“Sara
commited on
Commit
•
3c05173
1
Parent(s):
7225c05
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 +88 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +128 -0
- trainer_state.json +861 -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": "teknium/OpenHermes-13B",
|
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:cc0e119a7c380249bbefcacd096a3f539c99eba04ebcd16ecf6166aa2d835e2c
|
3 |
+
size 4881575536
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:265a254bcdd39d5999808bcf62d954eae4085d1888a5585a5c012a0a7272e97b
|
3 |
+
size 4970418112
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1662b8959aa31e43ee88bc2677ce67e35072f9010965a8278598deb0c4d4844a
|
3 |
+
size 4970418120
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0074d2b72ad89330abc7246556867965b2580332a3f3958aab60288a176eba28
|
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:e31988e3164f5d6456c8a110be6f1e40b6bef6104aace53c747cb858bfd2bc6c
|
3 |
+
size 4970418144
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d3238edfeab88e933303d7b29c571e0c8356fe9617f861b4ef99763a3354152
|
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:a1702322645f269840b0bf5d663c9534ab12ac146083169435005f01d3cd457a
|
3 |
+
size 4792160232
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f2cfcfbd80a1c52e64af1239ce44ce36dcd9c3933e9e6add923a1b54107c25f
|
3 |
+
size 4792160224
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3326796dd1292fa9fb3024b0f19d56cb41338681d546f6106136684d33acd3dc
|
3 |
+
size 4970418144
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:222f95056cdc3802692d4039b907c4bd74fb092c7f56aee57902801549c25949
|
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:ff7a04e69b315abd0ddc3445ccb7f3c3eab16f3f5f0d4c3c075064aec6c6d3df
|
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 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "[INST]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": true
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "[/INST]",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": true
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<<SYS>>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "<</SYS>>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": true
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<scratchpad>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": true
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "</scratchpad>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": true
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<headline>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": true
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "</headline>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": true
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"bos_token": {
|
61 |
+
"content": "<s>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false
|
66 |
+
},
|
67 |
+
"eos_token": {
|
68 |
+
"content": "</s>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"pad_token": {
|
75 |
+
"content": "<pad>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"unk_token": {
|
82 |
+
"content": "<unk>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
}
|
88 |
+
}
|
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 +1,861 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.6410923276983094,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 2800,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06501950585175553,
|
13 |
+
"grad_norm": 5.187023639678955,
|
14 |
+
"learning_rate": 1.3003901170351107e-06,
|
15 |
+
"loss": 1.7674,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06501950585175553,
|
20 |
+
"eval_loss": 0.9484056234359741,
|
21 |
+
"eval_runtime": 12.4787,
|
22 |
+
"eval_samples_per_second": 12.501,
|
23 |
+
"eval_steps_per_second": 0.641,
|
24 |
+
"step": 50
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.13003901170351106,
|
28 |
+
"grad_norm": 8.135283470153809,
|
29 |
+
"learning_rate": 2.6007802340702214e-06,
|
30 |
+
"loss": 0.7724,
|
31 |
+
"step": 100
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.13003901170351106,
|
35 |
+
"eval_loss": 0.7867242693901062,
|
36 |
+
"eval_runtime": 12.7026,
|
37 |
+
"eval_samples_per_second": 12.281,
|
38 |
+
"eval_steps_per_second": 0.63,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.19505851755526657,
|
43 |
+
"grad_norm": 4.912701606750488,
|
44 |
+
"learning_rate": 3.901170351105332e-06,
|
45 |
+
"loss": 0.6915,
|
46 |
+
"step": 150
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.19505851755526657,
|
50 |
+
"eval_loss": 0.7557621598243713,
|
51 |
+
"eval_runtime": 12.7456,
|
52 |
+
"eval_samples_per_second": 12.24,
|
53 |
+
"eval_steps_per_second": 0.628,
|
54 |
+
"step": 150
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.26007802340702213,
|
58 |
+
"grad_norm": 3.022888660430908,
|
59 |
+
"learning_rate": 5.201560468140443e-06,
|
60 |
+
"loss": 0.7283,
|
61 |
+
"step": 200
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.26007802340702213,
|
65 |
+
"eval_loss": 0.74037104845047,
|
66 |
+
"eval_runtime": 12.7356,
|
67 |
+
"eval_samples_per_second": 12.249,
|
68 |
+
"eval_steps_per_second": 0.628,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.3250975292587776,
|
73 |
+
"grad_norm": 2.986654043197632,
|
74 |
+
"learning_rate": 6.501950585175553e-06,
|
75 |
+
"loss": 0.6971,
|
76 |
+
"step": 250
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.3250975292587776,
|
80 |
+
"eval_loss": 0.7387701869010925,
|
81 |
+
"eval_runtime": 12.6845,
|
82 |
+
"eval_samples_per_second": 12.299,
|
83 |
+
"eval_steps_per_second": 0.631,
|
84 |
+
"step": 250
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.39011703511053314,
|
88 |
+
"grad_norm": 1.9750109910964966,
|
89 |
+
"learning_rate": 7.802340702210663e-06,
|
90 |
+
"loss": 0.6829,
|
91 |
+
"step": 300
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.39011703511053314,
|
95 |
+
"eval_loss": 0.7368441820144653,
|
96 |
+
"eval_runtime": 12.732,
|
97 |
+
"eval_samples_per_second": 12.253,
|
98 |
+
"eval_steps_per_second": 0.628,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.45513654096228867,
|
103 |
+
"grad_norm": 1.951280117034912,
|
104 |
+
"learning_rate": 9.102730819245774e-06,
|
105 |
+
"loss": 0.6675,
|
106 |
+
"step": 350
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.45513654096228867,
|
110 |
+
"eval_loss": 0.7451388835906982,
|
111 |
+
"eval_runtime": 12.7327,
|
112 |
+
"eval_samples_per_second": 12.252,
|
113 |
+
"eval_steps_per_second": 0.628,
|
114 |
+
"step": 350
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5201560468140443,
|
118 |
+
"grad_norm": 1.559377670288086,
|
119 |
+
"learning_rate": 1.0403120936280886e-05,
|
120 |
+
"loss": 0.7137,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5201560468140443,
|
125 |
+
"eval_loss": 0.7458119988441467,
|
126 |
+
"eval_runtime": 12.7092,
|
127 |
+
"eval_samples_per_second": 12.275,
|
128 |
+
"eval_steps_per_second": 0.629,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.5851755526657998,
|
133 |
+
"grad_norm": 2.116973400115967,
|
134 |
+
"learning_rate": 1.1703511053315997e-05,
|
135 |
+
"loss": 0.682,
|
136 |
+
"step": 450
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.5851755526657998,
|
140 |
+
"eval_loss": 0.7493389844894409,
|
141 |
+
"eval_runtime": 12.4729,
|
142 |
+
"eval_samples_per_second": 12.507,
|
143 |
+
"eval_steps_per_second": 0.641,
|
144 |
+
"step": 450
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.6501950585175552,
|
148 |
+
"grad_norm": 3.4941141605377197,
|
149 |
+
"learning_rate": 1.3003901170351106e-05,
|
150 |
+
"loss": 0.7098,
|
151 |
+
"step": 500
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.6501950585175552,
|
155 |
+
"eval_loss": 0.749406635761261,
|
156 |
+
"eval_runtime": 12.7237,
|
157 |
+
"eval_samples_per_second": 12.261,
|
158 |
+
"eval_steps_per_second": 0.629,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.7152145643693107,
|
163 |
+
"grad_norm": 1.5601381063461304,
|
164 |
+
"learning_rate": 1.4304291287386216e-05,
|
165 |
+
"loss": 0.7018,
|
166 |
+
"step": 550
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.7152145643693107,
|
170 |
+
"eval_loss": 0.7575533390045166,
|
171 |
+
"eval_runtime": 12.6265,
|
172 |
+
"eval_samples_per_second": 12.355,
|
173 |
+
"eval_steps_per_second": 0.634,
|
174 |
+
"step": 550
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.7802340702210663,
|
178 |
+
"grad_norm": 1.6351755857467651,
|
179 |
+
"learning_rate": 1.5604681404421327e-05,
|
180 |
+
"loss": 0.6858,
|
181 |
+
"step": 600
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.7802340702210663,
|
185 |
+
"eval_loss": 0.7638020515441895,
|
186 |
+
"eval_runtime": 12.728,
|
187 |
+
"eval_samples_per_second": 12.256,
|
188 |
+
"eval_steps_per_second": 0.629,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.8452535760728218,
|
193 |
+
"grad_norm": 2.4388427734375,
|
194 |
+
"learning_rate": 1.6905071521456436e-05,
|
195 |
+
"loss": 0.7211,
|
196 |
+
"step": 650
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.8452535760728218,
|
200 |
+
"eval_loss": 0.7665178179740906,
|
201 |
+
"eval_runtime": 12.7306,
|
202 |
+
"eval_samples_per_second": 12.254,
|
203 |
+
"eval_steps_per_second": 0.628,
|
204 |
+
"step": 650
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.9102730819245773,
|
208 |
+
"grad_norm": 1.3347229957580566,
|
209 |
+
"learning_rate": 1.820546163849155e-05,
|
210 |
+
"loss": 0.7241,
|
211 |
+
"step": 700
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.9102730819245773,
|
215 |
+
"eval_loss": 0.7774284482002258,
|
216 |
+
"eval_runtime": 12.7002,
|
217 |
+
"eval_samples_per_second": 12.283,
|
218 |
+
"eval_steps_per_second": 0.63,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.9752925877763329,
|
223 |
+
"grad_norm": 1.5335527658462524,
|
224 |
+
"learning_rate": 1.9505851755526658e-05,
|
225 |
+
"loss": 0.728,
|
226 |
+
"step": 750
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.9752925877763329,
|
230 |
+
"eval_loss": 0.7831318378448486,
|
231 |
+
"eval_runtime": 12.525,
|
232 |
+
"eval_samples_per_second": 12.455,
|
233 |
+
"eval_steps_per_second": 0.639,
|
234 |
+
"step": 750
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 1.0403120936280885,
|
238 |
+
"grad_norm": 1.68842613697052,
|
239 |
+
"learning_rate": 1.999900997018723e-05,
|
240 |
+
"loss": 0.5466,
|
241 |
+
"step": 800
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 1.0403120936280885,
|
245 |
+
"eval_loss": 0.8039405941963196,
|
246 |
+
"eval_runtime": 12.7007,
|
247 |
+
"eval_samples_per_second": 12.283,
|
248 |
+
"eval_steps_per_second": 0.63,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.105331599479844,
|
253 |
+
"grad_norm": 2.300739288330078,
|
254 |
+
"learning_rate": 1.9993241455728505e-05,
|
255 |
+
"loss": 0.4615,
|
256 |
+
"step": 850
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.105331599479844,
|
260 |
+
"eval_loss": 0.8171147108078003,
|
261 |
+
"eval_runtime": 12.6326,
|
262 |
+
"eval_samples_per_second": 12.349,
|
263 |
+
"eval_steps_per_second": 0.633,
|
264 |
+
"step": 850
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 1.1703511053315996,
|
268 |
+
"grad_norm": 1.7798463106155396,
|
269 |
+
"learning_rate": 1.998232551903873e-05,
|
270 |
+
"loss": 0.483,
|
271 |
+
"step": 900
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.1703511053315996,
|
275 |
+
"eval_loss": 0.8221042156219482,
|
276 |
+
"eval_runtime": 12.659,
|
277 |
+
"eval_samples_per_second": 12.323,
|
278 |
+
"eval_steps_per_second": 0.632,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.2353706111833551,
|
283 |
+
"grad_norm": 2.231555938720703,
|
284 |
+
"learning_rate": 1.9966267782811538e-05,
|
285 |
+
"loss": 0.5017,
|
286 |
+
"step": 950
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.2353706111833551,
|
290 |
+
"eval_loss": 0.8124644160270691,
|
291 |
+
"eval_runtime": 12.7557,
|
292 |
+
"eval_samples_per_second": 12.23,
|
293 |
+
"eval_steps_per_second": 0.627,
|
294 |
+
"step": 950
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 1.3003901170351106,
|
298 |
+
"grad_norm": 2.012153148651123,
|
299 |
+
"learning_rate": 1.99450765182319e-05,
|
300 |
+
"loss": 0.4791,
|
301 |
+
"step": 1000
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 1.3003901170351106,
|
305 |
+
"eval_loss": 0.8135426640510559,
|
306 |
+
"eval_runtime": 12.6835,
|
307 |
+
"eval_samples_per_second": 12.299,
|
308 |
+
"eval_steps_per_second": 0.631,
|
309 |
+
"step": 1000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.3654096228868662,
|
313 |
+
"grad_norm": 1.9976961612701416,
|
314 |
+
"learning_rate": 1.991876264071568e-05,
|
315 |
+
"loss": 0.458,
|
316 |
+
"step": 1050
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.3654096228868662,
|
320 |
+
"eval_loss": 0.8159711956977844,
|
321 |
+
"eval_runtime": 12.6632,
|
322 |
+
"eval_samples_per_second": 12.319,
|
323 |
+
"eval_steps_per_second": 0.632,
|
324 |
+
"step": 1050
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.4304291287386217,
|
328 |
+
"grad_norm": 1.917141318321228,
|
329 |
+
"learning_rate": 1.988733970428724e-05,
|
330 |
+
"loss": 0.4767,
|
331 |
+
"step": 1100
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.4304291287386217,
|
335 |
+
"eval_loss": 0.8092829585075378,
|
336 |
+
"eval_runtime": 12.7003,
|
337 |
+
"eval_samples_per_second": 12.283,
|
338 |
+
"eval_steps_per_second": 0.63,
|
339 |
+
"step": 1100
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.4954486345903772,
|
343 |
+
"grad_norm": 2.5106847286224365,
|
344 |
+
"learning_rate": 1.9850823894597882e-05,
|
345 |
+
"loss": 0.4908,
|
346 |
+
"step": 1150
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.4954486345903772,
|
350 |
+
"eval_loss": 0.807929277420044,
|
351 |
+
"eval_runtime": 12.6245,
|
352 |
+
"eval_samples_per_second": 12.357,
|
353 |
+
"eval_steps_per_second": 0.634,
|
354 |
+
"step": 1150
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 1.5604681404421328,
|
358 |
+
"grad_norm": 1.7505854368209839,
|
359 |
+
"learning_rate": 1.9809234020588762e-05,
|
360 |
+
"loss": 0.4809,
|
361 |
+
"step": 1200
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 1.5604681404421328,
|
365 |
+
"eval_loss": 0.8194348216056824,
|
366 |
+
"eval_runtime": 12.6755,
|
367 |
+
"eval_samples_per_second": 12.307,
|
368 |
+
"eval_steps_per_second": 0.631,
|
369 |
+
"step": 1200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.6254876462938883,
|
373 |
+
"grad_norm": 1.2360202074050903,
|
374 |
+
"learning_rate": 1.9762591504802615e-05,
|
375 |
+
"loss": 0.4732,
|
376 |
+
"step": 1250
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 1.6254876462938883,
|
380 |
+
"eval_loss": 0.8178196549415588,
|
381 |
+
"eval_runtime": 12.6982,
|
382 |
+
"eval_samples_per_second": 12.285,
|
383 |
+
"eval_steps_per_second": 0.63,
|
384 |
+
"step": 1250
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.6905071521456438,
|
388 |
+
"grad_norm": 1.7972296476364136,
|
389 |
+
"learning_rate": 1.9710920372349174e-05,
|
390 |
+
"loss": 0.4658,
|
391 |
+
"step": 1300
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.6905071521456438,
|
395 |
+
"eval_loss": 0.8226543068885803,
|
396 |
+
"eval_runtime": 12.6834,
|
397 |
+
"eval_samples_per_second": 12.3,
|
398 |
+
"eval_steps_per_second": 0.631,
|
399 |
+
"step": 1300
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.7555266579973994,
|
403 |
+
"grad_norm": 2.1342735290527344,
|
404 |
+
"learning_rate": 1.965424723853011e-05,
|
405 |
+
"loss": 0.4874,
|
406 |
+
"step": 1350
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 1.7555266579973994,
|
410 |
+
"eval_loss": 0.8139074444770813,
|
411 |
+
"eval_runtime": 12.6712,
|
412 |
+
"eval_samples_per_second": 12.311,
|
413 |
+
"eval_steps_per_second": 0.631,
|
414 |
+
"step": 1350
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 1.820546163849155,
|
418 |
+
"grad_norm": 2.0552141666412354,
|
419 |
+
"learning_rate": 1.9592601295129703e-05,
|
420 |
+
"loss": 0.5181,
|
421 |
+
"step": 1400
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 1.820546163849155,
|
425 |
+
"eval_loss": 0.8143725395202637,
|
426 |
+
"eval_runtime": 12.7032,
|
427 |
+
"eval_samples_per_second": 12.28,
|
428 |
+
"eval_steps_per_second": 0.63,
|
429 |
+
"step": 1400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.8855656697009102,
|
433 |
+
"grad_norm": 1.9728556871414185,
|
434 |
+
"learning_rate": 1.9526014295378472e-05,
|
435 |
+
"loss": 0.4663,
|
436 |
+
"step": 1450
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.8855656697009102,
|
440 |
+
"eval_loss": 0.8104857206344604,
|
441 |
+
"eval_runtime": 12.6152,
|
442 |
+
"eval_samples_per_second": 12.366,
|
443 |
+
"eval_steps_per_second": 0.634,
|
444 |
+
"step": 1450
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.9505851755526658,
|
448 |
+
"grad_norm": 2.6176164150238037,
|
449 |
+
"learning_rate": 1.9454520537597364e-05,
|
450 |
+
"loss": 0.5003,
|
451 |
+
"step": 1500
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.9505851755526658,
|
455 |
+
"eval_loss": 0.8162646293640137,
|
456 |
+
"eval_runtime": 12.7145,
|
457 |
+
"eval_samples_per_second": 12.269,
|
458 |
+
"eval_steps_per_second": 0.629,
|
459 |
+
"step": 1500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.0156046814044215,
|
463 |
+
"grad_norm": 1.6983990669250488,
|
464 |
+
"learning_rate": 1.9378156847531047e-05,
|
465 |
+
"loss": 0.4377,
|
466 |
+
"step": 1550
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 2.0156046814044215,
|
470 |
+
"eval_loss": 0.8717073202133179,
|
471 |
+
"eval_runtime": 12.636,
|
472 |
+
"eval_samples_per_second": 12.346,
|
473 |
+
"eval_steps_per_second": 0.633,
|
474 |
+
"step": 1550
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 2.080624187256177,
|
478 |
+
"grad_norm": 1.206516146659851,
|
479 |
+
"learning_rate": 1.9296962559379296e-05,
|
480 |
+
"loss": 0.251,
|
481 |
+
"step": 1600
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 2.080624187256177,
|
485 |
+
"eval_loss": 0.9452024698257446,
|
486 |
+
"eval_runtime": 12.7171,
|
487 |
+
"eval_samples_per_second": 12.267,
|
488 |
+
"eval_steps_per_second": 0.629,
|
489 |
+
"step": 1600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 2.1456436931079326,
|
493 |
+
"grad_norm": 1.4168466329574585,
|
494 |
+
"learning_rate": 1.9210979495536353e-05,
|
495 |
+
"loss": 0.2465,
|
496 |
+
"step": 1650
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 2.1456436931079326,
|
500 |
+
"eval_loss": 0.9140231013298035,
|
501 |
+
"eval_runtime": 12.6828,
|
502 |
+
"eval_samples_per_second": 12.3,
|
503 |
+
"eval_steps_per_second": 0.631,
|
504 |
+
"step": 1650
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.210663198959688,
|
508 |
+
"grad_norm": 1.882591724395752,
|
509 |
+
"learning_rate": 1.91202519450486e-05,
|
510 |
+
"loss": 0.2494,
|
511 |
+
"step": 1700
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 2.210663198959688,
|
515 |
+
"eval_loss": 0.9127895832061768,
|
516 |
+
"eval_runtime": 12.6517,
|
517 |
+
"eval_samples_per_second": 12.33,
|
518 |
+
"eval_steps_per_second": 0.632,
|
519 |
+
"step": 1700
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 2.2756827048114436,
|
523 |
+
"grad_norm": 1.1632663011550903,
|
524 |
+
"learning_rate": 1.9024826640801694e-05,
|
525 |
+
"loss": 0.2564,
|
526 |
+
"step": 1750
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 2.2756827048114436,
|
530 |
+
"eval_loss": 0.9155619740486145,
|
531 |
+
"eval_runtime": 12.7147,
|
532 |
+
"eval_samples_per_second": 12.269,
|
533 |
+
"eval_steps_per_second": 0.629,
|
534 |
+
"step": 1750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.340702210663199,
|
538 |
+
"grad_norm": 1.2240418195724487,
|
539 |
+
"learning_rate": 1.8924752735448927e-05,
|
540 |
+
"loss": 0.2565,
|
541 |
+
"step": 1800
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.340702210663199,
|
545 |
+
"eval_loss": 0.9181879758834839,
|
546 |
+
"eval_runtime": 12.7403,
|
547 |
+
"eval_samples_per_second": 12.245,
|
548 |
+
"eval_steps_per_second": 0.628,
|
549 |
+
"step": 1800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 2.4057217165149547,
|
553 |
+
"grad_norm": 1.44245183467865,
|
554 |
+
"learning_rate": 1.882008177609315e-05,
|
555 |
+
"loss": 0.2587,
|
556 |
+
"step": 1850
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 2.4057217165149547,
|
560 |
+
"eval_loss": 0.9207939505577087,
|
561 |
+
"eval_runtime": 12.7382,
|
562 |
+
"eval_samples_per_second": 12.247,
|
563 |
+
"eval_steps_per_second": 0.628,
|
564 |
+
"step": 1850
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 2.4707412223667102,
|
568 |
+
"grad_norm": 1.4404542446136475,
|
569 |
+
"learning_rate": 1.8710867677735368e-05,
|
570 |
+
"loss": 0.2725,
|
571 |
+
"step": 1900
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.4707412223667102,
|
575 |
+
"eval_loss": 0.9286116361618042,
|
576 |
+
"eval_runtime": 12.6909,
|
577 |
+
"eval_samples_per_second": 12.292,
|
578 |
+
"eval_steps_per_second": 0.63,
|
579 |
+
"step": 1900
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 2.5357607282184658,
|
583 |
+
"grad_norm": 1.5826677083969116,
|
584 |
+
"learning_rate": 1.859716669550364e-05,
|
585 |
+
"loss": 0.2582,
|
586 |
+
"step": 1950
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 2.5357607282184658,
|
590 |
+
"eval_loss": 0.9147523045539856,
|
591 |
+
"eval_runtime": 12.8088,
|
592 |
+
"eval_samples_per_second": 12.179,
|
593 |
+
"eval_steps_per_second": 0.625,
|
594 |
+
"step": 1950
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 2.6007802340702213,
|
598 |
+
"grad_norm": 1.4913737773895264,
|
599 |
+
"learning_rate": 1.8479037395676613e-05,
|
600 |
+
"loss": 0.2558,
|
601 |
+
"step": 2000
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 2.6007802340702213,
|
605 |
+
"eval_loss": 0.913769543170929,
|
606 |
+
"eval_runtime": 12.7464,
|
607 |
+
"eval_samples_per_second": 12.239,
|
608 |
+
"eval_steps_per_second": 0.628,
|
609 |
+
"step": 2000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 2.665799739921977,
|
613 |
+
"grad_norm": 1.355419397354126,
|
614 |
+
"learning_rate": 1.835654062551658e-05,
|
615 |
+
"loss": 0.2625,
|
616 |
+
"step": 2050
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 2.665799739921977,
|
620 |
+
"eval_loss": 0.9320564270019531,
|
621 |
+
"eval_runtime": 12.7189,
|
622 |
+
"eval_samples_per_second": 12.265,
|
623 |
+
"eval_steps_per_second": 0.629,
|
624 |
+
"step": 2050
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 2.7308192457737324,
|
628 |
+
"grad_norm": 1.2386664152145386,
|
629 |
+
"learning_rate": 1.8229739481927665e-05,
|
630 |
+
"loss": 0.2601,
|
631 |
+
"step": 2100
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 2.7308192457737324,
|
635 |
+
"eval_loss": 0.932084321975708,
|
636 |
+
"eval_runtime": 12.7032,
|
637 |
+
"eval_samples_per_second": 12.28,
|
638 |
+
"eval_steps_per_second": 0.63,
|
639 |
+
"step": 2100
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 2.795838751625488,
|
643 |
+
"grad_norm": 1.9765559434890747,
|
644 |
+
"learning_rate": 1.809869927895519e-05,
|
645 |
+
"loss": 0.2644,
|
646 |
+
"step": 2150
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 2.795838751625488,
|
650 |
+
"eval_loss": 0.9155560731887817,
|
651 |
+
"eval_runtime": 12.7374,
|
652 |
+
"eval_samples_per_second": 12.247,
|
653 |
+
"eval_steps_per_second": 0.628,
|
654 |
+
"step": 2150
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.8608582574772434,
|
658 |
+
"grad_norm": 1.5704264640808105,
|
659 |
+
"learning_rate": 1.7963487514143073e-05,
|
660 |
+
"loss": 0.2724,
|
661 |
+
"step": 2200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 2.8608582574772434,
|
665 |
+
"eval_loss": 0.9207773208618164,
|
666 |
+
"eval_runtime": 12.6727,
|
667 |
+
"eval_samples_per_second": 12.31,
|
668 |
+
"eval_steps_per_second": 0.631,
|
669 |
+
"step": 2200
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.925877763328999,
|
673 |
+
"grad_norm": 2.2694146633148193,
|
674 |
+
"learning_rate": 1.7824173833766457e-05,
|
675 |
+
"loss": 0.2649,
|
676 |
+
"step": 2250
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.925877763328999,
|
680 |
+
"eval_loss": 0.9216504096984863,
|
681 |
+
"eval_runtime": 12.761,
|
682 |
+
"eval_samples_per_second": 12.225,
|
683 |
+
"eval_steps_per_second": 0.627,
|
684 |
+
"step": 2250
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.9908972691807545,
|
688 |
+
"grad_norm": 0.9763782024383545,
|
689 |
+
"learning_rate": 1.7680829996957617e-05,
|
690 |
+
"loss": 0.2701,
|
691 |
+
"step": 2300
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 2.9908972691807545,
|
695 |
+
"eval_loss": 0.9425987601280212,
|
696 |
+
"eval_runtime": 12.7408,
|
697 |
+
"eval_samples_per_second": 12.244,
|
698 |
+
"eval_steps_per_second": 0.628,
|
699 |
+
"step": 2300
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 3.0559167750325096,
|
703 |
+
"grad_norm": 1.0670485496520996,
|
704 |
+
"learning_rate": 1.7533529838743514e-05,
|
705 |
+
"loss": 0.1548,
|
706 |
+
"step": 2350
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 3.0559167750325096,
|
710 |
+
"eval_loss": 0.9931546449661255,
|
711 |
+
"eval_runtime": 12.6597,
|
712 |
+
"eval_samples_per_second": 12.323,
|
713 |
+
"eval_steps_per_second": 0.632,
|
714 |
+
"step": 2350
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 3.120936280884265,
|
718 |
+
"grad_norm": 1.126699686050415,
|
719 |
+
"learning_rate": 1.7382349232014083e-05,
|
720 |
+
"loss": 0.1425,
|
721 |
+
"step": 2400
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 3.120936280884265,
|
725 |
+
"eval_loss": 1.0121082067489624,
|
726 |
+
"eval_runtime": 12.7889,
|
727 |
+
"eval_samples_per_second": 12.198,
|
728 |
+
"eval_steps_per_second": 0.626,
|
729 |
+
"step": 2400
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 3.1859557867360206,
|
733 |
+
"grad_norm": 1.1538535356521606,
|
734 |
+
"learning_rate": 1.7227366048440822e-05,
|
735 |
+
"loss": 0.148,
|
736 |
+
"step": 2450
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 3.1859557867360206,
|
740 |
+
"eval_loss": 1.010581374168396,
|
741 |
+
"eval_runtime": 12.6419,
|
742 |
+
"eval_samples_per_second": 12.34,
|
743 |
+
"eval_steps_per_second": 0.633,
|
744 |
+
"step": 2450
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 3.250975292587776,
|
748 |
+
"grad_norm": 0.9063160419464111,
|
749 |
+
"learning_rate": 1.7068660118365894e-05,
|
750 |
+
"loss": 0.1425,
|
751 |
+
"step": 2500
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 3.250975292587776,
|
755 |
+
"eval_loss": 1.010384440422058,
|
756 |
+
"eval_runtime": 12.7187,
|
757 |
+
"eval_samples_per_second": 12.265,
|
758 |
+
"eval_steps_per_second": 0.629,
|
759 |
+
"step": 2500
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 3.3159947984395317,
|
763 |
+
"grad_norm": 1.3215436935424805,
|
764 |
+
"learning_rate": 1.6906313189682227e-05,
|
765 |
+
"loss": 0.1433,
|
766 |
+
"step": 2550
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 3.3159947984395317,
|
770 |
+
"eval_loss": 1.0235826969146729,
|
771 |
+
"eval_runtime": 12.7063,
|
772 |
+
"eval_samples_per_second": 12.277,
|
773 |
+
"eval_steps_per_second": 0.63,
|
774 |
+
"step": 2550
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 3.3810143042912872,
|
778 |
+
"grad_norm": 1.1784850358963013,
|
779 |
+
"learning_rate": 1.674040888572602e-05,
|
780 |
+
"loss": 0.1501,
|
781 |
+
"step": 2600
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 3.3810143042912872,
|
785 |
+
"eval_loss": 1.029763102531433,
|
786 |
+
"eval_runtime": 12.7431,
|
787 |
+
"eval_samples_per_second": 12.242,
|
788 |
+
"eval_steps_per_second": 0.628,
|
789 |
+
"step": 2600
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 3.4460338101430428,
|
793 |
+
"grad_norm": 1.062929391860962,
|
794 |
+
"learning_rate": 1.6571032662203126e-05,
|
795 |
+
"loss": 0.1553,
|
796 |
+
"step": 2650
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 3.4460338101430428,
|
800 |
+
"eval_loss": 1.0215131044387817,
|
801 |
+
"eval_runtime": 12.6931,
|
802 |
+
"eval_samples_per_second": 12.29,
|
803 |
+
"eval_steps_per_second": 0.63,
|
804 |
+
"step": 2650
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 3.5110533159947983,
|
808 |
+
"grad_norm": 1.3030365705490112,
|
809 |
+
"learning_rate": 1.6398271763171663e-05,
|
810 |
+
"loss": 0.1521,
|
811 |
+
"step": 2700
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 3.5110533159947983,
|
815 |
+
"eval_loss": 1.002717137336731,
|
816 |
+
"eval_runtime": 12.6796,
|
817 |
+
"eval_samples_per_second": 12.303,
|
818 |
+
"eval_steps_per_second": 0.631,
|
819 |
+
"step": 2700
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 3.576072821846554,
|
823 |
+
"grad_norm": 1.0211737155914307,
|
824 |
+
"learning_rate": 1.6222215176103445e-05,
|
825 |
+
"loss": 0.1456,
|
826 |
+
"step": 2750
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 3.576072821846554,
|
830 |
+
"eval_loss": 1.0083057880401611,
|
831 |
+
"eval_runtime": 12.9744,
|
832 |
+
"eval_samples_per_second": 12.024,
|
833 |
+
"eval_steps_per_second": 0.617,
|
834 |
+
"step": 2750
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 3.6410923276983094,
|
838 |
+
"grad_norm": 1.2589364051818848,
|
839 |
+
"learning_rate": 1.6042953586047382e-05,
|
840 |
+
"loss": 0.1449,
|
841 |
+
"step": 2800
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 3.6410923276983094,
|
845 |
+
"eval_loss": 1.0153865814208984,
|
846 |
+
"eval_runtime": 12.6224,
|
847 |
+
"eval_samples_per_second": 12.359,
|
848 |
+
"eval_steps_per_second": 0.634,
|
849 |
+
"step": 2800
|
850 |
+
}
|
851 |
+
],
|
852 |
+
"logging_steps": 50,
|
853 |
+
"max_steps": 7690,
|
854 |
+
"num_input_tokens_seen": 0,
|
855 |
+
"num_train_epochs": 10,
|
856 |
+
"save_steps": 400,
|
857 |
+
"total_flos": 2.549607587339305e+17,
|
858 |
+
"train_batch_size": 1,
|
859 |
+
"trial_name": null,
|
860 |
+
"trial_params": null
|
861 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ce0c11bbddcc9ce30732f4c7497f246a8842198f8e5df437a6c45ed34eddd23
|
3 |
+
size 5112
|