Training in progress, step 10
Browse files- config.json +35 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +217 -0
- trainer_log.jsonl +40 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "apple/DCLM-7B",
|
3 |
+
"apply_qk_norm": true,
|
4 |
+
"architectures": [
|
5 |
+
"OpenLMForCausalLM"
|
6 |
+
],
|
7 |
+
"attn_activation": null,
|
8 |
+
"attn_name": "torch_attn",
|
9 |
+
"attn_seq_scalar": null,
|
10 |
+
"attn_seq_scalar_alpha": null,
|
11 |
+
"dim": 4096,
|
12 |
+
"ffn_type": "swiglu_torch",
|
13 |
+
"model": "open_lm_7b",
|
14 |
+
"model_type": "openlm",
|
15 |
+
"moe_capacity_factor": 1.25,
|
16 |
+
"moe_expert_model_parallelism": false,
|
17 |
+
"moe_freq": 0,
|
18 |
+
"moe_loss_weight": 0.1,
|
19 |
+
"moe_num_experts": null,
|
20 |
+
"moe_top_k": 2,
|
21 |
+
"moe_weight_parallelism": false,
|
22 |
+
"n_heads": 32,
|
23 |
+
"n_layers": 32,
|
24 |
+
"norm_eps": 1e-05,
|
25 |
+
"norm_type": "gain_only_lp_layer_norm",
|
26 |
+
"params": null,
|
27 |
+
"positional_embedding_type": "rotary",
|
28 |
+
"post_embed_norm": false,
|
29 |
+
"qk_norm": true,
|
30 |
+
"seq_len": 2048,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.46.1",
|
33 |
+
"vocab_size": 50432,
|
34 |
+
"weight_tying": false
|
35 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b844ba0198fd0cf9665b46e9fe4cb9617f4d65691d29e344a81d5d7ea1ffc642
|
3 |
+
size 5000000704
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9d2160a3fdac02839bf41bec8c9e7d3e60f8328ab99293789149e8588a90dbf
|
3 |
+
size 4857411192
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c46168efc9443cf0a14a1b300344ec7115ebfccf689851b39dbee1ac854798f
|
3 |
+
size 3921970888
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13779349504
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.layers.0.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
7 |
+
"model.layers.0.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.attention_norm.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.1.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.1.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.attention_norm.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.10.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.10.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
27 |
+
"model.layers.10.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
28 |
+
"model.layers.10.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.attention_norm.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
31 |
+
"model.layers.10.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.11.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.11.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
36 |
+
"model.layers.11.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
37 |
+
"model.layers.11.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
38 |
+
"model.layers.11.attention_norm.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.12.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.12.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.attention_norm.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.13.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.13.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.attention_norm.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.14.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.14.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.attention_norm.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.15.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.15.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.attention_norm.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.16.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.16.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.attention_norm.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.17.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.17.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.attention_norm.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.18.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.18.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.attention_norm.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.19.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.19.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.attention_norm.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.2.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
115 |
+
"model.layers.2.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
116 |
+
"model.layers.2.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.attention_norm.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.20.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
124 |
+
"model.layers.20.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
125 |
+
"model.layers.20.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.attention_norm.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.21.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.21.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.attention_norm.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.22.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.22.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
144 |
+
"model.layers.22.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
145 |
+
"model.layers.22.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
146 |
+
"model.layers.22.attention_norm.weight": "model-00002-of-00003.safetensors",
|
147 |
+
"model.layers.22.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
|
148 |
+
"model.layers.22.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.ffn_norm.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.23.attention.in_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.23.attention.k_norm.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.attention.out_proj.weight": "model-00002-of-00003.safetensors",
|
153 |
+
"model.layers.23.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
|
154 |
+
"model.layers.23.attention.q_norm.weight": "model-00002-of-00003.safetensors",
|
155 |
+
"model.layers.23.attention_norm.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.24.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.24.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.attention_norm.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.25.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.25.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.attention_norm.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.26.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.26.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.attention_norm.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.27.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.27.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.attention_norm.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.28.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.28.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.attention_norm.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.29.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.29.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.attention_norm.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.3.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
214 |
+
"model.layers.3.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
215 |
+
"model.layers.3.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.attention_norm.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.30.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
223 |
+
"model.layers.30.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
224 |
+
"model.layers.30.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.attention_norm.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.31.attention.in_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.31.attention.k_norm.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.attention.out_proj.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.attention.q_norm.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.attention_norm.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.ffn_norm.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.4.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
241 |
+
"model.layers.4.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
242 |
+
"model.layers.4.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.attention_norm.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.5.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.5.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.attention_norm.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.6.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.6.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.attention_norm.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.7.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.7.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.attention_norm.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.8.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.8.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.attention_norm.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.9.attention.in_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.9.attention.k_norm.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.attention.out_proj.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.attention.q_norm.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.attention_norm.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.ffn_norm.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.norm.weight": "model-00003-of-00003.safetensors",
|
295 |
+
"model.output.weight": "model-00003-of-00003.safetensors",
|
296 |
+
"model.tok_embeddings.weight": "model-00001-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|padding|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50254": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50255": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50256": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50257": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50258": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50259": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50260": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50261": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50262": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50263": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50264": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50265": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50266": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50267": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50268": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50269": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50270": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50271": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50272": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50273": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50274": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50275": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50276": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
}
|
206 |
+
},
|
207 |
+
"bos_token": "<|endoftext|>",
|
208 |
+
"chat_template": "{% set system_message = 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
|
209 |
+
"clean_up_tokenization_spaces": false,
|
210 |
+
"eos_token": "<|endoftext|>",
|
211 |
+
"model_max_length": 1000000000000000019884624838656,
|
212 |
+
"pad_token": "<|endoftext|>",
|
213 |
+
"padding_side": "right",
|
214 |
+
"split_special_tokens": false,
|
215 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
216 |
+
"unk_token": "<|endoftext|>"
|
217 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 9875, "loss": 1.453, "lr": 1.0121457489878544e-08, "epoch": 0.0005063291139240507, "percentage": 0.01, "elapsed_time": "0:00:16", "remaining_time": "1 day, 22:21:15"}
|
2 |
+
{"current_steps": 2, "total_steps": 9875, "loss": 1.4052, "lr": 2.0242914979757088e-08, "epoch": 0.0010126582278481013, "percentage": 0.02, "elapsed_time": "0:00:18", "remaining_time": "1 day, 1:24:52"}
|
3 |
+
{"current_steps": 3, "total_steps": 9875, "loss": 1.282, "lr": 3.036437246963563e-08, "epoch": 0.0015189873417721519, "percentage": 0.03, "elapsed_time": "0:00:20", "remaining_time": "18:24:36"}
|
4 |
+
{"current_steps": 4, "total_steps": 9875, "loss": 1.489, "lr": 4.0485829959514176e-08, "epoch": 0.0020253164556962027, "percentage": 0.04, "elapsed_time": "0:00:21", "remaining_time": "14:52:32"}
|
5 |
+
{"current_steps": 5, "total_steps": 9875, "loss": 1.385, "lr": 5.0607287449392715e-08, "epoch": 0.002531645569620253, "percentage": 0.05, "elapsed_time": "0:00:23", "remaining_time": "12:46:29"}
|
6 |
+
{"current_steps": 6, "total_steps": 9875, "loss": 1.3136, "lr": 6.072874493927126e-08, "epoch": 0.0030379746835443038, "percentage": 0.06, "elapsed_time": "0:00:24", "remaining_time": "11:23:03"}
|
7 |
+
{"current_steps": 7, "total_steps": 9875, "loss": 1.4723, "lr": 7.08502024291498e-08, "epoch": 0.0035443037974683543, "percentage": 0.07, "elapsed_time": "0:00:26", "remaining_time": "10:22:07"}
|
8 |
+
{"current_steps": 8, "total_steps": 9875, "loss": 1.4201, "lr": 8.097165991902835e-08, "epoch": 0.004050632911392405, "percentage": 0.08, "elapsed_time": "0:00:28", "remaining_time": "9:36:57"}
|
9 |
+
{"current_steps": 9, "total_steps": 9875, "loss": 1.3341, "lr": 9.109311740890688e-08, "epoch": 0.004556962025316456, "percentage": 0.09, "elapsed_time": "0:00:29", "remaining_time": "9:01:41"}
|
10 |
+
{"current_steps": 10, "total_steps": 9875, "loss": 1.3569, "lr": 1.0121457489878543e-07, "epoch": 0.005063291139240506, "percentage": 0.1, "elapsed_time": "0:00:31", "remaining_time": "8:33:14"}
|
11 |
+
{"current_steps": 11, "total_steps": 9875, "loss": 1.4145, "lr": 1.1133603238866398e-07, "epoch": 0.005569620253164557, "percentage": 0.11, "elapsed_time": "0:02:48", "remaining_time": "1 day, 18:02:57"}
|
12 |
+
{"current_steps": 12, "total_steps": 9875, "loss": 1.1369, "lr": 1.2145748987854252e-07, "epoch": 0.0060759493670886075, "percentage": 0.12, "elapsed_time": "0:02:50", "remaining_time": "1 day, 14:54:11"}
|
13 |
+
{"current_steps": 13, "total_steps": 9875, "loss": 1.543, "lr": 1.3157894736842107e-07, "epoch": 0.006582278481012658, "percentage": 0.13, "elapsed_time": "0:02:51", "remaining_time": "1 day, 12:14:26"}
|
14 |
+
{"current_steps": 14, "total_steps": 9875, "loss": 1.5217, "lr": 1.417004048582996e-07, "epoch": 0.007088607594936709, "percentage": 0.14, "elapsed_time": "0:02:53", "remaining_time": "1 day, 9:57:27"}
|
15 |
+
{"current_steps": 15, "total_steps": 9875, "loss": 1.5287, "lr": 1.5182186234817813e-07, "epoch": 0.007594936708860759, "percentage": 0.15, "elapsed_time": "0:02:55", "remaining_time": "1 day, 7:58:51"}
|
16 |
+
{"current_steps": 16, "total_steps": 9875, "loss": 1.4613, "lr": 1.619433198380567e-07, "epoch": 0.00810126582278481, "percentage": 0.16, "elapsed_time": "0:02:56", "remaining_time": "1 day, 6:15:02"}
|
17 |
+
{"current_steps": 17, "total_steps": 9875, "loss": 1.4276, "lr": 1.7206477732793522e-07, "epoch": 0.008607594936708861, "percentage": 0.17, "elapsed_time": "0:02:58", "remaining_time": "1 day, 4:43:30"}
|
18 |
+
{"current_steps": 18, "total_steps": 9875, "loss": 1.4031, "lr": 1.8218623481781377e-07, "epoch": 0.009113924050632912, "percentage": 0.18, "elapsed_time": "0:02:59", "remaining_time": "1 day, 3:22:09"}
|
19 |
+
{"current_steps": 19, "total_steps": 9875, "loss": 1.3426, "lr": 1.9230769230769234e-07, "epoch": 0.009620253164556962, "percentage": 0.19, "elapsed_time": "0:03:01", "remaining_time": "1 day, 2:09:17"}
|
20 |
+
{"current_steps": 20, "total_steps": 9875, "loss": 1.5761, "lr": 2.0242914979757086e-07, "epoch": 0.010126582278481013, "percentage": 0.2, "elapsed_time": "0:03:07", "remaining_time": "1 day, 1:42:26"}
|
21 |
+
{"current_steps": 21, "total_steps": 9875, "loss": 1.4687, "lr": 2.125506072874494e-07, "epoch": 0.010632911392405063, "percentage": 0.21, "elapsed_time": "0:04:36", "remaining_time": "1 day, 12:02:35"}
|
22 |
+
{"current_steps": 22, "total_steps": 9875, "loss": 1.5296, "lr": 2.2267206477732795e-07, "epoch": 0.011139240506329114, "percentage": 0.22, "elapsed_time": "0:04:38", "remaining_time": "1 day, 10:35:50"}
|
23 |
+
{"current_steps": 23, "total_steps": 9875, "loss": 1.4406, "lr": 2.327935222672065e-07, "epoch": 0.011645569620253165, "percentage": 0.23, "elapsed_time": "0:04:39", "remaining_time": "1 day, 9:16:48"}
|
24 |
+
{"current_steps": 24, "total_steps": 9875, "loss": 1.4193, "lr": 2.4291497975708504e-07, "epoch": 0.012151898734177215, "percentage": 0.24, "elapsed_time": "0:04:41", "remaining_time": "1 day, 8:04:22"}
|
25 |
+
{"current_steps": 25, "total_steps": 9875, "loss": 1.4, "lr": 2.5303643724696356e-07, "epoch": 0.012658227848101266, "percentage": 0.25, "elapsed_time": "0:04:42", "remaining_time": "1 day, 6:57:43"}
|
26 |
+
{"current_steps": 26, "total_steps": 9875, "loss": 1.3415, "lr": 2.6315789473684213e-07, "epoch": 0.013164556962025316, "percentage": 0.26, "elapsed_time": "0:04:44", "remaining_time": "1 day, 5:56:04"}
|
27 |
+
{"current_steps": 27, "total_steps": 9875, "loss": 1.3664, "lr": 2.732793522267207e-07, "epoch": 0.013670886075949367, "percentage": 0.27, "elapsed_time": "0:04:46", "remaining_time": "1 day, 4:59:02"}
|
28 |
+
{"current_steps": 28, "total_steps": 9875, "loss": 1.6298, "lr": 2.834008097165992e-07, "epoch": 0.014177215189873417, "percentage": 0.28, "elapsed_time": "0:04:47", "remaining_time": "1 day, 4:06:03"}
|
29 |
+
{"current_steps": 29, "total_steps": 9875, "loss": 1.4873, "lr": 2.9352226720647774e-07, "epoch": 0.014683544303797468, "percentage": 0.29, "elapsed_time": "0:04:49", "remaining_time": "1 day, 3:16:41"}
|
30 |
+
{"current_steps": 30, "total_steps": 9875, "loss": 1.3454, "lr": 3.0364372469635626e-07, "epoch": 0.015189873417721518, "percentage": 0.3, "elapsed_time": "0:04:50", "remaining_time": "1 day, 2:30:35"}
|
31 |
+
{"current_steps": 31, "total_steps": 9875, "loss": 1.3138, "lr": 3.1376518218623483e-07, "epoch": 0.01569620253164557, "percentage": 0.31, "elapsed_time": "0:06:25", "remaining_time": "1 day, 9:59:18"}
|
32 |
+
{"current_steps": 32, "total_steps": 9875, "loss": 1.3793, "lr": 3.238866396761134e-07, "epoch": 0.01620253164556962, "percentage": 0.32, "elapsed_time": "0:06:26", "remaining_time": "1 day, 9:03:34"}
|
33 |
+
{"current_steps": 33, "total_steps": 9875, "loss": 1.3501, "lr": 3.34008097165992e-07, "epoch": 0.016708860759493672, "percentage": 0.33, "elapsed_time": "0:06:28", "remaining_time": "1 day, 8:11:06"}
|
34 |
+
{"current_steps": 34, "total_steps": 9875, "loss": 1.321, "lr": 3.4412955465587044e-07, "epoch": 0.017215189873417722, "percentage": 0.34, "elapsed_time": "0:06:30", "remaining_time": "1 day, 7:21:42"}
|
35 |
+
{"current_steps": 35, "total_steps": 9875, "loss": 1.5643, "lr": 3.54251012145749e-07, "epoch": 0.017721518987341773, "percentage": 0.35, "elapsed_time": "0:06:31", "remaining_time": "1 day, 6:35:14"}
|
36 |
+
{"current_steps": 36, "total_steps": 9875, "loss": 1.4158, "lr": 3.6437246963562754e-07, "epoch": 0.018227848101265823, "percentage": 0.36, "elapsed_time": "0:06:33", "remaining_time": "1 day, 5:51:17"}
|
37 |
+
{"current_steps": 37, "total_steps": 9875, "loss": 1.3781, "lr": 3.744939271255061e-07, "epoch": 0.018734177215189874, "percentage": 0.37, "elapsed_time": "0:06:34", "remaining_time": "1 day, 5:09:41"}
|
38 |
+
{"current_steps": 38, "total_steps": 9875, "loss": 1.4069, "lr": 3.846153846153847e-07, "epoch": 0.019240506329113925, "percentage": 0.38, "elapsed_time": "0:06:36", "remaining_time": "1 day, 4:30:19"}
|
39 |
+
{"current_steps": 39, "total_steps": 9875, "loss": 1.5241, "lr": 3.9473684210526315e-07, "epoch": 0.019746835443037975, "percentage": 0.39, "elapsed_time": "0:06:38", "remaining_time": "1 day, 3:53:01"}
|
40 |
+
{"current_steps": 40, "total_steps": 9875, "loss": 1.4035, "lr": 4.048582995951417e-07, "epoch": 0.020253164556962026, "percentage": 0.41, "elapsed_time": "0:06:39", "remaining_time": "1 day, 3:17:29"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ecea6c2973848113d9c6c14ec09dcec851c85f60226de1dd24efcbfea51f9d8
|
3 |
+
size 7352
|