GreenGenomicsLab commited on
Commit
af9b4e4
·
verified ·
1 Parent(s): c9260fa

Upload 8 files

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: TianlaiChen/PepMLM-650M
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TianlaiChen/PepMLM-650M",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "key",
24
+ "query",
25
+ "value"
26
+ ],
27
+ "task_type": "SEQ_CLS",
28
+ "use_dora": false,
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631051c680e34d63ab0d16b716ebec487e255134babd4b72a18edaa907a8027b
3
+ size 14707472
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7622b3d0137ae949b6ee2797c9c97718fedb4ad59e2af29bd44ff704f98ef762
3
+ size 29479290
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f33dd295aab577c830fa7c40c25eef11385d54fadaa6f9877fb50a6df60eb3
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ebb633099a186053f06b548bfd7a7a2393922f44951adfcfebad6ea4d2e895
3
+ size 1000
trainer_state.json ADDED
@@ -0,0 +1,3021 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.995008319467554,
5
+ "eval_steps": 500,
6
+ "global_step": 18000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008319467554076539,
13
+ "grad_norm": 0.5583499073982239,
14
+ "learning_rate": 0.0004999994583628932,
15
+ "loss": 0.7169,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.016638935108153077,
20
+ "grad_norm": 0.19315695762634277,
21
+ "learning_rate": 0.0004999989167257863,
22
+ "loss": 0.6946,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.024958402662229616,
27
+ "grad_norm": 0.2500464618206024,
28
+ "learning_rate": 0.0004999983750886796,
29
+ "loss": 0.6934,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.033277870216306155,
34
+ "grad_norm": 0.10472989827394485,
35
+ "learning_rate": 0.0004999978334515727,
36
+ "loss": 0.6922,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.04159733777038269,
41
+ "grad_norm": 0.08617454022169113,
42
+ "learning_rate": 0.0004999972918144659,
43
+ "loss": 0.6891,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.04991680532445923,
48
+ "grad_norm": 0.25109192728996277,
49
+ "learning_rate": 0.0004999967501773591,
50
+ "loss": 0.687,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.05823627287853577,
55
+ "grad_norm": 0.06475350260734558,
56
+ "learning_rate": 0.0004999962085402523,
57
+ "loss": 0.6854,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.06655574043261231,
62
+ "grad_norm": 0.5543227791786194,
63
+ "learning_rate": 0.0004999956669031455,
64
+ "loss": 0.6836,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.07487520798668885,
69
+ "grad_norm": 0.39940813183784485,
70
+ "learning_rate": 0.0004999951252660387,
71
+ "loss": 0.6808,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.08319467554076539,
76
+ "grad_norm": 0.3018794655799866,
77
+ "learning_rate": 0.0004999945836289318,
78
+ "loss": 0.6762,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.08319467554076539,
83
+ "eval_accuracy": 0.5590276660651246,
84
+ "eval_auc": 0.5967892656129481,
85
+ "eval_f1": 0.4315189357947604,
86
+ "eval_loss": 0.6786146759986877,
87
+ "eval_precision": 0.6065314861727951,
88
+ "eval_recall": 0.3348881306732058,
89
+ "eval_runtime": 3130.7158,
90
+ "eval_samples_per_second": 109.208,
91
+ "eval_steps_per_second": 13.651,
92
+ "step": 500
93
+ },
94
+ {
95
+ "epoch": 0.09151414309484193,
96
+ "grad_norm": 0.2409348487854004,
97
+ "learning_rate": 0.000499994041991825,
98
+ "loss": 0.6738,
99
+ "step": 550
100
+ },
101
+ {
102
+ "epoch": 0.09983361064891846,
103
+ "grad_norm": 0.292751282453537,
104
+ "learning_rate": 0.0004999935003547182,
105
+ "loss": 0.6718,
106
+ "step": 600
107
+ },
108
+ {
109
+ "epoch": 0.10815307820299501,
110
+ "grad_norm": 0.4114605486392975,
111
+ "learning_rate": 0.0004999929587176114,
112
+ "loss": 0.6691,
113
+ "step": 650
114
+ },
115
+ {
116
+ "epoch": 0.11647254575707154,
117
+ "grad_norm": 0.30100876092910767,
118
+ "learning_rate": 0.0004999924170805046,
119
+ "loss": 0.6691,
120
+ "step": 700
121
+ },
122
+ {
123
+ "epoch": 0.12479201331114809,
124
+ "grad_norm": 0.20736241340637207,
125
+ "learning_rate": 0.0004999918754433977,
126
+ "loss": 0.6653,
127
+ "step": 750
128
+ },
129
+ {
130
+ "epoch": 0.13311148086522462,
131
+ "grad_norm": 0.11416225880384445,
132
+ "learning_rate": 0.0004999913338062909,
133
+ "loss": 0.6629,
134
+ "step": 800
135
+ },
136
+ {
137
+ "epoch": 0.14143094841930118,
138
+ "grad_norm": 0.23378710448741913,
139
+ "learning_rate": 0.000499990792169184,
140
+ "loss": 0.66,
141
+ "step": 850
142
+ },
143
+ {
144
+ "epoch": 0.1497504159733777,
145
+ "grad_norm": 0.3658539652824402,
146
+ "learning_rate": 0.0004999902505320771,
147
+ "loss": 0.6538,
148
+ "step": 900
149
+ },
150
+ {
151
+ "epoch": 0.15806988352745424,
152
+ "grad_norm": 0.23335859179496765,
153
+ "learning_rate": 0.0004999897088949704,
154
+ "loss": 0.6572,
155
+ "step": 950
156
+ },
157
+ {
158
+ "epoch": 0.16638935108153077,
159
+ "grad_norm": 0.11527813971042633,
160
+ "learning_rate": 0.0004999891672578635,
161
+ "loss": 0.6559,
162
+ "step": 1000
163
+ },
164
+ {
165
+ "epoch": 0.16638935108153077,
166
+ "eval_accuracy": 0.6038917926054186,
167
+ "eval_auc": 0.6553736533116105,
168
+ "eval_f1": 0.5857262157127257,
169
+ "eval_loss": 0.650829017162323,
170
+ "eval_precision": 0.6135620810315436,
171
+ "eval_recall": 0.5603064335836225,
172
+ "eval_runtime": 3082.7349,
173
+ "eval_samples_per_second": 110.908,
174
+ "eval_steps_per_second": 13.864,
175
+ "step": 1000
176
+ },
177
+ {
178
+ "epoch": 0.17470881863560733,
179
+ "grad_norm": 0.12938088178634644,
180
+ "learning_rate": 0.0004999886256207567,
181
+ "loss": 0.6453,
182
+ "step": 1050
183
+ },
184
+ {
185
+ "epoch": 0.18302828618968386,
186
+ "grad_norm": 0.16796837747097015,
187
+ "learning_rate": 0.0004999880839836499,
188
+ "loss": 0.6459,
189
+ "step": 1100
190
+ },
191
+ {
192
+ "epoch": 0.1913477537437604,
193
+ "grad_norm": 0.31427496671676636,
194
+ "learning_rate": 0.0004999875423465431,
195
+ "loss": 0.6404,
196
+ "step": 1150
197
+ },
198
+ {
199
+ "epoch": 0.19966722129783693,
200
+ "grad_norm": 0.24732699990272522,
201
+ "learning_rate": 0.0004999870007094363,
202
+ "loss": 0.638,
203
+ "step": 1200
204
+ },
205
+ {
206
+ "epoch": 0.2079866888519135,
207
+ "grad_norm": 0.19166573882102966,
208
+ "learning_rate": 0.0004999864590723295,
209
+ "loss": 0.6316,
210
+ "step": 1250
211
+ },
212
+ {
213
+ "epoch": 0.21630615640599002,
214
+ "grad_norm": 0.23063616454601288,
215
+ "learning_rate": 0.0004999859174352226,
216
+ "loss": 0.6243,
217
+ "step": 1300
218
+ },
219
+ {
220
+ "epoch": 0.22462562396006655,
221
+ "grad_norm": 0.21349310874938965,
222
+ "learning_rate": 0.0004999853757981158,
223
+ "loss": 0.6229,
224
+ "step": 1350
225
+ },
226
+ {
227
+ "epoch": 0.23294509151414308,
228
+ "grad_norm": 0.21778538823127747,
229
+ "learning_rate": 0.000499984834161009,
230
+ "loss": 0.6173,
231
+ "step": 1400
232
+ },
233
+ {
234
+ "epoch": 0.24126455906821964,
235
+ "grad_norm": 0.3121509850025177,
236
+ "learning_rate": 0.0004999842925239022,
237
+ "loss": 0.6061,
238
+ "step": 1450
239
+ },
240
+ {
241
+ "epoch": 0.24958402662229617,
242
+ "grad_norm": 0.30077889561653137,
243
+ "learning_rate": 0.0004999837508867954,
244
+ "loss": 0.597,
245
+ "step": 1500
246
+ },
247
+ {
248
+ "epoch": 0.24958402662229617,
249
+ "eval_accuracy": 0.6591010795585831,
250
+ "eval_auc": 0.7267389932367714,
251
+ "eval_f1": 0.6891016322077618,
252
+ "eval_loss": 0.5957785844802856,
253
+ "eval_precision": 0.6331130956465479,
254
+ "eval_recall": 0.7559533911944238,
255
+ "eval_runtime": 3116.4637,
256
+ "eval_samples_per_second": 109.707,
257
+ "eval_steps_per_second": 13.714,
258
+ "step": 1500
259
+ },
260
+ {
261
+ "epoch": 0.2579034941763727,
262
+ "grad_norm": 0.29947781562805176,
263
+ "learning_rate": 0.0004999832092496885,
264
+ "loss": 0.594,
265
+ "step": 1550
266
+ },
267
+ {
268
+ "epoch": 0.26622296173044924,
269
+ "grad_norm": 0.35637083649635315,
270
+ "learning_rate": 0.0004999826676125817,
271
+ "loss": 0.5865,
272
+ "step": 1600
273
+ },
274
+ {
275
+ "epoch": 0.27454242928452577,
276
+ "grad_norm": 0.4300802946090698,
277
+ "learning_rate": 0.0004999821259754749,
278
+ "loss": 0.5795,
279
+ "step": 1650
280
+ },
281
+ {
282
+ "epoch": 0.28286189683860236,
283
+ "grad_norm": 0.37862110137939453,
284
+ "learning_rate": 0.0004999815843383681,
285
+ "loss": 0.5767,
286
+ "step": 1700
287
+ },
288
+ {
289
+ "epoch": 0.2911813643926789,
290
+ "grad_norm": 0.5083811283111572,
291
+ "learning_rate": 0.0004999810427012613,
292
+ "loss": 0.5665,
293
+ "step": 1750
294
+ },
295
+ {
296
+ "epoch": 0.2995008319467554,
297
+ "grad_norm": 0.4686565399169922,
298
+ "learning_rate": 0.0004999805010641545,
299
+ "loss": 0.5628,
300
+ "step": 1800
301
+ },
302
+ {
303
+ "epoch": 0.30782029950083195,
304
+ "grad_norm": 0.6207341551780701,
305
+ "learning_rate": 0.0004999799594270476,
306
+ "loss": 0.5612,
307
+ "step": 1850
308
+ },
309
+ {
310
+ "epoch": 0.3161397670549085,
311
+ "grad_norm": 0.400837779045105,
312
+ "learning_rate": 0.0004999794177899408,
313
+ "loss": 0.5546,
314
+ "step": 1900
315
+ },
316
+ {
317
+ "epoch": 0.324459234608985,
318
+ "grad_norm": 0.3956456184387207,
319
+ "learning_rate": 0.000499978876152834,
320
+ "loss": 0.5522,
321
+ "step": 1950
322
+ },
323
+ {
324
+ "epoch": 0.33277870216306155,
325
+ "grad_norm": 0.39825043082237244,
326
+ "learning_rate": 0.0004999783345157272,
327
+ "loss": 0.547,
328
+ "step": 2000
329
+ },
330
+ {
331
+ "epoch": 0.33277870216306155,
332
+ "eval_accuracy": 0.696047663198781,
333
+ "eval_auc": 0.7729761853730717,
334
+ "eval_f1": 0.7419938676961655,
335
+ "eval_loss": 0.5397406220436096,
336
+ "eval_precision": 0.644336742613705,
337
+ "eval_recall": 0.8745413152766154,
338
+ "eval_runtime": 3213.3641,
339
+ "eval_samples_per_second": 106.399,
340
+ "eval_steps_per_second": 13.3,
341
+ "step": 2000
342
+ },
343
+ {
344
+ "epoch": 0.3410981697171381,
345
+ "grad_norm": 0.4658432900905609,
346
+ "learning_rate": 0.0004999777928786204,
347
+ "loss": 0.5417,
348
+ "step": 2050
349
+ },
350
+ {
351
+ "epoch": 0.34941763727121466,
352
+ "grad_norm": 0.3485628664493561,
353
+ "learning_rate": 0.0004999772512415135,
354
+ "loss": 0.5391,
355
+ "step": 2100
356
+ },
357
+ {
358
+ "epoch": 0.3577371048252912,
359
+ "grad_norm": 0.3111945390701294,
360
+ "learning_rate": 0.0004999767096044067,
361
+ "loss": 0.5395,
362
+ "step": 2150
363
+ },
364
+ {
365
+ "epoch": 0.36605657237936773,
366
+ "grad_norm": 0.33330038189888,
367
+ "learning_rate": 0.0004999761679672999,
368
+ "loss": 0.5341,
369
+ "step": 2200
370
+ },
371
+ {
372
+ "epoch": 0.37437603993344426,
373
+ "grad_norm": 0.6060266494750977,
374
+ "learning_rate": 0.0004999756263301931,
375
+ "loss": 0.5348,
376
+ "step": 2250
377
+ },
378
+ {
379
+ "epoch": 0.3826955074875208,
380
+ "grad_norm": 0.38933542370796204,
381
+ "learning_rate": 0.0004999750846930863,
382
+ "loss": 0.5346,
383
+ "step": 2300
384
+ },
385
+ {
386
+ "epoch": 0.3910149750415973,
387
+ "grad_norm": 0.30752280354499817,
388
+ "learning_rate": 0.0004999745430559793,
389
+ "loss": 0.5292,
390
+ "step": 2350
391
+ },
392
+ {
393
+ "epoch": 0.39933444259567386,
394
+ "grad_norm": 0.3584199845790863,
395
+ "learning_rate": 0.0004999740014188725,
396
+ "loss": 0.528,
397
+ "step": 2400
398
+ },
399
+ {
400
+ "epoch": 0.40765391014975044,
401
+ "grad_norm": 0.34107691049575806,
402
+ "learning_rate": 0.0004999734597817657,
403
+ "loss": 0.5255,
404
+ "step": 2450
405
+ },
406
+ {
407
+ "epoch": 0.415973377703827,
408
+ "grad_norm": 0.33743101358413696,
409
+ "learning_rate": 0.0004999729181446589,
410
+ "loss": 0.5241,
411
+ "step": 2500
412
+ },
413
+ {
414
+ "epoch": 0.415973377703827,
415
+ "eval_accuracy": 0.7029268877651003,
416
+ "eval_auc": 0.7850390034483034,
417
+ "eval_f1": 0.7599834583801028,
418
+ "eval_loss": 0.5229647755622864,
419
+ "eval_precision": 0.6373332382107441,
420
+ "eval_recall": 0.9410893725602655,
421
+ "eval_runtime": 3103.5803,
422
+ "eval_samples_per_second": 110.163,
423
+ "eval_steps_per_second": 13.771,
424
+ "step": 2500
425
+ },
426
+ {
427
+ "epoch": 0.4242928452579035,
428
+ "grad_norm": 0.43357181549072266,
429
+ "learning_rate": 0.0004999723765075521,
430
+ "loss": 0.526,
431
+ "step": 2550
432
+ },
433
+ {
434
+ "epoch": 0.43261231281198004,
435
+ "grad_norm": 0.536624550819397,
436
+ "learning_rate": 0.0004999718348704453,
437
+ "loss": 0.5235,
438
+ "step": 2600
439
+ },
440
+ {
441
+ "epoch": 0.44093178036605657,
442
+ "grad_norm": 0.26722005009651184,
443
+ "learning_rate": 0.0004999712932333384,
444
+ "loss": 0.5238,
445
+ "step": 2650
446
+ },
447
+ {
448
+ "epoch": 0.4492512479201331,
449
+ "grad_norm": 0.29940328001976013,
450
+ "learning_rate": 0.0004999707515962316,
451
+ "loss": 0.5127,
452
+ "step": 2700
453
+ },
454
+ {
455
+ "epoch": 0.45757071547420963,
456
+ "grad_norm": 0.27166950702667236,
457
+ "learning_rate": 0.0004999702099591248,
458
+ "loss": 0.5167,
459
+ "step": 2750
460
+ },
461
+ {
462
+ "epoch": 0.46589018302828616,
463
+ "grad_norm": 0.5428174138069153,
464
+ "learning_rate": 0.000499969668322018,
465
+ "loss": 0.5148,
466
+ "step": 2800
467
+ },
468
+ {
469
+ "epoch": 0.47420965058236275,
470
+ "grad_norm": 0.37499845027923584,
471
+ "learning_rate": 0.0004999691266849112,
472
+ "loss": 0.5135,
473
+ "step": 2850
474
+ },
475
+ {
476
+ "epoch": 0.4825291181364393,
477
+ "grad_norm": 0.5476682186126709,
478
+ "learning_rate": 0.0004999685850478043,
479
+ "loss": 0.5127,
480
+ "step": 2900
481
+ },
482
+ {
483
+ "epoch": 0.4908485856905158,
484
+ "grad_norm": 0.24501897394657135,
485
+ "learning_rate": 0.0004999680434106975,
486
+ "loss": 0.5098,
487
+ "step": 2950
488
+ },
489
+ {
490
+ "epoch": 0.49916805324459235,
491
+ "grad_norm": 0.3694550395011902,
492
+ "learning_rate": 0.0004999675017735907,
493
+ "loss": 0.5138,
494
+ "step": 3000
495
+ },
496
+ {
497
+ "epoch": 0.49916805324459235,
498
+ "eval_accuracy": 0.7139476863050199,
499
+ "eval_auc": 0.794041583180005,
500
+ "eval_f1": 0.7427284708283901,
501
+ "eval_loss": 0.5122376084327698,
502
+ "eval_precision": 0.6745716224352297,
503
+ "eval_recall": 0.8262060408851225,
504
+ "eval_runtime": 3072.5721,
505
+ "eval_samples_per_second": 111.275,
506
+ "eval_steps_per_second": 13.91,
507
+ "step": 3000
508
+ },
509
+ {
510
+ "epoch": 0.5074875207986689,
511
+ "grad_norm": 0.2761985957622528,
512
+ "learning_rate": 0.0004999669601364839,
513
+ "loss": 0.5187,
514
+ "step": 3050
515
+ },
516
+ {
517
+ "epoch": 0.5158069883527454,
518
+ "grad_norm": 0.23015080392360687,
519
+ "learning_rate": 0.0004999664184993771,
520
+ "loss": 0.5117,
521
+ "step": 3100
522
+ },
523
+ {
524
+ "epoch": 0.5241264559068219,
525
+ "grad_norm": 0.26510143280029297,
526
+ "learning_rate": 0.0004999658768622703,
527
+ "loss": 0.5124,
528
+ "step": 3150
529
+ },
530
+ {
531
+ "epoch": 0.5324459234608985,
532
+ "grad_norm": 0.6037235260009766,
533
+ "learning_rate": 0.0004999653352251634,
534
+ "loss": 0.5111,
535
+ "step": 3200
536
+ },
537
+ {
538
+ "epoch": 0.540765391014975,
539
+ "grad_norm": 0.4400153160095215,
540
+ "learning_rate": 0.0004999647935880566,
541
+ "loss": 0.5167,
542
+ "step": 3250
543
+ },
544
+ {
545
+ "epoch": 0.5490848585690515,
546
+ "grad_norm": 0.33088386058807373,
547
+ "learning_rate": 0.0004999642519509498,
548
+ "loss": 0.5103,
549
+ "step": 3300
550
+ },
551
+ {
552
+ "epoch": 0.5574043261231281,
553
+ "grad_norm": 0.45530447363853455,
554
+ "learning_rate": 0.000499963710313843,
555
+ "loss": 0.5136,
556
+ "step": 3350
557
+ },
558
+ {
559
+ "epoch": 0.5657237936772047,
560
+ "grad_norm": 0.38819849491119385,
561
+ "learning_rate": 0.0004999631686767362,
562
+ "loss": 0.5094,
563
+ "step": 3400
564
+ },
565
+ {
566
+ "epoch": 0.5740432612312812,
567
+ "grad_norm": 0.2275410294532776,
568
+ "learning_rate": 0.0004999626270396293,
569
+ "loss": 0.5095,
570
+ "step": 3450
571
+ },
572
+ {
573
+ "epoch": 0.5823627287853578,
574
+ "grad_norm": 0.25340116024017334,
575
+ "learning_rate": 0.0004999620854025226,
576
+ "loss": 0.5109,
577
+ "step": 3500
578
+ },
579
+ {
580
+ "epoch": 0.5823627287853578,
581
+ "eval_accuracy": 0.7234504926893615,
582
+ "eval_auc": 0.8032986510196456,
583
+ "eval_f1": 0.7607974094312893,
584
+ "eval_loss": 0.5012865662574768,
585
+ "eval_precision": 0.6700384562254078,
586
+ "eval_recall": 0.8799957862456034,
587
+ "eval_runtime": 3072.7802,
588
+ "eval_samples_per_second": 111.267,
589
+ "eval_steps_per_second": 13.909,
590
+ "step": 3500
591
+ },
592
+ {
593
+ "epoch": 0.5906821963394343,
594
+ "grad_norm": 0.2851439416408539,
595
+ "learning_rate": 0.0004999615437654157,
596
+ "loss": 0.5072,
597
+ "step": 3550
598
+ },
599
+ {
600
+ "epoch": 0.5990016638935108,
601
+ "grad_norm": 0.2701944410800934,
602
+ "learning_rate": 0.0004999610021283089,
603
+ "loss": 0.5013,
604
+ "step": 3600
605
+ },
606
+ {
607
+ "epoch": 0.6073211314475874,
608
+ "grad_norm": 0.3663853704929352,
609
+ "learning_rate": 0.0004999604604912021,
610
+ "loss": 0.509,
611
+ "step": 3650
612
+ },
613
+ {
614
+ "epoch": 0.6156405990016639,
615
+ "grad_norm": 0.3946699798107147,
616
+ "learning_rate": 0.0004999599188540951,
617
+ "loss": 0.5073,
618
+ "step": 3700
619
+ },
620
+ {
621
+ "epoch": 0.6239600665557404,
622
+ "grad_norm": 0.20986106991767883,
623
+ "learning_rate": 0.0004999593772169885,
624
+ "loss": 0.5032,
625
+ "step": 3750
626
+ },
627
+ {
628
+ "epoch": 0.632279534109817,
629
+ "grad_norm": 0.44309139251708984,
630
+ "learning_rate": 0.0004999588355798815,
631
+ "loss": 0.5062,
632
+ "step": 3800
633
+ },
634
+ {
635
+ "epoch": 0.6405990016638935,
636
+ "grad_norm": 0.3160322904586792,
637
+ "learning_rate": 0.0004999582939427747,
638
+ "loss": 0.5003,
639
+ "step": 3850
640
+ },
641
+ {
642
+ "epoch": 0.64891846921797,
643
+ "grad_norm": 0.36600473523139954,
644
+ "learning_rate": 0.0004999577523056679,
645
+ "loss": 0.5047,
646
+ "step": 3900
647
+ },
648
+ {
649
+ "epoch": 0.6572379367720466,
650
+ "grad_norm": 0.4690772593021393,
651
+ "learning_rate": 0.0004999572106685611,
652
+ "loss": 0.504,
653
+ "step": 3950
654
+ },
655
+ {
656
+ "epoch": 0.6655574043261231,
657
+ "grad_norm": 0.2607940137386322,
658
+ "learning_rate": 0.0004999566690314542,
659
+ "loss": 0.5039,
660
+ "step": 4000
661
+ },
662
+ {
663
+ "epoch": 0.6655574043261231,
664
+ "eval_accuracy": 0.7287415289310586,
665
+ "eval_auc": 0.8093233697055171,
666
+ "eval_f1": 0.7662815165757343,
667
+ "eval_loss": 0.49741330742836,
668
+ "eval_precision": 0.6728864418931957,
669
+ "eval_recall": 0.8897810603444745,
670
+ "eval_runtime": 3108.812,
671
+ "eval_samples_per_second": 109.977,
672
+ "eval_steps_per_second": 13.747,
673
+ "step": 4000
674
+ },
675
+ {
676
+ "epoch": 0.6738768718801996,
677
+ "grad_norm": 0.4410100281238556,
678
+ "learning_rate": 0.0004999561273943475,
679
+ "loss": 0.5004,
680
+ "step": 4050
681
+ },
682
+ {
683
+ "epoch": 0.6821963394342762,
684
+ "grad_norm": 0.3221227824687958,
685
+ "learning_rate": 0.0004999555857572406,
686
+ "loss": 0.4987,
687
+ "step": 4100
688
+ },
689
+ {
690
+ "epoch": 0.6905158069883528,
691
+ "grad_norm": 0.3825673460960388,
692
+ "learning_rate": 0.0004999550441201338,
693
+ "loss": 0.5006,
694
+ "step": 4150
695
+ },
696
+ {
697
+ "epoch": 0.6988352745424293,
698
+ "grad_norm": 0.4332997798919678,
699
+ "learning_rate": 0.000499954502483027,
700
+ "loss": 0.498,
701
+ "step": 4200
702
+ },
703
+ {
704
+ "epoch": 0.7071547420965059,
705
+ "grad_norm": 0.4402281939983368,
706
+ "learning_rate": 0.0004999539608459201,
707
+ "loss": 0.497,
708
+ "step": 4250
709
+ },
710
+ {
711
+ "epoch": 0.7154742096505824,
712
+ "grad_norm": 0.2534608840942383,
713
+ "learning_rate": 0.0004999534192088134,
714
+ "loss": 0.4959,
715
+ "step": 4300
716
+ },
717
+ {
718
+ "epoch": 0.7237936772046589,
719
+ "grad_norm": 0.43906906247138977,
720
+ "learning_rate": 0.0004999528775717065,
721
+ "loss": 0.4923,
722
+ "step": 4350
723
+ },
724
+ {
725
+ "epoch": 0.7321131447587355,
726
+ "grad_norm": 0.3567379117012024,
727
+ "learning_rate": 0.0004999523359345997,
728
+ "loss": 0.497,
729
+ "step": 4400
730
+ },
731
+ {
732
+ "epoch": 0.740432612312812,
733
+ "grad_norm": 0.26709049940109253,
734
+ "learning_rate": 0.0004999517942974929,
735
+ "loss": 0.494,
736
+ "step": 4450
737
+ },
738
+ {
739
+ "epoch": 0.7487520798668885,
740
+ "grad_norm": 0.3749837577342987,
741
+ "learning_rate": 0.0004999512526603861,
742
+ "loss": 0.4954,
743
+ "step": 4500
744
+ },
745
+ {
746
+ "epoch": 0.7487520798668885,
747
+ "eval_accuracy": 0.7357143483894366,
748
+ "eval_auc": 0.8154262901262641,
749
+ "eval_f1": 0.7617121262865868,
750
+ "eval_loss": 0.48994818329811096,
751
+ "eval_precision": 0.6932252366415145,
752
+ "eval_recall": 0.8452147551633122,
753
+ "eval_runtime": 3064.0111,
754
+ "eval_samples_per_second": 111.585,
755
+ "eval_steps_per_second": 13.948,
756
+ "step": 4500
757
+ },
758
+ {
759
+ "epoch": 0.757071547420965,
760
+ "grad_norm": 0.34779804944992065,
761
+ "learning_rate": 0.0004999507110232793,
762
+ "loss": 0.4947,
763
+ "step": 4550
764
+ },
765
+ {
766
+ "epoch": 0.7653910149750416,
767
+ "grad_norm": 0.48780205845832825,
768
+ "learning_rate": 0.0004999501693861724,
769
+ "loss": 0.5003,
770
+ "step": 4600
771
+ },
772
+ {
773
+ "epoch": 0.7737104825291181,
774
+ "grad_norm": 0.25045379996299744,
775
+ "learning_rate": 0.0004999496277490656,
776
+ "loss": 0.4922,
777
+ "step": 4650
778
+ },
779
+ {
780
+ "epoch": 0.7820299500831946,
781
+ "grad_norm": 0.29499462246894836,
782
+ "learning_rate": 0.0004999490861119588,
783
+ "loss": 0.4891,
784
+ "step": 4700
785
+ },
786
+ {
787
+ "epoch": 0.7903494176372712,
788
+ "grad_norm": 0.34115445613861084,
789
+ "learning_rate": 0.000499948544474852,
790
+ "loss": 0.4984,
791
+ "step": 4750
792
+ },
793
+ {
794
+ "epoch": 0.7986688851913477,
795
+ "grad_norm": 0.5018367171287537,
796
+ "learning_rate": 0.0004999480028377452,
797
+ "loss": 0.4935,
798
+ "step": 4800
799
+ },
800
+ {
801
+ "epoch": 0.8069883527454242,
802
+ "grad_norm": 0.492158442735672,
803
+ "learning_rate": 0.0004999474612006384,
804
+ "loss": 0.4914,
805
+ "step": 4850
806
+ },
807
+ {
808
+ "epoch": 0.8153078202995009,
809
+ "grad_norm": 0.3154297173023224,
810
+ "learning_rate": 0.0004999469195635315,
811
+ "loss": 0.4946,
812
+ "step": 4900
813
+ },
814
+ {
815
+ "epoch": 0.8236272878535774,
816
+ "grad_norm": 0.27449771761894226,
817
+ "learning_rate": 0.0004999463779264247,
818
+ "loss": 0.4906,
819
+ "step": 4950
820
+ },
821
+ {
822
+ "epoch": 0.831946755407654,
823
+ "grad_norm": 0.37241068482398987,
824
+ "learning_rate": 0.0004999458362893179,
825
+ "loss": 0.4906,
826
+ "step": 5000
827
+ },
828
+ {
829
+ "epoch": 0.831946755407654,
830
+ "eval_accuracy": 0.7396014612502523,
831
+ "eval_auc": 0.8197279172699253,
832
+ "eval_f1": 0.7709238179535209,
833
+ "eval_loss": 0.48505428433418274,
834
+ "eval_precision": 0.6878946087547468,
835
+ "eval_recall": 0.876747683898191,
836
+ "eval_runtime": 3075.4729,
837
+ "eval_samples_per_second": 111.17,
838
+ "eval_steps_per_second": 13.896,
839
+ "step": 5000
840
+ },
841
+ {
842
+ "epoch": 0.8402662229617305,
843
+ "grad_norm": 0.2525058090686798,
844
+ "learning_rate": 0.0004999452946522111,
845
+ "loss": 0.4907,
846
+ "step": 5050
847
+ },
848
+ {
849
+ "epoch": 0.848585690515807,
850
+ "grad_norm": 0.3323892056941986,
851
+ "learning_rate": 0.0004999447530151043,
852
+ "loss": 0.4914,
853
+ "step": 5100
854
+ },
855
+ {
856
+ "epoch": 0.8569051580698835,
857
+ "grad_norm": 0.28021496534347534,
858
+ "learning_rate": 0.0004999442113779973,
859
+ "loss": 0.4891,
860
+ "step": 5150
861
+ },
862
+ {
863
+ "epoch": 0.8652246256239601,
864
+ "grad_norm": 0.2550656497478485,
865
+ "learning_rate": 0.0004999436697408905,
866
+ "loss": 0.4866,
867
+ "step": 5200
868
+ },
869
+ {
870
+ "epoch": 0.8735440931780366,
871
+ "grad_norm": 0.27683132886886597,
872
+ "learning_rate": 0.0004999431281037837,
873
+ "loss": 0.4867,
874
+ "step": 5250
875
+ },
876
+ {
877
+ "epoch": 0.8818635607321131,
878
+ "grad_norm": 0.3277775049209595,
879
+ "learning_rate": 0.0004999425864666769,
880
+ "loss": 0.4897,
881
+ "step": 5300
882
+ },
883
+ {
884
+ "epoch": 0.8901830282861897,
885
+ "grad_norm": 0.29307055473327637,
886
+ "learning_rate": 0.0004999420448295701,
887
+ "loss": 0.4861,
888
+ "step": 5350
889
+ },
890
+ {
891
+ "epoch": 0.8985024958402662,
892
+ "grad_norm": 0.4498750865459442,
893
+ "learning_rate": 0.0004999415031924633,
894
+ "loss": 0.4839,
895
+ "step": 5400
896
+ },
897
+ {
898
+ "epoch": 0.9068219633943427,
899
+ "grad_norm": 0.2954080104827881,
900
+ "learning_rate": 0.0004999409615553564,
901
+ "loss": 0.4857,
902
+ "step": 5450
903
+ },
904
+ {
905
+ "epoch": 0.9151414309484193,
906
+ "grad_norm": 0.35260140895843506,
907
+ "learning_rate": 0.0004999404199182496,
908
+ "loss": 0.487,
909
+ "step": 5500
910
+ },
911
+ {
912
+ "epoch": 0.9151414309484193,
913
+ "eval_accuracy": 0.7438073817121431,
914
+ "eval_auc": 0.8241829377605762,
915
+ "eval_f1": 0.7730318561781915,
916
+ "eval_loss": 0.4809417724609375,
917
+ "eval_precision": 0.6936197123499789,
918
+ "eval_recall": 0.8729787146878603,
919
+ "eval_runtime": 3075.8035,
920
+ "eval_samples_per_second": 111.158,
921
+ "eval_steps_per_second": 13.895,
922
+ "step": 5500
923
+ },
924
+ {
925
+ "epoch": 0.9234608985024958,
926
+ "grad_norm": 0.353834867477417,
927
+ "learning_rate": 0.0004999398782811428,
928
+ "loss": 0.4848,
929
+ "step": 5550
930
+ },
931
+ {
932
+ "epoch": 0.9317803660565723,
933
+ "grad_norm": 0.47889459133148193,
934
+ "learning_rate": 0.000499939336644036,
935
+ "loss": 0.4862,
936
+ "step": 5600
937
+ },
938
+ {
939
+ "epoch": 0.940099833610649,
940
+ "grad_norm": 0.24000470340251923,
941
+ "learning_rate": 0.0004999387950069292,
942
+ "loss": 0.4807,
943
+ "step": 5650
944
+ },
945
+ {
946
+ "epoch": 0.9484193011647255,
947
+ "grad_norm": 0.34989428520202637,
948
+ "learning_rate": 0.0004999382533698223,
949
+ "loss": 0.4862,
950
+ "step": 5700
951
+ },
952
+ {
953
+ "epoch": 0.956738768718802,
954
+ "grad_norm": 0.3731101155281067,
955
+ "learning_rate": 0.0004999377117327155,
956
+ "loss": 0.4875,
957
+ "step": 5750
958
+ },
959
+ {
960
+ "epoch": 0.9650582362728786,
961
+ "grad_norm": 0.26715531945228577,
962
+ "learning_rate": 0.0004999371700956087,
963
+ "loss": 0.4824,
964
+ "step": 5800
965
+ },
966
+ {
967
+ "epoch": 0.9733777038269551,
968
+ "grad_norm": 0.25930115580558777,
969
+ "learning_rate": 0.0004999366284585019,
970
+ "loss": 0.4805,
971
+ "step": 5850
972
+ },
973
+ {
974
+ "epoch": 0.9816971713810316,
975
+ "grad_norm": 0.3994530439376831,
976
+ "learning_rate": 0.0004999360868213951,
977
+ "loss": 0.4848,
978
+ "step": 5900
979
+ },
980
+ {
981
+ "epoch": 0.9900166389351082,
982
+ "grad_norm": 0.3294505178928375,
983
+ "learning_rate": 0.0004999355451842882,
984
+ "loss": 0.4848,
985
+ "step": 5950
986
+ },
987
+ {
988
+ "epoch": 0.9983361064891847,
989
+ "grad_norm": 0.3712209165096283,
990
+ "learning_rate": 0.0004999350035471814,
991
+ "loss": 0.4819,
992
+ "step": 6000
993
+ },
994
+ {
995
+ "epoch": 0.9983361064891847,
996
+ "eval_accuracy": 0.7473610627699994,
997
+ "eval_auc": 0.827144023087403,
998
+ "eval_f1": 0.7763430113178821,
999
+ "eval_loss": 0.4787616729736328,
1000
+ "eval_precision": 0.6961882470952102,
1001
+ "eval_recall": 0.8773563373110395,
1002
+ "eval_runtime": 3107.0522,
1003
+ "eval_samples_per_second": 110.04,
1004
+ "eval_steps_per_second": 13.755,
1005
+ "step": 6000
1006
+ },
1007
+ {
1008
+ "epoch": 1.0066555740432612,
1009
+ "grad_norm": 0.4111676812171936,
1010
+ "learning_rate": 0.0004999344619100746,
1011
+ "loss": 0.4793,
1012
+ "step": 6050
1013
+ },
1014
+ {
1015
+ "epoch": 1.0149750415973378,
1016
+ "grad_norm": 0.28988873958587646,
1017
+ "learning_rate": 0.0004999339202729678,
1018
+ "loss": 0.4809,
1019
+ "step": 6100
1020
+ },
1021
+ {
1022
+ "epoch": 1.0232945091514143,
1023
+ "grad_norm": 0.4895919859409332,
1024
+ "learning_rate": 0.000499933378635861,
1025
+ "loss": 0.4774,
1026
+ "step": 6150
1027
+ },
1028
+ {
1029
+ "epoch": 1.0316139767054908,
1030
+ "grad_norm": 0.40186378359794617,
1031
+ "learning_rate": 0.0004999328369987542,
1032
+ "loss": 0.4783,
1033
+ "step": 6200
1034
+ },
1035
+ {
1036
+ "epoch": 1.0399334442595674,
1037
+ "grad_norm": 0.31091171503067017,
1038
+ "learning_rate": 0.0004999322953616473,
1039
+ "loss": 0.472,
1040
+ "step": 6250
1041
+ },
1042
+ {
1043
+ "epoch": 1.0482529118136439,
1044
+ "grad_norm": 0.4297674000263214,
1045
+ "learning_rate": 0.0004999317645572826,
1046
+ "loss": 0.4755,
1047
+ "step": 6300
1048
+ },
1049
+ {
1050
+ "epoch": 1.0565723793677204,
1051
+ "grad_norm": 0.5054673552513123,
1052
+ "learning_rate": 0.0004999312229201758,
1053
+ "loss": 0.4715,
1054
+ "step": 6350
1055
+ },
1056
+ {
1057
+ "epoch": 1.064891846921797,
1058
+ "grad_norm": 0.3952338993549347,
1059
+ "learning_rate": 0.000499930681283069,
1060
+ "loss": 0.4742,
1061
+ "step": 6400
1062
+ },
1063
+ {
1064
+ "epoch": 1.0732113144758735,
1065
+ "grad_norm": 0.2842634320259094,
1066
+ "learning_rate": 0.0004999301396459622,
1067
+ "loss": 0.4772,
1068
+ "step": 6450
1069
+ },
1070
+ {
1071
+ "epoch": 1.08153078202995,
1072
+ "grad_norm": 0.3358585238456726,
1073
+ "learning_rate": 0.0004999295980088553,
1074
+ "loss": 0.4709,
1075
+ "step": 6500
1076
+ },
1077
+ {
1078
+ "epoch": 1.08153078202995,
1079
+ "eval_accuracy": 0.7469252615538508,
1080
+ "eval_auc": 0.8303769212813772,
1081
+ "eval_f1": 0.759462915601023,
1082
+ "eval_loss": 0.47938379645347595,
1083
+ "eval_precision": 0.7233056748441893,
1084
+ "eval_recall": 0.7994252907197912,
1085
+ "eval_runtime": 3090.922,
1086
+ "eval_samples_per_second": 110.614,
1087
+ "eval_steps_per_second": 13.827,
1088
+ "step": 6500
1089
+ },
1090
+ {
1091
+ "epoch": 1.0898502495840265,
1092
+ "grad_norm": 0.33011338114738464,
1093
+ "learning_rate": 0.0004999290563717485,
1094
+ "loss": 0.4741,
1095
+ "step": 6550
1096
+ },
1097
+ {
1098
+ "epoch": 1.098169717138103,
1099
+ "grad_norm": 0.3731289207935333,
1100
+ "learning_rate": 0.0004999285147346417,
1101
+ "loss": 0.4797,
1102
+ "step": 6600
1103
+ },
1104
+ {
1105
+ "epoch": 1.1064891846921796,
1106
+ "grad_norm": 0.3975057601928711,
1107
+ "learning_rate": 0.0004999279730975349,
1108
+ "loss": 0.4768,
1109
+ "step": 6650
1110
+ },
1111
+ {
1112
+ "epoch": 1.1148086522462561,
1113
+ "grad_norm": 0.37461864948272705,
1114
+ "learning_rate": 0.0004999274314604281,
1115
+ "loss": 0.4715,
1116
+ "step": 6700
1117
+ },
1118
+ {
1119
+ "epoch": 1.1231281198003327,
1120
+ "grad_norm": 0.4079597294330597,
1121
+ "learning_rate": 0.0004999268898233213,
1122
+ "loss": 0.4738,
1123
+ "step": 6750
1124
+ },
1125
+ {
1126
+ "epoch": 1.1314475873544092,
1127
+ "grad_norm": 0.25766322016716003,
1128
+ "learning_rate": 0.0004999263481862144,
1129
+ "loss": 0.4749,
1130
+ "step": 6800
1131
+ },
1132
+ {
1133
+ "epoch": 1.1397670549084857,
1134
+ "grad_norm": 0.32334184646606445,
1135
+ "learning_rate": 0.0004999258065491076,
1136
+ "loss": 0.4753,
1137
+ "step": 6850
1138
+ },
1139
+ {
1140
+ "epoch": 1.1480865224625625,
1141
+ "grad_norm": 0.3726251423358917,
1142
+ "learning_rate": 0.0004999252649120008,
1143
+ "loss": 0.4706,
1144
+ "step": 6900
1145
+ },
1146
+ {
1147
+ "epoch": 1.156405990016639,
1148
+ "grad_norm": 0.2608793079853058,
1149
+ "learning_rate": 0.000499924723274894,
1150
+ "loss": 0.4758,
1151
+ "step": 6950
1152
+ },
1153
+ {
1154
+ "epoch": 1.1647254575707155,
1155
+ "grad_norm": 0.2321689873933792,
1156
+ "learning_rate": 0.0004999241816377872,
1157
+ "loss": 0.4775,
1158
+ "step": 7000
1159
+ },
1160
+ {
1161
+ "epoch": 1.1647254575707155,
1162
+ "eval_accuracy": 0.7482034167985282,
1163
+ "eval_auc": 0.8299646263747171,
1164
+ "eval_f1": 0.7817299037815499,
1165
+ "eval_loss": 0.4775802195072174,
1166
+ "eval_precision": 0.6896254014833636,
1167
+ "eval_recall": 0.9022291931245574,
1168
+ "eval_runtime": 3102.1713,
1169
+ "eval_samples_per_second": 110.213,
1170
+ "eval_steps_per_second": 13.777,
1171
+ "step": 7000
1172
+ },
1173
+ {
1174
+ "epoch": 1.173044925124792,
1175
+ "grad_norm": 0.4716586172580719,
1176
+ "learning_rate": 0.0004999236400006803,
1177
+ "loss": 0.4688,
1178
+ "step": 7050
1179
+ },
1180
+ {
1181
+ "epoch": 1.1813643926788686,
1182
+ "grad_norm": 0.3553094267845154,
1183
+ "learning_rate": 0.0004999230983635735,
1184
+ "loss": 0.4699,
1185
+ "step": 7100
1186
+ },
1187
+ {
1188
+ "epoch": 1.1896838602329451,
1189
+ "grad_norm": 0.5420466065406799,
1190
+ "learning_rate": 0.0004999225567264667,
1191
+ "loss": 0.4742,
1192
+ "step": 7150
1193
+ },
1194
+ {
1195
+ "epoch": 1.1980033277870217,
1196
+ "grad_norm": 0.26752716302871704,
1197
+ "learning_rate": 0.0004999220150893599,
1198
+ "loss": 0.4725,
1199
+ "step": 7200
1200
+ },
1201
+ {
1202
+ "epoch": 1.2063227953410982,
1203
+ "grad_norm": 0.2967946529388428,
1204
+ "learning_rate": 0.0004999214734522531,
1205
+ "loss": 0.4671,
1206
+ "step": 7250
1207
+ },
1208
+ {
1209
+ "epoch": 1.2146422628951747,
1210
+ "grad_norm": 0.24301719665527344,
1211
+ "learning_rate": 0.0004999209318151461,
1212
+ "loss": 0.4741,
1213
+ "step": 7300
1214
+ },
1215
+ {
1216
+ "epoch": 1.2229617304492513,
1217
+ "grad_norm": 0.3372076451778412,
1218
+ "learning_rate": 0.0004999203901780393,
1219
+ "loss": 0.4718,
1220
+ "step": 7350
1221
+ },
1222
+ {
1223
+ "epoch": 1.2312811980033278,
1224
+ "grad_norm": 0.28806430101394653,
1225
+ "learning_rate": 0.0004999198485409325,
1226
+ "loss": 0.4751,
1227
+ "step": 7400
1228
+ },
1229
+ {
1230
+ "epoch": 1.2396006655574043,
1231
+ "grad_norm": 0.28929972648620605,
1232
+ "learning_rate": 0.0004999193069038257,
1233
+ "loss": 0.4748,
1234
+ "step": 7450
1235
+ },
1236
+ {
1237
+ "epoch": 1.2479201331114809,
1238
+ "grad_norm": 0.5165761113166809,
1239
+ "learning_rate": 0.0004999187652667189,
1240
+ "loss": 0.4738,
1241
+ "step": 7500
1242
+ },
1243
+ {
1244
+ "epoch": 1.2479201331114809,
1245
+ "eval_accuracy": 0.7527018212981027,
1246
+ "eval_auc": 0.8341791803614174,
1247
+ "eval_f1": 0.7692807265047057,
1248
+ "eval_loss": 0.4720609784126282,
1249
+ "eval_precision": 0.7206515404042986,
1250
+ "eval_recall": 0.8249477670027916,
1251
+ "eval_runtime": 3117.7578,
1252
+ "eval_samples_per_second": 109.662,
1253
+ "eval_steps_per_second": 13.708,
1254
+ "step": 7500
1255
+ },
1256
+ {
1257
+ "epoch": 1.2562396006655574,
1258
+ "grad_norm": 0.3871491551399231,
1259
+ "learning_rate": 0.0004999182236296121,
1260
+ "loss": 0.4749,
1261
+ "step": 7550
1262
+ },
1263
+ {
1264
+ "epoch": 1.264559068219634,
1265
+ "grad_norm": 0.34656795859336853,
1266
+ "learning_rate": 0.0004999176819925052,
1267
+ "loss": 0.4729,
1268
+ "step": 7600
1269
+ },
1270
+ {
1271
+ "epoch": 1.2728785357737105,
1272
+ "grad_norm": 0.4117598533630371,
1273
+ "learning_rate": 0.0004999171403553984,
1274
+ "loss": 0.4677,
1275
+ "step": 7650
1276
+ },
1277
+ {
1278
+ "epoch": 1.281198003327787,
1279
+ "grad_norm": 0.25794079899787903,
1280
+ "learning_rate": 0.0004999165987182916,
1281
+ "loss": 0.4723,
1282
+ "step": 7700
1283
+ },
1284
+ {
1285
+ "epoch": 1.2895174708818635,
1286
+ "grad_norm": 0.33428308367729187,
1287
+ "learning_rate": 0.0004999160570811848,
1288
+ "loss": 0.471,
1289
+ "step": 7750
1290
+ },
1291
+ {
1292
+ "epoch": 1.29783693843594,
1293
+ "grad_norm": 0.3722244203090668,
1294
+ "learning_rate": 0.000499915515444078,
1295
+ "loss": 0.4695,
1296
+ "step": 7800
1297
+ },
1298
+ {
1299
+ "epoch": 1.3061564059900166,
1300
+ "grad_norm": 0.34326881170272827,
1301
+ "learning_rate": 0.0004999149738069711,
1302
+ "loss": 0.4693,
1303
+ "step": 7850
1304
+ },
1305
+ {
1306
+ "epoch": 1.3144758735440931,
1307
+ "grad_norm": 0.473015695810318,
1308
+ "learning_rate": 0.0004999144321698643,
1309
+ "loss": 0.4773,
1310
+ "step": 7900
1311
+ },
1312
+ {
1313
+ "epoch": 1.3227953410981697,
1314
+ "grad_norm": 0.39536336064338684,
1315
+ "learning_rate": 0.0004999138905327575,
1316
+ "loss": 0.4633,
1317
+ "step": 7950
1318
+ },
1319
+ {
1320
+ "epoch": 1.3311148086522462,
1321
+ "grad_norm": 0.24282647669315338,
1322
+ "learning_rate": 0.0004999133488956507,
1323
+ "loss": 0.4704,
1324
+ "step": 8000
1325
+ },
1326
+ {
1327
+ "epoch": 1.3311148086522462,
1328
+ "eval_accuracy": 0.7551382133320074,
1329
+ "eval_auc": 0.8357908200441471,
1330
+ "eval_f1": 0.7845750840156658,
1331
+ "eval_loss": 0.46888816356658936,
1332
+ "eval_precision": 0.7001180258003481,
1333
+ "eval_recall": 0.8922039691225442,
1334
+ "eval_runtime": 3128.319,
1335
+ "eval_samples_per_second": 109.292,
1336
+ "eval_steps_per_second": 13.662,
1337
+ "step": 8000
1338
+ },
1339
+ {
1340
+ "epoch": 1.3394342762063227,
1341
+ "grad_norm": 0.46165645122528076,
1342
+ "learning_rate": 0.0004999128072585439,
1343
+ "loss": 0.4677,
1344
+ "step": 8050
1345
+ },
1346
+ {
1347
+ "epoch": 1.3477537437603995,
1348
+ "grad_norm": 0.2814394235610962,
1349
+ "learning_rate": 0.0004999122656214371,
1350
+ "loss": 0.4655,
1351
+ "step": 8100
1352
+ },
1353
+ {
1354
+ "epoch": 1.356073211314476,
1355
+ "grad_norm": 0.24799716472625732,
1356
+ "learning_rate": 0.0004999117239843302,
1357
+ "loss": 0.4705,
1358
+ "step": 8150
1359
+ },
1360
+ {
1361
+ "epoch": 1.3643926788685525,
1362
+ "grad_norm": 0.3806433379650116,
1363
+ "learning_rate": 0.0004999111823472234,
1364
+ "loss": 0.4689,
1365
+ "step": 8200
1366
+ },
1367
+ {
1368
+ "epoch": 1.372712146422629,
1369
+ "grad_norm": 0.3523135185241699,
1370
+ "learning_rate": 0.0004999106407101166,
1371
+ "loss": 0.4695,
1372
+ "step": 8250
1373
+ },
1374
+ {
1375
+ "epoch": 1.3810316139767056,
1376
+ "grad_norm": 0.2665747106075287,
1377
+ "learning_rate": 0.0004999100990730098,
1378
+ "loss": 0.4737,
1379
+ "step": 8300
1380
+ },
1381
+ {
1382
+ "epoch": 1.3893510815307821,
1383
+ "grad_norm": 0.28612571954727173,
1384
+ "learning_rate": 0.000499909557435903,
1385
+ "loss": 0.4686,
1386
+ "step": 8350
1387
+ },
1388
+ {
1389
+ "epoch": 1.3976705490848587,
1390
+ "grad_norm": 0.2960534691810608,
1391
+ "learning_rate": 0.0004999090157987961,
1392
+ "loss": 0.4696,
1393
+ "step": 8400
1394
+ },
1395
+ {
1396
+ "epoch": 1.4059900166389352,
1397
+ "grad_norm": 0.34513574838638306,
1398
+ "learning_rate": 0.0004999084741616894,
1399
+ "loss": 0.4694,
1400
+ "step": 8450
1401
+ },
1402
+ {
1403
+ "epoch": 1.4143094841930117,
1404
+ "grad_norm": 0.3929885923862457,
1405
+ "learning_rate": 0.0004999079325245825,
1406
+ "loss": 0.4687,
1407
+ "step": 8500
1408
+ },
1409
+ {
1410
+ "epoch": 1.4143094841930117,
1411
+ "eval_accuracy": 0.7571154054267488,
1412
+ "eval_auc": 0.8376226439602212,
1413
+ "eval_f1": 0.7821289144488288,
1414
+ "eval_loss": 0.4663051962852478,
1415
+ "eval_precision": 0.7088304808282172,
1416
+ "eval_recall": 0.8723349466550399,
1417
+ "eval_runtime": 3128.487,
1418
+ "eval_samples_per_second": 109.286,
1419
+ "eval_steps_per_second": 13.661,
1420
+ "step": 8500
1421
+ },
1422
+ {
1423
+ "epoch": 1.4226289517470883,
1424
+ "grad_norm": 0.667980968952179,
1425
+ "learning_rate": 0.0004999074017202178,
1426
+ "loss": 0.4712,
1427
+ "step": 8550
1428
+ },
1429
+ {
1430
+ "epoch": 1.4309484193011648,
1431
+ "grad_norm": 0.27172645926475525,
1432
+ "learning_rate": 0.000499906860083111,
1433
+ "loss": 0.4713,
1434
+ "step": 8600
1435
+ },
1436
+ {
1437
+ "epoch": 1.4392678868552413,
1438
+ "grad_norm": 0.4408021569252014,
1439
+ "learning_rate": 0.0004999063184460041,
1440
+ "loss": 0.4706,
1441
+ "step": 8650
1442
+ },
1443
+ {
1444
+ "epoch": 1.4475873544093179,
1445
+ "grad_norm": 0.25165098905563354,
1446
+ "learning_rate": 0.0004999057768088973,
1447
+ "loss": 0.4699,
1448
+ "step": 8700
1449
+ },
1450
+ {
1451
+ "epoch": 1.4559068219633944,
1452
+ "grad_norm": 0.35004204511642456,
1453
+ "learning_rate": 0.0004999052351717905,
1454
+ "loss": 0.4708,
1455
+ "step": 8750
1456
+ },
1457
+ {
1458
+ "epoch": 1.464226289517471,
1459
+ "grad_norm": 0.33756914734840393,
1460
+ "learning_rate": 0.0004999046935346837,
1461
+ "loss": 0.4665,
1462
+ "step": 8800
1463
+ },
1464
+ {
1465
+ "epoch": 1.4725457570715474,
1466
+ "grad_norm": 0.4379380941390991,
1467
+ "learning_rate": 0.0004999041518975769,
1468
+ "loss": 0.4671,
1469
+ "step": 8850
1470
+ },
1471
+ {
1472
+ "epoch": 1.480865224625624,
1473
+ "grad_norm": 0.450702965259552,
1474
+ "learning_rate": 0.0004999036102604701,
1475
+ "loss": 0.4682,
1476
+ "step": 8900
1477
+ },
1478
+ {
1479
+ "epoch": 1.4891846921797005,
1480
+ "grad_norm": 0.429463654756546,
1481
+ "learning_rate": 0.0004999030686233632,
1482
+ "loss": 0.4657,
1483
+ "step": 8950
1484
+ },
1485
+ {
1486
+ "epoch": 1.497504159733777,
1487
+ "grad_norm": 0.26801300048828125,
1488
+ "learning_rate": 0.0004999025269862564,
1489
+ "loss": 0.4663,
1490
+ "step": 9000
1491
+ },
1492
+ {
1493
+ "epoch": 1.497504159733777,
1494
+ "eval_accuracy": 0.7582911912582371,
1495
+ "eval_auc": 0.839204544655265,
1496
+ "eval_f1": 0.7839499717650011,
1497
+ "eval_loss": 0.4652154743671417,
1498
+ "eval_precision": 0.7084461454863326,
1499
+ "eval_recall": 0.8774675336076175,
1500
+ "eval_runtime": 3125.7976,
1501
+ "eval_samples_per_second": 109.38,
1502
+ "eval_steps_per_second": 13.673,
1503
+ "step": 9000
1504
+ },
1505
+ {
1506
+ "epoch": 1.5058236272878536,
1507
+ "grad_norm": 0.41154783964157104,
1508
+ "learning_rate": 0.0004999019853491496,
1509
+ "loss": 0.4675,
1510
+ "step": 9050
1511
+ },
1512
+ {
1513
+ "epoch": 1.51414309484193,
1514
+ "grad_norm": 0.5559844374656677,
1515
+ "learning_rate": 0.0004999014437120428,
1516
+ "loss": 0.4668,
1517
+ "step": 9100
1518
+ },
1519
+ {
1520
+ "epoch": 1.5224625623960066,
1521
+ "grad_norm": 0.2977549135684967,
1522
+ "learning_rate": 0.000499900902074936,
1523
+ "loss": 0.4652,
1524
+ "step": 9150
1525
+ },
1526
+ {
1527
+ "epoch": 1.5307820299500832,
1528
+ "grad_norm": 0.24874624609947205,
1529
+ "learning_rate": 0.0004999003604378291,
1530
+ "loss": 0.465,
1531
+ "step": 9200
1532
+ },
1533
+ {
1534
+ "epoch": 1.5391014975041597,
1535
+ "grad_norm": 0.7150341868400574,
1536
+ "learning_rate": 0.0004998998188007223,
1537
+ "loss": 0.468,
1538
+ "step": 9250
1539
+ },
1540
+ {
1541
+ "epoch": 1.5474209650582362,
1542
+ "grad_norm": 0.2461651861667633,
1543
+ "learning_rate": 0.0004998992771636155,
1544
+ "loss": 0.4664,
1545
+ "step": 9300
1546
+ },
1547
+ {
1548
+ "epoch": 1.5557404326123128,
1549
+ "grad_norm": 0.4250808358192444,
1550
+ "learning_rate": 0.0004998987355265087,
1551
+ "loss": 0.4641,
1552
+ "step": 9350
1553
+ },
1554
+ {
1555
+ "epoch": 1.5640599001663893,
1556
+ "grad_norm": 0.3863760530948639,
1557
+ "learning_rate": 0.0004998981938894019,
1558
+ "loss": 0.4675,
1559
+ "step": 9400
1560
+ },
1561
+ {
1562
+ "epoch": 1.5723793677204658,
1563
+ "grad_norm": 0.31154608726501465,
1564
+ "learning_rate": 0.000499897652252295,
1565
+ "loss": 0.4639,
1566
+ "step": 9450
1567
+ },
1568
+ {
1569
+ "epoch": 1.5806988352745424,
1570
+ "grad_norm": 0.3062475323677063,
1571
+ "learning_rate": 0.0004998971106151881,
1572
+ "loss": 0.4667,
1573
+ "step": 9500
1574
+ },
1575
+ {
1576
+ "epoch": 1.5806988352745424,
1577
+ "eval_accuracy": 0.7589258816200106,
1578
+ "eval_auc": 0.840721603017736,
1579
+ "eval_f1": 0.7787355473290578,
1580
+ "eval_loss": 0.46345818042755127,
1581
+ "eval_precision": 0.7193166038484428,
1582
+ "eval_recall": 0.8488549707670788,
1583
+ "eval_runtime": 3071.5791,
1584
+ "eval_samples_per_second": 111.31,
1585
+ "eval_steps_per_second": 13.914,
1586
+ "step": 9500
1587
+ },
1588
+ {
1589
+ "epoch": 1.589018302828619,
1590
+ "grad_norm": 0.2855340838432312,
1591
+ "learning_rate": 0.0004998965689780813,
1592
+ "loss": 0.4682,
1593
+ "step": 9550
1594
+ },
1595
+ {
1596
+ "epoch": 1.5973377703826954,
1597
+ "grad_norm": 0.309037983417511,
1598
+ "learning_rate": 0.0004998960273409745,
1599
+ "loss": 0.464,
1600
+ "step": 9600
1601
+ },
1602
+ {
1603
+ "epoch": 1.605657237936772,
1604
+ "grad_norm": 0.4070012867450714,
1605
+ "learning_rate": 0.0004998954857038677,
1606
+ "loss": 0.4652,
1607
+ "step": 9650
1608
+ },
1609
+ {
1610
+ "epoch": 1.6139767054908485,
1611
+ "grad_norm": 0.4464728534221649,
1612
+ "learning_rate": 0.0004998949440667609,
1613
+ "loss": 0.4655,
1614
+ "step": 9700
1615
+ },
1616
+ {
1617
+ "epoch": 1.622296173044925,
1618
+ "grad_norm": 0.2548810541629791,
1619
+ "learning_rate": 0.000499894402429654,
1620
+ "loss": 0.4694,
1621
+ "step": 9750
1622
+ },
1623
+ {
1624
+ "epoch": 1.6306156405990015,
1625
+ "grad_norm": 0.2812168002128601,
1626
+ "learning_rate": 0.0004998938607925473,
1627
+ "loss": 0.4618,
1628
+ "step": 9800
1629
+ },
1630
+ {
1631
+ "epoch": 1.638935108153078,
1632
+ "grad_norm": 0.28069692850112915,
1633
+ "learning_rate": 0.0004998933191554404,
1634
+ "loss": 0.4669,
1635
+ "step": 9850
1636
+ },
1637
+ {
1638
+ "epoch": 1.6472545757071546,
1639
+ "grad_norm": 0.2677462100982666,
1640
+ "learning_rate": 0.0004998927775183336,
1641
+ "loss": 0.469,
1642
+ "step": 9900
1643
+ },
1644
+ {
1645
+ "epoch": 1.6555740432612311,
1646
+ "grad_norm": 0.3109247386455536,
1647
+ "learning_rate": 0.0004998922358812268,
1648
+ "loss": 0.4621,
1649
+ "step": 9950
1650
+ },
1651
+ {
1652
+ "epoch": 1.6638935108153077,
1653
+ "grad_norm": 0.3598281741142273,
1654
+ "learning_rate": 0.0004998916942441199,
1655
+ "loss": 0.4614,
1656
+ "step": 10000
1657
+ },
1658
+ {
1659
+ "epoch": 1.6638935108153077,
1660
+ "eval_accuracy": 0.7620525359828487,
1661
+ "eval_auc": 0.8427547777707038,
1662
+ "eval_f1": 0.7841862883458367,
1663
+ "eval_loss": 0.460246205329895,
1664
+ "eval_precision": 0.7171692666003542,
1665
+ "eval_recall": 0.8650194008275346,
1666
+ "eval_runtime": 3091.9645,
1667
+ "eval_samples_per_second": 110.577,
1668
+ "eval_steps_per_second": 13.822,
1669
+ "step": 10000
1670
+ },
1671
+ {
1672
+ "epoch": 1.6722129783693842,
1673
+ "grad_norm": 0.5699976682662964,
1674
+ "learning_rate": 0.0004998911526070131,
1675
+ "loss": 0.4668,
1676
+ "step": 10050
1677
+ },
1678
+ {
1679
+ "epoch": 1.6805324459234607,
1680
+ "grad_norm": 0.3142874538898468,
1681
+ "learning_rate": 0.0004998906109699063,
1682
+ "loss": 0.4634,
1683
+ "step": 10100
1684
+ },
1685
+ {
1686
+ "epoch": 1.6888519134775375,
1687
+ "grad_norm": 0.3907163441181183,
1688
+ "learning_rate": 0.0004998900693327995,
1689
+ "loss": 0.4686,
1690
+ "step": 10150
1691
+ },
1692
+ {
1693
+ "epoch": 1.697171381031614,
1694
+ "grad_norm": 0.39660388231277466,
1695
+ "learning_rate": 0.0004998895276956927,
1696
+ "loss": 0.465,
1697
+ "step": 10200
1698
+ },
1699
+ {
1700
+ "epoch": 1.7054908485856906,
1701
+ "grad_norm": 0.6148430705070496,
1702
+ "learning_rate": 0.0004998889860585859,
1703
+ "loss": 0.4654,
1704
+ "step": 10250
1705
+ },
1706
+ {
1707
+ "epoch": 1.713810316139767,
1708
+ "grad_norm": 0.2848416864871979,
1709
+ "learning_rate": 0.000499888444421479,
1710
+ "loss": 0.4617,
1711
+ "step": 10300
1712
+ },
1713
+ {
1714
+ "epoch": 1.7221297836938436,
1715
+ "grad_norm": 0.4551065266132355,
1716
+ "learning_rate": 0.0004998879027843723,
1717
+ "loss": 0.4622,
1718
+ "step": 10350
1719
+ },
1720
+ {
1721
+ "epoch": 1.7304492512479202,
1722
+ "grad_norm": 0.24504904448986053,
1723
+ "learning_rate": 0.0004998873611472654,
1724
+ "loss": 0.4558,
1725
+ "step": 10400
1726
+ },
1727
+ {
1728
+ "epoch": 1.7387687188019967,
1729
+ "grad_norm": 0.2634543776512146,
1730
+ "learning_rate": 0.0004998868195101586,
1731
+ "loss": 0.4621,
1732
+ "step": 10450
1733
+ },
1734
+ {
1735
+ "epoch": 1.7470881863560732,
1736
+ "grad_norm": 0.3404432237148285,
1737
+ "learning_rate": 0.0004998862778730518,
1738
+ "loss": 0.465,
1739
+ "step": 10500
1740
+ },
1741
+ {
1742
+ "epoch": 1.7470881863560732,
1743
+ "eval_accuracy": 0.7618653461987313,
1744
+ "eval_auc": 0.8441348324318876,
1745
+ "eval_f1": 0.7790148521301081,
1746
+ "eval_loss": 0.45925500988960266,
1747
+ "eval_precision": 0.7263860135754164,
1748
+ "eval_recall": 0.8398656280542404,
1749
+ "eval_runtime": 3075.9859,
1750
+ "eval_samples_per_second": 111.151,
1751
+ "eval_steps_per_second": 13.894,
1752
+ "step": 10500
1753
+ },
1754
+ {
1755
+ "epoch": 1.7554076539101497,
1756
+ "grad_norm": 0.35343432426452637,
1757
+ "learning_rate": 0.0004998857362359449,
1758
+ "loss": 0.4592,
1759
+ "step": 10550
1760
+ },
1761
+ {
1762
+ "epoch": 1.7637271214642263,
1763
+ "grad_norm": 0.3516612648963928,
1764
+ "learning_rate": 0.0004998851945988382,
1765
+ "loss": 0.464,
1766
+ "step": 10600
1767
+ },
1768
+ {
1769
+ "epoch": 1.7720465890183028,
1770
+ "grad_norm": 0.295074462890625,
1771
+ "learning_rate": 0.0004998846529617313,
1772
+ "loss": 0.4642,
1773
+ "step": 10650
1774
+ },
1775
+ {
1776
+ "epoch": 1.7803660565723793,
1777
+ "grad_norm": 0.3098844885826111,
1778
+ "learning_rate": 0.0004998841113246245,
1779
+ "loss": 0.463,
1780
+ "step": 10700
1781
+ },
1782
+ {
1783
+ "epoch": 1.7886855241264559,
1784
+ "grad_norm": 0.3475278317928314,
1785
+ "learning_rate": 0.0004998835696875177,
1786
+ "loss": 0.4593,
1787
+ "step": 10750
1788
+ },
1789
+ {
1790
+ "epoch": 1.7970049916805324,
1791
+ "grad_norm": 0.2945404350757599,
1792
+ "learning_rate": 0.0004998830280504109,
1793
+ "loss": 0.4663,
1794
+ "step": 10800
1795
+ },
1796
+ {
1797
+ "epoch": 1.805324459234609,
1798
+ "grad_norm": 0.3487035632133484,
1799
+ "learning_rate": 0.000499882486413304,
1800
+ "loss": 0.4637,
1801
+ "step": 10850
1802
+ },
1803
+ {
1804
+ "epoch": 1.8136439267886857,
1805
+ "grad_norm": 0.3474220931529999,
1806
+ "learning_rate": 0.0004998819447761971,
1807
+ "loss": 0.4639,
1808
+ "step": 10900
1809
+ },
1810
+ {
1811
+ "epoch": 1.8219633943427622,
1812
+ "grad_norm": 0.5383617877960205,
1813
+ "learning_rate": 0.0004998814031390903,
1814
+ "loss": 0.4615,
1815
+ "step": 10950
1816
+ },
1817
+ {
1818
+ "epoch": 1.8302828618968388,
1819
+ "grad_norm": 0.30488741397857666,
1820
+ "learning_rate": 0.0004998808615019835,
1821
+ "loss": 0.4602,
1822
+ "step": 11000
1823
+ },
1824
+ {
1825
+ "epoch": 1.8302828618968388,
1826
+ "eval_accuracy": 0.7627603473540432,
1827
+ "eval_auc": 0.8444230596164721,
1828
+ "eval_f1": 0.7833894140896224,
1829
+ "eval_loss": 0.4582211673259735,
1830
+ "eval_precision": 0.720434596814201,
1831
+ "eval_recall": 0.8584002949628078,
1832
+ "eval_runtime": 3088.1236,
1833
+ "eval_samples_per_second": 110.714,
1834
+ "eval_steps_per_second": 13.839,
1835
+ "step": 11000
1836
+ },
1837
+ {
1838
+ "epoch": 1.8386023294509153,
1839
+ "grad_norm": 0.3203362822532654,
1840
+ "learning_rate": 0.0004998803198648767,
1841
+ "loss": 0.461,
1842
+ "step": 11050
1843
+ },
1844
+ {
1845
+ "epoch": 1.8469217970049918,
1846
+ "grad_norm": 0.272316038608551,
1847
+ "learning_rate": 0.0004998797782277699,
1848
+ "loss": 0.4634,
1849
+ "step": 11100
1850
+ },
1851
+ {
1852
+ "epoch": 1.8552412645590683,
1853
+ "grad_norm": 0.3532938063144684,
1854
+ "learning_rate": 0.0004998792365906631,
1855
+ "loss": 0.4616,
1856
+ "step": 11150
1857
+ },
1858
+ {
1859
+ "epoch": 1.8635607321131449,
1860
+ "grad_norm": 0.32843783497810364,
1861
+ "learning_rate": 0.0004998786949535562,
1862
+ "loss": 0.4698,
1863
+ "step": 11200
1864
+ },
1865
+ {
1866
+ "epoch": 1.8718801996672214,
1867
+ "grad_norm": 0.43027517199516296,
1868
+ "learning_rate": 0.0004998781533164494,
1869
+ "loss": 0.4561,
1870
+ "step": 11250
1871
+ },
1872
+ {
1873
+ "epoch": 1.880199667221298,
1874
+ "grad_norm": 0.7312646508216858,
1875
+ "learning_rate": 0.0004998776116793426,
1876
+ "loss": 0.4621,
1877
+ "step": 11300
1878
+ },
1879
+ {
1880
+ "epoch": 1.8885191347753745,
1881
+ "grad_norm": 0.33167243003845215,
1882
+ "learning_rate": 0.0004998770700422358,
1883
+ "loss": 0.4587,
1884
+ "step": 11350
1885
+ },
1886
+ {
1887
+ "epoch": 1.896838602329451,
1888
+ "grad_norm": 0.25895464420318604,
1889
+ "learning_rate": 0.000499876528405129,
1890
+ "loss": 0.4629,
1891
+ "step": 11400
1892
+ },
1893
+ {
1894
+ "epoch": 1.9051580698835275,
1895
+ "grad_norm": 0.34123238921165466,
1896
+ "learning_rate": 0.0004998759867680221,
1897
+ "loss": 0.4603,
1898
+ "step": 11450
1899
+ },
1900
+ {
1901
+ "epoch": 1.913477537437604,
1902
+ "grad_norm": 0.3420165479183197,
1903
+ "learning_rate": 0.0004998754451309153,
1904
+ "loss": 0.4611,
1905
+ "step": 11500
1906
+ },
1907
+ {
1908
+ "epoch": 1.913477537437604,
1909
+ "eval_accuracy": 0.7647872617351908,
1910
+ "eval_auc": 0.8470155046356656,
1911
+ "eval_f1": 0.7896492104554169,
1912
+ "eval_loss": 0.4563252329826355,
1913
+ "eval_precision": 0.7138904653802497,
1914
+ "eval_recall": 0.8833960519462278,
1915
+ "eval_runtime": 3116.3735,
1916
+ "eval_samples_per_second": 109.711,
1917
+ "eval_steps_per_second": 13.714,
1918
+ "step": 11500
1919
+ },
1920
+ {
1921
+ "epoch": 1.9217970049916806,
1922
+ "grad_norm": 0.31535664200782776,
1923
+ "learning_rate": 0.0004998749034938085,
1924
+ "loss": 0.454,
1925
+ "step": 11550
1926
+ },
1927
+ {
1928
+ "epoch": 1.9301164725457571,
1929
+ "grad_norm": 0.3028728663921356,
1930
+ "learning_rate": 0.0004998743618567017,
1931
+ "loss": 0.4655,
1932
+ "step": 11600
1933
+ },
1934
+ {
1935
+ "epoch": 1.9384359400998337,
1936
+ "grad_norm": 0.35277822613716125,
1937
+ "learning_rate": 0.0004998738202195949,
1938
+ "loss": 0.4579,
1939
+ "step": 11650
1940
+ },
1941
+ {
1942
+ "epoch": 1.9467554076539102,
1943
+ "grad_norm": 0.2921321988105774,
1944
+ "learning_rate": 0.0004998732785824881,
1945
+ "loss": 0.4597,
1946
+ "step": 11700
1947
+ },
1948
+ {
1949
+ "epoch": 1.9550748752079867,
1950
+ "grad_norm": 0.49088171124458313,
1951
+ "learning_rate": 0.0004998727369453812,
1952
+ "loss": 0.454,
1953
+ "step": 11750
1954
+ },
1955
+ {
1956
+ "epoch": 1.9633943427620633,
1957
+ "grad_norm": 0.37039515376091003,
1958
+ "learning_rate": 0.0004998721953082744,
1959
+ "loss": 0.463,
1960
+ "step": 11800
1961
+ },
1962
+ {
1963
+ "epoch": 1.9717138103161398,
1964
+ "grad_norm": 0.3478553295135498,
1965
+ "learning_rate": 0.0004998716536711676,
1966
+ "loss": 0.4596,
1967
+ "step": 11850
1968
+ },
1969
+ {
1970
+ "epoch": 1.9800332778702163,
1971
+ "grad_norm": 0.31678304076194763,
1972
+ "learning_rate": 0.0004998711120340608,
1973
+ "loss": 0.4627,
1974
+ "step": 11900
1975
+ },
1976
+ {
1977
+ "epoch": 1.9883527454242929,
1978
+ "grad_norm": 0.2272387593984604,
1979
+ "learning_rate": 0.000499870570396954,
1980
+ "loss": 0.4627,
1981
+ "step": 11950
1982
+ },
1983
+ {
1984
+ "epoch": 1.9966722129783694,
1985
+ "grad_norm": 0.26735177636146545,
1986
+ "learning_rate": 0.0004998700287598471,
1987
+ "loss": 0.4614,
1988
+ "step": 12000
1989
+ },
1990
+ {
1991
+ "epoch": 1.9966722129783694,
1992
+ "eval_accuracy": 0.7641379471715332,
1993
+ "eval_auc": 0.8468346428705298,
1994
+ "eval_f1": 0.7830218885794621,
1995
+ "eval_loss": 0.45656195282936096,
1996
+ "eval_precision": 0.72468698016794,
1997
+ "eval_recall": 0.8515705013782489,
1998
+ "eval_runtime": 3066.5927,
1999
+ "eval_samples_per_second": 111.491,
2000
+ "eval_steps_per_second": 13.937,
2001
+ "step": 12000
2002
+ },
2003
+ {
2004
+ "epoch": 2.004991680532446,
2005
+ "grad_norm": 0.4045884907245636,
2006
+ "learning_rate": 0.0004998694871227403,
2007
+ "loss": 0.457,
2008
+ "step": 12050
2009
+ },
2010
+ {
2011
+ "epoch": 2.0133111480865225,
2012
+ "grad_norm": 0.3358103036880493,
2013
+ "learning_rate": 0.0004998689454856335,
2014
+ "loss": 0.4457,
2015
+ "step": 12100
2016
+ },
2017
+ {
2018
+ "epoch": 2.021630615640599,
2019
+ "grad_norm": 0.4295903742313385,
2020
+ "learning_rate": 0.0004998684038485267,
2021
+ "loss": 0.4526,
2022
+ "step": 12150
2023
+ },
2024
+ {
2025
+ "epoch": 2.0299500831946755,
2026
+ "grad_norm": 0.30707797408103943,
2027
+ "learning_rate": 0.0004998678622114199,
2028
+ "loss": 0.4523,
2029
+ "step": 12200
2030
+ },
2031
+ {
2032
+ "epoch": 2.038269550748752,
2033
+ "grad_norm": 0.30385756492614746,
2034
+ "learning_rate": 0.000499867320574313,
2035
+ "loss": 0.4529,
2036
+ "step": 12250
2037
+ },
2038
+ {
2039
+ "epoch": 2.0465890183028286,
2040
+ "grad_norm": 0.25600412487983704,
2041
+ "learning_rate": 0.0004998667897699483,
2042
+ "loss": 0.4551,
2043
+ "step": 12300
2044
+ },
2045
+ {
2046
+ "epoch": 2.054908485856905,
2047
+ "grad_norm": 0.4305065870285034,
2048
+ "learning_rate": 0.0004998662481328415,
2049
+ "loss": 0.4545,
2050
+ "step": 12350
2051
+ },
2052
+ {
2053
+ "epoch": 2.0632279534109816,
2054
+ "grad_norm": 0.49212226271629333,
2055
+ "learning_rate": 0.0004998657064957347,
2056
+ "loss": 0.4561,
2057
+ "step": 12400
2058
+ },
2059
+ {
2060
+ "epoch": 2.071547420965058,
2061
+ "grad_norm": 0.2785611152648926,
2062
+ "learning_rate": 0.0004998651648586279,
2063
+ "loss": 0.457,
2064
+ "step": 12450
2065
+ },
2066
+ {
2067
+ "epoch": 2.0798668885191347,
2068
+ "grad_norm": 0.37156569957733154,
2069
+ "learning_rate": 0.0004998646232215211,
2070
+ "loss": 0.4543,
2071
+ "step": 12500
2072
+ },
2073
+ {
2074
+ "epoch": 2.0798668885191347,
2075
+ "eval_accuracy": 0.7628480925653482,
2076
+ "eval_auc": 0.847242187715394,
2077
+ "eval_f1": 0.791982226053404,
2078
+ "eval_loss": 0.45966818928718567,
2079
+ "eval_precision": 0.7050727451293881,
2080
+ "eval_recall": 0.9033294512170142,
2081
+ "eval_runtime": 3110.1977,
2082
+ "eval_samples_per_second": 109.928,
2083
+ "eval_steps_per_second": 13.741,
2084
+ "step": 12500
2085
+ },
2086
+ {
2087
+ "epoch": 2.0881863560732112,
2088
+ "grad_norm": 0.3126935660839081,
2089
+ "learning_rate": 0.0004998640815844142,
2090
+ "loss": 0.4533,
2091
+ "step": 12550
2092
+ },
2093
+ {
2094
+ "epoch": 2.0965058236272878,
2095
+ "grad_norm": 0.2464996725320816,
2096
+ "learning_rate": 0.0004998635399473074,
2097
+ "loss": 0.4572,
2098
+ "step": 12600
2099
+ },
2100
+ {
2101
+ "epoch": 2.1048252911813643,
2102
+ "grad_norm": 0.5269837379455566,
2103
+ "learning_rate": 0.0004998629983102006,
2104
+ "loss": 0.4573,
2105
+ "step": 12650
2106
+ },
2107
+ {
2108
+ "epoch": 2.113144758735441,
2109
+ "grad_norm": 0.3495631217956543,
2110
+ "learning_rate": 0.0004998624566730938,
2111
+ "loss": 0.4509,
2112
+ "step": 12700
2113
+ },
2114
+ {
2115
+ "epoch": 2.1214642262895174,
2116
+ "grad_norm": 0.24060170352458954,
2117
+ "learning_rate": 0.000499861915035987,
2118
+ "loss": 0.4542,
2119
+ "step": 12750
2120
+ },
2121
+ {
2122
+ "epoch": 2.129783693843594,
2123
+ "grad_norm": 0.43895021080970764,
2124
+ "learning_rate": 0.0004998613733988801,
2125
+ "loss": 0.4528,
2126
+ "step": 12800
2127
+ },
2128
+ {
2129
+ "epoch": 2.1381031613976704,
2130
+ "grad_norm": 0.30949124693870544,
2131
+ "learning_rate": 0.0004998608317617733,
2132
+ "loss": 0.4481,
2133
+ "step": 12850
2134
+ },
2135
+ {
2136
+ "epoch": 2.146422628951747,
2137
+ "grad_norm": 0.3358418345451355,
2138
+ "learning_rate": 0.0004998602901246665,
2139
+ "loss": 0.4504,
2140
+ "step": 12900
2141
+ },
2142
+ {
2143
+ "epoch": 2.1547420965058235,
2144
+ "grad_norm": 0.40767422318458557,
2145
+ "learning_rate": 0.0004998597484875597,
2146
+ "loss": 0.4583,
2147
+ "step": 12950
2148
+ },
2149
+ {
2150
+ "epoch": 2.1630615640599,
2151
+ "grad_norm": 0.3742935061454773,
2152
+ "learning_rate": 0.0004998592068504528,
2153
+ "loss": 0.4574,
2154
+ "step": 13000
2155
+ },
2156
+ {
2157
+ "epoch": 2.1630615640599,
2158
+ "eval_accuracy": 0.7631610504856697,
2159
+ "eval_auc": 0.8489359071807063,
2160
+ "eval_f1": 0.794699065212045,
2161
+ "eval_loss": 0.45762190222740173,
2162
+ "eval_precision": 0.7010583667334669,
2163
+ "eval_recall": 0.9172114309792883,
2164
+ "eval_runtime": 3073.781,
2165
+ "eval_samples_per_second": 111.231,
2166
+ "eval_steps_per_second": 13.904,
2167
+ "step": 13000
2168
+ },
2169
+ {
2170
+ "epoch": 2.1713810316139766,
2171
+ "grad_norm": 0.3705851137638092,
2172
+ "learning_rate": 0.000499858665213346,
2173
+ "loss": 0.4513,
2174
+ "step": 13050
2175
+ },
2176
+ {
2177
+ "epoch": 2.179700499168053,
2178
+ "grad_norm": 0.222339928150177,
2179
+ "learning_rate": 0.0004998581235762391,
2180
+ "loss": 0.4536,
2181
+ "step": 13100
2182
+ },
2183
+ {
2184
+ "epoch": 2.1880199667221296,
2185
+ "grad_norm": 0.3179910182952881,
2186
+ "learning_rate": 0.0004998575819391323,
2187
+ "loss": 0.4527,
2188
+ "step": 13150
2189
+ },
2190
+ {
2191
+ "epoch": 2.196339434276206,
2192
+ "grad_norm": 0.43729254603385925,
2193
+ "learning_rate": 0.0004998570403020255,
2194
+ "loss": 0.4521,
2195
+ "step": 13200
2196
+ },
2197
+ {
2198
+ "epoch": 2.2046589018302827,
2199
+ "grad_norm": 0.31573063135147095,
2200
+ "learning_rate": 0.0004998564986649187,
2201
+ "loss": 0.4573,
2202
+ "step": 13250
2203
+ },
2204
+ {
2205
+ "epoch": 2.212978369384359,
2206
+ "grad_norm": 0.34133201837539673,
2207
+ "learning_rate": 0.0004998559570278119,
2208
+ "loss": 0.4547,
2209
+ "step": 13300
2210
+ },
2211
+ {
2212
+ "epoch": 2.2212978369384357,
2213
+ "grad_norm": 0.32229501008987427,
2214
+ "learning_rate": 0.000499855415390705,
2215
+ "loss": 0.4552,
2216
+ "step": 13350
2217
+ },
2218
+ {
2219
+ "epoch": 2.2296173044925123,
2220
+ "grad_norm": 0.25182995200157166,
2221
+ "learning_rate": 0.0004998548737535982,
2222
+ "loss": 0.4519,
2223
+ "step": 13400
2224
+ },
2225
+ {
2226
+ "epoch": 2.237936772046589,
2227
+ "grad_norm": 0.38632023334503174,
2228
+ "learning_rate": 0.0004998543321164914,
2229
+ "loss": 0.4549,
2230
+ "step": 13450
2231
+ },
2232
+ {
2233
+ "epoch": 2.2462562396006653,
2234
+ "grad_norm": 0.4629928469657898,
2235
+ "learning_rate": 0.0004998537904793846,
2236
+ "loss": 0.4532,
2237
+ "step": 13500
2238
+ },
2239
+ {
2240
+ "epoch": 2.2462562396006653,
2241
+ "eval_accuracy": 0.7667761531914395,
2242
+ "eval_auc": 0.8491075200735866,
2243
+ "eval_f1": 0.7892359376528085,
2244
+ "eval_loss": 0.4522622525691986,
2245
+ "eval_precision": 0.7196284656615124,
2246
+ "eval_recall": 0.8737512363272448,
2247
+ "eval_runtime": 3076.782,
2248
+ "eval_samples_per_second": 111.122,
2249
+ "eval_steps_per_second": 13.89,
2250
+ "step": 13500
2251
+ },
2252
+ {
2253
+ "epoch": 2.254575707154742,
2254
+ "grad_norm": 0.3204486668109894,
2255
+ "learning_rate": 0.0004998532488422778,
2256
+ "loss": 0.4549,
2257
+ "step": 13550
2258
+ },
2259
+ {
2260
+ "epoch": 2.2628951747088184,
2261
+ "grad_norm": 0.2668420076370239,
2262
+ "learning_rate": 0.0004998527072051709,
2263
+ "loss": 0.4498,
2264
+ "step": 13600
2265
+ },
2266
+ {
2267
+ "epoch": 2.271214642262895,
2268
+ "grad_norm": 0.34950193762779236,
2269
+ "learning_rate": 0.0004998521655680641,
2270
+ "loss": 0.4492,
2271
+ "step": 13650
2272
+ },
2273
+ {
2274
+ "epoch": 2.2795341098169715,
2275
+ "grad_norm": 0.39468878507614136,
2276
+ "learning_rate": 0.0004998516239309573,
2277
+ "loss": 0.4572,
2278
+ "step": 13700
2279
+ },
2280
+ {
2281
+ "epoch": 2.2878535773710484,
2282
+ "grad_norm": 0.40462568402290344,
2283
+ "learning_rate": 0.0004998510822938505,
2284
+ "loss": 0.4521,
2285
+ "step": 13750
2286
+ },
2287
+ {
2288
+ "epoch": 2.296173044925125,
2289
+ "grad_norm": 0.3331548571586609,
2290
+ "learning_rate": 0.0004998505406567437,
2291
+ "loss": 0.4473,
2292
+ "step": 13800
2293
+ },
2294
+ {
2295
+ "epoch": 2.3044925124792015,
2296
+ "grad_norm": 0.2660551965236664,
2297
+ "learning_rate": 0.0004998499990196369,
2298
+ "loss": 0.4534,
2299
+ "step": 13850
2300
+ },
2301
+ {
2302
+ "epoch": 2.312811980033278,
2303
+ "grad_norm": 0.311027854681015,
2304
+ "learning_rate": 0.00049984945738253,
2305
+ "loss": 0.45,
2306
+ "step": 13900
2307
+ },
2308
+ {
2309
+ "epoch": 2.3211314475873546,
2310
+ "grad_norm": 0.5009548664093018,
2311
+ "learning_rate": 0.0004998489157454232,
2312
+ "loss": 0.4558,
2313
+ "step": 13950
2314
+ },
2315
+ {
2316
+ "epoch": 2.329450915141431,
2317
+ "grad_norm": 0.28578829765319824,
2318
+ "learning_rate": 0.0004998483741083164,
2319
+ "loss": 0.4472,
2320
+ "step": 14000
2321
+ },
2322
+ {
2323
+ "epoch": 2.329450915141431,
2324
+ "eval_accuracy": 0.7664251723462192,
2325
+ "eval_auc": 0.8494449173929353,
2326
+ "eval_f1": 0.7848782550838166,
2327
+ "eval_loss": 0.452217161655426,
2328
+ "eval_precision": 0.7271184579602511,
2329
+ "eval_recall": 0.8526063826674236,
2330
+ "eval_runtime": 3063.8475,
2331
+ "eval_samples_per_second": 111.591,
2332
+ "eval_steps_per_second": 13.949,
2333
+ "step": 14000
2334
+ },
2335
+ {
2336
+ "epoch": 2.3377703826955076,
2337
+ "grad_norm": 0.351082444190979,
2338
+ "learning_rate": 0.0004998478324712096,
2339
+ "loss": 0.4548,
2340
+ "step": 14050
2341
+ },
2342
+ {
2343
+ "epoch": 2.346089850249584,
2344
+ "grad_norm": 0.35973915457725525,
2345
+ "learning_rate": 0.0004998472908341028,
2346
+ "loss": 0.4514,
2347
+ "step": 14100
2348
+ },
2349
+ {
2350
+ "epoch": 2.3544093178036607,
2351
+ "grad_norm": 0.4456665515899658,
2352
+ "learning_rate": 0.0004998467491969959,
2353
+ "loss": 0.4553,
2354
+ "step": 14150
2355
+ },
2356
+ {
2357
+ "epoch": 2.3627287853577372,
2358
+ "grad_norm": 0.34595686197280884,
2359
+ "learning_rate": 0.0004998462075598891,
2360
+ "loss": 0.4559,
2361
+ "step": 14200
2362
+ },
2363
+ {
2364
+ "epoch": 2.3710482529118138,
2365
+ "grad_norm": 0.3657195270061493,
2366
+ "learning_rate": 0.0004998456659227823,
2367
+ "loss": 0.4499,
2368
+ "step": 14250
2369
+ },
2370
+ {
2371
+ "epoch": 2.3793677204658903,
2372
+ "grad_norm": 0.398843377828598,
2373
+ "learning_rate": 0.0004998451242856755,
2374
+ "loss": 0.4523,
2375
+ "step": 14300
2376
+ },
2377
+ {
2378
+ "epoch": 2.387687188019967,
2379
+ "grad_norm": 0.44224244356155396,
2380
+ "learning_rate": 0.0004998445826485687,
2381
+ "loss": 0.4479,
2382
+ "step": 14350
2383
+ },
2384
+ {
2385
+ "epoch": 2.3960066555740434,
2386
+ "grad_norm": 0.4334554374217987,
2387
+ "learning_rate": 0.0004998440410114619,
2388
+ "loss": 0.452,
2389
+ "step": 14400
2390
+ },
2391
+ {
2392
+ "epoch": 2.40432612312812,
2393
+ "grad_norm": 0.36450016498565674,
2394
+ "learning_rate": 0.0004998434993743549,
2395
+ "loss": 0.4517,
2396
+ "step": 14450
2397
+ },
2398
+ {
2399
+ "epoch": 2.4126455906821964,
2400
+ "grad_norm": 0.37175169587135315,
2401
+ "learning_rate": 0.0004998429577372481,
2402
+ "loss": 0.4505,
2403
+ "step": 14500
2404
+ },
2405
+ {
2406
+ "epoch": 2.4126455906821964,
2407
+ "eval_accuracy": 0.7648048107774518,
2408
+ "eval_auc": 0.8497144763208656,
2409
+ "eval_f1": 0.7768245941722891,
2410
+ "eval_loss": 0.45364442467689514,
2411
+ "eval_precision": 0.7387407360486477,
2412
+ "eval_recall": 0.8190485108474913,
2413
+ "eval_runtime": 3069.7075,
2414
+ "eval_samples_per_second": 111.378,
2415
+ "eval_steps_per_second": 13.922,
2416
+ "step": 14500
2417
+ },
2418
+ {
2419
+ "epoch": 2.420965058236273,
2420
+ "grad_norm": 0.4115402102470398,
2421
+ "learning_rate": 0.0004998424161001413,
2422
+ "loss": 0.4522,
2423
+ "step": 14550
2424
+ },
2425
+ {
2426
+ "epoch": 2.4292845257903495,
2427
+ "grad_norm": 0.33581915497779846,
2428
+ "learning_rate": 0.0004998418744630345,
2429
+ "loss": 0.4546,
2430
+ "step": 14600
2431
+ },
2432
+ {
2433
+ "epoch": 2.437603993344426,
2434
+ "grad_norm": 0.26651909947395325,
2435
+ "learning_rate": 0.0004998413328259277,
2436
+ "loss": 0.4527,
2437
+ "step": 14650
2438
+ },
2439
+ {
2440
+ "epoch": 2.4459234608985025,
2441
+ "grad_norm": 0.3490288555622101,
2442
+ "learning_rate": 0.0004998407911888208,
2443
+ "loss": 0.4479,
2444
+ "step": 14700
2445
+ },
2446
+ {
2447
+ "epoch": 2.454242928452579,
2448
+ "grad_norm": 0.3200080990791321,
2449
+ "learning_rate": 0.000499840249551714,
2450
+ "loss": 0.4471,
2451
+ "step": 14750
2452
+ },
2453
+ {
2454
+ "epoch": 2.4625623960066556,
2455
+ "grad_norm": 0.31173649430274963,
2456
+ "learning_rate": 0.0004998397079146072,
2457
+ "loss": 0.4488,
2458
+ "step": 14800
2459
+ },
2460
+ {
2461
+ "epoch": 2.470881863560732,
2462
+ "grad_norm": 0.431302934885025,
2463
+ "learning_rate": 0.0004998391662775004,
2464
+ "loss": 0.4509,
2465
+ "step": 14850
2466
+ },
2467
+ {
2468
+ "epoch": 2.4792013311148087,
2469
+ "grad_norm": 0.37330421805381775,
2470
+ "learning_rate": 0.0004998386246403936,
2471
+ "loss": 0.4537,
2472
+ "step": 14900
2473
+ },
2474
+ {
2475
+ "epoch": 2.487520798668885,
2476
+ "grad_norm": 0.2857615649700165,
2477
+ "learning_rate": 0.0004998380830032867,
2478
+ "loss": 0.4469,
2479
+ "step": 14950
2480
+ },
2481
+ {
2482
+ "epoch": 2.4958402662229617,
2483
+ "grad_norm": 0.3119502365589142,
2484
+ "learning_rate": 0.0004998375413661799,
2485
+ "loss": 0.4506,
2486
+ "step": 15000
2487
+ },
2488
+ {
2489
+ "epoch": 2.4958402662229617,
2490
+ "eval_accuracy": 0.7662789303273774,
2491
+ "eval_auc": 0.8515752861892085,
2492
+ "eval_f1": 0.7784029616893832,
2493
+ "eval_loss": 0.45170241594314575,
2494
+ "eval_precision": 0.7397014799510899,
2495
+ "eval_recall": 0.821377780638969,
2496
+ "eval_runtime": 3072.2397,
2497
+ "eval_samples_per_second": 111.287,
2498
+ "eval_steps_per_second": 13.911,
2499
+ "step": 15000
2500
+ },
2501
+ {
2502
+ "epoch": 2.5041597337770383,
2503
+ "grad_norm": 0.31348904967308044,
2504
+ "learning_rate": 0.0004998369997290731,
2505
+ "loss": 0.4502,
2506
+ "step": 15050
2507
+ },
2508
+ {
2509
+ "epoch": 2.512479201331115,
2510
+ "grad_norm": 0.280769020318985,
2511
+ "learning_rate": 0.0004998364580919663,
2512
+ "loss": 0.4507,
2513
+ "step": 15100
2514
+ },
2515
+ {
2516
+ "epoch": 2.5207986688851913,
2517
+ "grad_norm": 0.3579796850681305,
2518
+ "learning_rate": 0.0004998359164548595,
2519
+ "loss": 0.45,
2520
+ "step": 15150
2521
+ },
2522
+ {
2523
+ "epoch": 2.529118136439268,
2524
+ "grad_norm": 0.4033232629299164,
2525
+ "learning_rate": 0.0004998353748177527,
2526
+ "loss": 0.4506,
2527
+ "step": 15200
2528
+ },
2529
+ {
2530
+ "epoch": 2.5374376039933444,
2531
+ "grad_norm": 0.3025188148021698,
2532
+ "learning_rate": 0.0004998348331806458,
2533
+ "loss": 0.4515,
2534
+ "step": 15250
2535
+ },
2536
+ {
2537
+ "epoch": 2.545757071547421,
2538
+ "grad_norm": 0.28588080406188965,
2539
+ "learning_rate": 0.0004998342915435391,
2540
+ "loss": 0.4502,
2541
+ "step": 15300
2542
+ },
2543
+ {
2544
+ "epoch": 2.5540765391014975,
2545
+ "grad_norm": 0.36141297221183777,
2546
+ "learning_rate": 0.0004998337499064322,
2547
+ "loss": 0.446,
2548
+ "step": 15350
2549
+ },
2550
+ {
2551
+ "epoch": 2.562396006655574,
2552
+ "grad_norm": 0.5286752581596375,
2553
+ "learning_rate": 0.0004998332082693254,
2554
+ "loss": 0.4511,
2555
+ "step": 15400
2556
+ },
2557
+ {
2558
+ "epoch": 2.5707154742096505,
2559
+ "grad_norm": 0.3852572441101074,
2560
+ "learning_rate": 0.0004998326666322186,
2561
+ "loss": 0.455,
2562
+ "step": 15450
2563
+ },
2564
+ {
2565
+ "epoch": 2.579034941763727,
2566
+ "grad_norm": 0.3271165192127228,
2567
+ "learning_rate": 0.0004998321249951117,
2568
+ "loss": 0.4562,
2569
+ "step": 15500
2570
+ },
2571
+ {
2572
+ "epoch": 2.579034941763727,
2573
+ "eval_accuracy": 0.7698033629814652,
2574
+ "eval_auc": 0.8525774850851346,
2575
+ "eval_f1": 0.7916979853693137,
2576
+ "eval_loss": 0.447857141494751,
2577
+ "eval_precision": 0.7226562688737818,
2578
+ "eval_recall": 0.875325541789324,
2579
+ "eval_runtime": 3063.8515,
2580
+ "eval_samples_per_second": 111.591,
2581
+ "eval_steps_per_second": 13.949,
2582
+ "step": 15500
2583
+ },
2584
+ {
2585
+ "epoch": 2.5873544093178036,
2586
+ "grad_norm": 0.29755738377571106,
2587
+ "learning_rate": 0.000499831583358005,
2588
+ "loss": 0.4446,
2589
+ "step": 15550
2590
+ },
2591
+ {
2592
+ "epoch": 2.59567387687188,
2593
+ "grad_norm": 0.3373735547065735,
2594
+ "learning_rate": 0.0004998310417208981,
2595
+ "loss": 0.4515,
2596
+ "step": 15600
2597
+ },
2598
+ {
2599
+ "epoch": 2.6039933444259566,
2600
+ "grad_norm": 0.33765482902526855,
2601
+ "learning_rate": 0.0004998305000837913,
2602
+ "loss": 0.4488,
2603
+ "step": 15650
2604
+ },
2605
+ {
2606
+ "epoch": 2.612312811980033,
2607
+ "grad_norm": 0.4411982595920563,
2608
+ "learning_rate": 0.0004998299584466845,
2609
+ "loss": 0.4498,
2610
+ "step": 15700
2611
+ },
2612
+ {
2613
+ "epoch": 2.6206322795341097,
2614
+ "grad_norm": 0.3372790217399597,
2615
+ "learning_rate": 0.0004998294168095777,
2616
+ "loss": 0.4496,
2617
+ "step": 15750
2618
+ },
2619
+ {
2620
+ "epoch": 2.6289517470881862,
2621
+ "grad_norm": 0.2755867540836334,
2622
+ "learning_rate": 0.0004998288751724709,
2623
+ "loss": 0.4504,
2624
+ "step": 15800
2625
+ },
2626
+ {
2627
+ "epoch": 2.6372712146422628,
2628
+ "grad_norm": 0.33905473351478577,
2629
+ "learning_rate": 0.0004998283335353639,
2630
+ "loss": 0.4549,
2631
+ "step": 15850
2632
+ },
2633
+ {
2634
+ "epoch": 2.6455906821963393,
2635
+ "grad_norm": 0.38283759355545044,
2636
+ "learning_rate": 0.0004998277918982571,
2637
+ "loss": 0.445,
2638
+ "step": 15900
2639
+ },
2640
+ {
2641
+ "epoch": 2.653910149750416,
2642
+ "grad_norm": 0.3542182743549347,
2643
+ "learning_rate": 0.0004998272502611503,
2644
+ "loss": 0.448,
2645
+ "step": 15950
2646
+ },
2647
+ {
2648
+ "epoch": 2.6622296173044924,
2649
+ "grad_norm": 0.42483657598495483,
2650
+ "learning_rate": 0.0004998267086240435,
2651
+ "loss": 0.4434,
2652
+ "step": 16000
2653
+ },
2654
+ {
2655
+ "epoch": 2.6622296173044924,
2656
+ "eval_accuracy": 0.769505029263028,
2657
+ "eval_auc": 0.8523741424932588,
2658
+ "eval_f1": 0.7897149627226103,
2659
+ "eval_loss": 0.4486808776855469,
2660
+ "eval_precision": 0.7257674518978464,
2661
+ "eval_recall": 0.8660201674967373,
2662
+ "eval_runtime": 3076.2646,
2663
+ "eval_samples_per_second": 111.141,
2664
+ "eval_steps_per_second": 13.893,
2665
+ "step": 16000
2666
+ },
2667
+ {
2668
+ "epoch": 2.670549084858569,
2669
+ "grad_norm": 0.2930859327316284,
2670
+ "learning_rate": 0.0004998261669869367,
2671
+ "loss": 0.4467,
2672
+ "step": 16050
2673
+ },
2674
+ {
2675
+ "epoch": 2.6788685524126454,
2676
+ "grad_norm": 0.4802510142326355,
2677
+ "learning_rate": 0.0004998256253498299,
2678
+ "loss": 0.4472,
2679
+ "step": 16100
2680
+ },
2681
+ {
2682
+ "epoch": 2.687188019966722,
2683
+ "grad_norm": 0.30784839391708374,
2684
+ "learning_rate": 0.000499825083712723,
2685
+ "loss": 0.4489,
2686
+ "step": 16150
2687
+ },
2688
+ {
2689
+ "epoch": 2.695507487520799,
2690
+ "grad_norm": 0.27913177013397217,
2691
+ "learning_rate": 0.0004998245420756162,
2692
+ "loss": 0.451,
2693
+ "step": 16200
2694
+ },
2695
+ {
2696
+ "epoch": 2.7038269550748755,
2697
+ "grad_norm": 0.3060939311981201,
2698
+ "learning_rate": 0.0004998240004385094,
2699
+ "loss": 0.446,
2700
+ "step": 16250
2701
+ },
2702
+ {
2703
+ "epoch": 2.712146422628952,
2704
+ "grad_norm": 0.3916643261909485,
2705
+ "learning_rate": 0.0004998234696341447,
2706
+ "loss": 0.449,
2707
+ "step": 16300
2708
+ },
2709
+ {
2710
+ "epoch": 2.7204658901830285,
2711
+ "grad_norm": 0.3149168789386749,
2712
+ "learning_rate": 0.0004998229279970379,
2713
+ "loss": 0.4484,
2714
+ "step": 16350
2715
+ },
2716
+ {
2717
+ "epoch": 2.728785357737105,
2718
+ "grad_norm": 0.3204551339149475,
2719
+ "learning_rate": 0.000499822386359931,
2720
+ "loss": 0.4467,
2721
+ "step": 16400
2722
+ },
2723
+ {
2724
+ "epoch": 2.7371048252911816,
2725
+ "grad_norm": 0.4137204885482788,
2726
+ "learning_rate": 0.0004998218447228243,
2727
+ "loss": 0.4503,
2728
+ "step": 16450
2729
+ },
2730
+ {
2731
+ "epoch": 2.745424292845258,
2732
+ "grad_norm": 0.34219491481781006,
2733
+ "learning_rate": 0.0004998213030857175,
2734
+ "loss": 0.4482,
2735
+ "step": 16500
2736
+ },
2737
+ {
2738
+ "epoch": 2.745424292845258,
2739
+ "eval_accuracy": 0.7704673017470072,
2740
+ "eval_auc": 0.8527454649367189,
2741
+ "eval_f1": 0.7930540722281555,
2742
+ "eval_loss": 0.4480786919593811,
2743
+ "eval_precision": 0.7217273189790061,
2744
+ "eval_recall": 0.8800250484289134,
2745
+ "eval_runtime": 3081.5516,
2746
+ "eval_samples_per_second": 110.95,
2747
+ "eval_steps_per_second": 13.869,
2748
+ "step": 16500
2749
+ },
2750
+ {
2751
+ "epoch": 2.7537437603993347,
2752
+ "grad_norm": 0.38494977355003357,
2753
+ "learning_rate": 0.0004998207614486106,
2754
+ "loss": 0.4491,
2755
+ "step": 16550
2756
+ },
2757
+ {
2758
+ "epoch": 2.762063227953411,
2759
+ "grad_norm": 0.3267413079738617,
2760
+ "learning_rate": 0.0004998202198115037,
2761
+ "loss": 0.4502,
2762
+ "step": 16600
2763
+ },
2764
+ {
2765
+ "epoch": 2.7703826955074877,
2766
+ "grad_norm": 0.39887621998786926,
2767
+ "learning_rate": 0.000499819678174397,
2768
+ "loss": 0.4529,
2769
+ "step": 16650
2770
+ },
2771
+ {
2772
+ "epoch": 2.7787021630615643,
2773
+ "grad_norm": 0.4172428548336029,
2774
+ "learning_rate": 0.0004998191365372901,
2775
+ "loss": 0.4517,
2776
+ "step": 16700
2777
+ },
2778
+ {
2779
+ "epoch": 2.787021630615641,
2780
+ "grad_norm": 0.3547029197216034,
2781
+ "learning_rate": 0.0004998185949001833,
2782
+ "loss": 0.4471,
2783
+ "step": 16750
2784
+ },
2785
+ {
2786
+ "epoch": 2.7953410981697173,
2787
+ "grad_norm": 0.31628596782684326,
2788
+ "learning_rate": 0.0004998180532630765,
2789
+ "loss": 0.4472,
2790
+ "step": 16800
2791
+ },
2792
+ {
2793
+ "epoch": 2.803660565723794,
2794
+ "grad_norm": 0.29753875732421875,
2795
+ "learning_rate": 0.0004998175116259696,
2796
+ "loss": 0.4506,
2797
+ "step": 16850
2798
+ },
2799
+ {
2800
+ "epoch": 2.8119800332778704,
2801
+ "grad_norm": 0.48493313789367676,
2802
+ "learning_rate": 0.0004998169699888629,
2803
+ "loss": 0.4502,
2804
+ "step": 16900
2805
+ },
2806
+ {
2807
+ "epoch": 2.820299500831947,
2808
+ "grad_norm": 0.36175137758255005,
2809
+ "learning_rate": 0.000499816428351756,
2810
+ "loss": 0.4504,
2811
+ "step": 16950
2812
+ },
2813
+ {
2814
+ "epoch": 2.8286189683860234,
2815
+ "grad_norm": 0.3172094523906708,
2816
+ "learning_rate": 0.0004998158867146492,
2817
+ "loss": 0.4455,
2818
+ "step": 17000
2819
+ },
2820
+ {
2821
+ "epoch": 2.8286189683860234,
2822
+ "eval_accuracy": 0.770005176967467,
2823
+ "eval_auc": 0.85512334595064,
2824
+ "eval_f1": 0.782045916288558,
2825
+ "eval_loss": 0.4468492567539215,
2826
+ "eval_precision": 0.7428258511568151,
2827
+ "eval_recall": 0.8256383545289081,
2828
+ "eval_runtime": 3103.5745,
2829
+ "eval_samples_per_second": 110.163,
2830
+ "eval_steps_per_second": 13.771,
2831
+ "step": 17000
2832
+ },
2833
+ {
2834
+ "epoch": 2.8369384359401,
2835
+ "grad_norm": 0.49940770864486694,
2836
+ "learning_rate": 0.0004998153450775424,
2837
+ "loss": 0.4467,
2838
+ "step": 17050
2839
+ },
2840
+ {
2841
+ "epoch": 2.8452579034941765,
2842
+ "grad_norm": 0.3779182434082031,
2843
+ "learning_rate": 0.0004998148034404356,
2844
+ "loss": 0.4427,
2845
+ "step": 17100
2846
+ },
2847
+ {
2848
+ "epoch": 2.853577371048253,
2849
+ "grad_norm": 0.3529649078845978,
2850
+ "learning_rate": 0.0004998142726360708,
2851
+ "loss": 0.4469,
2852
+ "step": 17150
2853
+ },
2854
+ {
2855
+ "epoch": 2.8618968386023296,
2856
+ "grad_norm": 0.421783447265625,
2857
+ "learning_rate": 0.0004998137309989642,
2858
+ "loss": 0.4449,
2859
+ "step": 17200
2860
+ },
2861
+ {
2862
+ "epoch": 2.870216306156406,
2863
+ "grad_norm": 0.38324880599975586,
2864
+ "learning_rate": 0.0004998131893618572,
2865
+ "loss": 0.4446,
2866
+ "step": 17250
2867
+ },
2868
+ {
2869
+ "epoch": 2.8785357737104826,
2870
+ "grad_norm": 0.43824031949043274,
2871
+ "learning_rate": 0.0004998126477247504,
2872
+ "loss": 0.4465,
2873
+ "step": 17300
2874
+ },
2875
+ {
2876
+ "epoch": 2.886855241264559,
2877
+ "grad_norm": 0.3818030059337616,
2878
+ "learning_rate": 0.0004998121060876436,
2879
+ "loss": 0.4459,
2880
+ "step": 17350
2881
+ },
2882
+ {
2883
+ "epoch": 2.8951747088186357,
2884
+ "grad_norm": 0.30165761709213257,
2885
+ "learning_rate": 0.0004998115644505367,
2886
+ "loss": 0.4505,
2887
+ "step": 17400
2888
+ },
2889
+ {
2890
+ "epoch": 2.9034941763727122,
2891
+ "grad_norm": 0.28733378648757935,
2892
+ "learning_rate": 0.00049981102281343,
2893
+ "loss": 0.4526,
2894
+ "step": 17450
2895
+ },
2896
+ {
2897
+ "epoch": 2.9118136439267888,
2898
+ "grad_norm": 0.3203652799129486,
2899
+ "learning_rate": 0.0004998104811763231,
2900
+ "loss": 0.4428,
2901
+ "step": 17500
2902
+ },
2903
+ {
2904
+ "epoch": 2.9118136439267888,
2905
+ "eval_accuracy": 0.7715377933249293,
2906
+ "eval_auc": 0.8548695984738128,
2907
+ "eval_f1": 0.7888806302958228,
2908
+ "eval_loss": 0.44894230365753174,
2909
+ "eval_precision": 0.7329245264067177,
2910
+ "eval_recall": 0.8540870491429107,
2911
+ "eval_runtime": 3097.7551,
2912
+ "eval_samples_per_second": 110.37,
2913
+ "eval_steps_per_second": 13.796,
2914
+ "step": 17500
2915
+ },
2916
+ {
2917
+ "epoch": 2.9201331114808653,
2918
+ "grad_norm": 0.2848743498325348,
2919
+ "learning_rate": 0.0004998099395392163,
2920
+ "loss": 0.4506,
2921
+ "step": 17550
2922
+ },
2923
+ {
2924
+ "epoch": 2.928452579034942,
2925
+ "grad_norm": 0.3639114499092102,
2926
+ "learning_rate": 0.0004998093979021095,
2927
+ "loss": 0.45,
2928
+ "step": 17600
2929
+ },
2930
+ {
2931
+ "epoch": 2.9367720465890184,
2932
+ "grad_norm": 0.35603734850883484,
2933
+ "learning_rate": 0.0004998088562650027,
2934
+ "loss": 0.4445,
2935
+ "step": 17650
2936
+ },
2937
+ {
2938
+ "epoch": 2.945091514143095,
2939
+ "grad_norm": 0.3066865801811218,
2940
+ "learning_rate": 0.0004998083146278958,
2941
+ "loss": 0.4486,
2942
+ "step": 17700
2943
+ },
2944
+ {
2945
+ "epoch": 2.9534109816971714,
2946
+ "grad_norm": 0.30339953303337097,
2947
+ "learning_rate": 0.000499807772990789,
2948
+ "loss": 0.4523,
2949
+ "step": 17750
2950
+ },
2951
+ {
2952
+ "epoch": 2.961730449251248,
2953
+ "grad_norm": 0.2876887917518616,
2954
+ "learning_rate": 0.0004998072313536822,
2955
+ "loss": 0.4506,
2956
+ "step": 17800
2957
+ },
2958
+ {
2959
+ "epoch": 2.9700499168053245,
2960
+ "grad_norm": 0.32773932814598083,
2961
+ "learning_rate": 0.0004998066897165754,
2962
+ "loss": 0.4459,
2963
+ "step": 17850
2964
+ },
2965
+ {
2966
+ "epoch": 2.978369384359401,
2967
+ "grad_norm": 0.2950334846973419,
2968
+ "learning_rate": 0.0004998061480794686,
2969
+ "loss": 0.4454,
2970
+ "step": 17900
2971
+ },
2972
+ {
2973
+ "epoch": 2.9866888519134775,
2974
+ "grad_norm": 0.4425393044948578,
2975
+ "learning_rate": 0.0004998056064423617,
2976
+ "loss": 0.4434,
2977
+ "step": 17950
2978
+ },
2979
+ {
2980
+ "epoch": 2.995008319467554,
2981
+ "grad_norm": 0.2697887718677521,
2982
+ "learning_rate": 0.000499805064805255,
2983
+ "loss": 0.4465,
2984
+ "step": 18000
2985
+ },
2986
+ {
2987
+ "epoch": 2.995008319467554,
2988
+ "eval_accuracy": 0.773348269518191,
2989
+ "eval_auc": 0.8564303811560599,
2990
+ "eval_f1": 0.7921942795235261,
2991
+ "eval_loss": 0.4447154104709625,
2992
+ "eval_precision": 0.7310888599612942,
2993
+ "eval_recall": 0.8644458620346581,
2994
+ "eval_runtime": 3118.3883,
2995
+ "eval_samples_per_second": 109.64,
2996
+ "eval_steps_per_second": 13.705,
2997
+ "step": 18000
2998
+ }
2999
+ ],
3000
+ "logging_steps": 50,
3001
+ "max_steps": 90150,
3002
+ "num_input_tokens_seen": 0,
3003
+ "num_train_epochs": 15,
3004
+ "save_steps": 500,
3005
+ "stateful_callbacks": {
3006
+ "TrainerControl": {
3007
+ "args": {
3008
+ "should_epoch_stop": false,
3009
+ "should_evaluate": false,
3010
+ "should_log": false,
3011
+ "should_save": true,
3012
+ "should_training_stop": false
3013
+ },
3014
+ "attributes": {}
3015
+ }
3016
+ },
3017
+ "total_flos": 9.267314096665788e+18,
3018
+ "train_batch_size": 512,
3019
+ "trial_name": null,
3020
+ "trial_params": null
3021
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75980e262b6c0c19f65e1b1e28a8eefd3ed3d9eca42533bb813424fdd742137
3
+ size 5368