lewtun HF staff commited on
Commit
c3fffb3
1 Parent(s): d70e090

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: google/gemma-7b
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ datasets:
9
+ - generator
10
+ model-index:
11
+ - name: gemma-7b-sft-full-dolly-v1
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # gemma-7b-sft-full-dolly-v1
19
+
20
+ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 4e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 128
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 3
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.39.0.dev0
60
+ - Pytorch 2.1.2+cu121
61
+ - Datasets 2.14.6
62
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.79,
3
+ "train_loss": 22.794086201985678,
4
+ "train_runtime": 180.5723,
5
+ "train_samples": 15011,
6
+ "train_samples_per_second": 22.661,
7
+ "train_steps_per_second": 0.166
8
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-7b",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.39.0.dev0",
26
+ "use_cache": false,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1555e451235ebc6724e213878172a06fb2dac1b1ea474ec2f1bef7ff733a2317
3
+ size 4995496656
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d4149909547eed10016951003c0a7bbb9026d5d307d34fe07758112d24beb4
3
+ size 4982953168
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0f950cdf61cba256f7c06c9f8baf43d6caddbe658c07225ced5b4e522fa803
3
+ size 4982953200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a12ab2b3054792e4eee593e39f27417f1acf9e6d083bc1863617f873e7d35b
3
+ size 2113988336
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17075361792
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.norm.weight": "model-00004-of-00004.safetensors"
260
+ }
261
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
3
+ size 17477473
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "106": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<|im_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% else %}{{ eos_token }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 2048,
64
+ "pad_token": "<pad>",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "tokenizer_class": "GemmaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.79,
3
+ "train_loss": 22.794086201985678,
4
+ "train_runtime": 180.5723,
5
+ "train_samples": 15011,
6
+ "train_samples_per_second": 22.661,
7
+ "train_steps_per_second": 0.166
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.7906976744186047,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09,
13
+ "grad_norm": 9363.44167827181,
14
+ "learning_rate": 1.3333333333333333e-05,
15
+ "loss": 30.9126,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.47,
20
+ "grad_norm": 1160.9061028219837,
21
+ "learning_rate": 3.946089741159648e-05,
22
+ "loss": 24.2863,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.93,
27
+ "grad_norm": 1517.0566103485007,
28
+ "learning_rate": 3.372483275737468e-05,
29
+ "loss": 34.3937,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "grad_norm": 795.2235520034859,
35
+ "learning_rate": 2.3472963553338614e-05,
36
+ "loss": 24.2892,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 1.86,
41
+ "grad_norm": 458.09743259288496,
42
+ "learning_rate": 1.2078404679216864e-05,
43
+ "loss": 19.4514,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 2.33,
48
+ "grad_norm": 299.7088111243142,
49
+ "learning_rate": 3.290243771741275e-06,
50
+ "loss": 17.1994,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 2.79,
55
+ "grad_norm": 275.3311095749166,
56
+ "learning_rate": 0.0,
57
+ "loss": 15.8193,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 2.79,
62
+ "step": 30,
63
+ "total_flos": 8193589641216.0,
64
+ "train_loss": 22.794086201985678,
65
+ "train_runtime": 180.5723,
66
+ "train_samples_per_second": 22.661,
67
+ "train_steps_per_second": 0.166
68
+ }
69
+ ],
70
+ "logging_steps": 5,
71
+ "max_steps": 30,
72
+ "num_input_tokens_seen": 0,
73
+ "num_train_epochs": 3,
74
+ "save_steps": 100,
75
+ "total_flos": 8193589641216.0,
76
+ "train_batch_size": 4,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2fa69f683e9d35068d49da06e2de8d234aef70b8f066a8c5ad214b770235ebd
3
+ size 6136