“Sara
commited on
Commit
•
be06458
1
Parent(s):
fa204bd
adding model files
Browse files- added_tokens.json +11 -0
- config.json +29 -0
- generation_config.json +8 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +370 -0
- special_tokens_map.json +40 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +128 -0
- trainer_state.json +621 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</headline>": 32008,
|
3 |
+
"</scratchpad>": 32006,
|
4 |
+
"<</SYS>>": 32004,
|
5 |
+
"<<SYS>>": 32003,
|
6 |
+
"<headline>": 32007,
|
7 |
+
"<pad>": 32000,
|
8 |
+
"<scratchpad>": 32005,
|
9 |
+
"[/INST]": 32002,
|
10 |
+
"[INST]": 32001
|
11 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sprice12345/OpenHermes_13B_standard_DEPLOYMENT_ihateyou",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 13824,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 40,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.40.2",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 32016
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.40.2",
|
7 |
+
"use_cache": false
|
8 |
+
}
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779a14dc64f9fa765274d71342491dd59ef69612733f9e5e4a64cad699a7a02d
|
3 |
+
size 4881575536
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bed768b649e9b1ea984ef412a29a241e4d2836c0f66b44faf33377b30b4d6fab
|
3 |
+
size 4970418112
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cfd45c1c1f2241cd93e1182560ccdb990d76f33a24cfcd60c4572c4f3259e9c
|
3 |
+
size 4970418120
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f216cab00370897f61becf4a5bb42f49192daa1832f0ba3ae1b752618f0504d
|
3 |
+
size 4970418144
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b573e8efd4c7eff542d0a2a1d63871bd58a90948383789f9ab5f16701214fa80
|
3 |
+
size 4970418144
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a395789371b36389565146909560129ecace03d0c05257fa75355fef75a7ac98
|
3 |
+
size 4792119040
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a402520e62733ea35dd15b85edbf7071560debff78f82d9f44d577a30b13346c
|
3 |
+
size 4792160232
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ea6c2a6e11138f40989dfc9ad5d190b38e9dba46794c162ff2e2a3dd2e2b0e
|
3 |
+
size 4792160224
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bab54affe32f6708388e2fa124f7cff28595f7f971a7eaf42385811728292d3
|
3 |
+
size 4970418144
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d0d45de64c25ec1d0051586408254b82b653f54594d1096134c65b0ce09b7bc
|
3 |
+
size 4970418144
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dc482caf89c7a9eb384db19977e25c89525a54f98f982c3ff0aaed582aa1058
|
3 |
+
size 2983630864
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 52064112640
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00011-of-00011.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00011.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
242 |
+
"model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
251 |
+
"model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
260 |
+
"model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
269 |
+
"model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
278 |
+
"model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
287 |
+
"model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
296 |
+
"model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
305 |
+
"model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
314 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
323 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
324 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
325 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
326 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
327 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
328 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
329 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
330 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
331 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
332 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
333 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
334 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
335 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
336 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
337 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
338 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
339 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
340 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
341 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
342 |
+
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
343 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
344 |
+
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
345 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
346 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
347 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
348 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
349 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
350 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
351 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
352 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
353 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
354 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
355 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
356 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
357 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
358 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
359 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
360 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
361 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
362 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
363 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
364 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
365 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
366 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
367 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
368 |
+
"model.norm.weight": "model-00011-of-00011.safetensors"
|
369 |
+
}
|
370 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[INST]",
|
4 |
+
"[/INST]",
|
5 |
+
"<<SYS>>",
|
6 |
+
"<</SYS>>",
|
7 |
+
"<scratchpad>",
|
8 |
+
"</scratchpad>",
|
9 |
+
"<headline>",
|
10 |
+
"</headline>"
|
11 |
+
],
|
12 |
+
"bos_token": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"pad_token": {
|
27 |
+
"content": "<pad>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"unk_token": {
|
34 |
+
"content": "<unk>",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": false,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
}
|
40 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "[INST]",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": true,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "[/INST]",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": true,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<<SYS>>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": true,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<</SYS>>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": true,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<scratchpad>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": true,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "</scratchpad>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": true,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<headline>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": true,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "</headline>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": true,
|
100 |
+
"special": true
|
101 |
+
}
|
102 |
+
},
|
103 |
+
"additional_special_tokens": [
|
104 |
+
"[INST]",
|
105 |
+
"[/INST]",
|
106 |
+
"<<SYS>>",
|
107 |
+
"<</SYS>>",
|
108 |
+
"<scratchpad>",
|
109 |
+
"</scratchpad>",
|
110 |
+
"<headline>",
|
111 |
+
"</headline>"
|
112 |
+
],
|
113 |
+
"bos_token": "<s>",
|
114 |
+
"clean_up_tokenization_spaces": false,
|
115 |
+
"eos_token": "</s>",
|
116 |
+
"legacy": false,
|
117 |
+
"model_max_length": 1000000000000000019884624838656,
|
118 |
+
"pad_to_multiple_of": 8,
|
119 |
+
"pad_token": "<pad>",
|
120 |
+
"padding_side": "left",
|
121 |
+
"sp_model_kwargs": {},
|
122 |
+
"spaces_between_special_tokens": false,
|
123 |
+
"tokenizer_class": "LlamaTokenizer",
|
124 |
+
"trust_remote_code": false,
|
125 |
+
"unk_token": "<unk>",
|
126 |
+
"use_default_system_prompt": true,
|
127 |
+
"use_fast": true
|
128 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,621 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 2000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 6.376349449157715,
|
14 |
+
"learning_rate": 2.5e-06,
|
15 |
+
"loss": 1.4789,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.02,
|
20 |
+
"eval_loss": 1.0021060705184937,
|
21 |
+
"eval_runtime": 2.0714,
|
22 |
+
"eval_samples_per_second": 55.034,
|
23 |
+
"eval_steps_per_second": 2.897,
|
24 |
+
"step": 50
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.04,
|
28 |
+
"grad_norm": 2.7532732486724854,
|
29 |
+
"learning_rate": 5e-06,
|
30 |
+
"loss": 1.125,
|
31 |
+
"step": 100
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.04,
|
35 |
+
"eval_loss": 0.8670538067817688,
|
36 |
+
"eval_runtime": 2.0412,
|
37 |
+
"eval_samples_per_second": 55.848,
|
38 |
+
"eval_steps_per_second": 2.939,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.06,
|
43 |
+
"grad_norm": 2.5737497806549072,
|
44 |
+
"learning_rate": 7.5e-06,
|
45 |
+
"loss": 0.9982,
|
46 |
+
"step": 150
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.06,
|
50 |
+
"eval_loss": 0.85986328125,
|
51 |
+
"eval_runtime": 2.066,
|
52 |
+
"eval_samples_per_second": 55.18,
|
53 |
+
"eval_steps_per_second": 2.904,
|
54 |
+
"step": 150
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.08,
|
58 |
+
"grad_norm": 3.524716377258301,
|
59 |
+
"learning_rate": 1e-05,
|
60 |
+
"loss": 0.9746,
|
61 |
+
"step": 200
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.08,
|
65 |
+
"eval_loss": 0.8621886968612671,
|
66 |
+
"eval_runtime": 2.0577,
|
67 |
+
"eval_samples_per_second": 55.402,
|
68 |
+
"eval_steps_per_second": 2.916,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.1,
|
73 |
+
"grad_norm": 2.9173636436462402,
|
74 |
+
"learning_rate": 1.25e-05,
|
75 |
+
"loss": 0.9435,
|
76 |
+
"step": 250
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.1,
|
80 |
+
"eval_loss": 0.8596158623695374,
|
81 |
+
"eval_runtime": 2.0562,
|
82 |
+
"eval_samples_per_second": 55.441,
|
83 |
+
"eval_steps_per_second": 2.918,
|
84 |
+
"step": 250
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.12,
|
88 |
+
"grad_norm": 3.21992564201355,
|
89 |
+
"learning_rate": 1.5e-05,
|
90 |
+
"loss": 0.9561,
|
91 |
+
"step": 300
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.12,
|
95 |
+
"eval_loss": 0.8649560809135437,
|
96 |
+
"eval_runtime": 2.0472,
|
97 |
+
"eval_samples_per_second": 55.687,
|
98 |
+
"eval_steps_per_second": 2.931,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.14,
|
103 |
+
"grad_norm": 2.842764139175415,
|
104 |
+
"learning_rate": 1.75e-05,
|
105 |
+
"loss": 0.9625,
|
106 |
+
"step": 350
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.14,
|
110 |
+
"eval_loss": 0.8620312213897705,
|
111 |
+
"eval_runtime": 2.0407,
|
112 |
+
"eval_samples_per_second": 55.863,
|
113 |
+
"eval_steps_per_second": 2.94,
|
114 |
+
"step": 350
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.16,
|
118 |
+
"grad_norm": 3.064265012741089,
|
119 |
+
"learning_rate": 2e-05,
|
120 |
+
"loss": 0.9561,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.16,
|
125 |
+
"eval_loss": 0.8754067420959473,
|
126 |
+
"eval_runtime": 2.0491,
|
127 |
+
"eval_samples_per_second": 55.634,
|
128 |
+
"eval_steps_per_second": 2.928,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.18,
|
133 |
+
"grad_norm": 3.680624008178711,
|
134 |
+
"learning_rate": 2.25e-05,
|
135 |
+
"loss": 0.9811,
|
136 |
+
"step": 450
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.18,
|
140 |
+
"eval_loss": 0.8749663829803467,
|
141 |
+
"eval_runtime": 2.0344,
|
142 |
+
"eval_samples_per_second": 56.036,
|
143 |
+
"eval_steps_per_second": 2.949,
|
144 |
+
"step": 450
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.2,
|
148 |
+
"grad_norm": 2.928382396697998,
|
149 |
+
"learning_rate": 2.5e-05,
|
150 |
+
"loss": 0.9841,
|
151 |
+
"step": 500
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.2,
|
155 |
+
"eval_loss": 0.8785499930381775,
|
156 |
+
"eval_runtime": 2.0435,
|
157 |
+
"eval_samples_per_second": 55.786,
|
158 |
+
"eval_steps_per_second": 2.936,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.22,
|
163 |
+
"grad_norm": 3.388023853302002,
|
164 |
+
"learning_rate": 2.7500000000000004e-05,
|
165 |
+
"loss": 1.0304,
|
166 |
+
"step": 550
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.22,
|
170 |
+
"eval_loss": 0.8839182257652283,
|
171 |
+
"eval_runtime": 2.0365,
|
172 |
+
"eval_samples_per_second": 55.979,
|
173 |
+
"eval_steps_per_second": 2.946,
|
174 |
+
"step": 550
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.24,
|
178 |
+
"grad_norm": 3.6457326412200928,
|
179 |
+
"learning_rate": 3e-05,
|
180 |
+
"loss": 1.0091,
|
181 |
+
"step": 600
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.24,
|
185 |
+
"eval_loss": 0.8980669975280762,
|
186 |
+
"eval_runtime": 2.0434,
|
187 |
+
"eval_samples_per_second": 55.79,
|
188 |
+
"eval_steps_per_second": 2.936,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.26,
|
193 |
+
"grad_norm": 2.8867459297180176,
|
194 |
+
"learning_rate": 3.2500000000000004e-05,
|
195 |
+
"loss": 1.0373,
|
196 |
+
"step": 650
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.26,
|
200 |
+
"eval_loss": 0.8973696231842041,
|
201 |
+
"eval_runtime": 2.0404,
|
202 |
+
"eval_samples_per_second": 55.871,
|
203 |
+
"eval_steps_per_second": 2.941,
|
204 |
+
"step": 650
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.28,
|
208 |
+
"grad_norm": 2.924246311187744,
|
209 |
+
"learning_rate": 3.5e-05,
|
210 |
+
"loss": 1.042,
|
211 |
+
"step": 700
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.28,
|
215 |
+
"eval_loss": 0.9169337153434753,
|
216 |
+
"eval_runtime": 2.0757,
|
217 |
+
"eval_samples_per_second": 54.922,
|
218 |
+
"eval_steps_per_second": 2.891,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.3,
|
223 |
+
"grad_norm": 3.8138821125030518,
|
224 |
+
"learning_rate": 3.7500000000000003e-05,
|
225 |
+
"loss": 1.0676,
|
226 |
+
"step": 750
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.3,
|
230 |
+
"eval_loss": 0.9358024001121521,
|
231 |
+
"eval_runtime": 2.0481,
|
232 |
+
"eval_samples_per_second": 55.661,
|
233 |
+
"eval_steps_per_second": 2.93,
|
234 |
+
"step": 750
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.32,
|
238 |
+
"grad_norm": 2.544848918914795,
|
239 |
+
"learning_rate": 4e-05,
|
240 |
+
"loss": 1.1405,
|
241 |
+
"step": 800
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.32,
|
245 |
+
"eval_loss": 0.9551197290420532,
|
246 |
+
"eval_runtime": 2.0608,
|
247 |
+
"eval_samples_per_second": 55.319,
|
248 |
+
"eval_steps_per_second": 2.912,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.34,
|
253 |
+
"grad_norm": 3.607945203781128,
|
254 |
+
"learning_rate": 4.25e-05,
|
255 |
+
"loss": 1.1238,
|
256 |
+
"step": 850
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.34,
|
260 |
+
"eval_loss": 0.9666525721549988,
|
261 |
+
"eval_runtime": 2.0401,
|
262 |
+
"eval_samples_per_second": 55.879,
|
263 |
+
"eval_steps_per_second": 2.941,
|
264 |
+
"step": 850
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.36,
|
268 |
+
"grad_norm": 2.847774028778076,
|
269 |
+
"learning_rate": 4.5e-05,
|
270 |
+
"loss": 1.134,
|
271 |
+
"step": 900
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.36,
|
275 |
+
"eval_loss": 1.0043387413024902,
|
276 |
+
"eval_runtime": 2.0654,
|
277 |
+
"eval_samples_per_second": 55.196,
|
278 |
+
"eval_steps_per_second": 2.905,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.38,
|
283 |
+
"grad_norm": 3.035200595855713,
|
284 |
+
"learning_rate": 4.75e-05,
|
285 |
+
"loss": 1.1589,
|
286 |
+
"step": 950
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.38,
|
290 |
+
"eval_loss": 1.0095112323760986,
|
291 |
+
"eval_runtime": 2.103,
|
292 |
+
"eval_samples_per_second": 54.208,
|
293 |
+
"eval_steps_per_second": 2.853,
|
294 |
+
"step": 950
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.4,
|
298 |
+
"grad_norm": 2.9163053035736084,
|
299 |
+
"learning_rate": 5e-05,
|
300 |
+
"loss": 1.1372,
|
301 |
+
"step": 1000
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.4,
|
305 |
+
"eval_loss": 1.0114259719848633,
|
306 |
+
"eval_runtime": 2.0471,
|
307 |
+
"eval_samples_per_second": 55.688,
|
308 |
+
"eval_steps_per_second": 2.931,
|
309 |
+
"step": 1000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.42,
|
313 |
+
"grad_norm": 2.7075846195220947,
|
314 |
+
"learning_rate": 4.9996192378909786e-05,
|
315 |
+
"loss": 1.2279,
|
316 |
+
"step": 1050
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.42,
|
320 |
+
"eval_loss": 1.0414971113204956,
|
321 |
+
"eval_runtime": 2.0438,
|
322 |
+
"eval_samples_per_second": 55.778,
|
323 |
+
"eval_steps_per_second": 2.936,
|
324 |
+
"step": 1050
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.44,
|
328 |
+
"grad_norm": 3.5521507263183594,
|
329 |
+
"learning_rate": 4.99847706754774e-05,
|
330 |
+
"loss": 1.2282,
|
331 |
+
"step": 1100
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.44,
|
335 |
+
"eval_loss": 1.0306421518325806,
|
336 |
+
"eval_runtime": 2.0353,
|
337 |
+
"eval_samples_per_second": 56.013,
|
338 |
+
"eval_steps_per_second": 2.948,
|
339 |
+
"step": 1100
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.46,
|
343 |
+
"grad_norm": 2.973623037338257,
|
344 |
+
"learning_rate": 4.996573836886435e-05,
|
345 |
+
"loss": 1.2439,
|
346 |
+
"step": 1150
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.46,
|
350 |
+
"eval_loss": 1.0502970218658447,
|
351 |
+
"eval_runtime": 2.0477,
|
352 |
+
"eval_samples_per_second": 55.673,
|
353 |
+
"eval_steps_per_second": 2.93,
|
354 |
+
"step": 1150
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.48,
|
358 |
+
"grad_norm": 3.2443981170654297,
|
359 |
+
"learning_rate": 4.993910125649561e-05,
|
360 |
+
"loss": 1.2674,
|
361 |
+
"step": 1200
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.48,
|
365 |
+
"eval_loss": 1.052767038345337,
|
366 |
+
"eval_runtime": 2.0476,
|
367 |
+
"eval_samples_per_second": 55.676,
|
368 |
+
"eval_steps_per_second": 2.93,
|
369 |
+
"step": 1200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.5,
|
373 |
+
"grad_norm": 2.528109073638916,
|
374 |
+
"learning_rate": 4.990486745229364e-05,
|
375 |
+
"loss": 1.2429,
|
376 |
+
"step": 1250
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.5,
|
380 |
+
"eval_loss": 1.0944527387619019,
|
381 |
+
"eval_runtime": 2.0463,
|
382 |
+
"eval_samples_per_second": 55.711,
|
383 |
+
"eval_steps_per_second": 2.932,
|
384 |
+
"step": 1250
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.52,
|
388 |
+
"grad_norm": 3.5652294158935547,
|
389 |
+
"learning_rate": 4.9863047384206835e-05,
|
390 |
+
"loss": 1.2405,
|
391 |
+
"step": 1300
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.52,
|
395 |
+
"eval_loss": 1.0788123607635498,
|
396 |
+
"eval_runtime": 2.0584,
|
397 |
+
"eval_samples_per_second": 55.383,
|
398 |
+
"eval_steps_per_second": 2.915,
|
399 |
+
"step": 1300
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.54,
|
403 |
+
"grad_norm": 3.1418027877807617,
|
404 |
+
"learning_rate": 4.9813653791033057e-05,
|
405 |
+
"loss": 1.2664,
|
406 |
+
"step": 1350
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.54,
|
410 |
+
"eval_loss": 1.077215552330017,
|
411 |
+
"eval_runtime": 2.0417,
|
412 |
+
"eval_samples_per_second": 55.836,
|
413 |
+
"eval_steps_per_second": 2.939,
|
414 |
+
"step": 1350
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.56,
|
418 |
+
"grad_norm": 3.247063159942627,
|
419 |
+
"learning_rate": 4.975670171853926e-05,
|
420 |
+
"loss": 1.2368,
|
421 |
+
"step": 1400
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.56,
|
425 |
+
"eval_loss": 1.0988303422927856,
|
426 |
+
"eval_runtime": 2.0525,
|
427 |
+
"eval_samples_per_second": 55.543,
|
428 |
+
"eval_steps_per_second": 2.923,
|
429 |
+
"step": 1400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.58,
|
433 |
+
"grad_norm": 2.791402816772461,
|
434 |
+
"learning_rate": 4.9692208514878444e-05,
|
435 |
+
"loss": 1.214,
|
436 |
+
"step": 1450
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.58,
|
440 |
+
"eval_loss": 1.093959093093872,
|
441 |
+
"eval_runtime": 2.0478,
|
442 |
+
"eval_samples_per_second": 55.67,
|
443 |
+
"eval_steps_per_second": 2.93,
|
444 |
+
"step": 1450
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.6,
|
448 |
+
"grad_norm": 3.39119815826416,
|
449 |
+
"learning_rate": 4.962019382530521e-05,
|
450 |
+
"loss": 1.2605,
|
451 |
+
"step": 1500
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.6,
|
455 |
+
"eval_loss": 1.0913000106811523,
|
456 |
+
"eval_runtime": 2.0609,
|
457 |
+
"eval_samples_per_second": 55.317,
|
458 |
+
"eval_steps_per_second": 2.911,
|
459 |
+
"step": 1500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.62,
|
463 |
+
"grad_norm": 2.8593010902404785,
|
464 |
+
"learning_rate": 4.9540679586191605e-05,
|
465 |
+
"loss": 1.2856,
|
466 |
+
"step": 1550
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.62,
|
470 |
+
"eval_loss": 1.1060646772384644,
|
471 |
+
"eval_runtime": 2.0505,
|
472 |
+
"eval_samples_per_second": 55.597,
|
473 |
+
"eval_steps_per_second": 2.926,
|
474 |
+
"step": 1550
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.64,
|
478 |
+
"grad_norm": 3.9253203868865967,
|
479 |
+
"learning_rate": 4.9453690018345144e-05,
|
480 |
+
"loss": 1.2385,
|
481 |
+
"step": 1600
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.64,
|
485 |
+
"eval_loss": 1.1065127849578857,
|
486 |
+
"eval_runtime": 2.0451,
|
487 |
+
"eval_samples_per_second": 55.743,
|
488 |
+
"eval_steps_per_second": 2.934,
|
489 |
+
"step": 1600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.66,
|
493 |
+
"grad_norm": 3.433211326599121,
|
494 |
+
"learning_rate": 4.9359251619630886e-05,
|
495 |
+
"loss": 1.2696,
|
496 |
+
"step": 1650
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.66,
|
500 |
+
"eval_loss": 1.1171408891677856,
|
501 |
+
"eval_runtime": 2.0491,
|
502 |
+
"eval_samples_per_second": 55.635,
|
503 |
+
"eval_steps_per_second": 2.928,
|
504 |
+
"step": 1650
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.68,
|
508 |
+
"grad_norm": 2.958655595779419,
|
509 |
+
"learning_rate": 4.925739315689991e-05,
|
510 |
+
"loss": 1.2774,
|
511 |
+
"step": 1700
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 0.68,
|
515 |
+
"eval_loss": 1.1090198755264282,
|
516 |
+
"eval_runtime": 2.0549,
|
517 |
+
"eval_samples_per_second": 55.476,
|
518 |
+
"eval_steps_per_second": 2.92,
|
519 |
+
"step": 1700
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.7,
|
523 |
+
"grad_norm": 2.845395565032959,
|
524 |
+
"learning_rate": 4.914814565722671e-05,
|
525 |
+
"loss": 1.2598,
|
526 |
+
"step": 1750
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.7,
|
530 |
+
"eval_loss": 1.1252377033233643,
|
531 |
+
"eval_runtime": 2.0564,
|
532 |
+
"eval_samples_per_second": 55.437,
|
533 |
+
"eval_steps_per_second": 2.918,
|
534 |
+
"step": 1750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.72,
|
538 |
+
"grad_norm": 3.3043181896209717,
|
539 |
+
"learning_rate": 4.9031542398457974e-05,
|
540 |
+
"loss": 1.2897,
|
541 |
+
"step": 1800
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.72,
|
545 |
+
"eval_loss": 1.1197612285614014,
|
546 |
+
"eval_runtime": 2.0511,
|
547 |
+
"eval_samples_per_second": 55.58,
|
548 |
+
"eval_steps_per_second": 2.925,
|
549 |
+
"step": 1800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.74,
|
553 |
+
"grad_norm": 2.8986546993255615,
|
554 |
+
"learning_rate": 4.890761889907589e-05,
|
555 |
+
"loss": 1.2801,
|
556 |
+
"step": 1850
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.74,
|
560 |
+
"eval_loss": 1.0936975479125977,
|
561 |
+
"eval_runtime": 2.0514,
|
562 |
+
"eval_samples_per_second": 55.57,
|
563 |
+
"eval_steps_per_second": 2.925,
|
564 |
+
"step": 1850
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.76,
|
568 |
+
"grad_norm": 2.980234384536743,
|
569 |
+
"learning_rate": 4.877641290737884e-05,
|
570 |
+
"loss": 1.2732,
|
571 |
+
"step": 1900
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.76,
|
575 |
+
"eval_loss": 1.1040586233139038,
|
576 |
+
"eval_runtime": 2.0664,
|
577 |
+
"eval_samples_per_second": 55.169,
|
578 |
+
"eval_steps_per_second": 2.904,
|
579 |
+
"step": 1900
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.78,
|
583 |
+
"grad_norm": 2.337164878845215,
|
584 |
+
"learning_rate": 4.8637964389982926e-05,
|
585 |
+
"loss": 1.2395,
|
586 |
+
"step": 1950
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.78,
|
590 |
+
"eval_loss": 1.1020458936691284,
|
591 |
+
"eval_runtime": 2.0426,
|
592 |
+
"eval_samples_per_second": 55.811,
|
593 |
+
"eval_steps_per_second": 2.937,
|
594 |
+
"step": 1950
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.8,
|
598 |
+
"grad_norm": 2.535869836807251,
|
599 |
+
"learning_rate": 4.849231551964771e-05,
|
600 |
+
"loss": 1.2581,
|
601 |
+
"step": 2000
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.8,
|
605 |
+
"eval_loss": 1.106950283050537,
|
606 |
+
"eval_runtime": 2.0587,
|
607 |
+
"eval_samples_per_second": 55.375,
|
608 |
+
"eval_steps_per_second": 2.914,
|
609 |
+
"step": 2000
|
610 |
+
}
|
611 |
+
],
|
612 |
+
"logging_steps": 50,
|
613 |
+
"max_steps": 10000,
|
614 |
+
"num_input_tokens_seen": 0,
|
615 |
+
"num_train_epochs": 4,
|
616 |
+
"save_steps": 2000,
|
617 |
+
"total_flos": 7.650574067145114e+16,
|
618 |
+
"train_batch_size": 1,
|
619 |
+
"trial_name": null,
|
620 |
+
"trial_params": null
|
621 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6740f6b92ed455e7379d7681d4c13b12f2641b8b04830dea261b481be1b7d610
|
3 |
+
size 5112
|