justin13601 commited on
Commit
1d400f5
1 Parent(s): f82f610

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/phi-2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: Phi-2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # Phi-2
15
+
16
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0781
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 8
43
+ - gradient_accumulation_steps: 32
44
+ - total_train_batch_size: 2048
45
+ - total_eval_batch_size: 64
46
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.05
49
+ - num_epochs: 12.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.2903 | 0.64 | 25 | 0.1770 |
56
+ | 0.1566 | 1.28 | 50 | 0.1319 |
57
+ | 0.1379 | 1.92 | 75 | 0.1253 |
58
+ | 0.1246 | 2.56 | 100 | 0.1165 |
59
+ | 0.1159 | 3.2 | 125 | 0.1049 |
60
+ | 0.1048 | 3.84 | 150 | 0.0998 |
61
+ | 0.0947 | 4.48 | 175 | 0.0949 |
62
+ | 0.0872 | 5.12 | 200 | 0.0906 |
63
+ | 0.0836 | 5.76 | 225 | 0.0890 |
64
+ | 0.0774 | 6.39 | 250 | 0.0850 |
65
+ | 0.0717 | 7.03 | 275 | 0.0827 |
66
+ | 0.0639 | 7.67 | 300 | 0.0807 |
67
+ | 0.0596 | 8.31 | 325 | 0.0789 |
68
+ | 0.0555 | 8.95 | 350 | 0.0773 |
69
+ | 0.0498 | 9.59 | 375 | 0.0777 |
70
+ | 0.0491 | 10.23 | 400 | 0.0781 |
71
+ | 0.0467 | 10.87 | 425 | 0.0780 |
72
+ | 0.0459 | 11.51 | 450 | 0.0781 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.38.1
78
+ - Pytorch 2.2.1+cu121
79
+ - Datasets 2.18.0
80
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_size": 2560,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10240,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "phi",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "partial_rotary_factor": 0.4,
25
+ "qk_layernorm": false,
26
+ "resid_pdrop": 0.1,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.38.1",
32
+ "use_cache": false,
33
+ "vocab_size": 51200
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.38.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9ce99a75847b10cb791c3061119c202b6137b4668e5d132ff2f6008bb80316
3
+ size 4995584848
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfae44c95e5532b711a257309f8673be8643ed0adf51c6cee8a81ed70d5f442c
3
+ size 563833008
model.safetensors.index.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5559367680
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00002-of-00002.safetensors",
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
10
+ "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
11
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
94
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
108
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
118
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
130
+ "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
132
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
142
+ "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
154
+ "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
156
+ "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
166
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
168
+ "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
178
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
180
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
190
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
192
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
202
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
214
+ "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
226
+ "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
228
+ "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
+ "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
+ "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
252
+ "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
262
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
264
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
276
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
280
+ "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
286
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
298
+ "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
300
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
304
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
310
+ "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
312
+ "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
316
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
322
+ "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
324
+ "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
326
+ "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
328
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
334
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
336
+ "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
338
+ "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
340
+ "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
346
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
348
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
356
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
358
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
360
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
368
+ "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
370
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
374
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
382
+ "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
394
+ "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
396
+ "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
406
+ "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
408
+ "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
448
+ "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
459
+ }
460
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": " ",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": " ",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": " ",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": " ",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": " ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": " ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": " ",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": " ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": " ",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": " ",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": " ",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": " ",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": " ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": " ",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": " ",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": " ",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": " ",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": " ",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": " ",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50276": {
166
+ "content": " ",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50277": {
174
+ "content": " ",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50278": {
182
+ "content": " ",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50279": {
190
+ "content": " ",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50280": {
198
+ "content": " ",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50281": {
206
+ "content": " ",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50282": {
214
+ "content": " ",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50283": {
222
+ "content": " ",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50284": {
230
+ "content": " ",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50285": {
238
+ "content": " ",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50286": {
246
+ "content": " ",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50287": {
254
+ "content": "\t\t\t\t\t\t\t\t\t",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50288": {
262
+ "content": "\t\t\t\t\t\t\t\t",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50289": {
270
+ "content": "\t\t\t\t\t\t\t",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50290": {
278
+ "content": "\t\t\t\t\t\t",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50291": {
286
+ "content": "\t\t\t\t\t",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50292": {
294
+ "content": "\t\t\t\t",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50293": {
302
+ "content": "\t\t\t",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50294": {
310
+ "content": "\t\t",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ }
317
+ },
318
+ "bos_token": "<|endoftext|>",
319
+ "chat_template": "{% for message in messages %}\n{% if message['from'] == 'human' %}\n{{ '<|user|>\n' + message['value'] + eos_token }}\n{% elif message['from'] == 'system' %}\n{{ '<|system|>\n' + message['value'] + eos_token }}\n{% elif message['from'] == 'gpt' %}\n{{ '<|assistant|>\n' + message['value'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
320
+ "clean_up_tokenization_spaces": true,
321
+ "eos_token": "<|endoftext|>",
322
+ "errors": "replace",
323
+ "model_max_length": 2048,
324
+ "pad_token": "<|endoftext|>",
325
+ "padding_side": "right",
326
+ "tokenizer_class": "CodeGenTokenizer",
327
+ "unk_token": "<|endoftext|>"
328
+ }
trainer_state.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.971223021582734,
5
+ "eval_steps": 25,
6
+ "global_step": 468,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.64,
13
+ "grad_norm": 1.127359124604765,
14
+ "learning_rate": 9.999874838141888e-05,
15
+ "loss": 0.2903,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.64,
20
+ "eval_loss": 0.17698872089385986,
21
+ "eval_runtime": 109.7117,
22
+ "eval_samples_per_second": 91.157,
23
+ "eval_steps_per_second": 1.431,
24
+ "step": 25
25
+ },
26
+ {
27
+ "epoch": 1.28,
28
+ "grad_norm": 0.27062951121760287,
29
+ "learning_rate": 9.915628588978522e-05,
30
+ "loss": 0.1566,
31
+ "step": 50
32
+ },
33
+ {
34
+ "epoch": 1.28,
35
+ "eval_loss": 0.1319342851638794,
36
+ "eval_runtime": 109.0269,
37
+ "eval_samples_per_second": 91.73,
38
+ "eval_steps_per_second": 1.44,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 1.92,
43
+ "grad_norm": 0.24204285961516211,
44
+ "learning_rate": 9.67797005288181e-05,
45
+ "loss": 0.1379,
46
+ "step": 75
47
+ },
48
+ {
49
+ "epoch": 1.92,
50
+ "eval_loss": 0.12531398236751556,
51
+ "eval_runtime": 108.9721,
52
+ "eval_samples_per_second": 91.776,
53
+ "eval_steps_per_second": 1.441,
54
+ "step": 75
55
+ },
56
+ {
57
+ "epoch": 2.56,
58
+ "grad_norm": 0.17190878979127733,
59
+ "learning_rate": 9.294316336102132e-05,
60
+ "loss": 0.1246,
61
+ "step": 100
62
+ },
63
+ {
64
+ "epoch": 2.56,
65
+ "eval_loss": 0.11651688814163208,
66
+ "eval_runtime": 109.0854,
67
+ "eval_samples_per_second": 91.68,
68
+ "eval_steps_per_second": 1.439,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 3.2,
73
+ "grad_norm": 0.19157295828856058,
74
+ "learning_rate": 8.776640921382584e-05,
75
+ "loss": 0.1159,
76
+ "step": 125
77
+ },
78
+ {
79
+ "epoch": 3.2,
80
+ "eval_loss": 0.10494253039360046,
81
+ "eval_runtime": 109.434,
82
+ "eval_samples_per_second": 91.388,
83
+ "eval_steps_per_second": 1.435,
84
+ "step": 125
85
+ },
86
+ {
87
+ "epoch": 3.84,
88
+ "grad_norm": 0.13204284591576954,
89
+ "learning_rate": 8.141099986478212e-05,
90
+ "loss": 0.1048,
91
+ "step": 150
92
+ },
93
+ {
94
+ "epoch": 3.84,
95
+ "eval_loss": 0.09983079880475998,
96
+ "eval_runtime": 109.7612,
97
+ "eval_samples_per_second": 91.116,
98
+ "eval_steps_per_second": 1.43,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 4.48,
103
+ "grad_norm": 0.17932878424857554,
104
+ "learning_rate": 7.407528184577019e-05,
105
+ "loss": 0.0947,
106
+ "step": 175
107
+ },
108
+ {
109
+ "epoch": 4.48,
110
+ "eval_loss": 0.09489566832780838,
111
+ "eval_runtime": 108.9729,
112
+ "eval_samples_per_second": 91.775,
113
+ "eval_steps_per_second": 1.441,
114
+ "step": 175
115
+ },
116
+ {
117
+ "epoch": 5.12,
118
+ "grad_norm": 0.10314936548781714,
119
+ "learning_rate": 6.598819622856227e-05,
120
+ "loss": 0.0872,
121
+ "step": 200
122
+ },
123
+ {
124
+ "epoch": 5.12,
125
+ "eval_loss": 0.09059683978557587,
126
+ "eval_runtime": 109.4369,
127
+ "eval_samples_per_second": 91.386,
128
+ "eval_steps_per_second": 1.435,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 5.76,
133
+ "grad_norm": 0.09896949138120692,
134
+ "learning_rate": 5.7402133582686576e-05,
135
+ "loss": 0.0836,
136
+ "step": 225
137
+ },
138
+ {
139
+ "epoch": 5.76,
140
+ "eval_loss": 0.08898729830980301,
141
+ "eval_runtime": 109.6712,
142
+ "eval_samples_per_second": 91.191,
143
+ "eval_steps_per_second": 1.432,
144
+ "step": 225
145
+ },
146
+ {
147
+ "epoch": 6.39,
148
+ "grad_norm": 0.09411679948573648,
149
+ "learning_rate": 4.85850570958441e-05,
150
+ "loss": 0.0774,
151
+ "step": 250
152
+ },
153
+ {
154
+ "epoch": 6.39,
155
+ "eval_loss": 0.08496005833148956,
156
+ "eval_runtime": 108.989,
157
+ "eval_samples_per_second": 91.762,
158
+ "eval_steps_per_second": 1.441,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 7.03,
163
+ "grad_norm": 0.0741392458596649,
164
+ "learning_rate": 3.9812139687108815e-05,
165
+ "loss": 0.0717,
166
+ "step": 275
167
+ },
168
+ {
169
+ "epoch": 7.03,
170
+ "eval_loss": 0.08271028101444244,
171
+ "eval_runtime": 108.611,
172
+ "eval_samples_per_second": 92.081,
173
+ "eval_steps_per_second": 1.446,
174
+ "step": 275
175
+ },
176
+ {
177
+ "epoch": 7.67,
178
+ "grad_norm": 0.08461241295692067,
179
+ "learning_rate": 3.135717611098458e-05,
180
+ "loss": 0.0639,
181
+ "step": 300
182
+ },
183
+ {
184
+ "epoch": 7.67,
185
+ "eval_loss": 0.08073248714208603,
186
+ "eval_runtime": 109.2638,
187
+ "eval_samples_per_second": 91.531,
188
+ "eval_steps_per_second": 1.437,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 8.31,
193
+ "grad_norm": 0.10663906934510009,
194
+ "learning_rate": 2.3484038072721758e-05,
195
+ "loss": 0.0596,
196
+ "step": 325
197
+ },
198
+ {
199
+ "epoch": 8.31,
200
+ "eval_loss": 0.07886555045843124,
201
+ "eval_runtime": 109.6916,
202
+ "eval_samples_per_second": 91.174,
203
+ "eval_steps_per_second": 1.431,
204
+ "step": 325
205
+ },
206
+ {
207
+ "epoch": 8.95,
208
+ "grad_norm": 0.09636182626655444,
209
+ "learning_rate": 1.6438439032954855e-05,
210
+ "loss": 0.0555,
211
+ "step": 350
212
+ },
213
+ {
214
+ "epoch": 8.95,
215
+ "eval_loss": 0.0773012638092041,
216
+ "eval_runtime": 109.6624,
217
+ "eval_samples_per_second": 91.198,
218
+ "eval_steps_per_second": 1.432,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 9.59,
223
+ "grad_norm": 0.05049345737531785,
224
+ "learning_rate": 1.0440265714600572e-05,
225
+ "loss": 0.0498,
226
+ "step": 375
227
+ },
228
+ {
229
+ "epoch": 9.59,
230
+ "eval_loss": 0.07774835079908371,
231
+ "eval_runtime": 109.5603,
232
+ "eval_samples_per_second": 91.283,
233
+ "eval_steps_per_second": 1.433,
234
+ "step": 375
235
+ },
236
+ {
237
+ "epoch": 10.23,
238
+ "grad_norm": 0.0430056992457794,
239
+ "learning_rate": 5.676715638695063e-06,
240
+ "loss": 0.0491,
241
+ "step": 400
242
+ },
243
+ {
244
+ "epoch": 10.23,
245
+ "eval_loss": 0.07812906801700592,
246
+ "eval_runtime": 109.8294,
247
+ "eval_samples_per_second": 91.059,
248
+ "eval_steps_per_second": 1.429,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 10.87,
253
+ "grad_norm": 0.040355667582564335,
254
+ "learning_rate": 2.2964548604209213e-06,
255
+ "loss": 0.0467,
256
+ "step": 425
257
+ },
258
+ {
259
+ "epoch": 10.87,
260
+ "eval_loss": 0.07796623557806015,
261
+ "eval_runtime": 109.5541,
262
+ "eval_samples_per_second": 91.288,
263
+ "eval_steps_per_second": 1.433,
264
+ "step": 425
265
+ },
266
+ {
267
+ "epoch": 11.51,
268
+ "grad_norm": 0.041530575942009804,
269
+ "learning_rate": 4.049782370561583e-07,
270
+ "loss": 0.0459,
271
+ "step": 450
272
+ },
273
+ {
274
+ "epoch": 11.51,
275
+ "eval_loss": 0.07810305058956146,
276
+ "eval_runtime": 108.746,
277
+ "eval_samples_per_second": 91.967,
278
+ "eval_steps_per_second": 1.444,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 11.97,
283
+ "step": 468,
284
+ "total_flos": 1.0672624631808e+16,
285
+ "train_loss": 0.0933543870336989,
286
+ "train_runtime": 39555.7956,
287
+ "train_samples_per_second": 24.271,
288
+ "train_steps_per_second": 0.012
289
+ }
290
+ ],
291
+ "logging_steps": 25,
292
+ "max_steps": 468,
293
+ "num_input_tokens_seen": 0,
294
+ "num_train_epochs": 12,
295
+ "save_steps": 2000,
296
+ "total_flos": 1.0672624631808e+16,
297
+ "train_batch_size": 8,
298
+ "trial_name": null,
299
+ "trial_params": null
300
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a3dec295ca5c8c8cf749deab13f7603edf64198651f24ada022507b0031643
3
+ size 7160
vocab.json ADDED
The diff for this file is too large to render. See raw diff