13bv1
Browse files- added_tokens.json +3 -0
- config.json +27 -0
- generation_config.json +9 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +370 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +37 -0
- trainer_state.json +3682 -0
- training_args.bin +3 -0
- training_log.txt +689 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/baaidial/models/llama-2-13b-hf/",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 4096,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 40,
|
15 |
+
"num_hidden_layers": 40,
|
16 |
+
"num_key_value_heads": 40,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"pretraining_tp": 2,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.33.3",
|
25 |
+
"use_cache": false,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"temperature": 0.9,
|
7 |
+
"top_p": 0.6,
|
8 |
+
"transformers_version": "4.33.3"
|
9 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17e4ae964650282a197f0409497a1f49113b05ca56db62773ded37e8c728ecc9
|
3 |
+
size 9948719433
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa9724388278fe252121da2c8c62d94215c2f953403cc50c6d8647d9d6c4912f
|
3 |
+
size 9904155408
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65a10850c5956604e56447c9397e19e000fa4e1fc4a7f2ee86f5399b87d4fafd
|
3 |
+
size 6178978207
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26031728640
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
323 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
324 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
325 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
326 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
327 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
328 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
329 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
330 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
331 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
332 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
333 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
334 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
335 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
336 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
337 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
338 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
339 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
340 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
341 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
342 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
343 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
344 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
345 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
346 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
347 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
348 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
349 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
350 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
351 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
352 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
353 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
354 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
355 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
356 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
357 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
358 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
359 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
360 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
361 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
362 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
363 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
364 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
365 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
366 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
367 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
368 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
369 |
+
}
|
370 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 1024,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"spaces_between_special_tokens": false,
|
27 |
+
"tokenizer_class": "LlamaTokenizer",
|
28 |
+
"unk_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"use_default_system_prompt": true
|
37 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3682 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9963099630996313,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 609,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 1.3157894736842106e-06,
|
14 |
+
"loss": 1.3013,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 2.631578947368421e-06,
|
20 |
+
"loss": 1.2825,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 3.9473684210526315e-06,
|
26 |
+
"loss": 1.3755,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.02,
|
31 |
+
"learning_rate": 5.263157894736842e-06,
|
32 |
+
"loss": 1.2644,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 6.578947368421053e-06,
|
38 |
+
"loss": 1.2507,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.03,
|
43 |
+
"learning_rate": 7.894736842105263e-06,
|
44 |
+
"loss": 1.1368,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.03,
|
49 |
+
"learning_rate": 9.210526315789474e-06,
|
50 |
+
"loss": 1.1033,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04,
|
55 |
+
"learning_rate": 1.0526315789473684e-05,
|
56 |
+
"loss": 1.0729,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.04,
|
61 |
+
"learning_rate": 1.1842105263157895e-05,
|
62 |
+
"loss": 1.0756,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.05,
|
67 |
+
"learning_rate": 1.3157894736842106e-05,
|
68 |
+
"loss": 1.0396,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.05,
|
73 |
+
"learning_rate": 1.4473684210526317e-05,
|
74 |
+
"loss": 1.0539,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.06,
|
79 |
+
"learning_rate": 1.5789473684210526e-05,
|
80 |
+
"loss": 1.085,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.06,
|
85 |
+
"learning_rate": 1.7105263157894737e-05,
|
86 |
+
"loss": 1.0104,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.07,
|
91 |
+
"learning_rate": 1.8421052631578947e-05,
|
92 |
+
"loss": 1.0773,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.07,
|
97 |
+
"learning_rate": 1.9736842105263158e-05,
|
98 |
+
"loss": 1.0052,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.08,
|
103 |
+
"learning_rate": 2.105263157894737e-05,
|
104 |
+
"loss": 1.0603,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.08,
|
109 |
+
"learning_rate": 2.236842105263158e-05,
|
110 |
+
"loss": 1.0628,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.09,
|
115 |
+
"learning_rate": 2.368421052631579e-05,
|
116 |
+
"loss": 1.0233,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.09,
|
121 |
+
"learning_rate": 2.5e-05,
|
122 |
+
"loss": 1.0953,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.1,
|
127 |
+
"learning_rate": 2.499982279551347e-05,
|
128 |
+
"loss": 1.0786,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.1,
|
133 |
+
"learning_rate": 2.4999291187078104e-05,
|
134 |
+
"loss": 1.0389,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.11,
|
139 |
+
"learning_rate": 2.4998405189766444e-05,
|
140 |
+
"loss": 1.0168,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.11,
|
145 |
+
"learning_rate": 2.4997164828698926e-05,
|
146 |
+
"loss": 1.036,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.12,
|
151 |
+
"learning_rate": 2.4995570139043158e-05,
|
152 |
+
"loss": 1.0171,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.12,
|
157 |
+
"learning_rate": 2.4993621166012923e-05,
|
158 |
+
"loss": 1.0811,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.13,
|
163 |
+
"learning_rate": 2.4991317964866905e-05,
|
164 |
+
"loss": 1.0955,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.13,
|
169 |
+
"learning_rate": 2.4988660600907115e-05,
|
170 |
+
"loss": 1.0038,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.14,
|
175 |
+
"learning_rate": 2.4985649149477043e-05,
|
176 |
+
"loss": 1.0558,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.14,
|
181 |
+
"learning_rate": 2.4982283695959525e-05,
|
182 |
+
"loss": 1.0707,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.15,
|
187 |
+
"learning_rate": 2.4978564335774313e-05,
|
188 |
+
"loss": 1.1162,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.15,
|
193 |
+
"learning_rate": 2.4974491174375374e-05,
|
194 |
+
"loss": 1.006,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.16,
|
199 |
+
"learning_rate": 2.497006432724791e-05,
|
200 |
+
"loss": 1.0481,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.16,
|
205 |
+
"learning_rate": 2.4965283919905065e-05,
|
206 |
+
"loss": 1.0609,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.17,
|
211 |
+
"learning_rate": 2.4960150087884376e-05,
|
212 |
+
"loss": 1.0946,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.17,
|
217 |
+
"learning_rate": 2.4954662976743944e-05,
|
218 |
+
"loss": 1.0222,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.18,
|
223 |
+
"learning_rate": 2.494882274205827e-05,
|
224 |
+
"loss": 1.0427,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.18,
|
229 |
+
"learning_rate": 2.4942629549413894e-05,
|
230 |
+
"loss": 1.0987,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.19,
|
235 |
+
"learning_rate": 2.4936083574404646e-05,
|
236 |
+
"loss": 1.1212,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.19,
|
241 |
+
"learning_rate": 2.4929185002626714e-05,
|
242 |
+
"loss": 1.0986,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.2,
|
247 |
+
"learning_rate": 2.492193402967336e-05,
|
248 |
+
"loss": 1.05,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.2,
|
253 |
+
"learning_rate": 2.4914330861129376e-05,
|
254 |
+
"loss": 1.0784,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.21,
|
259 |
+
"learning_rate": 2.4906375712565245e-05,
|
260 |
+
"loss": 1.0997,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.21,
|
265 |
+
"learning_rate": 2.489806880953106e-05,
|
266 |
+
"loss": 1.0774,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.22,
|
271 |
+
"learning_rate": 2.4889410387550093e-05,
|
272 |
+
"loss": 1.0832,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.22,
|
277 |
+
"learning_rate": 2.488040069211214e-05,
|
278 |
+
"loss": 1.0649,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.23,
|
283 |
+
"learning_rate": 2.487103997866655e-05,
|
284 |
+
"loss": 1.0684,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.23,
|
289 |
+
"learning_rate": 2.4861328512615e-05,
|
290 |
+
"loss": 1.0857,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.24,
|
295 |
+
"learning_rate": 2.485126656930394e-05,
|
296 |
+
"loss": 1.0896,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.24,
|
301 |
+
"learning_rate": 2.4840854434016808e-05,
|
302 |
+
"loss": 1.0719,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.25,
|
307 |
+
"learning_rate": 2.4830092401965942e-05,
|
308 |
+
"loss": 1.0917,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.25,
|
313 |
+
"learning_rate": 2.4818980778284202e-05,
|
314 |
+
"loss": 1.0893,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.26,
|
319 |
+
"learning_rate": 2.4807519878016313e-05,
|
320 |
+
"loss": 1.0136,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.26,
|
325 |
+
"learning_rate": 2.4795710026109954e-05,
|
326 |
+
"loss": 1.0472,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.27,
|
331 |
+
"learning_rate": 2.4783551557406515e-05,
|
332 |
+
"loss": 1.0625,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.27,
|
337 |
+
"learning_rate": 2.4771044816631635e-05,
|
338 |
+
"loss": 1.1197,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.28,
|
343 |
+
"learning_rate": 2.4758190158385402e-05,
|
344 |
+
"loss": 1.0531,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.28,
|
349 |
+
"learning_rate": 2.4744987947132318e-05,
|
350 |
+
"loss": 1.0767,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.29,
|
355 |
+
"learning_rate": 2.473143855719095e-05,
|
356 |
+
"loss": 1.0852,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.29,
|
361 |
+
"learning_rate": 2.4717542372723333e-05,
|
362 |
+
"loss": 1.093,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.3,
|
367 |
+
"learning_rate": 2.4703299787724065e-05,
|
368 |
+
"loss": 1.0991,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.3,
|
373 |
+
"learning_rate": 2.468871120600913e-05,
|
374 |
+
"loss": 1.0982,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.31,
|
379 |
+
"learning_rate": 2.4673777041204478e-05,
|
380 |
+
"loss": 1.1232,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.31,
|
385 |
+
"learning_rate": 2.465849771673427e-05,
|
386 |
+
"loss": 1.0692,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.31,
|
391 |
+
"learning_rate": 2.4642873665808873e-05,
|
392 |
+
"loss": 1.1136,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.32,
|
397 |
+
"learning_rate": 2.4626905331412608e-05,
|
398 |
+
"loss": 1.0771,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.32,
|
403 |
+
"learning_rate": 2.4610593166291143e-05,
|
404 |
+
"loss": 1.0464,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.33,
|
409 |
+
"learning_rate": 2.4593937632938695e-05,
|
410 |
+
"loss": 1.0578,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.33,
|
415 |
+
"learning_rate": 2.457693920358491e-05,
|
416 |
+
"loss": 1.0322,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.34,
|
421 |
+
"learning_rate": 2.455959836018145e-05,
|
422 |
+
"loss": 1.0573,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.34,
|
427 |
+
"learning_rate": 2.454191559438836e-05,
|
428 |
+
"loss": 1.083,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.35,
|
433 |
+
"learning_rate": 2.4523891407560107e-05,
|
434 |
+
"loss": 1.0426,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.35,
|
439 |
+
"learning_rate": 2.4505526310731376e-05,
|
440 |
+
"loss": 1.0706,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.36,
|
445 |
+
"learning_rate": 2.448682082460257e-05,
|
446 |
+
"loss": 1.089,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.36,
|
451 |
+
"learning_rate": 2.446777547952507e-05,
|
452 |
+
"loss": 1.0918,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.37,
|
457 |
+
"learning_rate": 2.4448390815486165e-05,
|
458 |
+
"loss": 1.0869,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.37,
|
463 |
+
"learning_rate": 2.4428667382093762e-05,
|
464 |
+
"loss": 1.0751,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.38,
|
469 |
+
"learning_rate": 2.440860573856081e-05,
|
470 |
+
"loss": 1.0684,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.38,
|
475 |
+
"learning_rate": 2.438820645368942e-05,
|
476 |
+
"loss": 1.0704,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.39,
|
481 |
+
"learning_rate": 2.4367470105854766e-05,
|
482 |
+
"loss": 1.0671,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.39,
|
487 |
+
"learning_rate": 2.4346397282988666e-05,
|
488 |
+
"loss": 1.0434,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.4,
|
493 |
+
"learning_rate": 2.432498858256292e-05,
|
494 |
+
"loss": 1.0605,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.4,
|
499 |
+
"learning_rate": 2.4303244611572372e-05,
|
500 |
+
"loss": 1.0536,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.41,
|
505 |
+
"learning_rate": 2.4281165986517696e-05,
|
506 |
+
"loss": 1.0807,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.41,
|
511 |
+
"learning_rate": 2.425875333338792e-05,
|
512 |
+
"loss": 1.0605,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.42,
|
517 |
+
"learning_rate": 2.4236007287642664e-05,
|
518 |
+
"loss": 1.056,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.42,
|
523 |
+
"learning_rate": 2.421292849419416e-05,
|
524 |
+
"loss": 1.0294,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.43,
|
529 |
+
"learning_rate": 2.4189517607388918e-05,
|
530 |
+
"loss": 1.0571,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.43,
|
535 |
+
"learning_rate": 2.416577529098921e-05,
|
536 |
+
"loss": 1.1025,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.44,
|
541 |
+
"learning_rate": 2.4141702218154232e-05,
|
542 |
+
"loss": 1.1459,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.44,
|
547 |
+
"learning_rate": 2.4117299071421023e-05,
|
548 |
+
"loss": 1.0755,
|
549 |
+
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.45,
|
553 |
+
"learning_rate": 2.4092566542685123e-05,
|
554 |
+
"loss": 1.0686,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.45,
|
559 |
+
"learning_rate": 2.4067505333180938e-05,
|
560 |
+
"loss": 1.0586,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.46,
|
565 |
+
"learning_rate": 2.404211615346187e-05,
|
566 |
+
"loss": 1.1033,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.46,
|
571 |
+
"learning_rate": 2.401639972338016e-05,
|
572 |
+
"loss": 1.0253,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.47,
|
577 |
+
"learning_rate": 2.399035677206651e-05,
|
578 |
+
"loss": 1.0888,
|
579 |
+
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.47,
|
583 |
+
"learning_rate": 2.396398803790936e-05,
|
584 |
+
"loss": 1.0677,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.48,
|
589 |
+
"learning_rate": 2.393729426853399e-05,
|
590 |
+
"loss": 1.0582,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.48,
|
595 |
+
"learning_rate": 2.3910276220781314e-05,
|
596 |
+
"loss": 1.0223,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.49,
|
601 |
+
"learning_rate": 2.3882934660686418e-05,
|
602 |
+
"loss": 1.0885,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.49,
|
607 |
+
"learning_rate": 2.3855270363456833e-05,
|
608 |
+
"loss": 1.0553,
|
609 |
+
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.5,
|
613 |
+
"learning_rate": 2.382728411345058e-05,
|
614 |
+
"loss": 1.1293,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.5,
|
619 |
+
"learning_rate": 2.3798976704153906e-05,
|
620 |
+
"loss": 1.1106,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.51,
|
625 |
+
"learning_rate": 2.3770348938158805e-05,
|
626 |
+
"loss": 1.0647,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.51,
|
631 |
+
"learning_rate": 2.3741401627140242e-05,
|
632 |
+
"loss": 1.078,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.52,
|
637 |
+
"learning_rate": 2.371213559183316e-05,
|
638 |
+
"loss": 1.0344,
|
639 |
+
"step": 105
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.52,
|
643 |
+
"learning_rate": 2.3682551662009203e-05,
|
644 |
+
"loss": 1.095,
|
645 |
+
"step": 106
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.53,
|
649 |
+
"learning_rate": 2.3652650676453188e-05,
|
650 |
+
"loss": 1.0794,
|
651 |
+
"step": 107
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.53,
|
655 |
+
"learning_rate": 2.362243348293931e-05,
|
656 |
+
"loss": 0.9938,
|
657 |
+
"step": 108
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.54,
|
661 |
+
"learning_rate": 2.3591900938207147e-05,
|
662 |
+
"loss": 1.1374,
|
663 |
+
"step": 109
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.54,
|
667 |
+
"learning_rate": 2.3561053907937315e-05,
|
668 |
+
"loss": 1.0443,
|
669 |
+
"step": 110
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.55,
|
673 |
+
"learning_rate": 2.352989326672696e-05,
|
674 |
+
"loss": 1.0452,
|
675 |
+
"step": 111
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.55,
|
679 |
+
"learning_rate": 2.349841989806495e-05,
|
680 |
+
"loss": 1.0359,
|
681 |
+
"step": 112
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.56,
|
685 |
+
"learning_rate": 2.346663469430683e-05,
|
686 |
+
"loss": 1.0973,
|
687 |
+
"step": 113
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.56,
|
691 |
+
"learning_rate": 2.3434538556649515e-05,
|
692 |
+
"loss": 1.138,
|
693 |
+
"step": 114
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.57,
|
697 |
+
"learning_rate": 2.3402132395105737e-05,
|
698 |
+
"loss": 1.0806,
|
699 |
+
"step": 115
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.57,
|
703 |
+
"learning_rate": 2.336941712847825e-05,
|
704 |
+
"loss": 1.1112,
|
705 |
+
"step": 116
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.58,
|
709 |
+
"learning_rate": 2.3336393684333778e-05,
|
710 |
+
"loss": 1.0837,
|
711 |
+
"step": 117
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.58,
|
715 |
+
"learning_rate": 2.3303062998976712e-05,
|
716 |
+
"loss": 1.0794,
|
717 |
+
"step": 118
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.59,
|
721 |
+
"learning_rate": 2.3269426017422576e-05,
|
722 |
+
"loss": 1.0757,
|
723 |
+
"step": 119
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.59,
|
727 |
+
"learning_rate": 2.3235483693371214e-05,
|
728 |
+
"loss": 0.9923,
|
729 |
+
"step": 120
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.6,
|
733 |
+
"learning_rate": 2.3201236989179766e-05,
|
734 |
+
"loss": 1.0442,
|
735 |
+
"step": 121
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.6,
|
739 |
+
"learning_rate": 2.3166686875835365e-05,
|
740 |
+
"loss": 1.0608,
|
741 |
+
"step": 122
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.61,
|
745 |
+
"learning_rate": 2.313183433292764e-05,
|
746 |
+
"loss": 1.0806,
|
747 |
+
"step": 123
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.61,
|
751 |
+
"learning_rate": 2.3096680348620886e-05,
|
752 |
+
"loss": 1.0728,
|
753 |
+
"step": 124
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.62,
|
757 |
+
"learning_rate": 2.3061225919626124e-05,
|
758 |
+
"loss": 1.0979,
|
759 |
+
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.62,
|
763 |
+
"learning_rate": 2.3025472051172755e-05,
|
764 |
+
"loss": 1.0827,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.62,
|
769 |
+
"learning_rate": 2.2989419756980134e-05,
|
770 |
+
"loss": 1.0715,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.63,
|
775 |
+
"learning_rate": 2.295307005922879e-05,
|
776 |
+
"loss": 1.0668,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.63,
|
781 |
+
"learning_rate": 2.2916423988531437e-05,
|
782 |
+
"loss": 1.0726,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.64,
|
787 |
+
"learning_rate": 2.2879482583903783e-05,
|
788 |
+
"loss": 1.1038,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.64,
|
793 |
+
"learning_rate": 2.2842246892735053e-05,
|
794 |
+
"loss": 1.0698,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.65,
|
799 |
+
"learning_rate": 2.2804717970758286e-05,
|
800 |
+
"loss": 1.0782,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.65,
|
805 |
+
"learning_rate": 2.2766896882020422e-05,
|
806 |
+
"loss": 1.0834,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.66,
|
811 |
+
"learning_rate": 2.2728784698852114e-05,
|
812 |
+
"loss": 1.0536,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.66,
|
817 |
+
"learning_rate": 2.2690382501837344e-05,
|
818 |
+
"loss": 1.0867,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.67,
|
823 |
+
"learning_rate": 2.2651691379782764e-05,
|
824 |
+
"loss": 1.0369,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.67,
|
829 |
+
"learning_rate": 2.2612712429686845e-05,
|
830 |
+
"loss": 1.0474,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.68,
|
835 |
+
"learning_rate": 2.2573446756708754e-05,
|
836 |
+
"loss": 1.129,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.68,
|
841 |
+
"learning_rate": 2.2533895474137047e-05,
|
842 |
+
"loss": 1.0561,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.69,
|
847 |
+
"learning_rate": 2.2494059703358073e-05,
|
848 |
+
"loss": 1.1228,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.69,
|
853 |
+
"learning_rate": 2.24539405738242e-05,
|
854 |
+
"loss": 1.1673,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.7,
|
859 |
+
"learning_rate": 2.2413539223021794e-05,
|
860 |
+
"loss": 1.0184,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.7,
|
865 |
+
"learning_rate": 2.237285679643895e-05,
|
866 |
+
"loss": 1.0699,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.71,
|
871 |
+
"learning_rate": 2.2331894447533035e-05,
|
872 |
+
"loss": 1.0924,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.71,
|
877 |
+
"learning_rate": 2.229065333769796e-05,
|
878 |
+
"loss": 1.0106,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.72,
|
883 |
+
"learning_rate": 2.2249134636231285e-05,
|
884 |
+
"loss": 1.0525,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.72,
|
889 |
+
"learning_rate": 2.2207339520301033e-05,
|
890 |
+
"loss": 1.1001,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.73,
|
895 |
+
"learning_rate": 2.216526917491234e-05,
|
896 |
+
"loss": 1.0832,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.73,
|
901 |
+
"learning_rate": 2.2122924792873827e-05,
|
902 |
+
"loss": 0.9838,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.74,
|
907 |
+
"learning_rate": 2.2080307574763824e-05,
|
908 |
+
"loss": 1.0705,
|
909 |
+
"step": 150
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.74,
|
913 |
+
"learning_rate": 2.2037418728896282e-05,
|
914 |
+
"loss": 1.1082,
|
915 |
+
"step": 151
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.75,
|
919 |
+
"learning_rate": 2.1994259471286545e-05,
|
920 |
+
"loss": 1.0794,
|
921 |
+
"step": 152
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.75,
|
925 |
+
"learning_rate": 2.1950831025616873e-05,
|
926 |
+
"loss": 1.0738,
|
927 |
+
"step": 153
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.76,
|
931 |
+
"learning_rate": 2.190713462320173e-05,
|
932 |
+
"loss": 1.0687,
|
933 |
+
"step": 154
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.76,
|
937 |
+
"learning_rate": 2.186317150295289e-05,
|
938 |
+
"loss": 0.9987,
|
939 |
+
"step": 155
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.77,
|
943 |
+
"learning_rate": 2.1818942911344283e-05,
|
944 |
+
"loss": 1.0749,
|
945 |
+
"step": 156
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.77,
|
949 |
+
"learning_rate": 2.17744501023767e-05,
|
950 |
+
"loss": 1.053,
|
951 |
+
"step": 157
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.78,
|
955 |
+
"learning_rate": 2.1729694337542196e-05,
|
956 |
+
"loss": 1.0967,
|
957 |
+
"step": 158
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.78,
|
961 |
+
"learning_rate": 2.168467688578834e-05,
|
962 |
+
"loss": 1.1154,
|
963 |
+
"step": 159
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.79,
|
967 |
+
"learning_rate": 2.163939902348225e-05,
|
968 |
+
"loss": 1.0552,
|
969 |
+
"step": 160
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.79,
|
973 |
+
"learning_rate": 2.1593862034374365e-05,
|
974 |
+
"loss": 1.0798,
|
975 |
+
"step": 161
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.8,
|
979 |
+
"learning_rate": 2.15480672095621e-05,
|
980 |
+
"loss": 1.073,
|
981 |
+
"step": 162
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.8,
|
985 |
+
"learning_rate": 2.15020158474532e-05,
|
986 |
+
"loss": 1.0787,
|
987 |
+
"step": 163
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.81,
|
991 |
+
"learning_rate": 2.145570925372894e-05,
|
992 |
+
"loss": 1.034,
|
993 |
+
"step": 164
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.81,
|
997 |
+
"learning_rate": 2.1409148741307107e-05,
|
998 |
+
"loss": 1.0699,
|
999 |
+
"step": 165
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.82,
|
1003 |
+
"learning_rate": 2.1362335630304768e-05,
|
1004 |
+
"loss": 0.9939,
|
1005 |
+
"step": 166
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.82,
|
1009 |
+
"learning_rate": 2.131527124800086e-05,
|
1010 |
+
"loss": 1.0616,
|
1011 |
+
"step": 167
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.83,
|
1015 |
+
"learning_rate": 2.1267956928798525e-05,
|
1016 |
+
"loss": 0.992,
|
1017 |
+
"step": 168
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.83,
|
1021 |
+
"learning_rate": 2.1220394014187312e-05,
|
1022 |
+
"loss": 1.0463,
|
1023 |
+
"step": 169
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.84,
|
1027 |
+
"learning_rate": 2.1172583852705115e-05,
|
1028 |
+
"loss": 1.071,
|
1029 |
+
"step": 170
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.84,
|
1033 |
+
"learning_rate": 2.1124527799899953e-05,
|
1034 |
+
"loss": 1.0274,
|
1035 |
+
"step": 171
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.85,
|
1039 |
+
"learning_rate": 2.1076227218291535e-05,
|
1040 |
+
"loss": 1.0593,
|
1041 |
+
"step": 172
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.85,
|
1045 |
+
"learning_rate": 2.1027683477332623e-05,
|
1046 |
+
"loss": 1.0286,
|
1047 |
+
"step": 173
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.86,
|
1051 |
+
"learning_rate": 2.0978897953370204e-05,
|
1052 |
+
"loss": 1.0657,
|
1053 |
+
"step": 174
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.86,
|
1057 |
+
"learning_rate": 2.0929872029606472e-05,
|
1058 |
+
"loss": 1.0616,
|
1059 |
+
"step": 175
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.87,
|
1063 |
+
"learning_rate": 2.088060709605962e-05,
|
1064 |
+
"loss": 1.0425,
|
1065 |
+
"step": 176
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.87,
|
1069 |
+
"learning_rate": 2.08311045495244e-05,
|
1070 |
+
"loss": 1.0024,
|
1071 |
+
"step": 177
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.88,
|
1075 |
+
"learning_rate": 2.078136579353255e-05,
|
1076 |
+
"loss": 1.0252,
|
1077 |
+
"step": 178
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.88,
|
1081 |
+
"learning_rate": 2.0731392238312985e-05,
|
1082 |
+
"loss": 1.0623,
|
1083 |
+
"step": 179
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.89,
|
1087 |
+
"learning_rate": 2.0681185300751814e-05,
|
1088 |
+
"loss": 1.0712,
|
1089 |
+
"step": 180
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.89,
|
1093 |
+
"learning_rate": 2.0630746404352168e-05,
|
1094 |
+
"loss": 1.0976,
|
1095 |
+
"step": 181
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.9,
|
1099 |
+
"learning_rate": 2.058007697919386e-05,
|
1100 |
+
"loss": 1.0481,
|
1101 |
+
"step": 182
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.9,
|
1105 |
+
"learning_rate": 2.0529178461892785e-05,
|
1106 |
+
"loss": 1.0502,
|
1107 |
+
"step": 183
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.91,
|
1111 |
+
"learning_rate": 2.0478052295560253e-05,
|
1112 |
+
"loss": 1.0707,
|
1113 |
+
"step": 184
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.91,
|
1117 |
+
"learning_rate": 2.0426699929762035e-05,
|
1118 |
+
"loss": 1.0669,
|
1119 |
+
"step": 185
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.92,
|
1123 |
+
"learning_rate": 2.037512282047726e-05,
|
1124 |
+
"loss": 1.0067,
|
1125 |
+
"step": 186
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.92,
|
1129 |
+
"learning_rate": 2.0323322430057166e-05,
|
1130 |
+
"loss": 1.1202,
|
1131 |
+
"step": 187
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.92,
|
1135 |
+
"learning_rate": 2.0271300227183598e-05,
|
1136 |
+
"loss": 1.074,
|
1137 |
+
"step": 188
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.93,
|
1141 |
+
"learning_rate": 2.02190576868274e-05,
|
1142 |
+
"loss": 1.0394,
|
1143 |
+
"step": 189
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.93,
|
1147 |
+
"learning_rate": 2.016659629020658e-05,
|
1148 |
+
"loss": 1.0368,
|
1149 |
+
"step": 190
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.94,
|
1153 |
+
"learning_rate": 2.0113917524744308e-05,
|
1154 |
+
"loss": 1.0733,
|
1155 |
+
"step": 191
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.94,
|
1159 |
+
"learning_rate": 2.0061022884026762e-05,
|
1160 |
+
"loss": 1.0594,
|
1161 |
+
"step": 192
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.95,
|
1165 |
+
"learning_rate": 2.0007913867760763e-05,
|
1166 |
+
"loss": 1.0401,
|
1167 |
+
"step": 193
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.95,
|
1171 |
+
"learning_rate": 1.995459198173127e-05,
|
1172 |
+
"loss": 1.0903,
|
1173 |
+
"step": 194
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.96,
|
1177 |
+
"learning_rate": 1.9901058737758667e-05,
|
1178 |
+
"loss": 1.1046,
|
1179 |
+
"step": 195
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.96,
|
1183 |
+
"learning_rate": 1.9847315653655915e-05,
|
1184 |
+
"loss": 1.0478,
|
1185 |
+
"step": 196
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.97,
|
1189 |
+
"learning_rate": 1.9793364253185518e-05,
|
1190 |
+
"loss": 1.0747,
|
1191 |
+
"step": 197
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.97,
|
1195 |
+
"learning_rate": 1.9739206066016307e-05,
|
1196 |
+
"loss": 1.0484,
|
1197 |
+
"step": 198
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.98,
|
1201 |
+
"learning_rate": 1.9684842627680088e-05,
|
1202 |
+
"loss": 1.0897,
|
1203 |
+
"step": 199
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.98,
|
1207 |
+
"learning_rate": 1.963027547952808e-05,
|
1208 |
+
"loss": 1.0715,
|
1209 |
+
"step": 200
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.99,
|
1213 |
+
"learning_rate": 1.9575506168687247e-05,
|
1214 |
+
"loss": 1.0671,
|
1215 |
+
"step": 201
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.99,
|
1219 |
+
"learning_rate": 1.9520536248016403e-05,
|
1220 |
+
"loss": 0.9719,
|
1221 |
+
"step": 202
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.0,
|
1225 |
+
"learning_rate": 1.946536727606219e-05,
|
1226 |
+
"loss": 1.0384,
|
1227 |
+
"step": 203
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.0,
|
1231 |
+
"learning_rate": 1.941000081701492e-05,
|
1232 |
+
"loss": 0.7968,
|
1233 |
+
"step": 204
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.01,
|
1237 |
+
"learning_rate": 1.9354438440664167e-05,
|
1238 |
+
"loss": 0.6873,
|
1239 |
+
"step": 205
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.01,
|
1243 |
+
"learning_rate": 1.929868172235433e-05,
|
1244 |
+
"loss": 0.6435,
|
1245 |
+
"step": 206
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.02,
|
1249 |
+
"learning_rate": 1.9242732242939893e-05,
|
1250 |
+
"loss": 0.6083,
|
1251 |
+
"step": 207
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 1.02,
|
1255 |
+
"learning_rate": 1.9186591588740667e-05,
|
1256 |
+
"loss": 0.6499,
|
1257 |
+
"step": 208
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 1.03,
|
1261 |
+
"learning_rate": 1.913026135149678e-05,
|
1262 |
+
"loss": 0.6342,
|
1263 |
+
"step": 209
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.03,
|
1267 |
+
"learning_rate": 1.9073743128323558e-05,
|
1268 |
+
"loss": 0.6186,
|
1269 |
+
"step": 210
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.04,
|
1273 |
+
"learning_rate": 1.9017038521666232e-05,
|
1274 |
+
"loss": 0.6751,
|
1275 |
+
"step": 211
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 1.04,
|
1279 |
+
"learning_rate": 1.8960149139254513e-05,
|
1280 |
+
"loss": 0.6175,
|
1281 |
+
"step": 212
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.05,
|
1285 |
+
"learning_rate": 1.8903076594057013e-05,
|
1286 |
+
"loss": 0.5863,
|
1287 |
+
"step": 213
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.05,
|
1291 |
+
"learning_rate": 1.88458225042355e-05,
|
1292 |
+
"loss": 0.6271,
|
1293 |
+
"step": 214
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 1.06,
|
1297 |
+
"learning_rate": 1.8788388493099033e-05,
|
1298 |
+
"loss": 0.6416,
|
1299 |
+
"step": 215
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.06,
|
1303 |
+
"learning_rate": 1.8730776189057918e-05,
|
1304 |
+
"loss": 0.653,
|
1305 |
+
"step": 216
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.07,
|
1309 |
+
"learning_rate": 1.8672987225577552e-05,
|
1310 |
+
"loss": 0.6631,
|
1311 |
+
"step": 217
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.07,
|
1315 |
+
"learning_rate": 1.8615023241132127e-05,
|
1316 |
+
"loss": 0.6022,
|
1317 |
+
"step": 218
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 1.08,
|
1321 |
+
"learning_rate": 1.855688587915813e-05,
|
1322 |
+
"loss": 0.645,
|
1323 |
+
"step": 219
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.08,
|
1327 |
+
"learning_rate": 1.8498576788007775e-05,
|
1328 |
+
"loss": 0.6546,
|
1329 |
+
"step": 220
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.09,
|
1333 |
+
"learning_rate": 1.8440097620902284e-05,
|
1334 |
+
"loss": 0.6453,
|
1335 |
+
"step": 221
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 1.09,
|
1339 |
+
"learning_rate": 1.838145003588497e-05,
|
1340 |
+
"loss": 0.6509,
|
1341 |
+
"step": 222
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.1,
|
1345 |
+
"learning_rate": 1.832263569577427e-05,
|
1346 |
+
"loss": 0.5689,
|
1347 |
+
"step": 223
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.1,
|
1351 |
+
"learning_rate": 1.8263656268116576e-05,
|
1352 |
+
"loss": 0.5919,
|
1353 |
+
"step": 224
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.11,
|
1357 |
+
"learning_rate": 1.8204513425138952e-05,
|
1358 |
+
"loss": 0.6308,
|
1359 |
+
"step": 225
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.11,
|
1363 |
+
"learning_rate": 1.8145208843701742e-05,
|
1364 |
+
"loss": 0.6666,
|
1365 |
+
"step": 226
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 1.12,
|
1369 |
+
"learning_rate": 1.808574420525101e-05,
|
1370 |
+
"loss": 0.584,
|
1371 |
+
"step": 227
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.12,
|
1375 |
+
"learning_rate": 1.8026121195770874e-05,
|
1376 |
+
"loss": 0.5634,
|
1377 |
+
"step": 228
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.13,
|
1381 |
+
"learning_rate": 1.7966341505735695e-05,
|
1382 |
+
"loss": 0.5975,
|
1383 |
+
"step": 229
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.13,
|
1387 |
+
"learning_rate": 1.7906406830062156e-05,
|
1388 |
+
"loss": 0.6015,
|
1389 |
+
"step": 230
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.14,
|
1393 |
+
"learning_rate": 1.7846318868061212e-05,
|
1394 |
+
"loss": 0.5879,
|
1395 |
+
"step": 231
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.14,
|
1399 |
+
"learning_rate": 1.7786079323389893e-05,
|
1400 |
+
"loss": 0.6187,
|
1401 |
+
"step": 232
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 1.15,
|
1405 |
+
"learning_rate": 1.7725689904003006e-05,
|
1406 |
+
"loss": 0.617,
|
1407 |
+
"step": 233
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 1.15,
|
1411 |
+
"learning_rate": 1.766515232210473e-05,
|
1412 |
+
"loss": 0.6135,
|
1413 |
+
"step": 234
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.16,
|
1417 |
+
"learning_rate": 1.7604468294100034e-05,
|
1418 |
+
"loss": 0.6676,
|
1419 |
+
"step": 235
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.16,
|
1423 |
+
"learning_rate": 1.754363954054605e-05,
|
1424 |
+
"loss": 0.6294,
|
1425 |
+
"step": 236
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.17,
|
1429 |
+
"learning_rate": 1.7482667786103256e-05,
|
1430 |
+
"loss": 0.6308,
|
1431 |
+
"step": 237
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.17,
|
1435 |
+
"learning_rate": 1.7421554759486614e-05,
|
1436 |
+
"loss": 0.5851,
|
1437 |
+
"step": 238
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 1.18,
|
1441 |
+
"learning_rate": 1.736030219341651e-05,
|
1442 |
+
"loss": 0.6303,
|
1443 |
+
"step": 239
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 1.18,
|
1447 |
+
"learning_rate": 1.7298911824569676e-05,
|
1448 |
+
"loss": 0.6124,
|
1449 |
+
"step": 240
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.19,
|
1453 |
+
"learning_rate": 1.7237385393529916e-05,
|
1454 |
+
"loss": 0.6291,
|
1455 |
+
"step": 241
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 1.19,
|
1459 |
+
"learning_rate": 1.7175724644738773e-05,
|
1460 |
+
"loss": 0.6457,
|
1461 |
+
"step": 242
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 1.2,
|
1465 |
+
"learning_rate": 1.7113931326446054e-05,
|
1466 |
+
"loss": 0.6475,
|
1467 |
+
"step": 243
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.2,
|
1471 |
+
"learning_rate": 1.705200719066028e-05,
|
1472 |
+
"loss": 0.6723,
|
1473 |
+
"step": 244
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.21,
|
1477 |
+
"learning_rate": 1.6989953993098998e-05,
|
1478 |
+
"loss": 0.6456,
|
1479 |
+
"step": 245
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.21,
|
1483 |
+
"learning_rate": 1.6927773493139014e-05,
|
1484 |
+
"loss": 0.613,
|
1485 |
+
"step": 246
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 1.22,
|
1489 |
+
"learning_rate": 1.68654674537665e-05,
|
1490 |
+
"loss": 0.6202,
|
1491 |
+
"step": 247
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 1.22,
|
1495 |
+
"learning_rate": 1.6803037641527002e-05,
|
1496 |
+
"loss": 0.5821,
|
1497 |
+
"step": 248
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 1.23,
|
1501 |
+
"learning_rate": 1.674048582647538e-05,
|
1502 |
+
"loss": 0.6698,
|
1503 |
+
"step": 249
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 1.23,
|
1507 |
+
"learning_rate": 1.6677813782125592e-05,
|
1508 |
+
"loss": 0.6762,
|
1509 |
+
"step": 250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.23,
|
1513 |
+
"learning_rate": 1.6615023285400432e-05,
|
1514 |
+
"loss": 0.6087,
|
1515 |
+
"step": 251
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.24,
|
1519 |
+
"learning_rate": 1.6552116116581133e-05,
|
1520 |
+
"loss": 0.6154,
|
1521 |
+
"step": 252
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.24,
|
1525 |
+
"learning_rate": 1.648909405925691e-05,
|
1526 |
+
"loss": 0.6162,
|
1527 |
+
"step": 253
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 1.25,
|
1531 |
+
"learning_rate": 1.6425958900274362e-05,
|
1532 |
+
"loss": 0.624,
|
1533 |
+
"step": 254
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 1.25,
|
1537 |
+
"learning_rate": 1.6362712429686846e-05,
|
1538 |
+
"loss": 0.5986,
|
1539 |
+
"step": 255
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.26,
|
1543 |
+
"learning_rate": 1.629935644070369e-05,
|
1544 |
+
"loss": 0.6152,
|
1545 |
+
"step": 256
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.26,
|
1549 |
+
"learning_rate": 1.6235892729639378e-05,
|
1550 |
+
"loss": 0.6114,
|
1551 |
+
"step": 257
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 1.27,
|
1555 |
+
"learning_rate": 1.617232309586261e-05,
|
1556 |
+
"loss": 0.603,
|
1557 |
+
"step": 258
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.27,
|
1561 |
+
"learning_rate": 1.6108649341745262e-05,
|
1562 |
+
"loss": 0.6791,
|
1563 |
+
"step": 259
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.28,
|
1567 |
+
"learning_rate": 1.604487327261133e-05,
|
1568 |
+
"loss": 0.6662,
|
1569 |
+
"step": 260
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.28,
|
1573 |
+
"learning_rate": 1.59809966966857e-05,
|
1574 |
+
"loss": 0.6407,
|
1575 |
+
"step": 261
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 1.29,
|
1579 |
+
"learning_rate": 1.591702142504291e-05,
|
1580 |
+
"loss": 0.629,
|
1581 |
+
"step": 262
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 1.29,
|
1585 |
+
"learning_rate": 1.5852949271555787e-05,
|
1586 |
+
"loss": 0.6191,
|
1587 |
+
"step": 263
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 1.3,
|
1591 |
+
"learning_rate": 1.5788782052844015e-05,
|
1592 |
+
"loss": 0.6332,
|
1593 |
+
"step": 264
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.3,
|
1597 |
+
"learning_rate": 1.572452158822265e-05,
|
1598 |
+
"loss": 0.642,
|
1599 |
+
"step": 265
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.31,
|
1603 |
+
"learning_rate": 1.5660169699650503e-05,
|
1604 |
+
"loss": 0.6257,
|
1605 |
+
"step": 266
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 1.31,
|
1609 |
+
"learning_rate": 1.5595728211678525e-05,
|
1610 |
+
"loss": 0.6622,
|
1611 |
+
"step": 267
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.32,
|
1615 |
+
"learning_rate": 1.553119895139803e-05,
|
1616 |
+
"loss": 0.6221,
|
1617 |
+
"step": 268
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 1.32,
|
1621 |
+
"learning_rate": 1.546658374838894e-05,
|
1622 |
+
"loss": 0.641,
|
1623 |
+
"step": 269
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 1.33,
|
1627 |
+
"learning_rate": 1.5401884434667864e-05,
|
1628 |
+
"loss": 0.6199,
|
1629 |
+
"step": 270
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.33,
|
1633 |
+
"learning_rate": 1.5337102844636188e-05,
|
1634 |
+
"loss": 0.6204,
|
1635 |
+
"step": 271
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 1.34,
|
1639 |
+
"learning_rate": 1.5272240815028067e-05,
|
1640 |
+
"loss": 0.6315,
|
1641 |
+
"step": 272
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.34,
|
1645 |
+
"learning_rate": 1.520730018485832e-05,
|
1646 |
+
"loss": 0.6727,
|
1647 |
+
"step": 273
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.35,
|
1651 |
+
"learning_rate": 1.5142282795370305e-05,
|
1652 |
+
"loss": 0.6628,
|
1653 |
+
"step": 274
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 1.35,
|
1657 |
+
"learning_rate": 1.5077190489983728e-05,
|
1658 |
+
"loss": 0.6742,
|
1659 |
+
"step": 275
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 1.36,
|
1663 |
+
"learning_rate": 1.5012025114242355e-05,
|
1664 |
+
"loss": 0.6381,
|
1665 |
+
"step": 276
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.36,
|
1669 |
+
"learning_rate": 1.49467885157617e-05,
|
1670 |
+
"loss": 0.6467,
|
1671 |
+
"step": 277
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 1.37,
|
1675 |
+
"learning_rate": 1.4881482544176627e-05,
|
1676 |
+
"loss": 0.6497,
|
1677 |
+
"step": 278
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 1.37,
|
1681 |
+
"learning_rate": 1.4816109051088931e-05,
|
1682 |
+
"loss": 0.6165,
|
1683 |
+
"step": 279
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.38,
|
1687 |
+
"learning_rate": 1.4750669890014807e-05,
|
1688 |
+
"loss": 0.6183,
|
1689 |
+
"step": 280
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.38,
|
1693 |
+
"learning_rate": 1.468516691633233e-05,
|
1694 |
+
"loss": 0.6557,
|
1695 |
+
"step": 281
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 1.39,
|
1699 |
+
"learning_rate": 1.4619601987228832e-05,
|
1700 |
+
"loss": 0.6581,
|
1701 |
+
"step": 282
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 1.39,
|
1705 |
+
"learning_rate": 1.4553976961648244e-05,
|
1706 |
+
"loss": 0.6562,
|
1707 |
+
"step": 283
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.4,
|
1711 |
+
"learning_rate": 1.4488293700238401e-05,
|
1712 |
+
"loss": 0.6587,
|
1713 |
+
"step": 284
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 1.4,
|
1717 |
+
"learning_rate": 1.4422554065298286e-05,
|
1718 |
+
"loss": 0.6124,
|
1719 |
+
"step": 285
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.41,
|
1723 |
+
"learning_rate": 1.435675992072521e-05,
|
1724 |
+
"loss": 0.6168,
|
1725 |
+
"step": 286
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.41,
|
1729 |
+
"learning_rate": 1.4290913131961997e-05,
|
1730 |
+
"loss": 0.6346,
|
1731 |
+
"step": 287
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 1.42,
|
1735 |
+
"learning_rate": 1.4225015565944072e-05,
|
1736 |
+
"loss": 0.6851,
|
1737 |
+
"step": 288
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 1.42,
|
1741 |
+
"learning_rate": 1.4159069091046526e-05,
|
1742 |
+
"loss": 0.652,
|
1743 |
+
"step": 289
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 1.43,
|
1747 |
+
"learning_rate": 1.4093075577031157e-05,
|
1748 |
+
"loss": 0.6331,
|
1749 |
+
"step": 290
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.43,
|
1753 |
+
"learning_rate": 1.4027036894993442e-05,
|
1754 |
+
"loss": 0.6402,
|
1755 |
+
"step": 291
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 1.44,
|
1759 |
+
"learning_rate": 1.396095491730951e-05,
|
1760 |
+
"loss": 0.6072,
|
1761 |
+
"step": 292
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 1.44,
|
1765 |
+
"learning_rate": 1.3894831517583017e-05,
|
1766 |
+
"loss": 0.6314,
|
1767 |
+
"step": 293
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.45,
|
1771 |
+
"learning_rate": 1.3828668570592069e-05,
|
1772 |
+
"loss": 0.5981,
|
1773 |
+
"step": 294
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.45,
|
1777 |
+
"learning_rate": 1.3762467952236027e-05,
|
1778 |
+
"loss": 0.6045,
|
1779 |
+
"step": 295
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.46,
|
1783 |
+
"learning_rate": 1.369623153948235e-05,
|
1784 |
+
"loss": 0.6773,
|
1785 |
+
"step": 296
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 1.46,
|
1789 |
+
"learning_rate": 1.3629961210313353e-05,
|
1790 |
+
"loss": 0.6185,
|
1791 |
+
"step": 297
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 1.47,
|
1795 |
+
"learning_rate": 1.3563658843672985e-05,
|
1796 |
+
"loss": 0.6684,
|
1797 |
+
"step": 298
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 1.47,
|
1801 |
+
"learning_rate": 1.3497326319413539e-05,
|
1802 |
+
"loss": 0.5952,
|
1803 |
+
"step": 299
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 1.48,
|
1807 |
+
"learning_rate": 1.3430965518242362e-05,
|
1808 |
+
"loss": 0.6146,
|
1809 |
+
"step": 300
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.48,
|
1813 |
+
"learning_rate": 1.336457832166852e-05,
|
1814 |
+
"loss": 0.6532,
|
1815 |
+
"step": 301
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.49,
|
1819 |
+
"learning_rate": 1.3298166611949467e-05,
|
1820 |
+
"loss": 0.6521,
|
1821 |
+
"step": 302
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 1.49,
|
1825 |
+
"learning_rate": 1.3231732272037672e-05,
|
1826 |
+
"loss": 0.6157,
|
1827 |
+
"step": 303
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.5,
|
1831 |
+
"learning_rate": 1.3165277185527234e-05,
|
1832 |
+
"loss": 0.6474,
|
1833 |
+
"step": 304
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 1.5,
|
1837 |
+
"learning_rate": 1.3098803236600462e-05,
|
1838 |
+
"loss": 0.5977,
|
1839 |
+
"step": 305
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 1.51,
|
1843 |
+
"learning_rate": 1.3032312309974482e-05,
|
1844 |
+
"loss": 0.624,
|
1845 |
+
"step": 306
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 1.51,
|
1849 |
+
"learning_rate": 1.2965806290847768e-05,
|
1850 |
+
"loss": 0.6255,
|
1851 |
+
"step": 307
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.52,
|
1855 |
+
"learning_rate": 1.2899287064846725e-05,
|
1856 |
+
"loss": 0.6181,
|
1857 |
+
"step": 308
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 1.52,
|
1861 |
+
"learning_rate": 1.2832756517972185e-05,
|
1862 |
+
"loss": 0.6159,
|
1863 |
+
"step": 309
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 1.53,
|
1867 |
+
"learning_rate": 1.2766216536545984e-05,
|
1868 |
+
"loss": 0.6414,
|
1869 |
+
"step": 310
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 1.53,
|
1873 |
+
"learning_rate": 1.2699669007157435e-05,
|
1874 |
+
"loss": 0.5773,
|
1875 |
+
"step": 311
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 1.54,
|
1879 |
+
"learning_rate": 1.2633115816609867e-05,
|
1880 |
+
"loss": 0.627,
|
1881 |
+
"step": 312
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 1.54,
|
1885 |
+
"learning_rate": 1.2566558851867106e-05,
|
1886 |
+
"loss": 0.5812,
|
1887 |
+
"step": 313
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 1.54,
|
1891 |
+
"learning_rate": 1.25e-05,
|
1892 |
+
"loss": 0.6219,
|
1893 |
+
"step": 314
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.55,
|
1897 |
+
"learning_rate": 1.2433441148132897e-05,
|
1898 |
+
"loss": 0.6287,
|
1899 |
+
"step": 315
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 1.55,
|
1903 |
+
"learning_rate": 1.236688418339014e-05,
|
1904 |
+
"loss": 0.5863,
|
1905 |
+
"step": 316
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 1.56,
|
1909 |
+
"learning_rate": 1.2300330992842566e-05,
|
1910 |
+
"loss": 0.5904,
|
1911 |
+
"step": 317
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 1.56,
|
1915 |
+
"learning_rate": 1.223378346345402e-05,
|
1916 |
+
"loss": 0.6398,
|
1917 |
+
"step": 318
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 1.57,
|
1921 |
+
"learning_rate": 1.2167243482027816e-05,
|
1922 |
+
"loss": 0.6025,
|
1923 |
+
"step": 319
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 1.57,
|
1927 |
+
"learning_rate": 1.2100712935153283e-05,
|
1928 |
+
"loss": 0.6047,
|
1929 |
+
"step": 320
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.58,
|
1933 |
+
"learning_rate": 1.2034193709152231e-05,
|
1934 |
+
"loss": 0.6134,
|
1935 |
+
"step": 321
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.58,
|
1939 |
+
"learning_rate": 1.196768769002552e-05,
|
1940 |
+
"loss": 0.6624,
|
1941 |
+
"step": 322
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 1.59,
|
1945 |
+
"learning_rate": 1.190119676339954e-05,
|
1946 |
+
"loss": 0.6065,
|
1947 |
+
"step": 323
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 1.59,
|
1951 |
+
"learning_rate": 1.1834722814472771e-05,
|
1952 |
+
"loss": 0.6245,
|
1953 |
+
"step": 324
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 1.6,
|
1957 |
+
"learning_rate": 1.1768267727962328e-05,
|
1958 |
+
"loss": 0.6223,
|
1959 |
+
"step": 325
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 1.6,
|
1963 |
+
"learning_rate": 1.1701833388050536e-05,
|
1964 |
+
"loss": 0.638,
|
1965 |
+
"step": 326
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 1.61,
|
1969 |
+
"learning_rate": 1.1635421678331485e-05,
|
1970 |
+
"loss": 0.6685,
|
1971 |
+
"step": 327
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 1.61,
|
1975 |
+
"learning_rate": 1.1569034481757644e-05,
|
1976 |
+
"loss": 0.6236,
|
1977 |
+
"step": 328
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 1.62,
|
1981 |
+
"learning_rate": 1.150267368058646e-05,
|
1982 |
+
"loss": 0.6174,
|
1983 |
+
"step": 329
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 1.62,
|
1987 |
+
"learning_rate": 1.1436341156327016e-05,
|
1988 |
+
"loss": 0.6431,
|
1989 |
+
"step": 330
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 1.63,
|
1993 |
+
"learning_rate": 1.137003878968665e-05,
|
1994 |
+
"loss": 0.6326,
|
1995 |
+
"step": 331
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 1.63,
|
1999 |
+
"learning_rate": 1.1303768460517657e-05,
|
2000 |
+
"loss": 0.6585,
|
2001 |
+
"step": 332
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 1.64,
|
2005 |
+
"learning_rate": 1.1237532047763974e-05,
|
2006 |
+
"loss": 0.653,
|
2007 |
+
"step": 333
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 1.64,
|
2011 |
+
"learning_rate": 1.1171331429407934e-05,
|
2012 |
+
"loss": 0.6169,
|
2013 |
+
"step": 334
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 1.65,
|
2017 |
+
"learning_rate": 1.1105168482416984e-05,
|
2018 |
+
"loss": 0.5823,
|
2019 |
+
"step": 335
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.65,
|
2023 |
+
"learning_rate": 1.1039045082690496e-05,
|
2024 |
+
"loss": 0.6307,
|
2025 |
+
"step": 336
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 1.66,
|
2029 |
+
"learning_rate": 1.0972963105006556e-05,
|
2030 |
+
"loss": 0.6119,
|
2031 |
+
"step": 337
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 1.66,
|
2035 |
+
"learning_rate": 1.0906924422968846e-05,
|
2036 |
+
"loss": 0.6236,
|
2037 |
+
"step": 338
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 1.67,
|
2041 |
+
"learning_rate": 1.0840930908953477e-05,
|
2042 |
+
"loss": 0.5794,
|
2043 |
+
"step": 339
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 1.67,
|
2047 |
+
"learning_rate": 1.0774984434055932e-05,
|
2048 |
+
"loss": 0.6227,
|
2049 |
+
"step": 340
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 1.68,
|
2053 |
+
"learning_rate": 1.0709086868038005e-05,
|
2054 |
+
"loss": 0.6367,
|
2055 |
+
"step": 341
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 1.68,
|
2059 |
+
"learning_rate": 1.064324007927479e-05,
|
2060 |
+
"loss": 0.6325,
|
2061 |
+
"step": 342
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.69,
|
2065 |
+
"learning_rate": 1.0577445934701717e-05,
|
2066 |
+
"loss": 0.6073,
|
2067 |
+
"step": 343
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 1.69,
|
2071 |
+
"learning_rate": 1.0511706299761602e-05,
|
2072 |
+
"loss": 0.6616,
|
2073 |
+
"step": 344
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 1.7,
|
2077 |
+
"learning_rate": 1.044602303835176e-05,
|
2078 |
+
"loss": 0.6514,
|
2079 |
+
"step": 345
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 1.7,
|
2083 |
+
"learning_rate": 1.0380398012771169e-05,
|
2084 |
+
"loss": 0.6421,
|
2085 |
+
"step": 346
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 1.71,
|
2089 |
+
"learning_rate": 1.0314833083667672e-05,
|
2090 |
+
"loss": 0.6286,
|
2091 |
+
"step": 347
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 1.71,
|
2095 |
+
"learning_rate": 1.0249330109985198e-05,
|
2096 |
+
"loss": 0.6372,
|
2097 |
+
"step": 348
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 1.72,
|
2101 |
+
"learning_rate": 1.0183890948911074e-05,
|
2102 |
+
"loss": 0.6379,
|
2103 |
+
"step": 349
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 1.72,
|
2107 |
+
"learning_rate": 1.0118517455823374e-05,
|
2108 |
+
"loss": 0.6726,
|
2109 |
+
"step": 350
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 1.73,
|
2113 |
+
"learning_rate": 1.0053211484238303e-05,
|
2114 |
+
"loss": 0.6715,
|
2115 |
+
"step": 351
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 1.73,
|
2119 |
+
"learning_rate": 9.987974885757647e-06,
|
2120 |
+
"loss": 0.6376,
|
2121 |
+
"step": 352
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 1.74,
|
2125 |
+
"learning_rate": 9.922809510016277e-06,
|
2126 |
+
"loss": 0.6052,
|
2127 |
+
"step": 353
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 1.74,
|
2131 |
+
"learning_rate": 9.857717204629696e-06,
|
2132 |
+
"loss": 0.6083,
|
2133 |
+
"step": 354
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 1.75,
|
2137 |
+
"learning_rate": 9.792699815141685e-06,
|
2138 |
+
"loss": 0.6343,
|
2139 |
+
"step": 355
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 1.75,
|
2143 |
+
"learning_rate": 9.727759184971936e-06,
|
2144 |
+
"loss": 0.631,
|
2145 |
+
"step": 356
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 1.76,
|
2149 |
+
"learning_rate": 9.662897155363814e-06,
|
2150 |
+
"loss": 0.6598,
|
2151 |
+
"step": 357
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 1.76,
|
2155 |
+
"learning_rate": 9.598115565332142e-06,
|
2156 |
+
"loss": 0.6396,
|
2157 |
+
"step": 358
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 1.77,
|
2161 |
+
"learning_rate": 9.533416251611064e-06,
|
2162 |
+
"loss": 0.6778,
|
2163 |
+
"step": 359
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 1.77,
|
2167 |
+
"learning_rate": 9.468801048601972e-06,
|
2168 |
+
"loss": 0.6252,
|
2169 |
+
"step": 360
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 1.78,
|
2173 |
+
"learning_rate": 9.404271788321482e-06,
|
2174 |
+
"loss": 0.6119,
|
2175 |
+
"step": 361
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 1.78,
|
2179 |
+
"learning_rate": 9.339830300349498e-06,
|
2180 |
+
"loss": 0.6523,
|
2181 |
+
"step": 362
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 1.79,
|
2185 |
+
"learning_rate": 9.275478411777354e-06,
|
2186 |
+
"loss": 0.6336,
|
2187 |
+
"step": 363
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 1.79,
|
2191 |
+
"learning_rate": 9.211217947155986e-06,
|
2192 |
+
"loss": 0.592,
|
2193 |
+
"step": 364
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 1.8,
|
2197 |
+
"learning_rate": 9.147050728444215e-06,
|
2198 |
+
"loss": 0.6204,
|
2199 |
+
"step": 365
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 1.8,
|
2203 |
+
"learning_rate": 9.08297857495709e-06,
|
2204 |
+
"loss": 0.6273,
|
2205 |
+
"step": 366
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 1.81,
|
2209 |
+
"learning_rate": 9.0190033033143e-06,
|
2210 |
+
"loss": 0.5883,
|
2211 |
+
"step": 367
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 1.81,
|
2215 |
+
"learning_rate": 8.955126727388672e-06,
|
2216 |
+
"loss": 0.6282,
|
2217 |
+
"step": 368
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 1.82,
|
2221 |
+
"learning_rate": 8.89135065825474e-06,
|
2222 |
+
"loss": 0.6745,
|
2223 |
+
"step": 369
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 1.82,
|
2227 |
+
"learning_rate": 8.827676904137397e-06,
|
2228 |
+
"loss": 0.6146,
|
2229 |
+
"step": 370
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 1.83,
|
2233 |
+
"learning_rate": 8.76410727036062e-06,
|
2234 |
+
"loss": 0.5944,
|
2235 |
+
"step": 371
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 1.83,
|
2239 |
+
"learning_rate": 8.700643559296313e-06,
|
2240 |
+
"loss": 0.6359,
|
2241 |
+
"step": 372
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 1.84,
|
2245 |
+
"learning_rate": 8.637287570313159e-06,
|
2246 |
+
"loss": 0.5846,
|
2247 |
+
"step": 373
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 1.84,
|
2251 |
+
"learning_rate": 8.574041099725644e-06,
|
2252 |
+
"loss": 0.6315,
|
2253 |
+
"step": 374
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 1.85,
|
2257 |
+
"learning_rate": 8.510905940743093e-06,
|
2258 |
+
"loss": 0.5993,
|
2259 |
+
"step": 375
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 1.85,
|
2263 |
+
"learning_rate": 8.447883883418866e-06,
|
2264 |
+
"loss": 0.652,
|
2265 |
+
"step": 376
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 1.85,
|
2269 |
+
"learning_rate": 8.38497671459957e-06,
|
2270 |
+
"loss": 0.6542,
|
2271 |
+
"step": 377
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 1.86,
|
2275 |
+
"learning_rate": 8.32218621787441e-06,
|
2276 |
+
"loss": 0.6168,
|
2277 |
+
"step": 378
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 1.86,
|
2281 |
+
"learning_rate": 8.25951417352462e-06,
|
2282 |
+
"loss": 0.632,
|
2283 |
+
"step": 379
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 1.87,
|
2287 |
+
"learning_rate": 8.196962358473e-06,
|
2288 |
+
"loss": 0.6016,
|
2289 |
+
"step": 380
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 1.87,
|
2293 |
+
"learning_rate": 8.134532546233505e-06,
|
2294 |
+
"loss": 0.5967,
|
2295 |
+
"step": 381
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 1.88,
|
2299 |
+
"learning_rate": 8.072226506860988e-06,
|
2300 |
+
"loss": 0.6398,
|
2301 |
+
"step": 382
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 1.88,
|
2305 |
+
"learning_rate": 8.010046006901001e-06,
|
2306 |
+
"loss": 0.6485,
|
2307 |
+
"step": 383
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 1.89,
|
2311 |
+
"learning_rate": 7.947992809339723e-06,
|
2312 |
+
"loss": 0.588,
|
2313 |
+
"step": 384
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 1.89,
|
2317 |
+
"learning_rate": 7.88606867355395e-06,
|
2318 |
+
"loss": 0.6784,
|
2319 |
+
"step": 385
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 1.9,
|
2323 |
+
"learning_rate": 7.824275355261233e-06,
|
2324 |
+
"loss": 0.6223,
|
2325 |
+
"step": 386
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 1.9,
|
2329 |
+
"learning_rate": 7.762614606470084e-06,
|
2330 |
+
"loss": 0.5966,
|
2331 |
+
"step": 387
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 1.91,
|
2335 |
+
"learning_rate": 7.701088175430327e-06,
|
2336 |
+
"loss": 0.6124,
|
2337 |
+
"step": 388
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 1.91,
|
2341 |
+
"learning_rate": 7.639697806583493e-06,
|
2342 |
+
"loss": 0.637,
|
2343 |
+
"step": 389
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 1.92,
|
2347 |
+
"learning_rate": 7.578445240513393e-06,
|
2348 |
+
"loss": 0.6198,
|
2349 |
+
"step": 390
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 1.92,
|
2353 |
+
"learning_rate": 7.517332213896743e-06,
|
2354 |
+
"loss": 0.6397,
|
2355 |
+
"step": 391
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 1.93,
|
2359 |
+
"learning_rate": 7.456360459453952e-06,
|
2360 |
+
"loss": 0.6308,
|
2361 |
+
"step": 392
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 1.93,
|
2365 |
+
"learning_rate": 7.395531705899969e-06,
|
2366 |
+
"loss": 0.5814,
|
2367 |
+
"step": 393
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 1.94,
|
2371 |
+
"learning_rate": 7.334847677895276e-06,
|
2372 |
+
"loss": 0.5953,
|
2373 |
+
"step": 394
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 1.94,
|
2377 |
+
"learning_rate": 7.274310095997e-06,
|
2378 |
+
"loss": 0.6071,
|
2379 |
+
"step": 395
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 1.95,
|
2383 |
+
"learning_rate": 7.213920676610112e-06,
|
2384 |
+
"loss": 0.6304,
|
2385 |
+
"step": 396
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 1.95,
|
2389 |
+
"learning_rate": 7.153681131938791e-06,
|
2390 |
+
"loss": 0.6411,
|
2391 |
+
"step": 397
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 1.96,
|
2395 |
+
"learning_rate": 7.093593169937849e-06,
|
2396 |
+
"loss": 0.6012,
|
2397 |
+
"step": 398
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 1.96,
|
2401 |
+
"learning_rate": 7.033658494264309e-06,
|
2402 |
+
"loss": 0.6503,
|
2403 |
+
"step": 399
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 1.97,
|
2407 |
+
"learning_rate": 6.973878804229131e-06,
|
2408 |
+
"loss": 0.6363,
|
2409 |
+
"step": 400
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 1.97,
|
2413 |
+
"learning_rate": 6.914255794748989e-06,
|
2414 |
+
"loss": 0.6212,
|
2415 |
+
"step": 401
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 1.98,
|
2419 |
+
"learning_rate": 6.8547911562982595e-06,
|
2420 |
+
"loss": 0.6694,
|
2421 |
+
"step": 402
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 1.98,
|
2425 |
+
"learning_rate": 6.7954865748610515e-06,
|
2426 |
+
"loss": 0.6147,
|
2427 |
+
"step": 403
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 1.99,
|
2431 |
+
"learning_rate": 6.736343731883425e-06,
|
2432 |
+
"loss": 0.6615,
|
2433 |
+
"step": 404
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 1.99,
|
2437 |
+
"learning_rate": 6.677364304225731e-06,
|
2438 |
+
"loss": 0.602,
|
2439 |
+
"step": 405
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 2.0,
|
2443 |
+
"learning_rate": 6.618549964115033e-06,
|
2444 |
+
"loss": 0.604,
|
2445 |
+
"step": 406
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 2.0,
|
2449 |
+
"learning_rate": 6.559902379097721e-06,
|
2450 |
+
"loss": 0.4458,
|
2451 |
+
"step": 407
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 2.01,
|
2455 |
+
"learning_rate": 6.501423211992224e-06,
|
2456 |
+
"loss": 0.3383,
|
2457 |
+
"step": 408
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 2.01,
|
2461 |
+
"learning_rate": 6.443114120841874e-06,
|
2462 |
+
"loss": 0.3288,
|
2463 |
+
"step": 409
|
2464 |
+
},
|
2465 |
+
{
|
2466 |
+
"epoch": 2.02,
|
2467 |
+
"learning_rate": 6.384976758867875e-06,
|
2468 |
+
"loss": 0.3252,
|
2469 |
+
"step": 410
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 2.02,
|
2473 |
+
"learning_rate": 6.32701277442245e-06,
|
2474 |
+
"loss": 0.3226,
|
2475 |
+
"step": 411
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 2.03,
|
2479 |
+
"learning_rate": 6.269223810942086e-06,
|
2480 |
+
"loss": 0.3122,
|
2481 |
+
"step": 412
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 2.03,
|
2485 |
+
"learning_rate": 6.211611506900973e-06,
|
2486 |
+
"loss": 0.2519,
|
2487 |
+
"step": 413
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 2.04,
|
2491 |
+
"learning_rate": 6.1541774957645045e-06,
|
2492 |
+
"loss": 0.3158,
|
2493 |
+
"step": 414
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 2.04,
|
2497 |
+
"learning_rate": 6.096923405942989e-06,
|
2498 |
+
"loss": 0.2846,
|
2499 |
+
"step": 415
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 2.05,
|
2503 |
+
"learning_rate": 6.03985086074549e-06,
|
2504 |
+
"loss": 0.2747,
|
2505 |
+
"step": 416
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 2.05,
|
2509 |
+
"learning_rate": 5.982961478333768e-06,
|
2510 |
+
"loss": 0.2876,
|
2511 |
+
"step": 417
|
2512 |
+
},
|
2513 |
+
{
|
2514 |
+
"epoch": 2.06,
|
2515 |
+
"learning_rate": 5.926256871676443e-06,
|
2516 |
+
"loss": 0.2596,
|
2517 |
+
"step": 418
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 2.06,
|
2521 |
+
"learning_rate": 5.86973864850322e-06,
|
2522 |
+
"loss": 0.28,
|
2523 |
+
"step": 419
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 2.07,
|
2527 |
+
"learning_rate": 5.813408411259331e-06,
|
2528 |
+
"loss": 0.2694,
|
2529 |
+
"step": 420
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 2.07,
|
2533 |
+
"learning_rate": 5.757267757060109e-06,
|
2534 |
+
"loss": 0.2707,
|
2535 |
+
"step": 421
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 2.08,
|
2539 |
+
"learning_rate": 5.701318277645675e-06,
|
2540 |
+
"loss": 0.2814,
|
2541 |
+
"step": 422
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 2.08,
|
2545 |
+
"learning_rate": 5.645561559335832e-06,
|
2546 |
+
"loss": 0.2916,
|
2547 |
+
"step": 423
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 2.09,
|
2551 |
+
"learning_rate": 5.589999182985087e-06,
|
2552 |
+
"loss": 0.3062,
|
2553 |
+
"step": 424
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 2.09,
|
2557 |
+
"learning_rate": 5.534632723937809e-06,
|
2558 |
+
"loss": 0.2818,
|
2559 |
+
"step": 425
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 2.1,
|
2563 |
+
"learning_rate": 5.479463751983603e-06,
|
2564 |
+
"loss": 0.263,
|
2565 |
+
"step": 426
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 2.1,
|
2569 |
+
"learning_rate": 5.424493831312757e-06,
|
2570 |
+
"loss": 0.2992,
|
2571 |
+
"step": 427
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 2.11,
|
2575 |
+
"learning_rate": 5.369724520471925e-06,
|
2576 |
+
"loss": 0.2966,
|
2577 |
+
"step": 428
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 2.11,
|
2581 |
+
"learning_rate": 5.315157372319915e-06,
|
2582 |
+
"loss": 0.2803,
|
2583 |
+
"step": 429
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 2.12,
|
2587 |
+
"learning_rate": 5.2607939339836945e-06,
|
2588 |
+
"loss": 0.2749,
|
2589 |
+
"step": 430
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 2.12,
|
2593 |
+
"learning_rate": 5.2066357468144824e-06,
|
2594 |
+
"loss": 0.2728,
|
2595 |
+
"step": 431
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 2.13,
|
2599 |
+
"learning_rate": 5.152684346344087e-06,
|
2600 |
+
"loss": 0.2545,
|
2601 |
+
"step": 432
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 2.13,
|
2605 |
+
"learning_rate": 5.0989412622413345e-06,
|
2606 |
+
"loss": 0.2722,
|
2607 |
+
"step": 433
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 2.14,
|
2611 |
+
"learning_rate": 5.0454080182687314e-06,
|
2612 |
+
"loss": 0.3021,
|
2613 |
+
"step": 434
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 2.14,
|
2617 |
+
"learning_rate": 4.992086132239238e-06,
|
2618 |
+
"loss": 0.2483,
|
2619 |
+
"step": 435
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 2.15,
|
2623 |
+
"learning_rate": 4.938977115973242e-06,
|
2624 |
+
"loss": 0.2703,
|
2625 |
+
"step": 436
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 2.15,
|
2629 |
+
"learning_rate": 4.886082475255694e-06,
|
2630 |
+
"loss": 0.2829,
|
2631 |
+
"step": 437
|
2632 |
+
},
|
2633 |
+
{
|
2634 |
+
"epoch": 2.15,
|
2635 |
+
"learning_rate": 4.833403709793424e-06,
|
2636 |
+
"loss": 0.2634,
|
2637 |
+
"step": 438
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 2.16,
|
2641 |
+
"learning_rate": 4.780942313172602e-06,
|
2642 |
+
"loss": 0.2684,
|
2643 |
+
"step": 439
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 2.16,
|
2647 |
+
"learning_rate": 4.728699772816407e-06,
|
2648 |
+
"loss": 0.3123,
|
2649 |
+
"step": 440
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 2.17,
|
2653 |
+
"learning_rate": 4.6766775699428365e-06,
|
2654 |
+
"loss": 0.2837,
|
2655 |
+
"step": 441
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 2.17,
|
2659 |
+
"learning_rate": 4.624877179522742e-06,
|
2660 |
+
"loss": 0.2915,
|
2661 |
+
"step": 442
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 2.18,
|
2665 |
+
"learning_rate": 4.573300070237973e-06,
|
2666 |
+
"loss": 0.305,
|
2667 |
+
"step": 443
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 2.18,
|
2671 |
+
"learning_rate": 4.5219477044397525e-06,
|
2672 |
+
"loss": 0.2537,
|
2673 |
+
"step": 444
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 2.19,
|
2677 |
+
"learning_rate": 4.470821538107219e-06,
|
2678 |
+
"loss": 0.2782,
|
2679 |
+
"step": 445
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 2.19,
|
2683 |
+
"learning_rate": 4.419923020806148e-06,
|
2684 |
+
"loss": 0.3202,
|
2685 |
+
"step": 446
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 2.2,
|
2689 |
+
"learning_rate": 4.36925359564783e-06,
|
2690 |
+
"loss": 0.2547,
|
2691 |
+
"step": 447
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 2.2,
|
2695 |
+
"learning_rate": 4.318814699248188e-06,
|
2696 |
+
"loss": 0.2707,
|
2697 |
+
"step": 448
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 2.21,
|
2701 |
+
"learning_rate": 4.268607761687019e-06,
|
2702 |
+
"loss": 0.246,
|
2703 |
+
"step": 449
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 2.21,
|
2707 |
+
"learning_rate": 4.218634206467449e-06,
|
2708 |
+
"loss": 0.2737,
|
2709 |
+
"step": 450
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 2.22,
|
2713 |
+
"learning_rate": 4.1688954504756e-06,
|
2714 |
+
"loss": 0.2921,
|
2715 |
+
"step": 451
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 2.22,
|
2719 |
+
"learning_rate": 4.119392903940384e-06,
|
2720 |
+
"loss": 0.2677,
|
2721 |
+
"step": 452
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 2.23,
|
2725 |
+
"learning_rate": 4.07012797039353e-06,
|
2726 |
+
"loss": 0.2979,
|
2727 |
+
"step": 453
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 2.23,
|
2731 |
+
"learning_rate": 4.021102046629799e-06,
|
2732 |
+
"loss": 0.2459,
|
2733 |
+
"step": 454
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 2.24,
|
2737 |
+
"learning_rate": 3.972316522667381e-06,
|
2738 |
+
"loss": 0.2745,
|
2739 |
+
"step": 455
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 2.24,
|
2743 |
+
"learning_rate": 3.923772781708468e-06,
|
2744 |
+
"loss": 0.2943,
|
2745 |
+
"step": 456
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 2.25,
|
2749 |
+
"learning_rate": 3.875472200100051e-06,
|
2750 |
+
"loss": 0.2403,
|
2751 |
+
"step": 457
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 2.25,
|
2755 |
+
"learning_rate": 3.827416147294888e-06,
|
2756 |
+
"loss": 0.2781,
|
2757 |
+
"step": 458
|
2758 |
+
},
|
2759 |
+
{
|
2760 |
+
"epoch": 2.26,
|
2761 |
+
"learning_rate": 3.7796059858126927e-06,
|
2762 |
+
"loss": 0.2766,
|
2763 |
+
"step": 459
|
2764 |
+
},
|
2765 |
+
{
|
2766 |
+
"epoch": 2.26,
|
2767 |
+
"learning_rate": 3.7320430712014796e-06,
|
2768 |
+
"loss": 0.2738,
|
2769 |
+
"step": 460
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 2.27,
|
2773 |
+
"learning_rate": 3.6847287519991434e-06,
|
2774 |
+
"loss": 0.3136,
|
2775 |
+
"step": 461
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 2.27,
|
2779 |
+
"learning_rate": 3.637664369695233e-06,
|
2780 |
+
"loss": 0.2902,
|
2781 |
+
"step": 462
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 2.28,
|
2785 |
+
"learning_rate": 3.590851258692894e-06,
|
2786 |
+
"loss": 0.2516,
|
2787 |
+
"step": 463
|
2788 |
+
},
|
2789 |
+
{
|
2790 |
+
"epoch": 2.28,
|
2791 |
+
"learning_rate": 3.5442907462710605e-06,
|
2792 |
+
"loss": 0.2668,
|
2793 |
+
"step": 464
|
2794 |
+
},
|
2795 |
+
{
|
2796 |
+
"epoch": 2.29,
|
2797 |
+
"learning_rate": 3.4979841525468016e-06,
|
2798 |
+
"loss": 0.2789,
|
2799 |
+
"step": 465
|
2800 |
+
},
|
2801 |
+
{
|
2802 |
+
"epoch": 2.29,
|
2803 |
+
"learning_rate": 3.451932790437898e-06,
|
2804 |
+
"loss": 0.2794,
|
2805 |
+
"step": 466
|
2806 |
+
},
|
2807 |
+
{
|
2808 |
+
"epoch": 2.3,
|
2809 |
+
"learning_rate": 3.4061379656256345e-06,
|
2810 |
+
"loss": 0.273,
|
2811 |
+
"step": 467
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 2.3,
|
2815 |
+
"learning_rate": 3.3606009765177555e-06,
|
2816 |
+
"loss": 0.2828,
|
2817 |
+
"step": 468
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 2.31,
|
2821 |
+
"learning_rate": 3.3153231142116617e-06,
|
2822 |
+
"loss": 0.2836,
|
2823 |
+
"step": 469
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 2.31,
|
2827 |
+
"learning_rate": 3.270305662457805e-06,
|
2828 |
+
"loss": 0.2781,
|
2829 |
+
"step": 470
|
2830 |
+
},
|
2831 |
+
{
|
2832 |
+
"epoch": 2.32,
|
2833 |
+
"learning_rate": 3.225549897623302e-06,
|
2834 |
+
"loss": 0.2911,
|
2835 |
+
"step": 471
|
2836 |
+
},
|
2837 |
+
{
|
2838 |
+
"epoch": 2.32,
|
2839 |
+
"learning_rate": 3.181057088655719e-06,
|
2840 |
+
"loss": 0.3071,
|
2841 |
+
"step": 472
|
2842 |
+
},
|
2843 |
+
{
|
2844 |
+
"epoch": 2.33,
|
2845 |
+
"learning_rate": 3.136828497047116e-06,
|
2846 |
+
"loss": 0.2583,
|
2847 |
+
"step": 473
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 2.33,
|
2851 |
+
"learning_rate": 3.0928653767982695e-06,
|
2852 |
+
"loss": 0.2976,
|
2853 |
+
"step": 474
|
2854 |
+
},
|
2855 |
+
{
|
2856 |
+
"epoch": 2.34,
|
2857 |
+
"learning_rate": 3.0491689743831277e-06,
|
2858 |
+
"loss": 0.2727,
|
2859 |
+
"step": 475
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 2.34,
|
2863 |
+
"learning_rate": 3.005740528713458e-06,
|
2864 |
+
"loss": 0.2843,
|
2865 |
+
"step": 476
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 2.35,
|
2869 |
+
"learning_rate": 2.9625812711037206e-06,
|
2870 |
+
"loss": 0.2655,
|
2871 |
+
"step": 477
|
2872 |
+
},
|
2873 |
+
{
|
2874 |
+
"epoch": 2.35,
|
2875 |
+
"learning_rate": 2.91969242523618e-06,
|
2876 |
+
"loss": 0.2759,
|
2877 |
+
"step": 478
|
2878 |
+
},
|
2879 |
+
{
|
2880 |
+
"epoch": 2.36,
|
2881 |
+
"learning_rate": 2.87707520712617e-06,
|
2882 |
+
"loss": 0.272,
|
2883 |
+
"step": 479
|
2884 |
+
},
|
2885 |
+
{
|
2886 |
+
"epoch": 2.36,
|
2887 |
+
"learning_rate": 2.834730825087663e-06,
|
2888 |
+
"loss": 0.2734,
|
2889 |
+
"step": 480
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 2.37,
|
2893 |
+
"learning_rate": 2.7926604796989676e-06,
|
2894 |
+
"loss": 0.312,
|
2895 |
+
"step": 481
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 2.37,
|
2899 |
+
"learning_rate": 2.7508653637687176e-06,
|
2900 |
+
"loss": 0.2608,
|
2901 |
+
"step": 482
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 2.38,
|
2905 |
+
"learning_rate": 2.709346662302041e-06,
|
2906 |
+
"loss": 0.3084,
|
2907 |
+
"step": 483
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 2.38,
|
2911 |
+
"learning_rate": 2.6681055524669694e-06,
|
2912 |
+
"loss": 0.3209,
|
2913 |
+
"step": 484
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 2.39,
|
2917 |
+
"learning_rate": 2.6271432035610513e-06,
|
2918 |
+
"loss": 0.2781,
|
2919 |
+
"step": 485
|
2920 |
+
},
|
2921 |
+
{
|
2922 |
+
"epoch": 2.39,
|
2923 |
+
"learning_rate": 2.5864607769782084e-06,
|
2924 |
+
"loss": 0.2379,
|
2925 |
+
"step": 486
|
2926 |
+
},
|
2927 |
+
{
|
2928 |
+
"epoch": 2.4,
|
2929 |
+
"learning_rate": 2.5460594261757996e-06,
|
2930 |
+
"loss": 0.2945,
|
2931 |
+
"step": 487
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 2.4,
|
2935 |
+
"learning_rate": 2.5059402966419303e-06,
|
2936 |
+
"loss": 0.2545,
|
2937 |
+
"step": 488
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 2.41,
|
2941 |
+
"learning_rate": 2.466104525862957e-06,
|
2942 |
+
"loss": 0.285,
|
2943 |
+
"step": 489
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 2.41,
|
2947 |
+
"learning_rate": 2.426553243291249e-06,
|
2948 |
+
"loss": 0.2818,
|
2949 |
+
"step": 490
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 2.42,
|
2953 |
+
"learning_rate": 2.3872875703131583e-06,
|
2954 |
+
"loss": 0.2743,
|
2955 |
+
"step": 491
|
2956 |
+
},
|
2957 |
+
{
|
2958 |
+
"epoch": 2.42,
|
2959 |
+
"learning_rate": 2.3483086202172377e-06,
|
2960 |
+
"loss": 0.2991,
|
2961 |
+
"step": 492
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 2.43,
|
2965 |
+
"learning_rate": 2.309617498162657e-06,
|
2966 |
+
"loss": 0.2778,
|
2967 |
+
"step": 493
|
2968 |
+
},
|
2969 |
+
{
|
2970 |
+
"epoch": 2.43,
|
2971 |
+
"learning_rate": 2.271215301147887e-06,
|
2972 |
+
"loss": 0.2723,
|
2973 |
+
"step": 494
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 2.44,
|
2977 |
+
"learning_rate": 2.2331031179795792e-06,
|
2978 |
+
"loss": 0.2684,
|
2979 |
+
"step": 495
|
2980 |
+
},
|
2981 |
+
{
|
2982 |
+
"epoch": 2.44,
|
2983 |
+
"learning_rate": 2.1952820292417143e-06,
|
2984 |
+
"loss": 0.2818,
|
2985 |
+
"step": 496
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 2.45,
|
2989 |
+
"learning_rate": 2.1577531072649495e-06,
|
2990 |
+
"loss": 0.2658,
|
2991 |
+
"step": 497
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 2.45,
|
2995 |
+
"learning_rate": 2.120517416096217e-06,
|
2996 |
+
"loss": 0.2865,
|
2997 |
+
"step": 498
|
2998 |
+
},
|
2999 |
+
{
|
3000 |
+
"epoch": 2.46,
|
3001 |
+
"learning_rate": 2.083576011468562e-06,
|
3002 |
+
"loss": 0.2744,
|
3003 |
+
"step": 499
|
3004 |
+
},
|
3005 |
+
{
|
3006 |
+
"epoch": 2.46,
|
3007 |
+
"learning_rate": 2.0469299407712112e-06,
|
3008 |
+
"loss": 0.2939,
|
3009 |
+
"step": 500
|
3010 |
+
},
|
3011 |
+
{
|
3012 |
+
"epoch": 2.46,
|
3013 |
+
"learning_rate": 2.010580243019865e-06,
|
3014 |
+
"loss": 0.3174,
|
3015 |
+
"step": 501
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 2.47,
|
3019 |
+
"learning_rate": 1.9745279488272484e-06,
|
3020 |
+
"loss": 0.2805,
|
3021 |
+
"step": 502
|
3022 |
+
},
|
3023 |
+
{
|
3024 |
+
"epoch": 2.47,
|
3025 |
+
"learning_rate": 1.938774080373884e-06,
|
3026 |
+
"loss": 0.2587,
|
3027 |
+
"step": 503
|
3028 |
+
},
|
3029 |
+
{
|
3030 |
+
"epoch": 2.48,
|
3031 |
+
"learning_rate": 1.9033196513791138e-06,
|
3032 |
+
"loss": 0.2591,
|
3033 |
+
"step": 504
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 2.48,
|
3037 |
+
"learning_rate": 1.8681656670723663e-06,
|
3038 |
+
"loss": 0.28,
|
3039 |
+
"step": 505
|
3040 |
+
},
|
3041 |
+
{
|
3042 |
+
"epoch": 2.49,
|
3043 |
+
"learning_rate": 1.833313124164636e-06,
|
3044 |
+
"loss": 0.2757,
|
3045 |
+
"step": 506
|
3046 |
+
},
|
3047 |
+
{
|
3048 |
+
"epoch": 2.49,
|
3049 |
+
"learning_rate": 1.7987630108202355e-06,
|
3050 |
+
"loss": 0.2684,
|
3051 |
+
"step": 507
|
3052 |
+
},
|
3053 |
+
{
|
3054 |
+
"epoch": 2.5,
|
3055 |
+
"learning_rate": 1.764516306628787e-06,
|
3056 |
+
"loss": 0.3003,
|
3057 |
+
"step": 508
|
3058 |
+
},
|
3059 |
+
{
|
3060 |
+
"epoch": 2.5,
|
3061 |
+
"learning_rate": 1.7305739825774228e-06,
|
3062 |
+
"loss": 0.2826,
|
3063 |
+
"step": 509
|
3064 |
+
},
|
3065 |
+
{
|
3066 |
+
"epoch": 2.51,
|
3067 |
+
"learning_rate": 1.6969370010232882e-06,
|
3068 |
+
"loss": 0.2531,
|
3069 |
+
"step": 510
|
3070 |
+
},
|
3071 |
+
{
|
3072 |
+
"epoch": 2.51,
|
3073 |
+
"learning_rate": 1.663606315666226e-06,
|
3074 |
+
"loss": 0.277,
|
3075 |
+
"step": 511
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 2.52,
|
3079 |
+
"learning_rate": 1.6305828715217506e-06,
|
3080 |
+
"loss": 0.2838,
|
3081 |
+
"step": 512
|
3082 |
+
},
|
3083 |
+
{
|
3084 |
+
"epoch": 2.52,
|
3085 |
+
"learning_rate": 1.597867604894264e-06,
|
3086 |
+
"loss": 0.3017,
|
3087 |
+
"step": 513
|
3088 |
+
},
|
3089 |
+
{
|
3090 |
+
"epoch": 2.53,
|
3091 |
+
"learning_rate": 1.5654614433504841e-06,
|
3092 |
+
"loss": 0.2695,
|
3093 |
+
"step": 514
|
3094 |
+
},
|
3095 |
+
{
|
3096 |
+
"epoch": 2.53,
|
3097 |
+
"learning_rate": 1.5333653056931684e-06,
|
3098 |
+
"loss": 0.3005,
|
3099 |
+
"step": 515
|
3100 |
+
},
|
3101 |
+
{
|
3102 |
+
"epoch": 2.54,
|
3103 |
+
"learning_rate": 1.5015801019350476e-06,
|
3104 |
+
"loss": 0.259,
|
3105 |
+
"step": 516
|
3106 |
+
},
|
3107 |
+
{
|
3108 |
+
"epoch": 2.54,
|
3109 |
+
"learning_rate": 1.4701067332730426e-06,
|
3110 |
+
"loss": 0.276,
|
3111 |
+
"step": 517
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 2.55,
|
3115 |
+
"learning_rate": 1.4389460920626887e-06,
|
3116 |
+
"loss": 0.2706,
|
3117 |
+
"step": 518
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 2.55,
|
3121 |
+
"learning_rate": 1.4080990617928571e-06,
|
3122 |
+
"loss": 0.2808,
|
3123 |
+
"step": 519
|
3124 |
+
},
|
3125 |
+
{
|
3126 |
+
"epoch": 2.56,
|
3127 |
+
"learning_rate": 1.3775665170606896e-06,
|
3128 |
+
"loss": 0.2925,
|
3129 |
+
"step": 520
|
3130 |
+
},
|
3131 |
+
{
|
3132 |
+
"epoch": 2.56,
|
3133 |
+
"learning_rate": 1.3473493235468177e-06,
|
3134 |
+
"loss": 0.2644,
|
3135 |
+
"step": 521
|
3136 |
+
},
|
3137 |
+
{
|
3138 |
+
"epoch": 2.57,
|
3139 |
+
"learning_rate": 1.3174483379907996e-06,
|
3140 |
+
"loss": 0.2484,
|
3141 |
+
"step": 522
|
3142 |
+
},
|
3143 |
+
{
|
3144 |
+
"epoch": 2.57,
|
3145 |
+
"learning_rate": 1.2878644081668403e-06,
|
3146 |
+
"loss": 0.3012,
|
3147 |
+
"step": 523
|
3148 |
+
},
|
3149 |
+
{
|
3150 |
+
"epoch": 2.58,
|
3151 |
+
"learning_rate": 1.2585983728597608e-06,
|
3152 |
+
"loss": 0.3033,
|
3153 |
+
"step": 524
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 2.58,
|
3157 |
+
"learning_rate": 1.2296510618411957e-06,
|
3158 |
+
"loss": 0.33,
|
3159 |
+
"step": 525
|
3160 |
+
},
|
3161 |
+
{
|
3162 |
+
"epoch": 2.59,
|
3163 |
+
"learning_rate": 1.201023295846093e-06,
|
3164 |
+
"loss": 0.2513,
|
3165 |
+
"step": 526
|
3166 |
+
},
|
3167 |
+
{
|
3168 |
+
"epoch": 2.59,
|
3169 |
+
"learning_rate": 1.1727158865494206e-06,
|
3170 |
+
"loss": 0.2871,
|
3171 |
+
"step": 527
|
3172 |
+
},
|
3173 |
+
{
|
3174 |
+
"epoch": 2.6,
|
3175 |
+
"learning_rate": 1.1447296365431668e-06,
|
3176 |
+
"loss": 0.2592,
|
3177 |
+
"step": 528
|
3178 |
+
},
|
3179 |
+
{
|
3180 |
+
"epoch": 2.6,
|
3181 |
+
"learning_rate": 1.1170653393135847e-06,
|
3182 |
+
"loss": 0.2672,
|
3183 |
+
"step": 529
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 2.61,
|
3187 |
+
"learning_rate": 1.0897237792186862e-06,
|
3188 |
+
"loss": 0.2589,
|
3189 |
+
"step": 530
|
3190 |
+
},
|
3191 |
+
{
|
3192 |
+
"epoch": 2.61,
|
3193 |
+
"learning_rate": 1.0627057314660114e-06,
|
3194 |
+
"loss": 0.2851,
|
3195 |
+
"step": 531
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 2.62,
|
3199 |
+
"learning_rate": 1.0360119620906426e-06,
|
3200 |
+
"loss": 0.2319,
|
3201 |
+
"step": 532
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 2.62,
|
3205 |
+
"learning_rate": 1.0096432279334905e-06,
|
3206 |
+
"loss": 0.2757,
|
3207 |
+
"step": 533
|
3208 |
+
},
|
3209 |
+
{
|
3210 |
+
"epoch": 2.63,
|
3211 |
+
"learning_rate": 9.836002766198379e-07,
|
3212 |
+
"loss": 0.2742,
|
3213 |
+
"step": 534
|
3214 |
+
},
|
3215 |
+
{
|
3216 |
+
"epoch": 2.63,
|
3217 |
+
"learning_rate": 9.57883846538135e-07,
|
3218 |
+
"loss": 0.324,
|
3219 |
+
"step": 535
|
3220 |
+
},
|
3221 |
+
{
|
3222 |
+
"epoch": 2.64,
|
3223 |
+
"learning_rate": 9.324946668190657e-07,
|
3224 |
+
"loss": 0.2435,
|
3225 |
+
"step": 536
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 2.64,
|
3229 |
+
"learning_rate": 9.074334573148783e-07,
|
3230 |
+
"loss": 0.2795,
|
3231 |
+
"step": 537
|
3232 |
+
},
|
3233 |
+
{
|
3234 |
+
"epoch": 2.65,
|
3235 |
+
"learning_rate": 8.827009285789778e-07,
|
3236 |
+
"loss": 0.3012,
|
3237 |
+
"step": 538
|
3238 |
+
},
|
3239 |
+
{
|
3240 |
+
"epoch": 2.65,
|
3241 |
+
"learning_rate": 8.582977818457696e-07,
|
3242 |
+
"loss": 0.2663,
|
3243 |
+
"step": 539
|
3244 |
+
},
|
3245 |
+
{
|
3246 |
+
"epoch": 2.66,
|
3247 |
+
"learning_rate": 8.342247090107919e-07,
|
3248 |
+
"loss": 0.2469,
|
3249 |
+
"step": 540
|
3250 |
+
},
|
3251 |
+
{
|
3252 |
+
"epoch": 2.66,
|
3253 |
+
"learning_rate": 8.104823926110811e-07,
|
3254 |
+
"loss": 0.2835,
|
3255 |
+
"step": 541
|
3256 |
+
},
|
3257 |
+
{
|
3258 |
+
"epoch": 2.67,
|
3259 |
+
"learning_rate": 7.870715058058406e-07,
|
3260 |
+
"loss": 0.2554,
|
3261 |
+
"step": 542
|
3262 |
+
},
|
3263 |
+
{
|
3264 |
+
"epoch": 2.67,
|
3265 |
+
"learning_rate": 7.639927123573351e-07,
|
3266 |
+
"loss": 0.2571,
|
3267 |
+
"step": 543
|
3268 |
+
},
|
3269 |
+
{
|
3270 |
+
"epoch": 2.68,
|
3271 |
+
"learning_rate": 7.412466666120846e-07,
|
3272 |
+
"loss": 0.2679,
|
3273 |
+
"step": 544
|
3274 |
+
},
|
3275 |
+
{
|
3276 |
+
"epoch": 2.68,
|
3277 |
+
"learning_rate": 7.188340134823043e-07,
|
3278 |
+
"loss": 0.2569,
|
3279 |
+
"step": 545
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 2.69,
|
3283 |
+
"learning_rate": 6.967553884276279e-07,
|
3284 |
+
"loss": 0.2704,
|
3285 |
+
"step": 546
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 2.69,
|
3289 |
+
"learning_rate": 6.750114174370797e-07,
|
3290 |
+
"loss": 0.3005,
|
3291 |
+
"step": 547
|
3292 |
+
},
|
3293 |
+
{
|
3294 |
+
"epoch": 2.7,
|
3295 |
+
"learning_rate": 6.536027170113354e-07,
|
3296 |
+
"loss": 0.2542,
|
3297 |
+
"step": 548
|
3298 |
+
},
|
3299 |
+
{
|
3300 |
+
"epoch": 2.7,
|
3301 |
+
"learning_rate": 6.32529894145234e-07,
|
3302 |
+
"loss": 0.2783,
|
3303 |
+
"step": 549
|
3304 |
+
},
|
3305 |
+
{
|
3306 |
+
"epoch": 2.71,
|
3307 |
+
"learning_rate": 6.117935463105809e-07,
|
3308 |
+
"loss": 0.2264,
|
3309 |
+
"step": 550
|
3310 |
+
},
|
3311 |
+
{
|
3312 |
+
"epoch": 2.71,
|
3313 |
+
"learning_rate": 5.913942614391931e-07,
|
3314 |
+
"loss": 0.2635,
|
3315 |
+
"step": 551
|
3316 |
+
},
|
3317 |
+
{
|
3318 |
+
"epoch": 2.72,
|
3319 |
+
"learning_rate": 5.713326179062409e-07,
|
3320 |
+
"loss": 0.2658,
|
3321 |
+
"step": 552
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 2.72,
|
3325 |
+
"learning_rate": 5.516091845138377e-07,
|
3326 |
+
"loss": 0.2681,
|
3327 |
+
"step": 553
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 2.73,
|
3331 |
+
"learning_rate": 5.322245204749319e-07,
|
3332 |
+
"loss": 0.3189,
|
3333 |
+
"step": 554
|
3334 |
+
},
|
3335 |
+
{
|
3336 |
+
"epoch": 2.73,
|
3337 |
+
"learning_rate": 5.131791753974296e-07,
|
3338 |
+
"loss": 0.2983,
|
3339 |
+
"step": 555
|
3340 |
+
},
|
3341 |
+
{
|
3342 |
+
"epoch": 2.74,
|
3343 |
+
"learning_rate": 4.944736892686278e-07,
|
3344 |
+
"loss": 0.2887,
|
3345 |
+
"step": 556
|
3346 |
+
},
|
3347 |
+
{
|
3348 |
+
"epoch": 2.74,
|
3349 |
+
"learning_rate": 4.761085924398959e-07,
|
3350 |
+
"loss": 0.2594,
|
3351 |
+
"step": 557
|
3352 |
+
},
|
3353 |
+
{
|
3354 |
+
"epoch": 2.75,
|
3355 |
+
"learning_rate": 4.580844056116418e-07,
|
3356 |
+
"loss": 0.2366,
|
3357 |
+
"step": 558
|
3358 |
+
},
|
3359 |
+
{
|
3360 |
+
"epoch": 2.75,
|
3361 |
+
"learning_rate": 4.4040163981855095e-07,
|
3362 |
+
"loss": 0.3332,
|
3363 |
+
"step": 559
|
3364 |
+
},
|
3365 |
+
{
|
3366 |
+
"epoch": 2.76,
|
3367 |
+
"learning_rate": 4.2306079641509094e-07,
|
3368 |
+
"loss": 0.2593,
|
3369 |
+
"step": 560
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 2.76,
|
3373 |
+
"learning_rate": 4.0606236706130367e-07,
|
3374 |
+
"loss": 0.2825,
|
3375 |
+
"step": 561
|
3376 |
+
},
|
3377 |
+
{
|
3378 |
+
"epoch": 2.77,
|
3379 |
+
"learning_rate": 3.89406833708858e-07,
|
3380 |
+
"loss": 0.2865,
|
3381 |
+
"step": 562
|
3382 |
+
},
|
3383 |
+
{
|
3384 |
+
"epoch": 2.77,
|
3385 |
+
"learning_rate": 3.73094668587394e-07,
|
3386 |
+
"loss": 0.3002,
|
3387 |
+
"step": 563
|
3388 |
+
},
|
3389 |
+
{
|
3390 |
+
"epoch": 2.77,
|
3391 |
+
"learning_rate": 3.5712633419112686e-07,
|
3392 |
+
"loss": 0.2941,
|
3393 |
+
"step": 564
|
3394 |
+
},
|
3395 |
+
{
|
3396 |
+
"epoch": 2.78,
|
3397 |
+
"learning_rate": 3.4150228326573356e-07,
|
3398 |
+
"loss": 0.3138,
|
3399 |
+
"step": 565
|
3400 |
+
},
|
3401 |
+
{
|
3402 |
+
"epoch": 2.78,
|
3403 |
+
"learning_rate": 3.262229587955232e-07,
|
3404 |
+
"loss": 0.3054,
|
3405 |
+
"step": 566
|
3406 |
+
},
|
3407 |
+
{
|
3408 |
+
"epoch": 2.79,
|
3409 |
+
"learning_rate": 3.112887939908715e-07,
|
3410 |
+
"loss": 0.2502,
|
3411 |
+
"step": 567
|
3412 |
+
},
|
3413 |
+
{
|
3414 |
+
"epoch": 2.79,
|
3415 |
+
"learning_rate": 2.9670021227593965e-07,
|
3416 |
+
"loss": 0.2679,
|
3417 |
+
"step": 568
|
3418 |
+
},
|
3419 |
+
{
|
3420 |
+
"epoch": 2.8,
|
3421 |
+
"learning_rate": 2.824576272766666e-07,
|
3422 |
+
"loss": 0.2683,
|
3423 |
+
"step": 569
|
3424 |
+
},
|
3425 |
+
{
|
3426 |
+
"epoch": 2.8,
|
3427 |
+
"learning_rate": 2.6856144280904967e-07,
|
3428 |
+
"loss": 0.3101,
|
3429 |
+
"step": 570
|
3430 |
+
},
|
3431 |
+
{
|
3432 |
+
"epoch": 2.81,
|
3433 |
+
"learning_rate": 2.550120528676841e-07,
|
3434 |
+
"loss": 0.2749,
|
3435 |
+
"step": 571
|
3436 |
+
},
|
3437 |
+
{
|
3438 |
+
"epoch": 2.81,
|
3439 |
+
"learning_rate": 2.4180984161460004e-07,
|
3440 |
+
"loss": 0.2455,
|
3441 |
+
"step": 572
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 2.82,
|
3445 |
+
"learning_rate": 2.2895518336836923e-07,
|
3446 |
+
"loss": 0.2607,
|
3447 |
+
"step": 573
|
3448 |
+
},
|
3449 |
+
{
|
3450 |
+
"epoch": 2.82,
|
3451 |
+
"learning_rate": 2.164484425934879e-07,
|
3452 |
+
"loss": 0.2729,
|
3453 |
+
"step": 574
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 2.83,
|
3457 |
+
"learning_rate": 2.0428997389004972e-07,
|
3458 |
+
"loss": 0.2669,
|
3459 |
+
"step": 575
|
3460 |
+
},
|
3461 |
+
{
|
3462 |
+
"epoch": 2.83,
|
3463 |
+
"learning_rate": 1.9248012198368748e-07,
|
3464 |
+
"loss": 0.3026,
|
3465 |
+
"step": 576
|
3466 |
+
},
|
3467 |
+
{
|
3468 |
+
"epoch": 2.84,
|
3469 |
+
"learning_rate": 1.8101922171580022e-07,
|
3470 |
+
"loss": 0.2394,
|
3471 |
+
"step": 577
|
3472 |
+
},
|
3473 |
+
{
|
3474 |
+
"epoch": 2.84,
|
3475 |
+
"learning_rate": 1.699075980340581e-07,
|
3476 |
+
"loss": 0.2578,
|
3477 |
+
"step": 578
|
3478 |
+
},
|
3479 |
+
{
|
3480 |
+
"epoch": 2.85,
|
3481 |
+
"learning_rate": 1.5914556598319307e-07,
|
3482 |
+
"loss": 0.252,
|
3483 |
+
"step": 579
|
3484 |
+
},
|
3485 |
+
{
|
3486 |
+
"epoch": 2.85,
|
3487 |
+
"learning_rate": 1.4873343069606305e-07,
|
3488 |
+
"loss": 0.2478,
|
3489 |
+
"step": 580
|
3490 |
+
},
|
3491 |
+
{
|
3492 |
+
"epoch": 2.86,
|
3493 |
+
"learning_rate": 1.3867148738500313e-07,
|
3494 |
+
"loss": 0.3517,
|
3495 |
+
"step": 581
|
3496 |
+
},
|
3497 |
+
{
|
3498 |
+
"epoch": 2.86,
|
3499 |
+
"learning_rate": 1.289600213334505e-07,
|
3500 |
+
"loss": 0.285,
|
3501 |
+
"step": 582
|
3502 |
+
},
|
3503 |
+
{
|
3504 |
+
"epoch": 2.87,
|
3505 |
+
"learning_rate": 1.195993078878646e-07,
|
3506 |
+
"loss": 0.2673,
|
3507 |
+
"step": 583
|
3508 |
+
},
|
3509 |
+
{
|
3510 |
+
"epoch": 2.87,
|
3511 |
+
"learning_rate": 1.1058961244991144e-07,
|
3512 |
+
"loss": 0.2644,
|
3513 |
+
"step": 584
|
3514 |
+
},
|
3515 |
+
{
|
3516 |
+
"epoch": 2.88,
|
3517 |
+
"learning_rate": 1.0193119046894295e-07,
|
3518 |
+
"loss": 0.2689,
|
3519 |
+
"step": 585
|
3520 |
+
},
|
3521 |
+
{
|
3522 |
+
"epoch": 2.88,
|
3523 |
+
"learning_rate": 9.362428743475565e-08,
|
3524 |
+
"loss": 0.2699,
|
3525 |
+
"step": 586
|
3526 |
+
},
|
3527 |
+
{
|
3528 |
+
"epoch": 2.89,
|
3529 |
+
"learning_rate": 8.566913887062683e-08,
|
3530 |
+
"loss": 0.2677,
|
3531 |
+
"step": 587
|
3532 |
+
},
|
3533 |
+
{
|
3534 |
+
"epoch": 2.89,
|
3535 |
+
"learning_rate": 7.806597032663925e-08,
|
3536 |
+
"loss": 0.2846,
|
3537 |
+
"step": 588
|
3538 |
+
},
|
3539 |
+
{
|
3540 |
+
"epoch": 2.9,
|
3541 |
+
"learning_rate": 7.081499737328634e-08,
|
3542 |
+
"loss": 0.2686,
|
3543 |
+
"step": 589
|
3544 |
+
},
|
3545 |
+
{
|
3546 |
+
"epoch": 2.9,
|
3547 |
+
"learning_rate": 6.391642559535616e-08,
|
3548 |
+
"loss": 0.2542,
|
3549 |
+
"step": 590
|
3550 |
+
},
|
3551 |
+
{
|
3552 |
+
"epoch": 2.91,
|
3553 |
+
"learning_rate": 5.7370450586109737e-08,
|
3554 |
+
"loss": 0.2678,
|
3555 |
+
"step": 591
|
3556 |
+
},
|
3557 |
+
{
|
3558 |
+
"epoch": 2.91,
|
3559 |
+
"learning_rate": 5.117725794172995e-08,
|
3560 |
+
"loss": 0.237,
|
3561 |
+
"step": 592
|
3562 |
+
},
|
3563 |
+
{
|
3564 |
+
"epoch": 2.92,
|
3565 |
+
"learning_rate": 4.533702325605904e-08,
|
3566 |
+
"loss": 0.2847,
|
3567 |
+
"step": 593
|
3568 |
+
},
|
3569 |
+
{
|
3570 |
+
"epoch": 2.92,
|
3571 |
+
"learning_rate": 3.9849912115623446e-08,
|
3572 |
+
"loss": 0.2397,
|
3573 |
+
"step": 594
|
3574 |
+
},
|
3575 |
+
{
|
3576 |
+
"epoch": 2.93,
|
3577 |
+
"learning_rate": 3.471608009493754e-08,
|
3578 |
+
"loss": 0.2672,
|
3579 |
+
"step": 595
|
3580 |
+
},
|
3581 |
+
{
|
3582 |
+
"epoch": 2.93,
|
3583 |
+
"learning_rate": 2.9935672752090525e-08,
|
3584 |
+
"loss": 0.2767,
|
3585 |
+
"step": 596
|
3586 |
+
},
|
3587 |
+
{
|
3588 |
+
"epoch": 2.94,
|
3589 |
+
"learning_rate": 2.5508825624626088e-08,
|
3590 |
+
"loss": 0.2758,
|
3591 |
+
"step": 597
|
3592 |
+
},
|
3593 |
+
{
|
3594 |
+
"epoch": 2.94,
|
3595 |
+
"learning_rate": 2.1435664225688547e-08,
|
3596 |
+
"loss": 0.2576,
|
3597 |
+
"step": 598
|
3598 |
+
},
|
3599 |
+
{
|
3600 |
+
"epoch": 2.95,
|
3601 |
+
"learning_rate": 1.7716304040475697e-08,
|
3602 |
+
"loss": 0.3037,
|
3603 |
+
"step": 599
|
3604 |
+
},
|
3605 |
+
{
|
3606 |
+
"epoch": 2.95,
|
3607 |
+
"learning_rate": 1.4350850522956705e-08,
|
3608 |
+
"loss": 0.271,
|
3609 |
+
"step": 600
|
3610 |
+
},
|
3611 |
+
{
|
3612 |
+
"epoch": 2.96,
|
3613 |
+
"learning_rate": 1.1339399092885616e-08,
|
3614 |
+
"loss": 0.2347,
|
3615 |
+
"step": 601
|
3616 |
+
},
|
3617 |
+
{
|
3618 |
+
"epoch": 2.96,
|
3619 |
+
"learning_rate": 8.682035133096566e-09,
|
3620 |
+
"loss": 0.2924,
|
3621 |
+
"step": 602
|
3622 |
+
},
|
3623 |
+
{
|
3624 |
+
"epoch": 2.97,
|
3625 |
+
"learning_rate": 6.378833987077948e-09,
|
3626 |
+
"loss": 0.2847,
|
3627 |
+
"step": 603
|
3628 |
+
},
|
3629 |
+
{
|
3630 |
+
"epoch": 2.97,
|
3631 |
+
"learning_rate": 4.429860956842169e-09,
|
3632 |
+
"loss": 0.2594,
|
3633 |
+
"step": 604
|
3634 |
+
},
|
3635 |
+
{
|
3636 |
+
"epoch": 2.98,
|
3637 |
+
"learning_rate": 2.8351713010743573e-09,
|
3638 |
+
"loss": 0.2613,
|
3639 |
+
"step": 605
|
3640 |
+
},
|
3641 |
+
{
|
3642 |
+
"epoch": 2.98,
|
3643 |
+
"learning_rate": 1.5948102335572313e-09,
|
3644 |
+
"loss": 0.2603,
|
3645 |
+
"step": 606
|
3646 |
+
},
|
3647 |
+
{
|
3648 |
+
"epoch": 2.99,
|
3649 |
+
"learning_rate": 7.088129218985052e-10,
|
3650 |
+
"loss": 0.2915,
|
3651 |
+
"step": 607
|
3652 |
+
},
|
3653 |
+
{
|
3654 |
+
"epoch": 2.99,
|
3655 |
+
"learning_rate": 1.772044865316902e-10,
|
3656 |
+
"loss": 0.2903,
|
3657 |
+
"step": 608
|
3658 |
+
},
|
3659 |
+
{
|
3660 |
+
"epoch": 3.0,
|
3661 |
+
"learning_rate": 0.0,
|
3662 |
+
"loss": 0.2426,
|
3663 |
+
"step": 609
|
3664 |
+
},
|
3665 |
+
{
|
3666 |
+
"epoch": 3.0,
|
3667 |
+
"step": 609,
|
3668 |
+
"total_flos": 7.120623193701745e+17,
|
3669 |
+
"train_loss": 0.6601732866517429,
|
3670 |
+
"train_runtime": 5691.3236,
|
3671 |
+
"train_samples_per_second": 27.41,
|
3672 |
+
"train_steps_per_second": 0.107
|
3673 |
+
}
|
3674 |
+
],
|
3675 |
+
"logging_steps": 1.0,
|
3676 |
+
"max_steps": 609,
|
3677 |
+
"num_train_epochs": 3,
|
3678 |
+
"save_steps": -609,
|
3679 |
+
"total_flos": 7.120623193701745e+17,
|
3680 |
+
"trial_name": null,
|
3681 |
+
"trial_params": null
|
3682 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:352d15a68911002e728d452d615d17736a6cb8e85caf8e0aead9183648824d33
|
3 |
+
size 5947
|
training_log.txt
ADDED
@@ -0,0 +1,689 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[2024-01-10 03:41:18,555] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
2 |
+
[2024-01-10 03:41:20,266] [WARNING] [runner.py:203:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
|
3 |
+
[2024-01-10 03:41:20,266] [INFO] [runner.py:570:main] cmd = /root/anaconda3/envs/dj_comp/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgMywgNCwgNSwgNiwgN119 --master_addr=127.0.0.1 --master_port=50000 --enable_each_rank_log=None train.py --model_name_or_path /home/baaidial/models/llama-2-13b-hf/ --tokenizer /home/baaidial/models/llama-2-13b-hf/ --data_path /home/baaidial/fengduanyu/lima_code/code/data/alpaca/alpaca_predata.jsonl --output_dir /home/baaidial/fengduanyu/lima_code/code/model_save/after_sft/alpaca_Llama-2-13b_all/ --per_device_train_batch_size 8 --gradient_accumulation_steps 4 --lang en --bf16 True --gradient_checkpointing_enable True --num_train_epochs 3 --model_max_length 1024 --learning_rate 2.5e-5 --weight_decay 0 --warmup_ratio 0.03 --evaluation_strategy no --save_strategy no --save_steps -1 --save_total_limit 999 --lr_scheduler_type cosine --logging_steps 1 --tf32 True --deepspeed /home/baaidial/fengduanyu/FT-Data-Ranker/competition_kit/lm-training/train_scripts/deepspeed_configs/ds_config_stage3.json
|
4 |
+
[2024-01-10 03:41:21,810] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
5 |
+
[2024-01-10 03:41:23,124] [INFO] [launch.py:138:main] 0 NCCL_VERSION=2.18.1
|
6 |
+
[2024-01-10 03:41:23,124] [INFO] [launch.py:145:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3, 4, 5, 6, 7]}
|
7 |
+
[2024-01-10 03:41:23,124] [INFO] [launch.py:151:main] nnodes=1, num_local_procs=8, node_rank=0
|
8 |
+
[2024-01-10 03:41:23,124] [INFO] [launch.py:162:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3, 4, 5, 6, 7]})
|
9 |
+
[2024-01-10 03:41:23,124] [INFO] [launch.py:163:main] dist_world_size=8
|
10 |
+
[2024-01-10 03:41:23,124] [INFO] [launch.py:165:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
|
11 |
+
[2024-01-10 03:41:25,938] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
12 |
+
[2024-01-10 03:41:26,237] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
13 |
+
[2024-01-10 03:41:26,239] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
14 |
+
[2024-01-10 03:41:26,338] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
15 |
+
[2024-01-10 03:41:26,339] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
16 |
+
[2024-01-10 03:41:26,351] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
17 |
+
[2024-01-10 03:41:26,353] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
18 |
+
[2024-01-10 03:41:26,357] [INFO] [real_accelerator.py:158:get_accelerator] Setting ds_accelerator to cuda (auto detect)
|
19 |
+
[2024-01-10 03:41:27,429] [INFO] [comm.py:637:init_distributed] cdb=None
|
20 |
+
[2024-01-10 03:41:27,429] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
|
21 |
+
[2024-01-10 03:41:27,709] [INFO] [comm.py:637:init_distributed] cdb=None
|
22 |
+
[2024-01-10 03:41:27,773] [INFO] [comm.py:637:init_distributed] cdb=None
|
23 |
+
[2024-01-10 03:41:27,835] [INFO] [comm.py:637:init_distributed] cdb=None
|
24 |
+
[2024-01-10 03:41:27,866] [INFO] [comm.py:637:init_distributed] cdb=None
|
25 |
+
[2024-01-10 03:41:27,867] [INFO] [comm.py:637:init_distributed] cdb=None
|
26 |
+
[2024-01-10 03:41:27,894] [INFO] [comm.py:637:init_distributed] cdb=None
|
27 |
+
[2024-01-10 03:41:27,933] [INFO] [comm.py:637:init_distributed] cdb=None
|
28 |
+
Loading model from /home/baaidial/models/llama-2-13b-hf/
|
29 |
+
[2024-01-10 03:41:30,329] [INFO] [partition_parameters.py:347:__exit__] finished initializing model - num_params = 363, num_elems = 13.02B
|
30 |
+
gradient_checkpointing_enable
|
31 |
+
Model class: <class 'transformers.models.llama.modeling_llama.LlamaForCausalLM'>
|
32 |
+
Tokenizer class: <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>
|
33 |
+
+---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
|
34 |
+
| |pad_token|pad_token_id|bos_token|bos_token_id|eos_token|eos_token_id|unk_token|unk_token_id|model_max_length|
|
35 |
+
+---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
|
36 |
+
|tokenizer| <unk> | 0 | <s> | 1 | </s> | 2 | <unk> | 0 | 1024 |
|
37 |
+
+---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
|
38 |
+
| model | - | 0 | - | 1 | - | 2 | - | - | - |
|
39 |
+
+---------+---------+------------+---------+------------+---------+------------+---------+------------+----------------+
|
40 |
+
There are 52002 training samples in data path
|
41 |
+
Formatting inputs...
|
42 |
+
Tokenizing inputs... This may take some time...
|
43 |
+
PROMPT:
|
44 |
+
'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nWhen did the Second World War end?\n\n### Response:'
|
45 |
+
RESPONSE:
|
46 |
+
'The Second World War ended on September 2, 1945 with the official surrender of Japan. The Allies officially declared victory over Germany on May 8, 1945, which is known as V-E Day, or Victory in Europe Day.</s>'
|
47 |
+
====================================================================================================
|
48 |
+
PROMPT:
|
49 |
+
'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nExplain why the following statement is wrong: "Cloud computing stores your data on the Internet."\n\n### Response:'
|
50 |
+
RESPONSE:
|
51 |
+
'The statement is incorrect because cloud computing does not store data on the Internet. Instead, cloud computing stores data in a remote server which is usually connected to the Internet. Data can be accessed and retrieved from the remote server through the Internet using an application.</s>'
|
52 |
+
====================================================================================================
|
53 |
+
PROMPT:
|
54 |
+
'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nIdentify 5 major differences between two similar items.\n\n### Input:\nBlackberry and Raspberry\n\n### Response:'
|
55 |
+
RESPONSE:
|
56 |
+
'1. Blackberries have a rounded shape, while raspberries have a distinct hollow core when picked off the plant.\n2. Raspberries have a rich and intense flavor profile, while blackberries are sweeter and less tart.\n3. Blackberries typically have very tiny seeds that are barely noticeable when eaten, while raspberries have larger, more noticeable seeds.\n4. Blackberries tend to be darker in color than raspberries, which tend to be a pinkish-red.\n5. Raspberries are generally more fragile, and can spoil or bruise more easily than blackberries.</s>'
|
57 |
+
====================================================================================================
|
58 |
+
PROMPT:
|
59 |
+
'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nClassify the following text as opinion, fact, or non-credible\n\n### Input:\nThis new book is amazing!\n\n### Response:'
|
60 |
+
RESPONSE:
|
61 |
+
'Opinion.</s>'
|
62 |
+
====================================================================================================
|
63 |
+
PROMPT:
|
64 |
+
'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nClean the HTML code by removing all the unnecessary tags.\n\n### Input:\n<html><head><title>Website</title></head><body><p>This is a paragraph.</p><p>This is the second paragraph.</p></body></html>\n\n### Response:'
|
65 |
+
RESPONSE:
|
66 |
+
'<html><head><title>Website</title></head><body>This is a paragraph.<p>This is the second paragraph.</p></body></html></s>'
|
67 |
+
====================================================================================================
|
68 |
+
ORI NUMBER: 52002, AFTER FILETER: 52000, DROP NUMBER: 2
|
69 |
+
Total 52000 samples [ 6.56M tokens] in training!
|
70 |
+
Parameter Offload: Total persistent parameters: 414720 in 81 params
|
71 |
+
{'loss': 1.3013, 'learning_rate': 1.3157894736842106e-06, 'epoch': 0.0}
|
72 |
+
{'loss': 1.2825, 'learning_rate': 2.631578947368421e-06, 'epoch': 0.01}
|
73 |
+
{'loss': 1.3755, 'learning_rate': 3.9473684210526315e-06, 'epoch': 0.01}
|
74 |
+
{'loss': 1.2644, 'learning_rate': 5.263157894736842e-06, 'epoch': 0.02}
|
75 |
+
{'loss': 1.2507, 'learning_rate': 6.578947368421053e-06, 'epoch': 0.02}
|
76 |
+
{'loss': 1.1368, 'learning_rate': 7.894736842105263e-06, 'epoch': 0.03}
|
77 |
+
{'loss': 1.1033, 'learning_rate': 9.210526315789474e-06, 'epoch': 0.03}
|
78 |
+
{'loss': 1.0729, 'learning_rate': 1.0526315789473684e-05, 'epoch': 0.04}
|
79 |
+
{'loss': 1.0756, 'learning_rate': 1.1842105263157895e-05, 'epoch': 0.04}
|
80 |
+
{'loss': 1.0396, 'learning_rate': 1.3157894736842106e-05, 'epoch': 0.05}
|
81 |
+
{'loss': 1.0539, 'learning_rate': 1.4473684210526317e-05, 'epoch': 0.05}
|
82 |
+
{'loss': 1.085, 'learning_rate': 1.5789473684210526e-05, 'epoch': 0.06}
|
83 |
+
{'loss': 1.0104, 'learning_rate': 1.7105263157894737e-05, 'epoch': 0.06}
|
84 |
+
{'loss': 1.0773, 'learning_rate': 1.8421052631578947e-05, 'epoch': 0.07}
|
85 |
+
{'loss': 1.0052, 'learning_rate': 1.9736842105263158e-05, 'epoch': 0.07}
|
86 |
+
{'loss': 1.0603, 'learning_rate': 2.105263157894737e-05, 'epoch': 0.08}
|
87 |
+
{'loss': 1.0628, 'learning_rate': 2.236842105263158e-05, 'epoch': 0.08}
|
88 |
+
{'loss': 1.0233, 'learning_rate': 2.368421052631579e-05, 'epoch': 0.09}
|
89 |
+
{'loss': 1.0953, 'learning_rate': 2.5e-05, 'epoch': 0.09}
|
90 |
+
{'loss': 1.0786, 'learning_rate': 2.499982279551347e-05, 'epoch': 0.1}
|
91 |
+
{'loss': 1.0389, 'learning_rate': 2.4999291187078104e-05, 'epoch': 0.1}
|
92 |
+
{'loss': 1.0168, 'learning_rate': 2.4998405189766444e-05, 'epoch': 0.11}
|
93 |
+
{'loss': 1.036, 'learning_rate': 2.4997164828698926e-05, 'epoch': 0.11}
|
94 |
+
{'loss': 1.0171, 'learning_rate': 2.4995570139043158e-05, 'epoch': 0.12}
|
95 |
+
{'loss': 1.0811, 'learning_rate': 2.4993621166012923e-05, 'epoch': 0.12}
|
96 |
+
{'loss': 1.0955, 'learning_rate': 2.4991317964866905e-05, 'epoch': 0.13}
|
97 |
+
{'loss': 1.0038, 'learning_rate': 2.4988660600907115e-05, 'epoch': 0.13}
|
98 |
+
{'loss': 1.0558, 'learning_rate': 2.4985649149477043e-05, 'epoch': 0.14}
|
99 |
+
{'loss': 1.0707, 'learning_rate': 2.4982283695959525e-05, 'epoch': 0.14}
|
100 |
+
{'loss': 1.1162, 'learning_rate': 2.4978564335774313e-05, 'epoch': 0.15}
|
101 |
+
{'loss': 1.006, 'learning_rate': 2.4974491174375374e-05, 'epoch': 0.15}
|
102 |
+
{'loss': 1.0481, 'learning_rate': 2.497006432724791e-05, 'epoch': 0.16}
|
103 |
+
{'loss': 1.0609, 'learning_rate': 2.4965283919905065e-05, 'epoch': 0.16}
|
104 |
+
{'loss': 1.0946, 'learning_rate': 2.4960150087884376e-05, 'epoch': 0.17}
|
105 |
+
{'loss': 1.0222, 'learning_rate': 2.4954662976743944e-05, 'epoch': 0.17}
|
106 |
+
{'loss': 1.0427, 'learning_rate': 2.494882274205827e-05, 'epoch': 0.18}
|
107 |
+
{'loss': 1.0987, 'learning_rate': 2.4942629549413894e-05, 'epoch': 0.18}
|
108 |
+
{'loss': 1.1212, 'learning_rate': 2.4936083574404646e-05, 'epoch': 0.19}
|
109 |
+
{'loss': 1.0986, 'learning_rate': 2.4929185002626714e-05, 'epoch': 0.19}
|
110 |
+
{'loss': 1.05, 'learning_rate': 2.492193402967336e-05, 'epoch': 0.2}
|
111 |
+
{'loss': 1.0784, 'learning_rate': 2.4914330861129376e-05, 'epoch': 0.2}
|
112 |
+
{'loss': 1.0997, 'learning_rate': 2.4906375712565245e-05, 'epoch': 0.21}
|
113 |
+
{'loss': 1.0774, 'learning_rate': 2.489806880953106e-05, 'epoch': 0.21}
|
114 |
+
{'loss': 1.0832, 'learning_rate': 2.4889410387550093e-05, 'epoch': 0.22}
|
115 |
+
{'loss': 1.0649, 'learning_rate': 2.488040069211214e-05, 'epoch': 0.22}
|
116 |
+
{'loss': 1.0684, 'learning_rate': 2.487103997866655e-05, 'epoch': 0.23}
|
117 |
+
{'loss': 1.0857, 'learning_rate': 2.4861328512615e-05, 'epoch': 0.23}
|
118 |
+
{'loss': 1.0896, 'learning_rate': 2.485126656930394e-05, 'epoch': 0.24}
|
119 |
+
{'loss': 1.0719, 'learning_rate': 2.4840854434016808e-05, 'epoch': 0.24}
|
120 |
+
{'loss': 1.0917, 'learning_rate': 2.4830092401965942e-05, 'epoch': 0.25}
|
121 |
+
{'loss': 1.0893, 'learning_rate': 2.4818980778284202e-05, 'epoch': 0.25}
|
122 |
+
{'loss': 1.0136, 'learning_rate': 2.4807519878016313e-05, 'epoch': 0.26}
|
123 |
+
{'loss': 1.0472, 'learning_rate': 2.4795710026109954e-05, 'epoch': 0.26}
|
124 |
+
{'loss': 1.0625, 'learning_rate': 2.4783551557406515e-05, 'epoch': 0.27}
|
125 |
+
{'loss': 1.1197, 'learning_rate': 2.4771044816631635e-05, 'epoch': 0.27}
|
126 |
+
{'loss': 1.0531, 'learning_rate': 2.4758190158385402e-05, 'epoch': 0.28}
|
127 |
+
{'loss': 1.0767, 'learning_rate': 2.4744987947132318e-05, 'epoch': 0.28}
|
128 |
+
{'loss': 1.0852, 'learning_rate': 2.473143855719095e-05, 'epoch': 0.29}
|
129 |
+
{'loss': 1.093, 'learning_rate': 2.4717542372723333e-05, 'epoch': 0.29}
|
130 |
+
{'loss': 1.0991, 'learning_rate': 2.4703299787724065e-05, 'epoch': 0.3}
|
131 |
+
{'loss': 1.0982, 'learning_rate': 2.468871120600913e-05, 'epoch': 0.3}
|
132 |
+
{'loss': 1.1232, 'learning_rate': 2.4673777041204478e-05, 'epoch': 0.31}
|
133 |
+
{'loss': 1.0692, 'learning_rate': 2.465849771673427e-05, 'epoch': 0.31}
|
134 |
+
{'loss': 1.1136, 'learning_rate': 2.4642873665808873e-05, 'epoch': 0.31}
|
135 |
+
{'loss': 1.0771, 'learning_rate': 2.4626905331412608e-05, 'epoch': 0.32}
|
136 |
+
{'loss': 1.0464, 'learning_rate': 2.4610593166291143e-05, 'epoch': 0.32}
|
137 |
+
{'loss': 1.0578, 'learning_rate': 2.4593937632938695e-05, 'epoch': 0.33}
|
138 |
+
{'loss': 1.0322, 'learning_rate': 2.457693920358491e-05, 'epoch': 0.33}
|
139 |
+
{'loss': 1.0573, 'learning_rate': 2.455959836018145e-05, 'epoch': 0.34}
|
140 |
+
{'loss': 1.083, 'learning_rate': 2.454191559438836e-05, 'epoch': 0.34}
|
141 |
+
{'loss': 1.0426, 'learning_rate': 2.4523891407560107e-05, 'epoch': 0.35}
|
142 |
+
{'loss': 1.0706, 'learning_rate': 2.4505526310731376e-05, 'epoch': 0.35}
|
143 |
+
{'loss': 1.089, 'learning_rate': 2.448682082460257e-05, 'epoch': 0.36}
|
144 |
+
{'loss': 1.0918, 'learning_rate': 2.446777547952507e-05, 'epoch': 0.36}
|
145 |
+
{'loss': 1.0869, 'learning_rate': 2.4448390815486165e-05, 'epoch': 0.37}
|
146 |
+
{'loss': 1.0751, 'learning_rate': 2.4428667382093762e-05, 'epoch': 0.37}
|
147 |
+
{'loss': 1.0684, 'learning_rate': 2.440860573856081e-05, 'epoch': 0.38}
|
148 |
+
{'loss': 1.0704, 'learning_rate': 2.438820645368942e-05, 'epoch': 0.38}
|
149 |
+
{'loss': 1.0671, 'learning_rate': 2.4367470105854766e-05, 'epoch': 0.39}
|
150 |
+
{'loss': 1.0434, 'learning_rate': 2.4346397282988666e-05, 'epoch': 0.39}
|
151 |
+
{'loss': 1.0605, 'learning_rate': 2.432498858256292e-05, 'epoch': 0.4}
|
152 |
+
{'loss': 1.0536, 'learning_rate': 2.4303244611572372e-05, 'epoch': 0.4}
|
153 |
+
{'loss': 1.0807, 'learning_rate': 2.4281165986517696e-05, 'epoch': 0.41}
|
154 |
+
{'loss': 1.0605, 'learning_rate': 2.425875333338792e-05, 'epoch': 0.41}
|
155 |
+
{'loss': 1.056, 'learning_rate': 2.4236007287642664e-05, 'epoch': 0.42}
|
156 |
+
{'loss': 1.0294, 'learning_rate': 2.421292849419416e-05, 'epoch': 0.42}
|
157 |
+
{'loss': 1.0571, 'learning_rate': 2.4189517607388918e-05, 'epoch': 0.43}
|
158 |
+
{'loss': 1.1025, 'learning_rate': 2.416577529098921e-05, 'epoch': 0.43}
|
159 |
+
{'loss': 1.1459, 'learning_rate': 2.4141702218154232e-05, 'epoch': 0.44}
|
160 |
+
{'loss': 1.0755, 'learning_rate': 2.4117299071421023e-05, 'epoch': 0.44}
|
161 |
+
{'loss': 1.0686, 'learning_rate': 2.4092566542685123e-05, 'epoch': 0.45}
|
162 |
+
{'loss': 1.0586, 'learning_rate': 2.4067505333180938e-05, 'epoch': 0.45}
|
163 |
+
{'loss': 1.1033, 'learning_rate': 2.404211615346187e-05, 'epoch': 0.46}
|
164 |
+
{'loss': 1.0253, 'learning_rate': 2.401639972338016e-05, 'epoch': 0.46}
|
165 |
+
{'loss': 1.0888, 'learning_rate': 2.399035677206651e-05, 'epoch': 0.47}
|
166 |
+
{'loss': 1.0677, 'learning_rate': 2.396398803790936e-05, 'epoch': 0.47}
|
167 |
+
{'loss': 1.0582, 'learning_rate': 2.393729426853399e-05, 'epoch': 0.48}
|
168 |
+
{'loss': 1.0223, 'learning_rate': 2.3910276220781314e-05, 'epoch': 0.48}
|
169 |
+
{'loss': 1.0885, 'learning_rate': 2.3882934660686418e-05, 'epoch': 0.49}
|
170 |
+
{'loss': 1.0553, 'learning_rate': 2.3855270363456833e-05, 'epoch': 0.49}
|
171 |
+
{'loss': 1.1293, 'learning_rate': 2.382728411345058e-05, 'epoch': 0.5}
|
172 |
+
{'loss': 1.1106, 'learning_rate': 2.3798976704153906e-05, 'epoch': 0.5}
|
173 |
+
{'loss': 1.0647, 'learning_rate': 2.3770348938158805e-05, 'epoch': 0.51}
|
174 |
+
{'loss': 1.078, 'learning_rate': 2.3741401627140242e-05, 'epoch': 0.51}
|
175 |
+
{'loss': 1.0344, 'learning_rate': 2.371213559183316e-05, 'epoch': 0.52}
|
176 |
+
{'loss': 1.095, 'learning_rate': 2.3682551662009203e-05, 'epoch': 0.52}
|
177 |
+
{'loss': 1.0794, 'learning_rate': 2.3652650676453188e-05, 'epoch': 0.53}
|
178 |
+
{'loss': 0.9938, 'learning_rate': 2.362243348293931e-05, 'epoch': 0.53}
|
179 |
+
{'loss': 1.1374, 'learning_rate': 2.3591900938207147e-05, 'epoch': 0.54}
|
180 |
+
{'loss': 1.0443, 'learning_rate': 2.3561053907937315e-05, 'epoch': 0.54}
|
181 |
+
{'loss': 1.0452, 'learning_rate': 2.352989326672696e-05, 'epoch': 0.55}
|
182 |
+
{'loss': 1.0359, 'learning_rate': 2.349841989806495e-05, 'epoch': 0.55}
|
183 |
+
{'loss': 1.0973, 'learning_rate': 2.346663469430683e-05, 'epoch': 0.56}
|
184 |
+
{'loss': 1.138, 'learning_rate': 2.3434538556649515e-05, 'epoch': 0.56}
|
185 |
+
{'loss': 1.0806, 'learning_rate': 2.3402132395105737e-05, 'epoch': 0.57}
|
186 |
+
{'loss': 1.1112, 'learning_rate': 2.336941712847825e-05, 'epoch': 0.57}
|
187 |
+
{'loss': 1.0837, 'learning_rate': 2.3336393684333778e-05, 'epoch': 0.58}
|
188 |
+
{'loss': 1.0794, 'learning_rate': 2.3303062998976712e-05, 'epoch': 0.58}
|
189 |
+
{'loss': 1.0757, 'learning_rate': 2.3269426017422576e-05, 'epoch': 0.59}
|
190 |
+
{'loss': 0.9923, 'learning_rate': 2.3235483693371214e-05, 'epoch': 0.59}
|
191 |
+
{'loss': 1.0442, 'learning_rate': 2.3201236989179766e-05, 'epoch': 0.6}
|
192 |
+
{'loss': 1.0608, 'learning_rate': 2.3166686875835365e-05, 'epoch': 0.6}
|
193 |
+
{'loss': 1.0806, 'learning_rate': 2.313183433292764e-05, 'epoch': 0.61}
|
194 |
+
{'loss': 1.0728, 'learning_rate': 2.3096680348620886e-05, 'epoch': 0.61}
|
195 |
+
{'loss': 1.0979, 'learning_rate': 2.3061225919626124e-05, 'epoch': 0.62}
|
196 |
+
{'loss': 1.0827, 'learning_rate': 2.3025472051172755e-05, 'epoch': 0.62}
|
197 |
+
{'loss': 1.0715, 'learning_rate': 2.2989419756980134e-05, 'epoch': 0.62}
|
198 |
+
{'loss': 1.0668, 'learning_rate': 2.295307005922879e-05, 'epoch': 0.63}
|
199 |
+
{'loss': 1.0726, 'learning_rate': 2.2916423988531437e-05, 'epoch': 0.63}
|
200 |
+
{'loss': 1.1038, 'learning_rate': 2.2879482583903783e-05, 'epoch': 0.64}
|
201 |
+
{'loss': 1.0698, 'learning_rate': 2.2842246892735053e-05, 'epoch': 0.64}
|
202 |
+
{'loss': 1.0782, 'learning_rate': 2.2804717970758286e-05, 'epoch': 0.65}
|
203 |
+
{'loss': 1.0834, 'learning_rate': 2.2766896882020422e-05, 'epoch': 0.65}
|
204 |
+
{'loss': 1.0536, 'learning_rate': 2.2728784698852114e-05, 'epoch': 0.66}
|
205 |
+
{'loss': 1.0867, 'learning_rate': 2.2690382501837344e-05, 'epoch': 0.66}
|
206 |
+
{'loss': 1.0369, 'learning_rate': 2.2651691379782764e-05, 'epoch': 0.67}
|
207 |
+
{'loss': 1.0474, 'learning_rate': 2.2612712429686845e-05, 'epoch': 0.67}
|
208 |
+
{'loss': 1.129, 'learning_rate': 2.2573446756708754e-05, 'epoch': 0.68}
|
209 |
+
{'loss': 1.0561, 'learning_rate': 2.2533895474137047e-05, 'epoch': 0.68}
|
210 |
+
{'loss': 1.1228, 'learning_rate': 2.2494059703358073e-05, 'epoch': 0.69}
|
211 |
+
{'loss': 1.1673, 'learning_rate': 2.24539405738242e-05, 'epoch': 0.69}
|
212 |
+
{'loss': 1.0184, 'learning_rate': 2.2413539223021794e-05, 'epoch': 0.7}
|
213 |
+
{'loss': 1.0699, 'learning_rate': 2.237285679643895e-05, 'epoch': 0.7}
|
214 |
+
{'loss': 1.0924, 'learning_rate': 2.2331894447533035e-05, 'epoch': 0.71}
|
215 |
+
{'loss': 1.0106, 'learning_rate': 2.229065333769796e-05, 'epoch': 0.71}
|
216 |
+
{'loss': 1.0525, 'learning_rate': 2.2249134636231285e-05, 'epoch': 0.72}
|
217 |
+
{'loss': 1.1001, 'learning_rate': 2.2207339520301033e-05, 'epoch': 0.72}
|
218 |
+
{'loss': 1.0832, 'learning_rate': 2.216526917491234e-05, 'epoch': 0.73}
|
219 |
+
{'loss': 0.9838, 'learning_rate': 2.2122924792873827e-05, 'epoch': 0.73}
|
220 |
+
{'loss': 1.0705, 'learning_rate': 2.2080307574763824e-05, 'epoch': 0.74}
|
221 |
+
{'loss': 1.1082, 'learning_rate': 2.2037418728896282e-05, 'epoch': 0.74}
|
222 |
+
{'loss': 1.0794, 'learning_rate': 2.1994259471286545e-05, 'epoch': 0.75}
|
223 |
+
{'loss': 1.0738, 'learning_rate': 2.1950831025616873e-05, 'epoch': 0.75}
|
224 |
+
{'loss': 1.0687, 'learning_rate': 2.190713462320173e-05, 'epoch': 0.76}
|
225 |
+
{'loss': 0.9987, 'learning_rate': 2.186317150295289e-05, 'epoch': 0.76}
|
226 |
+
{'loss': 1.0749, 'learning_rate': 2.1818942911344283e-05, 'epoch': 0.77}
|
227 |
+
{'loss': 1.053, 'learning_rate': 2.17744501023767e-05, 'epoch': 0.77}
|
228 |
+
{'loss': 1.0967, 'learning_rate': 2.1729694337542196e-05, 'epoch': 0.78}
|
229 |
+
{'loss': 1.1154, 'learning_rate': 2.168467688578834e-05, 'epoch': 0.78}
|
230 |
+
{'loss': 1.0552, 'learning_rate': 2.163939902348225e-05, 'epoch': 0.79}
|
231 |
+
{'loss': 1.0798, 'learning_rate': 2.1593862034374365e-05, 'epoch': 0.79}
|
232 |
+
{'loss': 1.073, 'learning_rate': 2.15480672095621e-05, 'epoch': 0.8}
|
233 |
+
{'loss': 1.0787, 'learning_rate': 2.15020158474532e-05, 'epoch': 0.8}
|
234 |
+
{'loss': 1.034, 'learning_rate': 2.145570925372894e-05, 'epoch': 0.81}
|
235 |
+
{'loss': 1.0699, 'learning_rate': 2.1409148741307107e-05, 'epoch': 0.81}
|
236 |
+
{'loss': 0.9939, 'learning_rate': 2.1362335630304768e-05, 'epoch': 0.82}
|
237 |
+
{'loss': 1.0616, 'learning_rate': 2.131527124800086e-05, 'epoch': 0.82}
|
238 |
+
{'loss': 0.992, 'learning_rate': 2.1267956928798525e-05, 'epoch': 0.83}
|
239 |
+
{'loss': 1.0463, 'learning_rate': 2.1220394014187312e-05, 'epoch': 0.83}
|
240 |
+
{'loss': 1.071, 'learning_rate': 2.1172583852705115e-05, 'epoch': 0.84}
|
241 |
+
{'loss': 1.0274, 'learning_rate': 2.1124527799899953e-05, 'epoch': 0.84}
|
242 |
+
{'loss': 1.0593, 'learning_rate': 2.1076227218291535e-05, 'epoch': 0.85}
|
243 |
+
{'loss': 1.0286, 'learning_rate': 2.1027683477332623e-05, 'epoch': 0.85}
|
244 |
+
{'loss': 1.0657, 'learning_rate': 2.0978897953370204e-05, 'epoch': 0.86}
|
245 |
+
{'loss': 1.0616, 'learning_rate': 2.0929872029606472e-05, 'epoch': 0.86}
|
246 |
+
{'loss': 1.0425, 'learning_rate': 2.088060709605962e-05, 'epoch': 0.87}
|
247 |
+
{'loss': 1.0024, 'learning_rate': 2.08311045495244e-05, 'epoch': 0.87}
|
248 |
+
{'loss': 1.0252, 'learning_rate': 2.078136579353255e-05, 'epoch': 0.88}
|
249 |
+
{'loss': 1.0623, 'learning_rate': 2.0731392238312985e-05, 'epoch': 0.88}
|
250 |
+
{'loss': 1.0712, 'learning_rate': 2.0681185300751814e-05, 'epoch': 0.89}
|
251 |
+
{'loss': 1.0976, 'learning_rate': 2.0630746404352168e-05, 'epoch': 0.89}
|
252 |
+
{'loss': 1.0481, 'learning_rate': 2.058007697919386e-05, 'epoch': 0.9}
|
253 |
+
{'loss': 1.0502, 'learning_rate': 2.0529178461892785e-05, 'epoch': 0.9}
|
254 |
+
{'loss': 1.0707, 'learning_rate': 2.0478052295560253e-05, 'epoch': 0.91}
|
255 |
+
{'loss': 1.0669, 'learning_rate': 2.0426699929762035e-05, 'epoch': 0.91}
|
256 |
+
{'loss': 1.0067, 'learning_rate': 2.037512282047726e-05, 'epoch': 0.92}
|
257 |
+
{'loss': 1.1202, 'learning_rate': 2.0323322430057166e-05, 'epoch': 0.92}
|
258 |
+
{'loss': 1.074, 'learning_rate': 2.0271300227183598e-05, 'epoch': 0.92}
|
259 |
+
{'loss': 1.0394, 'learning_rate': 2.02190576868274e-05, 'epoch': 0.93}
|
260 |
+
{'loss': 1.0368, 'learning_rate': 2.016659629020658e-05, 'epoch': 0.93}
|
261 |
+
{'loss': 1.0733, 'learning_rate': 2.0113917524744308e-05, 'epoch': 0.94}
|
262 |
+
{'loss': 1.0594, 'learning_rate': 2.0061022884026762e-05, 'epoch': 0.94}
|
263 |
+
{'loss': 1.0401, 'learning_rate': 2.0007913867760763e-05, 'epoch': 0.95}
|
264 |
+
{'loss': 1.0903, 'learning_rate': 1.995459198173127e-05, 'epoch': 0.95}
|
265 |
+
{'loss': 1.1046, 'learning_rate': 1.9901058737758667e-05, 'epoch': 0.96}
|
266 |
+
{'loss': 1.0478, 'learning_rate': 1.9847315653655915e-05, 'epoch': 0.96}
|
267 |
+
{'loss': 1.0747, 'learning_rate': 1.9793364253185518e-05, 'epoch': 0.97}
|
268 |
+
{'loss': 1.0484, 'learning_rate': 1.9739206066016307e-05, 'epoch': 0.97}
|
269 |
+
{'loss': 1.0897, 'learning_rate': 1.9684842627680088e-05, 'epoch': 0.98}
|
270 |
+
{'loss': 1.0715, 'learning_rate': 1.963027547952808e-05, 'epoch': 0.98}
|
271 |
+
{'loss': 1.0671, 'learning_rate': 1.9575506168687247e-05, 'epoch': 0.99}
|
272 |
+
{'loss': 0.9719, 'learning_rate': 1.9520536248016403e-05, 'epoch': 0.99}
|
273 |
+
{'loss': 1.0384, 'learning_rate': 1.946536727606219e-05, 'epoch': 1.0}
|
274 |
+
{'loss': 0.7968, 'learning_rate': 1.941000081701492e-05, 'epoch': 1.0}
|
275 |
+
{'loss': 0.6873, 'learning_rate': 1.9354438440664167e-05, 'epoch': 1.01}
|
276 |
+
{'loss': 0.6435, 'learning_rate': 1.929868172235433e-05, 'epoch': 1.01}
|
277 |
+
{'loss': 0.6083, 'learning_rate': 1.9242732242939893e-05, 'epoch': 1.02}
|
278 |
+
{'loss': 0.6499, 'learning_rate': 1.9186591588740667e-05, 'epoch': 1.02}
|
279 |
+
{'loss': 0.6342, 'learning_rate': 1.913026135149678e-05, 'epoch': 1.03}
|
280 |
+
{'loss': 0.6186, 'learning_rate': 1.9073743128323558e-05, 'epoch': 1.03}
|
281 |
+
{'loss': 0.6751, 'learning_rate': 1.9017038521666232e-05, 'epoch': 1.04}
|
282 |
+
{'loss': 0.6175, 'learning_rate': 1.8960149139254513e-05, 'epoch': 1.04}
|
283 |
+
{'loss': 0.5863, 'learning_rate': 1.8903076594057013e-05, 'epoch': 1.05}
|
284 |
+
{'loss': 0.6271, 'learning_rate': 1.88458225042355e-05, 'epoch': 1.05}
|
285 |
+
{'loss': 0.6416, 'learning_rate': 1.8788388493099033e-05, 'epoch': 1.06}
|
286 |
+
{'loss': 0.653, 'learning_rate': 1.8730776189057918e-05, 'epoch': 1.06}
|
287 |
+
{'loss': 0.6631, 'learning_rate': 1.8672987225577552e-05, 'epoch': 1.07}
|
288 |
+
{'loss': 0.6022, 'learning_rate': 1.8615023241132127e-05, 'epoch': 1.07}
|
289 |
+
{'loss': 0.645, 'learning_rate': 1.855688587915813e-05, 'epoch': 1.08}
|
290 |
+
{'loss': 0.6546, 'learning_rate': 1.8498576788007775e-05, 'epoch': 1.08}
|
291 |
+
{'loss': 0.6453, 'learning_rate': 1.8440097620902284e-05, 'epoch': 1.09}
|
292 |
+
{'loss': 0.6509, 'learning_rate': 1.838145003588497e-05, 'epoch': 1.09}
|
293 |
+
{'loss': 0.5689, 'learning_rate': 1.832263569577427e-05, 'epoch': 1.1}
|
294 |
+
{'loss': 0.5919, 'learning_rate': 1.8263656268116576e-05, 'epoch': 1.1}
|
295 |
+
{'loss': 0.6308, 'learning_rate': 1.8204513425138952e-05, 'epoch': 1.11}
|
296 |
+
{'loss': 0.6666, 'learning_rate': 1.8145208843701742e-05, 'epoch': 1.11}
|
297 |
+
{'loss': 0.584, 'learning_rate': 1.808574420525101e-05, 'epoch': 1.12}
|
298 |
+
{'loss': 0.5634, 'learning_rate': 1.8026121195770874e-05, 'epoch': 1.12}
|
299 |
+
{'loss': 0.5975, 'learning_rate': 1.7966341505735695e-05, 'epoch': 1.13}
|
300 |
+
{'loss': 0.6015, 'learning_rate': 1.7906406830062156e-05, 'epoch': 1.13}
|
301 |
+
{'loss': 0.5879, 'learning_rate': 1.7846318868061212e-05, 'epoch': 1.14}
|
302 |
+
{'loss': 0.6187, 'learning_rate': 1.7786079323389893e-05, 'epoch': 1.14}
|
303 |
+
{'loss': 0.617, 'learning_rate': 1.7725689904003006e-05, 'epoch': 1.15}
|
304 |
+
{'loss': 0.6135, 'learning_rate': 1.766515232210473e-05, 'epoch': 1.15}
|
305 |
+
{'loss': 0.6676, 'learning_rate': 1.7604468294100034e-05, 'epoch': 1.16}
|
306 |
+
{'loss': 0.6294, 'learning_rate': 1.754363954054605e-05, 'epoch': 1.16}
|
307 |
+
{'loss': 0.6308, 'learning_rate': 1.7482667786103256e-05, 'epoch': 1.17}
|
308 |
+
{'loss': 0.5851, 'learning_rate': 1.7421554759486614e-05, 'epoch': 1.17}
|
309 |
+
{'loss': 0.6303, 'learning_rate': 1.736030219341651e-05, 'epoch': 1.18}
|
310 |
+
{'loss': 0.6124, 'learning_rate': 1.7298911824569676e-05, 'epoch': 1.18}
|
311 |
+
{'loss': 0.6291, 'learning_rate': 1.7237385393529916e-05, 'epoch': 1.19}
|
312 |
+
{'loss': 0.6457, 'learning_rate': 1.7175724644738773e-05, 'epoch': 1.19}
|
313 |
+
{'loss': 0.6475, 'learning_rate': 1.7113931326446054e-05, 'epoch': 1.2}
|
314 |
+
{'loss': 0.6723, 'learning_rate': 1.705200719066028e-05, 'epoch': 1.2}
|
315 |
+
{'loss': 0.6456, 'learning_rate': 1.6989953993098998e-05, 'epoch': 1.21}
|
316 |
+
{'loss': 0.613, 'learning_rate': 1.6927773493139014e-05, 'epoch': 1.21}
|
317 |
+
{'loss': 0.6202, 'learning_rate': 1.68654674537665e-05, 'epoch': 1.22}
|
318 |
+
{'loss': 0.5821, 'learning_rate': 1.6803037641527002e-05, 'epoch': 1.22}
|
319 |
+
{'loss': 0.6698, 'learning_rate': 1.674048582647538e-05, 'epoch': 1.23}
|
320 |
+
{'loss': 0.6762, 'learning_rate': 1.6677813782125592e-05, 'epoch': 1.23}
|
321 |
+
{'loss': 0.6087, 'learning_rate': 1.6615023285400432e-05, 'epoch': 1.23}
|
322 |
+
{'loss': 0.6154, 'learning_rate': 1.6552116116581133e-05, 'epoch': 1.24}
|
323 |
+
{'loss': 0.6162, 'learning_rate': 1.648909405925691e-05, 'epoch': 1.24}
|
324 |
+
{'loss': 0.624, 'learning_rate': 1.6425958900274362e-05, 'epoch': 1.25}
|
325 |
+
{'loss': 0.5986, 'learning_rate': 1.6362712429686846e-05, 'epoch': 1.25}
|
326 |
+
{'loss': 0.6152, 'learning_rate': 1.629935644070369e-05, 'epoch': 1.26}
|
327 |
+
{'loss': 0.6114, 'learning_rate': 1.6235892729639378e-05, 'epoch': 1.26}
|
328 |
+
{'loss': 0.603, 'learning_rate': 1.617232309586261e-05, 'epoch': 1.27}
|
329 |
+
{'loss': 0.6791, 'learning_rate': 1.6108649341745262e-05, 'epoch': 1.27}
|
330 |
+
{'loss': 0.6662, 'learning_rate': 1.604487327261133e-05, 'epoch': 1.28}
|
331 |
+
{'loss': 0.6407, 'learning_rate': 1.59809966966857e-05, 'epoch': 1.28}
|
332 |
+
{'loss': 0.629, 'learning_rate': 1.591702142504291e-05, 'epoch': 1.29}
|
333 |
+
{'loss': 0.6191, 'learning_rate': 1.5852949271555787e-05, 'epoch': 1.29}
|
334 |
+
{'loss': 0.6332, 'learning_rate': 1.5788782052844015e-05, 'epoch': 1.3}
|
335 |
+
{'loss': 0.642, 'learning_rate': 1.572452158822265e-05, 'epoch': 1.3}
|
336 |
+
{'loss': 0.6257, 'learning_rate': 1.5660169699650503e-05, 'epoch': 1.31}
|
337 |
+
{'loss': 0.6622, 'learning_rate': 1.5595728211678525e-05, 'epoch': 1.31}
|
338 |
+
{'loss': 0.6221, 'learning_rate': 1.553119895139803e-05, 'epoch': 1.32}
|
339 |
+
{'loss': 0.641, 'learning_rate': 1.546658374838894e-05, 'epoch': 1.32}
|
340 |
+
{'loss': 0.6199, 'learning_rate': 1.5401884434667864e-05, 'epoch': 1.33}
|
341 |
+
{'loss': 0.6204, 'learning_rate': 1.5337102844636188e-05, 'epoch': 1.33}
|
342 |
+
{'loss': 0.6315, 'learning_rate': 1.5272240815028067e-05, 'epoch': 1.34}
|
343 |
+
{'loss': 0.6727, 'learning_rate': 1.520730018485832e-05, 'epoch': 1.34}
|
344 |
+
{'loss': 0.6628, 'learning_rate': 1.5142282795370305e-05, 'epoch': 1.35}
|
345 |
+
{'loss': 0.6742, 'learning_rate': 1.5077190489983728e-05, 'epoch': 1.35}
|
346 |
+
{'loss': 0.6381, 'learning_rate': 1.5012025114242355e-05, 'epoch': 1.36}
|
347 |
+
{'loss': 0.6467, 'learning_rate': 1.49467885157617e-05, 'epoch': 1.36}
|
348 |
+
{'loss': 0.6497, 'learning_rate': 1.4881482544176627e-05, 'epoch': 1.37}
|
349 |
+
{'loss': 0.6165, 'learning_rate': 1.4816109051088931e-05, 'epoch': 1.37}
|
350 |
+
{'loss': 0.6183, 'learning_rate': 1.4750669890014807e-05, 'epoch': 1.38}
|
351 |
+
{'loss': 0.6557, 'learning_rate': 1.468516691633233e-05, 'epoch': 1.38}
|
352 |
+
{'loss': 0.6581, 'learning_rate': 1.4619601987228832e-05, 'epoch': 1.39}
|
353 |
+
{'loss': 0.6562, 'learning_rate': 1.4553976961648244e-05, 'epoch': 1.39}
|
354 |
+
{'loss': 0.6587, 'learning_rate': 1.4488293700238401e-05, 'epoch': 1.4}
|
355 |
+
{'loss': 0.6124, 'learning_rate': 1.4422554065298286e-05, 'epoch': 1.4}
|
356 |
+
{'loss': 0.6168, 'learning_rate': 1.435675992072521e-05, 'epoch': 1.41}
|
357 |
+
{'loss': 0.6346, 'learning_rate': 1.4290913131961997e-05, 'epoch': 1.41}
|
358 |
+
{'loss': 0.6851, 'learning_rate': 1.4225015565944072e-05, 'epoch': 1.42}
|
359 |
+
{'loss': 0.652, 'learning_rate': 1.4159069091046526e-05, 'epoch': 1.42}
|
360 |
+
{'loss': 0.6331, 'learning_rate': 1.4093075577031157e-05, 'epoch': 1.43}
|
361 |
+
{'loss': 0.6402, 'learning_rate': 1.4027036894993442e-05, 'epoch': 1.43}
|
362 |
+
{'loss': 0.6072, 'learning_rate': 1.396095491730951e-05, 'epoch': 1.44}
|
363 |
+
{'loss': 0.6314, 'learning_rate': 1.3894831517583017e-05, 'epoch': 1.44}
|
364 |
+
{'loss': 0.5981, 'learning_rate': 1.3828668570592069e-05, 'epoch': 1.45}
|
365 |
+
{'loss': 0.6045, 'learning_rate': 1.3762467952236027e-05, 'epoch': 1.45}
|
366 |
+
{'loss': 0.6773, 'learning_rate': 1.369623153948235e-05, 'epoch': 1.46}
|
367 |
+
{'loss': 0.6185, 'learning_rate': 1.3629961210313353e-05, 'epoch': 1.46}
|
368 |
+
{'loss': 0.6684, 'learning_rate': 1.3563658843672985e-05, 'epoch': 1.47}
|
369 |
+
{'loss': 0.5952, 'learning_rate': 1.3497326319413539e-05, 'epoch': 1.47}
|
370 |
+
{'loss': 0.6146, 'learning_rate': 1.3430965518242362e-05, 'epoch': 1.48}
|
371 |
+
{'loss': 0.6532, 'learning_rate': 1.336457832166852e-05, 'epoch': 1.48}
|
372 |
+
{'loss': 0.6521, 'learning_rate': 1.3298166611949467e-05, 'epoch': 1.49}
|
373 |
+
{'loss': 0.6157, 'learning_rate': 1.3231732272037672e-05, 'epoch': 1.49}
|
374 |
+
{'loss': 0.6474, 'learning_rate': 1.3165277185527234e-05, 'epoch': 1.5}
|
375 |
+
{'loss': 0.5977, 'learning_rate': 1.3098803236600462e-05, 'epoch': 1.5}
|
376 |
+
{'loss': 0.624, 'learning_rate': 1.3032312309974482e-05, 'epoch': 1.51}
|
377 |
+
{'loss': 0.6255, 'learning_rate': 1.2965806290847768e-05, 'epoch': 1.51}
|
378 |
+
{'loss': 0.6181, 'learning_rate': 1.2899287064846725e-05, 'epoch': 1.52}
|
379 |
+
{'loss': 0.6159, 'learning_rate': 1.2832756517972185e-05, 'epoch': 1.52}
|
380 |
+
{'loss': 0.6414, 'learning_rate': 1.2766216536545984e-05, 'epoch': 1.53}
|
381 |
+
{'loss': 0.5773, 'learning_rate': 1.2699669007157435e-05, 'epoch': 1.53}
|
382 |
+
{'loss': 0.627, 'learning_rate': 1.2633115816609867e-05, 'epoch': 1.54}
|
383 |
+
{'loss': 0.5812, 'learning_rate': 1.2566558851867106e-05, 'epoch': 1.54}
|
384 |
+
{'loss': 0.6219, 'learning_rate': 1.25e-05, 'epoch': 1.54}
|
385 |
+
{'loss': 0.6287, 'learning_rate': 1.2433441148132897e-05, 'epoch': 1.55}
|
386 |
+
{'loss': 0.5863, 'learning_rate': 1.236688418339014e-05, 'epoch': 1.55}
|
387 |
+
{'loss': 0.5904, 'learning_rate': 1.2300330992842566e-05, 'epoch': 1.56}
|
388 |
+
{'loss': 0.6398, 'learning_rate': 1.223378346345402e-05, 'epoch': 1.56}
|
389 |
+
{'loss': 0.6025, 'learning_rate': 1.2167243482027816e-05, 'epoch': 1.57}
|
390 |
+
{'loss': 0.6047, 'learning_rate': 1.2100712935153283e-05, 'epoch': 1.57}
|
391 |
+
{'loss': 0.6134, 'learning_rate': 1.2034193709152231e-05, 'epoch': 1.58}
|
392 |
+
{'loss': 0.6624, 'learning_rate': 1.196768769002552e-05, 'epoch': 1.58}
|
393 |
+
{'loss': 0.6065, 'learning_rate': 1.190119676339954e-05, 'epoch': 1.59}
|
394 |
+
{'loss': 0.6245, 'learning_rate': 1.1834722814472771e-05, 'epoch': 1.59}
|
395 |
+
{'loss': 0.6223, 'learning_rate': 1.1768267727962328e-05, 'epoch': 1.6}
|
396 |
+
{'loss': 0.638, 'learning_rate': 1.1701833388050536e-05, 'epoch': 1.6}
|
397 |
+
{'loss': 0.6685, 'learning_rate': 1.1635421678331485e-05, 'epoch': 1.61}
|
398 |
+
{'loss': 0.6236, 'learning_rate': 1.1569034481757644e-05, 'epoch': 1.61}
|
399 |
+
{'loss': 0.6174, 'learning_rate': 1.150267368058646e-05, 'epoch': 1.62}
|
400 |
+
{'loss': 0.6431, 'learning_rate': 1.1436341156327016e-05, 'epoch': 1.62}
|
401 |
+
{'loss': 0.6326, 'learning_rate': 1.137003878968665e-05, 'epoch': 1.63}
|
402 |
+
{'loss': 0.6585, 'learning_rate': 1.1303768460517657e-05, 'epoch': 1.63}
|
403 |
+
{'loss': 0.653, 'learning_rate': 1.1237532047763974e-05, 'epoch': 1.64}
|
404 |
+
{'loss': 0.6169, 'learning_rate': 1.1171331429407934e-05, 'epoch': 1.64}
|
405 |
+
{'loss': 0.5823, 'learning_rate': 1.1105168482416984e-05, 'epoch': 1.65}
|
406 |
+
{'loss': 0.6307, 'learning_rate': 1.1039045082690496e-05, 'epoch': 1.65}
|
407 |
+
{'loss': 0.6119, 'learning_rate': 1.0972963105006556e-05, 'epoch': 1.66}
|
408 |
+
{'loss': 0.6236, 'learning_rate': 1.0906924422968846e-05, 'epoch': 1.66}
|
409 |
+
{'loss': 0.5794, 'learning_rate': 1.0840930908953477e-05, 'epoch': 1.67}
|
410 |
+
{'loss': 0.6227, 'learning_rate': 1.0774984434055932e-05, 'epoch': 1.67}
|
411 |
+
{'loss': 0.6367, 'learning_rate': 1.0709086868038005e-05, 'epoch': 1.68}
|
412 |
+
{'loss': 0.6325, 'learning_rate': 1.064324007927479e-05, 'epoch': 1.68}
|
413 |
+
{'loss': 0.6073, 'learning_rate': 1.0577445934701717e-05, 'epoch': 1.69}
|
414 |
+
{'loss': 0.6616, 'learning_rate': 1.0511706299761602e-05, 'epoch': 1.69}
|
415 |
+
{'loss': 0.6514, 'learning_rate': 1.044602303835176e-05, 'epoch': 1.7}
|
416 |
+
{'loss': 0.6421, 'learning_rate': 1.0380398012771169e-05, 'epoch': 1.7}
|
417 |
+
{'loss': 0.6286, 'learning_rate': 1.0314833083667672e-05, 'epoch': 1.71}
|
418 |
+
{'loss': 0.6372, 'learning_rate': 1.0249330109985198e-05, 'epoch': 1.71}
|
419 |
+
{'loss': 0.6379, 'learning_rate': 1.0183890948911074e-05, 'epoch': 1.72}
|
420 |
+
{'loss': 0.6726, 'learning_rate': 1.0118517455823374e-05, 'epoch': 1.72}
|
421 |
+
{'loss': 0.6715, 'learning_rate': 1.0053211484238303e-05, 'epoch': 1.73}
|
422 |
+
{'loss': 0.6376, 'learning_rate': 9.987974885757647e-06, 'epoch': 1.73}
|
423 |
+
{'loss': 0.6052, 'learning_rate': 9.922809510016277e-06, 'epoch': 1.74}
|
424 |
+
{'loss': 0.6083, 'learning_rate': 9.857717204629696e-06, 'epoch': 1.74}
|
425 |
+
{'loss': 0.6343, 'learning_rate': 9.792699815141685e-06, 'epoch': 1.75}
|
426 |
+
{'loss': 0.631, 'learning_rate': 9.727759184971936e-06, 'epoch': 1.75}
|
427 |
+
{'loss': 0.6598, 'learning_rate': 9.662897155363814e-06, 'epoch': 1.76}
|
428 |
+
{'loss': 0.6396, 'learning_rate': 9.598115565332142e-06, 'epoch': 1.76}
|
429 |
+
{'loss': 0.6778, 'learning_rate': 9.533416251611064e-06, 'epoch': 1.77}
|
430 |
+
{'loss': 0.6252, 'learning_rate': 9.468801048601972e-06, 'epoch': 1.77}
|
431 |
+
{'loss': 0.6119, 'learning_rate': 9.404271788321482e-06, 'epoch': 1.78}
|
432 |
+
{'loss': 0.6523, 'learning_rate': 9.339830300349498e-06, 'epoch': 1.78}
|
433 |
+
{'loss': 0.6336, 'learning_rate': 9.275478411777354e-06, 'epoch': 1.79}
|
434 |
+
{'loss': 0.592, 'learning_rate': 9.211217947155986e-06, 'epoch': 1.79}
|
435 |
+
{'loss': 0.6204, 'learning_rate': 9.147050728444215e-06, 'epoch': 1.8}
|
436 |
+
{'loss': 0.6273, 'learning_rate': 9.08297857495709e-06, 'epoch': 1.8}
|
437 |
+
{'loss': 0.5883, 'learning_rate': 9.0190033033143e-06, 'epoch': 1.81}
|
438 |
+
{'loss': 0.6282, 'learning_rate': 8.955126727388672e-06, 'epoch': 1.81}
|
439 |
+
{'loss': 0.6745, 'learning_rate': 8.89135065825474e-06, 'epoch': 1.82}
|
440 |
+
{'loss': 0.6146, 'learning_rate': 8.827676904137397e-06, 'epoch': 1.82}
|
441 |
+
{'loss': 0.5944, 'learning_rate': 8.76410727036062e-06, 'epoch': 1.83}
|
442 |
+
{'loss': 0.6359, 'learning_rate': 8.700643559296313e-06, 'epoch': 1.83}
|
443 |
+
{'loss': 0.5846, 'learning_rate': 8.637287570313159e-06, 'epoch': 1.84}
|
444 |
+
{'loss': 0.6315, 'learning_rate': 8.574041099725644e-06, 'epoch': 1.84}
|
445 |
+
{'loss': 0.5993, 'learning_rate': 8.510905940743093e-06, 'epoch': 1.85}
|
446 |
+
{'loss': 0.652, 'learning_rate': 8.447883883418866e-06, 'epoch': 1.85}
|
447 |
+
{'loss': 0.6542, 'learning_rate': 8.38497671459957e-06, 'epoch': 1.85}
|
448 |
+
{'loss': 0.6168, 'learning_rate': 8.32218621787441e-06, 'epoch': 1.86}
|
449 |
+
{'loss': 0.632, 'learning_rate': 8.25951417352462e-06, 'epoch': 1.86}
|
450 |
+
{'loss': 0.6016, 'learning_rate': 8.196962358473e-06, 'epoch': 1.87}
|
451 |
+
{'loss': 0.5967, 'learning_rate': 8.134532546233505e-06, 'epoch': 1.87}
|
452 |
+
{'loss': 0.6398, 'learning_rate': 8.072226506860988e-06, 'epoch': 1.88}
|
453 |
+
{'loss': 0.6485, 'learning_rate': 8.010046006901001e-06, 'epoch': 1.88}
|
454 |
+
{'loss': 0.588, 'learning_rate': 7.947992809339723e-06, 'epoch': 1.89}
|
455 |
+
{'loss': 0.6784, 'learning_rate': 7.88606867355395e-06, 'epoch': 1.89}
|
456 |
+
{'loss': 0.6223, 'learning_rate': 7.824275355261233e-06, 'epoch': 1.9}
|
457 |
+
{'loss': 0.5966, 'learning_rate': 7.762614606470084e-06, 'epoch': 1.9}
|
458 |
+
{'loss': 0.6124, 'learning_rate': 7.701088175430327e-06, 'epoch': 1.91}
|
459 |
+
{'loss': 0.637, 'learning_rate': 7.639697806583493e-06, 'epoch': 1.91}
|
460 |
+
{'loss': 0.6198, 'learning_rate': 7.578445240513393e-06, 'epoch': 1.92}
|
461 |
+
{'loss': 0.6397, 'learning_rate': 7.517332213896743e-06, 'epoch': 1.92}
|
462 |
+
{'loss': 0.6308, 'learning_rate': 7.456360459453952e-06, 'epoch': 1.93}
|
463 |
+
{'loss': 0.5814, 'learning_rate': 7.395531705899969e-06, 'epoch': 1.93}
|
464 |
+
{'loss': 0.5953, 'learning_rate': 7.334847677895276e-06, 'epoch': 1.94}
|
465 |
+
{'loss': 0.6071, 'learning_rate': 7.274310095997e-06, 'epoch': 1.94}
|
466 |
+
{'loss': 0.6304, 'learning_rate': 7.213920676610112e-06, 'epoch': 1.95}
|
467 |
+
{'loss': 0.6411, 'learning_rate': 7.153681131938791e-06, 'epoch': 1.95}
|
468 |
+
{'loss': 0.6012, 'learning_rate': 7.093593169937849e-06, 'epoch': 1.96}
|
469 |
+
{'loss': 0.6503, 'learning_rate': 7.033658494264309e-06, 'epoch': 1.96}
|
470 |
+
{'loss': 0.6363, 'learning_rate': 6.973878804229131e-06, 'epoch': 1.97}
|
471 |
+
{'loss': 0.6212, 'learning_rate': 6.914255794748989e-06, 'epoch': 1.97}
|
472 |
+
{'loss': 0.6694, 'learning_rate': 6.8547911562982595e-06, 'epoch': 1.98}
|
473 |
+
{'loss': 0.6147, 'learning_rate': 6.7954865748610515e-06, 'epoch': 1.98}
|
474 |
+
{'loss': 0.6615, 'learning_rate': 6.736343731883425e-06, 'epoch': 1.99}
|
475 |
+
{'loss': 0.602, 'learning_rate': 6.677364304225731e-06, 'epoch': 1.99}
|
476 |
+
{'loss': 0.604, 'learning_rate': 6.618549964115033e-06, 'epoch': 2.0}
|
477 |
+
{'loss': 0.4458, 'learning_rate': 6.559902379097721e-06, 'epoch': 2.0}
|
478 |
+
{'loss': 0.3383, 'learning_rate': 6.501423211992224e-06, 'epoch': 2.01}
|
479 |
+
{'loss': 0.3288, 'learning_rate': 6.443114120841874e-06, 'epoch': 2.01}
|
480 |
+
{'loss': 0.3252, 'learning_rate': 6.384976758867875e-06, 'epoch': 2.02}
|
481 |
+
{'loss': 0.3226, 'learning_rate': 6.32701277442245e-06, 'epoch': 2.02}
|
482 |
+
{'loss': 0.3122, 'learning_rate': 6.269223810942086e-06, 'epoch': 2.03}
|
483 |
+
{'loss': 0.2519, 'learning_rate': 6.211611506900973e-06, 'epoch': 2.03}
|
484 |
+
{'loss': 0.3158, 'learning_rate': 6.1541774957645045e-06, 'epoch': 2.04}
|
485 |
+
{'loss': 0.2846, 'learning_rate': 6.096923405942989e-06, 'epoch': 2.04}
|
486 |
+
{'loss': 0.2747, 'learning_rate': 6.03985086074549e-06, 'epoch': 2.05}
|
487 |
+
{'loss': 0.2876, 'learning_rate': 5.982961478333768e-06, 'epoch': 2.05}
|
488 |
+
{'loss': 0.2596, 'learning_rate': 5.926256871676443e-06, 'epoch': 2.06}
|
489 |
+
{'loss': 0.28, 'learning_rate': 5.86973864850322e-06, 'epoch': 2.06}
|
490 |
+
{'loss': 0.2694, 'learning_rate': 5.813408411259331e-06, 'epoch': 2.07}
|
491 |
+
{'loss': 0.2707, 'learning_rate': 5.757267757060109e-06, 'epoch': 2.07}
|
492 |
+
{'loss': 0.2814, 'learning_rate': 5.701318277645675e-06, 'epoch': 2.08}
|
493 |
+
{'loss': 0.2916, 'learning_rate': 5.645561559335832e-06, 'epoch': 2.08}
|
494 |
+
{'loss': 0.3062, 'learning_rate': 5.589999182985087e-06, 'epoch': 2.09}
|
495 |
+
{'loss': 0.2818, 'learning_rate': 5.534632723937809e-06, 'epoch': 2.09}
|
496 |
+
{'loss': 0.263, 'learning_rate': 5.479463751983603e-06, 'epoch': 2.1}
|
497 |
+
{'loss': 0.2992, 'learning_rate': 5.424493831312757e-06, 'epoch': 2.1}
|
498 |
+
{'loss': 0.2966, 'learning_rate': 5.369724520471925e-06, 'epoch': 2.11}
|
499 |
+
{'loss': 0.2803, 'learning_rate': 5.315157372319915e-06, 'epoch': 2.11}
|
500 |
+
{'loss': 0.2749, 'learning_rate': 5.2607939339836945e-06, 'epoch': 2.12}
|
501 |
+
{'loss': 0.2728, 'learning_rate': 5.2066357468144824e-06, 'epoch': 2.12}
|
502 |
+
{'loss': 0.2545, 'learning_rate': 5.152684346344087e-06, 'epoch': 2.13}
|
503 |
+
{'loss': 0.2722, 'learning_rate': 5.0989412622413345e-06, 'epoch': 2.13}
|
504 |
+
{'loss': 0.3021, 'learning_rate': 5.0454080182687314e-06, 'epoch': 2.14}
|
505 |
+
{'loss': 0.2483, 'learning_rate': 4.992086132239238e-06, 'epoch': 2.14}
|
506 |
+
{'loss': 0.2703, 'learning_rate': 4.938977115973242e-06, 'epoch': 2.15}
|
507 |
+
{'loss': 0.2829, 'learning_rate': 4.886082475255694e-06, 'epoch': 2.15}
|
508 |
+
{'loss': 0.2634, 'learning_rate': 4.833403709793424e-06, 'epoch': 2.15}
|
509 |
+
{'loss': 0.2684, 'learning_rate': 4.780942313172602e-06, 'epoch': 2.16}
|
510 |
+
{'loss': 0.3123, 'learning_rate': 4.728699772816407e-06, 'epoch': 2.16}
|
511 |
+
{'loss': 0.2837, 'learning_rate': 4.6766775699428365e-06, 'epoch': 2.17}
|
512 |
+
{'loss': 0.2915, 'learning_rate': 4.624877179522742e-06, 'epoch': 2.17}
|
513 |
+
{'loss': 0.305, 'learning_rate': 4.573300070237973e-06, 'epoch': 2.18}
|
514 |
+
{'loss': 0.2537, 'learning_rate': 4.5219477044397525e-06, 'epoch': 2.18}
|
515 |
+
{'loss': 0.2782, 'learning_rate': 4.470821538107219e-06, 'epoch': 2.19}
|
516 |
+
{'loss': 0.3202, 'learning_rate': 4.419923020806148e-06, 'epoch': 2.19}
|
517 |
+
{'loss': 0.2547, 'learning_rate': 4.36925359564783e-06, 'epoch': 2.2}
|
518 |
+
{'loss': 0.2707, 'learning_rate': 4.318814699248188e-06, 'epoch': 2.2}
|
519 |
+
{'loss': 0.246, 'learning_rate': 4.268607761687019e-06, 'epoch': 2.21}
|
520 |
+
{'loss': 0.2737, 'learning_rate': 4.218634206467449e-06, 'epoch': 2.21}
|
521 |
+
{'loss': 0.2921, 'learning_rate': 4.1688954504756e-06, 'epoch': 2.22}
|
522 |
+
{'loss': 0.2677, 'learning_rate': 4.119392903940384e-06, 'epoch': 2.22}
|
523 |
+
{'loss': 0.2979, 'learning_rate': 4.07012797039353e-06, 'epoch': 2.23}
|
524 |
+
{'loss': 0.2459, 'learning_rate': 4.021102046629799e-06, 'epoch': 2.23}
|
525 |
+
{'loss': 0.2745, 'learning_rate': 3.972316522667381e-06, 'epoch': 2.24}
|
526 |
+
{'loss': 0.2943, 'learning_rate': 3.923772781708468e-06, 'epoch': 2.24}
|
527 |
+
{'loss': 0.2403, 'learning_rate': 3.875472200100051e-06, 'epoch': 2.25}
|
528 |
+
{'loss': 0.2781, 'learning_rate': 3.827416147294888e-06, 'epoch': 2.25}
|
529 |
+
{'loss': 0.2766, 'learning_rate': 3.7796059858126927e-06, 'epoch': 2.26}
|
530 |
+
{'loss': 0.2738, 'learning_rate': 3.7320430712014796e-06, 'epoch': 2.26}
|
531 |
+
{'loss': 0.3136, 'learning_rate': 3.6847287519991434e-06, 'epoch': 2.27}
|
532 |
+
{'loss': 0.2902, 'learning_rate': 3.637664369695233e-06, 'epoch': 2.27}
|
533 |
+
{'loss': 0.2516, 'learning_rate': 3.590851258692894e-06, 'epoch': 2.28}
|
534 |
+
{'loss': 0.2668, 'learning_rate': 3.5442907462710605e-06, 'epoch': 2.28}
|
535 |
+
{'loss': 0.2789, 'learning_rate': 3.4979841525468016e-06, 'epoch': 2.29}
|
536 |
+
{'loss': 0.2794, 'learning_rate': 3.451932790437898e-06, 'epoch': 2.29}
|
537 |
+
{'loss': 0.273, 'learning_rate': 3.4061379656256345e-06, 'epoch': 2.3}
|
538 |
+
{'loss': 0.2828, 'learning_rate': 3.3606009765177555e-06, 'epoch': 2.3}
|
539 |
+
{'loss': 0.2836, 'learning_rate': 3.3153231142116617e-06, 'epoch': 2.31}
|
540 |
+
{'loss': 0.2781, 'learning_rate': 3.270305662457805e-06, 'epoch': 2.31}
|
541 |
+
{'loss': 0.2911, 'learning_rate': 3.225549897623302e-06, 'epoch': 2.32}
|
542 |
+
{'loss': 0.3071, 'learning_rate': 3.181057088655719e-06, 'epoch': 2.32}
|
543 |
+
{'loss': 0.2583, 'learning_rate': 3.136828497047116e-06, 'epoch': 2.33}
|
544 |
+
{'loss': 0.2976, 'learning_rate': 3.0928653767982695e-06, 'epoch': 2.33}
|
545 |
+
{'loss': 0.2727, 'learning_rate': 3.0491689743831277e-06, 'epoch': 2.34}
|
546 |
+
{'loss': 0.2843, 'learning_rate': 3.005740528713458e-06, 'epoch': 2.34}
|
547 |
+
{'loss': 0.2655, 'learning_rate': 2.9625812711037206e-06, 'epoch': 2.35}
|
548 |
+
{'loss': 0.2759, 'learning_rate': 2.91969242523618e-06, 'epoch': 2.35}
|
549 |
+
{'loss': 0.272, 'learning_rate': 2.87707520712617e-06, 'epoch': 2.36}
|
550 |
+
{'loss': 0.2734, 'learning_rate': 2.834730825087663e-06, 'epoch': 2.36}
|
551 |
+
{'loss': 0.312, 'learning_rate': 2.7926604796989676e-06, 'epoch': 2.37}
|
552 |
+
{'loss': 0.2608, 'learning_rate': 2.7508653637687176e-06, 'epoch': 2.37}
|
553 |
+
{'loss': 0.3084, 'learning_rate': 2.709346662302041e-06, 'epoch': 2.38}
|
554 |
+
{'loss': 0.3209, 'learning_rate': 2.6681055524669694e-06, 'epoch': 2.38}
|
555 |
+
{'loss': 0.2781, 'learning_rate': 2.6271432035610513e-06, 'epoch': 2.39}
|
556 |
+
{'loss': 0.2379, 'learning_rate': 2.5864607769782084e-06, 'epoch': 2.39}
|
557 |
+
{'loss': 0.2945, 'learning_rate': 2.5460594261757996e-06, 'epoch': 2.4}
|
558 |
+
{'loss': 0.2545, 'learning_rate': 2.5059402966419303e-06, 'epoch': 2.4}
|
559 |
+
{'loss': 0.285, 'learning_rate': 2.466104525862957e-06, 'epoch': 2.41}
|
560 |
+
{'loss': 0.2818, 'learning_rate': 2.426553243291249e-06, 'epoch': 2.41}
|
561 |
+
{'loss': 0.2743, 'learning_rate': 2.3872875703131583e-06, 'epoch': 2.42}
|
562 |
+
{'loss': 0.2991, 'learning_rate': 2.3483086202172377e-06, 'epoch': 2.42}
|
563 |
+
{'loss': 0.2778, 'learning_rate': 2.309617498162657e-06, 'epoch': 2.43}
|
564 |
+
{'loss': 0.2723, 'learning_rate': 2.271215301147887e-06, 'epoch': 2.43}
|
565 |
+
{'loss': 0.2684, 'learning_rate': 2.2331031179795792e-06, 'epoch': 2.44}
|
566 |
+
{'loss': 0.2818, 'learning_rate': 2.1952820292417143e-06, 'epoch': 2.44}
|
567 |
+
{'loss': 0.2658, 'learning_rate': 2.1577531072649495e-06, 'epoch': 2.45}
|
568 |
+
{'loss': 0.2865, 'learning_rate': 2.120517416096217e-06, 'epoch': 2.45}
|
569 |
+
{'loss': 0.2744, 'learning_rate': 2.083576011468562e-06, 'epoch': 2.46}
|
570 |
+
{'loss': 0.2939, 'learning_rate': 2.0469299407712112e-06, 'epoch': 2.46}
|
571 |
+
{'loss': 0.3174, 'learning_rate': 2.010580243019865e-06, 'epoch': 2.46}
|
572 |
+
{'loss': 0.2805, 'learning_rate': 1.9745279488272484e-06, 'epoch': 2.47}
|
573 |
+
{'loss': 0.2587, 'learning_rate': 1.938774080373884e-06, 'epoch': 2.47}
|
574 |
+
{'loss': 0.2591, 'learning_rate': 1.9033196513791138e-06, 'epoch': 2.48}
|
575 |
+
{'loss': 0.28, 'learning_rate': 1.8681656670723663e-06, 'epoch': 2.48}
|
576 |
+
{'loss': 0.2757, 'learning_rate': 1.833313124164636e-06, 'epoch': 2.49}
|
577 |
+
{'loss': 0.2684, 'learning_rate': 1.7987630108202355e-06, 'epoch': 2.49}
|
578 |
+
{'loss': 0.3003, 'learning_rate': 1.764516306628787e-06, 'epoch': 2.5}
|
579 |
+
{'loss': 0.2826, 'learning_rate': 1.7305739825774228e-06, 'epoch': 2.5}
|
580 |
+
{'loss': 0.2531, 'learning_rate': 1.6969370010232882e-06, 'epoch': 2.51}
|
581 |
+
{'loss': 0.277, 'learning_rate': 1.663606315666226e-06, 'epoch': 2.51}
|
582 |
+
{'loss': 0.2838, 'learning_rate': 1.6305828715217506e-06, 'epoch': 2.52}
|
583 |
+
{'loss': 0.3017, 'learning_rate': 1.597867604894264e-06, 'epoch': 2.52}
|
584 |
+
{'loss': 0.2695, 'learning_rate': 1.5654614433504841e-06, 'epoch': 2.53}
|
585 |
+
{'loss': 0.3005, 'learning_rate': 1.5333653056931684e-06, 'epoch': 2.53}
|
586 |
+
{'loss': 0.259, 'learning_rate': 1.5015801019350476e-06, 'epoch': 2.54}
|
587 |
+
{'loss': 0.276, 'learning_rate': 1.4701067332730426e-06, 'epoch': 2.54}
|
588 |
+
{'loss': 0.2706, 'learning_rate': 1.4389460920626887e-06, 'epoch': 2.55}
|
589 |
+
{'loss': 0.2808, 'learning_rate': 1.4080990617928571e-06, 'epoch': 2.55}
|
590 |
+
{'loss': 0.2925, 'learning_rate': 1.3775665170606896e-06, 'epoch': 2.56}
|
591 |
+
{'loss': 0.2644, 'learning_rate': 1.3473493235468177e-06, 'epoch': 2.56}
|
592 |
+
{'loss': 0.2484, 'learning_rate': 1.3174483379907996e-06, 'epoch': 2.57}
|
593 |
+
{'loss': 0.3012, 'learning_rate': 1.2878644081668403e-06, 'epoch': 2.57}
|
594 |
+
{'loss': 0.3033, 'learning_rate': 1.2585983728597608e-06, 'epoch': 2.58}
|
595 |
+
{'loss': 0.33, 'learning_rate': 1.2296510618411957e-06, 'epoch': 2.58}
|
596 |
+
{'loss': 0.2513, 'learning_rate': 1.201023295846093e-06, 'epoch': 2.59}
|
597 |
+
{'loss': 0.2871, 'learning_rate': 1.1727158865494206e-06, 'epoch': 2.59}
|
598 |
+
{'loss': 0.2592, 'learning_rate': 1.1447296365431668e-06, 'epoch': 2.6}
|
599 |
+
{'loss': 0.2672, 'learning_rate': 1.1170653393135847e-06, 'epoch': 2.6}
|
600 |
+
{'loss': 0.2589, 'learning_rate': 1.0897237792186862e-06, 'epoch': 2.61}
|
601 |
+
{'loss': 0.2851, 'learning_rate': 1.0627057314660114e-06, 'epoch': 2.61}
|
602 |
+
{'loss': 0.2319, 'learning_rate': 1.0360119620906426e-06, 'epoch': 2.62}
|
603 |
+
{'loss': 0.2757, 'learning_rate': 1.0096432279334905e-06, 'epoch': 2.62}
|
604 |
+
{'loss': 0.2742, 'learning_rate': 9.836002766198379e-07, 'epoch': 2.63}
|
605 |
+
{'loss': 0.324, 'learning_rate': 9.57883846538135e-07, 'epoch': 2.63}
|
606 |
+
{'loss': 0.2435, 'learning_rate': 9.324946668190657e-07, 'epoch': 2.64}
|
607 |
+
{'loss': 0.2795, 'learning_rate': 9.074334573148783e-07, 'epoch': 2.64}
|
608 |
+
{'loss': 0.3012, 'learning_rate': 8.827009285789778e-07, 'epoch': 2.65}
|
609 |
+
{'loss': 0.2663, 'learning_rate': 8.582977818457696e-07, 'epoch': 2.65}
|
610 |
+
{'loss': 0.2469, 'learning_rate': 8.342247090107919e-07, 'epoch': 2.66}
|
611 |
+
{'loss': 0.2835, 'learning_rate': 8.104823926110811e-07, 'epoch': 2.66}
|
612 |
+
{'loss': 0.2554, 'learning_rate': 7.870715058058406e-07, 'epoch': 2.67}
|
613 |
+
{'loss': 0.2571, 'learning_rate': 7.639927123573351e-07, 'epoch': 2.67}
|
614 |
+
{'loss': 0.2679, 'learning_rate': 7.412466666120846e-07, 'epoch': 2.68}
|
615 |
+
{'loss': 0.2569, 'learning_rate': 7.188340134823043e-07, 'epoch': 2.68}
|
616 |
+
{'loss': 0.2704, 'learning_rate': 6.967553884276279e-07, 'epoch': 2.69}
|
617 |
+
{'loss': 0.3005, 'learning_rate': 6.750114174370797e-07, 'epoch': 2.69}
|
618 |
+
{'loss': 0.2542, 'learning_rate': 6.536027170113354e-07, 'epoch': 2.7}
|
619 |
+
{'loss': 0.2783, 'learning_rate': 6.32529894145234e-07, 'epoch': 2.7}
|
620 |
+
{'loss': 0.2264, 'learning_rate': 6.117935463105809e-07, 'epoch': 2.71}
|
621 |
+
{'loss': 0.2635, 'learning_rate': 5.913942614391931e-07, 'epoch': 2.71}
|
622 |
+
{'loss': 0.2658, 'learning_rate': 5.713326179062409e-07, 'epoch': 2.72}
|
623 |
+
{'loss': 0.2681, 'learning_rate': 5.516091845138377e-07, 'epoch': 2.72}
|
624 |
+
{'loss': 0.3189, 'learning_rate': 5.322245204749319e-07, 'epoch': 2.73}
|
625 |
+
{'loss': 0.2983, 'learning_rate': 5.131791753974296e-07, 'epoch': 2.73}
|
626 |
+
{'loss': 0.2887, 'learning_rate': 4.944736892686278e-07, 'epoch': 2.74}
|
627 |
+
{'loss': 0.2594, 'learning_rate': 4.761085924398959e-07, 'epoch': 2.74}
|
628 |
+
{'loss': 0.2366, 'learning_rate': 4.580844056116418e-07, 'epoch': 2.75}
|
629 |
+
{'loss': 0.3332, 'learning_rate': 4.4040163981855095e-07, 'epoch': 2.75}
|
630 |
+
{'loss': 0.2593, 'learning_rate': 4.2306079641509094e-07, 'epoch': 2.76}
|
631 |
+
{'loss': 0.2825, 'learning_rate': 4.0606236706130367e-07, 'epoch': 2.76}
|
632 |
+
{'loss': 0.2865, 'learning_rate': 3.89406833708858e-07, 'epoch': 2.77}
|
633 |
+
{'loss': 0.3002, 'learning_rate': 3.73094668587394e-07, 'epoch': 2.77}
|
634 |
+
{'loss': 0.2941, 'learning_rate': 3.5712633419112686e-07, 'epoch': 2.77}
|
635 |
+
{'loss': 0.3138, 'learning_rate': 3.4150228326573356e-07, 'epoch': 2.78}
|
636 |
+
{'loss': 0.3054, 'learning_rate': 3.262229587955232e-07, 'epoch': 2.78}
|
637 |
+
{'loss': 0.2502, 'learning_rate': 3.112887939908715e-07, 'epoch': 2.79}
|
638 |
+
{'loss': 0.2679, 'learning_rate': 2.9670021227593965e-07, 'epoch': 2.79}
|
639 |
+
{'loss': 0.2683, 'learning_rate': 2.824576272766666e-07, 'epoch': 2.8}
|
640 |
+
{'loss': 0.3101, 'learning_rate': 2.6856144280904967e-07, 'epoch': 2.8}
|
641 |
+
{'loss': 0.2749, 'learning_rate': 2.550120528676841e-07, 'epoch': 2.81}
|
642 |
+
{'loss': 0.2455, 'learning_rate': 2.4180984161460004e-07, 'epoch': 2.81}
|
643 |
+
{'loss': 0.2607, 'learning_rate': 2.2895518336836923e-07, 'epoch': 2.82}
|
644 |
+
{'loss': 0.2729, 'learning_rate': 2.164484425934879e-07, 'epoch': 2.82}
|
645 |
+
{'loss': 0.2669, 'learning_rate': 2.0428997389004972e-07, 'epoch': 2.83}
|
646 |
+
{'loss': 0.3026, 'learning_rate': 1.9248012198368748e-07, 'epoch': 2.83}
|
647 |
+
{'loss': 0.2394, 'learning_rate': 1.8101922171580022e-07, 'epoch': 2.84}
|
648 |
+
{'loss': 0.2578, 'learning_rate': 1.699075980340581e-07, 'epoch': 2.84}
|
649 |
+
{'loss': 0.252, 'learning_rate': 1.5914556598319307e-07, 'epoch': 2.85}
|
650 |
+
{'loss': 0.2478, 'learning_rate': 1.4873343069606305e-07, 'epoch': 2.85}
|
651 |
+
{'loss': 0.3517, 'learning_rate': 1.3867148738500313e-07, 'epoch': 2.86}
|
652 |
+
{'loss': 0.285, 'learning_rate': 1.289600213334505e-07, 'epoch': 2.86}
|
653 |
+
{'loss': 0.2673, 'learning_rate': 1.195993078878646e-07, 'epoch': 2.87}
|
654 |
+
{'loss': 0.2644, 'learning_rate': 1.1058961244991144e-07, 'epoch': 2.87}
|
655 |
+
{'loss': 0.2689, 'learning_rate': 1.0193119046894295e-07, 'epoch': 2.88}
|
656 |
+
{'loss': 0.2699, 'learning_rate': 9.362428743475565e-08, 'epoch': 2.88}
|
657 |
+
{'loss': 0.2677, 'learning_rate': 8.566913887062683e-08, 'epoch': 2.89}
|
658 |
+
{'loss': 0.2846, 'learning_rate': 7.806597032663925e-08, 'epoch': 2.89}
|
659 |
+
{'loss': 0.2686, 'learning_rate': 7.081499737328634e-08, 'epoch': 2.9}
|
660 |
+
{'loss': 0.2542, 'learning_rate': 6.391642559535616e-08, 'epoch': 2.9}
|
661 |
+
{'loss': 0.2678, 'learning_rate': 5.7370450586109737e-08, 'epoch': 2.91}
|
662 |
+
{'loss': 0.237, 'learning_rate': 5.117725794172995e-08, 'epoch': 2.91}
|
663 |
+
{'loss': 0.2847, 'learning_rate': 4.533702325605904e-08, 'epoch': 2.92}
|
664 |
+
{'loss': 0.2397, 'learning_rate': 3.9849912115623446e-08, 'epoch': 2.92}
|
665 |
+
{'loss': 0.2672, 'learning_rate': 3.471608009493754e-08, 'epoch': 2.93}
|
666 |
+
{'loss': 0.2767, 'learning_rate': 2.9935672752090525e-08, 'epoch': 2.93}
|
667 |
+
{'loss': 0.2758, 'learning_rate': 2.5508825624626088e-08, 'epoch': 2.94}
|
668 |
+
{'loss': 0.2576, 'learning_rate': 2.1435664225688547e-08, 'epoch': 2.94}
|
669 |
+
{'loss': 0.3037, 'learning_rate': 1.7716304040475697e-08, 'epoch': 2.95}
|
670 |
+
{'loss': 0.271, 'learning_rate': 1.4350850522956705e-08, 'epoch': 2.95}
|
671 |
+
{'loss': 0.2347, 'learning_rate': 1.1339399092885616e-08, 'epoch': 2.96}
|
672 |
+
{'loss': 0.2924, 'learning_rate': 8.682035133096566e-09, 'epoch': 2.96}
|
673 |
+
{'loss': 0.2847, 'learning_rate': 6.378833987077948e-09, 'epoch': 2.97}
|
674 |
+
{'loss': 0.2594, 'learning_rate': 4.429860956842169e-09, 'epoch': 2.97}
|
675 |
+
{'loss': 0.2613, 'learning_rate': 2.8351713010743573e-09, 'epoch': 2.98}
|
676 |
+
{'loss': 0.2603, 'learning_rate': 1.5948102335572313e-09, 'epoch': 2.98}
|
677 |
+
{'loss': 0.2915, 'learning_rate': 7.088129218985052e-10, 'epoch': 2.99}
|
678 |
+
{'loss': 0.2903, 'learning_rate': 1.772044865316902e-10, 'epoch': 2.99}
|
679 |
+
{'loss': 0.2426, 'learning_rate': 0.0, 'epoch': 3.0}
|
680 |
+
{'train_runtime': 5691.3236, 'train_samples_per_second': 27.41, 'train_steps_per_second': 0.107, 'train_loss': 0.6601732866517429, 'epoch': 3.0}
|
681 |
+
[2024-01-10 05:17:55,050] [INFO] [launch.py:347:main] Process 63171 exits successfully.
|
682 |
+
[2024-01-10 05:17:55,050] [INFO] [launch.py:347:main] Process 63167 exits successfully.
|
683 |
+
[2024-01-10 05:17:55,051] [INFO] [launch.py:347:main] Process 63166 exits successfully.
|
684 |
+
[2024-01-10 05:17:56,052] [INFO] [launch.py:347:main] Process 63169 exits successfully.
|
685 |
+
[2024-01-10 05:17:56,052] [INFO] [launch.py:347:main] Process 63168 exits successfully.
|
686 |
+
[2024-01-10 05:17:56,052] [INFO] [launch.py:347:main] Process 63165 exits successfully.
|
687 |
+
[2024-01-10 05:17:56,053] [INFO] [launch.py:347:main] Process 63170 exits successfully.
|
688 |
+
Finish training...
|
689 |
+
[2024-01-10 05:18:11,068] [INFO] [launch.py:347:main] Process 63164 exits successfully.
|