ikno commited on
Commit
8b1f8da
1 Parent(s): f09f97c

Model save

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: OrionStarAI/Orion-14B-Chat
3
+ tags:
4
+ - trl
5
+ - sft
6
+ - generated_from_trainer
7
+ datasets:
8
+ - generator
9
+ model-index:
10
+ - name: rinko-test
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # rinko-test
18
+
19
+ This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the generator dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1707
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-07
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 8
48
+ - total_eval_batch_size: 4
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 3
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.3348 | 0.99 | 62 | 0.2483 |
59
+ | 0.2659 | 2.0 | 125 | 0.1883 |
60
+ | 0.2447 | 2.98 | 186 | 0.1707 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.38.2
66
+ - Pytorch 2.1.0+cu118
67
+ - Datasets 2.14.6
68
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "train_loss": 0.3222779505034929,
4
+ "train_runtime": 18917.8994,
5
+ "train_samples": 5850,
6
+ "train_samples_per_second": 0.079,
7
+ "train_steps_per_second": 0.01
8
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "OrionStarAI/Orion-14B-Chat",
3
+ "architectures": [
4
+ "OrionForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "auto_map": {
8
+ "AutoConfig": "OrionStarAI/Orion-14B-Chat--configuration_orion.OrionConfig",
9
+ "AutoModelForCausalLM": "OrionStarAI/Orion-14B-Chat--modeling_orion.OrionForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 15360,
17
+ "max_position_embeddings": 4096,
18
+ "max_sequence_length": 4096,
19
+ "model_type": "orion",
20
+ "num_attention_heads": 40,
21
+ "num_hidden_layers": 40,
22
+ "num_key_value_heads": 40,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 10000.0,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.38.2",
31
+ "use_cache": false,
32
+ "vocab_size": 84608
33
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_new_tokens": 1024,
7
+ "pad_token_id": 0,
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 0.3,
10
+ "top_k": 5,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.38.2"
13
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371a444d2e751f6d935abee8873b654115f554324b80a4bc4098958cb6cf21cb
3
+ size 4956085824
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3323f7e7b368f7f09fb0ccf81cf234bf914a007eedda5a0550ddf64487bf04
3
+ size 4981032096
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b485407cbdcab834489d1ad02c81a304961b821155bddaff2ad9e153de036b6
3
+ size 4928602984
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a319bcbd3ad5afb9a796243b2ec5a96300f2176c8ae590de5a3074a437e8de
3
+ size 4928602976
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde60bda83debe8dffe5a05b95cf3dac769b1eec9342a481e35797a0d10e6701
3
+ size 4981073320
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df9e2965112cc7ceca860420e720c240407aac8dd074f762552bdb06f8f76e3
3
+ size 4222060984
model.safetensors.index.json ADDED
@@ -0,0 +1,451 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28997406720
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.10.input_layernorm.bias": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.input_layernorm.bias": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.12.input_layernorm.bias": "model-00002-of-00006.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
58
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.13.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
69
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
74
+ "model.layers.14.input_layernorm.bias": "model-00003-of-00006.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.14.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
80
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.15.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
91
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.16.input_layernorm.bias": "model-00003-of-00006.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.16.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
102
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.17.input_layernorm.bias": "model-00003-of-00006.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.17.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
113
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.18.input_layernorm.bias": "model-00003-of-00006.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.18.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
124
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.19.input_layernorm.bias": "model-00003-of-00006.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.19.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
135
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
145
+ "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
146
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
151
+ "model.layers.20.input_layernorm.bias": "model-00004-of-00006.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
156
+ "model.layers.20.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
157
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
162
+ "model.layers.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
167
+ "model.layers.21.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
168
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.22.input_layernorm.bias": "model-00004-of-00006.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.22.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
179
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.23.input_layernorm.bias": "model-00004-of-00006.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.23.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
190
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.24.input_layernorm.bias": "model-00004-of-00006.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.24.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
201
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.25.input_layernorm.bias": "model-00004-of-00006.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.25.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
212
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.26.input_layernorm.bias": "model-00004-of-00006.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
222
+ "model.layers.26.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
223
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
233
+ "model.layers.27.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
234
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.28.input_layernorm.bias": "model-00005-of-00006.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
244
+ "model.layers.28.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
245
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.29.input_layernorm.bias": "model-00005-of-00006.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.29.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
256
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
266
+ "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
267
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
272
+ "model.layers.30.input_layernorm.bias": "model-00005-of-00006.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.30.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
278
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.31.input_layernorm.bias": "model-00005-of-00006.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.31.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
289
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.32.input_layernorm.bias": "model-00005-of-00006.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.32.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
300
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.33.input_layernorm.bias": "model-00005-of-00006.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
310
+ "model.layers.33.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
311
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
316
+ "model.layers.34.input_layernorm.bias": "model-00005-of-00006.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
321
+ "model.layers.34.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
322
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
327
+ "model.layers.35.input_layernorm.bias": "model-00006-of-00006.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
332
+ "model.layers.35.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
333
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
338
+ "model.layers.36.input_layernorm.bias": "model-00006-of-00006.safetensors",
339
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
340
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
341
+ "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
342
+ "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
343
+ "model.layers.36.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
344
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
345
+ "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
346
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
347
+ "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
348
+ "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
349
+ "model.layers.37.input_layernorm.bias": "model-00006-of-00006.safetensors",
350
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
351
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
352
+ "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
353
+ "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
354
+ "model.layers.37.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
355
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
356
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
357
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
358
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
359
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
360
+ "model.layers.38.input_layernorm.bias": "model-00006-of-00006.safetensors",
361
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
362
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
363
+ "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
364
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
365
+ "model.layers.38.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
366
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
367
+ "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
368
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
369
+ "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
370
+ "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
371
+ "model.layers.39.input_layernorm.bias": "model-00006-of-00006.safetensors",
372
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
373
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
374
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
375
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
376
+ "model.layers.39.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
377
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
378
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
379
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
380
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
381
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
382
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00006.safetensors",
383
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
384
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
385
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
386
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
387
+ "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
388
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
389
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
390
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
391
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
392
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
393
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00006.safetensors",
394
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
395
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
396
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
397
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
398
+ "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
399
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
400
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
401
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
402
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
404
+ "model.layers.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
405
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
406
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
407
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
408
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
409
+ "model.layers.6.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
410
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
411
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
412
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
413
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
414
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
415
+ "model.layers.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
416
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
417
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
418
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
419
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
420
+ "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
421
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
422
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
423
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
424
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
425
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
426
+ "model.layers.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
427
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
428
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
429
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
430
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
431
+ "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
432
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
433
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
434
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
435
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
436
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
437
+ "model.layers.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
438
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
439
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
440
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
441
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
442
+ "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
443
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
444
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
445
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
446
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
447
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
448
+ "model.norm.bias": "model-00006-of-00006.safetensors",
449
+ "model.norm.weight": "model-00006-of-00006.safetensors"
450
+ }
451
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded43118b7418f56db97a4eed08a5c265c03120158229ddd4fbcc9658241d5f0
3
+ size 1520600
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "auto_map": {
31
+ "AutoTokenizer": [
32
+ "OrionStarAI/Orion-14B-Chat--tokenization_orion.OrionTokenizer",
33
+ null
34
+ ]
35
+ },
36
+ "bos_token": "<s>",
37
+ "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] }}\n\n{% elif message['role'] == 'assistant' %}\n{{ 'Assistant: '+eos_token + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ 'Assistant: </s>' }}{% endif %}{% endfor %}",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 4096,
41
+ "pad_token": "<unk>",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "OrionTokenizer",
44
+ "unk_token": "<unk>"
45
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "train_loss": 0.3222779505034929,
4
+ "train_runtime": 18917.8994,
5
+ "train_samples": 5850,
6
+ "train_samples_per_second": 0.079,
7
+ "train_steps_per_second": 0.01
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.976,
5
+ "eval_steps": 500,
6
+ "global_step": 186,
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": 4.6117611690953515,
14
+ "learning_rate": 1.0526315789473683e-08,
15
+ "loss": 0.4933,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.08,
20
+ "grad_norm": 4.485227520015997,
21
+ "learning_rate": 5.2631578947368416e-08,
22
+ "loss": 0.4996,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "grad_norm": 4.765524959241675,
28
+ "learning_rate": 1.0526315789473683e-07,
29
+ "loss": 0.5018,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.24,
34
+ "grad_norm": 4.710513305333378,
35
+ "learning_rate": 1.5789473684210525e-07,
36
+ "loss": 0.4844,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.32,
41
+ "grad_norm": 4.537921702304328,
42
+ "learning_rate": 1.9998230608242914e-07,
43
+ "loss": 0.4739,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.4,
48
+ "grad_norm": 3.917599997580791,
49
+ "learning_rate": 1.993636761762317e-07,
50
+ "loss": 0.4759,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.48,
55
+ "grad_norm": 3.988201318412564,
56
+ "learning_rate": 1.9786660193313148e-07,
57
+ "loss": 0.4606,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.56,
62
+ "grad_norm": 2.843430355228346,
63
+ "learning_rate": 1.9550431853565574e-07,
64
+ "loss": 0.4171,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.64,
69
+ "grad_norm": 2.9412621389290257,
70
+ "learning_rate": 1.9229771021990092e-07,
71
+ "loss": 0.4075,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.72,
76
+ "grad_norm": 2.5891798071506584,
77
+ "learning_rate": 1.8827512564429073e-07,
78
+ "loss": 0.3895,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 2.311260337839049,
84
+ "learning_rate": 1.8347212726762435e-07,
85
+ "loss": 0.3826,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.88,
90
+ "grad_norm": 1.7315001394623175,
91
+ "learning_rate": 1.7793117695208826e-07,
92
+ "loss": 0.3429,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.96,
97
+ "grad_norm": 1.3441016711237108,
98
+ "learning_rate": 1.717012605707203e-07,
99
+ "loss": 0.3348,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.99,
104
+ "eval_loss": 0.2483493983745575,
105
+ "eval_runtime": 131.0647,
106
+ "eval_samples_per_second": 0.275,
107
+ "eval_steps_per_second": 0.069,
108
+ "step": 62
109
+ },
110
+ {
111
+ "epoch": 1.04,
112
+ "grad_norm": 1.2392330789677268,
113
+ "learning_rate": 1.6483745493805867e-07,
114
+ "loss": 0.3216,
115
+ "step": 65
116
+ },
117
+ {
118
+ "epoch": 1.12,
119
+ "grad_norm": 1.219453051753039,
120
+ "learning_rate": 1.5740044089261134e-07,
121
+ "loss": 0.3185,
122
+ "step": 70
123
+ },
124
+ {
125
+ "epoch": 1.2,
126
+ "grad_norm": 1.1222350719240004,
127
+ "learning_rate": 1.4945596683583752e-07,
128
+ "loss": 0.3083,
129
+ "step": 75
130
+ },
131
+ {
132
+ "epoch": 1.28,
133
+ "grad_norm": 1.1144412166765716,
134
+ "learning_rate": 1.4107426747033074e-07,
135
+ "loss": 0.3047,
136
+ "step": 80
137
+ },
138
+ {
139
+ "epoch": 1.36,
140
+ "grad_norm": 1.1344036025375182,
141
+ "learning_rate": 1.323294428759652e-07,
142
+ "loss": 0.3083,
143
+ "step": 85
144
+ },
145
+ {
146
+ "epoch": 1.44,
147
+ "grad_norm": 1.114097744195408,
148
+ "learning_rate": 1.232988034134053e-07,
149
+ "loss": 0.2968,
150
+ "step": 90
151
+ },
152
+ {
153
+ "epoch": 1.52,
154
+ "grad_norm": 1.04860266630711,
155
+ "learning_rate": 1.1406218624648985e-07,
156
+ "loss": 0.2964,
157
+ "step": 95
158
+ },
159
+ {
160
+ "epoch": 1.6,
161
+ "grad_norm": 1.0412871936488755,
162
+ "learning_rate": 1.0470124952590976e-07,
163
+ "loss": 0.2933,
164
+ "step": 100
165
+ },
166
+ {
167
+ "epoch": 1.68,
168
+ "grad_norm": 1.0589673455582587,
169
+ "learning_rate": 9.529875047409026e-08,
170
+ "loss": 0.2908,
171
+ "step": 105
172
+ },
173
+ {
174
+ "epoch": 1.76,
175
+ "grad_norm": 1.0322727028980907,
176
+ "learning_rate": 8.59378137535102e-08,
177
+ "loss": 0.2756,
178
+ "step": 110
179
+ },
180
+ {
181
+ "epoch": 1.84,
182
+ "grad_norm": 1.0299988465119796,
183
+ "learning_rate": 7.670119658659468e-08,
184
+ "loss": 0.276,
185
+ "step": 115
186
+ },
187
+ {
188
+ "epoch": 1.92,
189
+ "grad_norm": 1.0150896602116855,
190
+ "learning_rate": 6.76705571240348e-08,
191
+ "loss": 0.2666,
192
+ "step": 120
193
+ },
194
+ {
195
+ "epoch": 2.0,
196
+ "grad_norm": 1.0283555629278627,
197
+ "learning_rate": 5.892573252966926e-08,
198
+ "loss": 0.2659,
199
+ "step": 125
200
+ },
201
+ {
202
+ "epoch": 2.0,
203
+ "eval_loss": 0.18834702670574188,
204
+ "eval_runtime": 131.135,
205
+ "eval_samples_per_second": 0.275,
206
+ "eval_steps_per_second": 0.069,
207
+ "step": 125
208
+ },
209
+ {
210
+ "epoch": 2.08,
211
+ "grad_norm": 1.0093549041505132,
212
+ "learning_rate": 5.054403316416247e-08,
213
+ "loss": 0.2524,
214
+ "step": 130
215
+ },
216
+ {
217
+ "epoch": 2.16,
218
+ "grad_norm": 1.018811573391022,
219
+ "learning_rate": 4.2599559107388636e-08,
220
+ "loss": 0.2506,
221
+ "step": 135
222
+ },
223
+ {
224
+ "epoch": 2.24,
225
+ "grad_norm": 1.039650875543289,
226
+ "learning_rate": 3.516254506194133e-08,
227
+ "loss": 0.2578,
228
+ "step": 140
229
+ },
230
+ {
231
+ "epoch": 2.32,
232
+ "grad_norm": 1.035580954839146,
233
+ "learning_rate": 2.8298739429279706e-08,
234
+ "loss": 0.2522,
235
+ "step": 145
236
+ },
237
+ {
238
+ "epoch": 2.4,
239
+ "grad_norm": 1.0360132857828035,
240
+ "learning_rate": 2.2068823047911754e-08,
241
+ "loss": 0.2517,
242
+ "step": 150
243
+ },
244
+ {
245
+ "epoch": 2.48,
246
+ "grad_norm": 1.0267979523571857,
247
+ "learning_rate": 1.6527872732375646e-08,
248
+ "loss": 0.2386,
249
+ "step": 155
250
+ },
251
+ {
252
+ "epoch": 2.56,
253
+ "grad_norm": 1.0903062573289466,
254
+ "learning_rate": 1.1724874355709258e-08,
255
+ "loss": 0.2412,
256
+ "step": 160
257
+ },
258
+ {
259
+ "epoch": 2.64,
260
+ "grad_norm": 1.049473662481498,
261
+ "learning_rate": 7.70228978009907e-09,
262
+ "loss": 0.2397,
263
+ "step": 165
264
+ },
265
+ {
266
+ "epoch": 2.72,
267
+ "grad_norm": 1.0294155234866598,
268
+ "learning_rate": 4.4956814643442585e-09,
269
+ "loss": 0.2353,
270
+ "step": 170
271
+ },
272
+ {
273
+ "epoch": 2.8,
274
+ "grad_norm": 1.0562623811700738,
275
+ "learning_rate": 2.1333980668685415e-09,
276
+ "loss": 0.2418,
277
+ "step": 175
278
+ },
279
+ {
280
+ "epoch": 2.88,
281
+ "grad_norm": 1.0446606479668537,
282
+ "learning_rate": 6.363238237683033e-10,
283
+ "loss": 0.2383,
284
+ "step": 180
285
+ },
286
+ {
287
+ "epoch": 2.96,
288
+ "grad_norm": 1.0364893408749978,
289
+ "learning_rate": 1.7693917570837934e-11,
290
+ "loss": 0.2447,
291
+ "step": 185
292
+ },
293
+ {
294
+ "epoch": 2.98,
295
+ "eval_loss": 0.1706668883562088,
296
+ "eval_runtime": 129.4132,
297
+ "eval_samples_per_second": 0.278,
298
+ "eval_steps_per_second": 0.07,
299
+ "step": 186
300
+ },
301
+ {
302
+ "epoch": 2.98,
303
+ "step": 186,
304
+ "total_flos": 30250327080960.0,
305
+ "train_loss": 0.3222779505034929,
306
+ "train_runtime": 18917.8994,
307
+ "train_samples_per_second": 0.079,
308
+ "train_steps_per_second": 0.01
309
+ }
310
+ ],
311
+ "logging_steps": 5,
312
+ "max_steps": 186,
313
+ "num_input_tokens_seen": 0,
314
+ "num_train_epochs": 3,
315
+ "save_steps": 1,
316
+ "total_flos": 30250327080960.0,
317
+ "train_batch_size": 1,
318
+ "trial_name": null,
319
+ "trial_params": null
320
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b01e6e3cebdb75887d863a0bfca1da655ab013959c66156af35bd86f73d5101
3
+ size 6072