vwxyzjn commited on
Commit
75584dd
1 Parent(s): 3c36b32

Model save

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-v0.1
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ datasets:
9
+ - generator
10
+ model-index:
11
+ - name: zephyr-7b-sft-cai
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
+ # zephyr-7b-sft-cai
19
+
20
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.9344
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 8
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 256
49
+ - total_eval_batch_size: 64
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: cosine
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - num_epochs: 1
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss |
58
+ |:-------------:|:-----:|:----:|:---------------:|
59
+ | 0.9241 | 1.0 | 550 | 0.9344 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.36.2
65
+ - Pytorch 2.1.2+cu121
66
+ - Datasets 2.14.6
67
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9343938231468201,
4
+ "eval_runtime": 143.0083,
5
+ "eval_samples": 24266,
6
+ "eval_samples_per_second": 108.476,
7
+ "eval_steps_per_second": 1.699,
8
+ "train_loss": 0.9703456902503967,
9
+ "train_runtime": 5589.9273,
10
+ "train_samples": 229133,
11
+ "train_samples_per_second": 25.215,
12
+ "train_steps_per_second": 0.098
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9343938231468201,
4
+ "eval_runtime": 143.0083,
5
+ "eval_samples": 24266,
6
+ "eval_samples_per_second": 108.476,
7
+ "eval_steps_per_second": 1.699
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0e5b3fdfd71fbc05f4fbd182e375b0adabca2a11c0299a8548f4ca989fa4fc
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d55ee6871eaf629651513e8cc554ac3ef9c141ac79e8457a2f2de2d9322a34
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a26597ee7386b448c45af889970bd16eb8340eeec541d9d2230abb91263f241
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
runs/Jan31_15-04-00_ip-26-0-161-123/events.out.tfevents.1706714127.ip-26-0-161-123.1458979.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89569c4b8d655cb1db969566439b6fb606f26c6aca89dd6101fe1fcfd941fdbe
3
- size 20217
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913cc1d70e4ec4217ddf87ebcd3a7f058772f46f890c0d8a7397aae661569a4a
3
+ size 22412
runs/Jan31_15-04-00_ip-26-0-161-123/events.out.tfevents.1706719854.ip-26-0-161-123.1458979.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e23152cc68fd5e9d455bbadb69aed3b39c5cd54582445b6c661e30facbb7dfac
3
+ size 359
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.9703456902503967,
4
+ "train_runtime": 5589.9273,
5
+ "train_samples": 229133,
6
+ "train_samples_per_second": 25.215,
7
+ "train_steps_per_second": 0.098
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,704 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9986382206082615,
5
+ "eval_steps": 500,
6
+ "global_step": 550,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 3.6363636363636366e-07,
14
+ "loss": 1.6989,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 1.8181818181818183e-06,
20
+ "loss": 1.592,
21
+ "step": 5
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3.6363636363636366e-06,
26
+ "loss": 1.3096,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 5.4545454545454545e-06,
32
+ "loss": 1.1801,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 0.04,
37
+ "learning_rate": 7.272727272727273e-06,
38
+ "loss": 1.1065,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.05,
43
+ "learning_rate": 9.090909090909091e-06,
44
+ "loss": 1.0653,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.05,
49
+ "learning_rate": 1.0909090909090909e-05,
50
+ "loss": 1.0523,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.06,
55
+ "learning_rate": 1.2727272727272728e-05,
56
+ "loss": 1.0315,
57
+ "step": 35
58
+ },
59
+ {
60
+ "epoch": 0.07,
61
+ "learning_rate": 1.4545454545454546e-05,
62
+ "loss": 1.0111,
63
+ "step": 40
64
+ },
65
+ {
66
+ "epoch": 0.08,
67
+ "learning_rate": 1.6363636363636366e-05,
68
+ "loss": 1.0113,
69
+ "step": 45
70
+ },
71
+ {
72
+ "epoch": 0.09,
73
+ "learning_rate": 1.8181818181818182e-05,
74
+ "loss": 1.0169,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.1,
79
+ "learning_rate": 2e-05,
80
+ "loss": 0.998,
81
+ "step": 55
82
+ },
83
+ {
84
+ "epoch": 0.11,
85
+ "learning_rate": 1.9994965423831853e-05,
86
+ "loss": 1.0046,
87
+ "step": 60
88
+ },
89
+ {
90
+ "epoch": 0.12,
91
+ "learning_rate": 1.9979866764718846e-05,
92
+ "loss": 1.0102,
93
+ "step": 65
94
+ },
95
+ {
96
+ "epoch": 0.13,
97
+ "learning_rate": 1.9954719225730847e-05,
98
+ "loss": 1.012,
99
+ "step": 70
100
+ },
101
+ {
102
+ "epoch": 0.14,
103
+ "learning_rate": 1.9919548128307954e-05,
104
+ "loss": 1.0108,
105
+ "step": 75
106
+ },
107
+ {
108
+ "epoch": 0.15,
109
+ "learning_rate": 1.9874388886763944e-05,
110
+ "loss": 0.9918,
111
+ "step": 80
112
+ },
113
+ {
114
+ "epoch": 0.15,
115
+ "learning_rate": 1.9819286972627066e-05,
116
+ "loss": 0.9959,
117
+ "step": 85
118
+ },
119
+ {
120
+ "epoch": 0.16,
121
+ "learning_rate": 1.9754297868854075e-05,
122
+ "loss": 1.0019,
123
+ "step": 90
124
+ },
125
+ {
126
+ "epoch": 0.17,
127
+ "learning_rate": 1.9679487013963566e-05,
128
+ "loss": 0.9897,
129
+ "step": 95
130
+ },
131
+ {
132
+ "epoch": 0.18,
133
+ "learning_rate": 1.9594929736144978e-05,
134
+ "loss": 1.004,
135
+ "step": 100
136
+ },
137
+ {
138
+ "epoch": 0.19,
139
+ "learning_rate": 1.9500711177409456e-05,
140
+ "loss": 0.9838,
141
+ "step": 105
142
+ },
143
+ {
144
+ "epoch": 0.2,
145
+ "learning_rate": 1.9396926207859085e-05,
146
+ "loss": 0.9717,
147
+ "step": 110
148
+ },
149
+ {
150
+ "epoch": 0.21,
151
+ "learning_rate": 1.9283679330160726e-05,
152
+ "loss": 0.9931,
153
+ "step": 115
154
+ },
155
+ {
156
+ "epoch": 0.22,
157
+ "learning_rate": 1.9161084574320696e-05,
158
+ "loss": 0.9785,
159
+ "step": 120
160
+ },
161
+ {
162
+ "epoch": 0.23,
163
+ "learning_rate": 1.9029265382866216e-05,
164
+ "loss": 0.9876,
165
+ "step": 125
166
+ },
167
+ {
168
+ "epoch": 0.24,
169
+ "learning_rate": 1.8888354486549238e-05,
170
+ "loss": 0.9785,
171
+ "step": 130
172
+ },
173
+ {
174
+ "epoch": 0.25,
175
+ "learning_rate": 1.873849377069785e-05,
176
+ "loss": 0.9739,
177
+ "step": 135
178
+ },
179
+ {
180
+ "epoch": 0.25,
181
+ "learning_rate": 1.8579834132349773e-05,
182
+ "loss": 0.9751,
183
+ "step": 140
184
+ },
185
+ {
186
+ "epoch": 0.26,
187
+ "learning_rate": 1.8412535328311813e-05,
188
+ "loss": 0.9923,
189
+ "step": 145
190
+ },
191
+ {
192
+ "epoch": 0.27,
193
+ "learning_rate": 1.8236765814298328e-05,
194
+ "loss": 0.9823,
195
+ "step": 150
196
+ },
197
+ {
198
+ "epoch": 0.28,
199
+ "learning_rate": 1.8052702575310588e-05,
200
+ "loss": 0.9691,
201
+ "step": 155
202
+ },
203
+ {
204
+ "epoch": 0.29,
205
+ "learning_rate": 1.7860530947427878e-05,
206
+ "loss": 0.98,
207
+ "step": 160
208
+ },
209
+ {
210
+ "epoch": 0.3,
211
+ "learning_rate": 1.766044443118978e-05,
212
+ "loss": 0.978,
213
+ "step": 165
214
+ },
215
+ {
216
+ "epoch": 0.31,
217
+ "learning_rate": 1.745264449675755e-05,
218
+ "loss": 0.9827,
219
+ "step": 170
220
+ },
221
+ {
222
+ "epoch": 0.32,
223
+ "learning_rate": 1.72373403810507e-05,
224
+ "loss": 0.9785,
225
+ "step": 175
226
+ },
227
+ {
228
+ "epoch": 0.33,
229
+ "learning_rate": 1.7014748877063212e-05,
230
+ "loss": 0.9826,
231
+ "step": 180
232
+ },
233
+ {
234
+ "epoch": 0.34,
235
+ "learning_rate": 1.6785094115571323e-05,
236
+ "loss": 0.9877,
237
+ "step": 185
238
+ },
239
+ {
240
+ "epoch": 0.34,
241
+ "learning_rate": 1.6548607339452853e-05,
242
+ "loss": 0.982,
243
+ "step": 190
244
+ },
245
+ {
246
+ "epoch": 0.35,
247
+ "learning_rate": 1.6305526670845225e-05,
248
+ "loss": 0.973,
249
+ "step": 195
250
+ },
251
+ {
252
+ "epoch": 0.36,
253
+ "learning_rate": 1.6056096871376667e-05,
254
+ "loss": 0.9737,
255
+ "step": 200
256
+ },
257
+ {
258
+ "epoch": 0.37,
259
+ "learning_rate": 1.5800569095711983e-05,
260
+ "loss": 0.9677,
261
+ "step": 205
262
+ },
263
+ {
264
+ "epoch": 0.38,
265
+ "learning_rate": 1.5539200638661106e-05,
266
+ "loss": 0.973,
267
+ "step": 210
268
+ },
269
+ {
270
+ "epoch": 0.39,
271
+ "learning_rate": 1.5272254676105026e-05,
272
+ "loss": 0.9678,
273
+ "step": 215
274
+ },
275
+ {
276
+ "epoch": 0.4,
277
+ "learning_rate": 1.5000000000000002e-05,
278
+ "loss": 0.9669,
279
+ "step": 220
280
+ },
281
+ {
282
+ "epoch": 0.41,
283
+ "learning_rate": 1.472271074772683e-05,
284
+ "loss": 0.9834,
285
+ "step": 225
286
+ },
287
+ {
288
+ "epoch": 0.42,
289
+ "learning_rate": 1.4440666126057743e-05,
290
+ "loss": 0.9625,
291
+ "step": 230
292
+ },
293
+ {
294
+ "epoch": 0.43,
295
+ "learning_rate": 1.4154150130018867e-05,
296
+ "loss": 0.9639,
297
+ "step": 235
298
+ },
299
+ {
300
+ "epoch": 0.44,
301
+ "learning_rate": 1.3863451256931286e-05,
302
+ "loss": 0.9643,
303
+ "step": 240
304
+ },
305
+ {
306
+ "epoch": 0.44,
307
+ "learning_rate": 1.356886221591872e-05,
308
+ "loss": 0.9601,
309
+ "step": 245
310
+ },
311
+ {
312
+ "epoch": 0.45,
313
+ "learning_rate": 1.3270679633174219e-05,
314
+ "loss": 0.953,
315
+ "step": 250
316
+ },
317
+ {
318
+ "epoch": 0.46,
319
+ "learning_rate": 1.296920375328275e-05,
320
+ "loss": 0.9619,
321
+ "step": 255
322
+ },
323
+ {
324
+ "epoch": 0.47,
325
+ "learning_rate": 1.266473813690035e-05,
326
+ "loss": 0.9701,
327
+ "step": 260
328
+ },
329
+ {
330
+ "epoch": 0.48,
331
+ "learning_rate": 1.2357589355094275e-05,
332
+ "loss": 0.9593,
333
+ "step": 265
334
+ },
335
+ {
336
+ "epoch": 0.49,
337
+ "learning_rate": 1.2048066680651908e-05,
338
+ "loss": 0.9559,
339
+ "step": 270
340
+ },
341
+ {
342
+ "epoch": 0.5,
343
+ "learning_rate": 1.1736481776669307e-05,
344
+ "loss": 0.9474,
345
+ "step": 275
346
+ },
347
+ {
348
+ "epoch": 0.51,
349
+ "learning_rate": 1.1423148382732854e-05,
350
+ "loss": 0.9705,
351
+ "step": 280
352
+ },
353
+ {
354
+ "epoch": 0.52,
355
+ "learning_rate": 1.1108381999010111e-05,
356
+ "loss": 0.9541,
357
+ "step": 285
358
+ },
359
+ {
360
+ "epoch": 0.53,
361
+ "learning_rate": 1.0792499568567885e-05,
362
+ "loss": 0.9464,
363
+ "step": 290
364
+ },
365
+ {
366
+ "epoch": 0.54,
367
+ "learning_rate": 1.0475819158237426e-05,
368
+ "loss": 0.9634,
369
+ "step": 295
370
+ },
371
+ {
372
+ "epoch": 0.54,
373
+ "learning_rate": 1.015865963834808e-05,
374
+ "loss": 0.9418,
375
+ "step": 300
376
+ },
377
+ {
378
+ "epoch": 0.55,
379
+ "learning_rate": 9.841340361651921e-06,
380
+ "loss": 0.9425,
381
+ "step": 305
382
+ },
383
+ {
384
+ "epoch": 0.56,
385
+ "learning_rate": 9.524180841762577e-06,
386
+ "loss": 0.945,
387
+ "step": 310
388
+ },
389
+ {
390
+ "epoch": 0.57,
391
+ "learning_rate": 9.207500431432115e-06,
392
+ "loss": 0.9463,
393
+ "step": 315
394
+ },
395
+ {
396
+ "epoch": 0.58,
397
+ "learning_rate": 8.89161800098989e-06,
398
+ "loss": 0.9514,
399
+ "step": 320
400
+ },
401
+ {
402
+ "epoch": 0.59,
403
+ "learning_rate": 8.576851617267151e-06,
404
+ "loss": 0.937,
405
+ "step": 325
406
+ },
407
+ {
408
+ "epoch": 0.6,
409
+ "learning_rate": 8.263518223330698e-06,
410
+ "loss": 0.9444,
411
+ "step": 330
412
+ },
413
+ {
414
+ "epoch": 0.61,
415
+ "learning_rate": 7.951933319348095e-06,
416
+ "loss": 0.9529,
417
+ "step": 335
418
+ },
419
+ {
420
+ "epoch": 0.62,
421
+ "learning_rate": 7.642410644905726e-06,
422
+ "loss": 0.9397,
423
+ "step": 340
424
+ },
425
+ {
426
+ "epoch": 0.63,
427
+ "learning_rate": 7.335261863099652e-06,
428
+ "loss": 0.9284,
429
+ "step": 345
430
+ },
431
+ {
432
+ "epoch": 0.64,
433
+ "learning_rate": 7.0307962467172555e-06,
434
+ "loss": 0.936,
435
+ "step": 350
436
+ },
437
+ {
438
+ "epoch": 0.64,
439
+ "learning_rate": 6.729320366825785e-06,
440
+ "loss": 0.9419,
441
+ "step": 355
442
+ },
443
+ {
444
+ "epoch": 0.65,
445
+ "learning_rate": 6.431137784081283e-06,
446
+ "loss": 0.9369,
447
+ "step": 360
448
+ },
449
+ {
450
+ "epoch": 0.66,
451
+ "learning_rate": 6.136548743068713e-06,
452
+ "loss": 0.9404,
453
+ "step": 365
454
+ },
455
+ {
456
+ "epoch": 0.67,
457
+ "learning_rate": 5.845849869981137e-06,
458
+ "loss": 0.9283,
459
+ "step": 370
460
+ },
461
+ {
462
+ "epoch": 0.68,
463
+ "learning_rate": 5.559333873942259e-06,
464
+ "loss": 0.9346,
465
+ "step": 375
466
+ },
467
+ {
468
+ "epoch": 0.69,
469
+ "learning_rate": 5.277289252273175e-06,
470
+ "loss": 0.927,
471
+ "step": 380
472
+ },
473
+ {
474
+ "epoch": 0.7,
475
+ "learning_rate": 5.000000000000003e-06,
476
+ "loss": 0.9362,
477
+ "step": 385
478
+ },
479
+ {
480
+ "epoch": 0.71,
481
+ "learning_rate": 4.727745323894976e-06,
482
+ "loss": 0.947,
483
+ "step": 390
484
+ },
485
+ {
486
+ "epoch": 0.72,
487
+ "learning_rate": 4.460799361338898e-06,
488
+ "loss": 0.9318,
489
+ "step": 395
490
+ },
491
+ {
492
+ "epoch": 0.73,
493
+ "learning_rate": 4.19943090428802e-06,
494
+ "loss": 0.924,
495
+ "step": 400
496
+ },
497
+ {
498
+ "epoch": 0.74,
499
+ "learning_rate": 3.943903128623336e-06,
500
+ "loss": 0.9372,
501
+ "step": 405
502
+ },
503
+ {
504
+ "epoch": 0.74,
505
+ "learning_rate": 3.6944733291547784e-06,
506
+ "loss": 0.9273,
507
+ "step": 410
508
+ },
509
+ {
510
+ "epoch": 0.75,
511
+ "learning_rate": 3.4513926605471504e-06,
512
+ "loss": 0.9325,
513
+ "step": 415
514
+ },
515
+ {
516
+ "epoch": 0.76,
517
+ "learning_rate": 3.2149058844286796e-06,
518
+ "loss": 0.9203,
519
+ "step": 420
520
+ },
521
+ {
522
+ "epoch": 0.77,
523
+ "learning_rate": 2.9852511229367862e-06,
524
+ "loss": 0.9248,
525
+ "step": 425
526
+ },
527
+ {
528
+ "epoch": 0.78,
529
+ "learning_rate": 2.7626596189492983e-06,
530
+ "loss": 0.9276,
531
+ "step": 430
532
+ },
533
+ {
534
+ "epoch": 0.79,
535
+ "learning_rate": 2.5473555032424534e-06,
536
+ "loss": 0.9228,
537
+ "step": 435
538
+ },
539
+ {
540
+ "epoch": 0.8,
541
+ "learning_rate": 2.339555568810221e-06,
542
+ "loss": 0.9284,
543
+ "step": 440
544
+ },
545
+ {
546
+ "epoch": 0.81,
547
+ "learning_rate": 2.1394690525721275e-06,
548
+ "loss": 0.9285,
549
+ "step": 445
550
+ },
551
+ {
552
+ "epoch": 0.82,
553
+ "learning_rate": 1.947297424689414e-06,
554
+ "loss": 0.9314,
555
+ "step": 450
556
+ },
557
+ {
558
+ "epoch": 0.83,
559
+ "learning_rate": 1.7632341857016733e-06,
560
+ "loss": 0.9163,
561
+ "step": 455
562
+ },
563
+ {
564
+ "epoch": 0.84,
565
+ "learning_rate": 1.587464671688187e-06,
566
+ "loss": 0.9263,
567
+ "step": 460
568
+ },
569
+ {
570
+ "epoch": 0.84,
571
+ "learning_rate": 1.4201658676502294e-06,
572
+ "loss": 0.9303,
573
+ "step": 465
574
+ },
575
+ {
576
+ "epoch": 0.85,
577
+ "learning_rate": 1.2615062293021508e-06,
578
+ "loss": 0.9202,
579
+ "step": 470
580
+ },
581
+ {
582
+ "epoch": 0.86,
583
+ "learning_rate": 1.1116455134507665e-06,
584
+ "loss": 0.9149,
585
+ "step": 475
586
+ },
587
+ {
588
+ "epoch": 0.87,
589
+ "learning_rate": 9.707346171337895e-07,
590
+ "loss": 0.9147,
591
+ "step": 480
592
+ },
593
+ {
594
+ "epoch": 0.88,
595
+ "learning_rate": 8.389154256793042e-07,
596
+ "loss": 0.9155,
597
+ "step": 485
598
+ },
599
+ {
600
+ "epoch": 0.89,
601
+ "learning_rate": 7.163206698392744e-07,
602
+ "loss": 0.9227,
603
+ "step": 490
604
+ },
605
+ {
606
+ "epoch": 0.9,
607
+ "learning_rate": 6.030737921409169e-07,
608
+ "loss": 0.9236,
609
+ "step": 495
610
+ },
611
+ {
612
+ "epoch": 0.91,
613
+ "learning_rate": 4.992888225905467e-07,
614
+ "loss": 0.9196,
615
+ "step": 500
616
+ },
617
+ {
618
+ "epoch": 0.92,
619
+ "learning_rate": 4.0507026385502747e-07,
620
+ "loss": 0.928,
621
+ "step": 505
622
+ },
623
+ {
624
+ "epoch": 0.93,
625
+ "learning_rate": 3.2051298603643754e-07,
626
+ "loss": 0.9164,
627
+ "step": 510
628
+ },
629
+ {
630
+ "epoch": 0.94,
631
+ "learning_rate": 2.4570213114592957e-07,
632
+ "loss": 0.9266,
633
+ "step": 515
634
+ },
635
+ {
636
+ "epoch": 0.94,
637
+ "learning_rate": 1.8071302737293294e-07,
638
+ "loss": 0.9243,
639
+ "step": 520
640
+ },
641
+ {
642
+ "epoch": 0.95,
643
+ "learning_rate": 1.2561111323605714e-07,
644
+ "loss": 0.9185,
645
+ "step": 525
646
+ },
647
+ {
648
+ "epoch": 0.96,
649
+ "learning_rate": 8.04518716920466e-08,
650
+ "loss": 0.9124,
651
+ "step": 530
652
+ },
653
+ {
654
+ "epoch": 0.97,
655
+ "learning_rate": 4.528077426915412e-08,
656
+ "loss": 0.9208,
657
+ "step": 535
658
+ },
659
+ {
660
+ "epoch": 0.98,
661
+ "learning_rate": 2.013323528115674e-08,
662
+ "loss": 0.9314,
663
+ "step": 540
664
+ },
665
+ {
666
+ "epoch": 0.99,
667
+ "learning_rate": 5.034576168149175e-09,
668
+ "loss": 0.9243,
669
+ "step": 545
670
+ },
671
+ {
672
+ "epoch": 1.0,
673
+ "learning_rate": 0.0,
674
+ "loss": 0.9241,
675
+ "step": 550
676
+ },
677
+ {
678
+ "epoch": 1.0,
679
+ "eval_loss": 0.9343938231468201,
680
+ "eval_runtime": 144.3354,
681
+ "eval_samples_per_second": 107.479,
682
+ "eval_steps_per_second": 1.684,
683
+ "step": 550
684
+ },
685
+ {
686
+ "epoch": 1.0,
687
+ "step": 550,
688
+ "total_flos": 460425862840320.0,
689
+ "train_loss": 0.9703456902503967,
690
+ "train_runtime": 5589.9273,
691
+ "train_samples_per_second": 25.215,
692
+ "train_steps_per_second": 0.098
693
+ }
694
+ ],
695
+ "logging_steps": 5,
696
+ "max_steps": 550,
697
+ "num_input_tokens_seen": 0,
698
+ "num_train_epochs": 1,
699
+ "save_steps": 100,
700
+ "total_flos": 460425862840320.0,
701
+ "train_batch_size": 8,
702
+ "trial_name": null,
703
+ "trial_params": null
704
+ }