lectura commited on
Commit
4bb2073
1 Parent(s): cddade5

Training in progress, step 7000, checkpoint

Browse files
checkpoint-7000/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nickypro/tinyllama-110M",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2048,
13
+ "max_position_embeddings": 1024,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "num_key_value_heads": 12,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.34.1",
25
+ "use_cache": true,
26
+ "vocab_size": 46336
27
+ }
checkpoint-7000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.1"
6
+ }
checkpoint-7000/global_step7000/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823d7c1f336783f9a6bacfbd5681421fb9c0c2daa6d6d6b53ed2849c745a6539
3
+ size 1687740870
checkpoint-7000/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step7000
checkpoint-7000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c0ad50a15fb959fd718321de9fc4e8337d0b9d35505d1c013ea7b4007b884b
3
+ size 312287814
checkpoint-7000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f71697e02a7a00d78e5f4633d0181679c97c9e16a7b39f9378cf8aae72d48e6
3
+ size 15984
checkpoint-7000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26015bfb9be7139574994fe7603addf2e71d8bf57031b90f99e371bcfe4fafec
3
+ size 15984
checkpoint-7000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75774522e80bb98374b17920ff45c82fcd69460df9604b4a70399d3bdfd3d5fb
3
+ size 15984
checkpoint-7000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4877faef429dbe9cb92549d3088592d9b8e9a246099b59dad748e2b471d789c5
3
+ size 15984
checkpoint-7000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d17b126e0f0fcecbe073550853c0dc0b866bc8f5a1dd664c6bcac8d3a96ac48
3
+ size 15984
checkpoint-7000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5dd95712bf6180b5c61c303b3519f3fcf5fc19d4740e4cb1c1a6a52ef2123b
3
+ size 15984
checkpoint-7000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ef18993ba2fdfdfe695a3debe50fcc84ccf44224ae37584c0404450b044362
3
+ size 15984
checkpoint-7000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59ac35ac8554b8f6a97002691d06e8a783578d9c59072be1c8c231d50c8eca9
3
+ size 15984
checkpoint-7000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b49d2ee36bc1b96c6fb1e319d68707fcd0ab0d4b5e51365f915521148bc3a1
3
+ size 1064
checkpoint-7000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-7000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7000/tokenizer_config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
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": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "46331": {
28
+ "content": "<|sep|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "46332": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "46333": {
44
+ "content": "<|acc|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "46334": {
52
+ "content": "<|rrn|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "46335": {
60
+ "content": "<|tel|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "legacy": false,
72
+ "model_max_length": 1000000000000000019884624838656,
73
+ "pad_token": "<unk>",
74
+ "sp_model_kwargs": {},
75
+ "tokenizer_class": "LlamaTokenizer",
76
+ "unk_token": "<unk>",
77
+ "use_default_system_prompt": true
78
+ }
checkpoint-7000/trainer_state.json ADDED
@@ -0,0 +1,4219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 68.62745098039215,
5
+ "eval_steps": 500,
6
+ "global_step": 7000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "learning_rate": 0.0003996,
14
+ "loss": 9.2736,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.2,
19
+ "learning_rate": 0.0003992,
20
+ "loss": 7.7626,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.29,
25
+ "learning_rate": 0.00039880000000000004,
26
+ "loss": 7.5202,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.39,
31
+ "learning_rate": 0.00039840000000000003,
32
+ "loss": 7.371,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.49,
37
+ "learning_rate": 0.000398,
38
+ "loss": 7.2352,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.59,
43
+ "learning_rate": 0.0003976,
44
+ "loss": 7.1352,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.69,
49
+ "learning_rate": 0.0003972,
50
+ "loss": 7.0625,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.78,
55
+ "learning_rate": 0.0003968,
56
+ "loss": 6.911,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.88,
61
+ "learning_rate": 0.00039640000000000004,
62
+ "loss": 6.7717,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.98,
67
+ "learning_rate": 0.00039600000000000003,
68
+ "loss": 6.6484,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 1.08,
73
+ "learning_rate": 0.0003956,
74
+ "loss": 6.5492,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 1.18,
79
+ "learning_rate": 0.0003952,
80
+ "loss": 6.4417,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 1.27,
85
+ "learning_rate": 0.0003948,
86
+ "loss": 6.3311,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 1.37,
91
+ "learning_rate": 0.0003944,
92
+ "loss": 6.2206,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 1.47,
97
+ "learning_rate": 0.00039400000000000004,
98
+ "loss": 6.1179,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 1.57,
103
+ "learning_rate": 0.0003936,
104
+ "loss": 6.0151,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 1.67,
109
+ "learning_rate": 0.0003932,
110
+ "loss": 5.9035,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 1.76,
115
+ "learning_rate": 0.0003928,
116
+ "loss": 5.8222,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 1.86,
121
+ "learning_rate": 0.0003924,
122
+ "loss": 5.7042,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 1.96,
127
+ "learning_rate": 0.000392,
128
+ "loss": 5.6265,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 2.06,
133
+ "learning_rate": 0.00039160000000000003,
134
+ "loss": 5.5338,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 2.16,
139
+ "learning_rate": 0.0003912,
140
+ "loss": 5.4521,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 2.25,
145
+ "learning_rate": 0.0003908,
146
+ "loss": 5.3552,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 2.35,
151
+ "learning_rate": 0.0003904,
152
+ "loss": 5.2771,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 2.45,
157
+ "learning_rate": 0.00039,
158
+ "loss": 5.1587,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 2.55,
163
+ "learning_rate": 0.0003896,
164
+ "loss": 5.0899,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 2.65,
169
+ "learning_rate": 0.00038920000000000003,
170
+ "loss": 5.0191,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 2.75,
175
+ "learning_rate": 0.0003888,
176
+ "loss": 4.9602,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 2.84,
181
+ "learning_rate": 0.0003884,
182
+ "loss": 4.8366,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 2.94,
187
+ "learning_rate": 0.000388,
188
+ "loss": 4.7848,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 3.04,
193
+ "learning_rate": 0.0003876,
194
+ "loss": 4.7199,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 3.14,
199
+ "learning_rate": 0.00038720000000000003,
200
+ "loss": 4.6306,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 3.24,
205
+ "learning_rate": 0.0003868,
206
+ "loss": 4.5337,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 3.33,
211
+ "learning_rate": 0.0003864,
212
+ "loss": 4.4796,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 3.43,
217
+ "learning_rate": 0.000386,
218
+ "loss": 4.3881,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 3.53,
223
+ "learning_rate": 0.0003856,
224
+ "loss": 4.2989,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 3.63,
229
+ "learning_rate": 0.0003852,
230
+ "loss": 4.2533,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 3.73,
235
+ "learning_rate": 0.00038480000000000003,
236
+ "loss": 4.2379,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 3.82,
241
+ "learning_rate": 0.0003844,
242
+ "loss": 4.142,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 3.92,
247
+ "learning_rate": 0.000384,
248
+ "loss": 4.0793,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 4.02,
253
+ "learning_rate": 0.0003836,
254
+ "loss": 4.0005,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 4.12,
259
+ "learning_rate": 0.0003832,
260
+ "loss": 3.9619,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 4.22,
265
+ "learning_rate": 0.0003828,
266
+ "loss": 3.8687,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 4.31,
271
+ "learning_rate": 0.0003824,
272
+ "loss": 3.8486,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 4.41,
277
+ "learning_rate": 0.000382,
278
+ "loss": 3.7684,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 4.51,
283
+ "learning_rate": 0.0003816,
284
+ "loss": 3.7013,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 4.61,
289
+ "learning_rate": 0.0003812,
290
+ "loss": 3.6851,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 4.71,
295
+ "learning_rate": 0.0003808,
296
+ "loss": 3.6585,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 4.8,
301
+ "learning_rate": 0.0003804,
302
+ "loss": 3.6172,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 4.9,
307
+ "learning_rate": 0.00038,
308
+ "loss": 3.5557,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 5.0,
313
+ "learning_rate": 0.0003796,
314
+ "loss": 3.4746,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 5.1,
319
+ "learning_rate": 0.0003792,
320
+ "loss": 3.4473,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 5.2,
325
+ "learning_rate": 0.0003788,
326
+ "loss": 3.3828,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 5.29,
331
+ "learning_rate": 0.0003784,
332
+ "loss": 3.3868,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 5.39,
337
+ "learning_rate": 0.00037799999999999997,
338
+ "loss": 3.31,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 5.49,
343
+ "learning_rate": 0.0003776,
344
+ "loss": 3.2628,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 5.59,
349
+ "learning_rate": 0.0003772,
350
+ "loss": 3.2541,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 5.69,
355
+ "learning_rate": 0.0003768,
356
+ "loss": 3.223,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 5.78,
361
+ "learning_rate": 0.0003764,
362
+ "loss": 3.2028,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 5.88,
367
+ "learning_rate": 0.000376,
368
+ "loss": 3.1659,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 5.98,
373
+ "learning_rate": 0.0003756,
374
+ "loss": 3.0847,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 6.08,
379
+ "learning_rate": 0.0003752,
380
+ "loss": 3.0215,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 6.18,
385
+ "learning_rate": 0.00037480000000000006,
386
+ "loss": 3.0149,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 6.27,
391
+ "learning_rate": 0.00037440000000000005,
392
+ "loss": 3.0177,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 6.37,
397
+ "learning_rate": 0.00037400000000000004,
398
+ "loss": 2.9474,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 6.47,
403
+ "learning_rate": 0.00037360000000000003,
404
+ "loss": 2.9245,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 6.57,
409
+ "learning_rate": 0.0003732,
410
+ "loss": 2.9218,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 6.67,
415
+ "learning_rate": 0.00037280000000000006,
416
+ "loss": 2.8666,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 6.76,
421
+ "learning_rate": 0.00037240000000000005,
422
+ "loss": 2.8821,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 6.86,
427
+ "learning_rate": 0.00037200000000000004,
428
+ "loss": 2.8243,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 6.96,
433
+ "learning_rate": 0.00037160000000000003,
434
+ "loss": 2.7753,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 7.06,
439
+ "learning_rate": 0.0003712,
440
+ "loss": 2.7086,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 7.16,
445
+ "learning_rate": 0.0003708,
446
+ "loss": 2.7104,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 7.25,
451
+ "learning_rate": 0.00037040000000000006,
452
+ "loss": 2.7103,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 7.35,
457
+ "learning_rate": 0.00037000000000000005,
458
+ "loss": 2.6707,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 7.45,
463
+ "learning_rate": 0.00036960000000000004,
464
+ "loss": 2.6413,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 7.55,
469
+ "learning_rate": 0.00036920000000000003,
470
+ "loss": 2.6359,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 7.65,
475
+ "learning_rate": 0.0003688,
476
+ "loss": 2.5838,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 7.75,
481
+ "learning_rate": 0.0003684,
482
+ "loss": 2.6212,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 7.84,
487
+ "learning_rate": 0.00036800000000000005,
488
+ "loss": 2.5718,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 7.94,
493
+ "learning_rate": 0.00036760000000000004,
494
+ "loss": 2.5348,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 8.04,
499
+ "learning_rate": 0.00036720000000000004,
500
+ "loss": 2.4195,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 8.14,
505
+ "learning_rate": 0.0003668,
506
+ "loss": 2.4938,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 8.24,
511
+ "learning_rate": 0.0003664,
512
+ "loss": 2.4372,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 8.33,
517
+ "learning_rate": 0.000366,
518
+ "loss": 2.4567,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 8.43,
523
+ "learning_rate": 0.00036560000000000005,
524
+ "loss": 2.4108,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 8.53,
529
+ "learning_rate": 0.00036520000000000004,
530
+ "loss": 2.3993,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 8.63,
535
+ "learning_rate": 0.00036480000000000003,
536
+ "loss": 2.3739,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 8.73,
541
+ "learning_rate": 0.0003644,
542
+ "loss": 2.391,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 8.82,
547
+ "learning_rate": 0.000364,
548
+ "loss": 2.38,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 8.92,
553
+ "learning_rate": 0.00036360000000000006,
554
+ "loss": 2.3257,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 9.02,
559
+ "learning_rate": 0.00036320000000000005,
560
+ "loss": 2.1956,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 9.12,
565
+ "learning_rate": 0.00036280000000000004,
566
+ "loss": 2.2944,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 9.22,
571
+ "learning_rate": 0.0003624,
572
+ "loss": 2.2163,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 9.31,
577
+ "learning_rate": 0.000362,
578
+ "loss": 2.2641,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 9.41,
583
+ "learning_rate": 0.0003616,
584
+ "loss": 2.2035,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 9.51,
589
+ "learning_rate": 0.00036120000000000005,
590
+ "loss": 2.188,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 9.61,
595
+ "learning_rate": 0.00036080000000000004,
596
+ "loss": 2.197,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 9.71,
601
+ "learning_rate": 0.00036040000000000003,
602
+ "loss": 2.18,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 9.8,
607
+ "learning_rate": 0.00036,
608
+ "loss": 2.1994,
609
+ "step": 1000
610
+ },
611
+ {
612
+ "epoch": 9.9,
613
+ "learning_rate": 0.0003596,
614
+ "loss": 2.1538,
615
+ "step": 1010
616
+ },
617
+ {
618
+ "epoch": 10.0,
619
+ "learning_rate": 0.0003592,
620
+ "loss": 2.0495,
621
+ "step": 1020
622
+ },
623
+ {
624
+ "epoch": 10.1,
625
+ "learning_rate": 0.00035880000000000005,
626
+ "loss": 2.0501,
627
+ "step": 1030
628
+ },
629
+ {
630
+ "epoch": 10.2,
631
+ "learning_rate": 0.00035840000000000004,
632
+ "loss": 2.0302,
633
+ "step": 1040
634
+ },
635
+ {
636
+ "epoch": 10.29,
637
+ "learning_rate": 0.00035800000000000003,
638
+ "loss": 2.0996,
639
+ "step": 1050
640
+ },
641
+ {
642
+ "epoch": 10.39,
643
+ "learning_rate": 0.0003576,
644
+ "loss": 2.0369,
645
+ "step": 1060
646
+ },
647
+ {
648
+ "epoch": 10.49,
649
+ "learning_rate": 0.0003572,
650
+ "loss": 1.9996,
651
+ "step": 1070
652
+ },
653
+ {
654
+ "epoch": 10.59,
655
+ "learning_rate": 0.0003568,
656
+ "loss": 2.0254,
657
+ "step": 1080
658
+ },
659
+ {
660
+ "epoch": 10.69,
661
+ "learning_rate": 0.00035640000000000004,
662
+ "loss": 2.0004,
663
+ "step": 1090
664
+ },
665
+ {
666
+ "epoch": 10.78,
667
+ "learning_rate": 0.00035600000000000003,
668
+ "loss": 2.0154,
669
+ "step": 1100
670
+ },
671
+ {
672
+ "epoch": 10.88,
673
+ "learning_rate": 0.0003556,
674
+ "loss": 2.0014,
675
+ "step": 1110
676
+ },
677
+ {
678
+ "epoch": 10.98,
679
+ "learning_rate": 0.00035524,
680
+ "loss": 1.9377,
681
+ "step": 1120
682
+ },
683
+ {
684
+ "epoch": 11.08,
685
+ "learning_rate": 0.00035484000000000004,
686
+ "loss": 1.8296,
687
+ "step": 1130
688
+ },
689
+ {
690
+ "epoch": 11.18,
691
+ "learning_rate": 0.00035444000000000003,
692
+ "loss": 1.9002,
693
+ "step": 1140
694
+ },
695
+ {
696
+ "epoch": 11.27,
697
+ "learning_rate": 0.00035404,
698
+ "loss": 1.9336,
699
+ "step": 1150
700
+ },
701
+ {
702
+ "epoch": 11.37,
703
+ "learning_rate": 0.00035364,
704
+ "loss": 1.9041,
705
+ "step": 1160
706
+ },
707
+ {
708
+ "epoch": 11.47,
709
+ "learning_rate": 0.00035324,
710
+ "loss": 1.8324,
711
+ "step": 1170
712
+ },
713
+ {
714
+ "epoch": 11.57,
715
+ "learning_rate": 0.00035284,
716
+ "loss": 1.8663,
717
+ "step": 1180
718
+ },
719
+ {
720
+ "epoch": 11.67,
721
+ "learning_rate": 0.00035244000000000003,
722
+ "loss": 1.8358,
723
+ "step": 1190
724
+ },
725
+ {
726
+ "epoch": 11.76,
727
+ "learning_rate": 0.00035204,
728
+ "loss": 1.8586,
729
+ "step": 1200
730
+ },
731
+ {
732
+ "epoch": 11.86,
733
+ "learning_rate": 0.00035164,
734
+ "loss": 1.8452,
735
+ "step": 1210
736
+ },
737
+ {
738
+ "epoch": 11.96,
739
+ "learning_rate": 0.00035124,
740
+ "loss": 1.7957,
741
+ "step": 1220
742
+ },
743
+ {
744
+ "epoch": 12.06,
745
+ "learning_rate": 0.00035084,
746
+ "loss": 1.6603,
747
+ "step": 1230
748
+ },
749
+ {
750
+ "epoch": 12.16,
751
+ "learning_rate": 0.00035044000000000004,
752
+ "loss": 1.7903,
753
+ "step": 1240
754
+ },
755
+ {
756
+ "epoch": 12.25,
757
+ "learning_rate": 0.00035004000000000003,
758
+ "loss": 1.7574,
759
+ "step": 1250
760
+ },
761
+ {
762
+ "epoch": 12.35,
763
+ "learning_rate": 0.00034964,
764
+ "loss": 1.7823,
765
+ "step": 1260
766
+ },
767
+ {
768
+ "epoch": 12.45,
769
+ "learning_rate": 0.00034924,
770
+ "loss": 1.7038,
771
+ "step": 1270
772
+ },
773
+ {
774
+ "epoch": 12.55,
775
+ "learning_rate": 0.00034884,
776
+ "loss": 1.7186,
777
+ "step": 1280
778
+ },
779
+ {
780
+ "epoch": 12.65,
781
+ "learning_rate": 0.00034844,
782
+ "loss": 1.6948,
783
+ "step": 1290
784
+ },
785
+ {
786
+ "epoch": 12.75,
787
+ "learning_rate": 0.00034804000000000004,
788
+ "loss": 1.7347,
789
+ "step": 1300
790
+ },
791
+ {
792
+ "epoch": 12.84,
793
+ "learning_rate": 0.00034764,
794
+ "loss": 1.7304,
795
+ "step": 1310
796
+ },
797
+ {
798
+ "epoch": 12.94,
799
+ "learning_rate": 0.00034724,
800
+ "loss": 1.6862,
801
+ "step": 1320
802
+ },
803
+ {
804
+ "epoch": 13.04,
805
+ "learning_rate": 0.00034684,
806
+ "loss": 1.4857,
807
+ "step": 1330
808
+ },
809
+ {
810
+ "epoch": 13.14,
811
+ "learning_rate": 0.00034644,
812
+ "loss": 1.6981,
813
+ "step": 1340
814
+ },
815
+ {
816
+ "epoch": 13.24,
817
+ "learning_rate": 0.00034604,
818
+ "loss": 1.5926,
819
+ "step": 1350
820
+ },
821
+ {
822
+ "epoch": 13.33,
823
+ "learning_rate": 0.00034564000000000003,
824
+ "loss": 1.6545,
825
+ "step": 1360
826
+ },
827
+ {
828
+ "epoch": 13.43,
829
+ "learning_rate": 0.00034524,
830
+ "loss": 1.5918,
831
+ "step": 1370
832
+ },
833
+ {
834
+ "epoch": 13.53,
835
+ "learning_rate": 0.00034484,
836
+ "loss": 1.5743,
837
+ "step": 1380
838
+ },
839
+ {
840
+ "epoch": 13.63,
841
+ "learning_rate": 0.00034444,
842
+ "loss": 1.5867,
843
+ "step": 1390
844
+ },
845
+ {
846
+ "epoch": 13.73,
847
+ "learning_rate": 0.00034404,
848
+ "loss": 1.6042,
849
+ "step": 1400
850
+ },
851
+ {
852
+ "epoch": 13.82,
853
+ "learning_rate": 0.00034364,
854
+ "loss": 1.6308,
855
+ "step": 1410
856
+ },
857
+ {
858
+ "epoch": 13.92,
859
+ "learning_rate": 0.00034324000000000003,
860
+ "loss": 1.5813,
861
+ "step": 1420
862
+ },
863
+ {
864
+ "epoch": 14.02,
865
+ "learning_rate": 0.00034284,
866
+ "loss": 1.364,
867
+ "step": 1430
868
+ },
869
+ {
870
+ "epoch": 14.12,
871
+ "learning_rate": 0.00034244,
872
+ "loss": 1.5849,
873
+ "step": 1440
874
+ },
875
+ {
876
+ "epoch": 14.22,
877
+ "learning_rate": 0.00034204,
878
+ "loss": 1.4957,
879
+ "step": 1450
880
+ },
881
+ {
882
+ "epoch": 14.31,
883
+ "learning_rate": 0.00034164,
884
+ "loss": 1.5312,
885
+ "step": 1460
886
+ },
887
+ {
888
+ "epoch": 14.41,
889
+ "learning_rate": 0.00034124,
890
+ "loss": 1.4995,
891
+ "step": 1470
892
+ },
893
+ {
894
+ "epoch": 14.51,
895
+ "learning_rate": 0.00034084,
896
+ "loss": 1.4501,
897
+ "step": 1480
898
+ },
899
+ {
900
+ "epoch": 14.61,
901
+ "learning_rate": 0.00034044,
902
+ "loss": 1.4721,
903
+ "step": 1490
904
+ },
905
+ {
906
+ "epoch": 14.71,
907
+ "learning_rate": 0.00034004,
908
+ "loss": 1.4792,
909
+ "step": 1500
910
+ },
911
+ {
912
+ "epoch": 14.8,
913
+ "learning_rate": 0.00033964,
914
+ "loss": 1.513,
915
+ "step": 1510
916
+ },
917
+ {
918
+ "epoch": 14.9,
919
+ "learning_rate": 0.00033924,
920
+ "loss": 1.5028,
921
+ "step": 1520
922
+ },
923
+ {
924
+ "epoch": 15.0,
925
+ "learning_rate": 0.00033884000000000003,
926
+ "loss": 1.3511,
927
+ "step": 1530
928
+ },
929
+ {
930
+ "epoch": 15.1,
931
+ "learning_rate": 0.00033844,
932
+ "loss": 1.4152,
933
+ "step": 1540
934
+ },
935
+ {
936
+ "epoch": 15.2,
937
+ "learning_rate": 0.00033804,
938
+ "loss": 1.4216,
939
+ "step": 1550
940
+ },
941
+ {
942
+ "epoch": 15.29,
943
+ "learning_rate": 0.00033764,
944
+ "loss": 1.4177,
945
+ "step": 1560
946
+ },
947
+ {
948
+ "epoch": 15.39,
949
+ "learning_rate": 0.00033724,
950
+ "loss": 1.4074,
951
+ "step": 1570
952
+ },
953
+ {
954
+ "epoch": 15.49,
955
+ "learning_rate": 0.00033684,
956
+ "loss": 1.3532,
957
+ "step": 1580
958
+ },
959
+ {
960
+ "epoch": 15.59,
961
+ "learning_rate": 0.00033644,
962
+ "loss": 1.3525,
963
+ "step": 1590
964
+ },
965
+ {
966
+ "epoch": 15.69,
967
+ "learning_rate": 0.00033604,
968
+ "loss": 1.3755,
969
+ "step": 1600
970
+ },
971
+ {
972
+ "epoch": 15.78,
973
+ "learning_rate": 0.00033564,
974
+ "loss": 1.3989,
975
+ "step": 1610
976
+ },
977
+ {
978
+ "epoch": 15.88,
979
+ "learning_rate": 0.00033524,
980
+ "loss": 1.4012,
981
+ "step": 1620
982
+ },
983
+ {
984
+ "epoch": 15.98,
985
+ "learning_rate": 0.00033484,
986
+ "loss": 1.3386,
987
+ "step": 1630
988
+ },
989
+ {
990
+ "epoch": 16.08,
991
+ "learning_rate": 0.00033444,
992
+ "loss": 1.2476,
993
+ "step": 1640
994
+ },
995
+ {
996
+ "epoch": 16.18,
997
+ "learning_rate": 0.00033404,
998
+ "loss": 1.3435,
999
+ "step": 1650
1000
+ },
1001
+ {
1002
+ "epoch": 16.27,
1003
+ "learning_rate": 0.00033364,
1004
+ "loss": 1.3131,
1005
+ "step": 1660
1006
+ },
1007
+ {
1008
+ "epoch": 16.37,
1009
+ "learning_rate": 0.00033324,
1010
+ "loss": 1.3099,
1011
+ "step": 1670
1012
+ },
1013
+ {
1014
+ "epoch": 16.47,
1015
+ "learning_rate": 0.00033284,
1016
+ "loss": 1.2693,
1017
+ "step": 1680
1018
+ },
1019
+ {
1020
+ "epoch": 16.57,
1021
+ "learning_rate": 0.00033244,
1022
+ "loss": 1.2649,
1023
+ "step": 1690
1024
+ },
1025
+ {
1026
+ "epoch": 16.67,
1027
+ "learning_rate": 0.00033203999999999997,
1028
+ "loss": 1.2777,
1029
+ "step": 1700
1030
+ },
1031
+ {
1032
+ "epoch": 16.76,
1033
+ "learning_rate": 0.00033164,
1034
+ "loss": 1.2889,
1035
+ "step": 1710
1036
+ },
1037
+ {
1038
+ "epoch": 16.86,
1039
+ "learning_rate": 0.00033124,
1040
+ "loss": 1.2729,
1041
+ "step": 1720
1042
+ },
1043
+ {
1044
+ "epoch": 16.96,
1045
+ "learning_rate": 0.00033084,
1046
+ "loss": 1.2529,
1047
+ "step": 1730
1048
+ },
1049
+ {
1050
+ "epoch": 17.06,
1051
+ "learning_rate": 0.00033044,
1052
+ "loss": 1.1566,
1053
+ "step": 1740
1054
+ },
1055
+ {
1056
+ "epoch": 17.16,
1057
+ "learning_rate": 0.00033004,
1058
+ "loss": 1.2668,
1059
+ "step": 1750
1060
+ },
1061
+ {
1062
+ "epoch": 17.25,
1063
+ "learning_rate": 0.00032964,
1064
+ "loss": 1.2052,
1065
+ "step": 1760
1066
+ },
1067
+ {
1068
+ "epoch": 17.35,
1069
+ "learning_rate": 0.00032924,
1070
+ "loss": 1.2159,
1071
+ "step": 1770
1072
+ },
1073
+ {
1074
+ "epoch": 17.45,
1075
+ "learning_rate": 0.00032884000000000006,
1076
+ "loss": 1.2003,
1077
+ "step": 1780
1078
+ },
1079
+ {
1080
+ "epoch": 17.55,
1081
+ "learning_rate": 0.00032844000000000005,
1082
+ "loss": 1.1836,
1083
+ "step": 1790
1084
+ },
1085
+ {
1086
+ "epoch": 17.65,
1087
+ "learning_rate": 0.00032804000000000004,
1088
+ "loss": 1.1857,
1089
+ "step": 1800
1090
+ },
1091
+ {
1092
+ "epoch": 17.75,
1093
+ "learning_rate": 0.00032764000000000003,
1094
+ "loss": 1.2012,
1095
+ "step": 1810
1096
+ },
1097
+ {
1098
+ "epoch": 17.84,
1099
+ "learning_rate": 0.00032724,
1100
+ "loss": 1.1907,
1101
+ "step": 1820
1102
+ },
1103
+ {
1104
+ "epoch": 17.94,
1105
+ "learning_rate": 0.00032684,
1106
+ "loss": 1.1723,
1107
+ "step": 1830
1108
+ },
1109
+ {
1110
+ "epoch": 18.04,
1111
+ "learning_rate": 0.00032644000000000005,
1112
+ "loss": 1.0299,
1113
+ "step": 1840
1114
+ },
1115
+ {
1116
+ "epoch": 18.14,
1117
+ "learning_rate": 0.00032604000000000004,
1118
+ "loss": 1.1996,
1119
+ "step": 1850
1120
+ },
1121
+ {
1122
+ "epoch": 18.24,
1123
+ "learning_rate": 0.00032564000000000003,
1124
+ "loss": 1.0919,
1125
+ "step": 1860
1126
+ },
1127
+ {
1128
+ "epoch": 18.33,
1129
+ "learning_rate": 0.00032524,
1130
+ "loss": 1.1291,
1131
+ "step": 1870
1132
+ },
1133
+ {
1134
+ "epoch": 18.43,
1135
+ "learning_rate": 0.00032484,
1136
+ "loss": 1.1343,
1137
+ "step": 1880
1138
+ },
1139
+ {
1140
+ "epoch": 18.53,
1141
+ "learning_rate": 0.00032444000000000006,
1142
+ "loss": 1.0965,
1143
+ "step": 1890
1144
+ },
1145
+ {
1146
+ "epoch": 18.63,
1147
+ "learning_rate": 0.00032404000000000005,
1148
+ "loss": 1.1149,
1149
+ "step": 1900
1150
+ },
1151
+ {
1152
+ "epoch": 18.73,
1153
+ "learning_rate": 0.00032364000000000004,
1154
+ "loss": 1.132,
1155
+ "step": 1910
1156
+ },
1157
+ {
1158
+ "epoch": 18.82,
1159
+ "learning_rate": 0.00032324000000000003,
1160
+ "loss": 1.1218,
1161
+ "step": 1920
1162
+ },
1163
+ {
1164
+ "epoch": 18.92,
1165
+ "learning_rate": 0.00032284,
1166
+ "loss": 1.0928,
1167
+ "step": 1930
1168
+ },
1169
+ {
1170
+ "epoch": 19.02,
1171
+ "learning_rate": 0.00032244,
1172
+ "loss": 0.9377,
1173
+ "step": 1940
1174
+ },
1175
+ {
1176
+ "epoch": 19.12,
1177
+ "learning_rate": 0.00032204000000000005,
1178
+ "loss": 1.1132,
1179
+ "step": 1950
1180
+ },
1181
+ {
1182
+ "epoch": 19.22,
1183
+ "learning_rate": 0.00032164000000000004,
1184
+ "loss": 1.0275,
1185
+ "step": 1960
1186
+ },
1187
+ {
1188
+ "epoch": 19.31,
1189
+ "learning_rate": 0.00032124000000000003,
1190
+ "loss": 1.0312,
1191
+ "step": 1970
1192
+ },
1193
+ {
1194
+ "epoch": 19.41,
1195
+ "learning_rate": 0.00032084,
1196
+ "loss": 1.0248,
1197
+ "step": 1980
1198
+ },
1199
+ {
1200
+ "epoch": 19.51,
1201
+ "learning_rate": 0.00032044,
1202
+ "loss": 1.0063,
1203
+ "step": 1990
1204
+ },
1205
+ {
1206
+ "epoch": 19.61,
1207
+ "learning_rate": 0.00032004,
1208
+ "loss": 1.0438,
1209
+ "step": 2000
1210
+ },
1211
+ {
1212
+ "epoch": 19.71,
1213
+ "learning_rate": 0.00031964000000000005,
1214
+ "loss": 1.0608,
1215
+ "step": 2010
1216
+ },
1217
+ {
1218
+ "epoch": 19.8,
1219
+ "learning_rate": 0.00031924000000000004,
1220
+ "loss": 1.0503,
1221
+ "step": 2020
1222
+ },
1223
+ {
1224
+ "epoch": 19.9,
1225
+ "learning_rate": 0.00031884000000000003,
1226
+ "loss": 1.0422,
1227
+ "step": 2030
1228
+ },
1229
+ {
1230
+ "epoch": 20.0,
1231
+ "learning_rate": 0.00031844,
1232
+ "loss": 0.9331,
1233
+ "step": 2040
1234
+ },
1235
+ {
1236
+ "epoch": 20.1,
1237
+ "learning_rate": 0.00031804,
1238
+ "loss": 0.9744,
1239
+ "step": 2050
1240
+ },
1241
+ {
1242
+ "epoch": 20.2,
1243
+ "learning_rate": 0.00031768000000000003,
1244
+ "loss": 0.9977,
1245
+ "step": 2060
1246
+ },
1247
+ {
1248
+ "epoch": 20.29,
1249
+ "learning_rate": 0.00031728,
1250
+ "loss": 0.9579,
1251
+ "step": 2070
1252
+ },
1253
+ {
1254
+ "epoch": 20.39,
1255
+ "learning_rate": 0.00031688,
1256
+ "loss": 0.908,
1257
+ "step": 2080
1258
+ },
1259
+ {
1260
+ "epoch": 20.49,
1261
+ "learning_rate": 0.00031648,
1262
+ "loss": 0.9323,
1263
+ "step": 2090
1264
+ },
1265
+ {
1266
+ "epoch": 20.59,
1267
+ "learning_rate": 0.00031608,
1268
+ "loss": 0.9597,
1269
+ "step": 2100
1270
+ },
1271
+ {
1272
+ "epoch": 20.69,
1273
+ "learning_rate": 0.00031568000000000004,
1274
+ "loss": 0.975,
1275
+ "step": 2110
1276
+ },
1277
+ {
1278
+ "epoch": 20.78,
1279
+ "learning_rate": 0.00031528000000000003,
1280
+ "loss": 0.9676,
1281
+ "step": 2120
1282
+ },
1283
+ {
1284
+ "epoch": 20.88,
1285
+ "learning_rate": 0.00031488,
1286
+ "loss": 0.979,
1287
+ "step": 2130
1288
+ },
1289
+ {
1290
+ "epoch": 20.98,
1291
+ "learning_rate": 0.00031448,
1292
+ "loss": 0.9263,
1293
+ "step": 2140
1294
+ },
1295
+ {
1296
+ "epoch": 21.08,
1297
+ "learning_rate": 0.00031408,
1298
+ "loss": 0.8463,
1299
+ "step": 2150
1300
+ },
1301
+ {
1302
+ "epoch": 21.18,
1303
+ "learning_rate": 0.00031368,
1304
+ "loss": 0.9642,
1305
+ "step": 2160
1306
+ },
1307
+ {
1308
+ "epoch": 21.27,
1309
+ "learning_rate": 0.00031328000000000004,
1310
+ "loss": 0.8091,
1311
+ "step": 2170
1312
+ },
1313
+ {
1314
+ "epoch": 21.37,
1315
+ "learning_rate": 0.00031288,
1316
+ "loss": 0.7911,
1317
+ "step": 2180
1318
+ },
1319
+ {
1320
+ "epoch": 21.47,
1321
+ "learning_rate": 0.00031248,
1322
+ "loss": 0.8679,
1323
+ "step": 2190
1324
+ },
1325
+ {
1326
+ "epoch": 21.57,
1327
+ "learning_rate": 0.00031208,
1328
+ "loss": 0.893,
1329
+ "step": 2200
1330
+ },
1331
+ {
1332
+ "epoch": 21.67,
1333
+ "learning_rate": 0.00031168,
1334
+ "loss": 0.9048,
1335
+ "step": 2210
1336
+ },
1337
+ {
1338
+ "epoch": 21.76,
1339
+ "learning_rate": 0.00031128000000000004,
1340
+ "loss": 0.9283,
1341
+ "step": 2220
1342
+ },
1343
+ {
1344
+ "epoch": 21.86,
1345
+ "learning_rate": 0.00031088000000000003,
1346
+ "loss": 0.9238,
1347
+ "step": 2230
1348
+ },
1349
+ {
1350
+ "epoch": 21.96,
1351
+ "learning_rate": 0.00031048,
1352
+ "loss": 0.8698,
1353
+ "step": 2240
1354
+ },
1355
+ {
1356
+ "epoch": 22.06,
1357
+ "learning_rate": 0.00031008,
1358
+ "loss": 0.794,
1359
+ "step": 2250
1360
+ },
1361
+ {
1362
+ "epoch": 22.16,
1363
+ "learning_rate": 0.00030968,
1364
+ "loss": 0.8646,
1365
+ "step": 2260
1366
+ },
1367
+ {
1368
+ "epoch": 22.25,
1369
+ "learning_rate": 0.00030928,
1370
+ "loss": 0.7995,
1371
+ "step": 2270
1372
+ },
1373
+ {
1374
+ "epoch": 22.35,
1375
+ "learning_rate": 0.00030888000000000004,
1376
+ "loss": 0.8045,
1377
+ "step": 2280
1378
+ },
1379
+ {
1380
+ "epoch": 22.45,
1381
+ "learning_rate": 0.00030848000000000003,
1382
+ "loss": 0.8186,
1383
+ "step": 2290
1384
+ },
1385
+ {
1386
+ "epoch": 22.55,
1387
+ "learning_rate": 0.00030808,
1388
+ "loss": 0.8085,
1389
+ "step": 2300
1390
+ },
1391
+ {
1392
+ "epoch": 22.65,
1393
+ "learning_rate": 0.00030768,
1394
+ "loss": 0.8098,
1395
+ "step": 2310
1396
+ },
1397
+ {
1398
+ "epoch": 22.75,
1399
+ "learning_rate": 0.00030728,
1400
+ "loss": 0.8741,
1401
+ "step": 2320
1402
+ },
1403
+ {
1404
+ "epoch": 22.84,
1405
+ "learning_rate": 0.00030688,
1406
+ "loss": 0.8602,
1407
+ "step": 2330
1408
+ },
1409
+ {
1410
+ "epoch": 22.94,
1411
+ "learning_rate": 0.00030648000000000003,
1412
+ "loss": 0.7975,
1413
+ "step": 2340
1414
+ },
1415
+ {
1416
+ "epoch": 23.04,
1417
+ "learning_rate": 0.00030608,
1418
+ "loss": 0.6979,
1419
+ "step": 2350
1420
+ },
1421
+ {
1422
+ "epoch": 23.14,
1423
+ "learning_rate": 0.00030568,
1424
+ "loss": 0.8089,
1425
+ "step": 2360
1426
+ },
1427
+ {
1428
+ "epoch": 23.24,
1429
+ "learning_rate": 0.00030528,
1430
+ "loss": 0.7418,
1431
+ "step": 2370
1432
+ },
1433
+ {
1434
+ "epoch": 23.33,
1435
+ "learning_rate": 0.00030488,
1436
+ "loss": 0.752,
1437
+ "step": 2380
1438
+ },
1439
+ {
1440
+ "epoch": 23.43,
1441
+ "learning_rate": 0.00030448,
1442
+ "loss": 0.7302,
1443
+ "step": 2390
1444
+ },
1445
+ {
1446
+ "epoch": 23.53,
1447
+ "learning_rate": 0.00030408000000000003,
1448
+ "loss": 0.7431,
1449
+ "step": 2400
1450
+ },
1451
+ {
1452
+ "epoch": 23.63,
1453
+ "learning_rate": 0.00030368,
1454
+ "loss": 0.7443,
1455
+ "step": 2410
1456
+ },
1457
+ {
1458
+ "epoch": 23.73,
1459
+ "learning_rate": 0.00030328,
1460
+ "loss": 0.7954,
1461
+ "step": 2420
1462
+ },
1463
+ {
1464
+ "epoch": 23.82,
1465
+ "learning_rate": 0.00030288,
1466
+ "loss": 0.8135,
1467
+ "step": 2430
1468
+ },
1469
+ {
1470
+ "epoch": 23.92,
1471
+ "learning_rate": 0.00030248,
1472
+ "loss": 0.7517,
1473
+ "step": 2440
1474
+ },
1475
+ {
1476
+ "epoch": 24.02,
1477
+ "learning_rate": 0.00030208,
1478
+ "loss": 0.6313,
1479
+ "step": 2450
1480
+ },
1481
+ {
1482
+ "epoch": 24.12,
1483
+ "learning_rate": 0.00030168,
1484
+ "loss": 0.7276,
1485
+ "step": 2460
1486
+ },
1487
+ {
1488
+ "epoch": 24.22,
1489
+ "learning_rate": 0.00030128,
1490
+ "loss": 0.6859,
1491
+ "step": 2470
1492
+ },
1493
+ {
1494
+ "epoch": 24.31,
1495
+ "learning_rate": 0.00030088,
1496
+ "loss": 0.6701,
1497
+ "step": 2480
1498
+ },
1499
+ {
1500
+ "epoch": 24.41,
1501
+ "learning_rate": 0.00030048,
1502
+ "loss": 0.6492,
1503
+ "step": 2490
1504
+ },
1505
+ {
1506
+ "epoch": 24.51,
1507
+ "learning_rate": 0.00030008,
1508
+ "loss": 0.7006,
1509
+ "step": 2500
1510
+ },
1511
+ {
1512
+ "epoch": 24.61,
1513
+ "learning_rate": 0.00029968000000000003,
1514
+ "loss": 0.7105,
1515
+ "step": 2510
1516
+ },
1517
+ {
1518
+ "epoch": 24.71,
1519
+ "learning_rate": 0.00029928,
1520
+ "loss": 0.7175,
1521
+ "step": 2520
1522
+ },
1523
+ {
1524
+ "epoch": 24.8,
1525
+ "learning_rate": 0.00029888,
1526
+ "loss": 0.7297,
1527
+ "step": 2530
1528
+ },
1529
+ {
1530
+ "epoch": 24.9,
1531
+ "learning_rate": 0.00029848,
1532
+ "loss": 0.7295,
1533
+ "step": 2540
1534
+ },
1535
+ {
1536
+ "epoch": 25.0,
1537
+ "learning_rate": 0.00029808,
1538
+ "loss": 0.6337,
1539
+ "step": 2550
1540
+ },
1541
+ {
1542
+ "epoch": 25.1,
1543
+ "learning_rate": 0.00029768,
1544
+ "loss": 0.6452,
1545
+ "step": 2560
1546
+ },
1547
+ {
1548
+ "epoch": 25.2,
1549
+ "learning_rate": 0.00029728,
1550
+ "loss": 0.6282,
1551
+ "step": 2570
1552
+ },
1553
+ {
1554
+ "epoch": 25.29,
1555
+ "learning_rate": 0.00029688,
1556
+ "loss": 0.6218,
1557
+ "step": 2580
1558
+ },
1559
+ {
1560
+ "epoch": 25.39,
1561
+ "learning_rate": 0.00029648,
1562
+ "loss": 0.5982,
1563
+ "step": 2590
1564
+ },
1565
+ {
1566
+ "epoch": 25.49,
1567
+ "learning_rate": 0.00029608,
1568
+ "loss": 0.6601,
1569
+ "step": 2600
1570
+ },
1571
+ {
1572
+ "epoch": 25.59,
1573
+ "learning_rate": 0.00029568,
1574
+ "loss": 0.6761,
1575
+ "step": 2610
1576
+ },
1577
+ {
1578
+ "epoch": 25.69,
1579
+ "learning_rate": 0.00029528,
1580
+ "loss": 0.6685,
1581
+ "step": 2620
1582
+ },
1583
+ {
1584
+ "epoch": 25.78,
1585
+ "learning_rate": 0.00029488,
1586
+ "loss": 0.6506,
1587
+ "step": 2630
1588
+ },
1589
+ {
1590
+ "epoch": 25.88,
1591
+ "learning_rate": 0.00029448,
1592
+ "loss": 0.6804,
1593
+ "step": 2640
1594
+ },
1595
+ {
1596
+ "epoch": 25.98,
1597
+ "learning_rate": 0.00029408,
1598
+ "loss": 0.6387,
1599
+ "step": 2650
1600
+ },
1601
+ {
1602
+ "epoch": 26.08,
1603
+ "learning_rate": 0.00029368,
1604
+ "loss": 0.5516,
1605
+ "step": 2660
1606
+ },
1607
+ {
1608
+ "epoch": 26.18,
1609
+ "learning_rate": 0.00029328,
1610
+ "loss": 0.5891,
1611
+ "step": 2670
1612
+ },
1613
+ {
1614
+ "epoch": 26.27,
1615
+ "learning_rate": 0.00029288,
1616
+ "loss": 0.5907,
1617
+ "step": 2680
1618
+ },
1619
+ {
1620
+ "epoch": 26.37,
1621
+ "learning_rate": 0.00029248,
1622
+ "loss": 0.5559,
1623
+ "step": 2690
1624
+ },
1625
+ {
1626
+ "epoch": 26.47,
1627
+ "learning_rate": 0.00029208,
1628
+ "loss": 0.5942,
1629
+ "step": 2700
1630
+ },
1631
+ {
1632
+ "epoch": 26.57,
1633
+ "learning_rate": 0.00029168,
1634
+ "loss": 0.625,
1635
+ "step": 2710
1636
+ },
1637
+ {
1638
+ "epoch": 26.67,
1639
+ "learning_rate": 0.00029128,
1640
+ "loss": 0.621,
1641
+ "step": 2720
1642
+ },
1643
+ {
1644
+ "epoch": 26.76,
1645
+ "learning_rate": 0.00029088,
1646
+ "loss": 0.5987,
1647
+ "step": 2730
1648
+ },
1649
+ {
1650
+ "epoch": 26.86,
1651
+ "learning_rate": 0.00029047999999999997,
1652
+ "loss": 0.6137,
1653
+ "step": 2740
1654
+ },
1655
+ {
1656
+ "epoch": 26.96,
1657
+ "learning_rate": 0.00029008,
1658
+ "loss": 0.5928,
1659
+ "step": 2750
1660
+ },
1661
+ {
1662
+ "epoch": 27.06,
1663
+ "learning_rate": 0.00028968,
1664
+ "loss": 0.5423,
1665
+ "step": 2760
1666
+ },
1667
+ {
1668
+ "epoch": 27.16,
1669
+ "learning_rate": 0.00028928,
1670
+ "loss": 0.5484,
1671
+ "step": 2770
1672
+ },
1673
+ {
1674
+ "epoch": 27.25,
1675
+ "learning_rate": 0.00028888,
1676
+ "loss": 0.563,
1677
+ "step": 2780
1678
+ },
1679
+ {
1680
+ "epoch": 27.35,
1681
+ "learning_rate": 0.00028848,
1682
+ "loss": 0.5161,
1683
+ "step": 2790
1684
+ },
1685
+ {
1686
+ "epoch": 27.45,
1687
+ "learning_rate": 0.00028808,
1688
+ "loss": 0.5432,
1689
+ "step": 2800
1690
+ },
1691
+ {
1692
+ "epoch": 27.55,
1693
+ "learning_rate": 0.00028768,
1694
+ "loss": 0.5607,
1695
+ "step": 2810
1696
+ },
1697
+ {
1698
+ "epoch": 27.65,
1699
+ "learning_rate": 0.00028728,
1700
+ "loss": 0.557,
1701
+ "step": 2820
1702
+ },
1703
+ {
1704
+ "epoch": 27.75,
1705
+ "learning_rate": 0.00028688,
1706
+ "loss": 0.5698,
1707
+ "step": 2830
1708
+ },
1709
+ {
1710
+ "epoch": 27.84,
1711
+ "learning_rate": 0.00028648,
1712
+ "loss": 0.5571,
1713
+ "step": 2840
1714
+ },
1715
+ {
1716
+ "epoch": 27.94,
1717
+ "learning_rate": 0.00028607999999999997,
1718
+ "loss": 0.5525,
1719
+ "step": 2850
1720
+ },
1721
+ {
1722
+ "epoch": 28.04,
1723
+ "learning_rate": 0.00028568,
1724
+ "loss": 0.5017,
1725
+ "step": 2860
1726
+ },
1727
+ {
1728
+ "epoch": 28.14,
1729
+ "learning_rate": 0.00028528,
1730
+ "loss": 0.5348,
1731
+ "step": 2870
1732
+ },
1733
+ {
1734
+ "epoch": 28.24,
1735
+ "learning_rate": 0.00028488000000000005,
1736
+ "loss": 0.4948,
1737
+ "step": 2880
1738
+ },
1739
+ {
1740
+ "epoch": 28.33,
1741
+ "learning_rate": 0.00028448000000000004,
1742
+ "loss": 0.4791,
1743
+ "step": 2890
1744
+ },
1745
+ {
1746
+ "epoch": 28.43,
1747
+ "learning_rate": 0.00028408000000000003,
1748
+ "loss": 0.4908,
1749
+ "step": 2900
1750
+ },
1751
+ {
1752
+ "epoch": 28.53,
1753
+ "learning_rate": 0.00028368,
1754
+ "loss": 0.4943,
1755
+ "step": 2910
1756
+ },
1757
+ {
1758
+ "epoch": 28.63,
1759
+ "learning_rate": 0.00028328,
1760
+ "loss": 0.4995,
1761
+ "step": 2920
1762
+ },
1763
+ {
1764
+ "epoch": 28.73,
1765
+ "learning_rate": 0.00028288000000000006,
1766
+ "loss": 0.5252,
1767
+ "step": 2930
1768
+ },
1769
+ {
1770
+ "epoch": 28.82,
1771
+ "learning_rate": 0.00028248000000000005,
1772
+ "loss": 0.5126,
1773
+ "step": 2940
1774
+ },
1775
+ {
1776
+ "epoch": 28.92,
1777
+ "learning_rate": 0.00028208000000000004,
1778
+ "loss": 0.5077,
1779
+ "step": 2950
1780
+ },
1781
+ {
1782
+ "epoch": 29.02,
1783
+ "learning_rate": 0.00028168000000000003,
1784
+ "loss": 0.4462,
1785
+ "step": 2960
1786
+ },
1787
+ {
1788
+ "epoch": 29.12,
1789
+ "learning_rate": 0.00028128,
1790
+ "loss": 0.4924,
1791
+ "step": 2970
1792
+ },
1793
+ {
1794
+ "epoch": 29.22,
1795
+ "learning_rate": 0.00028088,
1796
+ "loss": 0.4502,
1797
+ "step": 2980
1798
+ },
1799
+ {
1800
+ "epoch": 29.31,
1801
+ "learning_rate": 0.00028048000000000005,
1802
+ "loss": 0.4494,
1803
+ "step": 2990
1804
+ },
1805
+ {
1806
+ "epoch": 29.41,
1807
+ "learning_rate": 0.00028008000000000004,
1808
+ "loss": 0.4389,
1809
+ "step": 3000
1810
+ },
1811
+ {
1812
+ "epoch": 29.51,
1813
+ "learning_rate": 0.00027968000000000003,
1814
+ "loss": 0.4506,
1815
+ "step": 3010
1816
+ },
1817
+ {
1818
+ "epoch": 29.61,
1819
+ "learning_rate": 0.00027928,
1820
+ "loss": 0.4621,
1821
+ "step": 3020
1822
+ },
1823
+ {
1824
+ "epoch": 29.71,
1825
+ "learning_rate": 0.00027888,
1826
+ "loss": 0.4678,
1827
+ "step": 3030
1828
+ },
1829
+ {
1830
+ "epoch": 29.8,
1831
+ "learning_rate": 0.00027848,
1832
+ "loss": 0.4587,
1833
+ "step": 3040
1834
+ },
1835
+ {
1836
+ "epoch": 29.9,
1837
+ "learning_rate": 0.00027808000000000005,
1838
+ "loss": 0.4719,
1839
+ "step": 3050
1840
+ },
1841
+ {
1842
+ "epoch": 30.0,
1843
+ "learning_rate": 0.00027768000000000004,
1844
+ "loss": 0.4271,
1845
+ "step": 3060
1846
+ },
1847
+ {
1848
+ "epoch": 30.1,
1849
+ "learning_rate": 0.00027728000000000003,
1850
+ "loss": 0.4325,
1851
+ "step": 3070
1852
+ },
1853
+ {
1854
+ "epoch": 30.2,
1855
+ "learning_rate": 0.00027688,
1856
+ "loss": 0.4136,
1857
+ "step": 3080
1858
+ },
1859
+ {
1860
+ "epoch": 30.29,
1861
+ "learning_rate": 0.00027648,
1862
+ "loss": 0.4362,
1863
+ "step": 3090
1864
+ },
1865
+ {
1866
+ "epoch": 30.39,
1867
+ "learning_rate": 0.00027608000000000005,
1868
+ "loss": 0.4099,
1869
+ "step": 3100
1870
+ },
1871
+ {
1872
+ "epoch": 30.49,
1873
+ "learning_rate": 0.00027568000000000004,
1874
+ "loss": 0.4238,
1875
+ "step": 3110
1876
+ },
1877
+ {
1878
+ "epoch": 30.59,
1879
+ "learning_rate": 0.00027528000000000003,
1880
+ "loss": 0.4295,
1881
+ "step": 3120
1882
+ },
1883
+ {
1884
+ "epoch": 30.69,
1885
+ "learning_rate": 0.00027488,
1886
+ "loss": 0.4264,
1887
+ "step": 3130
1888
+ },
1889
+ {
1890
+ "epoch": 30.78,
1891
+ "learning_rate": 0.00027448,
1892
+ "loss": 0.417,
1893
+ "step": 3140
1894
+ },
1895
+ {
1896
+ "epoch": 30.88,
1897
+ "learning_rate": 0.00027408,
1898
+ "loss": 0.4304,
1899
+ "step": 3150
1900
+ },
1901
+ {
1902
+ "epoch": 30.98,
1903
+ "learning_rate": 0.00027368000000000005,
1904
+ "loss": 0.4272,
1905
+ "step": 3160
1906
+ },
1907
+ {
1908
+ "epoch": 31.08,
1909
+ "learning_rate": 0.00027328000000000004,
1910
+ "loss": 0.3643,
1911
+ "step": 3170
1912
+ },
1913
+ {
1914
+ "epoch": 31.18,
1915
+ "learning_rate": 0.00027288000000000003,
1916
+ "loss": 0.3797,
1917
+ "step": 3180
1918
+ },
1919
+ {
1920
+ "epoch": 31.27,
1921
+ "learning_rate": 0.00027248,
1922
+ "loss": 0.4051,
1923
+ "step": 3190
1924
+ },
1925
+ {
1926
+ "epoch": 31.37,
1927
+ "learning_rate": 0.00027208,
1928
+ "loss": 0.3869,
1929
+ "step": 3200
1930
+ },
1931
+ {
1932
+ "epoch": 31.47,
1933
+ "learning_rate": 0.00027168,
1934
+ "loss": 0.3997,
1935
+ "step": 3210
1936
+ },
1937
+ {
1938
+ "epoch": 31.57,
1939
+ "learning_rate": 0.00027128000000000005,
1940
+ "loss": 0.4037,
1941
+ "step": 3220
1942
+ },
1943
+ {
1944
+ "epoch": 31.67,
1945
+ "learning_rate": 0.00027088000000000004,
1946
+ "loss": 0.385,
1947
+ "step": 3230
1948
+ },
1949
+ {
1950
+ "epoch": 31.76,
1951
+ "learning_rate": 0.00027048,
1952
+ "loss": 0.3919,
1953
+ "step": 3240
1954
+ },
1955
+ {
1956
+ "epoch": 31.86,
1957
+ "learning_rate": 0.00027008,
1958
+ "loss": 0.3823,
1959
+ "step": 3250
1960
+ },
1961
+ {
1962
+ "epoch": 31.96,
1963
+ "learning_rate": 0.00026968,
1964
+ "loss": 0.382,
1965
+ "step": 3260
1966
+ },
1967
+ {
1968
+ "epoch": 32.06,
1969
+ "learning_rate": 0.00026928,
1970
+ "loss": 0.349,
1971
+ "step": 3270
1972
+ },
1973
+ {
1974
+ "epoch": 32.16,
1975
+ "learning_rate": 0.00026888000000000004,
1976
+ "loss": 0.3416,
1977
+ "step": 3280
1978
+ },
1979
+ {
1980
+ "epoch": 32.25,
1981
+ "learning_rate": 0.00026848000000000003,
1982
+ "loss": 0.3733,
1983
+ "step": 3290
1984
+ },
1985
+ {
1986
+ "epoch": 32.35,
1987
+ "learning_rate": 0.00026808,
1988
+ "loss": 0.3589,
1989
+ "step": 3300
1990
+ },
1991
+ {
1992
+ "epoch": 32.45,
1993
+ "learning_rate": 0.00026768,
1994
+ "loss": 0.3697,
1995
+ "step": 3310
1996
+ },
1997
+ {
1998
+ "epoch": 32.55,
1999
+ "learning_rate": 0.00026728,
2000
+ "loss": 0.3787,
2001
+ "step": 3320
2002
+ },
2003
+ {
2004
+ "epoch": 32.65,
2005
+ "learning_rate": 0.00026688,
2006
+ "loss": 0.3564,
2007
+ "step": 3330
2008
+ },
2009
+ {
2010
+ "epoch": 32.75,
2011
+ "learning_rate": 0.00026648000000000004,
2012
+ "loss": 0.3636,
2013
+ "step": 3340
2014
+ },
2015
+ {
2016
+ "epoch": 32.84,
2017
+ "learning_rate": 0.00026608000000000003,
2018
+ "loss": 0.3519,
2019
+ "step": 3350
2020
+ },
2021
+ {
2022
+ "epoch": 32.94,
2023
+ "learning_rate": 0.00026568,
2024
+ "loss": 0.3526,
2025
+ "step": 3360
2026
+ },
2027
+ {
2028
+ "epoch": 33.04,
2029
+ "learning_rate": 0.00026528,
2030
+ "loss": 0.3287,
2031
+ "step": 3370
2032
+ },
2033
+ {
2034
+ "epoch": 33.14,
2035
+ "learning_rate": 0.00026488,
2036
+ "loss": 0.3138,
2037
+ "step": 3380
2038
+ },
2039
+ {
2040
+ "epoch": 33.24,
2041
+ "learning_rate": 0.00026448000000000004,
2042
+ "loss": 0.3274,
2043
+ "step": 3390
2044
+ },
2045
+ {
2046
+ "epoch": 33.33,
2047
+ "learning_rate": 0.00026408000000000003,
2048
+ "loss": 0.3302,
2049
+ "step": 3400
2050
+ },
2051
+ {
2052
+ "epoch": 33.43,
2053
+ "learning_rate": 0.00026368,
2054
+ "loss": 0.3327,
2055
+ "step": 3410
2056
+ },
2057
+ {
2058
+ "epoch": 33.53,
2059
+ "learning_rate": 0.00026328,
2060
+ "loss": 0.3383,
2061
+ "step": 3420
2062
+ },
2063
+ {
2064
+ "epoch": 33.63,
2065
+ "learning_rate": 0.00026288,
2066
+ "loss": 0.3343,
2067
+ "step": 3430
2068
+ },
2069
+ {
2070
+ "epoch": 33.73,
2071
+ "learning_rate": 0.00026248,
2072
+ "loss": 0.3375,
2073
+ "step": 3440
2074
+ },
2075
+ {
2076
+ "epoch": 33.82,
2077
+ "learning_rate": 0.00026208000000000004,
2078
+ "loss": 0.3378,
2079
+ "step": 3450
2080
+ },
2081
+ {
2082
+ "epoch": 33.92,
2083
+ "learning_rate": 0.00026168000000000003,
2084
+ "loss": 0.3298,
2085
+ "step": 3460
2086
+ },
2087
+ {
2088
+ "epoch": 34.02,
2089
+ "learning_rate": 0.00026128,
2090
+ "loss": 0.2956,
2091
+ "step": 3470
2092
+ },
2093
+ {
2094
+ "epoch": 34.12,
2095
+ "learning_rate": 0.00026088,
2096
+ "loss": 0.295,
2097
+ "step": 3480
2098
+ },
2099
+ {
2100
+ "epoch": 34.22,
2101
+ "learning_rate": 0.00026048,
2102
+ "loss": 0.2847,
2103
+ "step": 3490
2104
+ },
2105
+ {
2106
+ "epoch": 34.31,
2107
+ "learning_rate": 0.00026008,
2108
+ "loss": 0.2993,
2109
+ "step": 3500
2110
+ },
2111
+ {
2112
+ "epoch": 34.41,
2113
+ "learning_rate": 0.00025968000000000003,
2114
+ "loss": 0.2974,
2115
+ "step": 3510
2116
+ },
2117
+ {
2118
+ "epoch": 34.51,
2119
+ "learning_rate": 0.00025928,
2120
+ "loss": 0.3076,
2121
+ "step": 3520
2122
+ },
2123
+ {
2124
+ "epoch": 34.61,
2125
+ "learning_rate": 0.00025888,
2126
+ "loss": 0.3146,
2127
+ "step": 3530
2128
+ },
2129
+ {
2130
+ "epoch": 34.71,
2131
+ "learning_rate": 0.00025848,
2132
+ "loss": 0.3124,
2133
+ "step": 3540
2134
+ },
2135
+ {
2136
+ "epoch": 34.8,
2137
+ "learning_rate": 0.00025808,
2138
+ "loss": 0.3072,
2139
+ "step": 3550
2140
+ },
2141
+ {
2142
+ "epoch": 34.9,
2143
+ "learning_rate": 0.00025768,
2144
+ "loss": 0.3078,
2145
+ "step": 3560
2146
+ },
2147
+ {
2148
+ "epoch": 35.0,
2149
+ "learning_rate": 0.00025728000000000003,
2150
+ "loss": 0.2738,
2151
+ "step": 3570
2152
+ },
2153
+ {
2154
+ "epoch": 35.1,
2155
+ "learning_rate": 0.00025688,
2156
+ "loss": 0.2736,
2157
+ "step": 3580
2158
+ },
2159
+ {
2160
+ "epoch": 35.2,
2161
+ "learning_rate": 0.00025648,
2162
+ "loss": 0.257,
2163
+ "step": 3590
2164
+ },
2165
+ {
2166
+ "epoch": 35.29,
2167
+ "learning_rate": 0.00025608,
2168
+ "loss": 0.2671,
2169
+ "step": 3600
2170
+ },
2171
+ {
2172
+ "epoch": 35.39,
2173
+ "learning_rate": 0.00025568,
2174
+ "loss": 0.2638,
2175
+ "step": 3610
2176
+ },
2177
+ {
2178
+ "epoch": 35.49,
2179
+ "learning_rate": 0.00025528,
2180
+ "loss": 0.2707,
2181
+ "step": 3620
2182
+ },
2183
+ {
2184
+ "epoch": 35.59,
2185
+ "learning_rate": 0.00025488,
2186
+ "loss": 0.2795,
2187
+ "step": 3630
2188
+ },
2189
+ {
2190
+ "epoch": 35.69,
2191
+ "learning_rate": 0.00025448,
2192
+ "loss": 0.2765,
2193
+ "step": 3640
2194
+ },
2195
+ {
2196
+ "epoch": 35.78,
2197
+ "learning_rate": 0.00025408,
2198
+ "loss": 0.2757,
2199
+ "step": 3650
2200
+ },
2201
+ {
2202
+ "epoch": 35.88,
2203
+ "learning_rate": 0.00025368,
2204
+ "loss": 0.2779,
2205
+ "step": 3660
2206
+ },
2207
+ {
2208
+ "epoch": 35.98,
2209
+ "learning_rate": 0.00025328,
2210
+ "loss": 0.2628,
2211
+ "step": 3670
2212
+ },
2213
+ {
2214
+ "epoch": 36.08,
2215
+ "learning_rate": 0.00025288000000000003,
2216
+ "loss": 0.2403,
2217
+ "step": 3680
2218
+ },
2219
+ {
2220
+ "epoch": 36.18,
2221
+ "learning_rate": 0.00025248,
2222
+ "loss": 0.2361,
2223
+ "step": 3690
2224
+ },
2225
+ {
2226
+ "epoch": 36.27,
2227
+ "learning_rate": 0.00025208,
2228
+ "loss": 0.2394,
2229
+ "step": 3700
2230
+ },
2231
+ {
2232
+ "epoch": 36.37,
2233
+ "learning_rate": 0.00025168,
2234
+ "loss": 0.2309,
2235
+ "step": 3710
2236
+ },
2237
+ {
2238
+ "epoch": 36.47,
2239
+ "learning_rate": 0.00025128,
2240
+ "loss": 0.233,
2241
+ "step": 3720
2242
+ },
2243
+ {
2244
+ "epoch": 36.57,
2245
+ "learning_rate": 0.00025088,
2246
+ "loss": 0.2446,
2247
+ "step": 3730
2248
+ },
2249
+ {
2250
+ "epoch": 36.67,
2251
+ "learning_rate": 0.00025048000000000003,
2252
+ "loss": 0.2385,
2253
+ "step": 3740
2254
+ },
2255
+ {
2256
+ "epoch": 36.76,
2257
+ "learning_rate": 0.00025008,
2258
+ "loss": 0.239,
2259
+ "step": 3750
2260
+ },
2261
+ {
2262
+ "epoch": 36.86,
2263
+ "learning_rate": 0.00024968,
2264
+ "loss": 0.2392,
2265
+ "step": 3760
2266
+ },
2267
+ {
2268
+ "epoch": 36.96,
2269
+ "learning_rate": 0.00024928,
2270
+ "loss": 0.2318,
2271
+ "step": 3770
2272
+ },
2273
+ {
2274
+ "epoch": 37.06,
2275
+ "learning_rate": 0.00024888,
2276
+ "loss": 0.218,
2277
+ "step": 3780
2278
+ },
2279
+ {
2280
+ "epoch": 37.16,
2281
+ "learning_rate": 0.00024848,
2282
+ "loss": 0.2059,
2283
+ "step": 3790
2284
+ },
2285
+ {
2286
+ "epoch": 37.25,
2287
+ "learning_rate": 0.00024808,
2288
+ "loss": 0.2082,
2289
+ "step": 3800
2290
+ },
2291
+ {
2292
+ "epoch": 37.35,
2293
+ "learning_rate": 0.00024768,
2294
+ "loss": 0.2058,
2295
+ "step": 3810
2296
+ },
2297
+ {
2298
+ "epoch": 37.45,
2299
+ "learning_rate": 0.00024728,
2300
+ "loss": 0.2037,
2301
+ "step": 3820
2302
+ },
2303
+ {
2304
+ "epoch": 37.55,
2305
+ "learning_rate": 0.00024688,
2306
+ "loss": 0.2083,
2307
+ "step": 3830
2308
+ },
2309
+ {
2310
+ "epoch": 37.65,
2311
+ "learning_rate": 0.00024648,
2312
+ "loss": 0.2007,
2313
+ "step": 3840
2314
+ },
2315
+ {
2316
+ "epoch": 37.75,
2317
+ "learning_rate": 0.00024608,
2318
+ "loss": 0.2012,
2319
+ "step": 3850
2320
+ },
2321
+ {
2322
+ "epoch": 37.84,
2323
+ "learning_rate": 0.00024568,
2324
+ "loss": 0.1972,
2325
+ "step": 3860
2326
+ },
2327
+ {
2328
+ "epoch": 37.94,
2329
+ "learning_rate": 0.00024528,
2330
+ "loss": 0.1996,
2331
+ "step": 3870
2332
+ },
2333
+ {
2334
+ "epoch": 38.04,
2335
+ "learning_rate": 0.00024488,
2336
+ "loss": 0.1859,
2337
+ "step": 3880
2338
+ },
2339
+ {
2340
+ "epoch": 38.14,
2341
+ "learning_rate": 0.00024448,
2342
+ "loss": 0.1801,
2343
+ "step": 3890
2344
+ },
2345
+ {
2346
+ "epoch": 38.24,
2347
+ "learning_rate": 0.00024408,
2348
+ "loss": 0.1708,
2349
+ "step": 3900
2350
+ },
2351
+ {
2352
+ "epoch": 38.33,
2353
+ "learning_rate": 0.00024368,
2354
+ "loss": 0.1709,
2355
+ "step": 3910
2356
+ },
2357
+ {
2358
+ "epoch": 38.43,
2359
+ "learning_rate": 0.00024328,
2360
+ "loss": 0.1736,
2361
+ "step": 3920
2362
+ },
2363
+ {
2364
+ "epoch": 38.53,
2365
+ "learning_rate": 0.00024288,
2366
+ "loss": 0.1726,
2367
+ "step": 3930
2368
+ },
2369
+ {
2370
+ "epoch": 38.63,
2371
+ "learning_rate": 0.00024248,
2372
+ "loss": 0.1681,
2373
+ "step": 3940
2374
+ },
2375
+ {
2376
+ "epoch": 38.73,
2377
+ "learning_rate": 0.00024207999999999999,
2378
+ "loss": 0.1674,
2379
+ "step": 3950
2380
+ },
2381
+ {
2382
+ "epoch": 38.82,
2383
+ "learning_rate": 0.00024168,
2384
+ "loss": 0.1601,
2385
+ "step": 3960
2386
+ },
2387
+ {
2388
+ "epoch": 38.92,
2389
+ "learning_rate": 0.00024128,
2390
+ "loss": 0.1552,
2391
+ "step": 3970
2392
+ },
2393
+ {
2394
+ "epoch": 39.02,
2395
+ "learning_rate": 0.00024087999999999998,
2396
+ "loss": 0.1414,
2397
+ "step": 3980
2398
+ },
2399
+ {
2400
+ "epoch": 39.12,
2401
+ "learning_rate": 0.00024048,
2402
+ "loss": 0.151,
2403
+ "step": 3990
2404
+ },
2405
+ {
2406
+ "epoch": 39.22,
2407
+ "learning_rate": 0.00024008,
2408
+ "loss": 0.1418,
2409
+ "step": 4000
2410
+ },
2411
+ {
2412
+ "epoch": 39.31,
2413
+ "learning_rate": 0.00023967999999999998,
2414
+ "loss": 0.1372,
2415
+ "step": 4010
2416
+ },
2417
+ {
2418
+ "epoch": 39.41,
2419
+ "learning_rate": 0.00023928,
2420
+ "loss": 0.1334,
2421
+ "step": 4020
2422
+ },
2423
+ {
2424
+ "epoch": 39.51,
2425
+ "learning_rate": 0.00023888,
2426
+ "loss": 0.1339,
2427
+ "step": 4030
2428
+ },
2429
+ {
2430
+ "epoch": 39.61,
2431
+ "learning_rate": 0.00023847999999999998,
2432
+ "loss": 0.137,
2433
+ "step": 4040
2434
+ },
2435
+ {
2436
+ "epoch": 39.71,
2437
+ "learning_rate": 0.00023808,
2438
+ "loss": 0.1325,
2439
+ "step": 4050
2440
+ },
2441
+ {
2442
+ "epoch": 39.8,
2443
+ "learning_rate": 0.00023768,
2444
+ "loss": 0.1322,
2445
+ "step": 4060
2446
+ },
2447
+ {
2448
+ "epoch": 39.9,
2449
+ "learning_rate": 0.00023727999999999998,
2450
+ "loss": 0.1262,
2451
+ "step": 4070
2452
+ },
2453
+ {
2454
+ "epoch": 40.0,
2455
+ "learning_rate": 0.00023688,
2456
+ "loss": 0.1111,
2457
+ "step": 4080
2458
+ },
2459
+ {
2460
+ "epoch": 40.1,
2461
+ "learning_rate": 0.00023647999999999999,
2462
+ "loss": 0.1125,
2463
+ "step": 4090
2464
+ },
2465
+ {
2466
+ "epoch": 40.2,
2467
+ "learning_rate": 0.00023608,
2468
+ "loss": 0.1128,
2469
+ "step": 4100
2470
+ },
2471
+ {
2472
+ "epoch": 40.29,
2473
+ "learning_rate": 0.00023568,
2474
+ "loss": 0.1098,
2475
+ "step": 4110
2476
+ },
2477
+ {
2478
+ "epoch": 40.39,
2479
+ "learning_rate": 0.00023527999999999998,
2480
+ "loss": 0.1057,
2481
+ "step": 4120
2482
+ },
2483
+ {
2484
+ "epoch": 40.49,
2485
+ "learning_rate": 0.00023488000000000003,
2486
+ "loss": 0.1019,
2487
+ "step": 4130
2488
+ },
2489
+ {
2490
+ "epoch": 40.59,
2491
+ "learning_rate": 0.00023448000000000005,
2492
+ "loss": 0.1024,
2493
+ "step": 4140
2494
+ },
2495
+ {
2496
+ "epoch": 40.69,
2497
+ "learning_rate": 0.00023408000000000004,
2498
+ "loss": 0.1014,
2499
+ "step": 4150
2500
+ },
2501
+ {
2502
+ "epoch": 40.78,
2503
+ "learning_rate": 0.00023368000000000003,
2504
+ "loss": 0.1038,
2505
+ "step": 4160
2506
+ },
2507
+ {
2508
+ "epoch": 40.88,
2509
+ "learning_rate": 0.00023328000000000004,
2510
+ "loss": 0.096,
2511
+ "step": 4170
2512
+ },
2513
+ {
2514
+ "epoch": 40.98,
2515
+ "learning_rate": 0.00023288000000000003,
2516
+ "loss": 0.0943,
2517
+ "step": 4180
2518
+ },
2519
+ {
2520
+ "epoch": 41.08,
2521
+ "learning_rate": 0.00023248000000000002,
2522
+ "loss": 0.0821,
2523
+ "step": 4190
2524
+ },
2525
+ {
2526
+ "epoch": 41.18,
2527
+ "learning_rate": 0.00023208000000000004,
2528
+ "loss": 0.0861,
2529
+ "step": 4200
2530
+ },
2531
+ {
2532
+ "epoch": 41.27,
2533
+ "learning_rate": 0.00023168000000000003,
2534
+ "loss": 0.0854,
2535
+ "step": 4210
2536
+ },
2537
+ {
2538
+ "epoch": 41.37,
2539
+ "learning_rate": 0.00023128000000000002,
2540
+ "loss": 0.081,
2541
+ "step": 4220
2542
+ },
2543
+ {
2544
+ "epoch": 41.47,
2545
+ "learning_rate": 0.00023088000000000004,
2546
+ "loss": 0.0787,
2547
+ "step": 4230
2548
+ },
2549
+ {
2550
+ "epoch": 41.57,
2551
+ "learning_rate": 0.00023048000000000003,
2552
+ "loss": 0.0775,
2553
+ "step": 4240
2554
+ },
2555
+ {
2556
+ "epoch": 41.67,
2557
+ "learning_rate": 0.00023008000000000002,
2558
+ "loss": 0.0742,
2559
+ "step": 4250
2560
+ },
2561
+ {
2562
+ "epoch": 41.76,
2563
+ "learning_rate": 0.00022968000000000004,
2564
+ "loss": 0.0727,
2565
+ "step": 4260
2566
+ },
2567
+ {
2568
+ "epoch": 41.86,
2569
+ "learning_rate": 0.00022928000000000003,
2570
+ "loss": 0.0716,
2571
+ "step": 4270
2572
+ },
2573
+ {
2574
+ "epoch": 41.96,
2575
+ "learning_rate": 0.00022888000000000002,
2576
+ "loss": 0.0701,
2577
+ "step": 4280
2578
+ },
2579
+ {
2580
+ "epoch": 42.06,
2581
+ "learning_rate": 0.00022848000000000004,
2582
+ "loss": 0.0639,
2583
+ "step": 4290
2584
+ },
2585
+ {
2586
+ "epoch": 42.16,
2587
+ "learning_rate": 0.00022808000000000003,
2588
+ "loss": 0.0636,
2589
+ "step": 4300
2590
+ },
2591
+ {
2592
+ "epoch": 42.25,
2593
+ "learning_rate": 0.00022768000000000002,
2594
+ "loss": 0.0625,
2595
+ "step": 4310
2596
+ },
2597
+ {
2598
+ "epoch": 42.35,
2599
+ "learning_rate": 0.00022728000000000003,
2600
+ "loss": 0.0607,
2601
+ "step": 4320
2602
+ },
2603
+ {
2604
+ "epoch": 42.45,
2605
+ "learning_rate": 0.00022688000000000002,
2606
+ "loss": 0.058,
2607
+ "step": 4330
2608
+ },
2609
+ {
2610
+ "epoch": 42.55,
2611
+ "learning_rate": 0.00022648000000000001,
2612
+ "loss": 0.0567,
2613
+ "step": 4340
2614
+ },
2615
+ {
2616
+ "epoch": 42.65,
2617
+ "learning_rate": 0.00022608000000000003,
2618
+ "loss": 0.0538,
2619
+ "step": 4350
2620
+ },
2621
+ {
2622
+ "epoch": 42.75,
2623
+ "learning_rate": 0.00022568000000000002,
2624
+ "loss": 0.0528,
2625
+ "step": 4360
2626
+ },
2627
+ {
2628
+ "epoch": 42.84,
2629
+ "learning_rate": 0.00022528,
2630
+ "loss": 0.0507,
2631
+ "step": 4370
2632
+ },
2633
+ {
2634
+ "epoch": 42.94,
2635
+ "learning_rate": 0.00022488000000000003,
2636
+ "loss": 0.0481,
2637
+ "step": 4380
2638
+ },
2639
+ {
2640
+ "epoch": 43.04,
2641
+ "learning_rate": 0.00022448000000000002,
2642
+ "loss": 0.0434,
2643
+ "step": 4390
2644
+ },
2645
+ {
2646
+ "epoch": 43.14,
2647
+ "learning_rate": 0.00022408000000000004,
2648
+ "loss": 0.0451,
2649
+ "step": 4400
2650
+ },
2651
+ {
2652
+ "epoch": 43.24,
2653
+ "learning_rate": 0.00022368000000000003,
2654
+ "loss": 0.0433,
2655
+ "step": 4410
2656
+ },
2657
+ {
2658
+ "epoch": 43.33,
2659
+ "learning_rate": 0.00022328000000000002,
2660
+ "loss": 0.0419,
2661
+ "step": 4420
2662
+ },
2663
+ {
2664
+ "epoch": 43.43,
2665
+ "learning_rate": 0.00022288000000000003,
2666
+ "loss": 0.0408,
2667
+ "step": 4430
2668
+ },
2669
+ {
2670
+ "epoch": 43.53,
2671
+ "learning_rate": 0.00022248000000000002,
2672
+ "loss": 0.0386,
2673
+ "step": 4440
2674
+ },
2675
+ {
2676
+ "epoch": 43.63,
2677
+ "learning_rate": 0.00022208000000000002,
2678
+ "loss": 0.038,
2679
+ "step": 4450
2680
+ },
2681
+ {
2682
+ "epoch": 43.73,
2683
+ "learning_rate": 0.00022168000000000003,
2684
+ "loss": 0.0367,
2685
+ "step": 4460
2686
+ },
2687
+ {
2688
+ "epoch": 43.82,
2689
+ "learning_rate": 0.00022128000000000002,
2690
+ "loss": 0.0362,
2691
+ "step": 4470
2692
+ },
2693
+ {
2694
+ "epoch": 43.92,
2695
+ "learning_rate": 0.00022088,
2696
+ "loss": 0.0338,
2697
+ "step": 4480
2698
+ },
2699
+ {
2700
+ "epoch": 44.02,
2701
+ "learning_rate": 0.00022048000000000003,
2702
+ "loss": 0.0303,
2703
+ "step": 4490
2704
+ },
2705
+ {
2706
+ "epoch": 44.12,
2707
+ "learning_rate": 0.00022008000000000002,
2708
+ "loss": 0.0318,
2709
+ "step": 4500
2710
+ },
2711
+ {
2712
+ "epoch": 44.22,
2713
+ "learning_rate": 0.00021968,
2714
+ "loss": 0.031,
2715
+ "step": 4510
2716
+ },
2717
+ {
2718
+ "epoch": 44.31,
2719
+ "learning_rate": 0.00021928000000000003,
2720
+ "loss": 0.0295,
2721
+ "step": 4520
2722
+ },
2723
+ {
2724
+ "epoch": 44.41,
2725
+ "learning_rate": 0.00021888000000000002,
2726
+ "loss": 0.029,
2727
+ "step": 4530
2728
+ },
2729
+ {
2730
+ "epoch": 44.51,
2731
+ "learning_rate": 0.00021848,
2732
+ "loss": 0.0275,
2733
+ "step": 4540
2734
+ },
2735
+ {
2736
+ "epoch": 44.61,
2737
+ "learning_rate": 0.00021808000000000003,
2738
+ "loss": 0.0267,
2739
+ "step": 4550
2740
+ },
2741
+ {
2742
+ "epoch": 44.71,
2743
+ "learning_rate": 0.00021768000000000002,
2744
+ "loss": 0.0269,
2745
+ "step": 4560
2746
+ },
2747
+ {
2748
+ "epoch": 44.8,
2749
+ "learning_rate": 0.00021728,
2750
+ "loss": 0.0262,
2751
+ "step": 4570
2752
+ },
2753
+ {
2754
+ "epoch": 44.9,
2755
+ "learning_rate": 0.00021688000000000002,
2756
+ "loss": 0.0259,
2757
+ "step": 4580
2758
+ },
2759
+ {
2760
+ "epoch": 45.0,
2761
+ "learning_rate": 0.00021648000000000001,
2762
+ "loss": 0.0235,
2763
+ "step": 4590
2764
+ },
2765
+ {
2766
+ "epoch": 45.1,
2767
+ "learning_rate": 0.00021608,
2768
+ "loss": 0.0225,
2769
+ "step": 4600
2770
+ },
2771
+ {
2772
+ "epoch": 45.2,
2773
+ "learning_rate": 0.00021568000000000002,
2774
+ "loss": 0.0238,
2775
+ "step": 4610
2776
+ },
2777
+ {
2778
+ "epoch": 45.29,
2779
+ "learning_rate": 0.00021528,
2780
+ "loss": 0.0233,
2781
+ "step": 4620
2782
+ },
2783
+ {
2784
+ "epoch": 45.39,
2785
+ "learning_rate": 0.00021488,
2786
+ "loss": 0.0222,
2787
+ "step": 4630
2788
+ },
2789
+ {
2790
+ "epoch": 45.49,
2791
+ "learning_rate": 0.00021448000000000002,
2792
+ "loss": 0.0218,
2793
+ "step": 4640
2794
+ },
2795
+ {
2796
+ "epoch": 45.59,
2797
+ "learning_rate": 0.00021408,
2798
+ "loss": 0.0207,
2799
+ "step": 4650
2800
+ },
2801
+ {
2802
+ "epoch": 45.69,
2803
+ "learning_rate": 0.00021368,
2804
+ "loss": 0.0207,
2805
+ "step": 4660
2806
+ },
2807
+ {
2808
+ "epoch": 45.78,
2809
+ "learning_rate": 0.00021328000000000002,
2810
+ "loss": 0.0214,
2811
+ "step": 4670
2812
+ },
2813
+ {
2814
+ "epoch": 45.88,
2815
+ "learning_rate": 0.00021288,
2816
+ "loss": 0.021,
2817
+ "step": 4680
2818
+ },
2819
+ {
2820
+ "epoch": 45.98,
2821
+ "learning_rate": 0.00021248000000000003,
2822
+ "loss": 0.0205,
2823
+ "step": 4690
2824
+ },
2825
+ {
2826
+ "epoch": 46.08,
2827
+ "learning_rate": 0.00021208000000000002,
2828
+ "loss": 0.0179,
2829
+ "step": 4700
2830
+ },
2831
+ {
2832
+ "epoch": 46.18,
2833
+ "learning_rate": 0.00021168,
2834
+ "loss": 0.019,
2835
+ "step": 4710
2836
+ },
2837
+ {
2838
+ "epoch": 46.27,
2839
+ "learning_rate": 0.00021128000000000002,
2840
+ "loss": 0.0192,
2841
+ "step": 4720
2842
+ },
2843
+ {
2844
+ "epoch": 46.37,
2845
+ "learning_rate": 0.00021088000000000001,
2846
+ "loss": 0.0187,
2847
+ "step": 4730
2848
+ },
2849
+ {
2850
+ "epoch": 46.47,
2851
+ "learning_rate": 0.00021048,
2852
+ "loss": 0.0183,
2853
+ "step": 4740
2854
+ },
2855
+ {
2856
+ "epoch": 46.57,
2857
+ "learning_rate": 0.00021008000000000002,
2858
+ "loss": 0.0176,
2859
+ "step": 4750
2860
+ },
2861
+ {
2862
+ "epoch": 46.67,
2863
+ "learning_rate": 0.00020968,
2864
+ "loss": 0.0169,
2865
+ "step": 4760
2866
+ },
2867
+ {
2868
+ "epoch": 46.76,
2869
+ "learning_rate": 0.00020928,
2870
+ "loss": 0.0171,
2871
+ "step": 4770
2872
+ },
2873
+ {
2874
+ "epoch": 46.86,
2875
+ "learning_rate": 0.00020888000000000002,
2876
+ "loss": 0.0172,
2877
+ "step": 4780
2878
+ },
2879
+ {
2880
+ "epoch": 46.96,
2881
+ "learning_rate": 0.00020848,
2882
+ "loss": 0.0175,
2883
+ "step": 4790
2884
+ },
2885
+ {
2886
+ "epoch": 47.06,
2887
+ "learning_rate": 0.00020808,
2888
+ "loss": 0.0153,
2889
+ "step": 4800
2890
+ },
2891
+ {
2892
+ "epoch": 47.16,
2893
+ "learning_rate": 0.00020768000000000002,
2894
+ "loss": 0.0162,
2895
+ "step": 4810
2896
+ },
2897
+ {
2898
+ "epoch": 47.25,
2899
+ "learning_rate": 0.00020728,
2900
+ "loss": 0.0161,
2901
+ "step": 4820
2902
+ },
2903
+ {
2904
+ "epoch": 47.35,
2905
+ "learning_rate": 0.00020688,
2906
+ "loss": 0.0161,
2907
+ "step": 4830
2908
+ },
2909
+ {
2910
+ "epoch": 47.45,
2911
+ "learning_rate": 0.00020648000000000002,
2912
+ "loss": 0.0157,
2913
+ "step": 4840
2914
+ },
2915
+ {
2916
+ "epoch": 47.55,
2917
+ "learning_rate": 0.00020608,
2918
+ "loss": 0.0149,
2919
+ "step": 4850
2920
+ },
2921
+ {
2922
+ "epoch": 47.65,
2923
+ "learning_rate": 0.00020568,
2924
+ "loss": 0.0143,
2925
+ "step": 4860
2926
+ },
2927
+ {
2928
+ "epoch": 47.75,
2929
+ "learning_rate": 0.00020528,
2930
+ "loss": 0.0138,
2931
+ "step": 4870
2932
+ },
2933
+ {
2934
+ "epoch": 47.84,
2935
+ "learning_rate": 0.00020488,
2936
+ "loss": 0.0136,
2937
+ "step": 4880
2938
+ },
2939
+ {
2940
+ "epoch": 47.94,
2941
+ "learning_rate": 0.00020448,
2942
+ "loss": 0.014,
2943
+ "step": 4890
2944
+ },
2945
+ {
2946
+ "epoch": 48.04,
2947
+ "learning_rate": 0.00020408,
2948
+ "loss": 0.0131,
2949
+ "step": 4900
2950
+ },
2951
+ {
2952
+ "epoch": 48.14,
2953
+ "learning_rate": 0.00020368,
2954
+ "loss": 0.0141,
2955
+ "step": 4910
2956
+ },
2957
+ {
2958
+ "epoch": 48.24,
2959
+ "learning_rate": 0.00020328,
2960
+ "loss": 0.0134,
2961
+ "step": 4920
2962
+ },
2963
+ {
2964
+ "epoch": 48.33,
2965
+ "learning_rate": 0.00020288,
2966
+ "loss": 0.013,
2967
+ "step": 4930
2968
+ },
2969
+ {
2970
+ "epoch": 48.43,
2971
+ "learning_rate": 0.00020248,
2972
+ "loss": 0.0128,
2973
+ "step": 4940
2974
+ },
2975
+ {
2976
+ "epoch": 48.53,
2977
+ "learning_rate": 0.00020208,
2978
+ "loss": 0.0127,
2979
+ "step": 4950
2980
+ },
2981
+ {
2982
+ "epoch": 48.63,
2983
+ "learning_rate": 0.00020168,
2984
+ "loss": 0.012,
2985
+ "step": 4960
2986
+ },
2987
+ {
2988
+ "epoch": 48.73,
2989
+ "learning_rate": 0.00020128,
2990
+ "loss": 0.0114,
2991
+ "step": 4970
2992
+ },
2993
+ {
2994
+ "epoch": 48.82,
2995
+ "learning_rate": 0.00020088000000000001,
2996
+ "loss": 0.0113,
2997
+ "step": 4980
2998
+ },
2999
+ {
3000
+ "epoch": 48.92,
3001
+ "learning_rate": 0.00020048,
3002
+ "loss": 0.0118,
3003
+ "step": 4990
3004
+ },
3005
+ {
3006
+ "epoch": 49.02,
3007
+ "learning_rate": 0.00020008,
3008
+ "loss": 0.011,
3009
+ "step": 5000
3010
+ },
3011
+ {
3012
+ "epoch": 49.12,
3013
+ "learning_rate": 0.00019968,
3014
+ "loss": 0.012,
3015
+ "step": 5010
3016
+ },
3017
+ {
3018
+ "epoch": 49.22,
3019
+ "learning_rate": 0.00019928,
3020
+ "loss": 0.0116,
3021
+ "step": 5020
3022
+ },
3023
+ {
3024
+ "epoch": 49.31,
3025
+ "learning_rate": 0.00019888,
3026
+ "loss": 0.0106,
3027
+ "step": 5030
3028
+ },
3029
+ {
3030
+ "epoch": 49.41,
3031
+ "learning_rate": 0.00019848,
3032
+ "loss": 0.0103,
3033
+ "step": 5040
3034
+ },
3035
+ {
3036
+ "epoch": 49.51,
3037
+ "learning_rate": 0.00019808,
3038
+ "loss": 0.0098,
3039
+ "step": 5050
3040
+ },
3041
+ {
3042
+ "epoch": 49.61,
3043
+ "learning_rate": 0.00019768,
3044
+ "loss": 0.0101,
3045
+ "step": 5060
3046
+ },
3047
+ {
3048
+ "epoch": 49.71,
3049
+ "learning_rate": 0.00019728,
3050
+ "loss": 0.0099,
3051
+ "step": 5070
3052
+ },
3053
+ {
3054
+ "epoch": 49.8,
3055
+ "learning_rate": 0.00019688000000000003,
3056
+ "loss": 0.0096,
3057
+ "step": 5080
3058
+ },
3059
+ {
3060
+ "epoch": 49.9,
3061
+ "learning_rate": 0.00019648000000000002,
3062
+ "loss": 0.0098,
3063
+ "step": 5090
3064
+ },
3065
+ {
3066
+ "epoch": 50.0,
3067
+ "learning_rate": 0.00019608,
3068
+ "loss": 0.0096,
3069
+ "step": 5100
3070
+ },
3071
+ {
3072
+ "epoch": 50.1,
3073
+ "learning_rate": 0.00019568000000000002,
3074
+ "loss": 0.0093,
3075
+ "step": 5110
3076
+ },
3077
+ {
3078
+ "epoch": 50.2,
3079
+ "learning_rate": 0.00019528000000000001,
3080
+ "loss": 0.0099,
3081
+ "step": 5120
3082
+ },
3083
+ {
3084
+ "epoch": 50.29,
3085
+ "learning_rate": 0.00019488000000000003,
3086
+ "loss": 0.0095,
3087
+ "step": 5130
3088
+ },
3089
+ {
3090
+ "epoch": 50.39,
3091
+ "learning_rate": 0.00019448000000000002,
3092
+ "loss": 0.0087,
3093
+ "step": 5140
3094
+ },
3095
+ {
3096
+ "epoch": 50.49,
3097
+ "learning_rate": 0.00019408,
3098
+ "loss": 0.0084,
3099
+ "step": 5150
3100
+ },
3101
+ {
3102
+ "epoch": 50.59,
3103
+ "learning_rate": 0.00019368000000000003,
3104
+ "loss": 0.0086,
3105
+ "step": 5160
3106
+ },
3107
+ {
3108
+ "epoch": 50.69,
3109
+ "learning_rate": 0.00019328000000000002,
3110
+ "loss": 0.0087,
3111
+ "step": 5170
3112
+ },
3113
+ {
3114
+ "epoch": 50.78,
3115
+ "learning_rate": 0.00019288,
3116
+ "loss": 0.0086,
3117
+ "step": 5180
3118
+ },
3119
+ {
3120
+ "epoch": 50.88,
3121
+ "learning_rate": 0.00019248000000000003,
3122
+ "loss": 0.0082,
3123
+ "step": 5190
3124
+ },
3125
+ {
3126
+ "epoch": 50.98,
3127
+ "learning_rate": 0.00019208000000000002,
3128
+ "loss": 0.0085,
3129
+ "step": 5200
3130
+ },
3131
+ {
3132
+ "epoch": 51.08,
3133
+ "learning_rate": 0.00019168,
3134
+ "loss": 0.0081,
3135
+ "step": 5210
3136
+ },
3137
+ {
3138
+ "epoch": 51.18,
3139
+ "learning_rate": 0.00019128000000000003,
3140
+ "loss": 0.0084,
3141
+ "step": 5220
3142
+ },
3143
+ {
3144
+ "epoch": 51.27,
3145
+ "learning_rate": 0.00019088000000000002,
3146
+ "loss": 0.0086,
3147
+ "step": 5230
3148
+ },
3149
+ {
3150
+ "epoch": 51.37,
3151
+ "learning_rate": 0.00019048,
3152
+ "loss": 0.0081,
3153
+ "step": 5240
3154
+ },
3155
+ {
3156
+ "epoch": 51.47,
3157
+ "learning_rate": 0.00019008000000000002,
3158
+ "loss": 0.0078,
3159
+ "step": 5250
3160
+ },
3161
+ {
3162
+ "epoch": 51.57,
3163
+ "learning_rate": 0.00018968,
3164
+ "loss": 0.0076,
3165
+ "step": 5260
3166
+ },
3167
+ {
3168
+ "epoch": 51.67,
3169
+ "learning_rate": 0.00018928,
3170
+ "loss": 0.0076,
3171
+ "step": 5270
3172
+ },
3173
+ {
3174
+ "epoch": 51.76,
3175
+ "learning_rate": 0.00018888000000000002,
3176
+ "loss": 0.0079,
3177
+ "step": 5280
3178
+ },
3179
+ {
3180
+ "epoch": 51.86,
3181
+ "learning_rate": 0.00018848,
3182
+ "loss": 0.0077,
3183
+ "step": 5290
3184
+ },
3185
+ {
3186
+ "epoch": 51.96,
3187
+ "learning_rate": 0.00018808,
3188
+ "loss": 0.0075,
3189
+ "step": 5300
3190
+ },
3191
+ {
3192
+ "epoch": 52.06,
3193
+ "learning_rate": 0.00018768000000000002,
3194
+ "loss": 0.0071,
3195
+ "step": 5310
3196
+ },
3197
+ {
3198
+ "epoch": 52.16,
3199
+ "learning_rate": 0.00018728,
3200
+ "loss": 0.0079,
3201
+ "step": 5320
3202
+ },
3203
+ {
3204
+ "epoch": 52.25,
3205
+ "learning_rate": 0.00018688,
3206
+ "loss": 0.0078,
3207
+ "step": 5330
3208
+ },
3209
+ {
3210
+ "epoch": 52.35,
3211
+ "learning_rate": 0.00018648000000000002,
3212
+ "loss": 0.0076,
3213
+ "step": 5340
3214
+ },
3215
+ {
3216
+ "epoch": 52.45,
3217
+ "learning_rate": 0.00018608,
3218
+ "loss": 0.0076,
3219
+ "step": 5350
3220
+ },
3221
+ {
3222
+ "epoch": 52.55,
3223
+ "learning_rate": 0.00018568,
3224
+ "loss": 0.0072,
3225
+ "step": 5360
3226
+ },
3227
+ {
3228
+ "epoch": 52.65,
3229
+ "learning_rate": 0.00018528000000000001,
3230
+ "loss": 0.0072,
3231
+ "step": 5370
3232
+ },
3233
+ {
3234
+ "epoch": 52.75,
3235
+ "learning_rate": 0.00018488,
3236
+ "loss": 0.007,
3237
+ "step": 5380
3238
+ },
3239
+ {
3240
+ "epoch": 52.84,
3241
+ "learning_rate": 0.00018448,
3242
+ "loss": 0.0071,
3243
+ "step": 5390
3244
+ },
3245
+ {
3246
+ "epoch": 52.94,
3247
+ "learning_rate": 0.00018408,
3248
+ "loss": 0.0071,
3249
+ "step": 5400
3250
+ },
3251
+ {
3252
+ "epoch": 53.04,
3253
+ "learning_rate": 0.00018368,
3254
+ "loss": 0.0066,
3255
+ "step": 5410
3256
+ },
3257
+ {
3258
+ "epoch": 53.14,
3259
+ "learning_rate": 0.00018328000000000002,
3260
+ "loss": 0.0073,
3261
+ "step": 5420
3262
+ },
3263
+ {
3264
+ "epoch": 53.24,
3265
+ "learning_rate": 0.00018288,
3266
+ "loss": 0.0074,
3267
+ "step": 5430
3268
+ },
3269
+ {
3270
+ "epoch": 53.33,
3271
+ "learning_rate": 0.00018248,
3272
+ "loss": 0.0072,
3273
+ "step": 5440
3274
+ },
3275
+ {
3276
+ "epoch": 53.43,
3277
+ "learning_rate": 0.00018208000000000002,
3278
+ "loss": 0.0071,
3279
+ "step": 5450
3280
+ },
3281
+ {
3282
+ "epoch": 53.53,
3283
+ "learning_rate": 0.00018168,
3284
+ "loss": 0.007,
3285
+ "step": 5460
3286
+ },
3287
+ {
3288
+ "epoch": 53.63,
3289
+ "learning_rate": 0.00018128,
3290
+ "loss": 0.0069,
3291
+ "step": 5470
3292
+ },
3293
+ {
3294
+ "epoch": 53.73,
3295
+ "learning_rate": 0.00018088000000000002,
3296
+ "loss": 0.0069,
3297
+ "step": 5480
3298
+ },
3299
+ {
3300
+ "epoch": 53.82,
3301
+ "learning_rate": 0.00018048,
3302
+ "loss": 0.0069,
3303
+ "step": 5490
3304
+ },
3305
+ {
3306
+ "epoch": 53.92,
3307
+ "learning_rate": 0.00018008,
3308
+ "loss": 0.0066,
3309
+ "step": 5500
3310
+ },
3311
+ {
3312
+ "epoch": 54.02,
3313
+ "learning_rate": 0.00017968000000000001,
3314
+ "loss": 0.006,
3315
+ "step": 5510
3316
+ },
3317
+ {
3318
+ "epoch": 54.12,
3319
+ "learning_rate": 0.00017928,
3320
+ "loss": 0.0069,
3321
+ "step": 5520
3322
+ },
3323
+ {
3324
+ "epoch": 54.22,
3325
+ "learning_rate": 0.00017888,
3326
+ "loss": 0.0068,
3327
+ "step": 5530
3328
+ },
3329
+ {
3330
+ "epoch": 54.31,
3331
+ "learning_rate": 0.00017848,
3332
+ "loss": 0.0072,
3333
+ "step": 5540
3334
+ },
3335
+ {
3336
+ "epoch": 54.41,
3337
+ "learning_rate": 0.00017808,
3338
+ "loss": 0.0071,
3339
+ "step": 5550
3340
+ },
3341
+ {
3342
+ "epoch": 54.51,
3343
+ "learning_rate": 0.00017768,
3344
+ "loss": 0.0068,
3345
+ "step": 5560
3346
+ },
3347
+ {
3348
+ "epoch": 54.61,
3349
+ "learning_rate": 0.00017728,
3350
+ "loss": 0.0067,
3351
+ "step": 5570
3352
+ },
3353
+ {
3354
+ "epoch": 54.71,
3355
+ "learning_rate": 0.00017688,
3356
+ "loss": 0.0067,
3357
+ "step": 5580
3358
+ },
3359
+ {
3360
+ "epoch": 54.8,
3361
+ "learning_rate": 0.00017648,
3362
+ "loss": 0.0067,
3363
+ "step": 5590
3364
+ },
3365
+ {
3366
+ "epoch": 54.9,
3367
+ "learning_rate": 0.00017608,
3368
+ "loss": 0.0066,
3369
+ "step": 5600
3370
+ },
3371
+ {
3372
+ "epoch": 55.0,
3373
+ "learning_rate": 0.00017568,
3374
+ "loss": 0.0061,
3375
+ "step": 5610
3376
+ },
3377
+ {
3378
+ "epoch": 55.1,
3379
+ "learning_rate": 0.00017528,
3380
+ "loss": 0.0061,
3381
+ "step": 5620
3382
+ },
3383
+ {
3384
+ "epoch": 55.2,
3385
+ "learning_rate": 0.00017488,
3386
+ "loss": 0.0063,
3387
+ "step": 5630
3388
+ },
3389
+ {
3390
+ "epoch": 55.29,
3391
+ "learning_rate": 0.00017448,
3392
+ "loss": 0.0066,
3393
+ "step": 5640
3394
+ },
3395
+ {
3396
+ "epoch": 55.39,
3397
+ "learning_rate": 0.00017408,
3398
+ "loss": 0.0065,
3399
+ "step": 5650
3400
+ },
3401
+ {
3402
+ "epoch": 55.49,
3403
+ "learning_rate": 0.00017368,
3404
+ "loss": 0.007,
3405
+ "step": 5660
3406
+ },
3407
+ {
3408
+ "epoch": 55.59,
3409
+ "learning_rate": 0.00017328,
3410
+ "loss": 0.0067,
3411
+ "step": 5670
3412
+ },
3413
+ {
3414
+ "epoch": 55.69,
3415
+ "learning_rate": 0.00017287999999999998,
3416
+ "loss": 0.0065,
3417
+ "step": 5680
3418
+ },
3419
+ {
3420
+ "epoch": 55.78,
3421
+ "learning_rate": 0.00017248000000000003,
3422
+ "loss": 0.0063,
3423
+ "step": 5690
3424
+ },
3425
+ {
3426
+ "epoch": 55.88,
3427
+ "learning_rate": 0.00017208000000000002,
3428
+ "loss": 0.0064,
3429
+ "step": 5700
3430
+ },
3431
+ {
3432
+ "epoch": 55.98,
3433
+ "learning_rate": 0.00017168,
3434
+ "loss": 0.0062,
3435
+ "step": 5710
3436
+ },
3437
+ {
3438
+ "epoch": 56.08,
3439
+ "learning_rate": 0.00017128000000000003,
3440
+ "loss": 0.0057,
3441
+ "step": 5720
3442
+ },
3443
+ {
3444
+ "epoch": 56.18,
3445
+ "learning_rate": 0.00017088000000000002,
3446
+ "loss": 0.0061,
3447
+ "step": 5730
3448
+ },
3449
+ {
3450
+ "epoch": 56.27,
3451
+ "learning_rate": 0.00017048,
3452
+ "loss": 0.006,
3453
+ "step": 5740
3454
+ },
3455
+ {
3456
+ "epoch": 56.37,
3457
+ "learning_rate": 0.00017008000000000002,
3458
+ "loss": 0.0063,
3459
+ "step": 5750
3460
+ },
3461
+ {
3462
+ "epoch": 56.47,
3463
+ "learning_rate": 0.00016968000000000002,
3464
+ "loss": 0.0064,
3465
+ "step": 5760
3466
+ },
3467
+ {
3468
+ "epoch": 56.57,
3469
+ "learning_rate": 0.00016928,
3470
+ "loss": 0.0066,
3471
+ "step": 5770
3472
+ },
3473
+ {
3474
+ "epoch": 56.67,
3475
+ "learning_rate": 0.00016888000000000002,
3476
+ "loss": 0.0064,
3477
+ "step": 5780
3478
+ },
3479
+ {
3480
+ "epoch": 56.76,
3481
+ "learning_rate": 0.00016848,
3482
+ "loss": 0.0065,
3483
+ "step": 5790
3484
+ },
3485
+ {
3486
+ "epoch": 56.86,
3487
+ "learning_rate": 0.00016808,
3488
+ "loss": 0.0064,
3489
+ "step": 5800
3490
+ },
3491
+ {
3492
+ "epoch": 56.96,
3493
+ "learning_rate": 0.00016768000000000002,
3494
+ "loss": 0.0061,
3495
+ "step": 5810
3496
+ },
3497
+ {
3498
+ "epoch": 57.06,
3499
+ "learning_rate": 0.00016728,
3500
+ "loss": 0.0056,
3501
+ "step": 5820
3502
+ },
3503
+ {
3504
+ "epoch": 57.16,
3505
+ "learning_rate": 0.00016688,
3506
+ "loss": 0.0059,
3507
+ "step": 5830
3508
+ },
3509
+ {
3510
+ "epoch": 57.25,
3511
+ "learning_rate": 0.00016648000000000002,
3512
+ "loss": 0.0059,
3513
+ "step": 5840
3514
+ },
3515
+ {
3516
+ "epoch": 57.35,
3517
+ "learning_rate": 0.00016608,
3518
+ "loss": 0.006,
3519
+ "step": 5850
3520
+ },
3521
+ {
3522
+ "epoch": 57.45,
3523
+ "learning_rate": 0.00016568000000000003,
3524
+ "loss": 0.0064,
3525
+ "step": 5860
3526
+ },
3527
+ {
3528
+ "epoch": 57.55,
3529
+ "learning_rate": 0.00016528000000000002,
3530
+ "loss": 0.0064,
3531
+ "step": 5870
3532
+ },
3533
+ {
3534
+ "epoch": 57.65,
3535
+ "learning_rate": 0.00016488,
3536
+ "loss": 0.0063,
3537
+ "step": 5880
3538
+ },
3539
+ {
3540
+ "epoch": 57.75,
3541
+ "learning_rate": 0.00016448000000000002,
3542
+ "loss": 0.0062,
3543
+ "step": 5890
3544
+ },
3545
+ {
3546
+ "epoch": 57.84,
3547
+ "learning_rate": 0.00016408000000000001,
3548
+ "loss": 0.0063,
3549
+ "step": 5900
3550
+ },
3551
+ {
3552
+ "epoch": 57.94,
3553
+ "learning_rate": 0.00016368,
3554
+ "loss": 0.0062,
3555
+ "step": 5910
3556
+ },
3557
+ {
3558
+ "epoch": 58.04,
3559
+ "learning_rate": 0.00016328000000000002,
3560
+ "loss": 0.0055,
3561
+ "step": 5920
3562
+ },
3563
+ {
3564
+ "epoch": 58.14,
3565
+ "learning_rate": 0.00016288,
3566
+ "loss": 0.006,
3567
+ "step": 5930
3568
+ },
3569
+ {
3570
+ "epoch": 58.24,
3571
+ "learning_rate": 0.00016248,
3572
+ "loss": 0.0057,
3573
+ "step": 5940
3574
+ },
3575
+ {
3576
+ "epoch": 58.33,
3577
+ "learning_rate": 0.00016208000000000002,
3578
+ "loss": 0.0057,
3579
+ "step": 5950
3580
+ },
3581
+ {
3582
+ "epoch": 58.43,
3583
+ "learning_rate": 0.00016168,
3584
+ "loss": 0.006,
3585
+ "step": 5960
3586
+ },
3587
+ {
3588
+ "epoch": 58.53,
3589
+ "learning_rate": 0.00016128,
3590
+ "loss": 0.0063,
3591
+ "step": 5970
3592
+ },
3593
+ {
3594
+ "epoch": 58.63,
3595
+ "learning_rate": 0.00016088000000000002,
3596
+ "loss": 0.0064,
3597
+ "step": 5980
3598
+ },
3599
+ {
3600
+ "epoch": 58.73,
3601
+ "learning_rate": 0.00016048,
3602
+ "loss": 0.0064,
3603
+ "step": 5990
3604
+ },
3605
+ {
3606
+ "epoch": 58.82,
3607
+ "learning_rate": 0.00016008,
3608
+ "loss": 0.0062,
3609
+ "step": 6000
3610
+ },
3611
+ {
3612
+ "epoch": 58.92,
3613
+ "learning_rate": 0.00015968000000000002,
3614
+ "loss": 0.0062,
3615
+ "step": 6010
3616
+ },
3617
+ {
3618
+ "epoch": 59.02,
3619
+ "learning_rate": 0.00015928,
3620
+ "loss": 0.0057,
3621
+ "step": 6020
3622
+ },
3623
+ {
3624
+ "epoch": 59.12,
3625
+ "learning_rate": 0.00015888,
3626
+ "loss": 0.0058,
3627
+ "step": 6030
3628
+ },
3629
+ {
3630
+ "epoch": 59.22,
3631
+ "learning_rate": 0.00015848000000000001,
3632
+ "loss": 0.0055,
3633
+ "step": 6040
3634
+ },
3635
+ {
3636
+ "epoch": 59.31,
3637
+ "learning_rate": 0.00015808,
3638
+ "loss": 0.0056,
3639
+ "step": 6050
3640
+ },
3641
+ {
3642
+ "epoch": 59.41,
3643
+ "learning_rate": 0.00015768,
3644
+ "loss": 0.0058,
3645
+ "step": 6060
3646
+ },
3647
+ {
3648
+ "epoch": 59.51,
3649
+ "learning_rate": 0.00015728,
3650
+ "loss": 0.0063,
3651
+ "step": 6070
3652
+ },
3653
+ {
3654
+ "epoch": 59.61,
3655
+ "learning_rate": 0.00015688,
3656
+ "loss": 0.0065,
3657
+ "step": 6080
3658
+ },
3659
+ {
3660
+ "epoch": 59.71,
3661
+ "learning_rate": 0.00015648,
3662
+ "loss": 0.0064,
3663
+ "step": 6090
3664
+ },
3665
+ {
3666
+ "epoch": 59.8,
3667
+ "learning_rate": 0.00015608,
3668
+ "loss": 0.0063,
3669
+ "step": 6100
3670
+ },
3671
+ {
3672
+ "epoch": 59.9,
3673
+ "learning_rate": 0.00015568,
3674
+ "loss": 0.006,
3675
+ "step": 6110
3676
+ },
3677
+ {
3678
+ "epoch": 60.0,
3679
+ "learning_rate": 0.00015528,
3680
+ "loss": 0.0059,
3681
+ "step": 6120
3682
+ },
3683
+ {
3684
+ "epoch": 60.1,
3685
+ "learning_rate": 0.00015488,
3686
+ "loss": 0.006,
3687
+ "step": 6130
3688
+ },
3689
+ {
3690
+ "epoch": 60.2,
3691
+ "learning_rate": 0.00015448,
3692
+ "loss": 0.0058,
3693
+ "step": 6140
3694
+ },
3695
+ {
3696
+ "epoch": 60.29,
3697
+ "learning_rate": 0.00015408000000000002,
3698
+ "loss": 0.0057,
3699
+ "step": 6150
3700
+ },
3701
+ {
3702
+ "epoch": 60.39,
3703
+ "learning_rate": 0.00015368,
3704
+ "loss": 0.0056,
3705
+ "step": 6160
3706
+ },
3707
+ {
3708
+ "epoch": 60.49,
3709
+ "learning_rate": 0.00015328,
3710
+ "loss": 0.0056,
3711
+ "step": 6170
3712
+ },
3713
+ {
3714
+ "epoch": 60.59,
3715
+ "learning_rate": 0.00015288,
3716
+ "loss": 0.0061,
3717
+ "step": 6180
3718
+ },
3719
+ {
3720
+ "epoch": 60.69,
3721
+ "learning_rate": 0.00015248,
3722
+ "loss": 0.0067,
3723
+ "step": 6190
3724
+ },
3725
+ {
3726
+ "epoch": 60.78,
3727
+ "learning_rate": 0.00015208,
3728
+ "loss": 0.0066,
3729
+ "step": 6200
3730
+ },
3731
+ {
3732
+ "epoch": 60.88,
3733
+ "learning_rate": 0.00015168,
3734
+ "loss": 0.0062,
3735
+ "step": 6210
3736
+ },
3737
+ {
3738
+ "epoch": 60.98,
3739
+ "learning_rate": 0.00015128,
3740
+ "loss": 0.0058,
3741
+ "step": 6220
3742
+ },
3743
+ {
3744
+ "epoch": 61.08,
3745
+ "learning_rate": 0.00015088,
3746
+ "loss": 0.0055,
3747
+ "step": 6230
3748
+ },
3749
+ {
3750
+ "epoch": 61.18,
3751
+ "learning_rate": 0.00015048,
3752
+ "loss": 0.006,
3753
+ "step": 6240
3754
+ },
3755
+ {
3756
+ "epoch": 61.27,
3757
+ "learning_rate": 0.00015008,
3758
+ "loss": 0.0057,
3759
+ "step": 6250
3760
+ },
3761
+ {
3762
+ "epoch": 61.37,
3763
+ "learning_rate": 0.00014968,
3764
+ "loss": 0.0053,
3765
+ "step": 6260
3766
+ },
3767
+ {
3768
+ "epoch": 61.47,
3769
+ "learning_rate": 0.00014928,
3770
+ "loss": 0.0055,
3771
+ "step": 6270
3772
+ },
3773
+ {
3774
+ "epoch": 61.57,
3775
+ "learning_rate": 0.00014888,
3776
+ "loss": 0.0056,
3777
+ "step": 6280
3778
+ },
3779
+ {
3780
+ "epoch": 61.67,
3781
+ "learning_rate": 0.00014848,
3782
+ "loss": 0.0061,
3783
+ "step": 6290
3784
+ },
3785
+ {
3786
+ "epoch": 61.76,
3787
+ "learning_rate": 0.00014808,
3788
+ "loss": 0.0064,
3789
+ "step": 6300
3790
+ },
3791
+ {
3792
+ "epoch": 61.86,
3793
+ "learning_rate": 0.00014768,
3794
+ "loss": 0.0064,
3795
+ "step": 6310
3796
+ },
3797
+ {
3798
+ "epoch": 61.96,
3799
+ "learning_rate": 0.00014728,
3800
+ "loss": 0.0058,
3801
+ "step": 6320
3802
+ },
3803
+ {
3804
+ "epoch": 62.06,
3805
+ "learning_rate": 0.00014688000000000003,
3806
+ "loss": 0.0053,
3807
+ "step": 6330
3808
+ },
3809
+ {
3810
+ "epoch": 62.16,
3811
+ "learning_rate": 0.00014648000000000002,
3812
+ "loss": 0.0058,
3813
+ "step": 6340
3814
+ },
3815
+ {
3816
+ "epoch": 62.25,
3817
+ "learning_rate": 0.00014608,
3818
+ "loss": 0.0056,
3819
+ "step": 6350
3820
+ },
3821
+ {
3822
+ "epoch": 62.35,
3823
+ "learning_rate": 0.00014568000000000003,
3824
+ "loss": 0.0054,
3825
+ "step": 6360
3826
+ },
3827
+ {
3828
+ "epoch": 62.45,
3829
+ "learning_rate": 0.00014528000000000002,
3830
+ "loss": 0.0054,
3831
+ "step": 6370
3832
+ },
3833
+ {
3834
+ "epoch": 62.55,
3835
+ "learning_rate": 0.00014488,
3836
+ "loss": 0.0052,
3837
+ "step": 6380
3838
+ },
3839
+ {
3840
+ "epoch": 62.65,
3841
+ "learning_rate": 0.00014448000000000003,
3842
+ "loss": 0.0054,
3843
+ "step": 6390
3844
+ },
3845
+ {
3846
+ "epoch": 62.75,
3847
+ "learning_rate": 0.00014408000000000002,
3848
+ "loss": 0.0059,
3849
+ "step": 6400
3850
+ },
3851
+ {
3852
+ "epoch": 62.84,
3853
+ "learning_rate": 0.00014368,
3854
+ "loss": 0.0062,
3855
+ "step": 6410
3856
+ },
3857
+ {
3858
+ "epoch": 62.94,
3859
+ "learning_rate": 0.00014328000000000002,
3860
+ "loss": 0.0064,
3861
+ "step": 6420
3862
+ },
3863
+ {
3864
+ "epoch": 63.04,
3865
+ "learning_rate": 0.00014288000000000001,
3866
+ "loss": 0.0054,
3867
+ "step": 6430
3868
+ },
3869
+ {
3870
+ "epoch": 63.14,
3871
+ "learning_rate": 0.00014248,
3872
+ "loss": 0.0055,
3873
+ "step": 6440
3874
+ },
3875
+ {
3876
+ "epoch": 63.24,
3877
+ "learning_rate": 0.00014208000000000002,
3878
+ "loss": 0.0054,
3879
+ "step": 6450
3880
+ },
3881
+ {
3882
+ "epoch": 63.33,
3883
+ "learning_rate": 0.00014168,
3884
+ "loss": 0.0053,
3885
+ "step": 6460
3886
+ },
3887
+ {
3888
+ "epoch": 63.43,
3889
+ "learning_rate": 0.00014128,
3890
+ "loss": 0.0056,
3891
+ "step": 6470
3892
+ },
3893
+ {
3894
+ "epoch": 63.53,
3895
+ "learning_rate": 0.00014088000000000002,
3896
+ "loss": 0.0054,
3897
+ "step": 6480
3898
+ },
3899
+ {
3900
+ "epoch": 63.63,
3901
+ "learning_rate": 0.00014048,
3902
+ "loss": 0.0051,
3903
+ "step": 6490
3904
+ },
3905
+ {
3906
+ "epoch": 63.73,
3907
+ "learning_rate": 0.00014008,
3908
+ "loss": 0.0053,
3909
+ "step": 6500
3910
+ },
3911
+ {
3912
+ "epoch": 63.82,
3913
+ "learning_rate": 0.00013968000000000002,
3914
+ "loss": 0.0055,
3915
+ "step": 6510
3916
+ },
3917
+ {
3918
+ "epoch": 63.92,
3919
+ "learning_rate": 0.00013928,
3920
+ "loss": 0.0062,
3921
+ "step": 6520
3922
+ },
3923
+ {
3924
+ "epoch": 64.02,
3925
+ "learning_rate": 0.00013888,
3926
+ "loss": 0.006,
3927
+ "step": 6530
3928
+ },
3929
+ {
3930
+ "epoch": 64.12,
3931
+ "learning_rate": 0.00013848000000000002,
3932
+ "loss": 0.0062,
3933
+ "step": 6540
3934
+ },
3935
+ {
3936
+ "epoch": 64.22,
3937
+ "learning_rate": 0.00013808,
3938
+ "loss": 0.0055,
3939
+ "step": 6550
3940
+ },
3941
+ {
3942
+ "epoch": 64.31,
3943
+ "learning_rate": 0.00013768,
3944
+ "loss": 0.0051,
3945
+ "step": 6560
3946
+ },
3947
+ {
3948
+ "epoch": 64.41,
3949
+ "learning_rate": 0.00013728000000000001,
3950
+ "loss": 0.005,
3951
+ "step": 6570
3952
+ },
3953
+ {
3954
+ "epoch": 64.51,
3955
+ "learning_rate": 0.00013688,
3956
+ "loss": 0.0054,
3957
+ "step": 6580
3958
+ },
3959
+ {
3960
+ "epoch": 64.61,
3961
+ "learning_rate": 0.00013648,
3962
+ "loss": 0.0055,
3963
+ "step": 6590
3964
+ },
3965
+ {
3966
+ "epoch": 64.71,
3967
+ "learning_rate": 0.00013608,
3968
+ "loss": 0.0054,
3969
+ "step": 6600
3970
+ },
3971
+ {
3972
+ "epoch": 64.8,
3973
+ "learning_rate": 0.00013568,
3974
+ "loss": 0.0055,
3975
+ "step": 6610
3976
+ },
3977
+ {
3978
+ "epoch": 64.9,
3979
+ "learning_rate": 0.00013528000000000002,
3980
+ "loss": 0.0055,
3981
+ "step": 6620
3982
+ },
3983
+ {
3984
+ "epoch": 65.0,
3985
+ "learning_rate": 0.00013488,
3986
+ "loss": 0.0056,
3987
+ "step": 6630
3988
+ },
3989
+ {
3990
+ "epoch": 65.1,
3991
+ "learning_rate": 0.00013448,
3992
+ "loss": 0.0058,
3993
+ "step": 6640
3994
+ },
3995
+ {
3996
+ "epoch": 65.2,
3997
+ "learning_rate": 0.00013408000000000002,
3998
+ "loss": 0.0059,
3999
+ "step": 6650
4000
+ },
4001
+ {
4002
+ "epoch": 65.29,
4003
+ "learning_rate": 0.00013368,
4004
+ "loss": 0.0058,
4005
+ "step": 6660
4006
+ },
4007
+ {
4008
+ "epoch": 65.39,
4009
+ "learning_rate": 0.00013328,
4010
+ "loss": 0.0053,
4011
+ "step": 6670
4012
+ },
4013
+ {
4014
+ "epoch": 65.49,
4015
+ "learning_rate": 0.00013288000000000002,
4016
+ "loss": 0.005,
4017
+ "step": 6680
4018
+ },
4019
+ {
4020
+ "epoch": 65.59,
4021
+ "learning_rate": 0.00013248,
4022
+ "loss": 0.005,
4023
+ "step": 6690
4024
+ },
4025
+ {
4026
+ "epoch": 65.69,
4027
+ "learning_rate": 0.00013208,
4028
+ "loss": 0.0053,
4029
+ "step": 6700
4030
+ },
4031
+ {
4032
+ "epoch": 65.78,
4033
+ "learning_rate": 0.00013168,
4034
+ "loss": 0.0056,
4035
+ "step": 6710
4036
+ },
4037
+ {
4038
+ "epoch": 65.88,
4039
+ "learning_rate": 0.00013128,
4040
+ "loss": 0.006,
4041
+ "step": 6720
4042
+ },
4043
+ {
4044
+ "epoch": 65.98,
4045
+ "learning_rate": 0.00013088,
4046
+ "loss": 0.0057,
4047
+ "step": 6730
4048
+ },
4049
+ {
4050
+ "epoch": 66.08,
4051
+ "learning_rate": 0.00013048,
4052
+ "loss": 0.0053,
4053
+ "step": 6740
4054
+ },
4055
+ {
4056
+ "epoch": 66.18,
4057
+ "learning_rate": 0.00013008,
4058
+ "loss": 0.0055,
4059
+ "step": 6750
4060
+ },
4061
+ {
4062
+ "epoch": 66.27,
4063
+ "learning_rate": 0.00012968,
4064
+ "loss": 0.0054,
4065
+ "step": 6760
4066
+ },
4067
+ {
4068
+ "epoch": 66.37,
4069
+ "learning_rate": 0.00012928,
4070
+ "loss": 0.0055,
4071
+ "step": 6770
4072
+ },
4073
+ {
4074
+ "epoch": 66.47,
4075
+ "learning_rate": 0.00012888,
4076
+ "loss": 0.0055,
4077
+ "step": 6780
4078
+ },
4079
+ {
4080
+ "epoch": 66.57,
4081
+ "learning_rate": 0.00012848,
4082
+ "loss": 0.0052,
4083
+ "step": 6790
4084
+ },
4085
+ {
4086
+ "epoch": 66.67,
4087
+ "learning_rate": 0.00012808,
4088
+ "loss": 0.0049,
4089
+ "step": 6800
4090
+ },
4091
+ {
4092
+ "epoch": 66.76,
4093
+ "learning_rate": 0.00012768,
4094
+ "loss": 0.0051,
4095
+ "step": 6810
4096
+ },
4097
+ {
4098
+ "epoch": 66.86,
4099
+ "learning_rate": 0.00012728,
4100
+ "loss": 0.0056,
4101
+ "step": 6820
4102
+ },
4103
+ {
4104
+ "epoch": 66.96,
4105
+ "learning_rate": 0.00012688,
4106
+ "loss": 0.0061,
4107
+ "step": 6830
4108
+ },
4109
+ {
4110
+ "epoch": 67.06,
4111
+ "learning_rate": 0.00012648,
4112
+ "loss": 0.0055,
4113
+ "step": 6840
4114
+ },
4115
+ {
4116
+ "epoch": 67.16,
4117
+ "learning_rate": 0.00012607999999999999,
4118
+ "loss": 0.0054,
4119
+ "step": 6850
4120
+ },
4121
+ {
4122
+ "epoch": 67.25,
4123
+ "learning_rate": 0.00012568,
4124
+ "loss": 0.0052,
4125
+ "step": 6860
4126
+ },
4127
+ {
4128
+ "epoch": 67.35,
4129
+ "learning_rate": 0.00012528,
4130
+ "loss": 0.0049,
4131
+ "step": 6870
4132
+ },
4133
+ {
4134
+ "epoch": 67.45,
4135
+ "learning_rate": 0.00012488,
4136
+ "loss": 0.0052,
4137
+ "step": 6880
4138
+ },
4139
+ {
4140
+ "epoch": 67.55,
4141
+ "learning_rate": 0.00012448,
4142
+ "loss": 0.0053,
4143
+ "step": 6890
4144
+ },
4145
+ {
4146
+ "epoch": 67.65,
4147
+ "learning_rate": 0.00012408,
4148
+ "loss": 0.0052,
4149
+ "step": 6900
4150
+ },
4151
+ {
4152
+ "epoch": 67.75,
4153
+ "learning_rate": 0.00012368,
4154
+ "loss": 0.0049,
4155
+ "step": 6910
4156
+ },
4157
+ {
4158
+ "epoch": 67.84,
4159
+ "learning_rate": 0.00012328,
4160
+ "loss": 0.0048,
4161
+ "step": 6920
4162
+ },
4163
+ {
4164
+ "epoch": 67.94,
4165
+ "learning_rate": 0.00012288,
4166
+ "loss": 0.0052,
4167
+ "step": 6930
4168
+ },
4169
+ {
4170
+ "epoch": 68.04,
4171
+ "learning_rate": 0.00012248,
4172
+ "loss": 0.0053,
4173
+ "step": 6940
4174
+ },
4175
+ {
4176
+ "epoch": 68.14,
4177
+ "learning_rate": 0.00012208000000000002,
4178
+ "loss": 0.0057,
4179
+ "step": 6950
4180
+ },
4181
+ {
4182
+ "epoch": 68.24,
4183
+ "learning_rate": 0.00012168000000000001,
4184
+ "loss": 0.0055,
4185
+ "step": 6960
4186
+ },
4187
+ {
4188
+ "epoch": 68.33,
4189
+ "learning_rate": 0.00012128000000000002,
4190
+ "loss": 0.0052,
4191
+ "step": 6970
4192
+ },
4193
+ {
4194
+ "epoch": 68.43,
4195
+ "learning_rate": 0.00012088000000000002,
4196
+ "loss": 0.005,
4197
+ "step": 6980
4198
+ },
4199
+ {
4200
+ "epoch": 68.53,
4201
+ "learning_rate": 0.00012048000000000001,
4202
+ "loss": 0.0048,
4203
+ "step": 6990
4204
+ },
4205
+ {
4206
+ "epoch": 68.63,
4207
+ "learning_rate": 0.00012008000000000002,
4208
+ "loss": 0.0051,
4209
+ "step": 7000
4210
+ }
4211
+ ],
4212
+ "logging_steps": 10,
4213
+ "max_steps": 10000,
4214
+ "num_train_epochs": 99,
4215
+ "save_steps": 1000,
4216
+ "total_flos": 4.67673016172544e+17,
4217
+ "trial_name": null,
4218
+ "trial_params": null
4219
+ }
checkpoint-7000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b5d44c73b8e982d1bd71774d1ff8b2323fbcd973d1b01903f213cf13c78cc7
3
+ size 5880