": 4.124036059519931e-05,
3253
+ "loss": 2.8817,
3254
+ "step": 54100
3255
+ },
3256
+ {
3257
+ "epoch": 5.89,
3258
+ "learning_rate": 4.113174758336049e-05,
3259
+ "loss": 2.8336,
3260
+ "step": 54200
3261
+ },
3262
+ {
3263
+ "epoch": 5.9,
3264
+ "learning_rate": 4.102313457152167e-05,
3265
+ "loss": 2.8221,
3266
+ "step": 54300
3267
+ },
3268
+ {
3269
+ "epoch": 5.91,
3270
+ "learning_rate": 4.091452155968285e-05,
3271
+ "loss": 2.7564,
3272
+ "step": 54400
3273
+ },
3274
+ {
3275
+ "epoch": 5.92,
3276
+ "learning_rate": 4.0805908547844034e-05,
3277
+ "loss": 2.796,
3278
+ "step": 54500
3279
+ },
3280
+ {
3281
+ "epoch": 5.93,
3282
+ "learning_rate": 4.0697295536005214e-05,
3283
+ "loss": 2.7683,
3284
+ "step": 54600
3285
+ },
3286
+ {
3287
+ "epoch": 5.94,
3288
+ "learning_rate": 4.05886825241664e-05,
3289
+ "loss": 2.711,
3290
+ "step": 54700
3291
+ },
3292
+ {
3293
+ "epoch": 5.95,
3294
+ "learning_rate": 4.048006951232758e-05,
3295
+ "loss": 2.7996,
3296
+ "step": 54800
3297
+ },
3298
+ {
3299
+ "epoch": 5.96,
3300
+ "learning_rate": 4.037145650048876e-05,
3301
+ "loss": 2.7824,
3302
+ "step": 54900
3303
+ },
3304
+ {
3305
+ "epoch": 5.97,
3306
+ "learning_rate": 4.026284348864994e-05,
3307
+ "loss": 2.8153,
3308
+ "step": 55000
3309
+ },
3310
+ {
3311
+ "epoch": 5.98,
3312
+ "learning_rate": 4.015423047681112e-05,
3313
+ "loss": 2.8316,
3314
+ "step": 55100
3315
+ },
3316
+ {
3317
+ "epoch": 6.0,
3318
+ "learning_rate": 4.004561746497231e-05,
3319
+ "loss": 2.7809,
3320
+ "step": 55200
3321
+ },
3322
+ {
3323
+ "epoch": 6.01,
3324
+ "learning_rate": 3.993700445313349e-05,
3325
+ "loss": 2.745,
3326
+ "step": 55300
3327
+ },
3328
+ {
3329
+ "epoch": 6.02,
3330
+ "learning_rate": 3.9828391441294674e-05,
3331
+ "loss": 2.7401,
3332
+ "step": 55400
3333
+ },
3334
+ {
3335
+ "epoch": 6.03,
3336
+ "learning_rate": 3.9719778429455854e-05,
3337
+ "loss": 2.7371,
3338
+ "step": 55500
3339
+ },
3340
+ {
3341
+ "epoch": 6.04,
3342
+ "learning_rate": 3.961116541761703e-05,
3343
+ "loss": 2.723,
3344
+ "step": 55600
3345
+ },
3346
+ {
3347
+ "epoch": 6.05,
3348
+ "learning_rate": 3.9502552405778213e-05,
3349
+ "loss": 2.7057,
3350
+ "step": 55700
3351
+ },
3352
+ {
3353
+ "epoch": 6.06,
3354
+ "learning_rate": 3.939393939393939e-05,
3355
+ "loss": 2.8222,
3356
+ "step": 55800
3357
+ },
3358
+ {
3359
+ "epoch": 6.07,
3360
+ "learning_rate": 3.928532638210058e-05,
3361
+ "loss": 2.6662,
3362
+ "step": 55900
3363
+ },
3364
+ {
3365
+ "epoch": 6.08,
3366
+ "learning_rate": 3.917671337026176e-05,
3367
+ "loss": 2.7647,
3368
+ "step": 56000
3369
+ },
3370
+ {
3371
+ "epoch": 6.09,
3372
+ "learning_rate": 3.906810035842295e-05,
3373
+ "loss": 2.7936,
3374
+ "step": 56100
3375
+ },
3376
+ {
3377
+ "epoch": 6.1,
3378
+ "learning_rate": 3.895948734658412e-05,
3379
+ "loss": 2.7848,
3380
+ "step": 56200
3381
+ },
3382
+ {
3383
+ "epoch": 6.11,
3384
+ "learning_rate": 3.88508743347453e-05,
3385
+ "loss": 2.768,
3386
+ "step": 56300
3387
+ },
3388
+ {
3389
+ "epoch": 6.13,
3390
+ "learning_rate": 3.8742261322906486e-05,
3391
+ "loss": 2.7741,
3392
+ "step": 56400
3393
+ },
3394
+ {
3395
+ "epoch": 6.14,
3396
+ "learning_rate": 3.8633648311067666e-05,
3397
+ "loss": 2.7476,
3398
+ "step": 56500
3399
+ },
3400
+ {
3401
+ "epoch": 6.15,
3402
+ "learning_rate": 3.852503529922885e-05,
3403
+ "loss": 2.778,
3404
+ "step": 56600
3405
+ },
3406
+ {
3407
+ "epoch": 6.16,
3408
+ "learning_rate": 3.841642228739003e-05,
3409
+ "loss": 2.8299,
3410
+ "step": 56700
3411
+ },
3412
+ {
3413
+ "epoch": 6.17,
3414
+ "learning_rate": 3.830780927555121e-05,
3415
+ "loss": 2.785,
3416
+ "step": 56800
3417
+ },
3418
+ {
3419
+ "epoch": 6.18,
3420
+ "learning_rate": 3.819919626371239e-05,
3421
+ "loss": 2.6849,
3422
+ "step": 56900
3423
+ },
3424
+ {
3425
+ "epoch": 6.19,
3426
+ "learning_rate": 3.809058325187357e-05,
3427
+ "loss": 2.6925,
3428
+ "step": 57000
3429
+ },
3430
+ {
3431
+ "epoch": 6.2,
3432
+ "learning_rate": 3.798197024003476e-05,
3433
+ "loss": 2.6585,
3434
+ "step": 57100
3435
+ },
3436
+ {
3437
+ "epoch": 6.21,
3438
+ "learning_rate": 3.787335722819594e-05,
3439
+ "loss": 2.7174,
3440
+ "step": 57200
3441
+ },
3442
+ {
3443
+ "epoch": 6.22,
3444
+ "learning_rate": 3.7764744216357126e-05,
3445
+ "loss": 2.8318,
3446
+ "step": 57300
3447
+ },
3448
+ {
3449
+ "epoch": 6.23,
3450
+ "learning_rate": 3.7656131204518306e-05,
3451
+ "loss": 2.7448,
3452
+ "step": 57400
3453
+ },
3454
+ {
3455
+ "epoch": 6.25,
3456
+ "learning_rate": 3.7547518192679486e-05,
3457
+ "loss": 2.8137,
3458
+ "step": 57500
3459
+ },
3460
+ {
3461
+ "epoch": 6.26,
3462
+ "learning_rate": 3.7438905180840665e-05,
3463
+ "loss": 2.6344,
3464
+ "step": 57600
3465
+ },
3466
+ {
3467
+ "epoch": 6.27,
3468
+ "learning_rate": 3.7330292169001845e-05,
3469
+ "loss": 2.7126,
3470
+ "step": 57700
3471
+ },
3472
+ {
3473
+ "epoch": 6.28,
3474
+ "learning_rate": 3.722167915716303e-05,
3475
+ "loss": 2.7564,
3476
+ "step": 57800
3477
+ },
3478
+ {
3479
+ "epoch": 6.29,
3480
+ "learning_rate": 3.711306614532421e-05,
3481
+ "loss": 2.7657,
3482
+ "step": 57900
3483
+ },
3484
+ {
3485
+ "epoch": 6.3,
3486
+ "learning_rate": 3.700445313348539e-05,
3487
+ "loss": 2.8002,
3488
+ "step": 58000
3489
+ },
3490
+ {
3491
+ "epoch": 6.31,
3492
+ "learning_rate": 3.689584012164657e-05,
3493
+ "loss": 2.7179,
3494
+ "step": 58100
3495
+ },
3496
+ {
3497
+ "epoch": 6.32,
3498
+ "learning_rate": 3.678722710980776e-05,
3499
+ "loss": 2.7635,
3500
+ "step": 58200
3501
+ },
3502
+ {
3503
+ "epoch": 6.33,
3504
+ "learning_rate": 3.667861409796894e-05,
3505
+ "loss": 2.6482,
3506
+ "step": 58300
3507
+ },
3508
+ {
3509
+ "epoch": 6.34,
3510
+ "learning_rate": 3.657000108613012e-05,
3511
+ "loss": 2.7555,
3512
+ "step": 58400
3513
+ },
3514
+ {
3515
+ "epoch": 6.35,
3516
+ "learning_rate": 3.6461388074291305e-05,
3517
+ "loss": 2.7954,
3518
+ "step": 58500
3519
+ }
3520
+ ],
3521
+ "max_steps": 92070,
3522
+ "num_train_epochs": 10,
3523
+ "total_flos": 1.1996750282539008e+17,
3524
+ "trial_name": null,
3525
+ "trial_params": null
3526
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52604d1393aeba14e97237a974b338c69464ff44e31568207d80d68ee22a7ad
3
+ size 2607