Upload folder using huggingface_hub
Browse files- config.json +25 -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
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
- trainer_state.json +1807 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/workspace/llama-7b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 1,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"max_seq_len": 4096,
|
14 |
+
"max_sequence_length": 2048,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"pad_token_id": -1,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.29.2",
|
23 |
+
"use_cache": false,
|
24 |
+
"vocab_size": 32000
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.29.2"
|
7 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa4f3a56efca67a31e83a3306b0047391994df3a1802fd12a14cca9f17b5fae5
|
3 |
+
size 9877989586
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62ef6cdd2c2b29cec07abfede67890ac1b35a15ab7a8e6d4a18ddc0050e749c6
|
3 |
+
size 9894801014
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e91a490d897baf14e60123f390d1af71d91e4d512fdaa223cc4d85bba5e5386c
|
3 |
+
size 7180990649
|
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 |
+
}
|
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": 4096,
|
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 +1,1807 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 297,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 1.6666666666666667e-06,
|
13 |
+
"loss": 0.6895,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 3.3333333333333333e-06,
|
19 |
+
"loss": 0.7129,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.03,
|
24 |
+
"learning_rate": 5e-06,
|
25 |
+
"loss": 0.7467,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.04,
|
30 |
+
"learning_rate": 6.666666666666667e-06,
|
31 |
+
"loss": 0.6553,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.05,
|
36 |
+
"learning_rate": 8.333333333333334e-06,
|
37 |
+
"loss": 0.6908,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.06,
|
42 |
+
"learning_rate": 1e-05,
|
43 |
+
"loss": 0.6292,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.07,
|
48 |
+
"learning_rate": 1.1666666666666668e-05,
|
49 |
+
"loss": 0.648,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.08,
|
54 |
+
"learning_rate": 1.3333333333333333e-05,
|
55 |
+
"loss": 0.6291,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.09,
|
60 |
+
"learning_rate": 1.5000000000000002e-05,
|
61 |
+
"loss": 0.6205,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.1,
|
66 |
+
"learning_rate": 1.6666666666666667e-05,
|
67 |
+
"loss": 0.5143,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.11,
|
72 |
+
"learning_rate": 1.8333333333333333e-05,
|
73 |
+
"loss": 0.5343,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.12,
|
78 |
+
"learning_rate": 2e-05,
|
79 |
+
"loss": 0.6127,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.13,
|
84 |
+
"learning_rate": 1.9999392458943432e-05,
|
85 |
+
"loss": 0.5313,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.14,
|
90 |
+
"learning_rate": 1.9997569909594948e-05,
|
91 |
+
"loss": 0.486,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.15,
|
96 |
+
"learning_rate": 1.999453257340926e-05,
|
97 |
+
"loss": 0.5457,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.16,
|
102 |
+
"learning_rate": 1.9990280819447662e-05,
|
103 |
+
"loss": 0.5688,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.17,
|
108 |
+
"learning_rate": 1.9984815164333163e-05,
|
109 |
+
"loss": 0.5523,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.18,
|
114 |
+
"learning_rate": 1.9978136272187745e-05,
|
115 |
+
"loss": 0.5291,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.19,
|
120 |
+
"learning_rate": 1.9970244954551648e-05,
|
121 |
+
"loss": 0.4995,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.2,
|
126 |
+
"learning_rate": 1.9961142170284762e-05,
|
127 |
+
"loss": 0.4819,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.21,
|
132 |
+
"learning_rate": 1.9950829025450116e-05,
|
133 |
+
"loss": 0.485,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.22,
|
138 |
+
"learning_rate": 1.9939306773179498e-05,
|
139 |
+
"loss": 0.5592,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.23,
|
144 |
+
"learning_rate": 1.9926576813521167e-05,
|
145 |
+
"loss": 0.5018,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.24,
|
150 |
+
"learning_rate": 1.9912640693269754e-05,
|
151 |
+
"loss": 0.5148,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.25,
|
156 |
+
"learning_rate": 1.98975001057783e-05,
|
157 |
+
"loss": 0.4703,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.26,
|
162 |
+
"learning_rate": 1.9881156890752517e-05,
|
163 |
+
"loss": 0.46,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.27,
|
168 |
+
"learning_rate": 1.9863613034027224e-05,
|
169 |
+
"loss": 0.4772,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.28,
|
174 |
+
"learning_rate": 1.9844870667325073e-05,
|
175 |
+
"loss": 0.4644,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.29,
|
180 |
+
"learning_rate": 1.9824932067997516e-05,
|
181 |
+
"loss": 0.43,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.3,
|
186 |
+
"learning_rate": 1.9803799658748096e-05,
|
187 |
+
"loss": 0.4792,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.31,
|
192 |
+
"learning_rate": 1.9781476007338058e-05,
|
193 |
+
"loss": 0.4879,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.32,
|
198 |
+
"learning_rate": 1.9757963826274357e-05,
|
199 |
+
"loss": 0.466,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.33,
|
204 |
+
"learning_rate": 1.973326597248006e-05,
|
205 |
+
"loss": 0.4972,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.34,
|
210 |
+
"learning_rate": 1.97073854469472e-05,
|
211 |
+
"loss": 0.4756,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.35,
|
216 |
+
"learning_rate": 1.968032539437215e-05,
|
217 |
+
"loss": 0.5015,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.36,
|
222 |
+
"learning_rate": 1.9652089102773487e-05,
|
223 |
+
"loss": 0.4449,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.37,
|
228 |
+
"learning_rate": 1.9622680003092503e-05,
|
229 |
+
"loss": 0.411,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.38,
|
234 |
+
"learning_rate": 1.95921016687763e-05,
|
235 |
+
"loss": 0.4184,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.39,
|
240 |
+
"learning_rate": 1.9560357815343577e-05,
|
241 |
+
"loss": 0.4779,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.4,
|
246 |
+
"learning_rate": 1.9527452299933192e-05,
|
247 |
+
"loss": 0.4778,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.41,
|
252 |
+
"learning_rate": 1.9493389120835462e-05,
|
253 |
+
"loss": 0.3891,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.42,
|
258 |
+
"learning_rate": 1.9458172417006347e-05,
|
259 |
+
"loss": 0.4235,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.43,
|
264 |
+
"learning_rate": 1.9421806467564546e-05,
|
265 |
+
"loss": 0.4597,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.44,
|
270 |
+
"learning_rate": 1.9384295691271523e-05,
|
271 |
+
"loss": 0.4506,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.45,
|
276 |
+
"learning_rate": 1.934564464599461e-05,
|
277 |
+
"loss": 0.4283,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.46,
|
282 |
+
"learning_rate": 1.9305858028153186e-05,
|
283 |
+
"loss": 0.414,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.47,
|
288 |
+
"learning_rate": 1.9264940672148018e-05,
|
289 |
+
"loss": 0.3809,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.48,
|
294 |
+
"learning_rate": 1.922289754977385e-05,
|
295 |
+
"loss": 0.4041,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.49,
|
300 |
+
"learning_rate": 1.9179733769615273e-05,
|
301 |
+
"loss": 0.4192,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.51,
|
306 |
+
"learning_rate": 1.913545457642601e-05,
|
307 |
+
"loss": 0.4638,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.52,
|
312 |
+
"learning_rate": 1.909006535049163e-05,
|
313 |
+
"loss": 0.3532,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.53,
|
318 |
+
"learning_rate": 1.9043571606975776e-05,
|
319 |
+
"loss": 0.3824,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.54,
|
324 |
+
"learning_rate": 1.899597899525007e-05,
|
325 |
+
"loss": 0.4066,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.55,
|
330 |
+
"learning_rate": 1.8947293298207637e-05,
|
331 |
+
"loss": 0.4117,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.56,
|
336 |
+
"learning_rate": 1.8897520431560435e-05,
|
337 |
+
"loss": 0.4037,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.57,
|
342 |
+
"learning_rate": 1.884666644312046e-05,
|
343 |
+
"loss": 0.4009,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.58,
|
348 |
+
"learning_rate": 1.879473751206489e-05,
|
349 |
+
"loss": 0.3139,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.59,
|
354 |
+
"learning_rate": 1.8741739948185256e-05,
|
355 |
+
"loss": 0.4352,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.6,
|
360 |
+
"learning_rate": 1.8687680191120746e-05,
|
361 |
+
"loss": 0.4189,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.61,
|
366 |
+
"learning_rate": 1.863256480957574e-05,
|
367 |
+
"loss": 0.4013,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.62,
|
372 |
+
"learning_rate": 1.8576400500521673e-05,
|
373 |
+
"loss": 0.416,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.63,
|
378 |
+
"learning_rate": 1.851919408838327e-05,
|
379 |
+
"loss": 0.4034,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.64,
|
384 |
+
"learning_rate": 1.8460952524209355e-05,
|
385 |
+
"loss": 0.3081,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.65,
|
390 |
+
"learning_rate": 1.8401682884828212e-05,
|
391 |
+
"loss": 0.4454,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.66,
|
396 |
+
"learning_rate": 1.83413923719877e-05,
|
397 |
+
"loss": 0.4245,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.67,
|
402 |
+
"learning_rate": 1.8280088311480203e-05,
|
403 |
+
"loss": 0.4159,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.68,
|
408 |
+
"learning_rate": 1.821777815225245e-05,
|
409 |
+
"loss": 0.3682,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.69,
|
414 |
+
"learning_rate": 1.8154469465500447e-05,
|
415 |
+
"loss": 0.3361,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.7,
|
420 |
+
"learning_rate": 1.8090169943749477e-05,
|
421 |
+
"loss": 0.4249,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.71,
|
426 |
+
"learning_rate": 1.802488739991941e-05,
|
427 |
+
"loss": 0.3483,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.72,
|
432 |
+
"learning_rate": 1.7958629766375387e-05,
|
433 |
+
"loss": 0.3563,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.73,
|
438 |
+
"learning_rate": 1.789140509396394e-05,
|
439 |
+
"loss": 0.3829,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.74,
|
444 |
+
"learning_rate": 1.7823221551034766e-05,
|
445 |
+
"loss": 0.333,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.75,
|
450 |
+
"learning_rate": 1.7754087422448217e-05,
|
451 |
+
"loss": 0.3394,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.76,
|
456 |
+
"learning_rate": 1.7684011108568593e-05,
|
457 |
+
"loss": 0.2989,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.77,
|
462 |
+
"learning_rate": 1.7613001124243448e-05,
|
463 |
+
"loss": 0.3513,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.78,
|
468 |
+
"learning_rate": 1.7541066097768965e-05,
|
469 |
+
"loss": 0.4423,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.79,
|
474 |
+
"learning_rate": 1.7468214769841542e-05,
|
475 |
+
"loss": 0.3345,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.8,
|
480 |
+
"learning_rate": 1.7394455992495722e-05,
|
481 |
+
"loss": 0.3538,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.81,
|
486 |
+
"learning_rate": 1.7319798728028617e-05,
|
487 |
+
"loss": 0.311,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.82,
|
492 |
+
"learning_rate": 1.7244252047910893e-05,
|
493 |
+
"loss": 0.3137,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.83,
|
498 |
+
"learning_rate": 1.7167825131684516e-05,
|
499 |
+
"loss": 0.2986,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.84,
|
504 |
+
"learning_rate": 1.7090527265847375e-05,
|
505 |
+
"loss": 0.3376,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.85,
|
510 |
+
"learning_rate": 1.7012367842724887e-05,
|
511 |
+
"loss": 0.2555,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.86,
|
516 |
+
"learning_rate": 1.6933356359328756e-05,
|
517 |
+
"loss": 0.2784,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.87,
|
522 |
+
"learning_rate": 1.6853502416203e-05,
|
523 |
+
"loss": 0.4175,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.88,
|
528 |
+
"learning_rate": 1.6772815716257414e-05,
|
529 |
+
"loss": 0.402,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.89,
|
534 |
+
"learning_rate": 1.6691306063588583e-05,
|
535 |
+
"loss": 0.3356,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.9,
|
540 |
+
"learning_rate": 1.6608983362288612e-05,
|
541 |
+
"loss": 0.3317,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.91,
|
546 |
+
"learning_rate": 1.6525857615241686e-05,
|
547 |
+
"loss": 0.3149,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.92,
|
552 |
+
"learning_rate": 1.6441938922908644e-05,
|
553 |
+
"loss": 0.291,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.93,
|
558 |
+
"learning_rate": 1.6357237482099682e-05,
|
559 |
+
"loss": 0.3862,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.94,
|
564 |
+
"learning_rate": 1.6271763584735373e-05,
|
565 |
+
"loss": 0.3611,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.95,
|
570 |
+
"learning_rate": 1.6185527616596096e-05,
|
571 |
+
"loss": 0.3326,
|
572 |
+
"step": 94
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.96,
|
576 |
+
"learning_rate": 1.609854005606009e-05,
|
577 |
+
"loss": 0.4092,
|
578 |
+
"step": 95
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.97,
|
582 |
+
"learning_rate": 1.6010811472830253e-05,
|
583 |
+
"loss": 0.313,
|
584 |
+
"step": 96
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.98,
|
588 |
+
"learning_rate": 1.5922352526649803e-05,
|
589 |
+
"loss": 0.3875,
|
590 |
+
"step": 97
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.99,
|
594 |
+
"learning_rate": 1.583317396600707e-05,
|
595 |
+
"loss": 0.3525,
|
596 |
+
"step": 98
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 1.0,
|
600 |
+
"learning_rate": 1.5743286626829437e-05,
|
601 |
+
"loss": 0.3531,
|
602 |
+
"step": 99
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 1.01,
|
606 |
+
"learning_rate": 1.565270143116672e-05,
|
607 |
+
"loss": 0.3013,
|
608 |
+
"step": 100
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 1.02,
|
612 |
+
"learning_rate": 1.5561429385864005e-05,
|
613 |
+
"loss": 0.3702,
|
614 |
+
"step": 101
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 1.03,
|
618 |
+
"learning_rate": 1.5469481581224274e-05,
|
619 |
+
"loss": 0.3134,
|
620 |
+
"step": 102
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 1.04,
|
624 |
+
"learning_rate": 1.5376869189660784e-05,
|
625 |
+
"loss": 0.334,
|
626 |
+
"step": 103
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.05,
|
630 |
+
"learning_rate": 1.528360346433959e-05,
|
631 |
+
"loss": 0.3265,
|
632 |
+
"step": 104
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 1.06,
|
636 |
+
"learning_rate": 1.5189695737812153e-05,
|
637 |
+
"loss": 0.2694,
|
638 |
+
"step": 105
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 1.07,
|
642 |
+
"learning_rate": 1.5095157420638349e-05,
|
643 |
+
"loss": 0.3163,
|
644 |
+
"step": 106
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 1.08,
|
648 |
+
"learning_rate": 1.5000000000000002e-05,
|
649 |
+
"loss": 0.273,
|
650 |
+
"step": 107
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 1.09,
|
654 |
+
"learning_rate": 1.4904235038305084e-05,
|
655 |
+
"loss": 0.2774,
|
656 |
+
"step": 108
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 1.1,
|
660 |
+
"learning_rate": 1.4807874171782795e-05,
|
661 |
+
"loss": 0.3119,
|
662 |
+
"step": 109
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 1.11,
|
666 |
+
"learning_rate": 1.4710929109069674e-05,
|
667 |
+
"loss": 0.3072,
|
668 |
+
"step": 110
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.12,
|
672 |
+
"learning_rate": 1.461341162978688e-05,
|
673 |
+
"loss": 0.2993,
|
674 |
+
"step": 111
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 1.13,
|
678 |
+
"learning_rate": 1.4515333583108896e-05,
|
679 |
+
"loss": 0.2969,
|
680 |
+
"step": 112
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 1.14,
|
684 |
+
"learning_rate": 1.4416706886323741e-05,
|
685 |
+
"loss": 0.2728,
|
686 |
+
"step": 113
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 1.15,
|
690 |
+
"learning_rate": 1.4317543523384928e-05,
|
691 |
+
"loss": 0.282,
|
692 |
+
"step": 114
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 1.16,
|
696 |
+
"learning_rate": 1.4217855543455323e-05,
|
697 |
+
"loss": 0.2412,
|
698 |
+
"step": 115
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 1.17,
|
702 |
+
"learning_rate": 1.4117655059443052e-05,
|
703 |
+
"loss": 0.2805,
|
704 |
+
"step": 116
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 1.18,
|
708 |
+
"learning_rate": 1.4016954246529697e-05,
|
709 |
+
"loss": 0.2515,
|
710 |
+
"step": 117
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 1.19,
|
714 |
+
"learning_rate": 1.3915765340690916e-05,
|
715 |
+
"loss": 0.246,
|
716 |
+
"step": 118
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 1.2,
|
720 |
+
"learning_rate": 1.3814100637209663e-05,
|
721 |
+
"loss": 0.272,
|
722 |
+
"step": 119
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 1.21,
|
726 |
+
"learning_rate": 1.3711972489182208e-05,
|
727 |
+
"loss": 0.2769,
|
728 |
+
"step": 120
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 1.22,
|
732 |
+
"learning_rate": 1.3609393306017149e-05,
|
733 |
+
"loss": 0.2189,
|
734 |
+
"step": 121
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.23,
|
738 |
+
"learning_rate": 1.3506375551927546e-05,
|
739 |
+
"loss": 0.2174,
|
740 |
+
"step": 122
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 1.24,
|
744 |
+
"learning_rate": 1.3402931744416432e-05,
|
745 |
+
"loss": 0.2252,
|
746 |
+
"step": 123
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 1.25,
|
750 |
+
"learning_rate": 1.3299074452755829e-05,
|
751 |
+
"loss": 0.2361,
|
752 |
+
"step": 124
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.26,
|
756 |
+
"learning_rate": 1.3194816296459483e-05,
|
757 |
+
"loss": 0.2545,
|
758 |
+
"step": 125
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 1.27,
|
762 |
+
"learning_rate": 1.3090169943749475e-05,
|
763 |
+
"loss": 0.2656,
|
764 |
+
"step": 126
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 1.28,
|
768 |
+
"learning_rate": 1.2985148110016947e-05,
|
769 |
+
"loss": 0.2973,
|
770 |
+
"step": 127
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 1.29,
|
774 |
+
"learning_rate": 1.2879763556277062e-05,
|
775 |
+
"loss": 0.2965,
|
776 |
+
"step": 128
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 1.3,
|
780 |
+
"learning_rate": 1.2774029087618448e-05,
|
781 |
+
"loss": 0.2444,
|
782 |
+
"step": 129
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 1.31,
|
786 |
+
"learning_rate": 1.2667957551647263e-05,
|
787 |
+
"loss": 0.2817,
|
788 |
+
"step": 130
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 1.32,
|
792 |
+
"learning_rate": 1.2561561836926115e-05,
|
793 |
+
"loss": 0.2908,
|
794 |
+
"step": 131
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 1.33,
|
798 |
+
"learning_rate": 1.2454854871407993e-05,
|
799 |
+
"loss": 0.2854,
|
800 |
+
"step": 132
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 1.34,
|
804 |
+
"learning_rate": 1.234784962086541e-05,
|
805 |
+
"loss": 0.2955,
|
806 |
+
"step": 133
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 1.35,
|
810 |
+
"learning_rate": 1.224055908731496e-05,
|
811 |
+
"loss": 0.3027,
|
812 |
+
"step": 134
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 1.36,
|
816 |
+
"learning_rate": 1.213299630743747e-05,
|
817 |
+
"loss": 0.2459,
|
818 |
+
"step": 135
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 1.37,
|
822 |
+
"learning_rate": 1.2025174350993923e-05,
|
823 |
+
"loss": 0.2663,
|
824 |
+
"step": 136
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 1.38,
|
828 |
+
"learning_rate": 1.1917106319237386e-05,
|
829 |
+
"loss": 0.22,
|
830 |
+
"step": 137
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 1.39,
|
834 |
+
"learning_rate": 1.1808805343321102e-05,
|
835 |
+
"loss": 0.2549,
|
836 |
+
"step": 138
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 1.4,
|
840 |
+
"learning_rate": 1.1700284582702933e-05,
|
841 |
+
"loss": 0.2712,
|
842 |
+
"step": 139
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 1.41,
|
846 |
+
"learning_rate": 1.1591557223546394e-05,
|
847 |
+
"loss": 0.2347,
|
848 |
+
"step": 140
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 1.42,
|
852 |
+
"learning_rate": 1.148263647711842e-05,
|
853 |
+
"loss": 0.2478,
|
854 |
+
"step": 141
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 1.43,
|
858 |
+
"learning_rate": 1.1373535578184083e-05,
|
859 |
+
"loss": 0.2049,
|
860 |
+
"step": 142
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 1.44,
|
864 |
+
"learning_rate": 1.1264267783398463e-05,
|
865 |
+
"loss": 0.2375,
|
866 |
+
"step": 143
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 1.45,
|
870 |
+
"learning_rate": 1.1154846369695864e-05,
|
871 |
+
"loss": 0.2893,
|
872 |
+
"step": 144
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 1.46,
|
876 |
+
"learning_rate": 1.1045284632676535e-05,
|
877 |
+
"loss": 0.2361,
|
878 |
+
"step": 145
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 1.47,
|
882 |
+
"learning_rate": 1.093559588499118e-05,
|
883 |
+
"loss": 0.1738,
|
884 |
+
"step": 146
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.48,
|
888 |
+
"learning_rate": 1.0825793454723325e-05,
|
889 |
+
"loss": 0.2037,
|
890 |
+
"step": 147
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 1.49,
|
894 |
+
"learning_rate": 1.0715890683769872e-05,
|
895 |
+
"loss": 0.2048,
|
896 |
+
"step": 148
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 1.51,
|
900 |
+
"learning_rate": 1.060590092621994e-05,
|
901 |
+
"loss": 0.1777,
|
902 |
+
"step": 149
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 1.52,
|
906 |
+
"learning_rate": 1.0495837546732224e-05,
|
907 |
+
"loss": 0.2889,
|
908 |
+
"step": 150
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 1.53,
|
912 |
+
"learning_rate": 1.0385713918911104e-05,
|
913 |
+
"loss": 0.2363,
|
914 |
+
"step": 151
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 1.54,
|
918 |
+
"learning_rate": 1.0275543423681622e-05,
|
919 |
+
"loss": 0.2456,
|
920 |
+
"step": 152
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 1.55,
|
924 |
+
"learning_rate": 1.0165339447663586e-05,
|
925 |
+
"loss": 0.236,
|
926 |
+
"step": 153
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 1.56,
|
930 |
+
"learning_rate": 1.0055115381545006e-05,
|
931 |
+
"loss": 0.2409,
|
932 |
+
"step": 154
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 1.57,
|
936 |
+
"learning_rate": 9.944884618454996e-06,
|
937 |
+
"loss": 0.2758,
|
938 |
+
"step": 155
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 1.58,
|
942 |
+
"learning_rate": 9.834660552336415e-06,
|
943 |
+
"loss": 0.1752,
|
944 |
+
"step": 156
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 1.59,
|
948 |
+
"learning_rate": 9.724456576318383e-06,
|
949 |
+
"loss": 0.2372,
|
950 |
+
"step": 157
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 1.6,
|
954 |
+
"learning_rate": 9.614286081088895e-06,
|
955 |
+
"loss": 0.2148,
|
956 |
+
"step": 158
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 1.61,
|
960 |
+
"learning_rate": 9.504162453267776e-06,
|
961 |
+
"loss": 0.1684,
|
962 |
+
"step": 159
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 1.62,
|
966 |
+
"learning_rate": 9.394099073780066e-06,
|
967 |
+
"loss": 0.2243,
|
968 |
+
"step": 160
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 1.63,
|
972 |
+
"learning_rate": 9.284109316230133e-06,
|
973 |
+
"loss": 0.2365,
|
974 |
+
"step": 161
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 1.64,
|
978 |
+
"learning_rate": 9.174206545276678e-06,
|
979 |
+
"loss": 0.2333,
|
980 |
+
"step": 162
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 1.65,
|
984 |
+
"learning_rate": 9.064404115008824e-06,
|
985 |
+
"loss": 0.2108,
|
986 |
+
"step": 163
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 1.66,
|
990 |
+
"learning_rate": 8.954715367323468e-06,
|
991 |
+
"loss": 0.283,
|
992 |
+
"step": 164
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 1.67,
|
996 |
+
"learning_rate": 8.84515363030414e-06,
|
997 |
+
"loss": 0.2383,
|
998 |
+
"step": 165
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 1.68,
|
1002 |
+
"learning_rate": 8.735732216601538e-06,
|
1003 |
+
"loss": 0.1921,
|
1004 |
+
"step": 166
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 1.69,
|
1008 |
+
"learning_rate": 8.626464421815919e-06,
|
1009 |
+
"loss": 0.2585,
|
1010 |
+
"step": 167
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.7,
|
1014 |
+
"learning_rate": 8.51736352288158e-06,
|
1015 |
+
"loss": 0.2201,
|
1016 |
+
"step": 168
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 1.71,
|
1020 |
+
"learning_rate": 8.408442776453606e-06,
|
1021 |
+
"loss": 0.2088,
|
1022 |
+
"step": 169
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 1.72,
|
1026 |
+
"learning_rate": 8.299715417297072e-06,
|
1027 |
+
"loss": 0.1736,
|
1028 |
+
"step": 170
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 1.73,
|
1032 |
+
"learning_rate": 8.191194656678905e-06,
|
1033 |
+
"loss": 0.2028,
|
1034 |
+
"step": 171
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 1.74,
|
1038 |
+
"learning_rate": 8.082893680762619e-06,
|
1039 |
+
"loss": 0.2331,
|
1040 |
+
"step": 172
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 1.75,
|
1044 |
+
"learning_rate": 7.974825649006082e-06,
|
1045 |
+
"loss": 0.2313,
|
1046 |
+
"step": 173
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 1.76,
|
1050 |
+
"learning_rate": 7.867003692562533e-06,
|
1051 |
+
"loss": 0.3048,
|
1052 |
+
"step": 174
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.77,
|
1056 |
+
"learning_rate": 7.759440912685043e-06,
|
1057 |
+
"loss": 0.2014,
|
1058 |
+
"step": 175
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 1.78,
|
1062 |
+
"learning_rate": 7.652150379134593e-06,
|
1063 |
+
"loss": 0.2098,
|
1064 |
+
"step": 176
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 1.79,
|
1068 |
+
"learning_rate": 7.545145128592009e-06,
|
1069 |
+
"loss": 0.2076,
|
1070 |
+
"step": 177
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 1.8,
|
1074 |
+
"learning_rate": 7.438438163073884e-06,
|
1075 |
+
"loss": 0.1652,
|
1076 |
+
"step": 178
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 1.81,
|
1080 |
+
"learning_rate": 7.3320424483527385e-06,
|
1081 |
+
"loss": 0.1559,
|
1082 |
+
"step": 179
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 1.82,
|
1086 |
+
"learning_rate": 7.225970912381557e-06,
|
1087 |
+
"loss": 0.2062,
|
1088 |
+
"step": 180
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 1.83,
|
1092 |
+
"learning_rate": 7.120236443722941e-06,
|
1093 |
+
"loss": 0.2017,
|
1094 |
+
"step": 181
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.84,
|
1098 |
+
"learning_rate": 7.014851889983058e-06,
|
1099 |
+
"loss": 0.1794,
|
1100 |
+
"step": 182
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 1.85,
|
1104 |
+
"learning_rate": 6.909830056250527e-06,
|
1105 |
+
"loss": 0.1932,
|
1106 |
+
"step": 183
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 1.86,
|
1110 |
+
"learning_rate": 6.80518370354052e-06,
|
1111 |
+
"loss": 0.2138,
|
1112 |
+
"step": 184
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 1.87,
|
1116 |
+
"learning_rate": 6.700925547244173e-06,
|
1117 |
+
"loss": 0.1776,
|
1118 |
+
"step": 185
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 1.88,
|
1122 |
+
"learning_rate": 6.59706825558357e-06,
|
1123 |
+
"loss": 0.1961,
|
1124 |
+
"step": 186
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 1.89,
|
1128 |
+
"learning_rate": 6.4936244480724575e-06,
|
1129 |
+
"loss": 0.2006,
|
1130 |
+
"step": 187
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 1.9,
|
1134 |
+
"learning_rate": 6.3906066939828546e-06,
|
1135 |
+
"loss": 0.263,
|
1136 |
+
"step": 188
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.91,
|
1140 |
+
"learning_rate": 6.2880275108177915e-06,
|
1141 |
+
"loss": 0.201,
|
1142 |
+
"step": 189
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 1.92,
|
1146 |
+
"learning_rate": 6.18589936279034e-06,
|
1147 |
+
"loss": 0.1588,
|
1148 |
+
"step": 190
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 1.93,
|
1152 |
+
"learning_rate": 6.084234659309088e-06,
|
1153 |
+
"loss": 0.216,
|
1154 |
+
"step": 191
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 1.94,
|
1158 |
+
"learning_rate": 5.983045753470308e-06,
|
1159 |
+
"loss": 0.1918,
|
1160 |
+
"step": 192
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 1.95,
|
1164 |
+
"learning_rate": 5.8823449405569525e-06,
|
1165 |
+
"loss": 0.184,
|
1166 |
+
"step": 193
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 1.96,
|
1170 |
+
"learning_rate": 5.782144456544681e-06,
|
1171 |
+
"loss": 0.1564,
|
1172 |
+
"step": 194
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 1.97,
|
1176 |
+
"learning_rate": 5.6824564766150724e-06,
|
1177 |
+
"loss": 0.1936,
|
1178 |
+
"step": 195
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.98,
|
1182 |
+
"learning_rate": 5.58329311367626e-06,
|
1183 |
+
"loss": 0.1495,
|
1184 |
+
"step": 196
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 1.99,
|
1188 |
+
"learning_rate": 5.484666416891109e-06,
|
1189 |
+
"loss": 0.2793,
|
1190 |
+
"step": 197
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 2.0,
|
1194 |
+
"learning_rate": 5.386588370213124e-06,
|
1195 |
+
"loss": 0.1719,
|
1196 |
+
"step": 198
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 2.01,
|
1200 |
+
"learning_rate": 5.289070890930328e-06,
|
1201 |
+
"loss": 0.194,
|
1202 |
+
"step": 199
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 2.02,
|
1206 |
+
"learning_rate": 5.192125828217203e-06,
|
1207 |
+
"loss": 0.1358,
|
1208 |
+
"step": 200
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 2.03,
|
1212 |
+
"learning_rate": 5.095764961694923e-06,
|
1213 |
+
"loss": 0.16,
|
1214 |
+
"step": 201
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 2.04,
|
1218 |
+
"learning_rate": 5.000000000000003e-06,
|
1219 |
+
"loss": 0.1797,
|
1220 |
+
"step": 202
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 2.05,
|
1224 |
+
"learning_rate": 4.904842579361653e-06,
|
1225 |
+
"loss": 0.1968,
|
1226 |
+
"step": 203
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 2.06,
|
1230 |
+
"learning_rate": 4.8103042621878515e-06,
|
1231 |
+
"loss": 0.1639,
|
1232 |
+
"step": 204
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 2.07,
|
1236 |
+
"learning_rate": 4.716396535660412e-06,
|
1237 |
+
"loss": 0.1747,
|
1238 |
+
"step": 205
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 2.08,
|
1242 |
+
"learning_rate": 4.623130810339219e-06,
|
1243 |
+
"loss": 0.2478,
|
1244 |
+
"step": 206
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 2.09,
|
1248 |
+
"learning_rate": 4.530518418775734e-06,
|
1249 |
+
"loss": 0.1603,
|
1250 |
+
"step": 207
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 2.1,
|
1254 |
+
"learning_rate": 4.438570614135994e-06,
|
1255 |
+
"loss": 0.1551,
|
1256 |
+
"step": 208
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 2.11,
|
1260 |
+
"learning_rate": 4.347298568833281e-06,
|
1261 |
+
"loss": 0.1762,
|
1262 |
+
"step": 209
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 2.12,
|
1266 |
+
"learning_rate": 4.256713373170565e-06,
|
1267 |
+
"loss": 0.1881,
|
1268 |
+
"step": 210
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 2.13,
|
1272 |
+
"learning_rate": 4.166826033992939e-06,
|
1273 |
+
"loss": 0.1405,
|
1274 |
+
"step": 211
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 2.14,
|
1278 |
+
"learning_rate": 4.077647473350201e-06,
|
1279 |
+
"loss": 0.1996,
|
1280 |
+
"step": 212
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 2.15,
|
1284 |
+
"learning_rate": 3.989188527169749e-06,
|
1285 |
+
"loss": 0.1252,
|
1286 |
+
"step": 213
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 2.16,
|
1290 |
+
"learning_rate": 3.90145994393991e-06,
|
1291 |
+
"loss": 0.1156,
|
1292 |
+
"step": 214
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 2.17,
|
1296 |
+
"learning_rate": 3.8144723834039076e-06,
|
1297 |
+
"loss": 0.1462,
|
1298 |
+
"step": 215
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 2.18,
|
1302 |
+
"learning_rate": 3.72823641526463e-06,
|
1303 |
+
"loss": 0.2174,
|
1304 |
+
"step": 216
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 2.19,
|
1308 |
+
"learning_rate": 3.6427625179003223e-06,
|
1309 |
+
"loss": 0.2678,
|
1310 |
+
"step": 217
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 2.2,
|
1314 |
+
"learning_rate": 3.5580610770913593e-06,
|
1315 |
+
"loss": 0.1681,
|
1316 |
+
"step": 218
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 2.21,
|
1320 |
+
"learning_rate": 3.4741423847583134e-06,
|
1321 |
+
"loss": 0.2125,
|
1322 |
+
"step": 219
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 2.22,
|
1326 |
+
"learning_rate": 3.3910166377113894e-06,
|
1327 |
+
"loss": 0.1816,
|
1328 |
+
"step": 220
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 2.23,
|
1332 |
+
"learning_rate": 3.308693936411421e-06,
|
1333 |
+
"loss": 0.1421,
|
1334 |
+
"step": 221
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 2.24,
|
1338 |
+
"learning_rate": 3.2271842837425917e-06,
|
1339 |
+
"loss": 0.1898,
|
1340 |
+
"step": 222
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 2.25,
|
1344 |
+
"learning_rate": 3.1464975837970035e-06,
|
1345 |
+
"loss": 0.1321,
|
1346 |
+
"step": 223
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 2.26,
|
1350 |
+
"learning_rate": 3.0666436406712485e-06,
|
1351 |
+
"loss": 0.1529,
|
1352 |
+
"step": 224
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 2.27,
|
1356 |
+
"learning_rate": 2.9876321572751143e-06,
|
1357 |
+
"loss": 0.1399,
|
1358 |
+
"step": 225
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 2.28,
|
1362 |
+
"learning_rate": 2.9094727341526275e-06,
|
1363 |
+
"loss": 0.1596,
|
1364 |
+
"step": 226
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 2.29,
|
1368 |
+
"learning_rate": 2.8321748683154893e-06,
|
1369 |
+
"loss": 0.1354,
|
1370 |
+
"step": 227
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 2.3,
|
1374 |
+
"learning_rate": 2.7557479520891104e-06,
|
1375 |
+
"loss": 0.1474,
|
1376 |
+
"step": 228
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 2.31,
|
1380 |
+
"learning_rate": 2.680201271971383e-06,
|
1381 |
+
"loss": 0.1558,
|
1382 |
+
"step": 229
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 2.32,
|
1386 |
+
"learning_rate": 2.6055440075042793e-06,
|
1387 |
+
"loss": 0.1595,
|
1388 |
+
"step": 230
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 2.33,
|
1392 |
+
"learning_rate": 2.5317852301584642e-06,
|
1393 |
+
"loss": 0.1791,
|
1394 |
+
"step": 231
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 2.34,
|
1398 |
+
"learning_rate": 2.4589339022310386e-06,
|
1399 |
+
"loss": 0.1387,
|
1400 |
+
"step": 232
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 2.35,
|
1404 |
+
"learning_rate": 2.386998875756554e-06,
|
1405 |
+
"loss": 0.1032,
|
1406 |
+
"step": 233
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 2.36,
|
1410 |
+
"learning_rate": 2.315988891431412e-06,
|
1411 |
+
"loss": 0.1711,
|
1412 |
+
"step": 234
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 2.37,
|
1416 |
+
"learning_rate": 2.2459125775517854e-06,
|
1417 |
+
"loss": 0.1274,
|
1418 |
+
"step": 235
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 2.38,
|
1422 |
+
"learning_rate": 2.1767784489652345e-06,
|
1423 |
+
"loss": 0.1584,
|
1424 |
+
"step": 236
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 2.39,
|
1428 |
+
"learning_rate": 2.1085949060360654e-06,
|
1429 |
+
"loss": 0.1374,
|
1430 |
+
"step": 237
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 2.4,
|
1434 |
+
"learning_rate": 2.0413702336246156e-06,
|
1435 |
+
"loss": 0.1403,
|
1436 |
+
"step": 238
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 2.41,
|
1440 |
+
"learning_rate": 1.97511260008059e-06,
|
1441 |
+
"loss": 0.1533,
|
1442 |
+
"step": 239
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 2.42,
|
1446 |
+
"learning_rate": 1.9098300562505266e-06,
|
1447 |
+
"loss": 0.1528,
|
1448 |
+
"step": 240
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 2.43,
|
1452 |
+
"learning_rate": 1.8455305344995523e-06,
|
1453 |
+
"loss": 0.1275,
|
1454 |
+
"step": 241
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 2.44,
|
1458 |
+
"learning_rate": 1.7822218477475496e-06,
|
1459 |
+
"loss": 0.209,
|
1460 |
+
"step": 242
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 2.45,
|
1464 |
+
"learning_rate": 1.7199116885197996e-06,
|
1465 |
+
"loss": 0.1208,
|
1466 |
+
"step": 243
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 2.46,
|
1470 |
+
"learning_rate": 1.6586076280123032e-06,
|
1471 |
+
"loss": 0.0937,
|
1472 |
+
"step": 244
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 2.47,
|
1476 |
+
"learning_rate": 1.5983171151717924e-06,
|
1477 |
+
"loss": 0.1244,
|
1478 |
+
"step": 245
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 2.48,
|
1482 |
+
"learning_rate": 1.5390474757906449e-06,
|
1483 |
+
"loss": 0.1131,
|
1484 |
+
"step": 246
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 2.49,
|
1488 |
+
"learning_rate": 1.4808059116167306e-06,
|
1489 |
+
"loss": 0.1315,
|
1490 |
+
"step": 247
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 2.51,
|
1494 |
+
"learning_rate": 1.4235994994783297e-06,
|
1495 |
+
"loss": 0.1891,
|
1496 |
+
"step": 248
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 2.52,
|
1500 |
+
"learning_rate": 1.367435190424261e-06,
|
1501 |
+
"loss": 0.1316,
|
1502 |
+
"step": 249
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 2.53,
|
1506 |
+
"learning_rate": 1.3123198088792577e-06,
|
1507 |
+
"loss": 0.155,
|
1508 |
+
"step": 250
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 2.54,
|
1512 |
+
"learning_rate": 1.2582600518147448e-06,
|
1513 |
+
"loss": 0.1472,
|
1514 |
+
"step": 251
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 2.55,
|
1518 |
+
"learning_rate": 1.2052624879351105e-06,
|
1519 |
+
"loss": 0.1732,
|
1520 |
+
"step": 252
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 2.56,
|
1524 |
+
"learning_rate": 1.1533335568795412e-06,
|
1525 |
+
"loss": 0.1536,
|
1526 |
+
"step": 253
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 2.57,
|
1530 |
+
"learning_rate": 1.1024795684395695e-06,
|
1531 |
+
"loss": 0.1176,
|
1532 |
+
"step": 254
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 2.58,
|
1536 |
+
"learning_rate": 1.0527067017923654e-06,
|
1537 |
+
"loss": 0.1502,
|
1538 |
+
"step": 255
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 2.59,
|
1542 |
+
"learning_rate": 1.0040210047499289e-06,
|
1543 |
+
"loss": 0.1859,
|
1544 |
+
"step": 256
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 2.6,
|
1548 |
+
"learning_rate": 9.564283930242258e-07,
|
1549 |
+
"loss": 0.1167,
|
1550 |
+
"step": 257
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 2.61,
|
1554 |
+
"learning_rate": 9.09934649508375e-07,
|
1555 |
+
"loss": 0.1391,
|
1556 |
+
"step": 258
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 2.62,
|
1560 |
+
"learning_rate": 8.645454235739903e-07,
|
1561 |
+
"loss": 0.1438,
|
1562 |
+
"step": 259
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 2.63,
|
1566 |
+
"learning_rate": 8.202662303847298e-07,
|
1567 |
+
"loss": 0.1527,
|
1568 |
+
"step": 260
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 2.64,
|
1572 |
+
"learning_rate": 7.771024502261526e-07,
|
1573 |
+
"loss": 0.1238,
|
1574 |
+
"step": 261
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 2.65,
|
1578 |
+
"learning_rate": 7.350593278519824e-07,
|
1579 |
+
"loss": 0.1709,
|
1580 |
+
"step": 262
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 2.66,
|
1584 |
+
"learning_rate": 6.941419718468168e-07,
|
1585 |
+
"loss": 0.1836,
|
1586 |
+
"step": 263
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 2.67,
|
1590 |
+
"learning_rate": 6.543553540053926e-07,
|
1591 |
+
"loss": 0.1866,
|
1592 |
+
"step": 264
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 2.68,
|
1596 |
+
"learning_rate": 6.157043087284797e-07,
|
1597 |
+
"loss": 0.1365,
|
1598 |
+
"step": 265
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 2.69,
|
1602 |
+
"learning_rate": 5.781935324354571e-07,
|
1603 |
+
"loss": 0.1835,
|
1604 |
+
"step": 266
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 2.7,
|
1608 |
+
"learning_rate": 5.418275829936537e-07,
|
1609 |
+
"loss": 0.1197,
|
1610 |
+
"step": 267
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 2.71,
|
1614 |
+
"learning_rate": 5.066108791645407e-07,
|
1615 |
+
"loss": 0.1345,
|
1616 |
+
"step": 268
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 2.72,
|
1620 |
+
"learning_rate": 4.7254770006681105e-07,
|
1621 |
+
"loss": 0.1644,
|
1622 |
+
"step": 269
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 2.73,
|
1626 |
+
"learning_rate": 4.396421846564236e-07,
|
1627 |
+
"loss": 0.1511,
|
1628 |
+
"step": 270
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 2.74,
|
1632 |
+
"learning_rate": 4.078983312237017e-07,
|
1633 |
+
"loss": 0.179,
|
1634 |
+
"step": 271
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 2.75,
|
1638 |
+
"learning_rate": 3.773199969074959e-07,
|
1639 |
+
"loss": 0.1191,
|
1640 |
+
"step": 272
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 2.76,
|
1644 |
+
"learning_rate": 3.4791089722651437e-07,
|
1645 |
+
"loss": 0.127,
|
1646 |
+
"step": 273
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 2.77,
|
1650 |
+
"learning_rate": 3.1967460562785325e-07,
|
1651 |
+
"loss": 0.1226,
|
1652 |
+
"step": 274
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 2.78,
|
1656 |
+
"learning_rate": 2.926145530528002e-07,
|
1657 |
+
"loss": 0.1787,
|
1658 |
+
"step": 275
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 2.79,
|
1662 |
+
"learning_rate": 2.667340275199426e-07,
|
1663 |
+
"loss": 0.1438,
|
1664 |
+
"step": 276
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 2.8,
|
1668 |
+
"learning_rate": 2.420361737256438e-07,
|
1669 |
+
"loss": 0.1226,
|
1670 |
+
"step": 277
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 2.81,
|
1674 |
+
"learning_rate": 2.1852399266194312e-07,
|
1675 |
+
"loss": 0.1422,
|
1676 |
+
"step": 278
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 2.82,
|
1680 |
+
"learning_rate": 1.9620034125190645e-07,
|
1681 |
+
"loss": 0.1451,
|
1682 |
+
"step": 279
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 2.83,
|
1686 |
+
"learning_rate": 1.7506793200248507e-07,
|
1687 |
+
"loss": 0.1726,
|
1688 |
+
"step": 280
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 2.84,
|
1692 |
+
"learning_rate": 1.5512933267492813e-07,
|
1693 |
+
"loss": 0.1418,
|
1694 |
+
"step": 281
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 2.85,
|
1698 |
+
"learning_rate": 1.3638696597277678e-07,
|
1699 |
+
"loss": 0.1239,
|
1700 |
+
"step": 282
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 2.86,
|
1704 |
+
"learning_rate": 1.18843109247484e-07,
|
1705 |
+
"loss": 0.1554,
|
1706 |
+
"step": 283
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 2.87,
|
1710 |
+
"learning_rate": 1.0249989422169926e-07,
|
1711 |
+
"loss": 0.1818,
|
1712 |
+
"step": 284
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 2.88,
|
1716 |
+
"learning_rate": 8.735930673024806e-08,
|
1717 |
+
"loss": 0.1633,
|
1718 |
+
"step": 285
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 2.89,
|
1722 |
+
"learning_rate": 7.342318647883595e-08,
|
1723 |
+
"loss": 0.1912,
|
1724 |
+
"step": 286
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 2.9,
|
1728 |
+
"learning_rate": 6.069322682050516e-08,
|
1729 |
+
"loss": 0.1301,
|
1730 |
+
"step": 287
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 2.91,
|
1734 |
+
"learning_rate": 4.9170974549885844e-08,
|
1735 |
+
"loss": 0.1728,
|
1736 |
+
"step": 288
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 2.92,
|
1740 |
+
"learning_rate": 3.885782971524088e-08,
|
1741 |
+
"loss": 0.1156,
|
1742 |
+
"step": 289
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 2.93,
|
1746 |
+
"learning_rate": 2.9755045448351948e-08,
|
1747 |
+
"loss": 0.1304,
|
1748 |
+
"step": 290
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 2.94,
|
1752 |
+
"learning_rate": 2.1863727812254653e-08,
|
1753 |
+
"loss": 0.1408,
|
1754 |
+
"step": 291
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 2.95,
|
1758 |
+
"learning_rate": 1.518483566683826e-08,
|
1759 |
+
"loss": 0.2036,
|
1760 |
+
"step": 292
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 2.96,
|
1764 |
+
"learning_rate": 9.719180552341113e-09,
|
1765 |
+
"loss": 0.1597,
|
1766 |
+
"step": 293
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 2.97,
|
1770 |
+
"learning_rate": 5.467426590739511e-09,
|
1771 |
+
"loss": 0.1618,
|
1772 |
+
"step": 294
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 2.98,
|
1776 |
+
"learning_rate": 2.430090405054486e-09,
|
1777 |
+
"loss": 0.1651,
|
1778 |
+
"step": 295
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 2.99,
|
1782 |
+
"learning_rate": 6.075410565697937e-10,
|
1783 |
+
"loss": 0.1322,
|
1784 |
+
"step": 296
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 3.0,
|
1788 |
+
"learning_rate": 0.0,
|
1789 |
+
"loss": 0.1284,
|
1790 |
+
"step": 297
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 3.0,
|
1794 |
+
"step": 297,
|
1795 |
+
"total_flos": 7.834692227086418e+17,
|
1796 |
+
"train_loss": 0.27782333958329575,
|
1797 |
+
"train_runtime": 6854.2409,
|
1798 |
+
"train_samples_per_second": 5.521,
|
1799 |
+
"train_steps_per_second": 0.043
|
1800 |
+
}
|
1801 |
+
],
|
1802 |
+
"max_steps": 297,
|
1803 |
+
"num_train_epochs": 3,
|
1804 |
+
"total_flos": 7.834692227086418e+17,
|
1805 |
+
"trial_name": null,
|
1806 |
+
"trial_params": null
|
1807 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e88e487e3ec731ca0983617b8b7922fedadc7e30ccb71f07203cdc9e1a046b07
|
3 |
+
size 4091
|