hardlyworking commited on
Commit
530e9bd
·
verified ·
1 Parent(s): 66941c3

Training in progress, step 114, checkpoint

Browse files
checkpoint-114/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endofprompt|>": 100276,
3
+ "<|im_end|>": 100265,
4
+ "<|im_start|>": 100264
5
+ }
checkpoint-114/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-114/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": 100265,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 262144,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 100257,
22
+ "pretraining_tp": 1,
23
+ "resid_pdrop": 0.0,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_scaling": null,
26
+ "rope_theta": 128000000,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.52.4",
30
+ "use_cache": false,
31
+ "vocab_size": 102400
32
+ }
checkpoint-114/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "do_sample": true,
5
+ "eos_token_id": 100265,
6
+ "pad_token_id": 100257,
7
+ "transformers_version": "4.52.4",
8
+ "use_cache": false
9
+ }
checkpoint-114/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-114/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03c03182572292cdeeccd84dbb018c85657d9c274c1af379501b6607a589bbc
3
+ size 4983077832
checkpoint-114/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5743457f77a4952d914119b14a3a5988e3d1ff8485e9c42979fbaeb8f9f0a4
3
+ size 3842234168
checkpoint-114/model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8825282560
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.norm.weight": "model-00002-of-00002.safetensors"
260
+ }
261
+ }
checkpoint-114/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c9d614580d0968a0f86311aaf34e4cca264dbbeb00a6eb3bae2a57fccff036
3
+ size 11466962878
checkpoint-114/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
3
+ size 14244
checkpoint-114/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e370a8b067a6fd3de43ea0855e35d35626079fd6b55224a205d39fb4397e68bc
3
+ size 1064
checkpoint-114/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-114/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-114/tokenizer_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100257": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100258": {
13
+ "content": "<|fim_prefix|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100259": {
21
+ "content": "<|fim_middle|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100260": {
29
+ "content": "<|fim_suffix|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100264": {
37
+ "content": "<|im_start|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "100265": {
45
+ "content": "<|im_end|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100276": {
53
+ "content": "<|endofprompt|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "bos_token": "<|endoftext|>",
62
+ "clean_up_tokenization_spaces": false,
63
+ "eos_token": "<|im_end|>",
64
+ "extra_special_tokens": {},
65
+ "model_max_length": 262144,
66
+ "pad_token": "<|endoftext|>",
67
+ "tokenizer_class": "GPT2Tokenizer",
68
+ "unk_token": "<|endoftext|>"
69
+ }
checkpoint-114/trainer_state.json ADDED
@@ -0,0 +1,832 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9956331877729258,
6
+ "eval_steps": 500,
7
+ "global_step": 114,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008733624454148471,
14
+ "grad_norm": 2.234375,
15
+ "learning_rate": 0.0,
16
+ "loss": 2.578,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.017467248908296942,
21
+ "grad_norm": 2.515625,
22
+ "learning_rate": 4.5454545454545457e-07,
23
+ "loss": 2.6324,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.026200873362445413,
28
+ "grad_norm": 2.546875,
29
+ "learning_rate": 9.090909090909091e-07,
30
+ "loss": 2.6563,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.034934497816593885,
35
+ "grad_norm": 2.21875,
36
+ "learning_rate": 1.3636363636363636e-06,
37
+ "loss": 2.5986,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.043668122270742356,
42
+ "grad_norm": 2.40625,
43
+ "learning_rate": 1.8181818181818183e-06,
44
+ "loss": 2.6456,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.05240174672489083,
49
+ "grad_norm": 2.28125,
50
+ "learning_rate": 2.2727272727272728e-06,
51
+ "loss": 2.638,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0611353711790393,
56
+ "grad_norm": 2.421875,
57
+ "learning_rate": 2.7272727272727272e-06,
58
+ "loss": 2.6678,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.06986899563318777,
63
+ "grad_norm": 2.328125,
64
+ "learning_rate": 3.181818181818182e-06,
65
+ "loss": 2.6304,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.07860262008733625,
70
+ "grad_norm": 2.046875,
71
+ "learning_rate": 3.6363636363636366e-06,
72
+ "loss": 2.6253,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.08733624454148471,
77
+ "grad_norm": 2.109375,
78
+ "learning_rate": 4.0909090909090915e-06,
79
+ "loss": 2.6161,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.09606986899563319,
84
+ "grad_norm": 2.015625,
85
+ "learning_rate": 4.5454545454545455e-06,
86
+ "loss": 2.6971,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.10480349344978165,
91
+ "grad_norm": 1.75,
92
+ "learning_rate": 5e-06,
93
+ "loss": 2.5767,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.11353711790393013,
98
+ "grad_norm": 1.703125,
99
+ "learning_rate": 5.4545454545454545e-06,
100
+ "loss": 2.5748,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.1222707423580786,
105
+ "grad_norm": 1.6328125,
106
+ "learning_rate": 5.90909090909091e-06,
107
+ "loss": 2.5845,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.13100436681222707,
112
+ "grad_norm": 1.5234375,
113
+ "learning_rate": 6.363636363636364e-06,
114
+ "loss": 2.6236,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.13973799126637554,
119
+ "grad_norm": 1.3359375,
120
+ "learning_rate": 6.818181818181818e-06,
121
+ "loss": 2.6045,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.14847161572052403,
126
+ "grad_norm": 1.296875,
127
+ "learning_rate": 7.272727272727273e-06,
128
+ "loss": 2.617,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.1572052401746725,
133
+ "grad_norm": 1.15625,
134
+ "learning_rate": 7.727272727272727e-06,
135
+ "loss": 2.5447,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.16593886462882096,
140
+ "grad_norm": 1.1796875,
141
+ "learning_rate": 8.181818181818183e-06,
142
+ "loss": 2.6597,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.17467248908296942,
147
+ "grad_norm": 1.1328125,
148
+ "learning_rate": 8.636363636363637e-06,
149
+ "loss": 2.5515,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.18340611353711792,
154
+ "grad_norm": 1.140625,
155
+ "learning_rate": 9.090909090909091e-06,
156
+ "loss": 2.5699,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.19213973799126638,
161
+ "grad_norm": 1.1015625,
162
+ "learning_rate": 9.545454545454547e-06,
163
+ "loss": 2.6027,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.20087336244541484,
168
+ "grad_norm": 1.109375,
169
+ "learning_rate": 1e-05,
170
+ "loss": 2.5589,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.2096069868995633,
175
+ "grad_norm": 1.0859375,
176
+ "learning_rate": 9.999869003890174e-06,
177
+ "loss": 2.5869,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.2183406113537118,
182
+ "grad_norm": 1.078125,
183
+ "learning_rate": 9.999476022424688e-06,
184
+ "loss": 2.5414,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.22707423580786026,
189
+ "grad_norm": 1.03125,
190
+ "learning_rate": 9.998821076195158e-06,
191
+ "loss": 2.6005,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.23580786026200873,
196
+ "grad_norm": 1.078125,
197
+ "learning_rate": 9.997904199519748e-06,
198
+ "loss": 2.5769,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.2445414847161572,
203
+ "grad_norm": 1.0703125,
204
+ "learning_rate": 9.996725440441368e-06,
205
+ "loss": 2.6084,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.25327510917030566,
210
+ "grad_norm": 0.98828125,
211
+ "learning_rate": 9.995284860725162e-06,
212
+ "loss": 2.6237,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.26200873362445415,
217
+ "grad_norm": 0.9453125,
218
+ "learning_rate": 9.993582535855265e-06,
219
+ "loss": 2.577,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.27074235807860264,
224
+ "grad_norm": 0.953125,
225
+ "learning_rate": 9.991618555030848e-06,
226
+ "loss": 2.591,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.2794759825327511,
231
+ "grad_norm": 0.94921875,
232
+ "learning_rate": 9.989393021161455e-06,
233
+ "loss": 2.5533,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.28820960698689957,
238
+ "grad_norm": 0.99609375,
239
+ "learning_rate": 9.986906050861595e-06,
240
+ "loss": 2.5694,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.29694323144104806,
245
+ "grad_norm": 0.9765625,
246
+ "learning_rate": 9.98415777444464e-06,
247
+ "loss": 2.53,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.3056768558951965,
252
+ "grad_norm": 0.9296875,
253
+ "learning_rate": 9.981148335916e-06,
254
+ "loss": 2.5486,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.314410480349345,
259
+ "grad_norm": 0.92578125,
260
+ "learning_rate": 9.977877892965572e-06,
261
+ "loss": 2.5649,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.3231441048034934,
266
+ "grad_norm": 0.9609375,
267
+ "learning_rate": 9.974346616959476e-06,
268
+ "loss": 2.6342,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.3318777292576419,
273
+ "grad_norm": 0.9140625,
274
+ "learning_rate": 9.970554692931081e-06,
275
+ "loss": 2.5869,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.3406113537117904,
280
+ "grad_norm": 0.90234375,
281
+ "learning_rate": 9.966502319571303e-06,
282
+ "loss": 2.5639,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.34934497816593885,
287
+ "grad_norm": 0.9375,
288
+ "learning_rate": 9.962189709218202e-06,
289
+ "loss": 2.5443,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.35807860262008734,
294
+ "grad_norm": 0.9453125,
295
+ "learning_rate": 9.95761708784585e-06,
296
+ "loss": 2.5412,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.36681222707423583,
301
+ "grad_norm": 0.8828125,
302
+ "learning_rate": 9.952784695052494e-06,
303
+ "loss": 2.5115,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.37554585152838427,
308
+ "grad_norm": 0.99609375,
309
+ "learning_rate": 9.94769278404799e-06,
310
+ "loss": 2.4547,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.38427947598253276,
315
+ "grad_norm": 0.90234375,
316
+ "learning_rate": 9.942341621640558e-06,
317
+ "loss": 2.5528,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.3930131004366812,
322
+ "grad_norm": 0.96484375,
323
+ "learning_rate": 9.936731488222776e-06,
324
+ "loss": 2.5629,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.4017467248908297,
329
+ "grad_norm": 0.89453125,
330
+ "learning_rate": 9.930862677756912e-06,
331
+ "loss": 2.5632,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.4104803493449782,
336
+ "grad_norm": 0.890625,
337
+ "learning_rate": 9.924735497759497e-06,
338
+ "loss": 2.5625,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.4192139737991266,
343
+ "grad_norm": 0.875,
344
+ "learning_rate": 9.918350269285228e-06,
345
+ "loss": 2.5522,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.4279475982532751,
350
+ "grad_norm": 0.90234375,
351
+ "learning_rate": 9.911707326910145e-06,
352
+ "loss": 2.6349,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.4366812227074236,
357
+ "grad_norm": 0.91015625,
358
+ "learning_rate": 9.904807018714088e-06,
359
+ "loss": 2.6174,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.44541484716157204,
364
+ "grad_norm": 0.89453125,
365
+ "learning_rate": 9.897649706262474e-06,
366
+ "loss": 2.5732,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.45414847161572053,
371
+ "grad_norm": 0.91796875,
372
+ "learning_rate": 9.890235764587332e-06,
373
+ "loss": 2.6071,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.462882096069869,
378
+ "grad_norm": 0.89453125,
379
+ "learning_rate": 9.882565582167673e-06,
380
+ "loss": 2.5587,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.47161572052401746,
385
+ "grad_norm": 0.88671875,
386
+ "learning_rate": 9.874639560909118e-06,
387
+ "loss": 2.5676,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.48034934497816595,
392
+ "grad_norm": 0.890625,
393
+ "learning_rate": 9.866458116122852e-06,
394
+ "loss": 2.515,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.4890829694323144,
399
+ "grad_norm": 0.8984375,
400
+ "learning_rate": 9.858021676503846e-06,
401
+ "loss": 2.5355,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.4978165938864629,
406
+ "grad_norm": 0.90234375,
407
+ "learning_rate": 9.849330684108409e-06,
408
+ "loss": 2.5798,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.5065502183406113,
413
+ "grad_norm": 0.87890625,
414
+ "learning_rate": 9.840385594331022e-06,
415
+ "loss": 2.5391,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.5152838427947598,
420
+ "grad_norm": 0.90625,
421
+ "learning_rate": 9.831186875880467e-06,
422
+ "loss": 2.521,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.5240174672489083,
427
+ "grad_norm": 0.91796875,
428
+ "learning_rate": 9.82173501075528e-06,
429
+ "loss": 2.5553,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.5327510917030568,
434
+ "grad_norm": 0.890625,
435
+ "learning_rate": 9.812030494218484e-06,
436
+ "loss": 2.6096,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.5414847161572053,
441
+ "grad_norm": 0.88671875,
442
+ "learning_rate": 9.802073834771642e-06,
443
+ "loss": 2.5513,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.5502183406113537,
448
+ "grad_norm": 0.96484375,
449
+ "learning_rate": 9.79186555412822e-06,
450
+ "loss": 2.6127,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.5589519650655022,
455
+ "grad_norm": 0.90234375,
456
+ "learning_rate": 9.781406187186237e-06,
457
+ "loss": 2.5172,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.5676855895196506,
462
+ "grad_norm": 0.87890625,
463
+ "learning_rate": 9.770696282000245e-06,
464
+ "loss": 2.5562,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.5764192139737991,
469
+ "grad_norm": 0.88671875,
470
+ "learning_rate": 9.759736399752611e-06,
471
+ "loss": 2.5538,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.5851528384279476,
476
+ "grad_norm": 0.89453125,
477
+ "learning_rate": 9.748527114724111e-06,
478
+ "loss": 2.5661,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.5938864628820961,
483
+ "grad_norm": 0.91796875,
484
+ "learning_rate": 9.737069014263837e-06,
485
+ "loss": 2.6247,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.6026200873362445,
490
+ "grad_norm": 0.9296875,
491
+ "learning_rate": 9.725362698758425e-06,
492
+ "loss": 2.5432,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.611353711790393,
497
+ "grad_norm": 0.890625,
498
+ "learning_rate": 9.713408781600588e-06,
499
+ "loss": 2.51,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.6200873362445415,
504
+ "grad_norm": 0.8828125,
505
+ "learning_rate": 9.701207889156989e-06,
506
+ "loss": 2.5114,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.62882096069869,
511
+ "grad_norm": 0.9296875,
512
+ "learning_rate": 9.688760660735403e-06,
513
+ "loss": 2.5707,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.6375545851528385,
518
+ "grad_norm": 0.91015625,
519
+ "learning_rate": 9.676067748551232e-06,
520
+ "loss": 2.579,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.6462882096069869,
525
+ "grad_norm": 0.91015625,
526
+ "learning_rate": 9.663129817693323e-06,
527
+ "loss": 2.5844,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.6550218340611353,
532
+ "grad_norm": 0.9296875,
533
+ "learning_rate": 9.64994754608912e-06,
534
+ "loss": 2.5768,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.6637554585152838,
539
+ "grad_norm": 0.890625,
540
+ "learning_rate": 9.636521624469144e-06,
541
+ "loss": 2.5568,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.6724890829694323,
546
+ "grad_norm": 0.91796875,
547
+ "learning_rate": 9.622852756330797e-06,
548
+ "loss": 2.5348,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.6812227074235808,
553
+ "grad_norm": 0.88671875,
554
+ "learning_rate": 9.608941657901496e-06,
555
+ "loss": 2.5221,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.6899563318777293,
560
+ "grad_norm": 0.921875,
561
+ "learning_rate": 9.594789058101154e-06,
562
+ "loss": 2.6385,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.6986899563318777,
567
+ "grad_norm": 0.91796875,
568
+ "learning_rate": 9.580395698503979e-06,
569
+ "loss": 2.5107,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.7074235807860262,
574
+ "grad_norm": 0.953125,
575
+ "learning_rate": 9.565762333299616e-06,
576
+ "loss": 2.5751,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.7161572052401747,
581
+ "grad_norm": 0.93359375,
582
+ "learning_rate": 9.550889729253631e-06,
583
+ "loss": 2.6106,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.7248908296943232,
588
+ "grad_norm": 0.921875,
589
+ "learning_rate": 9.535778665667334e-06,
590
+ "loss": 2.6177,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.7336244541484717,
595
+ "grad_norm": 1.0,
596
+ "learning_rate": 9.520429934336944e-06,
597
+ "loss": 2.5421,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.74235807860262,
602
+ "grad_norm": 0.90234375,
603
+ "learning_rate": 9.504844339512096e-06,
604
+ "loss": 2.6234,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.7510917030567685,
609
+ "grad_norm": 0.91015625,
610
+ "learning_rate": 9.48902269785371e-06,
611
+ "loss": 2.5791,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.759825327510917,
616
+ "grad_norm": 0.8671875,
617
+ "learning_rate": 9.472965838391187e-06,
618
+ "loss": 2.5052,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.7685589519650655,
623
+ "grad_norm": 0.984375,
624
+ "learning_rate": 9.456674602478975e-06,
625
+ "loss": 2.5445,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.777292576419214,
630
+ "grad_norm": 1.1953125,
631
+ "learning_rate": 9.44014984375249e-06,
632
+ "loss": 2.5956,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.7860262008733624,
637
+ "grad_norm": 0.87109375,
638
+ "learning_rate": 9.423392428083374e-06,
639
+ "loss": 2.5261,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.7947598253275109,
644
+ "grad_norm": 0.89453125,
645
+ "learning_rate": 9.406403233534134e-06,
646
+ "loss": 2.5626,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.8034934497816594,
651
+ "grad_norm": 0.89453125,
652
+ "learning_rate": 9.389183150312124e-06,
653
+ "loss": 2.5228,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.8122270742358079,
658
+ "grad_norm": 0.875,
659
+ "learning_rate": 9.371733080722911e-06,
660
+ "loss": 2.5494,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.8209606986899564,
665
+ "grad_norm": 0.93359375,
666
+ "learning_rate": 9.354053939122988e-06,
667
+ "loss": 2.6738,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.8296943231441049,
672
+ "grad_norm": 0.91015625,
673
+ "learning_rate": 9.33614665187187e-06,
674
+ "loss": 2.5862,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.8384279475982532,
679
+ "grad_norm": 0.91015625,
680
+ "learning_rate": 9.318012157283533e-06,
681
+ "loss": 2.57,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.8471615720524017,
686
+ "grad_norm": 0.96875,
687
+ "learning_rate": 9.299651405577286e-06,
688
+ "loss": 2.6046,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.8558951965065502,
693
+ "grad_norm": 0.9140625,
694
+ "learning_rate": 9.28106535882794e-06,
695
+ "loss": 2.5911,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.8646288209606987,
700
+ "grad_norm": 0.90234375,
701
+ "learning_rate": 9.262254990915427e-06,
702
+ "loss": 2.5898,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.8733624454148472,
707
+ "grad_norm": 0.93359375,
708
+ "learning_rate": 9.243221287473755e-06,
709
+ "loss": 2.6268,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.8820960698689956,
714
+ "grad_norm": 0.91015625,
715
+ "learning_rate": 9.223965245839367e-06,
716
+ "loss": 2.5823,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.8908296943231441,
721
+ "grad_norm": 0.91796875,
722
+ "learning_rate": 9.20448787499888e-06,
723
+ "loss": 2.6937,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.8995633187772926,
728
+ "grad_norm": 0.9296875,
729
+ "learning_rate": 9.184790195536217e-06,
730
+ "loss": 2.5609,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.9082969432314411,
735
+ "grad_norm": 0.91015625,
736
+ "learning_rate": 9.164873239579133e-06,
737
+ "loss": 2.5716,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.9170305676855895,
742
+ "grad_norm": 0.99609375,
743
+ "learning_rate": 9.144738050745129e-06,
744
+ "loss": 2.5099,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.925764192139738,
749
+ "grad_norm": 0.91015625,
750
+ "learning_rate": 9.124385684086762e-06,
751
+ "loss": 2.5131,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.9344978165938864,
756
+ "grad_norm": 1.015625,
757
+ "learning_rate": 9.103817206036383e-06,
758
+ "loss": 2.5407,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.9432314410480349,
763
+ "grad_norm": 0.9609375,
764
+ "learning_rate": 9.08303369435023e-06,
765
+ "loss": 2.5364,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.9519650655021834,
770
+ "grad_norm": 0.9296875,
771
+ "learning_rate": 9.062036238051978e-06,
772
+ "loss": 2.6053,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.9606986899563319,
777
+ "grad_norm": 0.9296875,
778
+ "learning_rate": 9.040825937375664e-06,
779
+ "loss": 2.563,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.9694323144104804,
784
+ "grad_norm": 0.9375,
785
+ "learning_rate": 9.019403903708036e-06,
786
+ "loss": 2.5744,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.9781659388646288,
791
+ "grad_norm": 0.93359375,
792
+ "learning_rate": 8.997771259530324e-06,
793
+ "loss": 2.5768,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.9868995633187773,
798
+ "grad_norm": 0.96484375,
799
+ "learning_rate": 8.975929138359423e-06,
800
+ "loss": 2.577,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.9956331877729258,
805
+ "grad_norm": 0.92578125,
806
+ "learning_rate": 8.953878684688492e-06,
807
+ "loss": 2.6206,
808
+ "step": 114
809
+ }
810
+ ],
811
+ "logging_steps": 1,
812
+ "max_steps": 456,
813
+ "num_input_tokens_seen": 0,
814
+ "num_train_epochs": 4,
815
+ "save_steps": 114,
816
+ "stateful_callbacks": {
817
+ "TrainerControl": {
818
+ "args": {
819
+ "should_epoch_stop": false,
820
+ "should_evaluate": false,
821
+ "should_log": false,
822
+ "should_save": true,
823
+ "should_training_stop": false
824
+ },
825
+ "attributes": {}
826
+ }
827
+ },
828
+ "total_flos": 3.5800432534093824e+17,
829
+ "train_batch_size": 2,
830
+ "trial_name": null,
831
+ "trial_params": null
832
+ }
checkpoint-114/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0592bc0dda5ec7f7a3ef05f7a468bec687ffdab3262199ff4c718485bd04da
3
+ size 6520
checkpoint-114/vocab.json ADDED
The diff for this file is too large to render. See raw diff