statking commited on
Commit
90e3ff5
1 Parent(s): 5b5fb94

Model save

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-full
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-full
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: 0.9366
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: 16
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 8
47
+ - total_train_batch_size: 128
48
+ - total_eval_batch_size: 64
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.9201 | 1.0 | 1090 | 0.9366 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.40.2
64
+ - Pytorch 2.1.0a0+32f93b1
65
+ - Datasets 2.19.1
66
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 456447649382400.0,
4
+ "train_loss": 0.9783915571116526,
5
+ "train_runtime": 14076.1137,
6
+ "train_samples": 207864,
7
+ "train_samples_per_second": 9.905,
8
+ "train_steps_per_second": 0.077
9
+ }
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": "4.40.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eecdc50fe0e20df05eb75e44a0d0dcbeefa3c855818f71ed6df3b9ef5a97dca
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b96e2617e884baf2fcbf54145651c12b30a5f2bc8be12c20e9528dfcd9ae6c
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c4ca66dec6b94f8611b692dd2133896c87fb9fb2a099cbe19ad5ca9f3b7a17
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
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 456447649382400.0,
4
+ "train_loss": 0.9783915571116526,
5
+ "train_runtime": 14076.1137,
6
+ "train_samples": 207864,
7
+ "train_samples_per_second": 9.905,
8
+ "train_steps_per_second": 0.077
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1571 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1090,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0009174311926605505,
13
+ "grad_norm": 8.590026968869019,
14
+ "learning_rate": 1.8348623853211012e-07,
15
+ "loss": 1.1365,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0045871559633027525,
20
+ "grad_norm": 7.486574820466339,
21
+ "learning_rate": 9.174311926605506e-07,
22
+ "loss": 1.1311,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.009174311926605505,
27
+ "grad_norm": 4.039589713379416,
28
+ "learning_rate": 1.8348623853211011e-06,
29
+ "loss": 1.0455,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.013761467889908258,
34
+ "grad_norm": 3.7172848594571635,
35
+ "learning_rate": 2.7522935779816517e-06,
36
+ "loss": 1.0276,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.01834862385321101,
41
+ "grad_norm": 2.6728393178954097,
42
+ "learning_rate": 3.6697247706422022e-06,
43
+ "loss": 0.9965,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.022935779816513763,
48
+ "grad_norm": 2.1111759195076383,
49
+ "learning_rate": 4.587155963302753e-06,
50
+ "loss": 0.9946,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.027522935779816515,
55
+ "grad_norm": 2.2065873188991474,
56
+ "learning_rate": 5.504587155963303e-06,
57
+ "loss": 0.9918,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.03211009174311927,
62
+ "grad_norm": 2.3927751227272838,
63
+ "learning_rate": 6.422018348623854e-06,
64
+ "loss": 0.9876,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.03669724770642202,
69
+ "grad_norm": 2.198198830881205,
70
+ "learning_rate": 7.3394495412844045e-06,
71
+ "loss": 0.9949,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.04128440366972477,
76
+ "grad_norm": 2.3775388175981913,
77
+ "learning_rate": 8.256880733944956e-06,
78
+ "loss": 0.9785,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.045871559633027525,
83
+ "grad_norm": 2.3636192230061694,
84
+ "learning_rate": 9.174311926605506e-06,
85
+ "loss": 0.9851,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.05045871559633028,
90
+ "grad_norm": 2.551773091121245,
91
+ "learning_rate": 1.0091743119266055e-05,
92
+ "loss": 0.9935,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.05504587155963303,
97
+ "grad_norm": 2.075016097277958,
98
+ "learning_rate": 1.1009174311926607e-05,
99
+ "loss": 0.9969,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.05963302752293578,
104
+ "grad_norm": 2.288649040057403,
105
+ "learning_rate": 1.1926605504587156e-05,
106
+ "loss": 0.98,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.06422018348623854,
111
+ "grad_norm": 2.7581294894600163,
112
+ "learning_rate": 1.2844036697247708e-05,
113
+ "loss": 0.9864,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.06880733944954129,
118
+ "grad_norm": 2.727748671508115,
119
+ "learning_rate": 1.3761467889908258e-05,
120
+ "loss": 0.9998,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.07339449541284404,
125
+ "grad_norm": 2.513424527269286,
126
+ "learning_rate": 1.4678899082568809e-05,
127
+ "loss": 0.9892,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.0779816513761468,
132
+ "grad_norm": 2.0479456147390644,
133
+ "learning_rate": 1.559633027522936e-05,
134
+ "loss": 0.9927,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.08256880733944955,
139
+ "grad_norm": 2.0867568861039487,
140
+ "learning_rate": 1.6513761467889912e-05,
141
+ "loss": 1.0121,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.0871559633027523,
146
+ "grad_norm": 2.8827900604302603,
147
+ "learning_rate": 1.743119266055046e-05,
148
+ "loss": 1.0201,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.09174311926605505,
153
+ "grad_norm": 2.0709329055230112,
154
+ "learning_rate": 1.834862385321101e-05,
155
+ "loss": 0.996,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.0963302752293578,
160
+ "grad_norm": 2.5702081185928103,
161
+ "learning_rate": 1.9266055045871563e-05,
162
+ "loss": 1.0116,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.10091743119266056,
167
+ "grad_norm": 2.1947935409816486,
168
+ "learning_rate": 1.999994872196626e-05,
169
+ "loss": 1.0224,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.10550458715596331,
174
+ "grad_norm": 1.9964111903602946,
175
+ "learning_rate": 1.9998154046002822e-05,
176
+ "loss": 1.0057,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.11009174311926606,
181
+ "grad_norm": 1.8945144621768437,
182
+ "learning_rate": 1.999379599421534e-05,
183
+ "loss": 1.0062,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.11467889908256881,
188
+ "grad_norm": 1.8242468916557006,
189
+ "learning_rate": 1.9986875683942535e-05,
190
+ "loss": 1.0154,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.11926605504587157,
195
+ "grad_norm": 1.8529020549594846,
196
+ "learning_rate": 1.9977394889447526e-05,
197
+ "loss": 1.0127,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.12385321100917432,
202
+ "grad_norm": 1.8387109925666045,
203
+ "learning_rate": 1.9965356041462954e-05,
204
+ "loss": 0.9942,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.12844036697247707,
209
+ "grad_norm": 2.0279915275712623,
210
+ "learning_rate": 1.9950762226567783e-05,
211
+ "loss": 1.0222,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.13302752293577982,
216
+ "grad_norm": 2.1108737110478994,
217
+ "learning_rate": 1.9933617186395917e-05,
218
+ "loss": 1.0291,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.13761467889908258,
223
+ "grad_norm": 2.1293431381675427,
224
+ "learning_rate": 1.9913925316676946e-05,
225
+ "loss": 1.0215,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.14220183486238533,
230
+ "grad_norm": 1.9622943928954406,
231
+ "learning_rate": 1.9891691666109112e-05,
232
+ "loss": 1.0447,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.14678899082568808,
237
+ "grad_norm": 1.9552108684711231,
238
+ "learning_rate": 1.9866921935064907e-05,
239
+ "loss": 1.034,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.15137614678899083,
244
+ "grad_norm": 1.9190740305620202,
245
+ "learning_rate": 1.9839622474129595e-05,
246
+ "loss": 1.0446,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.1559633027522936,
251
+ "grad_norm": 1.8020873014525902,
252
+ "learning_rate": 1.9809800282473014e-05,
253
+ "loss": 1.0322,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.16055045871559634,
258
+ "grad_norm": 1.6996799547703936,
259
+ "learning_rate": 1.977746300605507e-05,
260
+ "loss": 1.0383,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.1651376146788991,
265
+ "grad_norm": 2.187092931511103,
266
+ "learning_rate": 1.9742618935665478e-05,
267
+ "loss": 1.0294,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.16972477064220184,
272
+ "grad_norm": 2.0403921365189963,
273
+ "learning_rate": 1.9705277004798072e-05,
274
+ "loss": 1.0349,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.1743119266055046,
279
+ "grad_norm": 1.8496031208738504,
280
+ "learning_rate": 1.9665446787360444e-05,
281
+ "loss": 1.0404,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.17889908256880735,
286
+ "grad_norm": 1.8823992627267585,
287
+ "learning_rate": 1.9623138495219292e-05,
288
+ "loss": 1.0209,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.1834862385321101,
293
+ "grad_norm": 2.095822495179804,
294
+ "learning_rate": 1.957836297558229e-05,
295
+ "loss": 1.0222,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.18807339449541285,
300
+ "grad_norm": 2.4911998482939355,
301
+ "learning_rate": 1.9531131708217005e-05,
302
+ "loss": 1.027,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.1926605504587156,
307
+ "grad_norm": 1.821496874433616,
308
+ "learning_rate": 1.948145680250766e-05,
309
+ "loss": 1.0231,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.19724770642201836,
314
+ "grad_norm": 1.759877910585677,
315
+ "learning_rate": 1.9429350994350483e-05,
316
+ "loss": 1.0345,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2018348623853211,
321
+ "grad_norm": 1.8748142613908458,
322
+ "learning_rate": 1.93748276428884e-05,
323
+ "loss": 1.0408,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.20642201834862386,
328
+ "grad_norm": 2.0102856321068514,
329
+ "learning_rate": 1.931790072708596e-05,
330
+ "loss": 1.0245,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.21100917431192662,
335
+ "grad_norm": 1.8044235525523873,
336
+ "learning_rate": 1.9258584842145342e-05,
337
+ "loss": 1.0434,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.21559633027522937,
342
+ "grad_norm": 2.1107770756344193,
343
+ "learning_rate": 1.9196895195764363e-05,
344
+ "loss": 1.0216,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.22018348623853212,
349
+ "grad_norm": 1.7741183736117787,
350
+ "learning_rate": 1.913284760423745e-05,
351
+ "loss": 1.0259,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.22477064220183487,
356
+ "grad_norm": 1.8121132100517001,
357
+ "learning_rate": 1.9066458488400586e-05,
358
+ "loss": 1.0249,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.22935779816513763,
363
+ "grad_norm": 1.6374262690884738,
364
+ "learning_rate": 1.8997744869421248e-05,
365
+ "loss": 1.02,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.23394495412844038,
370
+ "grad_norm": 1.7269378718345392,
371
+ "learning_rate": 1.8926724364434447e-05,
372
+ "loss": 1.013,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.23853211009174313,
377
+ "grad_norm": 1.7554961488227134,
378
+ "learning_rate": 1.8853415182025953e-05,
379
+ "loss": 1.0275,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.24311926605504589,
384
+ "grad_norm": 1.888907283355598,
385
+ "learning_rate": 1.8777836117563894e-05,
386
+ "loss": 1.0307,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.24770642201834864,
391
+ "grad_norm": 1.6943826060007061,
392
+ "learning_rate": 1.8700006548379898e-05,
393
+ "loss": 1.021,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.25229357798165136,
398
+ "grad_norm": 1.622531543885841,
399
+ "learning_rate": 1.861994642880105e-05,
400
+ "loss": 1.0392,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.25688073394495414,
405
+ "grad_norm": 1.5095301144772582,
406
+ "learning_rate": 1.8537676285033886e-05,
407
+ "loss": 1.0279,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.26146788990825687,
412
+ "grad_norm": 1.6417056350190902,
413
+ "learning_rate": 1.845321720990181e-05,
414
+ "loss": 1.0296,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.26605504587155965,
419
+ "grad_norm": 1.5722941630740008,
420
+ "learning_rate": 1.8366590857437182e-05,
421
+ "loss": 1.0334,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.2706422018348624,
426
+ "grad_norm": 1.8638842301102823,
427
+ "learning_rate": 1.8277819437329577e-05,
428
+ "loss": 1.0215,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.27522935779816515,
433
+ "grad_norm": 1.63281187814375,
434
+ "learning_rate": 1.8186925709231534e-05,
435
+ "loss": 1.0341,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.2798165137614679,
440
+ "grad_norm": 1.661078648257904,
441
+ "learning_rate": 1.809393297692334e-05,
442
+ "loss": 1.0246,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.28440366972477066,
447
+ "grad_norm": 1.7482598431925447,
448
+ "learning_rate": 1.799886508233829e-05,
449
+ "loss": 1.0442,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.2889908256880734,
454
+ "grad_norm": 1.577636868272626,
455
+ "learning_rate": 1.790174639944997e-05,
456
+ "loss": 1.0369,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.29357798165137616,
461
+ "grad_norm": 1.7044142589762405,
462
+ "learning_rate": 1.780260182802314e-05,
463
+ "loss": 1.0239,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.2981651376146789,
468
+ "grad_norm": 1.7546359102106406,
469
+ "learning_rate": 1.7701456787229805e-05,
470
+ "loss": 1.0327,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.30275229357798167,
475
+ "grad_norm": 1.5039111648273473,
476
+ "learning_rate": 1.7598337209132142e-05,
477
+ "loss": 1.0157,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.3073394495412844,
482
+ "grad_norm": 1.6602442070381076,
483
+ "learning_rate": 1.7493269532033882e-05,
484
+ "loss": 1.0182,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.3119266055045872,
489
+ "grad_norm": 1.53831993823906,
490
+ "learning_rate": 1.738628069370195e-05,
491
+ "loss": 1.029,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.3165137614678899,
496
+ "grad_norm": 1.6805290811393307,
497
+ "learning_rate": 1.7277398124460022e-05,
498
+ "loss": 1.0235,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.3211009174311927,
503
+ "grad_norm": 1.4853849203076779,
504
+ "learning_rate": 1.71666497401558e-05,
505
+ "loss": 0.9925,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.3256880733944954,
510
+ "grad_norm": 1.672232887496304,
511
+ "learning_rate": 1.7054063935003813e-05,
512
+ "loss": 1.0252,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.3302752293577982,
517
+ "grad_norm": 1.6345254123456943,
518
+ "learning_rate": 1.6939669574305565e-05,
519
+ "loss": 1.0085,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.3348623853211009,
524
+ "grad_norm": 1.5262133900432817,
525
+ "learning_rate": 1.6823495987048922e-05,
526
+ "loss": 1.0105,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.3394495412844037,
531
+ "grad_norm": 1.5242935487304878,
532
+ "learning_rate": 1.6705572958388576e-05,
533
+ "loss": 1.0108,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.3440366972477064,
538
+ "grad_norm": 1.6718301781389493,
539
+ "learning_rate": 1.6585930722009602e-05,
540
+ "loss": 1.0347,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.3486238532110092,
545
+ "grad_norm": 1.4913729762956598,
546
+ "learning_rate": 1.6464599952375998e-05,
547
+ "loss": 1.0232,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.3532110091743119,
552
+ "grad_norm": 1.5351597927925422,
553
+ "learning_rate": 1.63416117568662e-05,
554
+ "loss": 1.0177,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.3577981651376147,
559
+ "grad_norm": 1.5623411713080309,
560
+ "learning_rate": 1.621699766779763e-05,
561
+ "loss": 1.0144,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.3623853211009174,
566
+ "grad_norm": 1.4434170639068806,
567
+ "learning_rate": 1.6090789634342278e-05,
568
+ "loss": 1.005,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.3669724770642202,
573
+ "grad_norm": 1.524722181019825,
574
+ "learning_rate": 1.5963020014335437e-05,
575
+ "loss": 1.0134,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.37155963302752293,
580
+ "grad_norm": 1.5856120759168468,
581
+ "learning_rate": 1.583372156597961e-05,
582
+ "loss": 1.0059,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.3761467889908257,
587
+ "grad_norm": 1.4415082474651109,
588
+ "learning_rate": 1.570292743944583e-05,
589
+ "loss": 1.0029,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.38073394495412843,
594
+ "grad_norm": 1.4260675517472883,
595
+ "learning_rate": 1.557067116837444e-05,
596
+ "loss": 1.0219,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.3853211009174312,
601
+ "grad_norm": 1.468487983706826,
602
+ "learning_rate": 1.5436986661277578e-05,
603
+ "loss": 1.013,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.38990825688073394,
608
+ "grad_norm": 1.5254325276571765,
609
+ "learning_rate": 1.530190819284555e-05,
610
+ "loss": 1.0034,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.3944954128440367,
615
+ "grad_norm": 1.5798795100356116,
616
+ "learning_rate": 1.5165470395159314e-05,
617
+ "loss": 1.0332,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.39908256880733944,
622
+ "grad_norm": 1.552200364694848,
623
+ "learning_rate": 1.5027708248811331e-05,
624
+ "loss": 1.0007,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.4036697247706422,
629
+ "grad_norm": 1.4214931631494656,
630
+ "learning_rate": 1.4888657073937077e-05,
631
+ "loss": 1.0094,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.40825688073394495,
636
+ "grad_norm": 1.4843255397237436,
637
+ "learning_rate": 1.4748352521159492e-05,
638
+ "loss": 0.9961,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.41284403669724773,
643
+ "grad_norm": 1.4632988494224077,
644
+ "learning_rate": 1.4606830562448692e-05,
645
+ "loss": 1.0058,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.41743119266055045,
650
+ "grad_norm": 1.4953822979383466,
651
+ "learning_rate": 1.4464127481899312e-05,
652
+ "loss": 1.008,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.42201834862385323,
657
+ "grad_norm": 1.4559315828564945,
658
+ "learning_rate": 1.4320279866427798e-05,
659
+ "loss": 1.0065,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.42660550458715596,
664
+ "grad_norm": 1.6922761610390848,
665
+ "learning_rate": 1.4175324596392075e-05,
666
+ "loss": 1.0205,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.43119266055045874,
671
+ "grad_norm": 1.590358388704108,
672
+ "learning_rate": 1.402929883613599e-05,
673
+ "loss": 1.0069,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.43577981651376146,
678
+ "grad_norm": 1.4546641964451503,
679
+ "learning_rate": 1.3882240024460928e-05,
680
+ "loss": 0.9926,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.44036697247706424,
685
+ "grad_norm": 1.4097757101446433,
686
+ "learning_rate": 1.3734185865027061e-05,
687
+ "loss": 1.0109,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.44495412844036697,
692
+ "grad_norm": 1.4718695959287078,
693
+ "learning_rate": 1.358517431668672e-05,
694
+ "loss": 0.9992,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.44954128440366975,
699
+ "grad_norm": 1.3849859496158945,
700
+ "learning_rate": 1.3435243583752294e-05,
701
+ "loss": 0.9943,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.4541284403669725,
706
+ "grad_norm": 1.4115509115184626,
707
+ "learning_rate": 1.3284432106201233e-05,
708
+ "loss": 0.9882,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.45871559633027525,
713
+ "grad_norm": 1.541052954984908,
714
+ "learning_rate": 1.313277854982062e-05,
715
+ "loss": 1.0081,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.463302752293578,
720
+ "grad_norm": 1.6604691549617376,
721
+ "learning_rate": 1.2980321796293838e-05,
722
+ "loss": 0.9893,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.46788990825688076,
727
+ "grad_norm": 1.5419924069079967,
728
+ "learning_rate": 1.2827100933231904e-05,
729
+ "loss": 1.005,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.4724770642201835,
734
+ "grad_norm": 1.5391926952486923,
735
+ "learning_rate": 1.2673155244151985e-05,
736
+ "loss": 1.0106,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.47706422018348627,
741
+ "grad_norm": 1.5041092670535134,
742
+ "learning_rate": 1.2518524198405699e-05,
743
+ "loss": 0.9993,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.481651376146789,
748
+ "grad_norm": 1.5768343545674215,
749
+ "learning_rate": 1.2363247441059775e-05,
750
+ "loss": 0.9841,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.48623853211009177,
755
+ "grad_norm": 1.4584802149012241,
756
+ "learning_rate": 1.2207364782731657e-05,
757
+ "loss": 1.0082,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.4908256880733945,
762
+ "grad_norm": 1.428960359443167,
763
+ "learning_rate": 1.2050916189382646e-05,
764
+ "loss": 0.9731,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.4954128440366973,
769
+ "grad_norm": 1.4606267386566858,
770
+ "learning_rate": 1.189394177207125e-05,
771
+ "loss": 0.9795,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.5,
776
+ "grad_norm": 1.376913229782971,
777
+ "learning_rate": 1.1736481776669307e-05,
778
+ "loss": 0.9881,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.5045871559633027,
783
+ "grad_norm": 1.3836549478959417,
784
+ "learning_rate": 1.1578576573543541e-05,
785
+ "loss": 0.9641,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.5091743119266054,
790
+ "grad_norm": 1.356149707622323,
791
+ "learning_rate": 1.1420266647205232e-05,
792
+ "loss": 0.9744,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.5137614678899083,
797
+ "grad_norm": 1.3827419350659662,
798
+ "learning_rate": 1.1261592585930576e-05,
799
+ "loss": 0.9839,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.518348623853211,
804
+ "grad_norm": 1.4379779871173162,
805
+ "learning_rate": 1.1102595071354471e-05,
806
+ "loss": 0.9851,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.5229357798165137,
811
+ "grad_norm": 1.399288614224523,
812
+ "learning_rate": 1.0943314868040365e-05,
813
+ "loss": 0.9781,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.5275229357798165,
818
+ "grad_norm": 1.4412830988024221,
819
+ "learning_rate": 1.0783792813028828e-05,
820
+ "loss": 0.9881,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.5321100917431193,
825
+ "grad_norm": 1.365677938278276,
826
+ "learning_rate": 1.0624069805367558e-05,
827
+ "loss": 0.9696,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.536697247706422,
832
+ "grad_norm": 1.3825640573901334,
833
+ "learning_rate": 1.0464186795625481e-05,
834
+ "loss": 0.9726,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.5412844036697247,
839
+ "grad_norm": 1.4955792558472396,
840
+ "learning_rate": 1.0304184775393642e-05,
841
+ "loss": 0.9874,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.5458715596330275,
846
+ "grad_norm": 1.3824032912359923,
847
+ "learning_rate": 1.0144104766775574e-05,
848
+ "loss": 0.9695,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.5504587155963303,
853
+ "grad_norm": 1.3477277386187514,
854
+ "learning_rate": 9.983987811869863e-06,
855
+ "loss": 0.9617,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.555045871559633,
860
+ "grad_norm": 1.4036097176796005,
861
+ "learning_rate": 9.823874962247565e-06,
862
+ "loss": 0.9847,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.5596330275229358,
867
+ "grad_norm": 1.4536087002525018,
868
+ "learning_rate": 9.663807268427197e-06,
869
+ "loss": 0.9493,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.5642201834862385,
874
+ "grad_norm": 1.3938810806635806,
875
+ "learning_rate": 9.503825769350016e-06,
876
+ "loss": 0.9759,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.5688073394495413,
881
+ "grad_norm": 1.4313464690072646,
882
+ "learning_rate": 9.343971481858246e-06,
883
+ "loss": 0.9718,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.573394495412844,
888
+ "grad_norm": 1.3483789746433568,
889
+ "learning_rate": 9.184285390178978e-06,
890
+ "loss": 0.9685,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.5779816513761468,
895
+ "grad_norm": 1.3437326617499212,
896
+ "learning_rate": 9.024808435416435e-06,
897
+ "loss": 0.9565,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.5825688073394495,
902
+ "grad_norm": 1.3899537082883675,
903
+ "learning_rate": 8.865581505055292e-06,
904
+ "loss": 0.966,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.5871559633027523,
909
+ "grad_norm": 1.4049970453901013,
910
+ "learning_rate": 8.706645422477739e-06,
911
+ "loss": 0.9609,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.591743119266055,
916
+ "grad_norm": 1.563627127558928,
917
+ "learning_rate": 8.548040936496989e-06,
918
+ "loss": 0.9669,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.5963302752293578,
923
+ "grad_norm": 1.4175659667522775,
924
+ "learning_rate": 8.389808710909881e-06,
925
+ "loss": 0.969,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.6009174311926605,
930
+ "grad_norm": 1.3887375134393394,
931
+ "learning_rate": 8.231989314071318e-06,
932
+ "loss": 0.9672,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.6055045871559633,
937
+ "grad_norm": 1.3886857636850283,
938
+ "learning_rate": 8.07462320849313e-06,
939
+ "loss": 0.9825,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.6100917431192661,
944
+ "grad_norm": 1.3852031395838529,
945
+ "learning_rate": 7.917750740470116e-06,
946
+ "loss": 0.9612,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.6146788990825688,
951
+ "grad_norm": 1.3564902677213335,
952
+ "learning_rate": 7.761412129735853e-06,
953
+ "loss": 0.9606,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.6192660550458715,
958
+ "grad_norm": 1.364640541839942,
959
+ "learning_rate": 7.605647459150961e-06,
960
+ "loss": 0.9699,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.6238532110091743,
965
+ "grad_norm": 1.3628791024834306,
966
+ "learning_rate": 7.4504966644264775e-06,
967
+ "loss": 0.9499,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.6284403669724771,
972
+ "grad_norm": 1.3160716541619537,
973
+ "learning_rate": 7.295999523884921e-06,
974
+ "loss": 0.9605,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.6330275229357798,
979
+ "grad_norm": 1.3601615038063317,
980
+ "learning_rate": 7.142195648261747e-06,
981
+ "loss": 0.9712,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.6376146788990825,
986
+ "grad_norm": 1.3879140081588965,
987
+ "learning_rate": 6.989124470549746e-06,
988
+ "loss": 0.9397,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.6422018348623854,
993
+ "grad_norm": 1.3184740100520171,
994
+ "learning_rate": 6.83682523588902e-06,
995
+ "loss": 0.9636,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.6467889908256881,
1000
+ "grad_norm": 1.3571390496693267,
1001
+ "learning_rate": 6.685336991505122e-06,
1002
+ "loss": 0.9661,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.6513761467889908,
1007
+ "grad_norm": 1.306435428954974,
1008
+ "learning_rate": 6.5346985766979384e-06,
1009
+ "loss": 0.9546,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.6559633027522935,
1014
+ "grad_norm": 1.3143087769244612,
1015
+ "learning_rate": 6.384948612883872e-06,
1016
+ "loss": 0.9599,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.6605504587155964,
1021
+ "grad_norm": 1.2717322661805426,
1022
+ "learning_rate": 6.2361254936939e-06,
1023
+ "loss": 0.9589,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.6651376146788991,
1028
+ "grad_norm": 1.304695248009233,
1029
+ "learning_rate": 6.0882673751300235e-06,
1030
+ "loss": 0.9477,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.6697247706422018,
1035
+ "grad_norm": 1.3414217532090449,
1036
+ "learning_rate": 5.941412165782645e-06,
1037
+ "loss": 0.9568,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.6743119266055045,
1042
+ "grad_norm": 1.4013089394139884,
1043
+ "learning_rate": 5.79559751711138e-06,
1044
+ "loss": 0.9482,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.6788990825688074,
1049
+ "grad_norm": 1.3044699444068533,
1050
+ "learning_rate": 5.650860813791786e-06,
1051
+ "loss": 0.9486,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.6834862385321101,
1056
+ "grad_norm": 1.3828781502865561,
1057
+ "learning_rate": 5.507239164130501e-06,
1058
+ "loss": 0.9489,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.6880733944954128,
1063
+ "grad_norm": 1.3314126321208273,
1064
+ "learning_rate": 5.364769390551225e-06,
1065
+ "loss": 0.969,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.6926605504587156,
1070
+ "grad_norm": 1.2942289271606044,
1071
+ "learning_rate": 5.223488020154028e-06,
1072
+ "loss": 0.96,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.6972477064220184,
1077
+ "grad_norm": 1.3357321457662634,
1078
+ "learning_rate": 5.083431275350312e-06,
1079
+ "loss": 0.9258,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.7018348623853211,
1084
+ "grad_norm": 1.3041211686044023,
1085
+ "learning_rate": 4.9446350645759885e-06,
1086
+ "loss": 0.9417,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.7064220183486238,
1091
+ "grad_norm": 1.380479241153724,
1092
+ "learning_rate": 4.807134973085036e-06,
1093
+ "loss": 0.9666,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.7110091743119266,
1098
+ "grad_norm": 1.2413378517127889,
1099
+ "learning_rate": 4.670966253826027e-06,
1100
+ "loss": 0.9352,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.7155963302752294,
1105
+ "grad_norm": 1.4796267075105034,
1106
+ "learning_rate": 4.53616381840377e-06,
1107
+ "loss": 0.9473,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.7201834862385321,
1112
+ "grad_norm": 1.3651275142718018,
1113
+ "learning_rate": 4.402762228128531e-06,
1114
+ "loss": 0.9392,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.7247706422018348,
1119
+ "grad_norm": 1.4100087288923597,
1120
+ "learning_rate": 4.270795685155001e-06,
1121
+ "loss": 0.9478,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.7293577981651376,
1126
+ "grad_norm": 1.3017707707123873,
1127
+ "learning_rate": 4.140298023713416e-06,
1128
+ "loss": 0.9301,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.7339449541284404,
1133
+ "grad_norm": 1.3267041246218492,
1134
+ "learning_rate": 4.0113027014349374e-06,
1135
+ "loss": 0.9146,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.7385321100917431,
1140
+ "grad_norm": 1.2995509569521342,
1141
+ "learning_rate": 3.883842790773647e-06,
1142
+ "loss": 0.9573,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.7431192660550459,
1147
+ "grad_norm": 1.2910745261862546,
1148
+ "learning_rate": 3.757950970527249e-06,
1149
+ "loss": 0.9265,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.7477064220183486,
1154
+ "grad_norm": 1.2853989305550235,
1155
+ "learning_rate": 3.633659517458736e-06,
1156
+ "loss": 0.9248,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.7522935779816514,
1161
+ "grad_norm": 1.263114329710996,
1162
+ "learning_rate": 3.511000298021098e-06,
1163
+ "loss": 0.9231,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.7568807339449541,
1168
+ "grad_norm": 1.3202969619364027,
1169
+ "learning_rate": 3.39000476018726e-06,
1170
+ "loss": 0.9265,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.7614678899082569,
1175
+ "grad_norm": 1.2837511661684693,
1176
+ "learning_rate": 3.2707039253872796e-06,
1177
+ "loss": 0.9238,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.7660550458715596,
1182
+ "grad_norm": 1.272334565345566,
1183
+ "learning_rate": 3.153128380554941e-06,
1184
+ "loss": 0.9318,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.7706422018348624,
1189
+ "grad_norm": 1.2911962822321414,
1190
+ "learning_rate": 3.037308270285709e-06,
1191
+ "loss": 0.9229,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.7752293577981652,
1196
+ "grad_norm": 1.2871010544124712,
1197
+ "learning_rate": 2.923273289108115e-06,
1198
+ "loss": 0.9409,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.7798165137614679,
1203
+ "grad_norm": 1.2957020048675643,
1204
+ "learning_rate": 2.8110526738705345e-06,
1205
+ "loss": 0.9243,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.7844036697247706,
1210
+ "grad_norm": 1.291643068745679,
1211
+ "learning_rate": 2.700675196245288e-06,
1212
+ "loss": 0.9396,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.7889908256880734,
1217
+ "grad_norm": 1.2442630476677876,
1218
+ "learning_rate": 2.592169155352031e-06,
1219
+ "loss": 0.9416,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.7935779816513762,
1224
+ "grad_norm": 1.2808835563133167,
1225
+ "learning_rate": 2.485562370502279e-06,
1226
+ "loss": 0.9428,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.7981651376146789,
1231
+ "grad_norm": 1.322945652372357,
1232
+ "learning_rate": 2.3808821740669608e-06,
1233
+ "loss": 0.9358,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.8027522935779816,
1238
+ "grad_norm": 1.3273655469543255,
1239
+ "learning_rate": 2.2781554044688015e-06,
1240
+ "loss": 0.9379,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.8073394495412844,
1245
+ "grad_norm": 1.2953684297066224,
1246
+ "learning_rate": 2.1774083993013715e-06,
1247
+ "loss": 0.935,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.8119266055045872,
1252
+ "grad_norm": 1.314047012294258,
1253
+ "learning_rate": 2.0786669885765044e-06,
1254
+ "loss": 0.9273,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.8165137614678899,
1259
+ "grad_norm": 1.2910450886812495,
1260
+ "learning_rate": 1.981956488101898e-06,
1261
+ "loss": 0.9406,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.8211009174311926,
1266
+ "grad_norm": 1.2889304700514808,
1267
+ "learning_rate": 1.8873016929904942e-06,
1268
+ "loss": 0.9423,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.8256880733944955,
1273
+ "grad_norm": 1.2584483146134866,
1274
+ "learning_rate": 1.7947268713034128e-06,
1275
+ "loss": 0.9119,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.8302752293577982,
1280
+ "grad_norm": 1.2306571475976114,
1281
+ "learning_rate": 1.704255757827963e-06,
1282
+ "loss": 0.9147,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.8348623853211009,
1287
+ "grad_norm": 1.2996923914258511,
1288
+ "learning_rate": 1.6159115479924259e-06,
1289
+ "loss": 0.9309,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.8394495412844036,
1294
+ "grad_norm": 1.3030591756269578,
1295
+ "learning_rate": 1.529716891919074e-06,
1296
+ "loss": 0.9393,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.8440366972477065,
1301
+ "grad_norm": 1.289888704070606,
1302
+ "learning_rate": 1.4456938886170413e-06,
1303
+ "loss": 0.9106,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.8486238532110092,
1308
+ "grad_norm": 1.3368041078863482,
1309
+ "learning_rate": 1.3638640803164516e-06,
1310
+ "loss": 0.9242,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.8532110091743119,
1315
+ "grad_norm": 1.2917360929177786,
1316
+ "learning_rate": 1.2842484469453365e-06,
1317
+ "loss": 0.9143,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.8577981651376146,
1322
+ "grad_norm": 1.2939657342934223,
1323
+ "learning_rate": 1.2068674007506787e-06,
1324
+ "loss": 0.9286,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.8623853211009175,
1329
+ "grad_norm": 1.3560403644461199,
1330
+ "learning_rate": 1.1317407810650372e-06,
1331
+ "loss": 0.9264,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.8669724770642202,
1336
+ "grad_norm": 1.2478045531537327,
1337
+ "learning_rate": 1.0588878492200261e-06,
1338
+ "loss": 0.9319,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.8715596330275229,
1343
+ "grad_norm": 1.2774964714280372,
1344
+ "learning_rate": 9.883272836080116e-07,
1345
+ "loss": 0.9195,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 0.8761467889908257,
1350
+ "grad_norm": 1.2810847178825988,
1351
+ "learning_rate": 9.200771748932513e-07,
1352
+ "loss": 0.9327,
1353
+ "step": 955
1354
+ },
1355
+ {
1356
+ "epoch": 0.8807339449541285,
1357
+ "grad_norm": 1.300184919031024,
1358
+ "learning_rate": 8.541550213737171e-07,
1359
+ "loss": 0.9115,
1360
+ "step": 960
1361
+ },
1362
+ {
1363
+ "epoch": 0.8853211009174312,
1364
+ "grad_norm": 1.2673226234465946,
1365
+ "learning_rate": 7.905777244947954e-07,
1366
+ "loss": 0.9182,
1367
+ "step": 965
1368
+ },
1369
+ {
1370
+ "epoch": 0.8899082568807339,
1371
+ "grad_norm": 1.2812373865753657,
1372
+ "learning_rate": 7.293615845160196e-07,
1373
+ "loss": 0.9289,
1374
+ "step": 970
1375
+ },
1376
+ {
1377
+ "epoch": 0.8944954128440367,
1378
+ "grad_norm": 1.2598363534447818,
1379
+ "learning_rate": 6.705222963319191e-07,
1380
+ "loss": 0.9375,
1381
+ "step": 975
1382
+ },
1383
+ {
1384
+ "epoch": 0.8990825688073395,
1385
+ "grad_norm": 1.311487874418335,
1386
+ "learning_rate": 6.140749454480932e-07,
1387
+ "loss": 0.9116,
1388
+ "step": 980
1389
+ },
1390
+ {
1391
+ "epoch": 0.9036697247706422,
1392
+ "grad_norm": 1.2877511107465471,
1393
+ "learning_rate": 5.600340041135133e-07,
1394
+ "loss": 0.9185,
1395
+ "step": 985
1396
+ },
1397
+ {
1398
+ "epoch": 0.908256880733945,
1399
+ "grad_norm": 1.2931543960319436,
1400
+ "learning_rate": 5.0841332761005e-07,
1401
+ "loss": 0.9332,
1402
+ "step": 990
1403
+ },
1404
+ {
1405
+ "epoch": 0.9128440366972477,
1406
+ "grad_norm": 1.180427274170459,
1407
+ "learning_rate": 4.592261507001994e-07,
1408
+ "loss": 0.9144,
1409
+ "step": 995
1410
+ },
1411
+ {
1412
+ "epoch": 0.9174311926605505,
1413
+ "grad_norm": 1.2599014895347989,
1414
+ "learning_rate": 4.124850842338779e-07,
1415
+ "loss": 0.9195,
1416
+ "step": 1000
1417
+ },
1418
+ {
1419
+ "epoch": 0.9220183486238532,
1420
+ "grad_norm": 1.2650407345597277,
1421
+ "learning_rate": 3.6820211191520127e-07,
1422
+ "loss": 0.9233,
1423
+ "step": 1005
1424
+ },
1425
+ {
1426
+ "epoch": 0.926605504587156,
1427
+ "grad_norm": 1.2740336020686558,
1428
+ "learning_rate": 3.263885872300343e-07,
1429
+ "loss": 0.9229,
1430
+ "step": 1010
1431
+ },
1432
+ {
1433
+ "epoch": 0.9311926605504587,
1434
+ "grad_norm": 1.2585813421221876,
1435
+ "learning_rate": 2.870552305351382e-07,
1436
+ "loss": 0.9004,
1437
+ "step": 1015
1438
+ },
1439
+ {
1440
+ "epoch": 0.9357798165137615,
1441
+ "grad_norm": 1.265046561795281,
1442
+ "learning_rate": 2.5021212630962246e-07,
1443
+ "loss": 0.9273,
1444
+ "step": 1020
1445
+ },
1446
+ {
1447
+ "epoch": 0.9403669724770642,
1448
+ "grad_norm": 1.2115732603108056,
1449
+ "learning_rate": 2.158687205694443e-07,
1450
+ "loss": 0.907,
1451
+ "step": 1025
1452
+ },
1453
+ {
1454
+ "epoch": 0.944954128440367,
1455
+ "grad_norm": 1.2383709828148504,
1456
+ "learning_rate": 1.840338184455881e-07,
1457
+ "loss": 0.9273,
1458
+ "step": 1030
1459
+ },
1460
+ {
1461
+ "epoch": 0.9495412844036697,
1462
+ "grad_norm": 1.2701853729566557,
1463
+ "learning_rate": 1.5471558192656776e-07,
1464
+ "loss": 0.9162,
1465
+ "step": 1035
1466
+ },
1467
+ {
1468
+ "epoch": 0.9541284403669725,
1469
+ "grad_norm": 1.2175490882454665,
1470
+ "learning_rate": 1.279215277658097e-07,
1471
+ "loss": 0.9324,
1472
+ "step": 1040
1473
+ },
1474
+ {
1475
+ "epoch": 0.9587155963302753,
1476
+ "grad_norm": 1.2654519384436929,
1477
+ "learning_rate": 1.0365852555447642e-07,
1478
+ "loss": 0.9251,
1479
+ "step": 1045
1480
+ },
1481
+ {
1482
+ "epoch": 0.963302752293578,
1483
+ "grad_norm": 1.2262401130217693,
1484
+ "learning_rate": 8.19327959602012e-08,
1485
+ "loss": 0.9347,
1486
+ "step": 1050
1487
+ },
1488
+ {
1489
+ "epoch": 0.9678899082568807,
1490
+ "grad_norm": 1.252498856154254,
1491
+ "learning_rate": 6.274990913221035e-08,
1492
+ "loss": 0.9287,
1493
+ "step": 1055
1494
+ },
1495
+ {
1496
+ "epoch": 0.9724770642201835,
1497
+ "grad_norm": 1.2498743795801759,
1498
+ "learning_rate": 4.6114783273213395e-08,
1499
+ "loss": 0.9137,
1500
+ "step": 1060
1501
+ },
1502
+ {
1503
+ "epoch": 0.9770642201834863,
1504
+ "grad_norm": 1.2653583861940565,
1505
+ "learning_rate": 3.203168337845508e-08,
1506
+ "loss": 0.9067,
1507
+ "step": 1065
1508
+ },
1509
+ {
1510
+ "epoch": 0.981651376146789,
1511
+ "grad_norm": 1.2716276154907005,
1512
+ "learning_rate": 2.05042201422323e-08,
1513
+ "loss": 0.9157,
1514
+ "step": 1070
1515
+ },
1516
+ {
1517
+ "epoch": 0.9862385321100917,
1518
+ "grad_norm": 1.2922733325507376,
1519
+ "learning_rate": 1.1535349032167908e-08,
1520
+ "loss": 0.8985,
1521
+ "step": 1075
1522
+ },
1523
+ {
1524
+ "epoch": 0.9908256880733946,
1525
+ "grad_norm": 1.2484185326437052,
1526
+ "learning_rate": 5.127369531473525e-09,
1527
+ "loss": 0.9282,
1528
+ "step": 1080
1529
+ },
1530
+ {
1531
+ "epoch": 0.9954128440366973,
1532
+ "grad_norm": 1.2964676313466048,
1533
+ "learning_rate": 1.2819245493955746e-09,
1534
+ "loss": 0.9246,
1535
+ "step": 1085
1536
+ },
1537
+ {
1538
+ "epoch": 1.0,
1539
+ "grad_norm": 1.33366290382446,
1540
+ "learning_rate": 0.0,
1541
+ "loss": 0.9201,
1542
+ "step": 1090
1543
+ },
1544
+ {
1545
+ "epoch": 1.0,
1546
+ "eval_loss": 0.9365631341934204,
1547
+ "eval_runtime": 506.8306,
1548
+ "eval_samples_per_second": 30.446,
1549
+ "eval_steps_per_second": 0.477,
1550
+ "step": 1090
1551
+ },
1552
+ {
1553
+ "epoch": 1.0,
1554
+ "step": 1090,
1555
+ "total_flos": 456447649382400.0,
1556
+ "train_loss": 0.9783915571116526,
1557
+ "train_runtime": 14076.1137,
1558
+ "train_samples_per_second": 9.905,
1559
+ "train_steps_per_second": 0.077
1560
+ }
1561
+ ],
1562
+ "logging_steps": 5,
1563
+ "max_steps": 1090,
1564
+ "num_input_tokens_seen": 0,
1565
+ "num_train_epochs": 1,
1566
+ "save_steps": 100,
1567
+ "total_flos": 456447649382400.0,
1568
+ "train_batch_size": 16,
1569
+ "trial_name": null,
1570
+ "trial_params": null
1571
+ }