Osamarafique998
commited on
Commit
•
254e382
1
Parent(s):
8ce5c6a
Upload folder using huggingface_hub
Browse files- config.json +23 -0
- generation_config.json +7 -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 +330 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
- trainer_state.json +3016 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Devden/DialectAI-Vicuna-7B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.28.1",
|
21 |
+
"use_cache": false,
|
22 |
+
"vocab_size": 32000
|
23 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e8c46725b83f1a902a194b81fcb74da2b4fb3feca4dc6e0c84a90684ced29f5
|
3 |
+
size 9877993490
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e63e4e0f859906d040f35a9476760f72dd5f03324e98733d5e867d31b6d24d0f
|
3 |
+
size 9894805046
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa3cdb72bf689eb1d46431fd78a1d62ad4fc71ad3e93d42e0406c0ccc3ae757b
|
3 |
+
size 7180993529
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26953670656
|
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.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
329 |
+
}
|
330 |
+
}
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
|
3 |
+
size 14583
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
|
3 |
+
size 14583
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
|
3 |
+
size 14583
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
|
3 |
+
size 14583
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
|
3 |
+
size 557
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb2224823d3ab368867dc23cefb65658f627c811f1f24a4bfd52646ef5afbf5e
|
3 |
+
size 627
|
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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"model_max_length": 2048,
|
22 |
+
"pad_token": null,
|
23 |
+
"padding_side": "right",
|
24 |
+
"sp_model_kwargs": {},
|
25 |
+
"tokenizer_class": "LlamaTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3016 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.19707831399502376,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.0509721492380452e-08,
|
13 |
+
"loss": 1.1226,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.0,
|
18 |
+
"learning_rate": 2.1019442984760905e-08,
|
19 |
+
"loss": 1.035,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.0,
|
24 |
+
"learning_rate": 3.152916447714136e-08,
|
25 |
+
"loss": 1.0924,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.0,
|
30 |
+
"learning_rate": 4.203888596952181e-08,
|
31 |
+
"loss": 1.0726,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.0,
|
36 |
+
"learning_rate": 5.2548607461902266e-08,
|
37 |
+
"loss": 1.1055,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0,
|
42 |
+
"learning_rate": 6.305832895428272e-08,
|
43 |
+
"loss": 1.1069,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0,
|
48 |
+
"learning_rate": 7.356805044666317e-08,
|
49 |
+
"loss": 1.1214,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.0,
|
54 |
+
"learning_rate": 8.407777193904362e-08,
|
55 |
+
"loss": 1.0352,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.0,
|
60 |
+
"learning_rate": 9.458749343142408e-08,
|
61 |
+
"loss": 1.0834,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.0,
|
66 |
+
"learning_rate": 1.0509721492380453e-07,
|
67 |
+
"loss": 1.0943,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.0,
|
72 |
+
"learning_rate": 1.1560693641618497e-07,
|
73 |
+
"loss": 1.0665,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.0,
|
78 |
+
"learning_rate": 1.2611665790856543e-07,
|
79 |
+
"loss": 1.038,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.01,
|
84 |
+
"learning_rate": 1.3662637940094587e-07,
|
85 |
+
"loss": 1.0735,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"learning_rate": 1.4713610089332634e-07,
|
91 |
+
"loss": 1.1459,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.01,
|
96 |
+
"learning_rate": 1.5764582238570677e-07,
|
97 |
+
"loss": 1.0382,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.01,
|
102 |
+
"learning_rate": 1.6815554387808724e-07,
|
103 |
+
"loss": 1.0474,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.01,
|
108 |
+
"learning_rate": 1.786652653704677e-07,
|
109 |
+
"loss": 1.0968,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.01,
|
114 |
+
"learning_rate": 1.8917498686284816e-07,
|
115 |
+
"loss": 1.0508,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.01,
|
120 |
+
"learning_rate": 1.996847083552286e-07,
|
121 |
+
"loss": 1.0399,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.01,
|
126 |
+
"learning_rate": 2.1019442984760907e-07,
|
127 |
+
"loss": 1.0031,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.01,
|
132 |
+
"learning_rate": 2.2070415133998953e-07,
|
133 |
+
"loss": 0.9566,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.01,
|
138 |
+
"learning_rate": 2.3121387283236994e-07,
|
139 |
+
"loss": 1.0053,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.01,
|
144 |
+
"learning_rate": 2.417235943247504e-07,
|
145 |
+
"loss": 1.0701,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.01,
|
150 |
+
"learning_rate": 2.5223331581713087e-07,
|
151 |
+
"loss": 1.019,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.01,
|
156 |
+
"learning_rate": 2.627430373095113e-07,
|
157 |
+
"loss": 1.0403,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.01,
|
162 |
+
"learning_rate": 2.7325275880189174e-07,
|
163 |
+
"loss": 0.9973,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.01,
|
168 |
+
"learning_rate": 2.837624802942722e-07,
|
169 |
+
"loss": 0.9612,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.01,
|
174 |
+
"learning_rate": 2.9427220178665267e-07,
|
175 |
+
"loss": 0.9842,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.01,
|
180 |
+
"learning_rate": 3.0478192327903313e-07,
|
181 |
+
"loss": 1.01,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.01,
|
186 |
+
"learning_rate": 3.1529164477141355e-07,
|
187 |
+
"loss": 0.9919,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.01,
|
192 |
+
"learning_rate": 3.2580136626379406e-07,
|
193 |
+
"loss": 0.9786,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.01,
|
198 |
+
"learning_rate": 3.3631108775617447e-07,
|
199 |
+
"loss": 0.9469,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.01,
|
204 |
+
"learning_rate": 3.468208092485549e-07,
|
205 |
+
"loss": 0.9505,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.01,
|
210 |
+
"learning_rate": 3.573305307409354e-07,
|
211 |
+
"loss": 0.9357,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.01,
|
216 |
+
"learning_rate": 3.678402522333158e-07,
|
217 |
+
"loss": 1.0086,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.01,
|
222 |
+
"learning_rate": 3.7834997372569633e-07,
|
223 |
+
"loss": 1.0187,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.01,
|
228 |
+
"learning_rate": 3.8885969521807674e-07,
|
229 |
+
"loss": 0.9877,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.01,
|
234 |
+
"learning_rate": 3.993694167104572e-07,
|
235 |
+
"loss": 0.8856,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.02,
|
240 |
+
"learning_rate": 4.0987913820283767e-07,
|
241 |
+
"loss": 0.9854,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.02,
|
246 |
+
"learning_rate": 4.2038885969521813e-07,
|
247 |
+
"loss": 1.0107,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.02,
|
252 |
+
"learning_rate": 4.3089858118759854e-07,
|
253 |
+
"loss": 0.933,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.02,
|
258 |
+
"learning_rate": 4.4140830267997906e-07,
|
259 |
+
"loss": 0.9874,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.02,
|
264 |
+
"learning_rate": 4.5191802417235947e-07,
|
265 |
+
"loss": 0.9812,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.02,
|
270 |
+
"learning_rate": 4.624277456647399e-07,
|
271 |
+
"loss": 0.9467,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.02,
|
276 |
+
"learning_rate": 4.729374671571204e-07,
|
277 |
+
"loss": 0.9949,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.02,
|
282 |
+
"learning_rate": 4.834471886495008e-07,
|
283 |
+
"loss": 1.005,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.02,
|
288 |
+
"learning_rate": 4.939569101418812e-07,
|
289 |
+
"loss": 0.935,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.02,
|
294 |
+
"learning_rate": 5.044666316342617e-07,
|
295 |
+
"loss": 0.9481,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.02,
|
300 |
+
"learning_rate": 5.149763531266421e-07,
|
301 |
+
"loss": 0.9681,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.02,
|
306 |
+
"learning_rate": 5.254860746190226e-07,
|
307 |
+
"loss": 0.9508,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.02,
|
312 |
+
"learning_rate": 5.359957961114031e-07,
|
313 |
+
"loss": 0.8342,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.02,
|
318 |
+
"learning_rate": 5.465055176037835e-07,
|
319 |
+
"loss": 0.9349,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.02,
|
324 |
+
"learning_rate": 5.57015239096164e-07,
|
325 |
+
"loss": 0.9312,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.02,
|
330 |
+
"learning_rate": 5.675249605885444e-07,
|
331 |
+
"loss": 0.8591,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.02,
|
336 |
+
"learning_rate": 5.780346820809249e-07,
|
337 |
+
"loss": 0.9763,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.02,
|
342 |
+
"learning_rate": 5.885444035733053e-07,
|
343 |
+
"loss": 0.9114,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.02,
|
348 |
+
"learning_rate": 5.990541250656859e-07,
|
349 |
+
"loss": 0.9064,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.02,
|
354 |
+
"learning_rate": 6.095638465580663e-07,
|
355 |
+
"loss": 0.9438,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.02,
|
360 |
+
"learning_rate": 6.200735680504468e-07,
|
361 |
+
"loss": 0.865,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.02,
|
366 |
+
"learning_rate": 6.305832895428271e-07,
|
367 |
+
"loss": 0.8593,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.02,
|
372 |
+
"learning_rate": 6.410930110352076e-07,
|
373 |
+
"loss": 0.9031,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.02,
|
378 |
+
"learning_rate": 6.516027325275881e-07,
|
379 |
+
"loss": 0.9431,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.02,
|
384 |
+
"learning_rate": 6.621124540199684e-07,
|
385 |
+
"loss": 0.8947,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.03,
|
390 |
+
"learning_rate": 6.726221755123489e-07,
|
391 |
+
"loss": 0.9237,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.03,
|
396 |
+
"learning_rate": 6.831318970047295e-07,
|
397 |
+
"loss": 0.9067,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.03,
|
402 |
+
"learning_rate": 6.936416184971098e-07,
|
403 |
+
"loss": 0.905,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.03,
|
408 |
+
"learning_rate": 7.041513399894903e-07,
|
409 |
+
"loss": 0.8822,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.03,
|
414 |
+
"learning_rate": 7.146610614818708e-07,
|
415 |
+
"loss": 0.9116,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.03,
|
420 |
+
"learning_rate": 7.251707829742513e-07,
|
421 |
+
"loss": 0.8923,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.03,
|
426 |
+
"learning_rate": 7.356805044666316e-07,
|
427 |
+
"loss": 1.0088,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.03,
|
432 |
+
"learning_rate": 7.461902259590121e-07,
|
433 |
+
"loss": 0.9253,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.03,
|
438 |
+
"learning_rate": 7.566999474513927e-07,
|
439 |
+
"loss": 0.875,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.03,
|
444 |
+
"learning_rate": 7.672096689437731e-07,
|
445 |
+
"loss": 0.9378,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.03,
|
450 |
+
"learning_rate": 7.777193904361535e-07,
|
451 |
+
"loss": 0.9202,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.03,
|
456 |
+
"learning_rate": 7.88229111928534e-07,
|
457 |
+
"loss": 0.9185,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.03,
|
462 |
+
"learning_rate": 7.987388334209144e-07,
|
463 |
+
"loss": 0.9362,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.03,
|
468 |
+
"learning_rate": 8.092485549132949e-07,
|
469 |
+
"loss": 0.8857,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.03,
|
474 |
+
"learning_rate": 8.197582764056753e-07,
|
475 |
+
"loss": 0.8658,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.03,
|
480 |
+
"learning_rate": 8.302679978980557e-07,
|
481 |
+
"loss": 0.8919,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.03,
|
486 |
+
"learning_rate": 8.407777193904363e-07,
|
487 |
+
"loss": 0.9018,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.03,
|
492 |
+
"learning_rate": 8.512874408828168e-07,
|
493 |
+
"loss": 0.8743,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.03,
|
498 |
+
"learning_rate": 8.617971623751971e-07,
|
499 |
+
"loss": 0.9393,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.03,
|
504 |
+
"learning_rate": 8.723068838675776e-07,
|
505 |
+
"loss": 0.8945,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.03,
|
510 |
+
"learning_rate": 8.828166053599581e-07,
|
511 |
+
"loss": 0.9197,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.03,
|
516 |
+
"learning_rate": 8.933263268523384e-07,
|
517 |
+
"loss": 0.9709,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.03,
|
522 |
+
"learning_rate": 9.038360483447189e-07,
|
523 |
+
"loss": 0.8581,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.03,
|
528 |
+
"learning_rate": 9.143457698370995e-07,
|
529 |
+
"loss": 0.8924,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.03,
|
534 |
+
"learning_rate": 9.248554913294798e-07,
|
535 |
+
"loss": 0.8823,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.04,
|
540 |
+
"learning_rate": 9.353652128218603e-07,
|
541 |
+
"loss": 0.8701,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.04,
|
546 |
+
"learning_rate": 9.458749343142408e-07,
|
547 |
+
"loss": 0.8422,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.04,
|
552 |
+
"learning_rate": 9.563846558066212e-07,
|
553 |
+
"loss": 0.8954,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.04,
|
558 |
+
"learning_rate": 9.668943772990016e-07,
|
559 |
+
"loss": 0.9193,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.04,
|
564 |
+
"learning_rate": 9.774040987913822e-07,
|
565 |
+
"loss": 0.8889,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.04,
|
570 |
+
"learning_rate": 9.879138202837624e-07,
|
571 |
+
"loss": 0.8538,
|
572 |
+
"step": 94
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.04,
|
576 |
+
"learning_rate": 9.98423541776143e-07,
|
577 |
+
"loss": 0.8416,
|
578 |
+
"step": 95
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.04,
|
582 |
+
"learning_rate": 1.0089332632685235e-06,
|
583 |
+
"loss": 0.9169,
|
584 |
+
"step": 96
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.04,
|
588 |
+
"learning_rate": 1.0194429847609039e-06,
|
589 |
+
"loss": 0.8734,
|
590 |
+
"step": 97
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.04,
|
594 |
+
"learning_rate": 1.0299527062532843e-06,
|
595 |
+
"loss": 0.9196,
|
596 |
+
"step": 98
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.04,
|
600 |
+
"learning_rate": 1.040462427745665e-06,
|
601 |
+
"loss": 0.9213,
|
602 |
+
"step": 99
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.04,
|
606 |
+
"learning_rate": 1.0509721492380451e-06,
|
607 |
+
"loss": 0.8665,
|
608 |
+
"step": 100
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.04,
|
612 |
+
"learning_rate": 1.0614818707304257e-06,
|
613 |
+
"loss": 0.867,
|
614 |
+
"step": 101
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.04,
|
618 |
+
"learning_rate": 1.0719915922228062e-06,
|
619 |
+
"loss": 0.8649,
|
620 |
+
"step": 102
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.04,
|
624 |
+
"learning_rate": 1.0825013137151866e-06,
|
625 |
+
"loss": 0.8447,
|
626 |
+
"step": 103
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.04,
|
630 |
+
"learning_rate": 1.093011035207567e-06,
|
631 |
+
"loss": 0.865,
|
632 |
+
"step": 104
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.04,
|
636 |
+
"learning_rate": 1.1035207566999476e-06,
|
637 |
+
"loss": 0.9243,
|
638 |
+
"step": 105
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.04,
|
642 |
+
"learning_rate": 1.114030478192328e-06,
|
643 |
+
"loss": 0.916,
|
644 |
+
"step": 106
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.04,
|
648 |
+
"learning_rate": 1.1245401996847084e-06,
|
649 |
+
"loss": 0.8486,
|
650 |
+
"step": 107
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.04,
|
654 |
+
"learning_rate": 1.1350499211770888e-06,
|
655 |
+
"loss": 0.9284,
|
656 |
+
"step": 108
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.04,
|
660 |
+
"learning_rate": 1.1455596426694692e-06,
|
661 |
+
"loss": 0.8814,
|
662 |
+
"step": 109
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.04,
|
666 |
+
"learning_rate": 1.1560693641618499e-06,
|
667 |
+
"loss": 0.9023,
|
668 |
+
"step": 110
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.04,
|
672 |
+
"learning_rate": 1.1665790856542303e-06,
|
673 |
+
"loss": 0.9036,
|
674 |
+
"step": 111
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.04,
|
678 |
+
"learning_rate": 1.1770888071466107e-06,
|
679 |
+
"loss": 0.839,
|
680 |
+
"step": 112
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.04,
|
684 |
+
"learning_rate": 1.187598528638991e-06,
|
685 |
+
"loss": 0.83,
|
686 |
+
"step": 113
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.04,
|
690 |
+
"learning_rate": 1.1981082501313717e-06,
|
691 |
+
"loss": 0.8136,
|
692 |
+
"step": 114
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.05,
|
696 |
+
"learning_rate": 1.2086179716237521e-06,
|
697 |
+
"loss": 0.8475,
|
698 |
+
"step": 115
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.05,
|
702 |
+
"learning_rate": 1.2191276931161325e-06,
|
703 |
+
"loss": 0.8561,
|
704 |
+
"step": 116
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.05,
|
708 |
+
"learning_rate": 1.229637414608513e-06,
|
709 |
+
"loss": 0.8307,
|
710 |
+
"step": 117
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.05,
|
714 |
+
"learning_rate": 1.2401471361008936e-06,
|
715 |
+
"loss": 0.8672,
|
716 |
+
"step": 118
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.05,
|
720 |
+
"learning_rate": 1.250656857593274e-06,
|
721 |
+
"loss": 0.9235,
|
722 |
+
"step": 119
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.05,
|
726 |
+
"learning_rate": 1.2611665790856542e-06,
|
727 |
+
"loss": 0.9005,
|
728 |
+
"step": 120
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.05,
|
732 |
+
"learning_rate": 1.2716763005780348e-06,
|
733 |
+
"loss": 0.9471,
|
734 |
+
"step": 121
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.05,
|
738 |
+
"learning_rate": 1.2821860220704152e-06,
|
739 |
+
"loss": 0.8485,
|
740 |
+
"step": 122
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.05,
|
744 |
+
"learning_rate": 1.2926957435627956e-06,
|
745 |
+
"loss": 0.8306,
|
746 |
+
"step": 123
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.05,
|
750 |
+
"learning_rate": 1.3032054650551763e-06,
|
751 |
+
"loss": 0.8953,
|
752 |
+
"step": 124
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.05,
|
756 |
+
"learning_rate": 1.3137151865475567e-06,
|
757 |
+
"loss": 0.8887,
|
758 |
+
"step": 125
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.05,
|
762 |
+
"learning_rate": 1.3242249080399369e-06,
|
763 |
+
"loss": 0.9285,
|
764 |
+
"step": 126
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.05,
|
768 |
+
"learning_rate": 1.3347346295323175e-06,
|
769 |
+
"loss": 0.8876,
|
770 |
+
"step": 127
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.05,
|
774 |
+
"learning_rate": 1.3452443510246979e-06,
|
775 |
+
"loss": 0.8815,
|
776 |
+
"step": 128
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.05,
|
780 |
+
"learning_rate": 1.3557540725170785e-06,
|
781 |
+
"loss": 0.8883,
|
782 |
+
"step": 129
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.05,
|
786 |
+
"learning_rate": 1.366263794009459e-06,
|
787 |
+
"loss": 0.8416,
|
788 |
+
"step": 130
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.05,
|
792 |
+
"learning_rate": 1.3767735155018393e-06,
|
793 |
+
"loss": 0.8636,
|
794 |
+
"step": 131
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.05,
|
798 |
+
"learning_rate": 1.3872832369942195e-06,
|
799 |
+
"loss": 0.9279,
|
800 |
+
"step": 132
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.05,
|
804 |
+
"learning_rate": 1.3977929584866002e-06,
|
805 |
+
"loss": 0.8635,
|
806 |
+
"step": 133
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.05,
|
810 |
+
"learning_rate": 1.4083026799789806e-06,
|
811 |
+
"loss": 0.8704,
|
812 |
+
"step": 134
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.05,
|
816 |
+
"learning_rate": 1.4188124014713612e-06,
|
817 |
+
"loss": 0.9254,
|
818 |
+
"step": 135
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.05,
|
822 |
+
"learning_rate": 1.4293221229637416e-06,
|
823 |
+
"loss": 0.8566,
|
824 |
+
"step": 136
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.05,
|
828 |
+
"learning_rate": 1.439831844456122e-06,
|
829 |
+
"loss": 0.8802,
|
830 |
+
"step": 137
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.05,
|
834 |
+
"learning_rate": 1.4503415659485026e-06,
|
835 |
+
"loss": 0.8882,
|
836 |
+
"step": 138
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.05,
|
840 |
+
"learning_rate": 1.4608512874408828e-06,
|
841 |
+
"loss": 0.8894,
|
842 |
+
"step": 139
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.06,
|
846 |
+
"learning_rate": 1.4713610089332632e-06,
|
847 |
+
"loss": 0.8016,
|
848 |
+
"step": 140
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.06,
|
852 |
+
"learning_rate": 1.4818707304256439e-06,
|
853 |
+
"loss": 0.843,
|
854 |
+
"step": 141
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.06,
|
858 |
+
"learning_rate": 1.4923804519180243e-06,
|
859 |
+
"loss": 0.8225,
|
860 |
+
"step": 142
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.06,
|
864 |
+
"learning_rate": 1.502890173410405e-06,
|
865 |
+
"loss": 0.9416,
|
866 |
+
"step": 143
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.06,
|
870 |
+
"learning_rate": 1.5133998949027853e-06,
|
871 |
+
"loss": 0.8928,
|
872 |
+
"step": 144
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.06,
|
876 |
+
"learning_rate": 1.5239096163951655e-06,
|
877 |
+
"loss": 0.8778,
|
878 |
+
"step": 145
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.06,
|
882 |
+
"learning_rate": 1.5344193378875461e-06,
|
883 |
+
"loss": 0.8778,
|
884 |
+
"step": 146
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.06,
|
888 |
+
"learning_rate": 1.5449290593799265e-06,
|
889 |
+
"loss": 0.8203,
|
890 |
+
"step": 147
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.06,
|
894 |
+
"learning_rate": 1.555438780872307e-06,
|
895 |
+
"loss": 0.8298,
|
896 |
+
"step": 148
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.06,
|
900 |
+
"learning_rate": 1.5659485023646876e-06,
|
901 |
+
"loss": 0.8581,
|
902 |
+
"step": 149
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.06,
|
906 |
+
"learning_rate": 1.576458223857068e-06,
|
907 |
+
"loss": 0.8292,
|
908 |
+
"step": 150
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.06,
|
912 |
+
"learning_rate": 1.5869679453494482e-06,
|
913 |
+
"loss": 0.8326,
|
914 |
+
"step": 151
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.06,
|
918 |
+
"learning_rate": 1.5974776668418288e-06,
|
919 |
+
"loss": 0.8218,
|
920 |
+
"step": 152
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.06,
|
924 |
+
"learning_rate": 1.6079873883342092e-06,
|
925 |
+
"loss": 0.845,
|
926 |
+
"step": 153
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.06,
|
930 |
+
"learning_rate": 1.6184971098265898e-06,
|
931 |
+
"loss": 0.8576,
|
932 |
+
"step": 154
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.06,
|
936 |
+
"learning_rate": 1.6290068313189703e-06,
|
937 |
+
"loss": 0.87,
|
938 |
+
"step": 155
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.06,
|
942 |
+
"learning_rate": 1.6395165528113507e-06,
|
943 |
+
"loss": 0.9236,
|
944 |
+
"step": 156
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.06,
|
948 |
+
"learning_rate": 1.6500262743037309e-06,
|
949 |
+
"loss": 0.8897,
|
950 |
+
"step": 157
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.06,
|
954 |
+
"learning_rate": 1.6605359957961115e-06,
|
955 |
+
"loss": 0.8678,
|
956 |
+
"step": 158
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.06,
|
960 |
+
"learning_rate": 1.671045717288492e-06,
|
961 |
+
"loss": 0.8475,
|
962 |
+
"step": 159
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.06,
|
966 |
+
"learning_rate": 1.6815554387808725e-06,
|
967 |
+
"loss": 0.8253,
|
968 |
+
"step": 160
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.06,
|
972 |
+
"learning_rate": 1.692065160273253e-06,
|
973 |
+
"loss": 0.8887,
|
974 |
+
"step": 161
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.06,
|
978 |
+
"learning_rate": 1.7025748817656336e-06,
|
979 |
+
"loss": 0.9127,
|
980 |
+
"step": 162
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.06,
|
984 |
+
"learning_rate": 1.7130846032580138e-06,
|
985 |
+
"loss": 0.8863,
|
986 |
+
"step": 163
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.06,
|
990 |
+
"learning_rate": 1.7235943247503942e-06,
|
991 |
+
"loss": 0.8783,
|
992 |
+
"step": 164
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.07,
|
996 |
+
"learning_rate": 1.7341040462427746e-06,
|
997 |
+
"loss": 0.8765,
|
998 |
+
"step": 165
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.07,
|
1002 |
+
"learning_rate": 1.7446137677351552e-06,
|
1003 |
+
"loss": 0.8933,
|
1004 |
+
"step": 166
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.07,
|
1008 |
+
"learning_rate": 1.7551234892275356e-06,
|
1009 |
+
"loss": 0.8049,
|
1010 |
+
"step": 167
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.07,
|
1014 |
+
"learning_rate": 1.7656332107199162e-06,
|
1015 |
+
"loss": 0.8465,
|
1016 |
+
"step": 168
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.07,
|
1020 |
+
"learning_rate": 1.7761429322122964e-06,
|
1021 |
+
"loss": 0.8307,
|
1022 |
+
"step": 169
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.07,
|
1026 |
+
"learning_rate": 1.7866526537046768e-06,
|
1027 |
+
"loss": 0.8415,
|
1028 |
+
"step": 170
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.07,
|
1032 |
+
"learning_rate": 1.7971623751970575e-06,
|
1033 |
+
"loss": 0.9014,
|
1034 |
+
"step": 171
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.07,
|
1038 |
+
"learning_rate": 1.8076720966894379e-06,
|
1039 |
+
"loss": 0.8472,
|
1040 |
+
"step": 172
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.07,
|
1044 |
+
"learning_rate": 1.8181818181818183e-06,
|
1045 |
+
"loss": 0.8447,
|
1046 |
+
"step": 173
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.07,
|
1050 |
+
"learning_rate": 1.828691539674199e-06,
|
1051 |
+
"loss": 0.8928,
|
1052 |
+
"step": 174
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.07,
|
1056 |
+
"learning_rate": 1.8392012611665791e-06,
|
1057 |
+
"loss": 0.9114,
|
1058 |
+
"step": 175
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.07,
|
1062 |
+
"learning_rate": 1.8497109826589595e-06,
|
1063 |
+
"loss": 0.8536,
|
1064 |
+
"step": 176
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.07,
|
1068 |
+
"learning_rate": 1.8602207041513401e-06,
|
1069 |
+
"loss": 0.8554,
|
1070 |
+
"step": 177
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.07,
|
1074 |
+
"learning_rate": 1.8707304256437206e-06,
|
1075 |
+
"loss": 0.7809,
|
1076 |
+
"step": 178
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.07,
|
1080 |
+
"learning_rate": 1.8812401471361012e-06,
|
1081 |
+
"loss": 0.8485,
|
1082 |
+
"step": 179
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.07,
|
1086 |
+
"learning_rate": 1.8917498686284816e-06,
|
1087 |
+
"loss": 0.8215,
|
1088 |
+
"step": 180
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.07,
|
1092 |
+
"learning_rate": 1.902259590120862e-06,
|
1093 |
+
"loss": 0.8399,
|
1094 |
+
"step": 181
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.07,
|
1098 |
+
"learning_rate": 1.9127693116132424e-06,
|
1099 |
+
"loss": 0.8658,
|
1100 |
+
"step": 182
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.07,
|
1104 |
+
"learning_rate": 1.923279033105623e-06,
|
1105 |
+
"loss": 0.8194,
|
1106 |
+
"step": 183
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 0.07,
|
1110 |
+
"learning_rate": 1.9337887545980032e-06,
|
1111 |
+
"loss": 0.9043,
|
1112 |
+
"step": 184
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.07,
|
1116 |
+
"learning_rate": 1.9442984760903836e-06,
|
1117 |
+
"loss": 0.806,
|
1118 |
+
"step": 185
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.07,
|
1122 |
+
"learning_rate": 1.9548081975827645e-06,
|
1123 |
+
"loss": 0.8179,
|
1124 |
+
"step": 186
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.07,
|
1128 |
+
"learning_rate": 1.965317919075145e-06,
|
1129 |
+
"loss": 0.8461,
|
1130 |
+
"step": 187
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.07,
|
1134 |
+
"learning_rate": 1.975827640567525e-06,
|
1135 |
+
"loss": 0.8699,
|
1136 |
+
"step": 188
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.07,
|
1140 |
+
"learning_rate": 1.9863373620599057e-06,
|
1141 |
+
"loss": 0.9114,
|
1142 |
+
"step": 189
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.07,
|
1146 |
+
"learning_rate": 1.996847083552286e-06,
|
1147 |
+
"loss": 0.846,
|
1148 |
+
"step": 190
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.08,
|
1152 |
+
"learning_rate": 2.0073568050446665e-06,
|
1153 |
+
"loss": 0.8631,
|
1154 |
+
"step": 191
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.08,
|
1158 |
+
"learning_rate": 2.017866526537047e-06,
|
1159 |
+
"loss": 0.8162,
|
1160 |
+
"step": 192
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.08,
|
1164 |
+
"learning_rate": 2.0283762480294274e-06,
|
1165 |
+
"loss": 0.8563,
|
1166 |
+
"step": 193
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.08,
|
1170 |
+
"learning_rate": 2.0388859695218078e-06,
|
1171 |
+
"loss": 0.8067,
|
1172 |
+
"step": 194
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.08,
|
1176 |
+
"learning_rate": 2.049395691014188e-06,
|
1177 |
+
"loss": 0.8742,
|
1178 |
+
"step": 195
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.08,
|
1182 |
+
"learning_rate": 2.0599054125065686e-06,
|
1183 |
+
"loss": 0.8952,
|
1184 |
+
"step": 196
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.08,
|
1188 |
+
"learning_rate": 2.0704151339989494e-06,
|
1189 |
+
"loss": 0.8416,
|
1190 |
+
"step": 197
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.08,
|
1194 |
+
"learning_rate": 2.08092485549133e-06,
|
1195 |
+
"loss": 0.8678,
|
1196 |
+
"step": 198
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.08,
|
1200 |
+
"learning_rate": 2.0914345769837102e-06,
|
1201 |
+
"loss": 0.8226,
|
1202 |
+
"step": 199
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.08,
|
1206 |
+
"learning_rate": 2.1019442984760902e-06,
|
1207 |
+
"loss": 0.7962,
|
1208 |
+
"step": 200
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.08,
|
1212 |
+
"learning_rate": 2.112454019968471e-06,
|
1213 |
+
"loss": 0.8959,
|
1214 |
+
"step": 201
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.08,
|
1218 |
+
"learning_rate": 2.1229637414608515e-06,
|
1219 |
+
"loss": 0.8077,
|
1220 |
+
"step": 202
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.08,
|
1224 |
+
"learning_rate": 2.133473462953232e-06,
|
1225 |
+
"loss": 0.8309,
|
1226 |
+
"step": 203
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.08,
|
1230 |
+
"learning_rate": 2.1439831844456123e-06,
|
1231 |
+
"loss": 0.825,
|
1232 |
+
"step": 204
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.08,
|
1236 |
+
"learning_rate": 2.154492905937993e-06,
|
1237 |
+
"loss": 0.8421,
|
1238 |
+
"step": 205
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.08,
|
1242 |
+
"learning_rate": 2.165002627430373e-06,
|
1243 |
+
"loss": 0.8885,
|
1244 |
+
"step": 206
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.08,
|
1248 |
+
"learning_rate": 2.1755123489227535e-06,
|
1249 |
+
"loss": 0.8628,
|
1250 |
+
"step": 207
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.08,
|
1254 |
+
"learning_rate": 2.186022070415134e-06,
|
1255 |
+
"loss": 0.8114,
|
1256 |
+
"step": 208
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.08,
|
1260 |
+
"learning_rate": 2.1965317919075148e-06,
|
1261 |
+
"loss": 0.8257,
|
1262 |
+
"step": 209
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.08,
|
1266 |
+
"learning_rate": 2.207041513399895e-06,
|
1267 |
+
"loss": 0.8555,
|
1268 |
+
"step": 210
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.08,
|
1272 |
+
"learning_rate": 2.2175512348922756e-06,
|
1273 |
+
"loss": 0.8733,
|
1274 |
+
"step": 211
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.08,
|
1278 |
+
"learning_rate": 2.228060956384656e-06,
|
1279 |
+
"loss": 0.8273,
|
1280 |
+
"step": 212
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.08,
|
1284 |
+
"learning_rate": 2.2385706778770364e-06,
|
1285 |
+
"loss": 0.8197,
|
1286 |
+
"step": 213
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.08,
|
1290 |
+
"learning_rate": 2.249080399369417e-06,
|
1291 |
+
"loss": 0.7955,
|
1292 |
+
"step": 214
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.08,
|
1296 |
+
"learning_rate": 2.2595901208617972e-06,
|
1297 |
+
"loss": 0.806,
|
1298 |
+
"step": 215
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.09,
|
1302 |
+
"learning_rate": 2.2700998423541777e-06,
|
1303 |
+
"loss": 0.8325,
|
1304 |
+
"step": 216
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.09,
|
1308 |
+
"learning_rate": 2.2806095638465585e-06,
|
1309 |
+
"loss": 0.8283,
|
1310 |
+
"step": 217
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 0.09,
|
1314 |
+
"learning_rate": 2.2911192853389385e-06,
|
1315 |
+
"loss": 0.7938,
|
1316 |
+
"step": 218
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 0.09,
|
1320 |
+
"learning_rate": 2.301629006831319e-06,
|
1321 |
+
"loss": 0.8119,
|
1322 |
+
"step": 219
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.09,
|
1326 |
+
"learning_rate": 2.3121387283236997e-06,
|
1327 |
+
"loss": 0.8418,
|
1328 |
+
"step": 220
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 0.09,
|
1332 |
+
"learning_rate": 2.32264844981608e-06,
|
1333 |
+
"loss": 0.8606,
|
1334 |
+
"step": 221
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.09,
|
1338 |
+
"learning_rate": 2.3331581713084605e-06,
|
1339 |
+
"loss": 0.8541,
|
1340 |
+
"step": 222
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.09,
|
1344 |
+
"learning_rate": 2.343667892800841e-06,
|
1345 |
+
"loss": 0.8402,
|
1346 |
+
"step": 223
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.09,
|
1350 |
+
"learning_rate": 2.3541776142932214e-06,
|
1351 |
+
"loss": 0.8204,
|
1352 |
+
"step": 224
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 0.09,
|
1356 |
+
"learning_rate": 2.3646873357856018e-06,
|
1357 |
+
"loss": 0.8525,
|
1358 |
+
"step": 225
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 0.09,
|
1362 |
+
"learning_rate": 2.375197057277982e-06,
|
1363 |
+
"loss": 0.8229,
|
1364 |
+
"step": 226
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 0.09,
|
1368 |
+
"learning_rate": 2.3857067787703626e-06,
|
1369 |
+
"loss": 0.7948,
|
1370 |
+
"step": 227
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.09,
|
1374 |
+
"learning_rate": 2.3962165002627434e-06,
|
1375 |
+
"loss": 0.8312,
|
1376 |
+
"step": 228
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.09,
|
1380 |
+
"learning_rate": 2.406726221755124e-06,
|
1381 |
+
"loss": 0.8345,
|
1382 |
+
"step": 229
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.09,
|
1386 |
+
"learning_rate": 2.4172359432475043e-06,
|
1387 |
+
"loss": 0.816,
|
1388 |
+
"step": 230
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.09,
|
1392 |
+
"learning_rate": 2.4277456647398847e-06,
|
1393 |
+
"loss": 0.7643,
|
1394 |
+
"step": 231
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 0.09,
|
1398 |
+
"learning_rate": 2.438255386232265e-06,
|
1399 |
+
"loss": 0.8797,
|
1400 |
+
"step": 232
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 0.09,
|
1404 |
+
"learning_rate": 2.4487651077246455e-06,
|
1405 |
+
"loss": 0.8267,
|
1406 |
+
"step": 233
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.09,
|
1410 |
+
"learning_rate": 2.459274829217026e-06,
|
1411 |
+
"loss": 0.834,
|
1412 |
+
"step": 234
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 0.09,
|
1416 |
+
"learning_rate": 2.4697845507094063e-06,
|
1417 |
+
"loss": 0.8035,
|
1418 |
+
"step": 235
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.09,
|
1422 |
+
"learning_rate": 2.480294272201787e-06,
|
1423 |
+
"loss": 0.8127,
|
1424 |
+
"step": 236
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.09,
|
1428 |
+
"learning_rate": 2.490803993694167e-06,
|
1429 |
+
"loss": 0.8404,
|
1430 |
+
"step": 237
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.09,
|
1434 |
+
"learning_rate": 2.501313715186548e-06,
|
1435 |
+
"loss": 0.8017,
|
1436 |
+
"step": 238
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 0.09,
|
1440 |
+
"learning_rate": 2.5118234366789284e-06,
|
1441 |
+
"loss": 0.783,
|
1442 |
+
"step": 239
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 0.09,
|
1446 |
+
"learning_rate": 2.5223331581713084e-06,
|
1447 |
+
"loss": 0.8523,
|
1448 |
+
"step": 240
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 0.09,
|
1452 |
+
"learning_rate": 2.5328428796636888e-06,
|
1453 |
+
"loss": 0.8818,
|
1454 |
+
"step": 241
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 0.1,
|
1458 |
+
"learning_rate": 2.5433526011560696e-06,
|
1459 |
+
"loss": 0.8113,
|
1460 |
+
"step": 242
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.1,
|
1464 |
+
"learning_rate": 2.55386232264845e-06,
|
1465 |
+
"loss": 0.8489,
|
1466 |
+
"step": 243
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.1,
|
1470 |
+
"learning_rate": 2.5643720441408304e-06,
|
1471 |
+
"loss": 0.8477,
|
1472 |
+
"step": 244
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.1,
|
1476 |
+
"learning_rate": 2.574881765633211e-06,
|
1477 |
+
"loss": 0.8228,
|
1478 |
+
"step": 245
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 0.1,
|
1482 |
+
"learning_rate": 2.5853914871255913e-06,
|
1483 |
+
"loss": 0.8161,
|
1484 |
+
"step": 246
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 0.1,
|
1488 |
+
"learning_rate": 2.595901208617972e-06,
|
1489 |
+
"loss": 0.8977,
|
1490 |
+
"step": 247
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 0.1,
|
1494 |
+
"learning_rate": 2.6064109301103525e-06,
|
1495 |
+
"loss": 0.797,
|
1496 |
+
"step": 248
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 0.1,
|
1500 |
+
"learning_rate": 2.616920651602733e-06,
|
1501 |
+
"loss": 0.7946,
|
1502 |
+
"step": 249
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.1,
|
1506 |
+
"learning_rate": 2.6274303730951133e-06,
|
1507 |
+
"loss": 0.8672,
|
1508 |
+
"step": 250
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.1,
|
1512 |
+
"learning_rate": 2.6379400945874937e-06,
|
1513 |
+
"loss": 0.8719,
|
1514 |
+
"step": 251
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.1,
|
1518 |
+
"learning_rate": 2.6484498160798737e-06,
|
1519 |
+
"loss": 0.81,
|
1520 |
+
"step": 252
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 0.1,
|
1524 |
+
"learning_rate": 2.658959537572254e-06,
|
1525 |
+
"loss": 0.7862,
|
1526 |
+
"step": 253
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 0.1,
|
1530 |
+
"learning_rate": 2.669469259064635e-06,
|
1531 |
+
"loss": 0.8419,
|
1532 |
+
"step": 254
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 0.1,
|
1536 |
+
"learning_rate": 2.6799789805570154e-06,
|
1537 |
+
"loss": 0.8263,
|
1538 |
+
"step": 255
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 0.1,
|
1542 |
+
"learning_rate": 2.6904887020493958e-06,
|
1543 |
+
"loss": 0.9026,
|
1544 |
+
"step": 256
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.1,
|
1548 |
+
"learning_rate": 2.700998423541776e-06,
|
1549 |
+
"loss": 0.8,
|
1550 |
+
"step": 257
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.1,
|
1554 |
+
"learning_rate": 2.711508145034157e-06,
|
1555 |
+
"loss": 0.7938,
|
1556 |
+
"step": 258
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.1,
|
1560 |
+
"learning_rate": 2.7220178665265374e-06,
|
1561 |
+
"loss": 0.857,
|
1562 |
+
"step": 259
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 0.1,
|
1566 |
+
"learning_rate": 2.732527588018918e-06,
|
1567 |
+
"loss": 0.7823,
|
1568 |
+
"step": 260
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 0.1,
|
1572 |
+
"learning_rate": 2.7430373095112983e-06,
|
1573 |
+
"loss": 0.8051,
|
1574 |
+
"step": 261
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 0.1,
|
1578 |
+
"learning_rate": 2.7535470310036787e-06,
|
1579 |
+
"loss": 0.7843,
|
1580 |
+
"step": 262
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 0.1,
|
1584 |
+
"learning_rate": 2.7640567524960595e-06,
|
1585 |
+
"loss": 0.8237,
|
1586 |
+
"step": 263
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.1,
|
1590 |
+
"learning_rate": 2.774566473988439e-06,
|
1591 |
+
"loss": 0.8013,
|
1592 |
+
"step": 264
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.1,
|
1596 |
+
"learning_rate": 2.78507619548082e-06,
|
1597 |
+
"loss": 0.8332,
|
1598 |
+
"step": 265
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.1,
|
1602 |
+
"learning_rate": 2.7955859169732003e-06,
|
1603 |
+
"loss": 0.863,
|
1604 |
+
"step": 266
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 0.11,
|
1608 |
+
"learning_rate": 2.8060956384655807e-06,
|
1609 |
+
"loss": 0.789,
|
1610 |
+
"step": 267
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 0.11,
|
1614 |
+
"learning_rate": 2.816605359957961e-06,
|
1615 |
+
"loss": 0.7895,
|
1616 |
+
"step": 268
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 0.11,
|
1620 |
+
"learning_rate": 2.8271150814503416e-06,
|
1621 |
+
"loss": 0.8474,
|
1622 |
+
"step": 269
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 0.11,
|
1626 |
+
"learning_rate": 2.8376248029427224e-06,
|
1627 |
+
"loss": 0.9381,
|
1628 |
+
"step": 270
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.11,
|
1632 |
+
"learning_rate": 2.848134524435103e-06,
|
1633 |
+
"loss": 0.7906,
|
1634 |
+
"step": 271
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.11,
|
1638 |
+
"learning_rate": 2.858644245927483e-06,
|
1639 |
+
"loss": 0.8295,
|
1640 |
+
"step": 272
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.11,
|
1644 |
+
"learning_rate": 2.8691539674198636e-06,
|
1645 |
+
"loss": 0.8607,
|
1646 |
+
"step": 273
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 0.11,
|
1650 |
+
"learning_rate": 2.879663688912244e-06,
|
1651 |
+
"loss": 0.8294,
|
1652 |
+
"step": 274
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 0.11,
|
1656 |
+
"learning_rate": 2.890173410404625e-06,
|
1657 |
+
"loss": 0.8384,
|
1658 |
+
"step": 275
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.11,
|
1662 |
+
"learning_rate": 2.9006831318970053e-06,
|
1663 |
+
"loss": 0.8402,
|
1664 |
+
"step": 276
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 0.11,
|
1668 |
+
"learning_rate": 2.9111928533893853e-06,
|
1669 |
+
"loss": 0.8587,
|
1670 |
+
"step": 277
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.11,
|
1674 |
+
"learning_rate": 2.9217025748817657e-06,
|
1675 |
+
"loss": 0.7734,
|
1676 |
+
"step": 278
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.11,
|
1680 |
+
"learning_rate": 2.932212296374146e-06,
|
1681 |
+
"loss": 0.7796,
|
1682 |
+
"step": 279
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.11,
|
1686 |
+
"learning_rate": 2.9427220178665265e-06,
|
1687 |
+
"loss": 0.8167,
|
1688 |
+
"step": 280
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 0.11,
|
1692 |
+
"learning_rate": 2.9532317393589073e-06,
|
1693 |
+
"loss": 0.8551,
|
1694 |
+
"step": 281
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 0.11,
|
1698 |
+
"learning_rate": 2.9637414608512877e-06,
|
1699 |
+
"loss": 0.8125,
|
1700 |
+
"step": 282
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.11,
|
1704 |
+
"learning_rate": 2.974251182343668e-06,
|
1705 |
+
"loss": 0.7928,
|
1706 |
+
"step": 283
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 0.11,
|
1710 |
+
"learning_rate": 2.9847609038360486e-06,
|
1711 |
+
"loss": 0.7864,
|
1712 |
+
"step": 284
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.11,
|
1716 |
+
"learning_rate": 2.995270625328429e-06,
|
1717 |
+
"loss": 0.8908,
|
1718 |
+
"step": 285
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.11,
|
1722 |
+
"learning_rate": 3.00578034682081e-06,
|
1723 |
+
"loss": 0.8098,
|
1724 |
+
"step": 286
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.11,
|
1728 |
+
"learning_rate": 3.0162900683131902e-06,
|
1729 |
+
"loss": 0.784,
|
1730 |
+
"step": 287
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 0.11,
|
1734 |
+
"learning_rate": 3.0267997898055706e-06,
|
1735 |
+
"loss": 0.8152,
|
1736 |
+
"step": 288
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 0.11,
|
1740 |
+
"learning_rate": 3.0373095112979506e-06,
|
1741 |
+
"loss": 0.8079,
|
1742 |
+
"step": 289
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 0.11,
|
1746 |
+
"learning_rate": 3.047819232790331e-06,
|
1747 |
+
"loss": 0.8098,
|
1748 |
+
"step": 290
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 0.11,
|
1752 |
+
"learning_rate": 3.0583289542827114e-06,
|
1753 |
+
"loss": 0.8008,
|
1754 |
+
"step": 291
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.12,
|
1758 |
+
"learning_rate": 3.0688386757750923e-06,
|
1759 |
+
"loss": 0.8185,
|
1760 |
+
"step": 292
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 0.12,
|
1764 |
+
"learning_rate": 3.0793483972674727e-06,
|
1765 |
+
"loss": 0.8014,
|
1766 |
+
"step": 293
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.12,
|
1770 |
+
"learning_rate": 3.089858118759853e-06,
|
1771 |
+
"loss": 0.7557,
|
1772 |
+
"step": 294
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 0.12,
|
1776 |
+
"learning_rate": 3.1003678402522335e-06,
|
1777 |
+
"loss": 0.7783,
|
1778 |
+
"step": 295
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 0.12,
|
1782 |
+
"learning_rate": 3.110877561744614e-06,
|
1783 |
+
"loss": 0.8218,
|
1784 |
+
"step": 296
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 0.12,
|
1788 |
+
"learning_rate": 3.1213872832369948e-06,
|
1789 |
+
"loss": 0.8198,
|
1790 |
+
"step": 297
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 0.12,
|
1794 |
+
"learning_rate": 3.131897004729375e-06,
|
1795 |
+
"loss": 0.8062,
|
1796 |
+
"step": 298
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.12,
|
1800 |
+
"learning_rate": 3.1424067262217556e-06,
|
1801 |
+
"loss": 0.8037,
|
1802 |
+
"step": 299
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 0.12,
|
1806 |
+
"learning_rate": 3.152916447714136e-06,
|
1807 |
+
"loss": 0.8203,
|
1808 |
+
"step": 300
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.12,
|
1812 |
+
"learning_rate": 3.163426169206516e-06,
|
1813 |
+
"loss": 0.8182,
|
1814 |
+
"step": 301
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 0.12,
|
1818 |
+
"learning_rate": 3.1739358906988964e-06,
|
1819 |
+
"loss": 0.8488,
|
1820 |
+
"step": 302
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 0.12,
|
1824 |
+
"learning_rate": 3.1844456121912772e-06,
|
1825 |
+
"loss": 0.81,
|
1826 |
+
"step": 303
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.12,
|
1830 |
+
"learning_rate": 3.1949553336836576e-06,
|
1831 |
+
"loss": 0.8073,
|
1832 |
+
"step": 304
|
1833 |
+
},
|
1834 |
+
{
|
1835 |
+
"epoch": 0.12,
|
1836 |
+
"learning_rate": 3.205465055176038e-06,
|
1837 |
+
"loss": 0.8169,
|
1838 |
+
"step": 305
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.12,
|
1842 |
+
"learning_rate": 3.2159747766684185e-06,
|
1843 |
+
"loss": 0.8016,
|
1844 |
+
"step": 306
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 0.12,
|
1848 |
+
"learning_rate": 3.226484498160799e-06,
|
1849 |
+
"loss": 0.8066,
|
1850 |
+
"step": 307
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.12,
|
1854 |
+
"learning_rate": 3.2369942196531797e-06,
|
1855 |
+
"loss": 0.8052,
|
1856 |
+
"step": 308
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 0.12,
|
1860 |
+
"learning_rate": 3.24750394114556e-06,
|
1861 |
+
"loss": 0.7699,
|
1862 |
+
"step": 309
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 0.12,
|
1866 |
+
"learning_rate": 3.2580136626379405e-06,
|
1867 |
+
"loss": 0.8497,
|
1868 |
+
"step": 310
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 0.12,
|
1872 |
+
"learning_rate": 3.268523384130321e-06,
|
1873 |
+
"loss": 0.7892,
|
1874 |
+
"step": 311
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 0.12,
|
1878 |
+
"learning_rate": 3.2790331056227013e-06,
|
1879 |
+
"loss": 0.8514,
|
1880 |
+
"step": 312
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.12,
|
1884 |
+
"learning_rate": 3.289542827115082e-06,
|
1885 |
+
"loss": 0.7749,
|
1886 |
+
"step": 313
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 0.12,
|
1890 |
+
"learning_rate": 3.3000525486074617e-06,
|
1891 |
+
"loss": 0.7904,
|
1892 |
+
"step": 314
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.12,
|
1896 |
+
"learning_rate": 3.3105622700998426e-06,
|
1897 |
+
"loss": 0.7986,
|
1898 |
+
"step": 315
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 0.12,
|
1902 |
+
"learning_rate": 3.321071991592223e-06,
|
1903 |
+
"loss": 0.779,
|
1904 |
+
"step": 316
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 0.12,
|
1908 |
+
"learning_rate": 3.3315817130846034e-06,
|
1909 |
+
"loss": 0.8299,
|
1910 |
+
"step": 317
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 0.13,
|
1914 |
+
"learning_rate": 3.342091434576984e-06,
|
1915 |
+
"loss": 0.7993,
|
1916 |
+
"step": 318
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 0.13,
|
1920 |
+
"learning_rate": 3.3526011560693642e-06,
|
1921 |
+
"loss": 0.8412,
|
1922 |
+
"step": 319
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.13,
|
1926 |
+
"learning_rate": 3.363110877561745e-06,
|
1927 |
+
"loss": 0.8111,
|
1928 |
+
"step": 320
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.13,
|
1932 |
+
"learning_rate": 3.3736205990541255e-06,
|
1933 |
+
"loss": 0.8285,
|
1934 |
+
"step": 321
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.13,
|
1938 |
+
"learning_rate": 3.384130320546506e-06,
|
1939 |
+
"loss": 0.8332,
|
1940 |
+
"step": 322
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 0.13,
|
1944 |
+
"learning_rate": 3.3946400420388863e-06,
|
1945 |
+
"loss": 0.8837,
|
1946 |
+
"step": 323
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 0.13,
|
1950 |
+
"learning_rate": 3.405149763531267e-06,
|
1951 |
+
"loss": 0.8275,
|
1952 |
+
"step": 324
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 0.13,
|
1956 |
+
"learning_rate": 3.4156594850236475e-06,
|
1957 |
+
"loss": 0.8397,
|
1958 |
+
"step": 325
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 0.13,
|
1962 |
+
"learning_rate": 3.4261692065160275e-06,
|
1963 |
+
"loss": 0.835,
|
1964 |
+
"step": 326
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.13,
|
1968 |
+
"learning_rate": 3.436678928008408e-06,
|
1969 |
+
"loss": 0.8153,
|
1970 |
+
"step": 327
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 0.13,
|
1974 |
+
"learning_rate": 3.4471886495007883e-06,
|
1975 |
+
"loss": 0.8656,
|
1976 |
+
"step": 328
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.13,
|
1980 |
+
"learning_rate": 3.4576983709931688e-06,
|
1981 |
+
"loss": 0.8272,
|
1982 |
+
"step": 329
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 0.13,
|
1986 |
+
"learning_rate": 3.468208092485549e-06,
|
1987 |
+
"loss": 0.8442,
|
1988 |
+
"step": 330
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 0.13,
|
1992 |
+
"learning_rate": 3.47871781397793e-06,
|
1993 |
+
"loss": 0.8567,
|
1994 |
+
"step": 331
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 0.13,
|
1998 |
+
"learning_rate": 3.4892275354703104e-06,
|
1999 |
+
"loss": 0.7913,
|
2000 |
+
"step": 332
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 0.13,
|
2004 |
+
"learning_rate": 3.499737256962691e-06,
|
2005 |
+
"loss": 0.8499,
|
2006 |
+
"step": 333
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 0.13,
|
2010 |
+
"learning_rate": 3.5102469784550712e-06,
|
2011 |
+
"loss": 0.7344,
|
2012 |
+
"step": 334
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 0.13,
|
2016 |
+
"learning_rate": 3.5207566999474516e-06,
|
2017 |
+
"loss": 0.8471,
|
2018 |
+
"step": 335
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.13,
|
2022 |
+
"learning_rate": 3.5312664214398325e-06,
|
2023 |
+
"loss": 0.8772,
|
2024 |
+
"step": 336
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 0.13,
|
2028 |
+
"learning_rate": 3.541776142932213e-06,
|
2029 |
+
"loss": 0.9182,
|
2030 |
+
"step": 337
|
2031 |
+
},
|
2032 |
+
{
|
2033 |
+
"epoch": 0.13,
|
2034 |
+
"learning_rate": 3.552285864424593e-06,
|
2035 |
+
"loss": 0.7932,
|
2036 |
+
"step": 338
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 0.13,
|
2040 |
+
"learning_rate": 3.5627955859169733e-06,
|
2041 |
+
"loss": 0.8078,
|
2042 |
+
"step": 339
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 0.13,
|
2046 |
+
"learning_rate": 3.5733053074093537e-06,
|
2047 |
+
"loss": 0.7449,
|
2048 |
+
"step": 340
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 0.13,
|
2052 |
+
"learning_rate": 3.583815028901734e-06,
|
2053 |
+
"loss": 0.8372,
|
2054 |
+
"step": 341
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 0.13,
|
2058 |
+
"learning_rate": 3.594324750394115e-06,
|
2059 |
+
"loss": 0.8061,
|
2060 |
+
"step": 342
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.14,
|
2064 |
+
"learning_rate": 3.6048344718864954e-06,
|
2065 |
+
"loss": 0.7962,
|
2066 |
+
"step": 343
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 0.14,
|
2070 |
+
"learning_rate": 3.6153441933788758e-06,
|
2071 |
+
"loss": 0.7833,
|
2072 |
+
"step": 344
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 0.14,
|
2076 |
+
"learning_rate": 3.625853914871256e-06,
|
2077 |
+
"loss": 0.8089,
|
2078 |
+
"step": 345
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 0.14,
|
2082 |
+
"learning_rate": 3.6363636363636366e-06,
|
2083 |
+
"loss": 0.8276,
|
2084 |
+
"step": 346
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 0.14,
|
2088 |
+
"learning_rate": 3.6468733578560174e-06,
|
2089 |
+
"loss": 0.7673,
|
2090 |
+
"step": 347
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 0.14,
|
2094 |
+
"learning_rate": 3.657383079348398e-06,
|
2095 |
+
"loss": 0.85,
|
2096 |
+
"step": 348
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 0.14,
|
2100 |
+
"learning_rate": 3.6678928008407782e-06,
|
2101 |
+
"loss": 0.8004,
|
2102 |
+
"step": 349
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.14,
|
2106 |
+
"learning_rate": 3.6784025223331582e-06,
|
2107 |
+
"loss": 0.8385,
|
2108 |
+
"step": 350
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 0.14,
|
2112 |
+
"learning_rate": 3.6889122438255386e-06,
|
2113 |
+
"loss": 0.8413,
|
2114 |
+
"step": 351
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 0.14,
|
2118 |
+
"learning_rate": 3.699421965317919e-06,
|
2119 |
+
"loss": 0.8346,
|
2120 |
+
"step": 352
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 0.14,
|
2124 |
+
"learning_rate": 3.7099316868103e-06,
|
2125 |
+
"loss": 0.7425,
|
2126 |
+
"step": 353
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 0.14,
|
2130 |
+
"learning_rate": 3.7204414083026803e-06,
|
2131 |
+
"loss": 0.8421,
|
2132 |
+
"step": 354
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 0.14,
|
2136 |
+
"learning_rate": 3.7309511297950607e-06,
|
2137 |
+
"loss": 0.8623,
|
2138 |
+
"step": 355
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 0.14,
|
2142 |
+
"learning_rate": 3.741460851287441e-06,
|
2143 |
+
"loss": 0.7881,
|
2144 |
+
"step": 356
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.14,
|
2148 |
+
"learning_rate": 3.7519705727798215e-06,
|
2149 |
+
"loss": 0.8611,
|
2150 |
+
"step": 357
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 0.14,
|
2154 |
+
"learning_rate": 3.7624802942722024e-06,
|
2155 |
+
"loss": 0.8196,
|
2156 |
+
"step": 358
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 0.14,
|
2160 |
+
"learning_rate": 3.7729900157645828e-06,
|
2161 |
+
"loss": 0.8406,
|
2162 |
+
"step": 359
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 0.14,
|
2166 |
+
"learning_rate": 3.783499737256963e-06,
|
2167 |
+
"loss": 0.7493,
|
2168 |
+
"step": 360
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 0.14,
|
2172 |
+
"learning_rate": 3.7940094587493436e-06,
|
2173 |
+
"loss": 0.7704,
|
2174 |
+
"step": 361
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 0.14,
|
2178 |
+
"learning_rate": 3.804519180241724e-06,
|
2179 |
+
"loss": 0.7866,
|
2180 |
+
"step": 362
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 0.14,
|
2184 |
+
"learning_rate": 3.815028901734104e-06,
|
2185 |
+
"loss": 0.8068,
|
2186 |
+
"step": 363
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.14,
|
2190 |
+
"learning_rate": 3.825538623226485e-06,
|
2191 |
+
"loss": 0.7198,
|
2192 |
+
"step": 364
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 0.14,
|
2196 |
+
"learning_rate": 3.836048344718865e-06,
|
2197 |
+
"loss": 0.8212,
|
2198 |
+
"step": 365
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 0.14,
|
2202 |
+
"learning_rate": 3.846558066211246e-06,
|
2203 |
+
"loss": 0.777,
|
2204 |
+
"step": 366
|
2205 |
+
},
|
2206 |
+
{
|
2207 |
+
"epoch": 0.14,
|
2208 |
+
"learning_rate": 3.857067787703626e-06,
|
2209 |
+
"loss": 0.8647,
|
2210 |
+
"step": 367
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 0.15,
|
2214 |
+
"learning_rate": 3.8675775091960065e-06,
|
2215 |
+
"loss": 0.7956,
|
2216 |
+
"step": 368
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 0.15,
|
2220 |
+
"learning_rate": 3.878087230688387e-06,
|
2221 |
+
"loss": 0.8092,
|
2222 |
+
"step": 369
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 0.15,
|
2226 |
+
"learning_rate": 3.888596952180767e-06,
|
2227 |
+
"loss": 0.7958,
|
2228 |
+
"step": 370
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.15,
|
2232 |
+
"learning_rate": 3.899106673673148e-06,
|
2233 |
+
"loss": 0.85,
|
2234 |
+
"step": 371
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 0.15,
|
2238 |
+
"learning_rate": 3.909616395165529e-06,
|
2239 |
+
"loss": 0.7967,
|
2240 |
+
"step": 372
|
2241 |
+
},
|
2242 |
+
{
|
2243 |
+
"epoch": 0.15,
|
2244 |
+
"learning_rate": 3.920126116657909e-06,
|
2245 |
+
"loss": 0.7974,
|
2246 |
+
"step": 373
|
2247 |
+
},
|
2248 |
+
{
|
2249 |
+
"epoch": 0.15,
|
2250 |
+
"learning_rate": 3.93063583815029e-06,
|
2251 |
+
"loss": 0.7822,
|
2252 |
+
"step": 374
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 0.15,
|
2256 |
+
"learning_rate": 3.941145559642669e-06,
|
2257 |
+
"loss": 0.8445,
|
2258 |
+
"step": 375
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 0.15,
|
2262 |
+
"learning_rate": 3.95165528113505e-06,
|
2263 |
+
"loss": 0.8093,
|
2264 |
+
"step": 376
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 0.15,
|
2268 |
+
"learning_rate": 3.96216500262743e-06,
|
2269 |
+
"loss": 0.8476,
|
2270 |
+
"step": 377
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.15,
|
2274 |
+
"learning_rate": 3.9726747241198114e-06,
|
2275 |
+
"loss": 0.8214,
|
2276 |
+
"step": 378
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 0.15,
|
2280 |
+
"learning_rate": 3.983184445612192e-06,
|
2281 |
+
"loss": 0.8533,
|
2282 |
+
"step": 379
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 0.15,
|
2286 |
+
"learning_rate": 3.993694167104572e-06,
|
2287 |
+
"loss": 0.7723,
|
2288 |
+
"step": 380
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 0.15,
|
2292 |
+
"learning_rate": 4.004203888596953e-06,
|
2293 |
+
"loss": 0.807,
|
2294 |
+
"step": 381
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 0.15,
|
2298 |
+
"learning_rate": 4.014713610089333e-06,
|
2299 |
+
"loss": 0.8492,
|
2300 |
+
"step": 382
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 0.15,
|
2304 |
+
"learning_rate": 4.0252233315817135e-06,
|
2305 |
+
"loss": 0.8389,
|
2306 |
+
"step": 383
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.15,
|
2310 |
+
"learning_rate": 4.035733053074094e-06,
|
2311 |
+
"loss": 0.7838,
|
2312 |
+
"step": 384
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.15,
|
2316 |
+
"learning_rate": 4.046242774566474e-06,
|
2317 |
+
"loss": 0.8013,
|
2318 |
+
"step": 385
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 0.15,
|
2322 |
+
"learning_rate": 4.056752496058855e-06,
|
2323 |
+
"loss": 0.8072,
|
2324 |
+
"step": 386
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 0.15,
|
2328 |
+
"learning_rate": 4.067262217551235e-06,
|
2329 |
+
"loss": 0.8006,
|
2330 |
+
"step": 387
|
2331 |
+
},
|
2332 |
+
{
|
2333 |
+
"epoch": 0.15,
|
2334 |
+
"learning_rate": 4.0777719390436155e-06,
|
2335 |
+
"loss": 0.8104,
|
2336 |
+
"step": 388
|
2337 |
+
},
|
2338 |
+
{
|
2339 |
+
"epoch": 0.15,
|
2340 |
+
"learning_rate": 4.088281660535996e-06,
|
2341 |
+
"loss": 0.8065,
|
2342 |
+
"step": 389
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 0.15,
|
2346 |
+
"learning_rate": 4.098791382028376e-06,
|
2347 |
+
"loss": 0.7914,
|
2348 |
+
"step": 390
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.15,
|
2352 |
+
"learning_rate": 4.109301103520757e-06,
|
2353 |
+
"loss": 0.8036,
|
2354 |
+
"step": 391
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 0.15,
|
2358 |
+
"learning_rate": 4.119810825013137e-06,
|
2359 |
+
"loss": 0.8041,
|
2360 |
+
"step": 392
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 0.15,
|
2364 |
+
"learning_rate": 4.130320546505518e-06,
|
2365 |
+
"loss": 0.7746,
|
2366 |
+
"step": 393
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 0.16,
|
2370 |
+
"learning_rate": 4.140830267997899e-06,
|
2371 |
+
"loss": 0.765,
|
2372 |
+
"step": 394
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"epoch": 0.16,
|
2376 |
+
"learning_rate": 4.151339989490279e-06,
|
2377 |
+
"loss": 0.7855,
|
2378 |
+
"step": 395
|
2379 |
+
},
|
2380 |
+
{
|
2381 |
+
"epoch": 0.16,
|
2382 |
+
"learning_rate": 4.16184971098266e-06,
|
2383 |
+
"loss": 0.7624,
|
2384 |
+
"step": 396
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 0.16,
|
2388 |
+
"learning_rate": 4.17235943247504e-06,
|
2389 |
+
"loss": 0.7905,
|
2390 |
+
"step": 397
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 0.16,
|
2394 |
+
"learning_rate": 4.1828691539674205e-06,
|
2395 |
+
"loss": 0.7837,
|
2396 |
+
"step": 398
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 0.16,
|
2400 |
+
"learning_rate": 4.193378875459801e-06,
|
2401 |
+
"loss": 0.8263,
|
2402 |
+
"step": 399
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 0.16,
|
2406 |
+
"learning_rate": 4.2038885969521805e-06,
|
2407 |
+
"loss": 0.7906,
|
2408 |
+
"step": 400
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 0.16,
|
2412 |
+
"learning_rate": 4.214398318444562e-06,
|
2413 |
+
"loss": 0.829,
|
2414 |
+
"step": 401
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"epoch": 0.16,
|
2418 |
+
"learning_rate": 4.224908039936942e-06,
|
2419 |
+
"loss": 0.8397,
|
2420 |
+
"step": 402
|
2421 |
+
},
|
2422 |
+
{
|
2423 |
+
"epoch": 0.16,
|
2424 |
+
"learning_rate": 4.2354177614293225e-06,
|
2425 |
+
"loss": 0.8143,
|
2426 |
+
"step": 403
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 0.16,
|
2430 |
+
"learning_rate": 4.245927482921703e-06,
|
2431 |
+
"loss": 0.8318,
|
2432 |
+
"step": 404
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 0.16,
|
2436 |
+
"learning_rate": 4.256437204414083e-06,
|
2437 |
+
"loss": 0.7841,
|
2438 |
+
"step": 405
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 0.16,
|
2442 |
+
"learning_rate": 4.266946925906464e-06,
|
2443 |
+
"loss": 0.8352,
|
2444 |
+
"step": 406
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 0.16,
|
2448 |
+
"learning_rate": 4.277456647398844e-06,
|
2449 |
+
"loss": 0.8099,
|
2450 |
+
"step": 407
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 0.16,
|
2454 |
+
"learning_rate": 4.287966368891225e-06,
|
2455 |
+
"loss": 0.7887,
|
2456 |
+
"step": 408
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 0.16,
|
2460 |
+
"learning_rate": 4.298476090383605e-06,
|
2461 |
+
"loss": 0.8013,
|
2462 |
+
"step": 409
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 0.16,
|
2466 |
+
"learning_rate": 4.308985811875986e-06,
|
2467 |
+
"loss": 0.7538,
|
2468 |
+
"step": 410
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 0.16,
|
2472 |
+
"learning_rate": 4.319495533368367e-06,
|
2473 |
+
"loss": 0.8405,
|
2474 |
+
"step": 411
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 0.16,
|
2478 |
+
"learning_rate": 4.330005254860746e-06,
|
2479 |
+
"loss": 0.7894,
|
2480 |
+
"step": 412
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 0.16,
|
2484 |
+
"learning_rate": 4.340514976353127e-06,
|
2485 |
+
"loss": 0.7704,
|
2486 |
+
"step": 413
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 0.16,
|
2490 |
+
"learning_rate": 4.351024697845507e-06,
|
2491 |
+
"loss": 0.781,
|
2492 |
+
"step": 414
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 0.16,
|
2496 |
+
"learning_rate": 4.3615344193378875e-06,
|
2497 |
+
"loss": 0.7339,
|
2498 |
+
"step": 415
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 0.16,
|
2502 |
+
"learning_rate": 4.372044140830268e-06,
|
2503 |
+
"loss": 0.8059,
|
2504 |
+
"step": 416
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 0.16,
|
2508 |
+
"learning_rate": 4.382553862322649e-06,
|
2509 |
+
"loss": 0.7805,
|
2510 |
+
"step": 417
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 0.16,
|
2514 |
+
"learning_rate": 4.3930635838150296e-06,
|
2515 |
+
"loss": 0.8449,
|
2516 |
+
"step": 418
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 0.17,
|
2520 |
+
"learning_rate": 4.40357330530741e-06,
|
2521 |
+
"loss": 0.8233,
|
2522 |
+
"step": 419
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 0.17,
|
2526 |
+
"learning_rate": 4.41408302679979e-06,
|
2527 |
+
"loss": 0.8101,
|
2528 |
+
"step": 420
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 0.17,
|
2532 |
+
"learning_rate": 4.424592748292171e-06,
|
2533 |
+
"loss": 0.7501,
|
2534 |
+
"step": 421
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 0.17,
|
2538 |
+
"learning_rate": 4.435102469784551e-06,
|
2539 |
+
"loss": 0.8055,
|
2540 |
+
"step": 422
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 0.17,
|
2544 |
+
"learning_rate": 4.445612191276932e-06,
|
2545 |
+
"loss": 0.8196,
|
2546 |
+
"step": 423
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 0.17,
|
2550 |
+
"learning_rate": 4.456121912769312e-06,
|
2551 |
+
"loss": 0.8087,
|
2552 |
+
"step": 424
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 0.17,
|
2556 |
+
"learning_rate": 4.4666316342616924e-06,
|
2557 |
+
"loss": 0.8175,
|
2558 |
+
"step": 425
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 0.17,
|
2562 |
+
"learning_rate": 4.477141355754073e-06,
|
2563 |
+
"loss": 0.7983,
|
2564 |
+
"step": 426
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 0.17,
|
2568 |
+
"learning_rate": 4.487651077246453e-06,
|
2569 |
+
"loss": 0.7686,
|
2570 |
+
"step": 427
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 0.17,
|
2574 |
+
"learning_rate": 4.498160798738834e-06,
|
2575 |
+
"loss": 0.8567,
|
2576 |
+
"step": 428
|
2577 |
+
},
|
2578 |
+
{
|
2579 |
+
"epoch": 0.17,
|
2580 |
+
"learning_rate": 4.508670520231214e-06,
|
2581 |
+
"loss": 0.8355,
|
2582 |
+
"step": 429
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"epoch": 0.17,
|
2586 |
+
"learning_rate": 4.5191802417235945e-06,
|
2587 |
+
"loss": 0.7395,
|
2588 |
+
"step": 430
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"epoch": 0.17,
|
2592 |
+
"learning_rate": 4.529689963215975e-06,
|
2593 |
+
"loss": 0.7831,
|
2594 |
+
"step": 431
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 0.17,
|
2598 |
+
"learning_rate": 4.540199684708355e-06,
|
2599 |
+
"loss": 0.7781,
|
2600 |
+
"step": 432
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 0.17,
|
2604 |
+
"learning_rate": 4.5507094062007366e-06,
|
2605 |
+
"loss": 0.7756,
|
2606 |
+
"step": 433
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 0.17,
|
2610 |
+
"learning_rate": 4.561219127693117e-06,
|
2611 |
+
"loss": 0.7922,
|
2612 |
+
"step": 434
|
2613 |
+
},
|
2614 |
+
{
|
2615 |
+
"epoch": 0.17,
|
2616 |
+
"learning_rate": 4.571728849185497e-06,
|
2617 |
+
"loss": 0.743,
|
2618 |
+
"step": 435
|
2619 |
+
},
|
2620 |
+
{
|
2621 |
+
"epoch": 0.17,
|
2622 |
+
"learning_rate": 4.582238570677877e-06,
|
2623 |
+
"loss": 0.7949,
|
2624 |
+
"step": 436
|
2625 |
+
},
|
2626 |
+
{
|
2627 |
+
"epoch": 0.17,
|
2628 |
+
"learning_rate": 4.592748292170257e-06,
|
2629 |
+
"loss": 0.766,
|
2630 |
+
"step": 437
|
2631 |
+
},
|
2632 |
+
{
|
2633 |
+
"epoch": 0.17,
|
2634 |
+
"learning_rate": 4.603258013662638e-06,
|
2635 |
+
"loss": 0.7464,
|
2636 |
+
"step": 438
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 0.17,
|
2640 |
+
"learning_rate": 4.613767735155019e-06,
|
2641 |
+
"loss": 0.824,
|
2642 |
+
"step": 439
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 0.17,
|
2646 |
+
"learning_rate": 4.6242774566473994e-06,
|
2647 |
+
"loss": 0.7683,
|
2648 |
+
"step": 440
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 0.17,
|
2652 |
+
"learning_rate": 4.63478717813978e-06,
|
2653 |
+
"loss": 0.8004,
|
2654 |
+
"step": 441
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 0.17,
|
2658 |
+
"learning_rate": 4.64529689963216e-06,
|
2659 |
+
"loss": 0.8034,
|
2660 |
+
"step": 442
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 0.17,
|
2664 |
+
"learning_rate": 4.655806621124541e-06,
|
2665 |
+
"loss": 0.7548,
|
2666 |
+
"step": 443
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 0.18,
|
2670 |
+
"learning_rate": 4.666316342616921e-06,
|
2671 |
+
"loss": 0.8016,
|
2672 |
+
"step": 444
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 0.18,
|
2676 |
+
"learning_rate": 4.6768260641093015e-06,
|
2677 |
+
"loss": 0.7472,
|
2678 |
+
"step": 445
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 0.18,
|
2682 |
+
"learning_rate": 4.687335785601682e-06,
|
2683 |
+
"loss": 0.7707,
|
2684 |
+
"step": 446
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 0.18,
|
2688 |
+
"learning_rate": 4.697845507094062e-06,
|
2689 |
+
"loss": 0.8231,
|
2690 |
+
"step": 447
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 0.18,
|
2694 |
+
"learning_rate": 4.708355228586443e-06,
|
2695 |
+
"loss": 0.851,
|
2696 |
+
"step": 448
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 0.18,
|
2700 |
+
"learning_rate": 4.718864950078823e-06,
|
2701 |
+
"loss": 0.7595,
|
2702 |
+
"step": 449
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 0.18,
|
2706 |
+
"learning_rate": 4.7293746715712036e-06,
|
2707 |
+
"loss": 0.795,
|
2708 |
+
"step": 450
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 0.18,
|
2712 |
+
"learning_rate": 4.739884393063584e-06,
|
2713 |
+
"loss": 0.8017,
|
2714 |
+
"step": 451
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 0.18,
|
2718 |
+
"learning_rate": 4.750394114555964e-06,
|
2719 |
+
"loss": 0.7624,
|
2720 |
+
"step": 452
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 0.18,
|
2724 |
+
"learning_rate": 4.760903836048345e-06,
|
2725 |
+
"loss": 0.7707,
|
2726 |
+
"step": 453
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 0.18,
|
2730 |
+
"learning_rate": 4.771413557540725e-06,
|
2731 |
+
"loss": 0.8561,
|
2732 |
+
"step": 454
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 0.18,
|
2736 |
+
"learning_rate": 4.7819232790331065e-06,
|
2737 |
+
"loss": 0.7829,
|
2738 |
+
"step": 455
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 0.18,
|
2742 |
+
"learning_rate": 4.792433000525487e-06,
|
2743 |
+
"loss": 0.8147,
|
2744 |
+
"step": 456
|
2745 |
+
},
|
2746 |
+
{
|
2747 |
+
"epoch": 0.18,
|
2748 |
+
"learning_rate": 4.802942722017867e-06,
|
2749 |
+
"loss": 0.7943,
|
2750 |
+
"step": 457
|
2751 |
+
},
|
2752 |
+
{
|
2753 |
+
"epoch": 0.18,
|
2754 |
+
"learning_rate": 4.813452443510248e-06,
|
2755 |
+
"loss": 0.8013,
|
2756 |
+
"step": 458
|
2757 |
+
},
|
2758 |
+
{
|
2759 |
+
"epoch": 0.18,
|
2760 |
+
"learning_rate": 4.823962165002628e-06,
|
2761 |
+
"loss": 0.7784,
|
2762 |
+
"step": 459
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 0.18,
|
2766 |
+
"learning_rate": 4.8344718864950085e-06,
|
2767 |
+
"loss": 0.7541,
|
2768 |
+
"step": 460
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 0.18,
|
2772 |
+
"learning_rate": 4.844981607987388e-06,
|
2773 |
+
"loss": 0.7895,
|
2774 |
+
"step": 461
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 0.18,
|
2778 |
+
"learning_rate": 4.855491329479769e-06,
|
2779 |
+
"loss": 0.8256,
|
2780 |
+
"step": 462
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 0.18,
|
2784 |
+
"learning_rate": 4.86600105097215e-06,
|
2785 |
+
"loss": 0.7822,
|
2786 |
+
"step": 463
|
2787 |
+
},
|
2788 |
+
{
|
2789 |
+
"epoch": 0.18,
|
2790 |
+
"learning_rate": 4.87651077246453e-06,
|
2791 |
+
"loss": 0.8249,
|
2792 |
+
"step": 464
|
2793 |
+
},
|
2794 |
+
{
|
2795 |
+
"epoch": 0.18,
|
2796 |
+
"learning_rate": 4.8870204939569106e-06,
|
2797 |
+
"loss": 0.8216,
|
2798 |
+
"step": 465
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 0.18,
|
2802 |
+
"learning_rate": 4.897530215449291e-06,
|
2803 |
+
"loss": 0.7614,
|
2804 |
+
"step": 466
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 0.18,
|
2808 |
+
"learning_rate": 4.908039936941671e-06,
|
2809 |
+
"loss": 0.7757,
|
2810 |
+
"step": 467
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 0.18,
|
2814 |
+
"learning_rate": 4.918549658434052e-06,
|
2815 |
+
"loss": 0.7565,
|
2816 |
+
"step": 468
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 0.18,
|
2820 |
+
"learning_rate": 4.929059379926432e-06,
|
2821 |
+
"loss": 0.8064,
|
2822 |
+
"step": 469
|
2823 |
+
},
|
2824 |
+
{
|
2825 |
+
"epoch": 0.19,
|
2826 |
+
"learning_rate": 4.939569101418813e-06,
|
2827 |
+
"loss": 0.7756,
|
2828 |
+
"step": 470
|
2829 |
+
},
|
2830 |
+
{
|
2831 |
+
"epoch": 0.19,
|
2832 |
+
"learning_rate": 4.950078822911194e-06,
|
2833 |
+
"loss": 0.798,
|
2834 |
+
"step": 471
|
2835 |
+
},
|
2836 |
+
{
|
2837 |
+
"epoch": 0.19,
|
2838 |
+
"learning_rate": 4.960588544403574e-06,
|
2839 |
+
"loss": 0.7709,
|
2840 |
+
"step": 472
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 0.19,
|
2844 |
+
"learning_rate": 4.971098265895954e-06,
|
2845 |
+
"loss": 0.7985,
|
2846 |
+
"step": 473
|
2847 |
+
},
|
2848 |
+
{
|
2849 |
+
"epoch": 0.19,
|
2850 |
+
"learning_rate": 4.981607987388334e-06,
|
2851 |
+
"loss": 0.7588,
|
2852 |
+
"step": 474
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 0.19,
|
2856 |
+
"learning_rate": 4.992117708880715e-06,
|
2857 |
+
"loss": 0.7575,
|
2858 |
+
"step": 475
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 0.19,
|
2862 |
+
"learning_rate": 5.002627430373096e-06,
|
2863 |
+
"loss": 0.7779,
|
2864 |
+
"step": 476
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 0.19,
|
2868 |
+
"learning_rate": 5.0131371518654755e-06,
|
2869 |
+
"loss": 0.7804,
|
2870 |
+
"step": 477
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 0.19,
|
2874 |
+
"learning_rate": 5.023646873357857e-06,
|
2875 |
+
"loss": 0.7687,
|
2876 |
+
"step": 478
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 0.19,
|
2880 |
+
"learning_rate": 5.034156594850237e-06,
|
2881 |
+
"loss": 0.8063,
|
2882 |
+
"step": 479
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 0.19,
|
2886 |
+
"learning_rate": 5.044666316342617e-06,
|
2887 |
+
"loss": 0.8207,
|
2888 |
+
"step": 480
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 0.19,
|
2892 |
+
"learning_rate": 5.055176037834998e-06,
|
2893 |
+
"loss": 0.7946,
|
2894 |
+
"step": 481
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 0.19,
|
2898 |
+
"learning_rate": 5.0656857593273776e-06,
|
2899 |
+
"loss": 0.8119,
|
2900 |
+
"step": 482
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 0.19,
|
2904 |
+
"learning_rate": 5.076195480819759e-06,
|
2905 |
+
"loss": 0.8291,
|
2906 |
+
"step": 483
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 0.19,
|
2910 |
+
"learning_rate": 5.086705202312139e-06,
|
2911 |
+
"loss": 0.7851,
|
2912 |
+
"step": 484
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 0.19,
|
2916 |
+
"learning_rate": 5.09721492380452e-06,
|
2917 |
+
"loss": 0.8316,
|
2918 |
+
"step": 485
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 0.19,
|
2922 |
+
"learning_rate": 5.1077246452969e-06,
|
2923 |
+
"loss": 0.7544,
|
2924 |
+
"step": 486
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 0.19,
|
2928 |
+
"learning_rate": 5.1182343667892805e-06,
|
2929 |
+
"loss": 0.7991,
|
2930 |
+
"step": 487
|
2931 |
+
},
|
2932 |
+
{
|
2933 |
+
"epoch": 0.19,
|
2934 |
+
"learning_rate": 5.128744088281661e-06,
|
2935 |
+
"loss": 0.7846,
|
2936 |
+
"step": 488
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 0.19,
|
2940 |
+
"learning_rate": 5.139253809774042e-06,
|
2941 |
+
"loss": 0.8036,
|
2942 |
+
"step": 489
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 0.19,
|
2946 |
+
"learning_rate": 5.149763531266422e-06,
|
2947 |
+
"loss": 0.8046,
|
2948 |
+
"step": 490
|
2949 |
+
},
|
2950 |
+
{
|
2951 |
+
"epoch": 0.19,
|
2952 |
+
"learning_rate": 5.160273252758803e-06,
|
2953 |
+
"loss": 0.8217,
|
2954 |
+
"step": 491
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 0.19,
|
2958 |
+
"learning_rate": 5.1707829742511825e-06,
|
2959 |
+
"loss": 0.792,
|
2960 |
+
"step": 492
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 0.19,
|
2964 |
+
"learning_rate": 5.181292695743563e-06,
|
2965 |
+
"loss": 0.7791,
|
2966 |
+
"step": 493
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 0.19,
|
2970 |
+
"learning_rate": 5.191802417235944e-06,
|
2971 |
+
"loss": 0.8335,
|
2972 |
+
"step": 494
|
2973 |
+
},
|
2974 |
+
{
|
2975 |
+
"epoch": 0.2,
|
2976 |
+
"learning_rate": 5.202312138728324e-06,
|
2977 |
+
"loss": 0.8251,
|
2978 |
+
"step": 495
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 0.2,
|
2982 |
+
"learning_rate": 5.212821860220705e-06,
|
2983 |
+
"loss": 0.7816,
|
2984 |
+
"step": 496
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 0.2,
|
2988 |
+
"learning_rate": 5.2233315817130846e-06,
|
2989 |
+
"loss": 0.7564,
|
2990 |
+
"step": 497
|
2991 |
+
},
|
2992 |
+
{
|
2993 |
+
"epoch": 0.2,
|
2994 |
+
"learning_rate": 5.233841303205466e-06,
|
2995 |
+
"loss": 0.7769,
|
2996 |
+
"step": 498
|
2997 |
+
},
|
2998 |
+
{
|
2999 |
+
"epoch": 0.2,
|
3000 |
+
"learning_rate": 5.244351024697845e-06,
|
3001 |
+
"loss": 0.7552,
|
3002 |
+
"step": 499
|
3003 |
+
},
|
3004 |
+
{
|
3005 |
+
"epoch": 0.2,
|
3006 |
+
"learning_rate": 5.254860746190227e-06,
|
3007 |
+
"loss": 0.7614,
|
3008 |
+
"step": 500
|
3009 |
+
}
|
3010 |
+
],
|
3011 |
+
"max_steps": 63425,
|
3012 |
+
"num_train_epochs": 25,
|
3013 |
+
"total_flos": 1.324826417430528e+18,
|
3014 |
+
"trial_name": null,
|
3015 |
+
"trial_params": null
|
3016 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3a995e57c5ef351645b3d9b96a658552090bbf013ddf7014ddf41bb6049fc00
|
3 |
+
size 3771
|