ciyazzzk commited on
Commit
2efa347
1 Parent(s): 09fe0b4

First model version

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.42.3",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.42.3"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6511ff0683628044e78f67cf1c6cf634373cf52e9e347fed4923bc90e81274
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3e6847c0dbdf15b897b8f6644744089c0a82480be8338090e7d0ebfc61042a
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153ed14e9690e7db0e7e0faa0721ad7bd280dd1d78c0a517d3d5dc2153f55003
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
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.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,2121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9938573003622615,
5
+ "eval_steps": 500,
6
+ "global_step": 297,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010080327610647345,
13
+ "grad_norm": 20.48233413696289,
14
+ "learning_rate": 6.666666666666667e-07,
15
+ "loss": 1.318,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.02016065522129469,
20
+ "grad_norm": 22.18445587158203,
21
+ "learning_rate": 1.3333333333333334e-06,
22
+ "loss": 1.2034,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03024098283194204,
27
+ "grad_norm": 20.34792137145996,
28
+ "learning_rate": 2.0000000000000003e-06,
29
+ "loss": 1.0455,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.04032131044258938,
34
+ "grad_norm": 8.893705368041992,
35
+ "learning_rate": 2.666666666666667e-06,
36
+ "loss": 2.0515,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.05040163805323673,
41
+ "grad_norm": 6.274827003479004,
42
+ "learning_rate": 3.3333333333333333e-06,
43
+ "loss": 1.0793,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.06048196566388408,
48
+ "grad_norm": 6.051919937133789,
49
+ "learning_rate": 4.000000000000001e-06,
50
+ "loss": 0.9434,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.07056229327453142,
55
+ "grad_norm": 7.502919673919678,
56
+ "learning_rate": 4.666666666666667e-06,
57
+ "loss": 0.9741,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.08064262088517876,
62
+ "grad_norm": 6.437217712402344,
63
+ "learning_rate": 5.333333333333334e-06,
64
+ "loss": 1.1227,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.09072294849582611,
69
+ "grad_norm": 5.169360160827637,
70
+ "learning_rate": 6e-06,
71
+ "loss": 0.9156,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.10080327610647347,
76
+ "grad_norm": 5.1474432945251465,
77
+ "learning_rate": 6.666666666666667e-06,
78
+ "loss": 1.0925,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.1108836037171208,
83
+ "grad_norm": 6.759896755218506,
84
+ "learning_rate": 7.333333333333333e-06,
85
+ "loss": 0.8985,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.12096393132776816,
90
+ "grad_norm": 5.231770992279053,
91
+ "learning_rate": 8.000000000000001e-06,
92
+ "loss": 1.6954,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1310442589384155,
97
+ "grad_norm": 5.028665542602539,
98
+ "learning_rate": 8.666666666666668e-06,
99
+ "loss": 0.9763,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.14112458654906285,
104
+ "grad_norm": 7.008236408233643,
105
+ "learning_rate": 9.333333333333334e-06,
106
+ "loss": 0.9969,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.15120491415971019,
111
+ "grad_norm": 4.675139904022217,
112
+ "learning_rate": 1e-05,
113
+ "loss": 0.8619,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.16128524177035752,
118
+ "grad_norm": 5.249491214752197,
119
+ "learning_rate": 1.0666666666666667e-05,
120
+ "loss": 0.9176,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.1713655693810049,
125
+ "grad_norm": 4.5402092933654785,
126
+ "learning_rate": 1.1333333333333334e-05,
127
+ "loss": 0.8809,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.18144589699165223,
132
+ "grad_norm": 4.799923896789551,
133
+ "learning_rate": 1.2e-05,
134
+ "loss": 1.005,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.19152622460229957,
139
+ "grad_norm": 3.9302682876586914,
140
+ "learning_rate": 1.2666666666666667e-05,
141
+ "loss": 0.8784,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.20160655221294693,
146
+ "grad_norm": 4.542870044708252,
147
+ "learning_rate": 1.3333333333333333e-05,
148
+ "loss": 1.0378,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.21168687982359427,
153
+ "grad_norm": 10.4898042678833,
154
+ "learning_rate": 1.4e-05,
155
+ "loss": 0.8458,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.2217672074342416,
160
+ "grad_norm": 4.678144454956055,
161
+ "learning_rate": 1.4666666666666666e-05,
162
+ "loss": 0.9237,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.23184753504488895,
167
+ "grad_norm": 4.897671222686768,
168
+ "learning_rate": 1.5333333333333334e-05,
169
+ "loss": 0.9661,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.2419278626555363,
174
+ "grad_norm": 5.067351818084717,
175
+ "learning_rate": 1.6000000000000003e-05,
176
+ "loss": 0.9975,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.25200819026618365,
181
+ "grad_norm": 3.7107274532318115,
182
+ "learning_rate": 1.6666666666666667e-05,
183
+ "loss": 0.9316,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.262088517876831,
188
+ "grad_norm": 4.553698539733887,
189
+ "learning_rate": 1.7333333333333336e-05,
190
+ "loss": 0.871,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.27216884548747833,
195
+ "grad_norm": 5.10447359085083,
196
+ "learning_rate": 1.8e-05,
197
+ "loss": 0.8687,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.2822491730981257,
202
+ "grad_norm": 3.7116832733154297,
203
+ "learning_rate": 1.866666666666667e-05,
204
+ "loss": 0.8586,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.29232950070877306,
209
+ "grad_norm": 5.299854755401611,
210
+ "learning_rate": 1.9333333333333333e-05,
211
+ "loss": 0.8595,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.30240982831942037,
216
+ "grad_norm": 3.825899600982666,
217
+ "learning_rate": 2e-05,
218
+ "loss": 0.9615,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.31249015593006774,
223
+ "grad_norm": 4.806526184082031,
224
+ "learning_rate": 1.999930778307066e-05,
225
+ "loss": 0.8595,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.32257048354071505,
230
+ "grad_norm": 3.5444633960723877,
231
+ "learning_rate": 1.9997231228115487e-05,
232
+ "loss": 0.9748,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.3326508111513624,
237
+ "grad_norm": 4.36836051940918,
238
+ "learning_rate": 1.9993770622619784e-05,
239
+ "loss": 0.8577,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.3427311387620098,
244
+ "grad_norm": 3.0740671157836914,
245
+ "learning_rate": 1.9988926445681495e-05,
246
+ "loss": 0.8407,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3528114663726571,
251
+ "grad_norm": 3.8326187133789062,
252
+ "learning_rate": 1.998269936794487e-05,
253
+ "loss": 0.8997,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.36289179398330446,
258
+ "grad_norm": 3.6133008003234863,
259
+ "learning_rate": 1.9975090251507637e-05,
260
+ "loss": 0.9572,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3729721215939518,
265
+ "grad_norm": 4.111402988433838,
266
+ "learning_rate": 1.9966100149801648e-05,
267
+ "loss": 0.8465,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.38305244920459913,
272
+ "grad_norm": 3.105464220046997,
273
+ "learning_rate": 1.9955730307447015e-05,
274
+ "loss": 0.84,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3931327768152465,
279
+ "grad_norm": 3.377089738845825,
280
+ "learning_rate": 1.9943982160079823e-05,
281
+ "loss": 0.977,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.40321310442589386,
286
+ "grad_norm": 3.674912214279175,
287
+ "learning_rate": 1.9930857334153374e-05,
288
+ "loss": 0.9114,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.4132934320365412,
293
+ "grad_norm": 3.491791248321533,
294
+ "learning_rate": 1.9916357646713006e-05,
295
+ "loss": 0.8507,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.42337375964718854,
300
+ "grad_norm": 3.5988316535949707,
301
+ "learning_rate": 1.9900485105144544e-05,
302
+ "loss": 0.8459,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.4334540872578359,
307
+ "grad_norm": 3.147287368774414,
308
+ "learning_rate": 1.988324190689639e-05,
309
+ "loss": 0.9254,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4435344148684832,
314
+ "grad_norm": 3.4546704292297363,
315
+ "learning_rate": 1.9864630439175282e-05,
316
+ "loss": 0.9388,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.4536147424791306,
321
+ "grad_norm": 3.39437198638916,
322
+ "learning_rate": 1.9844653278615836e-05,
323
+ "loss": 0.8751,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.4636950700897779,
328
+ "grad_norm": 2.966585159301758,
329
+ "learning_rate": 1.9823313190923797e-05,
330
+ "loss": 0.833,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.47377539770042526,
335
+ "grad_norm": 6.668085098266602,
336
+ "learning_rate": 1.9800613130493158e-05,
337
+ "loss": 0.9399,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.4838557253110726,
342
+ "grad_norm": 4.198956489562988,
343
+ "learning_rate": 1.9776556239997146e-05,
344
+ "loss": 0.8604,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.49393605292171994,
349
+ "grad_norm": 3.0325896739959717,
350
+ "learning_rate": 1.9751145849953135e-05,
351
+ "loss": 0.8399,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.5040163805323673,
356
+ "grad_norm": 3.0284290313720703,
357
+ "learning_rate": 1.972438547826156e-05,
358
+ "loss": 0.962,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.5140967081430147,
363
+ "grad_norm": 3.7126681804656982,
364
+ "learning_rate": 1.9696278829718882e-05,
365
+ "loss": 0.8381,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.524177035753662,
370
+ "grad_norm": 3.0753326416015625,
371
+ "learning_rate": 1.9666829795504693e-05,
372
+ "loss": 1.2808,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.5342573633643093,
377
+ "grad_norm": 3.3041043281555176,
378
+ "learning_rate": 1.9636042452643004e-05,
379
+ "loss": 1.0921,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.5443376909749567,
384
+ "grad_norm": 2.974684953689575,
385
+ "learning_rate": 1.9603921063437795e-05,
386
+ "loss": 1.1766,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.554418018585604,
391
+ "grad_norm": 3.104491710662842,
392
+ "learning_rate": 1.9570470074882947e-05,
393
+ "loss": 0.8245,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.5644983461962514,
398
+ "grad_norm": 2.8233213424682617,
399
+ "learning_rate": 1.9535694118046584e-05,
400
+ "loss": 0.8327,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5745786738068988,
405
+ "grad_norm": 3.0855748653411865,
406
+ "learning_rate": 1.949959800742991e-05,
407
+ "loss": 0.8333,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5846590014175461,
412
+ "grad_norm": 3.309098482131958,
413
+ "learning_rate": 1.9462186740300697e-05,
414
+ "loss": 0.8437,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5947393290281934,
419
+ "grad_norm": 3.7956173419952393,
420
+ "learning_rate": 1.942346549600144e-05,
421
+ "loss": 0.8533,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.6048196566388407,
426
+ "grad_norm": 2.885507106781006,
427
+ "learning_rate": 1.9383439635232296e-05,
428
+ "loss": 0.9791,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.6148999842494881,
433
+ "grad_norm": 2.976921319961548,
434
+ "learning_rate": 1.9342114699308962e-05,
435
+ "loss": 0.9537,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.6249803118601355,
440
+ "grad_norm": 3.9822583198547363,
441
+ "learning_rate": 1.9299496409395482e-05,
442
+ "loss": 0.8513,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.6350606394707828,
447
+ "grad_norm": 3.2742626667022705,
448
+ "learning_rate": 1.9255590665712214e-05,
449
+ "loss": 0.8606,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.6451409670814301,
454
+ "grad_norm": 2.989588975906372,
455
+ "learning_rate": 1.921040354671897e-05,
456
+ "loss": 1.0236,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.6552212946920775,
461
+ "grad_norm": 3.3849992752075195,
462
+ "learning_rate": 1.9163941308273504e-05,
463
+ "loss": 0.8274,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.6653016223027248,
468
+ "grad_norm": 2.9485199451446533,
469
+ "learning_rate": 1.911621038276542e-05,
470
+ "loss": 0.8366,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6753819499133722,
475
+ "grad_norm": 2.8090484142303467,
476
+ "learning_rate": 1.9067217378225655e-05,
477
+ "loss": 1.0603,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6854622775240196,
482
+ "grad_norm": 2.795466899871826,
483
+ "learning_rate": 1.9016969077411645e-05,
484
+ "loss": 1.0391,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6955426051346669,
489
+ "grad_norm": 3.0513088703155518,
490
+ "learning_rate": 1.8965472436868288e-05,
491
+ "loss": 0.9469,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.7056229327453142,
496
+ "grad_norm": 2.89764404296875,
497
+ "learning_rate": 1.891273458596486e-05,
498
+ "loss": 0.8358,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.7157032603559615,
503
+ "grad_norm": 2.940281629562378,
504
+ "learning_rate": 1.8858762825908e-05,
505
+ "loss": 0.9117,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.7257835879666089,
510
+ "grad_norm": 3.0357506275177,
511
+ "learning_rate": 1.8803564628730916e-05,
512
+ "loss": 0.8441,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.7358639155772563,
517
+ "grad_norm": 3.0957512855529785,
518
+ "learning_rate": 1.874714763625892e-05,
519
+ "loss": 0.8154,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.7459442431879036,
524
+ "grad_norm": 3.3382112979888916,
525
+ "learning_rate": 1.8689519659051467e-05,
526
+ "loss": 1.0091,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.7560245707985509,
531
+ "grad_norm": 2.7359678745269775,
532
+ "learning_rate": 1.8630688675320844e-05,
533
+ "loss": 0.9901,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.7661048984091983,
538
+ "grad_norm": 2.9160029888153076,
539
+ "learning_rate": 1.8570662829827632e-05,
540
+ "loss": 1.0645,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7761852260198456,
545
+ "grad_norm": 3.7096657752990723,
546
+ "learning_rate": 1.8509450432753123e-05,
547
+ "loss": 0.8458,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.786265553630493,
552
+ "grad_norm": 2.9605114459991455,
553
+ "learning_rate": 1.8447059958548822e-05,
554
+ "loss": 0.8315,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7963458812411404,
559
+ "grad_norm": 3.1716909408569336,
560
+ "learning_rate": 1.8383500044763226e-05,
561
+ "loss": 0.8427,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.8064262088517877,
566
+ "grad_norm": 4.014035224914551,
567
+ "learning_rate": 1.8318779490846005e-05,
568
+ "loss": 0.8391,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.816506536462435,
573
+ "grad_norm": 2.6693358421325684,
574
+ "learning_rate": 1.8252907256929777e-05,
575
+ "loss": 1.0444,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.8265868640730824,
580
+ "grad_norm": 3.824836254119873,
581
+ "learning_rate": 1.818589246258964e-05,
582
+ "loss": 0.9738,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.8366671916837297,
587
+ "grad_norm": 3.0832369327545166,
588
+ "learning_rate": 1.8117744385580627e-05,
589
+ "loss": 0.9109,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.8467475192943771,
594
+ "grad_norm": 3.707331657409668,
595
+ "learning_rate": 1.804847246055326e-05,
596
+ "loss": 0.8324,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.8568278469050244,
601
+ "grad_norm": 3.3008220195770264,
602
+ "learning_rate": 1.797808627774738e-05,
603
+ "loss": 0.9383,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.8669081745156718,
608
+ "grad_norm": 3.1887435913085938,
609
+ "learning_rate": 1.7906595581664462e-05,
610
+ "loss": 0.8441,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.8769885021263191,
615
+ "grad_norm": 2.8672823905944824,
616
+ "learning_rate": 1.7834010269718526e-05,
617
+ "loss": 0.8353,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8870688297369664,
622
+ "grad_norm": 3.0346055030822754,
623
+ "learning_rate": 1.776034039086592e-05,
624
+ "loss": 1.348,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.8971491573476138,
629
+ "grad_norm": 3.2000229358673096,
630
+ "learning_rate": 1.768559614421411e-05,
631
+ "loss": 0.8544,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.9072294849582612,
636
+ "grad_norm": 3.007753610610962,
637
+ "learning_rate": 1.7609787877609678e-05,
638
+ "loss": 0.8505,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.9173098125689085,
643
+ "grad_norm": 2.9321534633636475,
644
+ "learning_rate": 1.753292608620573e-05,
645
+ "loss": 0.8402,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.9273901401795558,
650
+ "grad_norm": 2.6721303462982178,
651
+ "learning_rate": 1.7455021411008906e-05,
652
+ "loss": 0.8421,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.9374704677902032,
657
+ "grad_norm": 3.0125327110290527,
658
+ "learning_rate": 1.7376084637406222e-05,
659
+ "loss": 0.8443,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.9475507954008505,
664
+ "grad_norm": 2.6522045135498047,
665
+ "learning_rate": 1.7296126693671886e-05,
666
+ "loss": 1.2249,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.9576311230114979,
671
+ "grad_norm": 2.6742281913757324,
672
+ "learning_rate": 1.721515864945435e-05,
673
+ "loss": 0.846,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.9677114506221453,
678
+ "grad_norm": 2.9093592166900635,
679
+ "learning_rate": 1.7133191714243805e-05,
680
+ "loss": 0.9391,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.9777917782327926,
685
+ "grad_norm": 3.675670623779297,
686
+ "learning_rate": 1.7050237235820287e-05,
687
+ "loss": 0.8723,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.9878721058434399,
692
+ "grad_norm": 2.698991298675537,
693
+ "learning_rate": 1.6966306698682672e-05,
694
+ "loss": 0.8491,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.9979524334540872,
699
+ "grad_norm": 2.8708646297454834,
700
+ "learning_rate": 1.6881411722458688e-05,
701
+ "loss": 1.1059,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.0080327610647346,
706
+ "grad_norm": 3.9162817001342773,
707
+ "learning_rate": 1.6795564060296295e-05,
708
+ "loss": 0.711,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.018113088675382,
713
+ "grad_norm": 3.2829103469848633,
714
+ "learning_rate": 1.6708775597236507e-05,
715
+ "loss": 0.7179,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.0281934162860293,
720
+ "grad_norm": 4.782021999359131,
721
+ "learning_rate": 1.6621058348568008e-05,
722
+ "loss": 0.759,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.0382737438966767,
727
+ "grad_norm": 4.203643798828125,
728
+ "learning_rate": 1.6532424458163692e-05,
729
+ "loss": 0.7717,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.048354071507324,
734
+ "grad_norm": 4.421259880065918,
735
+ "learning_rate": 1.6442886196799465e-05,
736
+ "loss": 0.651,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.0584343991179714,
741
+ "grad_norm": 3.6463119983673096,
742
+ "learning_rate": 1.6352455960455385e-05,
743
+ "loss": 0.7719,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.0685147267286186,
748
+ "grad_norm": 3.408778429031372,
749
+ "learning_rate": 1.6261146268599564e-05,
750
+ "loss": 0.6591,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.078595054339266,
755
+ "grad_norm": 3.7105519771575928,
756
+ "learning_rate": 1.6168969762454897e-05,
757
+ "loss": 0.6645,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.0886753819499133,
762
+ "grad_norm": 3.8667266368865967,
763
+ "learning_rate": 1.607593920324899e-05,
764
+ "loss": 0.7159,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.0987557095605607,
769
+ "grad_norm": 3.4244542121887207,
770
+ "learning_rate": 1.598206747044746e-05,
771
+ "loss": 0.8331,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.108836037171208,
776
+ "grad_norm": 3.326638698577881,
777
+ "learning_rate": 1.5887367559970825e-05,
778
+ "loss": 0.6831,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.1189163647818554,
783
+ "grad_norm": 3.7026546001434326,
784
+ "learning_rate": 1.5791852582395334e-05,
785
+ "loss": 0.6642,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.1289966923925028,
790
+ "grad_norm": 3.1158483028411865,
791
+ "learning_rate": 1.569553576113789e-05,
792
+ "loss": 0.6531,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.1390770200031501,
797
+ "grad_norm": 3.1516995429992676,
798
+ "learning_rate": 1.5598430430625335e-05,
799
+ "loss": 0.6734,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.1491573476137975,
804
+ "grad_norm": 3.048830270767212,
805
+ "learning_rate": 1.5500550034448415e-05,
806
+ "loss": 0.6412,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.1592376752244449,
811
+ "grad_norm": 2.9057071208953857,
812
+ "learning_rate": 1.540190812350059e-05,
813
+ "loss": 0.6441,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.1693180028350922,
818
+ "grad_norm": 4.930371284484863,
819
+ "learning_rate": 1.5302518354101992e-05,
820
+ "loss": 0.6499,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.1793983304457396,
825
+ "grad_norm": 3.2132606506347656,
826
+ "learning_rate": 1.5202394486108823e-05,
827
+ "loss": 0.7648,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.1894786580563868,
832
+ "grad_norm": 3.247512102127075,
833
+ "learning_rate": 1.5101550381008377e-05,
834
+ "loss": 0.6341,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.1995589856670341,
839
+ "grad_norm": 2.8837008476257324,
840
+ "learning_rate": 1.5000000000000002e-05,
841
+ "loss": 0.6785,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.2096393132776815,
846
+ "grad_norm": 3.362884998321533,
847
+ "learning_rate": 1.4897757402062285e-05,
848
+ "loss": 0.6433,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.2197196408883288,
853
+ "grad_norm": 3.0538456439971924,
854
+ "learning_rate": 1.4794836742006667e-05,
855
+ "loss": 0.7454,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.2297999684989762,
860
+ "grad_norm": 3.1768131256103516,
861
+ "learning_rate": 1.4691252268517794e-05,
862
+ "loss": 0.7879,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.2398802961096236,
867
+ "grad_norm": 3.0788283348083496,
868
+ "learning_rate": 1.4587018322180906e-05,
869
+ "loss": 0.7103,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.249960623720271,
874
+ "grad_norm": 2.7563843727111816,
875
+ "learning_rate": 1.4482149333496455e-05,
876
+ "loss": 0.6592,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.2600409513309183,
881
+ "grad_norm": 3.421998977661133,
882
+ "learning_rate": 1.4376659820882308e-05,
883
+ "loss": 0.7862,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.2701212789415657,
888
+ "grad_norm": 3.0229763984680176,
889
+ "learning_rate": 1.4270564388663761e-05,
890
+ "loss": 0.6586,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.2802016065522128,
895
+ "grad_norm": 2.8393478393554688,
896
+ "learning_rate": 1.4163877725051677e-05,
897
+ "loss": 0.7359,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.2902819341628602,
902
+ "grad_norm": 3.009399175643921,
903
+ "learning_rate": 1.4056614600108998e-05,
904
+ "loss": 0.6755,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.3003622617735076,
909
+ "grad_norm": 2.9821226596832275,
910
+ "learning_rate": 1.3948789863705914e-05,
911
+ "loss": 0.629,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.310442589384155,
916
+ "grad_norm": 3.1034419536590576,
917
+ "learning_rate": 1.3840418443464015e-05,
918
+ "loss": 0.6466,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.3205229169948023,
923
+ "grad_norm": 3.318528413772583,
924
+ "learning_rate": 1.3731515342689654e-05,
925
+ "loss": 1.0047,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.3306032446054497,
930
+ "grad_norm": 2.9240915775299072,
931
+ "learning_rate": 1.3622095638296827e-05,
932
+ "loss": 0.668,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.340683572216097,
937
+ "grad_norm": 3.9342963695526123,
938
+ "learning_rate": 1.3512174478719896e-05,
939
+ "loss": 0.6465,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.3507638998267444,
944
+ "grad_norm": 2.6329188346862793,
945
+ "learning_rate": 1.340176708181637e-05,
946
+ "loss": 0.8036,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.3608442274373918,
951
+ "grad_norm": 3.2634246349334717,
952
+ "learning_rate": 1.32908887327601e-05,
953
+ "loss": 0.6348,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.3709245550480391,
958
+ "grad_norm": 2.8796093463897705,
959
+ "learning_rate": 1.317955478192515e-05,
960
+ "loss": 0.7079,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.3810048826586865,
965
+ "grad_norm": 3.15555477142334,
966
+ "learning_rate": 1.306778064276064e-05,
967
+ "loss": 0.7197,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.3910852102693338,
972
+ "grad_norm": 2.8696324825286865,
973
+ "learning_rate": 1.2955581789656844e-05,
974
+ "loss": 0.6422,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.4011655378799812,
979
+ "grad_norm": 2.841829538345337,
980
+ "learning_rate": 1.2842973755802872e-05,
981
+ "loss": 0.6522,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.4112458654906286,
986
+ "grad_norm": 2.869424819946289,
987
+ "learning_rate": 1.2729972131036212e-05,
988
+ "loss": 0.7462,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.4213261931012757,
993
+ "grad_norm": 3.1612401008605957,
994
+ "learning_rate": 1.2616592559684408e-05,
995
+ "loss": 0.6471,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.431406520711923,
1000
+ "grad_norm": 2.7609212398529053,
1001
+ "learning_rate": 1.25028507383992e-05,
1002
+ "loss": 0.7627,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.4414868483225705,
1007
+ "grad_norm": 2.678645610809326,
1008
+ "learning_rate": 1.2388762413983447e-05,
1009
+ "loss": 0.6729,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.4515671759332178,
1014
+ "grad_norm": 2.8031179904937744,
1015
+ "learning_rate": 1.2274343381211067e-05,
1016
+ "loss": 0.6497,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.4616475035438652,
1021
+ "grad_norm": 2.735318660736084,
1022
+ "learning_rate": 1.2159609480640361e-05,
1023
+ "loss": 0.6786,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.4717278311545126,
1028
+ "grad_norm": 2.9970738887786865,
1029
+ "learning_rate": 1.2044576596421003e-05,
1030
+ "loss": 0.6498,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.48180815876516,
1035
+ "grad_norm": 2.8578624725341797,
1036
+ "learning_rate": 1.192926065409497e-05,
1037
+ "loss": 0.6432,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.4918884863758073,
1042
+ "grad_norm": 2.9433505535125732,
1043
+ "learning_rate": 1.1813677618391759e-05,
1044
+ "loss": 0.6274,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.5019688139864544,
1049
+ "grad_norm": 2.799851417541504,
1050
+ "learning_rate": 1.1697843491018189e-05,
1051
+ "loss": 0.6507,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.5120491415971018,
1056
+ "grad_norm": 2.589261770248413,
1057
+ "learning_rate": 1.1581774308443042e-05,
1058
+ "loss": 0.8801,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.5221294692077492,
1063
+ "grad_norm": 2.7499136924743652,
1064
+ "learning_rate": 1.1465486139676955e-05,
1065
+ "loss": 0.6428,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.5322097968183965,
1070
+ "grad_norm": 3.6993484497070312,
1071
+ "learning_rate": 1.134899508404775e-05,
1072
+ "loss": 0.6641,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.542290124429044,
1077
+ "grad_norm": 5.174093723297119,
1078
+ "learning_rate": 1.1232317268971586e-05,
1079
+ "loss": 0.7828,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.5523704520396913,
1084
+ "grad_norm": 2.734003782272339,
1085
+ "learning_rate": 1.1115468847720245e-05,
1086
+ "loss": 0.7631,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.5624507796503386,
1091
+ "grad_norm": 3.996946334838867,
1092
+ "learning_rate": 1.0998465997184798e-05,
1093
+ "loss": 0.6416,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.572531107260986,
1098
+ "grad_norm": 3.302497386932373,
1099
+ "learning_rate": 1.088132491563602e-05,
1100
+ "loss": 0.6543,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.5826114348716334,
1105
+ "grad_norm": 2.9945664405822754,
1106
+ "learning_rate": 1.0764061820481872e-05,
1107
+ "loss": 0.6902,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.5926917624822807,
1112
+ "grad_norm": 2.6038448810577393,
1113
+ "learning_rate": 1.0646692946022285e-05,
1114
+ "loss": 0.6289,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.602772090092928,
1119
+ "grad_norm": 2.6396548748016357,
1120
+ "learning_rate": 1.0529234541201631e-05,
1121
+ "loss": 0.8164,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.6128524177035755,
1126
+ "grad_norm": 2.770799160003662,
1127
+ "learning_rate": 1.041170286735918e-05,
1128
+ "loss": 0.6438,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.6229327453142228,
1133
+ "grad_norm": 2.666429042816162,
1134
+ "learning_rate": 1.0294114195977796e-05,
1135
+ "loss": 0.6912,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.6330130729248702,
1140
+ "grad_norm": 2.9112017154693604,
1141
+ "learning_rate": 1.0176484806431288e-05,
1142
+ "loss": 0.7345,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.6430934005355176,
1147
+ "grad_norm": 3.0811562538146973,
1148
+ "learning_rate": 1.0058830983730622e-05,
1149
+ "loss": 0.7558,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.6531737281461647,
1154
+ "grad_norm": 2.8588948249816895,
1155
+ "learning_rate": 9.94116901626938e-06,
1156
+ "loss": 0.648,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.663254055756812,
1161
+ "grad_norm": 2.7404801845550537,
1162
+ "learning_rate": 9.823515193568715e-06,
1163
+ "loss": 0.695,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.6733343833674594,
1168
+ "grad_norm": 2.9604055881500244,
1169
+ "learning_rate": 9.705885804022207e-06,
1170
+ "loss": 0.6304,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.6834147109781068,
1175
+ "grad_norm": 3.1369986534118652,
1176
+ "learning_rate": 9.588297132640824e-06,
1177
+ "loss": 0.8216,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.6934950385887542,
1182
+ "grad_norm": 2.912094831466675,
1183
+ "learning_rate": 9.470765458798369e-06,
1184
+ "loss": 0.6653,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.7035753661994015,
1189
+ "grad_norm": 2.6910438537597656,
1190
+ "learning_rate": 9.353307053977717e-06,
1191
+ "loss": 0.6645,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.7136556938100487,
1196
+ "grad_norm": 2.958939790725708,
1197
+ "learning_rate": 9.235938179518131e-06,
1198
+ "loss": 0.6222,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.723736021420696,
1203
+ "grad_norm": 2.7143542766571045,
1204
+ "learning_rate": 9.118675084363986e-06,
1205
+ "loss": 0.7051,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.7338163490313434,
1210
+ "grad_norm": 2.6610677242279053,
1211
+ "learning_rate": 9.001534002815209e-06,
1212
+ "loss": 0.6333,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.7438966766419908,
1217
+ "grad_norm": 2.9667537212371826,
1218
+ "learning_rate": 8.884531152279757e-06,
1219
+ "loss": 0.6832,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.7539770042526381,
1224
+ "grad_norm": 2.64609956741333,
1225
+ "learning_rate": 8.767682731028415e-06,
1226
+ "loss": 0.9484,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.7640573318632855,
1231
+ "grad_norm": 2.682523012161255,
1232
+ "learning_rate": 8.651004915952252e-06,
1233
+ "loss": 0.8721,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.7741376594739329,
1238
+ "grad_norm": 2.5906975269317627,
1239
+ "learning_rate": 8.534513860323047e-06,
1240
+ "loss": 0.9793,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.7842179870845802,
1245
+ "grad_norm": 2.636467456817627,
1246
+ "learning_rate": 8.418225691556962e-06,
1247
+ "loss": 0.9016,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.7942983146952276,
1252
+ "grad_norm": 3.5005948543548584,
1253
+ "learning_rate": 8.302156508981816e-06,
1254
+ "loss": 0.738,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.804378642305875,
1259
+ "grad_norm": 2.7986643314361572,
1260
+ "learning_rate": 8.18632238160824e-06,
1261
+ "loss": 0.6635,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.8144589699165223,
1266
+ "grad_norm": 2.8597512245178223,
1267
+ "learning_rate": 8.070739345905032e-06,
1268
+ "loss": 0.7473,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.8245392975271697,
1273
+ "grad_norm": 2.7487239837646484,
1274
+ "learning_rate": 7.955423403578998e-06,
1275
+ "loss": 0.7526,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.834619625137817,
1280
+ "grad_norm": 2.68874454498291,
1281
+ "learning_rate": 7.840390519359644e-06,
1282
+ "loss": 0.6491,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.8446999527484644,
1287
+ "grad_norm": 2.8393709659576416,
1288
+ "learning_rate": 7.725656618788938e-06,
1289
+ "loss": 0.6401,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.8547802803591118,
1294
+ "grad_norm": 2.8322646617889404,
1295
+ "learning_rate": 7.611237586016558e-06,
1296
+ "loss": 0.7692,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.8648606079697592,
1301
+ "grad_norm": 2.760575771331787,
1302
+ "learning_rate": 7.497149261600803e-06,
1303
+ "loss": 0.926,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.8749409355804063,
1308
+ "grad_norm": 2.6379311084747314,
1309
+ "learning_rate": 7.383407440315595e-06,
1310
+ "loss": 0.654,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.8850212631910537,
1315
+ "grad_norm": 2.6411261558532715,
1316
+ "learning_rate": 7.27002786896379e-06,
1317
+ "loss": 0.7753,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.895101590801701,
1322
+ "grad_norm": 2.6866044998168945,
1323
+ "learning_rate": 7.157026244197132e-06,
1324
+ "loss": 0.6479,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.9051819184123484,
1329
+ "grad_norm": 2.743093252182007,
1330
+ "learning_rate": 7.044418210343161e-06,
1331
+ "loss": 0.7825,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.9152622460229958,
1336
+ "grad_norm": 2.7608628273010254,
1337
+ "learning_rate": 6.932219357239362e-06,
1338
+ "loss": 0.6497,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.9253425736336431,
1343
+ "grad_norm": 2.581033706665039,
1344
+ "learning_rate": 6.820445218074849e-06,
1345
+ "loss": 0.658,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.9354229012442903,
1350
+ "grad_norm": 2.8341994285583496,
1351
+ "learning_rate": 6.7091112672399e-06,
1352
+ "loss": 0.8367,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.9455032288549376,
1357
+ "grad_norm": 2.712247133255005,
1358
+ "learning_rate": 6.5982329181836325e-06,
1359
+ "loss": 0.647,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.955583556465585,
1364
+ "grad_norm": 2.683356761932373,
1365
+ "learning_rate": 6.487825521280109e-06,
1366
+ "loss": 0.7316,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.9656638840762324,
1371
+ "grad_norm": 2.6433842182159424,
1372
+ "learning_rate": 6.3779043617031775e-06,
1373
+ "loss": 0.84,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.9757442116868797,
1378
+ "grad_norm": 4.231180667877197,
1379
+ "learning_rate": 6.268484657310351e-06,
1380
+ "loss": 0.7416,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.9858245392975271,
1385
+ "grad_norm": 3.0023813247680664,
1386
+ "learning_rate": 6.159581556535989e-06,
1387
+ "loss": 0.8632,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.9959048669081745,
1392
+ "grad_norm": 2.6306092739105225,
1393
+ "learning_rate": 6.051210136294089e-06,
1394
+ "loss": 0.6557,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 2.005985194518822,
1399
+ "grad_norm": 3.3288090229034424,
1400
+ "learning_rate": 5.943385399891004e-06,
1401
+ "loss": 0.5327,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 2.016065522129469,
1406
+ "grad_norm": 3.394890069961548,
1407
+ "learning_rate": 5.8361222749483246e-06,
1408
+ "loss": 0.5682,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 2.0261458497401166,
1413
+ "grad_norm": 4.5706658363342285,
1414
+ "learning_rate": 5.729435611336239e-06,
1415
+ "loss": 0.521,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 2.036226177350764,
1420
+ "grad_norm": 3.595043420791626,
1421
+ "learning_rate": 5.6233401791176946e-06,
1422
+ "loss": 0.4973,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 2.0463065049614113,
1427
+ "grad_norm": 3.381319761276245,
1428
+ "learning_rate": 5.517850666503547e-06,
1429
+ "loss": 0.7273,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 2.0563868325720587,
1434
+ "grad_norm": 3.813019037246704,
1435
+ "learning_rate": 5.412981677819094e-06,
1436
+ "loss": 0.5748,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 2.066467160182706,
1441
+ "grad_norm": 2.9697418212890625,
1442
+ "learning_rate": 5.308747731482207e-06,
1443
+ "loss": 0.6197,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 2.0765474877933534,
1448
+ "grad_norm": 4.898626804351807,
1449
+ "learning_rate": 5.205163257993341e-06,
1450
+ "loss": 0.4839,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 2.0866278154040008,
1455
+ "grad_norm": 4.427509784698486,
1456
+ "learning_rate": 5.1022425979377174e-06,
1457
+ "loss": 0.455,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 2.096708143014648,
1462
+ "grad_norm": 3.7625739574432373,
1463
+ "learning_rate": 5.000000000000003e-06,
1464
+ "loss": 0.538,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 2.1067884706252955,
1469
+ "grad_norm": 2.9984402656555176,
1470
+ "learning_rate": 4.89844961899163e-06,
1471
+ "loss": 0.5426,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 2.116868798235943,
1476
+ "grad_norm": 3.2791342735290527,
1477
+ "learning_rate": 4.797605513891179e-06,
1478
+ "loss": 0.5505,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 2.12694912584659,
1483
+ "grad_norm": 3.1224496364593506,
1484
+ "learning_rate": 4.697481645898012e-06,
1485
+ "loss": 0.5466,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 2.137029453457237,
1490
+ "grad_norm": 2.9908924102783203,
1491
+ "learning_rate": 4.598091876499417e-06,
1492
+ "loss": 0.4739,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 2.1471097810678845,
1497
+ "grad_norm": 3.272909164428711,
1498
+ "learning_rate": 4.4994499655515865e-06,
1499
+ "loss": 0.4773,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 2.157190108678532,
1504
+ "grad_norm": 3.1660666465759277,
1505
+ "learning_rate": 4.4015695693746685e-06,
1506
+ "loss": 0.6012,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 2.1672704362891793,
1511
+ "grad_norm": 2.9826879501342773,
1512
+ "learning_rate": 4.304464238862115e-06,
1513
+ "loss": 0.559,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 2.1773507638998266,
1518
+ "grad_norm": 3.156632900238037,
1519
+ "learning_rate": 4.208147417604665e-06,
1520
+ "loss": 0.4658,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 2.187431091510474,
1525
+ "grad_norm": 2.7207696437835693,
1526
+ "learning_rate": 4.112632440029176e-06,
1527
+ "loss": 0.4746,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 2.1975114191211214,
1532
+ "grad_norm": 3.170917272567749,
1533
+ "learning_rate": 4.017932529552543e-06,
1534
+ "loss": 0.4555,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 2.2075917467317687,
1539
+ "grad_norm": 2.873971939086914,
1540
+ "learning_rate": 3.924060796751012e-06,
1541
+ "loss": 0.4927,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 2.217672074342416,
1546
+ "grad_norm": 3.0037410259246826,
1547
+ "learning_rate": 3.83103023754511e-06,
1548
+ "loss": 0.5199,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 2.2277524019530635,
1553
+ "grad_norm": 3.2414352893829346,
1554
+ "learning_rate": 3.7388537314004394e-06,
1555
+ "loss": 0.4665,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 2.237832729563711,
1560
+ "grad_norm": 2.9535632133483887,
1561
+ "learning_rate": 3.647544039544615e-06,
1562
+ "loss": 0.4625,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 2.247913057174358,
1567
+ "grad_norm": 2.874563455581665,
1568
+ "learning_rate": 3.557113803200537e-06,
1569
+ "loss": 0.4651,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 2.2579933847850056,
1574
+ "grad_norm": 2.8400771617889404,
1575
+ "learning_rate": 3.4675755418363054e-06,
1576
+ "loss": 0.4741,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 2.268073712395653,
1581
+ "grad_norm": 3.162914752960205,
1582
+ "learning_rate": 3.378941651431996e-06,
1583
+ "loss": 0.5043,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 2.2781540400063003,
1588
+ "grad_norm": 3.108367681503296,
1589
+ "learning_rate": 3.2912244027634953e-06,
1590
+ "loss": 0.4612,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 2.2882343676169477,
1595
+ "grad_norm": 2.9453072547912598,
1596
+ "learning_rate": 3.204435939703705e-06,
1597
+ "loss": 0.5951,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 2.298314695227595,
1602
+ "grad_norm": 2.926748752593994,
1603
+ "learning_rate": 3.1185882775413123e-06,
1604
+ "loss": 0.4727,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 2.3083950228382424,
1609
+ "grad_norm": 2.7505362033843994,
1610
+ "learning_rate": 3.0336933013173307e-06,
1611
+ "loss": 0.4771,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 2.3184753504488897,
1616
+ "grad_norm": 3.1303627490997314,
1617
+ "learning_rate": 2.949762764179711e-06,
1618
+ "loss": 0.5534,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 2.328555678059537,
1623
+ "grad_norm": 2.6740784645080566,
1624
+ "learning_rate": 2.8668082857562006e-06,
1625
+ "loss": 0.4713,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 2.3386360056701845,
1630
+ "grad_norm": 2.6228513717651367,
1631
+ "learning_rate": 2.7848413505456564e-06,
1632
+ "loss": 0.532,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 2.348716333280832,
1637
+ "grad_norm": 3.3503799438476562,
1638
+ "learning_rate": 2.7038733063281177e-06,
1639
+ "loss": 0.5022,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 2.358796660891479,
1644
+ "grad_norm": 2.798093557357788,
1645
+ "learning_rate": 2.6239153625937786e-06,
1646
+ "loss": 0.4674,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 2.368876988502126,
1651
+ "grad_norm": 2.9283840656280518,
1652
+ "learning_rate": 2.544978588991096e-06,
1653
+ "loss": 0.5145,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 2.3789573161127735,
1658
+ "grad_norm": 2.9294168949127197,
1659
+ "learning_rate": 2.4670739137942723e-06,
1660
+ "loss": 0.5262,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 2.389037643723421,
1665
+ "grad_norm": 2.9340579509735107,
1666
+ "learning_rate": 2.390212122390323e-06,
1667
+ "loss": 0.4654,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 2.3991179713340682,
1672
+ "grad_norm": 2.9282586574554443,
1673
+ "learning_rate": 2.3144038557858915e-06,
1674
+ "loss": 0.7147,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 2.4091982989447156,
1679
+ "grad_norm": 2.9570140838623047,
1680
+ "learning_rate": 2.2396596091340805e-06,
1681
+ "loss": 0.4643,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 2.419278626555363,
1686
+ "grad_norm": 2.7537012100219727,
1687
+ "learning_rate": 2.165989730281475e-06,
1688
+ "loss": 0.4467,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 2.4293589541660103,
1693
+ "grad_norm": 2.764420986175537,
1694
+ "learning_rate": 2.0934044183355384e-06,
1695
+ "loss": 0.4774,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 2.4394392817766577,
1700
+ "grad_norm": 3.11476993560791,
1701
+ "learning_rate": 2.0219137222526188e-06,
1702
+ "loss": 0.5792,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 2.449519609387305,
1707
+ "grad_norm": 4.960219860076904,
1708
+ "learning_rate": 1.9515275394467446e-06,
1709
+ "loss": 0.457,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 2.4595999369979524,
1714
+ "grad_norm": 3.0883636474609375,
1715
+ "learning_rate": 1.882255614419376e-06,
1716
+ "loss": 0.6268,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 2.4696802646086,
1721
+ "grad_norm": 2.9060003757476807,
1722
+ "learning_rate": 1.8141075374103634e-06,
1723
+ "loss": 0.5785,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 2.479760592219247,
1728
+ "grad_norm": 2.7196030616760254,
1729
+ "learning_rate": 1.7470927430702277e-06,
1730
+ "loss": 0.4658,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 2.4898409198298945,
1735
+ "grad_norm": 2.8663458824157715,
1736
+ "learning_rate": 1.6812205091539979e-06,
1737
+ "loss": 0.4635,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 2.499921247440542,
1742
+ "grad_norm": 2.7674198150634766,
1743
+ "learning_rate": 1.6164999552367767e-06,
1744
+ "loss": 0.475,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 2.5100015750511893,
1749
+ "grad_norm": 2.971801280975342,
1750
+ "learning_rate": 1.5529400414511809e-06,
1751
+ "loss": 0.5657,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 2.5200819026618366,
1756
+ "grad_norm": 3.0309677124023438,
1757
+ "learning_rate": 1.4905495672468784e-06,
1758
+ "loss": 0.4609,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 2.530162230272484,
1763
+ "grad_norm": 2.9311161041259766,
1764
+ "learning_rate": 1.4293371701723701e-06,
1765
+ "loss": 0.5184,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 2.5402425578831314,
1770
+ "grad_norm": 2.813347578048706,
1771
+ "learning_rate": 1.369311324679159e-06,
1772
+ "loss": 0.4675,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 2.5503228854937783,
1777
+ "grad_norm": 2.8366470336914062,
1778
+ "learning_rate": 1.3104803409485357e-06,
1779
+ "loss": 0.5566,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 2.5604032131044256,
1784
+ "grad_norm": 2.9654905796051025,
1785
+ "learning_rate": 1.252852363741084e-06,
1786
+ "loss": 0.4739,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 2.570483540715073,
1791
+ "grad_norm": 2.7376723289489746,
1792
+ "learning_rate": 1.196435371269089e-06,
1793
+ "loss": 0.4755,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 2.5805638683257204,
1798
+ "grad_norm": 2.603374719619751,
1799
+ "learning_rate": 1.1412371740920036e-06,
1800
+ "loss": 0.45,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 2.5906441959363677,
1805
+ "grad_norm": 2.7828543186187744,
1806
+ "learning_rate": 1.0872654140351458e-06,
1807
+ "loss": 0.7043,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 2.600724523547015,
1812
+ "grad_norm": 2.6468091011047363,
1813
+ "learning_rate": 1.0345275631317165e-06,
1814
+ "loss": 0.6008,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 2.6108048511576625,
1819
+ "grad_norm": 2.7856605052948,
1820
+ "learning_rate": 9.830309225883562e-07,
1821
+ "loss": 0.55,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 2.62088517876831,
1826
+ "grad_norm": 2.949894428253174,
1827
+ "learning_rate": 9.327826217743452e-07,
1828
+ "loss": 0.4517,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 2.630965506378957,
1833
+ "grad_norm": 3.2041678428649902,
1834
+ "learning_rate": 8.837896172345827e-07,
1835
+ "loss": 0.5641,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 2.6410458339896046,
1840
+ "grad_norm": 3.0084447860717773,
1841
+ "learning_rate": 8.360586917264979e-07,
1842
+ "loss": 0.4635,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 2.651126161600252,
1847
+ "grad_norm": 2.7008798122406006,
1848
+ "learning_rate": 7.895964532810318e-07,
1849
+ "loss": 0.5861,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 2.6612064892108993,
1854
+ "grad_norm": 2.8974366188049316,
1855
+ "learning_rate": 7.4440933428779e-07,
1856
+ "loss": 0.4619,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 2.6712868168215467,
1861
+ "grad_norm": 2.954524040222168,
1862
+ "learning_rate": 7.005035906045199e-07,
1863
+ "loss": 0.4819,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 2.681367144432194,
1868
+ "grad_norm": 2.6953723430633545,
1869
+ "learning_rate": 6.578853006910402e-07,
1870
+ "loss": 0.4843,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 2.6914474720428414,
1875
+ "grad_norm": 3.108698844909668,
1876
+ "learning_rate": 6.165603647677054e-07,
1877
+ "loss": 0.4586,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 2.7015277996534888,
1882
+ "grad_norm": 2.9222874641418457,
1883
+ "learning_rate": 5.765345039985648e-07,
1884
+ "loss": 0.4737,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 2.711608127264136,
1889
+ "grad_norm": 2.904561996459961,
1890
+ "learning_rate": 5.378132596993047e-07,
1891
+ "loss": 0.4641,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 2.7216884548747835,
1896
+ "grad_norm": 3.0697550773620605,
1897
+ "learning_rate": 5.004019925700921e-07,
1898
+ "loss": 0.5555,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 2.731768782485431,
1903
+ "grad_norm": 2.980802536010742,
1904
+ "learning_rate": 4.6430588195341853e-07,
1905
+ "loss": 0.5908,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 2.7418491100960782,
1910
+ "grad_norm": 3.690682888031006,
1911
+ "learning_rate": 4.295299251170537e-07,
1912
+ "loss": 0.5399,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 2.7519294377067256,
1917
+ "grad_norm": 2.920565128326416,
1918
+ "learning_rate": 3.960789365622075e-07,
1919
+ "loss": 0.7304,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 2.762009765317373,
1924
+ "grad_norm": 2.853963851928711,
1925
+ "learning_rate": 3.6395754735699896e-07,
1926
+ "loss": 0.571,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 2.7720900929280203,
1931
+ "grad_norm": 2.8439598083496094,
1932
+ "learning_rate": 3.3317020449530666e-07,
1933
+ "loss": 0.5728,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 2.7821704205386677,
1938
+ "grad_norm": 2.6904118061065674,
1939
+ "learning_rate": 3.0372117028111825e-07,
1940
+ "loss": 0.4688,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 2.792250748149315,
1945
+ "grad_norm": 2.8385207653045654,
1946
+ "learning_rate": 2.7561452173844206e-07,
1947
+ "loss": 0.5202,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 2.8023310757599624,
1952
+ "grad_norm": 2.739987373352051,
1953
+ "learning_rate": 2.488541500468666e-07,
1954
+ "loss": 0.586,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 2.81241140337061,
1959
+ "grad_norm": 2.9050772190093994,
1960
+ "learning_rate": 2.2344376000285606e-07,
1961
+ "loss": 0.4698,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 2.822491730981257,
1966
+ "grad_norm": 2.7418956756591797,
1967
+ "learning_rate": 1.993868695068457e-07,
1968
+ "loss": 0.4432,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 2.832572058591904,
1973
+ "grad_norm": 2.746795892715454,
1974
+ "learning_rate": 1.766868090762075e-07,
1975
+ "loss": 0.5331,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 2.8426523862025515,
1980
+ "grad_norm": 2.7366440296173096,
1981
+ "learning_rate": 1.553467213841664e-07,
1982
+ "loss": 0.4813,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 2.852732713813199,
1987
+ "grad_norm": 2.755558729171753,
1988
+ "learning_rate": 1.3536956082472074e-07,
1989
+ "loss": 0.4859,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 2.862813041423846,
1994
+ "grad_norm": 2.7609097957611084,
1995
+ "learning_rate": 1.1675809310361497e-07,
1996
+ "loss": 0.4655,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 2.8728933690344935,
2001
+ "grad_norm": 3.0042688846588135,
2002
+ "learning_rate": 9.951489485545696e-08,
2003
+ "loss": 0.4557,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 2.882973696645141,
2008
+ "grad_norm": 2.9627745151519775,
2009
+ "learning_rate": 8.364235328699566e-08,
2010
+ "loss": 0.4968,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 2.8930540242557883,
2015
+ "grad_norm": 2.8256924152374268,
2016
+ "learning_rate": 6.914266584662988e-08,
2017
+ "loss": 0.4728,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 2.9031343518664356,
2022
+ "grad_norm": 2.7654502391815186,
2023
+ "learning_rate": 5.6017839920180506e-08,
2024
+ "loss": 0.4594,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 2.913214679477083,
2029
+ "grad_norm": 5.463405609130859,
2030
+ "learning_rate": 4.426969255298841e-08,
2031
+ "loss": 0.4786,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 2.9232950070877304,
2036
+ "grad_norm": 2.978433132171631,
2037
+ "learning_rate": 3.38998501983534e-08,
2038
+ "loss": 0.4687,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 2.9333753346983777,
2043
+ "grad_norm": 2.887697458267212,
2044
+ "learning_rate": 2.4909748492362162e-08,
2045
+ "loss": 0.5466,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 2.943455662309025,
2050
+ "grad_norm": 2.823009729385376,
2051
+ "learning_rate": 1.730063205513277e-08,
2052
+ "loss": 0.5068,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 2.9535359899196725,
2057
+ "grad_norm": 2.9089882373809814,
2058
+ "learning_rate": 1.1073554318509206e-08,
2059
+ "loss": 0.4521,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 2.96361631753032,
2064
+ "grad_norm": 2.763700246810913,
2065
+ "learning_rate": 6.229377380218005e-09,
2066
+ "loss": 0.456,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 2.973696645140967,
2071
+ "grad_norm": 2.9146535396575928,
2072
+ "learning_rate": 2.7687718845148538e-09,
2073
+ "loss": 0.4586,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 2.9837769727516146,
2078
+ "grad_norm": 2.999981641769409,
2079
+ "learning_rate": 6.922169293421821e-10,
2080
+ "loss": 0.464,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 2.9938573003622615,
2085
+ "grad_norm": 4.130459785461426,
2086
+ "learning_rate": 0.0,
2087
+ "loss": 0.4729,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 2.9938573003622615,
2092
+ "step": 297,
2093
+ "total_flos": 1.3286712322107113e+19,
2094
+ "train_loss": 0.7266113918638389,
2095
+ "train_runtime": 26017.2965,
2096
+ "train_samples_per_second": 5.856,
2097
+ "train_steps_per_second": 0.011
2098
+ }
2099
+ ],
2100
+ "logging_steps": 1.0,
2101
+ "max_steps": 297,
2102
+ "num_input_tokens_seen": 0,
2103
+ "num_train_epochs": 3,
2104
+ "save_steps": 500,
2105
+ "stateful_callbacks": {
2106
+ "TrainerControl": {
2107
+ "args": {
2108
+ "should_epoch_stop": false,
2109
+ "should_evaluate": false,
2110
+ "should_log": false,
2111
+ "should_save": true,
2112
+ "should_training_stop": true
2113
+ },
2114
+ "attributes": {}
2115
+ }
2116
+ },
2117
+ "total_flos": 1.3286712322107113e+19,
2118
+ "train_batch_size": 2,
2119
+ "trial_name": null,
2120
+ "trial_params": null
2121
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef760d844811fa9b68a266ab0e29d3c7588dd7bfb975b7648c171a1a9170c1a
3
+ size 6776