step 1600
Browse files- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +244 -0
- trainer_state.json +1923 -0
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"transformers_version": "4.40.2"
|
7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46c5e3e1c7f14c651b8954733db0fe00d1853e8a5bd0eccae1b0073ec7067bf4
|
3 |
+
size 4949453792
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:259fe40447303fc97bb4d606b03ee2f84df297340acc35ec9d0de47df6cb070a
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b698cf45add049b21c866559ed166c0aff5ef78d4582a2cc8b37d4242b239cde
|
3 |
+
size 1929457496
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 11878703104
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
180 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
181 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
182 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
183 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
184 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
185 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
186 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
187 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
188 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
189 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
190 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
191 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
192 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
193 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
194 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
195 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
196 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
197 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
198 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
199 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
200 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
201 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
202 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
203 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
204 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
205 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
206 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
207 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
208 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
209 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
210 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
211 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
212 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
213 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
214 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
215 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
225 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
226 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
227 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
228 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
229 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
230 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
231 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
232 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
233 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
234 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
235 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
236 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
237 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
238 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
239 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
240 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
241 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
242 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
243 |
+
}
|
244 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1923 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3821579984474831,
|
5 |
+
"eval_steps": 400,
|
6 |
+
"global_step": 1600,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.00023884874902967696,
|
13 |
+
"eval_loss": 1.5979785919189453,
|
14 |
+
"eval_runtime": 224.9995,
|
15 |
+
"eval_samples_per_second": 3.778,
|
16 |
+
"eval_steps_per_second": 3.778,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.0014330924941780617,
|
21 |
+
"grad_norm": 20.875,
|
22 |
+
"learning_rate": 6.000000000000001e-07,
|
23 |
+
"loss": 1.8691,
|
24 |
+
"step": 6
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0028661849883561234,
|
28 |
+
"grad_norm": 14.0625,
|
29 |
+
"learning_rate": 1.2000000000000002e-06,
|
30 |
+
"loss": 1.8156,
|
31 |
+
"step": 12
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.004299277482534185,
|
35 |
+
"grad_norm": 11.1875,
|
36 |
+
"learning_rate": 1.8000000000000001e-06,
|
37 |
+
"loss": 1.6925,
|
38 |
+
"step": 18
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.005732369976712247,
|
42 |
+
"grad_norm": 7.15625,
|
43 |
+
"learning_rate": 2.4000000000000003e-06,
|
44 |
+
"loss": 1.612,
|
45 |
+
"step": 24
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0071654624708903086,
|
49 |
+
"grad_norm": 7.25,
|
50 |
+
"learning_rate": 3e-06,
|
51 |
+
"loss": 1.8222,
|
52 |
+
"step": 30
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.00859855496506837,
|
56 |
+
"grad_norm": 5.71875,
|
57 |
+
"learning_rate": 3.6000000000000003e-06,
|
58 |
+
"loss": 1.6277,
|
59 |
+
"step": 36
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.010031647459246432,
|
63 |
+
"grad_norm": 5.65625,
|
64 |
+
"learning_rate": 4.2000000000000004e-06,
|
65 |
+
"loss": 1.5655,
|
66 |
+
"step": 42
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.011464739953424494,
|
70 |
+
"grad_norm": 6.90625,
|
71 |
+
"learning_rate": 4.800000000000001e-06,
|
72 |
+
"loss": 1.7691,
|
73 |
+
"step": 48
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.012897832447602555,
|
77 |
+
"grad_norm": 6.96875,
|
78 |
+
"learning_rate": 5.400000000000001e-06,
|
79 |
+
"loss": 1.7085,
|
80 |
+
"step": 54
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.014330924941780617,
|
84 |
+
"grad_norm": 5.3125,
|
85 |
+
"learning_rate": 6e-06,
|
86 |
+
"loss": 1.4649,
|
87 |
+
"step": 60
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.01576401743595868,
|
91 |
+
"grad_norm": 15.8125,
|
92 |
+
"learning_rate": 6.600000000000001e-06,
|
93 |
+
"loss": 1.6534,
|
94 |
+
"step": 66
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.01719710993013674,
|
98 |
+
"grad_norm": 42.75,
|
99 |
+
"learning_rate": 7.2000000000000005e-06,
|
100 |
+
"loss": 1.673,
|
101 |
+
"step": 72
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.018630202424314804,
|
105 |
+
"grad_norm": 5.5,
|
106 |
+
"learning_rate": 7.800000000000002e-06,
|
107 |
+
"loss": 1.429,
|
108 |
+
"step": 78
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.020063294918492864,
|
112 |
+
"grad_norm": 3.875,
|
113 |
+
"learning_rate": 8.400000000000001e-06,
|
114 |
+
"loss": 1.6067,
|
115 |
+
"step": 84
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.021496387412670927,
|
119 |
+
"grad_norm": 4.53125,
|
120 |
+
"learning_rate": 9e-06,
|
121 |
+
"loss": 1.4336,
|
122 |
+
"step": 90
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.022929479906848987,
|
126 |
+
"grad_norm": 4.40625,
|
127 |
+
"learning_rate": 9.600000000000001e-06,
|
128 |
+
"loss": 1.5998,
|
129 |
+
"step": 96
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.02436257240102705,
|
133 |
+
"grad_norm": 5.40625,
|
134 |
+
"learning_rate": 1.02e-05,
|
135 |
+
"loss": 1.5259,
|
136 |
+
"step": 102
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.02579566489520511,
|
140 |
+
"grad_norm": 9.0,
|
141 |
+
"learning_rate": 1.0800000000000002e-05,
|
142 |
+
"loss": 1.5255,
|
143 |
+
"step": 108
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.027228757389383174,
|
147 |
+
"grad_norm": 5.34375,
|
148 |
+
"learning_rate": 1.14e-05,
|
149 |
+
"loss": 1.5375,
|
150 |
+
"step": 114
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.028661849883561234,
|
154 |
+
"grad_norm": 4.625,
|
155 |
+
"learning_rate": 1.2e-05,
|
156 |
+
"loss": 1.4729,
|
157 |
+
"step": 120
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.030094942377739298,
|
161 |
+
"grad_norm": 5.78125,
|
162 |
+
"learning_rate": 1.2600000000000001e-05,
|
163 |
+
"loss": 1.5446,
|
164 |
+
"step": 126
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.03152803487191736,
|
168 |
+
"grad_norm": 5.15625,
|
169 |
+
"learning_rate": 1.3200000000000002e-05,
|
170 |
+
"loss": 1.6895,
|
171 |
+
"step": 132
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.03296112736609542,
|
175 |
+
"grad_norm": 4.59375,
|
176 |
+
"learning_rate": 1.38e-05,
|
177 |
+
"loss": 1.6145,
|
178 |
+
"step": 138
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.03439421986027348,
|
182 |
+
"grad_norm": 4.96875,
|
183 |
+
"learning_rate": 1.4400000000000001e-05,
|
184 |
+
"loss": 1.4316,
|
185 |
+
"step": 144
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.035827312354451545,
|
189 |
+
"grad_norm": 4.71875,
|
190 |
+
"learning_rate": 1.5000000000000002e-05,
|
191 |
+
"loss": 1.5619,
|
192 |
+
"step": 150
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.03726040484862961,
|
196 |
+
"grad_norm": 7.9375,
|
197 |
+
"learning_rate": 1.5600000000000003e-05,
|
198 |
+
"loss": 1.6608,
|
199 |
+
"step": 156
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.038693497342807665,
|
203 |
+
"grad_norm": 4.34375,
|
204 |
+
"learning_rate": 1.62e-05,
|
205 |
+
"loss": 1.6418,
|
206 |
+
"step": 162
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.04012658983698573,
|
210 |
+
"grad_norm": 4.8125,
|
211 |
+
"learning_rate": 1.6800000000000002e-05,
|
212 |
+
"loss": 1.5532,
|
213 |
+
"step": 168
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.04155968233116379,
|
217 |
+
"grad_norm": 7.90625,
|
218 |
+
"learning_rate": 1.7400000000000003e-05,
|
219 |
+
"loss": 1.6124,
|
220 |
+
"step": 174
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.042992774825341855,
|
224 |
+
"grad_norm": 5.90625,
|
225 |
+
"learning_rate": 1.8e-05,
|
226 |
+
"loss": 1.5629,
|
227 |
+
"step": 180
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.04442586731951991,
|
231 |
+
"grad_norm": 9.4375,
|
232 |
+
"learning_rate": 1.86e-05,
|
233 |
+
"loss": 1.5727,
|
234 |
+
"step": 186
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.045858959813697975,
|
238 |
+
"grad_norm": 6.34375,
|
239 |
+
"learning_rate": 1.9200000000000003e-05,
|
240 |
+
"loss": 1.4866,
|
241 |
+
"step": 192
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.04729205230787604,
|
245 |
+
"grad_norm": 10.9375,
|
246 |
+
"learning_rate": 1.98e-05,
|
247 |
+
"loss": 1.6203,
|
248 |
+
"step": 198
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.0487251448020541,
|
252 |
+
"grad_norm": 5.46875,
|
253 |
+
"learning_rate": 1.9999756307053947e-05,
|
254 |
+
"loss": 1.6003,
|
255 |
+
"step": 204
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.05015823729623216,
|
259 |
+
"grad_norm": 7.34375,
|
260 |
+
"learning_rate": 1.9998476951563914e-05,
|
261 |
+
"loss": 1.7795,
|
262 |
+
"step": 210
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.05159132979041022,
|
266 |
+
"grad_norm": 5.03125,
|
267 |
+
"learning_rate": 1.9996101150403543e-05,
|
268 |
+
"loss": 1.6262,
|
269 |
+
"step": 216
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.053024422284588285,
|
273 |
+
"grad_norm": 6.03125,
|
274 |
+
"learning_rate": 1.999262916410621e-05,
|
275 |
+
"loss": 1.5033,
|
276 |
+
"step": 222
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.05445751477876635,
|
280 |
+
"grad_norm": 6.375,
|
281 |
+
"learning_rate": 1.9988061373414342e-05,
|
282 |
+
"loss": 1.528,
|
283 |
+
"step": 228
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.055890607272944405,
|
287 |
+
"grad_norm": 5.375,
|
288 |
+
"learning_rate": 1.9982398279237657e-05,
|
289 |
+
"loss": 1.6706,
|
290 |
+
"step": 234
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.05732369976712247,
|
294 |
+
"grad_norm": 5.3125,
|
295 |
+
"learning_rate": 1.9975640502598243e-05,
|
296 |
+
"loss": 1.8826,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.05875679226130053,
|
301 |
+
"grad_norm": 7.21875,
|
302 |
+
"learning_rate": 1.9967788784562474e-05,
|
303 |
+
"loss": 1.6844,
|
304 |
+
"step": 246
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.060189884755478595,
|
308 |
+
"grad_norm": 14.0,
|
309 |
+
"learning_rate": 1.9958843986159705e-05,
|
310 |
+
"loss": 1.6681,
|
311 |
+
"step": 252
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.06162297724965665,
|
315 |
+
"grad_norm": 5.3125,
|
316 |
+
"learning_rate": 1.9948807088287884e-05,
|
317 |
+
"loss": 1.5271,
|
318 |
+
"step": 258
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.06305606974383472,
|
322 |
+
"grad_norm": 5.78125,
|
323 |
+
"learning_rate": 1.9937679191605964e-05,
|
324 |
+
"loss": 1.5941,
|
325 |
+
"step": 264
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.06448916223801278,
|
329 |
+
"grad_norm": 7.75,
|
330 |
+
"learning_rate": 1.9925461516413224e-05,
|
331 |
+
"loss": 1.6754,
|
332 |
+
"step": 270
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.06592225473219084,
|
336 |
+
"grad_norm": 5.03125,
|
337 |
+
"learning_rate": 1.991215540251542e-05,
|
338 |
+
"loss": 1.6616,
|
339 |
+
"step": 276
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.0673553472263689,
|
343 |
+
"grad_norm": 5.46875,
|
344 |
+
"learning_rate": 1.989776230907789e-05,
|
345 |
+
"loss": 1.7207,
|
346 |
+
"step": 282
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.06878843972054696,
|
350 |
+
"grad_norm": 4.84375,
|
351 |
+
"learning_rate": 1.988228381446553e-05,
|
352 |
+
"loss": 1.6092,
|
353 |
+
"step": 288
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.07022153221472502,
|
357 |
+
"grad_norm": 15.625,
|
358 |
+
"learning_rate": 1.9865721616069695e-05,
|
359 |
+
"loss": 1.6828,
|
360 |
+
"step": 294
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.07165462470890309,
|
364 |
+
"grad_norm": 7.125,
|
365 |
+
"learning_rate": 1.9848077530122083e-05,
|
366 |
+
"loss": 1.7341,
|
367 |
+
"step": 300
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.07308771720308115,
|
371 |
+
"grad_norm": 10.625,
|
372 |
+
"learning_rate": 1.9829353491495545e-05,
|
373 |
+
"loss": 1.6181,
|
374 |
+
"step": 306
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.07452080969725922,
|
378 |
+
"grad_norm": 4.75,
|
379 |
+
"learning_rate": 1.9809551553491918e-05,
|
380 |
+
"loss": 1.548,
|
381 |
+
"step": 312
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.07595390219143727,
|
385 |
+
"grad_norm": 6.9375,
|
386 |
+
"learning_rate": 1.9788673887616852e-05,
|
387 |
+
"loss": 1.5703,
|
388 |
+
"step": 318
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.07738699468561533,
|
392 |
+
"grad_norm": 6.71875,
|
393 |
+
"learning_rate": 1.9766722783341682e-05,
|
394 |
+
"loss": 1.7147,
|
395 |
+
"step": 324
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.0788200871797934,
|
399 |
+
"grad_norm": 6.8125,
|
400 |
+
"learning_rate": 1.9743700647852356e-05,
|
401 |
+
"loss": 1.7598,
|
402 |
+
"step": 330
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.08025317967397146,
|
406 |
+
"grad_norm": 5.0625,
|
407 |
+
"learning_rate": 1.9719610005785466e-05,
|
408 |
+
"loss": 1.7136,
|
409 |
+
"step": 336
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.08168627216814951,
|
413 |
+
"grad_norm": 6.03125,
|
414 |
+
"learning_rate": 1.9694453498951392e-05,
|
415 |
+
"loss": 1.7161,
|
416 |
+
"step": 342
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.08311936466232758,
|
420 |
+
"grad_norm": 7.34375,
|
421 |
+
"learning_rate": 1.9668233886044597e-05,
|
422 |
+
"loss": 1.6319,
|
423 |
+
"step": 348
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.08455245715650564,
|
427 |
+
"grad_norm": 5.21875,
|
428 |
+
"learning_rate": 1.96409540423411e-05,
|
429 |
+
"loss": 1.5857,
|
430 |
+
"step": 354
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.08598554965068371,
|
434 |
+
"grad_norm": 10.6875,
|
435 |
+
"learning_rate": 1.961261695938319e-05,
|
436 |
+
"loss": 1.7632,
|
437 |
+
"step": 360
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.08741864214486177,
|
441 |
+
"grad_norm": 6.21875,
|
442 |
+
"learning_rate": 1.9583225744651334e-05,
|
443 |
+
"loss": 1.4205,
|
444 |
+
"step": 366
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.08885173463903982,
|
448 |
+
"grad_norm": 5.875,
|
449 |
+
"learning_rate": 1.9552783621223437e-05,
|
450 |
+
"loss": 1.7812,
|
451 |
+
"step": 372
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.0902848271332179,
|
455 |
+
"grad_norm": 4.46875,
|
456 |
+
"learning_rate": 1.9521293927421388e-05,
|
457 |
+
"loss": 1.5759,
|
458 |
+
"step": 378
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.09171791962739595,
|
462 |
+
"grad_norm": 6.53125,
|
463 |
+
"learning_rate": 1.9488760116444966e-05,
|
464 |
+
"loss": 1.6537,
|
465 |
+
"step": 384
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.09315101212157402,
|
469 |
+
"grad_norm": 10.8125,
|
470 |
+
"learning_rate": 1.945518575599317e-05,
|
471 |
+
"loss": 1.4973,
|
472 |
+
"step": 390
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.09458410461575208,
|
476 |
+
"grad_norm": 4.1875,
|
477 |
+
"learning_rate": 1.942057452787297e-05,
|
478 |
+
"loss": 1.578,
|
479 |
+
"step": 396
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.09553949961187078,
|
483 |
+
"eval_loss": 1.4027706384658813,
|
484 |
+
"eval_runtime": 224.2305,
|
485 |
+
"eval_samples_per_second": 3.791,
|
486 |
+
"eval_steps_per_second": 3.791,
|
487 |
+
"step": 400
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.09601719710993013,
|
491 |
+
"grad_norm": 3.875,
|
492 |
+
"learning_rate": 1.938493022759556e-05,
|
493 |
+
"loss": 1.6032,
|
494 |
+
"step": 402
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.0974502896041082,
|
498 |
+
"grad_norm": 6.125,
|
499 |
+
"learning_rate": 1.9348256763960146e-05,
|
500 |
+
"loss": 1.7055,
|
501 |
+
"step": 408
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.09888338209828626,
|
505 |
+
"grad_norm": 5.84375,
|
506 |
+
"learning_rate": 1.9310558158625286e-05,
|
507 |
+
"loss": 1.7454,
|
508 |
+
"step": 414
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.10031647459246432,
|
512 |
+
"grad_norm": 7.0625,
|
513 |
+
"learning_rate": 1.9271838545667876e-05,
|
514 |
+
"loss": 1.7345,
|
515 |
+
"step": 420
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.10174956708664239,
|
519 |
+
"grad_norm": 6.125,
|
520 |
+
"learning_rate": 1.923210217112981e-05,
|
521 |
+
"loss": 1.6099,
|
522 |
+
"step": 426
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.10318265958082044,
|
526 |
+
"grad_norm": 4.59375,
|
527 |
+
"learning_rate": 1.9191353392552346e-05,
|
528 |
+
"loss": 1.652,
|
529 |
+
"step": 432
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.10461575207499851,
|
533 |
+
"grad_norm": 5.96875,
|
534 |
+
"learning_rate": 1.914959667849825e-05,
|
535 |
+
"loss": 1.7092,
|
536 |
+
"step": 438
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.10604884456917657,
|
540 |
+
"grad_norm": 6.4375,
|
541 |
+
"learning_rate": 1.910683660806177e-05,
|
542 |
+
"loss": 1.7545,
|
543 |
+
"step": 444
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.10748193706335463,
|
547 |
+
"grad_norm": 10.4375,
|
548 |
+
"learning_rate": 1.9063077870366504e-05,
|
549 |
+
"loss": 1.5287,
|
550 |
+
"step": 450
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.1089150295575327,
|
554 |
+
"grad_norm": 7.84375,
|
555 |
+
"learning_rate": 1.901832526405114e-05,
|
556 |
+
"loss": 1.7219,
|
557 |
+
"step": 456
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.11034812205171075,
|
561 |
+
"grad_norm": 9.5625,
|
562 |
+
"learning_rate": 1.8972583696743284e-05,
|
563 |
+
"loss": 1.665,
|
564 |
+
"step": 462
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.11178121454588881,
|
568 |
+
"grad_norm": 10.0625,
|
569 |
+
"learning_rate": 1.892585818452126e-05,
|
570 |
+
"loss": 1.6363,
|
571 |
+
"step": 468
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.11321430704006688,
|
575 |
+
"grad_norm": 5.78125,
|
576 |
+
"learning_rate": 1.8878153851364013e-05,
|
577 |
+
"loss": 1.543,
|
578 |
+
"step": 474
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.11464739953424494,
|
582 |
+
"grad_norm": 6.125,
|
583 |
+
"learning_rate": 1.8829475928589272e-05,
|
584 |
+
"loss": 1.5826,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.11608049202842301,
|
589 |
+
"grad_norm": 4.8125,
|
590 |
+
"learning_rate": 1.8779829754279806e-05,
|
591 |
+
"loss": 1.581,
|
592 |
+
"step": 486
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.11751358452260106,
|
596 |
+
"grad_norm": 9.75,
|
597 |
+
"learning_rate": 1.8729220772698096e-05,
|
598 |
+
"loss": 1.5841,
|
599 |
+
"step": 492
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.11894667701677912,
|
603 |
+
"grad_norm": 13.3125,
|
604 |
+
"learning_rate": 1.8677654533689287e-05,
|
605 |
+
"loss": 1.6944,
|
606 |
+
"step": 498
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.12037976951095719,
|
610 |
+
"grad_norm": 4.96875,
|
611 |
+
"learning_rate": 1.8625136692072577e-05,
|
612 |
+
"loss": 1.6203,
|
613 |
+
"step": 504
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.12181286200513525,
|
617 |
+
"grad_norm": 6.3125,
|
618 |
+
"learning_rate": 1.8571673007021124e-05,
|
619 |
+
"loss": 1.5639,
|
620 |
+
"step": 510
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.1232459544993133,
|
624 |
+
"grad_norm": 5.5,
|
625 |
+
"learning_rate": 1.851726934143048e-05,
|
626 |
+
"loss": 1.6397,
|
627 |
+
"step": 516
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.12467904699349137,
|
631 |
+
"grad_norm": 5.125,
|
632 |
+
"learning_rate": 1.8461931661275642e-05,
|
633 |
+
"loss": 1.7315,
|
634 |
+
"step": 522
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.12611213948766944,
|
638 |
+
"grad_norm": 6.25,
|
639 |
+
"learning_rate": 1.8405666034956842e-05,
|
640 |
+
"loss": 1.7201,
|
641 |
+
"step": 528
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.1275452319818475,
|
645 |
+
"grad_norm": 8.9375,
|
646 |
+
"learning_rate": 1.8348478632634067e-05,
|
647 |
+
"loss": 1.6047,
|
648 |
+
"step": 534
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.12897832447602556,
|
652 |
+
"grad_norm": 46.25,
|
653 |
+
"learning_rate": 1.8290375725550417e-05,
|
654 |
+
"loss": 1.6949,
|
655 |
+
"step": 540
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.13041141697020361,
|
659 |
+
"grad_norm": 5.9375,
|
660 |
+
"learning_rate": 1.8231363685344422e-05,
|
661 |
+
"loss": 1.7245,
|
662 |
+
"step": 546
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.13184450946438167,
|
666 |
+
"grad_norm": 5.78125,
|
667 |
+
"learning_rate": 1.8171448983351284e-05,
|
668 |
+
"loss": 1.641,
|
669 |
+
"step": 552
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.13327760195855975,
|
673 |
+
"grad_norm": 24.125,
|
674 |
+
"learning_rate": 1.8110638189893267e-05,
|
675 |
+
"loss": 1.6125,
|
676 |
+
"step": 558
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.1347106944527378,
|
680 |
+
"grad_norm": 6.4375,
|
681 |
+
"learning_rate": 1.804893797355914e-05,
|
682 |
+
"loss": 1.6647,
|
683 |
+
"step": 564
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.13614378694691587,
|
687 |
+
"grad_norm": 6.34375,
|
688 |
+
"learning_rate": 1.798635510047293e-05,
|
689 |
+
"loss": 1.7073,
|
690 |
+
"step": 570
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.13757687944109392,
|
694 |
+
"grad_norm": 6.1875,
|
695 |
+
"learning_rate": 1.792289643355191e-05,
|
696 |
+
"loss": 1.6271,
|
697 |
+
"step": 576
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.13900997193527198,
|
701 |
+
"grad_norm": 5.0625,
|
702 |
+
"learning_rate": 1.785856893175402e-05,
|
703 |
+
"loss": 1.6317,
|
704 |
+
"step": 582
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.14044306442945004,
|
708 |
+
"grad_norm": 4.6875,
|
709 |
+
"learning_rate": 1.7793379649314743e-05,
|
710 |
+
"loss": 1.6578,
|
711 |
+
"step": 588
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.14187615692362812,
|
715 |
+
"grad_norm": 4.84375,
|
716 |
+
"learning_rate": 1.7727335734973512e-05,
|
717 |
+
"loss": 1.6554,
|
718 |
+
"step": 594
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.14330924941780618,
|
722 |
+
"grad_norm": 6.1875,
|
723 |
+
"learning_rate": 1.766044443118978e-05,
|
724 |
+
"loss": 1.5523,
|
725 |
+
"step": 600
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.14474234191198423,
|
729 |
+
"grad_norm": 23.375,
|
730 |
+
"learning_rate": 1.759271307334881e-05,
|
731 |
+
"loss": 1.616,
|
732 |
+
"step": 606
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.1461754344061623,
|
736 |
+
"grad_norm": 6.9375,
|
737 |
+
"learning_rate": 1.7524149088957244e-05,
|
738 |
+
"loss": 1.7729,
|
739 |
+
"step": 612
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.14760852690034035,
|
743 |
+
"grad_norm": 10.25,
|
744 |
+
"learning_rate": 1.7454759996828622e-05,
|
745 |
+
"loss": 1.5922,
|
746 |
+
"step": 618
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.14904161939451843,
|
750 |
+
"grad_norm": 7.21875,
|
751 |
+
"learning_rate": 1.7384553406258842e-05,
|
752 |
+
"loss": 1.583,
|
753 |
+
"step": 624
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.1504747118886965,
|
757 |
+
"grad_norm": 6.9375,
|
758 |
+
"learning_rate": 1.7313537016191706e-05,
|
759 |
+
"loss": 1.6019,
|
760 |
+
"step": 630
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.15190780438287455,
|
764 |
+
"grad_norm": 11.5,
|
765 |
+
"learning_rate": 1.7241718614374678e-05,
|
766 |
+
"loss": 1.6195,
|
767 |
+
"step": 636
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.1533408968770526,
|
771 |
+
"grad_norm": 5.5,
|
772 |
+
"learning_rate": 1.716910607650483e-05,
|
773 |
+
"loss": 1.5012,
|
774 |
+
"step": 642
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.15477398937123066,
|
778 |
+
"grad_norm": 6.71875,
|
779 |
+
"learning_rate": 1.709570736536521e-05,
|
780 |
+
"loss": 1.7686,
|
781 |
+
"step": 648
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.15620708186540874,
|
785 |
+
"grad_norm": 5.71875,
|
786 |
+
"learning_rate": 1.7021530529951627e-05,
|
787 |
+
"loss": 1.7922,
|
788 |
+
"step": 654
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.1576401743595868,
|
792 |
+
"grad_norm": 7.8125,
|
793 |
+
"learning_rate": 1.6946583704589973e-05,
|
794 |
+
"loss": 1.623,
|
795 |
+
"step": 660
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.15907326685376486,
|
799 |
+
"grad_norm": 6.34375,
|
800 |
+
"learning_rate": 1.6870875108044233e-05,
|
801 |
+
"loss": 1.6039,
|
802 |
+
"step": 666
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.1605063593479429,
|
806 |
+
"grad_norm": 6.46875,
|
807 |
+
"learning_rate": 1.6794413042615168e-05,
|
808 |
+
"loss": 1.6392,
|
809 |
+
"step": 672
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.16193945184212097,
|
813 |
+
"grad_norm": 5.4375,
|
814 |
+
"learning_rate": 1.6717205893229904e-05,
|
815 |
+
"loss": 1.5683,
|
816 |
+
"step": 678
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.16337254433629902,
|
820 |
+
"grad_norm": 4.78125,
|
821 |
+
"learning_rate": 1.6639262126522417e-05,
|
822 |
+
"loss": 1.6165,
|
823 |
+
"step": 684
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.1648056368304771,
|
827 |
+
"grad_norm": 5.4375,
|
828 |
+
"learning_rate": 1.6560590289905074e-05,
|
829 |
+
"loss": 1.5341,
|
830 |
+
"step": 690
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.16623872932465517,
|
834 |
+
"grad_norm": 5.25,
|
835 |
+
"learning_rate": 1.6481199010631312e-05,
|
836 |
+
"loss": 1.6573,
|
837 |
+
"step": 696
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.16767182181883322,
|
841 |
+
"grad_norm": 5.21875,
|
842 |
+
"learning_rate": 1.6401096994849558e-05,
|
843 |
+
"loss": 1.5056,
|
844 |
+
"step": 702
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.16910491431301128,
|
848 |
+
"grad_norm": 12.625,
|
849 |
+
"learning_rate": 1.632029302664851e-05,
|
850 |
+
"loss": 1.5337,
|
851 |
+
"step": 708
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.17053800680718934,
|
855 |
+
"grad_norm": 4.28125,
|
856 |
+
"learning_rate": 1.6238795967093865e-05,
|
857 |
+
"loss": 1.5038,
|
858 |
+
"step": 714
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.17197109930136742,
|
862 |
+
"grad_norm": 6.96875,
|
863 |
+
"learning_rate": 1.6156614753256583e-05,
|
864 |
+
"loss": 1.5587,
|
865 |
+
"step": 720
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.17340419179554548,
|
869 |
+
"grad_norm": 4.90625,
|
870 |
+
"learning_rate": 1.607375839723287e-05,
|
871 |
+
"loss": 1.563,
|
872 |
+
"step": 726
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.17483728428972353,
|
876 |
+
"grad_norm": 5.34375,
|
877 |
+
"learning_rate": 1.599023598515586e-05,
|
878 |
+
"loss": 1.6058,
|
879 |
+
"step": 732
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.1762703767839016,
|
883 |
+
"grad_norm": 5.25,
|
884 |
+
"learning_rate": 1.5906056676199256e-05,
|
885 |
+
"loss": 1.7244,
|
886 |
+
"step": 738
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.17770346927807965,
|
890 |
+
"grad_norm": 4.5,
|
891 |
+
"learning_rate": 1.5821229701572897e-05,
|
892 |
+
"loss": 1.6587,
|
893 |
+
"step": 744
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.17913656177225773,
|
897 |
+
"grad_norm": 12.75,
|
898 |
+
"learning_rate": 1.573576436351046e-05,
|
899 |
+
"loss": 1.6018,
|
900 |
+
"step": 750
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.1805696542664358,
|
904 |
+
"grad_norm": 6.0,
|
905 |
+
"learning_rate": 1.564967003424938e-05,
|
906 |
+
"loss": 1.6205,
|
907 |
+
"step": 756
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.18200274676061384,
|
911 |
+
"grad_norm": 5.59375,
|
912 |
+
"learning_rate": 1.556295615500305e-05,
|
913 |
+
"loss": 1.6345,
|
914 |
+
"step": 762
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.1834358392547919,
|
918 |
+
"grad_norm": 4.59375,
|
919 |
+
"learning_rate": 1.5475632234925505e-05,
|
920 |
+
"loss": 1.5226,
|
921 |
+
"step": 768
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.18486893174896996,
|
925 |
+
"grad_norm": 4.78125,
|
926 |
+
"learning_rate": 1.5387707850068633e-05,
|
927 |
+
"loss": 1.6488,
|
928 |
+
"step": 774
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.18630202424314804,
|
932 |
+
"grad_norm": 4.28125,
|
933 |
+
"learning_rate": 1.529919264233205e-05,
|
934 |
+
"loss": 1.5393,
|
935 |
+
"step": 780
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.1877351167373261,
|
939 |
+
"grad_norm": 7.625,
|
940 |
+
"learning_rate": 1.5210096318405768e-05,
|
941 |
+
"loss": 1.5374,
|
942 |
+
"step": 786
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.18916820923150415,
|
946 |
+
"grad_norm": 4.21875,
|
947 |
+
"learning_rate": 1.5120428648705716e-05,
|
948 |
+
"loss": 1.4963,
|
949 |
+
"step": 792
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.1906013017256822,
|
953 |
+
"grad_norm": 4.25,
|
954 |
+
"learning_rate": 1.5030199466302354e-05,
|
955 |
+
"loss": 1.5828,
|
956 |
+
"step": 798
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.19107899922374155,
|
960 |
+
"eval_loss": 1.3809266090393066,
|
961 |
+
"eval_runtime": 223.0505,
|
962 |
+
"eval_samples_per_second": 3.811,
|
963 |
+
"eval_steps_per_second": 3.811,
|
964 |
+
"step": 800
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.19203439421986027,
|
968 |
+
"grad_norm": 6.21875,
|
969 |
+
"learning_rate": 1.493941866584231e-05,
|
970 |
+
"loss": 1.5799,
|
971 |
+
"step": 804
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.19346748671403832,
|
975 |
+
"grad_norm": 8.5,
|
976 |
+
"learning_rate": 1.4848096202463373e-05,
|
977 |
+
"loss": 1.6519,
|
978 |
+
"step": 810
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.1949005792082164,
|
982 |
+
"grad_norm": 4.59375,
|
983 |
+
"learning_rate": 1.4756242090702756e-05,
|
984 |
+
"loss": 1.5897,
|
985 |
+
"step": 816
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 0.19633367170239446,
|
989 |
+
"grad_norm": 5.75,
|
990 |
+
"learning_rate": 1.4663866403398915e-05,
|
991 |
+
"loss": 1.6454,
|
992 |
+
"step": 822
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.19776676419657252,
|
996 |
+
"grad_norm": 4.1875,
|
997 |
+
"learning_rate": 1.4570979270586944e-05,
|
998 |
+
"loss": 1.5361,
|
999 |
+
"step": 828
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.19919985669075058,
|
1003 |
+
"grad_norm": 5.375,
|
1004 |
+
"learning_rate": 1.4477590878387697e-05,
|
1005 |
+
"loss": 1.5086,
|
1006 |
+
"step": 834
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.20063294918492863,
|
1010 |
+
"grad_norm": 4.375,
|
1011 |
+
"learning_rate": 1.4383711467890776e-05,
|
1012 |
+
"loss": 1.6474,
|
1013 |
+
"step": 840
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 0.20206604167910672,
|
1017 |
+
"grad_norm": 4.6875,
|
1018 |
+
"learning_rate": 1.4289351334031461e-05,
|
1019 |
+
"loss": 1.465,
|
1020 |
+
"step": 846
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.20349913417328477,
|
1024 |
+
"grad_norm": 8.6875,
|
1025 |
+
"learning_rate": 1.4194520824461773e-05,
|
1026 |
+
"loss": 1.5312,
|
1027 |
+
"step": 852
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 0.20493222666746283,
|
1031 |
+
"grad_norm": 5.53125,
|
1032 |
+
"learning_rate": 1.4099230338415728e-05,
|
1033 |
+
"loss": 1.4775,
|
1034 |
+
"step": 858
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.2063653191616409,
|
1038 |
+
"grad_norm": 9.8125,
|
1039 |
+
"learning_rate": 1.4003490325568953e-05,
|
1040 |
+
"loss": 1.8343,
|
1041 |
+
"step": 864
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.20779841165581894,
|
1045 |
+
"grad_norm": 8.0625,
|
1046 |
+
"learning_rate": 1.3907311284892737e-05,
|
1047 |
+
"loss": 1.537,
|
1048 |
+
"step": 870
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 0.20923150414999703,
|
1052 |
+
"grad_norm": 6.3125,
|
1053 |
+
"learning_rate": 1.3810703763502744e-05,
|
1054 |
+
"loss": 1.7239,
|
1055 |
+
"step": 876
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 0.21066459664417508,
|
1059 |
+
"grad_norm": 5.75,
|
1060 |
+
"learning_rate": 1.371367835550235e-05,
|
1061 |
+
"loss": 1.5176,
|
1062 |
+
"step": 882
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 0.21209768913835314,
|
1066 |
+
"grad_norm": 4.65625,
|
1067 |
+
"learning_rate": 1.3616245700820922e-05,
|
1068 |
+
"loss": 1.641,
|
1069 |
+
"step": 888
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 0.2135307816325312,
|
1073 |
+
"grad_norm": 4.0625,
|
1074 |
+
"learning_rate": 1.3518416484047018e-05,
|
1075 |
+
"loss": 1.5882,
|
1076 |
+
"step": 894
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.21496387412670925,
|
1080 |
+
"grad_norm": 5.09375,
|
1081 |
+
"learning_rate": 1.342020143325669e-05,
|
1082 |
+
"loss": 1.6042,
|
1083 |
+
"step": 900
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.2163969666208873,
|
1087 |
+
"grad_norm": 5.84375,
|
1088 |
+
"learning_rate": 1.3321611318837033e-05,
|
1089 |
+
"loss": 1.5516,
|
1090 |
+
"step": 906
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 0.2178300591150654,
|
1094 |
+
"grad_norm": 6.15625,
|
1095 |
+
"learning_rate": 1.3222656952305113e-05,
|
1096 |
+
"loss": 1.5349,
|
1097 |
+
"step": 912
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 0.21926315160924345,
|
1101 |
+
"grad_norm": 5.21875,
|
1102 |
+
"learning_rate": 1.3123349185122328e-05,
|
1103 |
+
"loss": 1.6652,
|
1104 |
+
"step": 918
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.2206962441034215,
|
1108 |
+
"grad_norm": 17.25,
|
1109 |
+
"learning_rate": 1.3023698907504447e-05,
|
1110 |
+
"loss": 1.7149,
|
1111 |
+
"step": 924
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 0.22212933659759956,
|
1115 |
+
"grad_norm": 6.8125,
|
1116 |
+
"learning_rate": 1.2923717047227368e-05,
|
1117 |
+
"loss": 1.6285,
|
1118 |
+
"step": 930
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.22356242909177762,
|
1122 |
+
"grad_norm": 4.1875,
|
1123 |
+
"learning_rate": 1.2823414568428767e-05,
|
1124 |
+
"loss": 1.5982,
|
1125 |
+
"step": 936
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.2249955215859557,
|
1129 |
+
"grad_norm": 5.8125,
|
1130 |
+
"learning_rate": 1.2722802470405744e-05,
|
1131 |
+
"loss": 1.5901,
|
1132 |
+
"step": 942
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.22642861408013376,
|
1136 |
+
"grad_norm": 4.75,
|
1137 |
+
"learning_rate": 1.2621891786408648e-05,
|
1138 |
+
"loss": 1.5705,
|
1139 |
+
"step": 948
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 0.22786170657431182,
|
1143 |
+
"grad_norm": 10.1875,
|
1144 |
+
"learning_rate": 1.252069358243114e-05,
|
1145 |
+
"loss": 1.5263,
|
1146 |
+
"step": 954
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 0.22929479906848987,
|
1150 |
+
"grad_norm": 3.671875,
|
1151 |
+
"learning_rate": 1.2419218955996677e-05,
|
1152 |
+
"loss": 1.5622,
|
1153 |
+
"step": 960
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 0.23072789156266793,
|
1157 |
+
"grad_norm": 4.625,
|
1158 |
+
"learning_rate": 1.2317479034941572e-05,
|
1159 |
+
"loss": 1.5984,
|
1160 |
+
"step": 966
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.23216098405684601,
|
1164 |
+
"grad_norm": 7.21875,
|
1165 |
+
"learning_rate": 1.2215484976194675e-05,
|
1166 |
+
"loss": 1.6465,
|
1167 |
+
"step": 972
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.23359407655102407,
|
1171 |
+
"grad_norm": 6.59375,
|
1172 |
+
"learning_rate": 1.211324796455389e-05,
|
1173 |
+
"loss": 1.705,
|
1174 |
+
"step": 978
|
1175 |
+
},
|
1176 |
+
{
|
1177 |
+
"epoch": 0.23502716904520213,
|
1178 |
+
"grad_norm": 5.96875,
|
1179 |
+
"learning_rate": 1.2010779211459649e-05,
|
1180 |
+
"loss": 1.5316,
|
1181 |
+
"step": 984
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 0.23646026153938018,
|
1185 |
+
"grad_norm": 5.3125,
|
1186 |
+
"learning_rate": 1.190808995376545e-05,
|
1187 |
+
"loss": 1.4676,
|
1188 |
+
"step": 990
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 0.23789335403355824,
|
1192 |
+
"grad_norm": 4.9375,
|
1193 |
+
"learning_rate": 1.1805191452505602e-05,
|
1194 |
+
"loss": 1.5319,
|
1195 |
+
"step": 996
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"epoch": 0.2393264465277363,
|
1199 |
+
"grad_norm": 5.625,
|
1200 |
+
"learning_rate": 1.1702094991660326e-05,
|
1201 |
+
"loss": 1.6112,
|
1202 |
+
"step": 1002
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.24075953902191438,
|
1206 |
+
"grad_norm": 4.71875,
|
1207 |
+
"learning_rate": 1.159881187691835e-05,
|
1208 |
+
"loss": 1.6341,
|
1209 |
+
"step": 1008
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.24219263151609244,
|
1213 |
+
"grad_norm": 4.3125,
|
1214 |
+
"learning_rate": 1.1495353434437098e-05,
|
1215 |
+
"loss": 1.4623,
|
1216 |
+
"step": 1014
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 0.2436257240102705,
|
1220 |
+
"grad_norm": 19.625,
|
1221 |
+
"learning_rate": 1.1391731009600655e-05,
|
1222 |
+
"loss": 1.4166,
|
1223 |
+
"step": 1020
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 0.24505881650444855,
|
1227 |
+
"grad_norm": 4.0625,
|
1228 |
+
"learning_rate": 1.128795596577563e-05,
|
1229 |
+
"loss": 1.5813,
|
1230 |
+
"step": 1026
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 0.2464919089986266,
|
1234 |
+
"grad_norm": 6.25,
|
1235 |
+
"learning_rate": 1.1184039683065014e-05,
|
1236 |
+
"loss": 1.5772,
|
1237 |
+
"step": 1032
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 0.2479250014928047,
|
1241 |
+
"grad_norm": 5.53125,
|
1242 |
+
"learning_rate": 1.1079993557060228e-05,
|
1243 |
+
"loss": 1.401,
|
1244 |
+
"step": 1038
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.24935809398698275,
|
1248 |
+
"grad_norm": 6.65625,
|
1249 |
+
"learning_rate": 1.0975828997591496e-05,
|
1250 |
+
"loss": 1.6248,
|
1251 |
+
"step": 1044
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.2507911864811608,
|
1255 |
+
"grad_norm": 856.0,
|
1256 |
+
"learning_rate": 1.0871557427476585e-05,
|
1257 |
+
"loss": 1.775,
|
1258 |
+
"step": 1050
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 0.2522242789753389,
|
1262 |
+
"grad_norm": 4.1875,
|
1263 |
+
"learning_rate": 1.0767190281268187e-05,
|
1264 |
+
"loss": 1.586,
|
1265 |
+
"step": 1056
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 0.25365737146951695,
|
1269 |
+
"grad_norm": 3.53125,
|
1270 |
+
"learning_rate": 1.0662739004000005e-05,
|
1271 |
+
"loss": 1.5397,
|
1272 |
+
"step": 1062
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 0.255090463963695,
|
1276 |
+
"grad_norm": 4.125,
|
1277 |
+
"learning_rate": 1.055821504993164e-05,
|
1278 |
+
"loss": 1.8712,
|
1279 |
+
"step": 1068
|
1280 |
+
},
|
1281 |
+
{
|
1282 |
+
"epoch": 0.25652355645787306,
|
1283 |
+
"grad_norm": 5.1875,
|
1284 |
+
"learning_rate": 1.0453629881292537e-05,
|
1285 |
+
"loss": 1.5357,
|
1286 |
+
"step": 1074
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.2579566489520511,
|
1290 |
+
"grad_norm": 3.921875,
|
1291 |
+
"learning_rate": 1.0348994967025012e-05,
|
1292 |
+
"loss": 1.4033,
|
1293 |
+
"step": 1080
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.25938974144622917,
|
1297 |
+
"grad_norm": 5.3125,
|
1298 |
+
"learning_rate": 1.0244321781526533e-05,
|
1299 |
+
"loss": 1.5611,
|
1300 |
+
"step": 1086
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.26082283394040723,
|
1304 |
+
"grad_norm": 4.8125,
|
1305 |
+
"learning_rate": 1.0139621803391454e-05,
|
1306 |
+
"loss": 1.577,
|
1307 |
+
"step": 1092
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 0.2622559264345853,
|
1311 |
+
"grad_norm": 5.46875,
|
1312 |
+
"learning_rate": 1.0034906514152239e-05,
|
1313 |
+
"loss": 1.5149,
|
1314 |
+
"step": 1098
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.26368901892876334,
|
1318 |
+
"grad_norm": 6.4375,
|
1319 |
+
"learning_rate": 9.930187397020385e-06,
|
1320 |
+
"loss": 1.5796,
|
1321 |
+
"step": 1104
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 0.2651221114229414,
|
1325 |
+
"grad_norm": 4.28125,
|
1326 |
+
"learning_rate": 9.825475935627165e-06,
|
1327 |
+
"loss": 1.5702,
|
1328 |
+
"step": 1110
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 0.2665552039171195,
|
1332 |
+
"grad_norm": 5.34375,
|
1333 |
+
"learning_rate": 9.720783612764314e-06,
|
1334 |
+
"loss": 1.5354,
|
1335 |
+
"step": 1116
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.26798829641129757,
|
1339 |
+
"grad_norm": 4.375,
|
1340 |
+
"learning_rate": 9.616121909124801e-06,
|
1341 |
+
"loss": 1.4122,
|
1342 |
+
"step": 1122
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.2694213889054756,
|
1346 |
+
"grad_norm": 5.46875,
|
1347 |
+
"learning_rate": 9.511502302043867e-06,
|
1348 |
+
"loss": 1.6959,
|
1349 |
+
"step": 1128
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 0.2708544813996537,
|
1353 |
+
"grad_norm": 8.4375,
|
1354 |
+
"learning_rate": 9.406936264240386e-06,
|
1355 |
+
"loss": 1.5493,
|
1356 |
+
"step": 1134
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 0.27228757389383174,
|
1360 |
+
"grad_norm": 5.46875,
|
1361 |
+
"learning_rate": 9.302435262558748e-06,
|
1362 |
+
"loss": 1.4156,
|
1363 |
+
"step": 1140
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 0.2737206663880098,
|
1367 |
+
"grad_norm": 720.0,
|
1368 |
+
"learning_rate": 9.198010756711413e-06,
|
1369 |
+
"loss": 1.567,
|
1370 |
+
"step": 1146
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.27515375888218785,
|
1374 |
+
"grad_norm": 3.875,
|
1375 |
+
"learning_rate": 9.093674198022201e-06,
|
1376 |
+
"loss": 1.3814,
|
1377 |
+
"step": 1152
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.2765868513763659,
|
1381 |
+
"grad_norm": 3.671875,
|
1382 |
+
"learning_rate": 8.989437028170537e-06,
|
1383 |
+
"loss": 1.4261,
|
1384 |
+
"step": 1158
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 0.27801994387054396,
|
1388 |
+
"grad_norm": 10.375,
|
1389 |
+
"learning_rate": 8.885310677936746e-06,
|
1390 |
+
"loss": 1.506,
|
1391 |
+
"step": 1164
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 0.279453036364722,
|
1395 |
+
"grad_norm": 3.46875,
|
1396 |
+
"learning_rate": 8.781306565948528e-06,
|
1397 |
+
"loss": 1.3967,
|
1398 |
+
"step": 1170
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.2808861288589001,
|
1402 |
+
"grad_norm": 3.984375,
|
1403 |
+
"learning_rate": 8.677436097428775e-06,
|
1404 |
+
"loss": 1.5761,
|
1405 |
+
"step": 1176
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 0.2823192213530782,
|
1409 |
+
"grad_norm": 3.484375,
|
1410 |
+
"learning_rate": 8.573710662944884e-06,
|
1411 |
+
"loss": 1.5428,
|
1412 |
+
"step": 1182
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 0.28375231384725624,
|
1416 |
+
"grad_norm": 6.25,
|
1417 |
+
"learning_rate": 8.47014163715962e-06,
|
1418 |
+
"loss": 1.5426,
|
1419 |
+
"step": 1188
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.2851854063414343,
|
1423 |
+
"grad_norm": 6.25,
|
1424 |
+
"learning_rate": 8.366740377583781e-06,
|
1425 |
+
"loss": 1.503,
|
1426 |
+
"step": 1194
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 0.28661849883561236,
|
1430 |
+
"grad_norm": 3.828125,
|
1431 |
+
"learning_rate": 8.263518223330698e-06,
|
1432 |
+
"loss": 1.4355,
|
1433 |
+
"step": 1200
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 0.28661849883561236,
|
1437 |
+
"eval_loss": 1.315157413482666,
|
1438 |
+
"eval_runtime": 223.8181,
|
1439 |
+
"eval_samples_per_second": 3.798,
|
1440 |
+
"eval_steps_per_second": 3.798,
|
1441 |
+
"step": 1200
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 0.2880515913297904,
|
1445 |
+
"grad_norm": 5.625,
|
1446 |
+
"learning_rate": 8.1604864938728e-06,
|
1447 |
+
"loss": 1.4389,
|
1448 |
+
"step": 1206
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 0.28948468382396847,
|
1452 |
+
"grad_norm": 5.0625,
|
1453 |
+
"learning_rate": 8.057656487800283e-06,
|
1454 |
+
"loss": 1.5346,
|
1455 |
+
"step": 1212
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.2909177763181465,
|
1459 |
+
"grad_norm": 4.21875,
|
1460 |
+
"learning_rate": 7.955039481582098e-06,
|
1461 |
+
"loss": 1.4492,
|
1462 |
+
"step": 1218
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 0.2923508688123246,
|
1466 |
+
"grad_norm": 4.9375,
|
1467 |
+
"learning_rate": 7.852646728329368e-06,
|
1468 |
+
"loss": 1.4305,
|
1469 |
+
"step": 1224
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 0.29378396130650264,
|
1473 |
+
"grad_norm": 4.9375,
|
1474 |
+
"learning_rate": 7.750489456561351e-06,
|
1475 |
+
"loss": 1.607,
|
1476 |
+
"step": 1230
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 0.2952170538006807,
|
1480 |
+
"grad_norm": 4.90625,
|
1481 |
+
"learning_rate": 7.6485788689741e-06,
|
1482 |
+
"loss": 1.3777,
|
1483 |
+
"step": 1236
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 0.2966501462948588,
|
1487 |
+
"grad_norm": 5.875,
|
1488 |
+
"learning_rate": 7.546926141211975e-06,
|
1489 |
+
"loss": 1.5751,
|
1490 |
+
"step": 1242
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 0.29808323878903686,
|
1494 |
+
"grad_norm": 4.8125,
|
1495 |
+
"learning_rate": 7.445542420642097e-06,
|
1496 |
+
"loss": 1.5106,
|
1497 |
+
"step": 1248
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.2995163312832149,
|
1501 |
+
"grad_norm": 4.875,
|
1502 |
+
"learning_rate": 7.344438825131912e-06,
|
1503 |
+
"loss": 1.5982,
|
1504 |
+
"step": 1254
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 0.300949423777393,
|
1508 |
+
"grad_norm": 5.09375,
|
1509 |
+
"learning_rate": 7.243626441830009e-06,
|
1510 |
+
"loss": 1.5328,
|
1511 |
+
"step": 1260
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 0.30238251627157103,
|
1515 |
+
"grad_norm": 4.09375,
|
1516 |
+
"learning_rate": 7.143116325950266e-06,
|
1517 |
+
"loss": 1.6138,
|
1518 |
+
"step": 1266
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 0.3038156087657491,
|
1522 |
+
"grad_norm": 3.8125,
|
1523 |
+
"learning_rate": 7.042919499559538e-06,
|
1524 |
+
"loss": 1.4547,
|
1525 |
+
"step": 1272
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 0.30524870125992715,
|
1529 |
+
"grad_norm": 4.1875,
|
1530 |
+
"learning_rate": 6.943046950368944e-06,
|
1531 |
+
"loss": 1.4393,
|
1532 |
+
"step": 1278
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 0.3066817937541052,
|
1536 |
+
"grad_norm": 5.34375,
|
1537 |
+
"learning_rate": 6.843509630528977e-06,
|
1538 |
+
"loss": 1.4009,
|
1539 |
+
"step": 1284
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.30811488624828326,
|
1543 |
+
"grad_norm": 5.125,
|
1544 |
+
"learning_rate": 6.744318455428436e-06,
|
1545 |
+
"loss": 1.5134,
|
1546 |
+
"step": 1290
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 0.3095479787424613,
|
1550 |
+
"grad_norm": 4.96875,
|
1551 |
+
"learning_rate": 6.645484302497452e-06,
|
1552 |
+
"loss": 1.5411,
|
1553 |
+
"step": 1296
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 0.3109810712366394,
|
1557 |
+
"grad_norm": 4.9375,
|
1558 |
+
"learning_rate": 6.547018010014654e-06,
|
1559 |
+
"loss": 1.5058,
|
1560 |
+
"step": 1302
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 0.3124141637308175,
|
1564 |
+
"grad_norm": 3.59375,
|
1565 |
+
"learning_rate": 6.448930375918632e-06,
|
1566 |
+
"loss": 1.4026,
|
1567 |
+
"step": 1308
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 0.31384725622499554,
|
1571 |
+
"grad_norm": 4.78125,
|
1572 |
+
"learning_rate": 6.351232156623803e-06,
|
1573 |
+
"loss": 1.3993,
|
1574 |
+
"step": 1314
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 0.3152803487191736,
|
1578 |
+
"grad_norm": 4.21875,
|
1579 |
+
"learning_rate": 6.25393406584088e-06,
|
1580 |
+
"loss": 1.6574,
|
1581 |
+
"step": 1320
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.31671344121335165,
|
1585 |
+
"grad_norm": 4.40625,
|
1586 |
+
"learning_rate": 6.157046773401964e-06,
|
1587 |
+
"loss": 1.5233,
|
1588 |
+
"step": 1326
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 0.3181465337075297,
|
1592 |
+
"grad_norm": 5.25,
|
1593 |
+
"learning_rate": 6.06058090409049e-06,
|
1594 |
+
"loss": 1.5095,
|
1595 |
+
"step": 1332
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 0.31957962620170777,
|
1599 |
+
"grad_norm": 4.625,
|
1600 |
+
"learning_rate": 5.9645470364761e-06,
|
1601 |
+
"loss": 1.3797,
|
1602 |
+
"step": 1338
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 0.3210127186958858,
|
1606 |
+
"grad_norm": 5.84375,
|
1607 |
+
"learning_rate": 5.868955701754584e-06,
|
1608 |
+
"loss": 1.6089,
|
1609 |
+
"step": 1344
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 0.3224458111900639,
|
1613 |
+
"grad_norm": 3.71875,
|
1614 |
+
"learning_rate": 5.773817382593008e-06,
|
1615 |
+
"loss": 1.4297,
|
1616 |
+
"step": 1350
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 0.32387890368424194,
|
1620 |
+
"grad_norm": 3.578125,
|
1621 |
+
"learning_rate": 5.679142511980176e-06,
|
1622 |
+
"loss": 1.327,
|
1623 |
+
"step": 1356
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.32531199617842,
|
1627 |
+
"grad_norm": 4.6875,
|
1628 |
+
"learning_rate": 5.584941472082549e-06,
|
1629 |
+
"loss": 1.4878,
|
1630 |
+
"step": 1362
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 0.32674508867259805,
|
1634 |
+
"grad_norm": 5.125,
|
1635 |
+
"learning_rate": 5.491224593105695e-06,
|
1636 |
+
"loss": 1.4593,
|
1637 |
+
"step": 1368
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 0.32817818116677616,
|
1641 |
+
"grad_norm": 7.1875,
|
1642 |
+
"learning_rate": 5.398002152161484e-06,
|
1643 |
+
"loss": 1.5287,
|
1644 |
+
"step": 1374
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.3296112736609542,
|
1648 |
+
"grad_norm": 5.71875,
|
1649 |
+
"learning_rate": 5.305284372141095e-06,
|
1650 |
+
"loss": 1.4808,
|
1651 |
+
"step": 1380
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 0.3310443661551323,
|
1655 |
+
"grad_norm": 4.09375,
|
1656 |
+
"learning_rate": 5.213081420593933e-06,
|
1657 |
+
"loss": 1.4244,
|
1658 |
+
"step": 1386
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.33247745864931033,
|
1662 |
+
"grad_norm": 9.5,
|
1663 |
+
"learning_rate": 5.121403408612672e-06,
|
1664 |
+
"loss": 1.5213,
|
1665 |
+
"step": 1392
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.3339105511434884,
|
1669 |
+
"grad_norm": 5.09375,
|
1670 |
+
"learning_rate": 5.030260389724447e-06,
|
1671 |
+
"loss": 1.4455,
|
1672 |
+
"step": 1398
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 0.33534364363766644,
|
1676 |
+
"grad_norm": 6.6875,
|
1677 |
+
"learning_rate": 4.939662358788364e-06,
|
1678 |
+
"loss": 1.5983,
|
1679 |
+
"step": 1404
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 0.3367767361318445,
|
1683 |
+
"grad_norm": 4.96875,
|
1684 |
+
"learning_rate": 4.849619250899458e-06,
|
1685 |
+
"loss": 1.3544,
|
1686 |
+
"step": 1410
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 0.33820982862602256,
|
1690 |
+
"grad_norm": 4.65625,
|
1691 |
+
"learning_rate": 4.76014094029921e-06,
|
1692 |
+
"loss": 1.4412,
|
1693 |
+
"step": 1416
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 0.3396429211202006,
|
1697 |
+
"grad_norm": 6.40625,
|
1698 |
+
"learning_rate": 4.671237239292699e-06,
|
1699 |
+
"loss": 1.4463,
|
1700 |
+
"step": 1422
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.34107601361437867,
|
1704 |
+
"grad_norm": 5.25,
|
1705 |
+
"learning_rate": 4.582917897172603e-06,
|
1706 |
+
"loss": 1.5306,
|
1707 |
+
"step": 1428
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.3425091061085568,
|
1711 |
+
"grad_norm": 4.40625,
|
1712 |
+
"learning_rate": 4.495192599150045e-06,
|
1713 |
+
"loss": 1.5532,
|
1714 |
+
"step": 1434
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 0.34394219860273484,
|
1718 |
+
"grad_norm": 5.15625,
|
1719 |
+
"learning_rate": 4.408070965292534e-06,
|
1720 |
+
"loss": 1.4818,
|
1721 |
+
"step": 1440
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 0.3453752910969129,
|
1725 |
+
"grad_norm": 4.125,
|
1726 |
+
"learning_rate": 4.321562549468991e-06,
|
1727 |
+
"loss": 1.4144,
|
1728 |
+
"step": 1446
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 0.34680838359109095,
|
1732 |
+
"grad_norm": 4.28125,
|
1733 |
+
"learning_rate": 4.235676838302069e-06,
|
1734 |
+
"loss": 1.4173,
|
1735 |
+
"step": 1452
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 0.348241476085269,
|
1739 |
+
"grad_norm": 8.5,
|
1740 |
+
"learning_rate": 4.150423250127846e-06,
|
1741 |
+
"loss": 1.4121,
|
1742 |
+
"step": 1458
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 0.34967456857944706,
|
1746 |
+
"grad_norm": 5.90625,
|
1747 |
+
"learning_rate": 4.065811133962987e-06,
|
1748 |
+
"loss": 1.4121,
|
1749 |
+
"step": 1464
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.3511076610736251,
|
1753 |
+
"grad_norm": 4.625,
|
1754 |
+
"learning_rate": 3.981849768479516e-06,
|
1755 |
+
"loss": 1.3973,
|
1756 |
+
"step": 1470
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 0.3525407535678032,
|
1760 |
+
"grad_norm": 5.1875,
|
1761 |
+
"learning_rate": 3.898548360987325e-06,
|
1762 |
+
"loss": 1.4554,
|
1763 |
+
"step": 1476
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 0.35397384606198123,
|
1767 |
+
"grad_norm": 5.40625,
|
1768 |
+
"learning_rate": 3.81591604642446e-06,
|
1769 |
+
"loss": 1.4958,
|
1770 |
+
"step": 1482
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 0.3554069385561593,
|
1774 |
+
"grad_norm": 5.28125,
|
1775 |
+
"learning_rate": 3.7339618863553983e-06,
|
1776 |
+
"loss": 1.4843,
|
1777 |
+
"step": 1488
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.35684003105033735,
|
1781 |
+
"grad_norm": 5.96875,
|
1782 |
+
"learning_rate": 3.6526948679773256e-06,
|
1783 |
+
"loss": 1.6051,
|
1784 |
+
"step": 1494
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 0.35827312354451546,
|
1788 |
+
"grad_norm": 3.6875,
|
1789 |
+
"learning_rate": 3.5721239031346067e-06,
|
1790 |
+
"loss": 1.4176,
|
1791 |
+
"step": 1500
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.3597062160386935,
|
1795 |
+
"grad_norm": 4.375,
|
1796 |
+
"learning_rate": 3.492257827341492e-06,
|
1797 |
+
"loss": 1.4049,
|
1798 |
+
"step": 1506
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 0.3611393085328716,
|
1802 |
+
"grad_norm": 3.71875,
|
1803 |
+
"learning_rate": 3.4131053988131947e-06,
|
1804 |
+
"loss": 1.5823,
|
1805 |
+
"step": 1512
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 0.36257240102704963,
|
1809 |
+
"grad_norm": 6.0,
|
1810 |
+
"learning_rate": 3.3346752975054763e-06,
|
1811 |
+
"loss": 1.4469,
|
1812 |
+
"step": 1518
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 0.3640054935212277,
|
1816 |
+
"grad_norm": 4.21875,
|
1817 |
+
"learning_rate": 3.2569761241627694e-06,
|
1818 |
+
"loss": 1.4373,
|
1819 |
+
"step": 1524
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 0.36543858601540574,
|
1823 |
+
"grad_norm": 6.03125,
|
1824 |
+
"learning_rate": 3.1800163993750166e-06,
|
1825 |
+
"loss": 1.4823,
|
1826 |
+
"step": 1530
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.3668716785095838,
|
1830 |
+
"grad_norm": 4.625,
|
1831 |
+
"learning_rate": 3.103804562643302e-06,
|
1832 |
+
"loss": 1.4585,
|
1833 |
+
"step": 1536
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.36830477100376185,
|
1837 |
+
"grad_norm": 4.28125,
|
1838 |
+
"learning_rate": 3.028348971454356e-06,
|
1839 |
+
"loss": 1.4233,
|
1840 |
+
"step": 1542
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 0.3697378634979399,
|
1844 |
+
"grad_norm": 14.625,
|
1845 |
+
"learning_rate": 2.953657900364053e-06,
|
1846 |
+
"loss": 1.4869,
|
1847 |
+
"step": 1548
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 0.37117095599211797,
|
1851 |
+
"grad_norm": 4.1875,
|
1852 |
+
"learning_rate": 2.8797395400900362e-06,
|
1853 |
+
"loss": 1.5315,
|
1854 |
+
"step": 1554
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.3726040484862961,
|
1858 |
+
"grad_norm": 4.125,
|
1859 |
+
"learning_rate": 2.8066019966134907e-06,
|
1860 |
+
"loss": 1.4887,
|
1861 |
+
"step": 1560
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 0.37403714098047414,
|
1865 |
+
"grad_norm": 3.796875,
|
1866 |
+
"learning_rate": 2.7342532902902418e-06,
|
1867 |
+
"loss": 1.4533,
|
1868 |
+
"step": 1566
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 0.3754702334746522,
|
1872 |
+
"grad_norm": 4.03125,
|
1873 |
+
"learning_rate": 2.6627013549712355e-06,
|
1874 |
+
"loss": 1.4017,
|
1875 |
+
"step": 1572
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.37690332596883025,
|
1879 |
+
"grad_norm": 6.84375,
|
1880 |
+
"learning_rate": 2.5919540371325005e-06,
|
1881 |
+
"loss": 1.3971,
|
1882 |
+
"step": 1578
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 0.3783364184630083,
|
1886 |
+
"grad_norm": 5.5625,
|
1887 |
+
"learning_rate": 2.522019095014683e-06,
|
1888 |
+
"loss": 1.5576,
|
1889 |
+
"step": 1584
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 0.37976951095718636,
|
1893 |
+
"grad_norm": 10.875,
|
1894 |
+
"learning_rate": 2.45290419777228e-06,
|
1895 |
+
"loss": 1.4719,
|
1896 |
+
"step": 1590
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 0.3812026034513644,
|
1900 |
+
"grad_norm": 5.15625,
|
1901 |
+
"learning_rate": 2.3846169246326345e-06,
|
1902 |
+
"loss": 1.4618,
|
1903 |
+
"step": 1596
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 0.3821579984474831,
|
1907 |
+
"eval_loss": 1.2876688241958618,
|
1908 |
+
"eval_runtime": 226.2654,
|
1909 |
+
"eval_samples_per_second": 3.757,
|
1910 |
+
"eval_steps_per_second": 3.757,
|
1911 |
+
"step": 1600
|
1912 |
+
}
|
1913 |
+
],
|
1914 |
+
"logging_steps": 6,
|
1915 |
+
"max_steps": 2000,
|
1916 |
+
"num_input_tokens_seen": 0,
|
1917 |
+
"num_train_epochs": 1,
|
1918 |
+
"save_steps": 400,
|
1919 |
+
"total_flos": 2.9553261973639004e+18,
|
1920 |
+
"train_batch_size": 1,
|
1921 |
+
"trial_name": null,
|
1922 |
+
"trial_params": null
|
1923 |
+
}
|