Violet24K commited on
Commit
e1793bb
1 Parent(s): 0f89946

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: 0.9357
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
+ | 0.9081 | 1.0 | 1090 | 0.9357 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.36.2
64
+ - Pytorch 2.2.0+cu121
65
+ - Datasets 2.14.6
66
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9357115030288696,
4
+ "eval_runtime": 337.5218,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 45.719,
7
+ "eval_steps_per_second": 0.717,
8
+ "train_loss": 0.9779492704146499,
9
+ "train_runtime": 12151.2808,
10
+ "train_samples": 207865,
11
+ "train_samples_per_second": 11.474,
12
+ "train_steps_per_second": 0.09
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.9357115030288696,
4
+ "eval_runtime": 337.5218,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 45.719,
7
+ "eval_steps_per_second": 0.717
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 sha256:9caa0e01c728e53d96bf22580aa44c7e7cbee59915dca4055d2b770d5496a3c7
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71821a0b0dd8f8297e58c224ae8c4c270b43a26d8f7124778e9319129e0c628a
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea43e2df8d41a2e19a56943a634eba0b781e850c96a8c7e807a97dd185546b2
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/Feb19_21-44-55_idealab-05.cs.illinois.edu/events.out.tfevents.1708400712.idealab-05.cs.illinois.edu.1156167.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d585f9e1c87204344ca2ccd9798fea0de357e80ffd43abf4c2fb03d87884a6ee
3
- size 35921
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd32886d34335aae402a1a2f31fc9779b4506475035c8e8509b13bbe9f19ead
3
+ size 39372
runs/Feb19_21-44-55_idealab-05.cs.illinois.edu/events.out.tfevents.1708413201.idealab-05.cs.illinois.edu.1156167.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41acb13e588a40234c4135916c7a8006feb1fc29fb8442f3d487cbf658e0d4ae
3
+ size 359
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.9779492704146499,
4
+ "train_runtime": 12151.2808,
5
+ "train_samples": 207865,
6
+ "train_samples_per_second": 11.474,
7
+ "train_steps_per_second": 0.09
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.0,
13
+ "learning_rate": 1.8348623853211012e-07,
14
+ "loss": 1.6972,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 9.174311926605506e-07,
20
+ "loss": 1.6464,
21
+ "step": 5
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 1.8348623853211011e-06,
26
+ "loss": 1.3918,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 2.7522935779816517e-06,
32
+ "loss": 1.2141,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 3.6697247706422022e-06,
38
+ "loss": 1.1699,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 4.587155963302753e-06,
44
+ "loss": 1.1172,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 5.504587155963303e-06,
50
+ "loss": 1.0704,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 6.422018348623854e-06,
56
+ "loss": 1.0575,
57
+ "step": 35
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 7.3394495412844045e-06,
62
+ "loss": 1.052,
63
+ "step": 40
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 8.256880733944956e-06,
68
+ "loss": 1.0469,
69
+ "step": 45
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 9.174311926605506e-06,
74
+ "loss": 1.0309,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 1.0091743119266055e-05,
80
+ "loss": 1.0092,
81
+ "step": 55
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 1.1009174311926607e-05,
86
+ "loss": 1.0362,
87
+ "step": 60
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 1.1926605504587156e-05,
92
+ "loss": 1.0082,
93
+ "step": 65
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 1.2844036697247708e-05,
98
+ "loss": 1.0004,
99
+ "step": 70
100
+ },
101
+ {
102
+ "epoch": 0.07,
103
+ "learning_rate": 1.3761467889908258e-05,
104
+ "loss": 1.0004,
105
+ "step": 75
106
+ },
107
+ {
108
+ "epoch": 0.07,
109
+ "learning_rate": 1.4678899082568809e-05,
110
+ "loss": 0.992,
111
+ "step": 80
112
+ },
113
+ {
114
+ "epoch": 0.08,
115
+ "learning_rate": 1.559633027522936e-05,
116
+ "loss": 1.0151,
117
+ "step": 85
118
+ },
119
+ {
120
+ "epoch": 0.08,
121
+ "learning_rate": 1.6513761467889912e-05,
122
+ "loss": 0.9973,
123
+ "step": 90
124
+ },
125
+ {
126
+ "epoch": 0.09,
127
+ "learning_rate": 1.743119266055046e-05,
128
+ "loss": 1.0153,
129
+ "step": 95
130
+ },
131
+ {
132
+ "epoch": 0.09,
133
+ "learning_rate": 1.834862385321101e-05,
134
+ "loss": 1.0163,
135
+ "step": 100
136
+ },
137
+ {
138
+ "epoch": 0.1,
139
+ "learning_rate": 1.9266055045871563e-05,
140
+ "loss": 0.9873,
141
+ "step": 105
142
+ },
143
+ {
144
+ "epoch": 0.1,
145
+ "learning_rate": 1.999994872196626e-05,
146
+ "loss": 1.0055,
147
+ "step": 110
148
+ },
149
+ {
150
+ "epoch": 0.11,
151
+ "learning_rate": 1.9998154046002822e-05,
152
+ "loss": 1.014,
153
+ "step": 115
154
+ },
155
+ {
156
+ "epoch": 0.11,
157
+ "learning_rate": 1.999379599421534e-05,
158
+ "loss": 1.0058,
159
+ "step": 120
160
+ },
161
+ {
162
+ "epoch": 0.11,
163
+ "learning_rate": 1.9986875683942535e-05,
164
+ "loss": 1.02,
165
+ "step": 125
166
+ },
167
+ {
168
+ "epoch": 0.12,
169
+ "learning_rate": 1.9977394889447526e-05,
170
+ "loss": 1.0237,
171
+ "step": 130
172
+ },
173
+ {
174
+ "epoch": 0.12,
175
+ "learning_rate": 1.9965356041462954e-05,
176
+ "loss": 1.0304,
177
+ "step": 135
178
+ },
179
+ {
180
+ "epoch": 0.13,
181
+ "learning_rate": 1.9950762226567783e-05,
182
+ "loss": 1.0283,
183
+ "step": 140
184
+ },
185
+ {
186
+ "epoch": 0.13,
187
+ "learning_rate": 1.9933617186395917e-05,
188
+ "loss": 1.0046,
189
+ "step": 145
190
+ },
191
+ {
192
+ "epoch": 0.14,
193
+ "learning_rate": 1.9913925316676946e-05,
194
+ "loss": 1.003,
195
+ "step": 150
196
+ },
197
+ {
198
+ "epoch": 0.14,
199
+ "learning_rate": 1.9891691666109112e-05,
200
+ "loss": 1.023,
201
+ "step": 155
202
+ },
203
+ {
204
+ "epoch": 0.15,
205
+ "learning_rate": 1.9866921935064907e-05,
206
+ "loss": 1.014,
207
+ "step": 160
208
+ },
209
+ {
210
+ "epoch": 0.15,
211
+ "learning_rate": 1.9839622474129595e-05,
212
+ "loss": 1.017,
213
+ "step": 165
214
+ },
215
+ {
216
+ "epoch": 0.16,
217
+ "learning_rate": 1.9809800282473014e-05,
218
+ "loss": 0.9986,
219
+ "step": 170
220
+ },
221
+ {
222
+ "epoch": 0.16,
223
+ "learning_rate": 1.977746300605507e-05,
224
+ "loss": 1.0227,
225
+ "step": 175
226
+ },
227
+ {
228
+ "epoch": 0.17,
229
+ "learning_rate": 1.9742618935665478e-05,
230
+ "loss": 1.0091,
231
+ "step": 180
232
+ },
233
+ {
234
+ "epoch": 0.17,
235
+ "learning_rate": 1.9705277004798072e-05,
236
+ "loss": 0.9988,
237
+ "step": 185
238
+ },
239
+ {
240
+ "epoch": 0.17,
241
+ "learning_rate": 1.9665446787360444e-05,
242
+ "loss": 1.0117,
243
+ "step": 190
244
+ },
245
+ {
246
+ "epoch": 0.18,
247
+ "learning_rate": 1.9623138495219292e-05,
248
+ "loss": 1.0089,
249
+ "step": 195
250
+ },
251
+ {
252
+ "epoch": 0.18,
253
+ "learning_rate": 1.957836297558229e-05,
254
+ "loss": 1.0276,
255
+ "step": 200
256
+ },
257
+ {
258
+ "epoch": 0.19,
259
+ "learning_rate": 1.9531131708217005e-05,
260
+ "loss": 0.9893,
261
+ "step": 205
262
+ },
263
+ {
264
+ "epoch": 0.19,
265
+ "learning_rate": 1.948145680250766e-05,
266
+ "loss": 1.0117,
267
+ "step": 210
268
+ },
269
+ {
270
+ "epoch": 0.2,
271
+ "learning_rate": 1.9429350994350483e-05,
272
+ "loss": 0.9932,
273
+ "step": 215
274
+ },
275
+ {
276
+ "epoch": 0.2,
277
+ "learning_rate": 1.93748276428884e-05,
278
+ "loss": 1.0232,
279
+ "step": 220
280
+ },
281
+ {
282
+ "epoch": 0.21,
283
+ "learning_rate": 1.931790072708596e-05,
284
+ "loss": 1.0191,
285
+ "step": 225
286
+ },
287
+ {
288
+ "epoch": 0.21,
289
+ "learning_rate": 1.9258584842145342e-05,
290
+ "loss": 1.002,
291
+ "step": 230
292
+ },
293
+ {
294
+ "epoch": 0.22,
295
+ "learning_rate": 1.9196895195764363e-05,
296
+ "loss": 0.9959,
297
+ "step": 235
298
+ },
299
+ {
300
+ "epoch": 0.22,
301
+ "learning_rate": 1.913284760423745e-05,
302
+ "loss": 1.0212,
303
+ "step": 240
304
+ },
305
+ {
306
+ "epoch": 0.22,
307
+ "learning_rate": 1.9066458488400586e-05,
308
+ "loss": 1.0255,
309
+ "step": 245
310
+ },
311
+ {
312
+ "epoch": 0.23,
313
+ "learning_rate": 1.8997744869421248e-05,
314
+ "loss": 1.0037,
315
+ "step": 250
316
+ },
317
+ {
318
+ "epoch": 0.23,
319
+ "learning_rate": 1.8926724364434447e-05,
320
+ "loss": 0.9952,
321
+ "step": 255
322
+ },
323
+ {
324
+ "epoch": 0.24,
325
+ "learning_rate": 1.8853415182025953e-05,
326
+ "loss": 1.0087,
327
+ "step": 260
328
+ },
329
+ {
330
+ "epoch": 0.24,
331
+ "learning_rate": 1.8777836117563894e-05,
332
+ "loss": 1.0198,
333
+ "step": 265
334
+ },
335
+ {
336
+ "epoch": 0.25,
337
+ "learning_rate": 1.8700006548379898e-05,
338
+ "loss": 0.9921,
339
+ "step": 270
340
+ },
341
+ {
342
+ "epoch": 0.25,
343
+ "learning_rate": 1.861994642880105e-05,
344
+ "loss": 1.0037,
345
+ "step": 275
346
+ },
347
+ {
348
+ "epoch": 0.26,
349
+ "learning_rate": 1.8537676285033886e-05,
350
+ "loss": 1.0064,
351
+ "step": 280
352
+ },
353
+ {
354
+ "epoch": 0.26,
355
+ "learning_rate": 1.845321720990181e-05,
356
+ "loss": 1.0098,
357
+ "step": 285
358
+ },
359
+ {
360
+ "epoch": 0.27,
361
+ "learning_rate": 1.8366590857437182e-05,
362
+ "loss": 1.0154,
363
+ "step": 290
364
+ },
365
+ {
366
+ "epoch": 0.27,
367
+ "learning_rate": 1.8277819437329577e-05,
368
+ "loss": 0.9931,
369
+ "step": 295
370
+ },
371
+ {
372
+ "epoch": 0.28,
373
+ "learning_rate": 1.8186925709231534e-05,
374
+ "loss": 0.9875,
375
+ "step": 300
376
+ },
377
+ {
378
+ "epoch": 0.28,
379
+ "learning_rate": 1.809393297692334e-05,
380
+ "loss": 0.9892,
381
+ "step": 305
382
+ },
383
+ {
384
+ "epoch": 0.28,
385
+ "learning_rate": 1.799886508233829e-05,
386
+ "loss": 0.9865,
387
+ "step": 310
388
+ },
389
+ {
390
+ "epoch": 0.29,
391
+ "learning_rate": 1.790174639944997e-05,
392
+ "loss": 0.9894,
393
+ "step": 315
394
+ },
395
+ {
396
+ "epoch": 0.29,
397
+ "learning_rate": 1.780260182802314e-05,
398
+ "loss": 0.9981,
399
+ "step": 320
400
+ },
401
+ {
402
+ "epoch": 0.3,
403
+ "learning_rate": 1.7701456787229805e-05,
404
+ "loss": 0.9876,
405
+ "step": 325
406
+ },
407
+ {
408
+ "epoch": 0.3,
409
+ "learning_rate": 1.7598337209132142e-05,
410
+ "loss": 1.0101,
411
+ "step": 330
412
+ },
413
+ {
414
+ "epoch": 0.31,
415
+ "learning_rate": 1.7493269532033882e-05,
416
+ "loss": 0.994,
417
+ "step": 335
418
+ },
419
+ {
420
+ "epoch": 0.31,
421
+ "learning_rate": 1.738628069370195e-05,
422
+ "loss": 0.9979,
423
+ "step": 340
424
+ },
425
+ {
426
+ "epoch": 0.32,
427
+ "learning_rate": 1.7277398124460022e-05,
428
+ "loss": 1.0069,
429
+ "step": 345
430
+ },
431
+ {
432
+ "epoch": 0.32,
433
+ "learning_rate": 1.71666497401558e-05,
434
+ "loss": 0.9926,
435
+ "step": 350
436
+ },
437
+ {
438
+ "epoch": 0.33,
439
+ "learning_rate": 1.7054063935003813e-05,
440
+ "loss": 0.9974,
441
+ "step": 355
442
+ },
443
+ {
444
+ "epoch": 0.33,
445
+ "learning_rate": 1.6939669574305565e-05,
446
+ "loss": 1.007,
447
+ "step": 360
448
+ },
449
+ {
450
+ "epoch": 0.33,
451
+ "learning_rate": 1.6823495987048922e-05,
452
+ "loss": 0.9704,
453
+ "step": 365
454
+ },
455
+ {
456
+ "epoch": 0.34,
457
+ "learning_rate": 1.6705572958388576e-05,
458
+ "loss": 0.9991,
459
+ "step": 370
460
+ },
461
+ {
462
+ "epoch": 0.34,
463
+ "learning_rate": 1.6585930722009602e-05,
464
+ "loss": 0.9951,
465
+ "step": 375
466
+ },
467
+ {
468
+ "epoch": 0.35,
469
+ "learning_rate": 1.6464599952375998e-05,
470
+ "loss": 0.997,
471
+ "step": 380
472
+ },
473
+ {
474
+ "epoch": 0.35,
475
+ "learning_rate": 1.63416117568662e-05,
476
+ "loss": 0.9813,
477
+ "step": 385
478
+ },
479
+ {
480
+ "epoch": 0.36,
481
+ "learning_rate": 1.621699766779763e-05,
482
+ "loss": 1.0091,
483
+ "step": 390
484
+ },
485
+ {
486
+ "epoch": 0.36,
487
+ "learning_rate": 1.6090789634342278e-05,
488
+ "loss": 1.0028,
489
+ "step": 395
490
+ },
491
+ {
492
+ "epoch": 0.37,
493
+ "learning_rate": 1.5963020014335437e-05,
494
+ "loss": 0.9934,
495
+ "step": 400
496
+ },
497
+ {
498
+ "epoch": 0.37,
499
+ "learning_rate": 1.583372156597961e-05,
500
+ "loss": 0.9753,
501
+ "step": 405
502
+ },
503
+ {
504
+ "epoch": 0.38,
505
+ "learning_rate": 1.570292743944583e-05,
506
+ "loss": 1.009,
507
+ "step": 410
508
+ },
509
+ {
510
+ "epoch": 0.38,
511
+ "learning_rate": 1.557067116837444e-05,
512
+ "loss": 0.9679,
513
+ "step": 415
514
+ },
515
+ {
516
+ "epoch": 0.39,
517
+ "learning_rate": 1.5436986661277578e-05,
518
+ "loss": 0.9958,
519
+ "step": 420
520
+ },
521
+ {
522
+ "epoch": 0.39,
523
+ "learning_rate": 1.530190819284555e-05,
524
+ "loss": 1.0129,
525
+ "step": 425
526
+ },
527
+ {
528
+ "epoch": 0.39,
529
+ "learning_rate": 1.5165470395159314e-05,
530
+ "loss": 0.9882,
531
+ "step": 430
532
+ },
533
+ {
534
+ "epoch": 0.4,
535
+ "learning_rate": 1.5027708248811331e-05,
536
+ "loss": 0.9889,
537
+ "step": 435
538
+ },
539
+ {
540
+ "epoch": 0.4,
541
+ "learning_rate": 1.4888657073937077e-05,
542
+ "loss": 0.9789,
543
+ "step": 440
544
+ },
545
+ {
546
+ "epoch": 0.41,
547
+ "learning_rate": 1.4748352521159492e-05,
548
+ "loss": 0.9768,
549
+ "step": 445
550
+ },
551
+ {
552
+ "epoch": 0.41,
553
+ "learning_rate": 1.4606830562448692e-05,
554
+ "loss": 0.9878,
555
+ "step": 450
556
+ },
557
+ {
558
+ "epoch": 0.42,
559
+ "learning_rate": 1.4464127481899312e-05,
560
+ "loss": 1.0,
561
+ "step": 455
562
+ },
563
+ {
564
+ "epoch": 0.42,
565
+ "learning_rate": 1.4320279866427798e-05,
566
+ "loss": 0.979,
567
+ "step": 460
568
+ },
569
+ {
570
+ "epoch": 0.43,
571
+ "learning_rate": 1.4175324596392075e-05,
572
+ "loss": 0.9831,
573
+ "step": 465
574
+ },
575
+ {
576
+ "epoch": 0.43,
577
+ "learning_rate": 1.402929883613599e-05,
578
+ "loss": 0.9766,
579
+ "step": 470
580
+ },
581
+ {
582
+ "epoch": 0.44,
583
+ "learning_rate": 1.3882240024460928e-05,
584
+ "loss": 0.9862,
585
+ "step": 475
586
+ },
587
+ {
588
+ "epoch": 0.44,
589
+ "learning_rate": 1.3734185865027061e-05,
590
+ "loss": 0.984,
591
+ "step": 480
592
+ },
593
+ {
594
+ "epoch": 0.44,
595
+ "learning_rate": 1.358517431668672e-05,
596
+ "loss": 0.9834,
597
+ "step": 485
598
+ },
599
+ {
600
+ "epoch": 0.45,
601
+ "learning_rate": 1.3435243583752294e-05,
602
+ "loss": 0.9753,
603
+ "step": 490
604
+ },
605
+ {
606
+ "epoch": 0.45,
607
+ "learning_rate": 1.3284432106201233e-05,
608
+ "loss": 0.9799,
609
+ "step": 495
610
+ },
611
+ {
612
+ "epoch": 0.46,
613
+ "learning_rate": 1.313277854982062e-05,
614
+ "loss": 0.9583,
615
+ "step": 500
616
+ },
617
+ {
618
+ "epoch": 0.46,
619
+ "learning_rate": 1.2980321796293838e-05,
620
+ "loss": 0.9887,
621
+ "step": 505
622
+ },
623
+ {
624
+ "epoch": 0.47,
625
+ "learning_rate": 1.2827100933231904e-05,
626
+ "loss": 0.9697,
627
+ "step": 510
628
+ },
629
+ {
630
+ "epoch": 0.47,
631
+ "learning_rate": 1.2673155244151985e-05,
632
+ "loss": 0.9796,
633
+ "step": 515
634
+ },
635
+ {
636
+ "epoch": 0.48,
637
+ "learning_rate": 1.2518524198405699e-05,
638
+ "loss": 0.9662,
639
+ "step": 520
640
+ },
641
+ {
642
+ "epoch": 0.48,
643
+ "learning_rate": 1.2363247441059775e-05,
644
+ "loss": 0.9711,
645
+ "step": 525
646
+ },
647
+ {
648
+ "epoch": 0.49,
649
+ "learning_rate": 1.2207364782731657e-05,
650
+ "loss": 0.9799,
651
+ "step": 530
652
+ },
653
+ {
654
+ "epoch": 0.49,
655
+ "learning_rate": 1.2050916189382646e-05,
656
+ "loss": 0.9637,
657
+ "step": 535
658
+ },
659
+ {
660
+ "epoch": 0.5,
661
+ "learning_rate": 1.189394177207125e-05,
662
+ "loss": 0.9827,
663
+ "step": 540
664
+ },
665
+ {
666
+ "epoch": 0.5,
667
+ "learning_rate": 1.1736481776669307e-05,
668
+ "loss": 0.9821,
669
+ "step": 545
670
+ },
671
+ {
672
+ "epoch": 0.5,
673
+ "learning_rate": 1.1578576573543541e-05,
674
+ "loss": 0.9614,
675
+ "step": 550
676
+ },
677
+ {
678
+ "epoch": 0.51,
679
+ "learning_rate": 1.1420266647205232e-05,
680
+ "loss": 0.9688,
681
+ "step": 555
682
+ },
683
+ {
684
+ "epoch": 0.51,
685
+ "learning_rate": 1.1261592585930576e-05,
686
+ "loss": 0.9879,
687
+ "step": 560
688
+ },
689
+ {
690
+ "epoch": 0.52,
691
+ "learning_rate": 1.1102595071354471e-05,
692
+ "loss": 0.9449,
693
+ "step": 565
694
+ },
695
+ {
696
+ "epoch": 0.52,
697
+ "learning_rate": 1.0943314868040365e-05,
698
+ "loss": 0.9586,
699
+ "step": 570
700
+ },
701
+ {
702
+ "epoch": 0.53,
703
+ "learning_rate": 1.0783792813028828e-05,
704
+ "loss": 0.9777,
705
+ "step": 575
706
+ },
707
+ {
708
+ "epoch": 0.53,
709
+ "learning_rate": 1.0624069805367558e-05,
710
+ "loss": 0.9405,
711
+ "step": 580
712
+ },
713
+ {
714
+ "epoch": 0.54,
715
+ "learning_rate": 1.0464186795625481e-05,
716
+ "loss": 0.9637,
717
+ "step": 585
718
+ },
719
+ {
720
+ "epoch": 0.54,
721
+ "learning_rate": 1.0304184775393642e-05,
722
+ "loss": 0.9574,
723
+ "step": 590
724
+ },
725
+ {
726
+ "epoch": 0.55,
727
+ "learning_rate": 1.0144104766775574e-05,
728
+ "loss": 0.9699,
729
+ "step": 595
730
+ },
731
+ {
732
+ "epoch": 0.55,
733
+ "learning_rate": 9.983987811869863e-06,
734
+ "loss": 0.9671,
735
+ "step": 600
736
+ },
737
+ {
738
+ "epoch": 0.56,
739
+ "learning_rate": 9.823874962247565e-06,
740
+ "loss": 0.9656,
741
+ "step": 605
742
+ },
743
+ {
744
+ "epoch": 0.56,
745
+ "learning_rate": 9.663807268427197e-06,
746
+ "loss": 0.9515,
747
+ "step": 610
748
+ },
749
+ {
750
+ "epoch": 0.56,
751
+ "learning_rate": 9.503825769350016e-06,
752
+ "loss": 0.9738,
753
+ "step": 615
754
+ },
755
+ {
756
+ "epoch": 0.57,
757
+ "learning_rate": 9.343971481858246e-06,
758
+ "loss": 0.9491,
759
+ "step": 620
760
+ },
761
+ {
762
+ "epoch": 0.57,
763
+ "learning_rate": 9.184285390178978e-06,
764
+ "loss": 0.964,
765
+ "step": 625
766
+ },
767
+ {
768
+ "epoch": 0.58,
769
+ "learning_rate": 9.024808435416435e-06,
770
+ "loss": 0.9433,
771
+ "step": 630
772
+ },
773
+ {
774
+ "epoch": 0.58,
775
+ "learning_rate": 8.865581505055292e-06,
776
+ "loss": 0.9508,
777
+ "step": 635
778
+ },
779
+ {
780
+ "epoch": 0.59,
781
+ "learning_rate": 8.706645422477739e-06,
782
+ "loss": 0.9619,
783
+ "step": 640
784
+ },
785
+ {
786
+ "epoch": 0.59,
787
+ "learning_rate": 8.548040936496989e-06,
788
+ "loss": 0.9462,
789
+ "step": 645
790
+ },
791
+ {
792
+ "epoch": 0.6,
793
+ "learning_rate": 8.389808710909881e-06,
794
+ "loss": 0.9751,
795
+ "step": 650
796
+ },
797
+ {
798
+ "epoch": 0.6,
799
+ "learning_rate": 8.231989314071318e-06,
800
+ "loss": 0.9619,
801
+ "step": 655
802
+ },
803
+ {
804
+ "epoch": 0.61,
805
+ "learning_rate": 8.07462320849313e-06,
806
+ "loss": 0.9613,
807
+ "step": 660
808
+ },
809
+ {
810
+ "epoch": 0.61,
811
+ "learning_rate": 7.917750740470116e-06,
812
+ "loss": 0.9713,
813
+ "step": 665
814
+ },
815
+ {
816
+ "epoch": 0.61,
817
+ "learning_rate": 7.761412129735853e-06,
818
+ "loss": 0.9636,
819
+ "step": 670
820
+ },
821
+ {
822
+ "epoch": 0.62,
823
+ "learning_rate": 7.605647459150961e-06,
824
+ "loss": 0.9491,
825
+ "step": 675
826
+ },
827
+ {
828
+ "epoch": 0.62,
829
+ "learning_rate": 7.4504966644264775e-06,
830
+ "loss": 0.9493,
831
+ "step": 680
832
+ },
833
+ {
834
+ "epoch": 0.63,
835
+ "learning_rate": 7.295999523884921e-06,
836
+ "loss": 0.9434,
837
+ "step": 685
838
+ },
839
+ {
840
+ "epoch": 0.63,
841
+ "learning_rate": 7.142195648261747e-06,
842
+ "loss": 0.9653,
843
+ "step": 690
844
+ },
845
+ {
846
+ "epoch": 0.64,
847
+ "learning_rate": 6.989124470549746e-06,
848
+ "loss": 0.9607,
849
+ "step": 695
850
+ },
851
+ {
852
+ "epoch": 0.64,
853
+ "learning_rate": 6.83682523588902e-06,
854
+ "loss": 0.9462,
855
+ "step": 700
856
+ },
857
+ {
858
+ "epoch": 0.65,
859
+ "learning_rate": 6.685336991505122e-06,
860
+ "loss": 0.958,
861
+ "step": 705
862
+ },
863
+ {
864
+ "epoch": 0.65,
865
+ "learning_rate": 6.5346985766979384e-06,
866
+ "loss": 0.9505,
867
+ "step": 710
868
+ },
869
+ {
870
+ "epoch": 0.66,
871
+ "learning_rate": 6.384948612883872e-06,
872
+ "loss": 0.9479,
873
+ "step": 715
874
+ },
875
+ {
876
+ "epoch": 0.66,
877
+ "learning_rate": 6.2361254936939e-06,
878
+ "loss": 0.9394,
879
+ "step": 720
880
+ },
881
+ {
882
+ "epoch": 0.67,
883
+ "learning_rate": 6.0882673751300235e-06,
884
+ "loss": 0.9506,
885
+ "step": 725
886
+ },
887
+ {
888
+ "epoch": 0.67,
889
+ "learning_rate": 5.941412165782645e-06,
890
+ "loss": 0.9491,
891
+ "step": 730
892
+ },
893
+ {
894
+ "epoch": 0.67,
895
+ "learning_rate": 5.79559751711138e-06,
896
+ "loss": 0.9355,
897
+ "step": 735
898
+ },
899
+ {
900
+ "epoch": 0.68,
901
+ "learning_rate": 5.650860813791786e-06,
902
+ "loss": 0.9451,
903
+ "step": 740
904
+ },
905
+ {
906
+ "epoch": 0.68,
907
+ "learning_rate": 5.507239164130501e-06,
908
+ "loss": 0.9533,
909
+ "step": 745
910
+ },
911
+ {
912
+ "epoch": 0.69,
913
+ "learning_rate": 5.364769390551225e-06,
914
+ "loss": 0.9515,
915
+ "step": 750
916
+ },
917
+ {
918
+ "epoch": 0.69,
919
+ "learning_rate": 5.223488020154028e-06,
920
+ "loss": 0.9487,
921
+ "step": 755
922
+ },
923
+ {
924
+ "epoch": 0.7,
925
+ "learning_rate": 5.083431275350312e-06,
926
+ "loss": 0.9399,
927
+ "step": 760
928
+ },
929
+ {
930
+ "epoch": 0.7,
931
+ "learning_rate": 4.9446350645759885e-06,
932
+ "loss": 0.9471,
933
+ "step": 765
934
+ },
935
+ {
936
+ "epoch": 0.71,
937
+ "learning_rate": 4.807134973085036e-06,
938
+ "loss": 0.9443,
939
+ "step": 770
940
+ },
941
+ {
942
+ "epoch": 0.71,
943
+ "learning_rate": 4.670966253826027e-06,
944
+ "loss": 0.9518,
945
+ "step": 775
946
+ },
947
+ {
948
+ "epoch": 0.72,
949
+ "learning_rate": 4.53616381840377e-06,
950
+ "loss": 0.934,
951
+ "step": 780
952
+ },
953
+ {
954
+ "epoch": 0.72,
955
+ "learning_rate": 4.402762228128531e-06,
956
+ "loss": 0.9413,
957
+ "step": 785
958
+ },
959
+ {
960
+ "epoch": 0.72,
961
+ "learning_rate": 4.270795685155001e-06,
962
+ "loss": 0.9488,
963
+ "step": 790
964
+ },
965
+ {
966
+ "epoch": 0.73,
967
+ "learning_rate": 4.140298023713416e-06,
968
+ "loss": 0.9291,
969
+ "step": 795
970
+ },
971
+ {
972
+ "epoch": 0.73,
973
+ "learning_rate": 4.0113027014349374e-06,
974
+ "loss": 0.9442,
975
+ "step": 800
976
+ },
977
+ {
978
+ "epoch": 0.74,
979
+ "learning_rate": 3.883842790773647e-06,
980
+ "loss": 0.9326,
981
+ "step": 805
982
+ },
983
+ {
984
+ "epoch": 0.74,
985
+ "learning_rate": 3.757950970527249e-06,
986
+ "loss": 0.9369,
987
+ "step": 810
988
+ },
989
+ {
990
+ "epoch": 0.75,
991
+ "learning_rate": 3.633659517458736e-06,
992
+ "loss": 0.9314,
993
+ "step": 815
994
+ },
995
+ {
996
+ "epoch": 0.75,
997
+ "learning_rate": 3.511000298021098e-06,
998
+ "loss": 0.9502,
999
+ "step": 820
1000
+ },
1001
+ {
1002
+ "epoch": 0.76,
1003
+ "learning_rate": 3.39000476018726e-06,
1004
+ "loss": 0.9445,
1005
+ "step": 825
1006
+ },
1007
+ {
1008
+ "epoch": 0.76,
1009
+ "learning_rate": 3.2707039253872796e-06,
1010
+ "loss": 0.9357,
1011
+ "step": 830
1012
+ },
1013
+ {
1014
+ "epoch": 0.77,
1015
+ "learning_rate": 3.153128380554941e-06,
1016
+ "loss": 0.9423,
1017
+ "step": 835
1018
+ },
1019
+ {
1020
+ "epoch": 0.77,
1021
+ "learning_rate": 3.037308270285709e-06,
1022
+ "loss": 0.9206,
1023
+ "step": 840
1024
+ },
1025
+ {
1026
+ "epoch": 0.78,
1027
+ "learning_rate": 2.923273289108115e-06,
1028
+ "loss": 0.9466,
1029
+ "step": 845
1030
+ },
1031
+ {
1032
+ "epoch": 0.78,
1033
+ "learning_rate": 2.8110526738705345e-06,
1034
+ "loss": 0.9378,
1035
+ "step": 850
1036
+ },
1037
+ {
1038
+ "epoch": 0.78,
1039
+ "learning_rate": 2.700675196245288e-06,
1040
+ "loss": 0.9469,
1041
+ "step": 855
1042
+ },
1043
+ {
1044
+ "epoch": 0.79,
1045
+ "learning_rate": 2.592169155352031e-06,
1046
+ "loss": 0.9159,
1047
+ "step": 860
1048
+ },
1049
+ {
1050
+ "epoch": 0.79,
1051
+ "learning_rate": 2.485562370502279e-06,
1052
+ "loss": 0.9286,
1053
+ "step": 865
1054
+ },
1055
+ {
1056
+ "epoch": 0.8,
1057
+ "learning_rate": 2.3808821740669608e-06,
1058
+ "loss": 0.9296,
1059
+ "step": 870
1060
+ },
1061
+ {
1062
+ "epoch": 0.8,
1063
+ "learning_rate": 2.2781554044688015e-06,
1064
+ "loss": 0.9405,
1065
+ "step": 875
1066
+ },
1067
+ {
1068
+ "epoch": 0.81,
1069
+ "learning_rate": 2.1774083993013715e-06,
1070
+ "loss": 0.9364,
1071
+ "step": 880
1072
+ },
1073
+ {
1074
+ "epoch": 0.81,
1075
+ "learning_rate": 2.0786669885765044e-06,
1076
+ "loss": 0.9349,
1077
+ "step": 885
1078
+ },
1079
+ {
1080
+ "epoch": 0.82,
1081
+ "learning_rate": 1.981956488101898e-06,
1082
+ "loss": 0.9247,
1083
+ "step": 890
1084
+ },
1085
+ {
1086
+ "epoch": 0.82,
1087
+ "learning_rate": 1.8873016929904942e-06,
1088
+ "loss": 0.9339,
1089
+ "step": 895
1090
+ },
1091
+ {
1092
+ "epoch": 0.83,
1093
+ "learning_rate": 1.7947268713034128e-06,
1094
+ "loss": 0.9484,
1095
+ "step": 900
1096
+ },
1097
+ {
1098
+ "epoch": 0.83,
1099
+ "learning_rate": 1.704255757827963e-06,
1100
+ "loss": 0.9355,
1101
+ "step": 905
1102
+ },
1103
+ {
1104
+ "epoch": 0.83,
1105
+ "learning_rate": 1.6159115479924259e-06,
1106
+ "loss": 0.9242,
1107
+ "step": 910
1108
+ },
1109
+ {
1110
+ "epoch": 0.84,
1111
+ "learning_rate": 1.529716891919074e-06,
1112
+ "loss": 0.9215,
1113
+ "step": 915
1114
+ },
1115
+ {
1116
+ "epoch": 0.84,
1117
+ "learning_rate": 1.4456938886170413e-06,
1118
+ "loss": 0.9383,
1119
+ "step": 920
1120
+ },
1121
+ {
1122
+ "epoch": 0.85,
1123
+ "learning_rate": 1.3638640803164516e-06,
1124
+ "loss": 0.925,
1125
+ "step": 925
1126
+ },
1127
+ {
1128
+ "epoch": 0.85,
1129
+ "learning_rate": 1.2842484469453365e-06,
1130
+ "loss": 0.916,
1131
+ "step": 930
1132
+ },
1133
+ {
1134
+ "epoch": 0.86,
1135
+ "learning_rate": 1.2068674007506787e-06,
1136
+ "loss": 0.9289,
1137
+ "step": 935
1138
+ },
1139
+ {
1140
+ "epoch": 0.86,
1141
+ "learning_rate": 1.1317407810650372e-06,
1142
+ "loss": 0.9217,
1143
+ "step": 940
1144
+ },
1145
+ {
1146
+ "epoch": 0.87,
1147
+ "learning_rate": 1.0588878492200261e-06,
1148
+ "loss": 0.9345,
1149
+ "step": 945
1150
+ },
1151
+ {
1152
+ "epoch": 0.87,
1153
+ "learning_rate": 9.883272836080116e-07,
1154
+ "loss": 0.9297,
1155
+ "step": 950
1156
+ },
1157
+ {
1158
+ "epoch": 0.88,
1159
+ "learning_rate": 9.200771748932513e-07,
1160
+ "loss": 0.942,
1161
+ "step": 955
1162
+ },
1163
+ {
1164
+ "epoch": 0.88,
1165
+ "learning_rate": 8.541550213737171e-07,
1166
+ "loss": 0.9243,
1167
+ "step": 960
1168
+ },
1169
+ {
1170
+ "epoch": 0.89,
1171
+ "learning_rate": 7.905777244947954e-07,
1172
+ "loss": 0.9195,
1173
+ "step": 965
1174
+ },
1175
+ {
1176
+ "epoch": 0.89,
1177
+ "learning_rate": 7.293615845160196e-07,
1178
+ "loss": 0.9132,
1179
+ "step": 970
1180
+ },
1181
+ {
1182
+ "epoch": 0.89,
1183
+ "learning_rate": 6.705222963319191e-07,
1184
+ "loss": 0.9282,
1185
+ "step": 975
1186
+ },
1187
+ {
1188
+ "epoch": 0.9,
1189
+ "learning_rate": 6.140749454480932e-07,
1190
+ "loss": 0.9386,
1191
+ "step": 980
1192
+ },
1193
+ {
1194
+ "epoch": 0.9,
1195
+ "learning_rate": 5.600340041135133e-07,
1196
+ "loss": 0.9263,
1197
+ "step": 985
1198
+ },
1199
+ {
1200
+ "epoch": 0.91,
1201
+ "learning_rate": 5.0841332761005e-07,
1202
+ "loss": 0.9281,
1203
+ "step": 990
1204
+ },
1205
+ {
1206
+ "epoch": 0.91,
1207
+ "learning_rate": 4.592261507001994e-07,
1208
+ "loss": 0.9252,
1209
+ "step": 995
1210
+ },
1211
+ {
1212
+ "epoch": 0.92,
1213
+ "learning_rate": 4.124850842338779e-07,
1214
+ "loss": 0.9253,
1215
+ "step": 1000
1216
+ },
1217
+ {
1218
+ "epoch": 0.92,
1219
+ "learning_rate": 3.6820211191520127e-07,
1220
+ "loss": 0.9236,
1221
+ "step": 1005
1222
+ },
1223
+ {
1224
+ "epoch": 0.93,
1225
+ "learning_rate": 3.263885872300343e-07,
1226
+ "loss": 0.9091,
1227
+ "step": 1010
1228
+ },
1229
+ {
1230
+ "epoch": 0.93,
1231
+ "learning_rate": 2.870552305351382e-07,
1232
+ "loss": 0.9293,
1233
+ "step": 1015
1234
+ },
1235
+ {
1236
+ "epoch": 0.94,
1237
+ "learning_rate": 2.5021212630962246e-07,
1238
+ "loss": 0.933,
1239
+ "step": 1020
1240
+ },
1241
+ {
1242
+ "epoch": 0.94,
1243
+ "learning_rate": 2.158687205694443e-07,
1244
+ "loss": 0.9217,
1245
+ "step": 1025
1246
+ },
1247
+ {
1248
+ "epoch": 0.94,
1249
+ "learning_rate": 1.840338184455881e-07,
1250
+ "loss": 0.9146,
1251
+ "step": 1030
1252
+ },
1253
+ {
1254
+ "epoch": 0.95,
1255
+ "learning_rate": 1.5471558192656776e-07,
1256
+ "loss": 0.9232,
1257
+ "step": 1035
1258
+ },
1259
+ {
1260
+ "epoch": 0.95,
1261
+ "learning_rate": 1.279215277658097e-07,
1262
+ "loss": 0.9128,
1263
+ "step": 1040
1264
+ },
1265
+ {
1266
+ "epoch": 0.96,
1267
+ "learning_rate": 1.0365852555447642e-07,
1268
+ "loss": 0.9408,
1269
+ "step": 1045
1270
+ },
1271
+ {
1272
+ "epoch": 0.96,
1273
+ "learning_rate": 8.19327959602012e-08,
1274
+ "loss": 0.9372,
1275
+ "step": 1050
1276
+ },
1277
+ {
1278
+ "epoch": 0.97,
1279
+ "learning_rate": 6.274990913221035e-08,
1280
+ "loss": 0.9205,
1281
+ "step": 1055
1282
+ },
1283
+ {
1284
+ "epoch": 0.97,
1285
+ "learning_rate": 4.6114783273213395e-08,
1286
+ "loss": 0.9216,
1287
+ "step": 1060
1288
+ },
1289
+ {
1290
+ "epoch": 0.98,
1291
+ "learning_rate": 3.203168337845508e-08,
1292
+ "loss": 0.9128,
1293
+ "step": 1065
1294
+ },
1295
+ {
1296
+ "epoch": 0.98,
1297
+ "learning_rate": 2.05042201422323e-08,
1298
+ "loss": 0.9273,
1299
+ "step": 1070
1300
+ },
1301
+ {
1302
+ "epoch": 0.99,
1303
+ "learning_rate": 1.1535349032167908e-08,
1304
+ "loss": 0.9247,
1305
+ "step": 1075
1306
+ },
1307
+ {
1308
+ "epoch": 0.99,
1309
+ "learning_rate": 5.127369531473525e-09,
1310
+ "loss": 0.9462,
1311
+ "step": 1080
1312
+ },
1313
+ {
1314
+ "epoch": 1.0,
1315
+ "learning_rate": 1.2819245493955746e-09,
1316
+ "loss": 0.9163,
1317
+ "step": 1085
1318
+ },
1319
+ {
1320
+ "epoch": 1.0,
1321
+ "learning_rate": 0.0,
1322
+ "loss": 0.9081,
1323
+ "step": 1090
1324
+ },
1325
+ {
1326
+ "epoch": 1.0,
1327
+ "eval_loss": 0.9357115030288696,
1328
+ "eval_runtime": 337.6383,
1329
+ "eval_samples_per_second": 45.703,
1330
+ "eval_steps_per_second": 0.717,
1331
+ "step": 1090
1332
+ },
1333
+ {
1334
+ "epoch": 1.0,
1335
+ "step": 1090,
1336
+ "total_flos": 456447649382400.0,
1337
+ "train_loss": 0.9779492704146499,
1338
+ "train_runtime": 12151.2808,
1339
+ "train_samples_per_second": 11.474,
1340
+ "train_steps_per_second": 0.09
1341
+ }
1342
+ ],
1343
+ "logging_steps": 5,
1344
+ "max_steps": 1090,
1345
+ "num_input_tokens_seen": 0,
1346
+ "num_train_epochs": 1,
1347
+ "save_steps": 100,
1348
+ "total_flos": 456447649382400.0,
1349
+ "train_batch_size": 16,
1350
+ "trial_name": null,
1351
+ "trial_params": null
1352
+ }