sophiefy commited on
Commit
6bcb4b9
1 Parent(s): 4a408f2
README.md CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: Qwen/Qwen-7B-Chat-Int4
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 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen-7B-Chat-Int4",
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": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "c_attn",
24
+ "w2",
25
+ "w1",
26
+ "c_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae35d214bd16fb0d2dec40bf7ed31dfab98934e0cb6bd06da11cc5f51e05612
3
+ size 286302920
qwen.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "<|endoftext|>"
3
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "auto_map": {
4
+ "AutoTokenizer": [
5
+ "Qwen/Qwen-7B-Chat-Int4--tokenization_qwen.QWenTokenizer",
6
+ null
7
+ ]
8
+ },
9
+ "clean_up_tokenization_spaces": true,
10
+ "model_max_length": 512,
11
+ "pad_token": "<|endoftext|>",
12
+ "padding_side": "right",
13
+ "tokenizer_class": "QWenTokenizer"
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,2004 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9946949602122017,
5
+ "eval_steps": 500,
6
+ "global_step": 282,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007073386383731211,
13
+ "grad_norm": 0.4045802652835846,
14
+ "learning_rate": 0.0,
15
+ "loss": 2.592,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.014146772767462422,
20
+ "grad_norm": 0.4087854325771332,
21
+ "learning_rate": 0.00018927892607143717,
22
+ "loss": 2.3663,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.021220159151193633,
27
+ "grad_norm": 0.391991525888443,
28
+ "learning_rate": 0.0003,
29
+ "loss": 2.3427,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.028293545534924844,
34
+ "grad_norm": 0.47497037053108215,
35
+ "learning_rate": 0.0003,
36
+ "loss": 2.4095,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03536693191865606,
41
+ "grad_norm": 0.3936399221420288,
42
+ "learning_rate": 0.0003,
43
+ "loss": 1.7048,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.042440318302387266,
48
+ "grad_norm": 0.6155605316162109,
49
+ "learning_rate": 0.0003,
50
+ "loss": 1.8204,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.04951370468611848,
55
+ "grad_norm": 0.49080851674079895,
56
+ "learning_rate": 0.0003,
57
+ "loss": 1.4646,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.05658709106984969,
62
+ "grad_norm": 0.5759713053703308,
63
+ "learning_rate": 0.0003,
64
+ "loss": 1.4984,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0636604774535809,
69
+ "grad_norm": 0.5349287390708923,
70
+ "learning_rate": 0.0003,
71
+ "loss": 1.3691,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.07073386383731212,
76
+ "grad_norm": 0.3948557674884796,
77
+ "learning_rate": 0.0003,
78
+ "loss": 1.4401,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.07780725022104333,
83
+ "grad_norm": 0.37507522106170654,
84
+ "learning_rate": 0.0003,
85
+ "loss": 1.1852,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.08488063660477453,
90
+ "grad_norm": 0.32405033707618713,
91
+ "learning_rate": 0.0003,
92
+ "loss": 1.051,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.09195402298850575,
97
+ "grad_norm": 0.4525175392627716,
98
+ "learning_rate": 0.0003,
99
+ "loss": 1.2695,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.09902740937223696,
104
+ "grad_norm": 0.42692625522613525,
105
+ "learning_rate": 0.0003,
106
+ "loss": 1.1057,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.10610079575596817,
111
+ "grad_norm": 0.5049455761909485,
112
+ "learning_rate": 0.0003,
113
+ "loss": 1.6851,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.11317418213969938,
118
+ "grad_norm": 0.38740119338035583,
119
+ "learning_rate": 0.0003,
120
+ "loss": 1.2632,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.12024756852343059,
125
+ "grad_norm": 0.3729807138442993,
126
+ "learning_rate": 0.0003,
127
+ "loss": 1.2857,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.1273209549071618,
132
+ "grad_norm": 0.4548921287059784,
133
+ "learning_rate": 0.0003,
134
+ "loss": 1.2233,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.134394341290893,
139
+ "grad_norm": 0.4324336051940918,
140
+ "learning_rate": 0.0003,
141
+ "loss": 1.1058,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.14146772767462423,
146
+ "grad_norm": 0.5775079727172852,
147
+ "learning_rate": 0.0003,
148
+ "loss": 1.0475,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.14854111405835543,
153
+ "grad_norm": 0.40563157200813293,
154
+ "learning_rate": 0.0003,
155
+ "loss": 1.1364,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.15561450044208666,
160
+ "grad_norm": 0.4697245657444,
161
+ "learning_rate": 0.0003,
162
+ "loss": 1.3599,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.16268788682581786,
167
+ "grad_norm": 0.42879530787467957,
168
+ "learning_rate": 0.0003,
169
+ "loss": 1.1086,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.16976127320954906,
174
+ "grad_norm": 0.42367979884147644,
175
+ "learning_rate": 0.0003,
176
+ "loss": 0.9705,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.1768346595932803,
181
+ "grad_norm": 0.3987770080566406,
182
+ "learning_rate": 0.0003,
183
+ "loss": 1.0087,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.1839080459770115,
188
+ "grad_norm": 0.3194337487220764,
189
+ "learning_rate": 0.0003,
190
+ "loss": 0.8143,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.1909814323607427,
195
+ "grad_norm": 0.3626921474933624,
196
+ "learning_rate": 0.0003,
197
+ "loss": 0.9763,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.19805481874447392,
202
+ "grad_norm": 0.38496437668800354,
203
+ "learning_rate": 0.0003,
204
+ "loss": 0.6315,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.20512820512820512,
209
+ "grad_norm": 0.41984379291534424,
210
+ "learning_rate": 0.0003,
211
+ "loss": 1.0303,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.21220159151193635,
216
+ "grad_norm": 0.4012935161590576,
217
+ "learning_rate": 0.0003,
218
+ "loss": 0.9862,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.21927497789566755,
223
+ "grad_norm": 0.40578627586364746,
224
+ "learning_rate": 0.0003,
225
+ "loss": 1.0094,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.22634836427939875,
230
+ "grad_norm": 0.41153454780578613,
231
+ "learning_rate": 0.0003,
232
+ "loss": 0.966,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.23342175066312998,
237
+ "grad_norm": 0.3835723400115967,
238
+ "learning_rate": 0.0003,
239
+ "loss": 0.5704,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.24049513704686118,
244
+ "grad_norm": 0.4588032066822052,
245
+ "learning_rate": 0.0003,
246
+ "loss": 0.8564,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.2475685234305924,
251
+ "grad_norm": 0.42644572257995605,
252
+ "learning_rate": 0.0003,
253
+ "loss": 0.8448,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.2546419098143236,
258
+ "grad_norm": 0.44491246342658997,
259
+ "learning_rate": 0.0003,
260
+ "loss": 1.1484,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.26171529619805484,
265
+ "grad_norm": 0.44271302223205566,
266
+ "learning_rate": 0.0003,
267
+ "loss": 0.7746,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.268788682581786,
272
+ "grad_norm": 0.4080619215965271,
273
+ "learning_rate": 0.0003,
274
+ "loss": 0.5377,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.27586206896551724,
279
+ "grad_norm": 0.3697488605976105,
280
+ "learning_rate": 0.0003,
281
+ "loss": 0.9936,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.28293545534924847,
286
+ "grad_norm": 0.37987953424453735,
287
+ "learning_rate": 0.0003,
288
+ "loss": 0.7066,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.29000884173297964,
293
+ "grad_norm": 0.5652127861976624,
294
+ "learning_rate": 0.0003,
295
+ "loss": 0.8813,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.29708222811671087,
300
+ "grad_norm": 0.45179855823516846,
301
+ "learning_rate": 0.0003,
302
+ "loss": 0.6442,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3041556145004421,
307
+ "grad_norm": 0.40251022577285767,
308
+ "learning_rate": 0.0003,
309
+ "loss": 0.6876,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.3112290008841733,
314
+ "grad_norm": 0.3425946831703186,
315
+ "learning_rate": 0.0003,
316
+ "loss": 0.4759,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.3183023872679045,
321
+ "grad_norm": 0.3156929016113281,
322
+ "learning_rate": 0.0003,
323
+ "loss": 0.5237,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.3253757736516357,
328
+ "grad_norm": 0.5097647309303284,
329
+ "learning_rate": 0.0003,
330
+ "loss": 1.0965,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.33244916003536695,
335
+ "grad_norm": 0.4245418906211853,
336
+ "learning_rate": 0.0003,
337
+ "loss": 0.717,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.3395225464190981,
342
+ "grad_norm": 0.36271074414253235,
343
+ "learning_rate": 0.0003,
344
+ "loss": 0.925,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.34659593280282935,
349
+ "grad_norm": 0.3543199300765991,
350
+ "learning_rate": 0.0003,
351
+ "loss": 0.52,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.3536693191865606,
356
+ "grad_norm": 0.4760311245918274,
357
+ "learning_rate": 0.0003,
358
+ "loss": 0.6514,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.36074270557029176,
363
+ "grad_norm": 0.36290043592453003,
364
+ "learning_rate": 0.0003,
365
+ "loss": 0.6391,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.367816091954023,
370
+ "grad_norm": 0.4390805959701538,
371
+ "learning_rate": 0.0003,
372
+ "loss": 0.7822,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.3748894783377542,
377
+ "grad_norm": 0.402041494846344,
378
+ "learning_rate": 0.0003,
379
+ "loss": 0.5967,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.3819628647214854,
384
+ "grad_norm": 0.42580777406692505,
385
+ "learning_rate": 0.0003,
386
+ "loss": 0.7591,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.3890362511052166,
391
+ "grad_norm": 0.4342993199825287,
392
+ "learning_rate": 0.0003,
393
+ "loss": 0.9428,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.39610963748894784,
398
+ "grad_norm": 0.42949816584587097,
399
+ "learning_rate": 0.0003,
400
+ "loss": 0.6546,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.40318302387267907,
405
+ "grad_norm": 0.44655221700668335,
406
+ "learning_rate": 0.0003,
407
+ "loss": 0.6999,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.41025641025641024,
412
+ "grad_norm": 0.38236895203590393,
413
+ "learning_rate": 0.0003,
414
+ "loss": 0.5464,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.41732979664014147,
419
+ "grad_norm": 0.39055347442626953,
420
+ "learning_rate": 0.0003,
421
+ "loss": 0.8726,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.4244031830238727,
426
+ "grad_norm": 0.47743409872055054,
427
+ "learning_rate": 0.0003,
428
+ "loss": 0.6839,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.43147656940760387,
433
+ "grad_norm": 0.5571391582489014,
434
+ "learning_rate": 0.0003,
435
+ "loss": 0.6384,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.4385499557913351,
440
+ "grad_norm": 0.4612606465816498,
441
+ "learning_rate": 0.0003,
442
+ "loss": 0.8187,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.44562334217506633,
447
+ "grad_norm": 0.3999072313308716,
448
+ "learning_rate": 0.0003,
449
+ "loss": 0.6792,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.4526967285587975,
454
+ "grad_norm": 0.4889736771583557,
455
+ "learning_rate": 0.0003,
456
+ "loss": 0.7837,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.45977011494252873,
461
+ "grad_norm": 0.4411163628101349,
462
+ "learning_rate": 0.0003,
463
+ "loss": 0.7325,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.46684350132625996,
468
+ "grad_norm": 0.4137038588523865,
469
+ "learning_rate": 0.0003,
470
+ "loss": 0.5974,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.4739168877099912,
475
+ "grad_norm": 0.4226423501968384,
476
+ "learning_rate": 0.0003,
477
+ "loss": 0.6251,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.48099027409372236,
482
+ "grad_norm": 0.4461803734302521,
483
+ "learning_rate": 0.0003,
484
+ "loss": 0.5721,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.4880636604774536,
489
+ "grad_norm": 0.4135233461856842,
490
+ "learning_rate": 0.0003,
491
+ "loss": 0.708,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.4951370468611848,
496
+ "grad_norm": 0.40338656306266785,
497
+ "learning_rate": 0.0003,
498
+ "loss": 0.6943,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.502210433244916,
503
+ "grad_norm": 0.47266095876693726,
504
+ "learning_rate": 0.0003,
505
+ "loss": 0.6883,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.5092838196286472,
510
+ "grad_norm": 0.45008358359336853,
511
+ "learning_rate": 0.0003,
512
+ "loss": 0.6347,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.5163572060123784,
517
+ "grad_norm": 0.36589792370796204,
518
+ "learning_rate": 0.0003,
519
+ "loss": 0.746,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.5234305923961097,
524
+ "grad_norm": 0.36300450563430786,
525
+ "learning_rate": 0.0003,
526
+ "loss": 0.7846,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.5305039787798409,
531
+ "grad_norm": 0.42305129766464233,
532
+ "learning_rate": 0.0003,
533
+ "loss": 0.7909,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.537577365163572,
538
+ "grad_norm": 0.36807361245155334,
539
+ "learning_rate": 0.0003,
540
+ "loss": 0.578,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.5446507515473032,
545
+ "grad_norm": 0.3479249179363251,
546
+ "learning_rate": 0.0003,
547
+ "loss": 0.4358,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.5517241379310345,
552
+ "grad_norm": 0.4373302161693573,
553
+ "learning_rate": 0.0003,
554
+ "loss": 0.8263,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.5587975243147657,
559
+ "grad_norm": 0.5427613854408264,
560
+ "learning_rate": 0.0003,
561
+ "loss": 0.7728,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.5658709106984969,
566
+ "grad_norm": 0.4510067403316498,
567
+ "learning_rate": 0.0003,
568
+ "loss": 0.7188,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.5729442970822282,
573
+ "grad_norm": 0.3964546322822571,
574
+ "learning_rate": 0.0003,
575
+ "loss": 0.6707,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.5800176834659593,
580
+ "grad_norm": 0.40177956223487854,
581
+ "learning_rate": 0.0003,
582
+ "loss": 0.7056,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.5870910698496905,
587
+ "grad_norm": 0.4081084728240967,
588
+ "learning_rate": 0.0003,
589
+ "loss": 0.6588,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.5941644562334217,
594
+ "grad_norm": 0.3595137298107147,
595
+ "learning_rate": 0.0003,
596
+ "loss": 0.6469,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.601237842617153,
601
+ "grad_norm": 0.40407031774520874,
602
+ "learning_rate": 0.0003,
603
+ "loss": 0.6954,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.6083112290008842,
608
+ "grad_norm": 0.47531482577323914,
609
+ "learning_rate": 0.0003,
610
+ "loss": 0.5842,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.6153846153846154,
615
+ "grad_norm": 0.3669019639492035,
616
+ "learning_rate": 0.0003,
617
+ "loss": 0.6278,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.6224580017683466,
622
+ "grad_norm": 0.3638778030872345,
623
+ "learning_rate": 0.0003,
624
+ "loss": 0.4731,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.6295313881520778,
629
+ "grad_norm": 0.39883217215538025,
630
+ "learning_rate": 0.0003,
631
+ "loss": 0.6891,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.636604774535809,
636
+ "grad_norm": 0.627139687538147,
637
+ "learning_rate": 0.0003,
638
+ "loss": 0.58,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.6436781609195402,
643
+ "grad_norm": 0.5339258313179016,
644
+ "learning_rate": 0.0003,
645
+ "loss": 0.6198,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.6507515473032714,
650
+ "grad_norm": 0.4699147939682007,
651
+ "learning_rate": 0.0003,
652
+ "loss": 0.7175,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.6578249336870027,
657
+ "grad_norm": 0.3144320249557495,
658
+ "learning_rate": 0.0003,
659
+ "loss": 0.4438,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.6648983200707339,
664
+ "grad_norm": 0.47343114018440247,
665
+ "learning_rate": 0.0003,
666
+ "loss": 0.7511,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.671971706454465,
671
+ "grad_norm": 0.43690529465675354,
672
+ "learning_rate": 0.0003,
673
+ "loss": 0.4847,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.6790450928381963,
678
+ "grad_norm": 0.5092759728431702,
679
+ "learning_rate": 0.0003,
680
+ "loss": 0.6703,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.6861184792219275,
685
+ "grad_norm": 0.7045844793319702,
686
+ "learning_rate": 0.0003,
687
+ "loss": 0.717,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.6931918656056587,
692
+ "grad_norm": 0.34709087014198303,
693
+ "learning_rate": 0.0003,
694
+ "loss": 0.5597,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.7002652519893899,
699
+ "grad_norm": 0.39407986402511597,
700
+ "learning_rate": 0.0003,
701
+ "loss": 0.5079,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.7073386383731212,
706
+ "grad_norm": 0.6836314797401428,
707
+ "learning_rate": 0.0003,
708
+ "loss": 0.5947,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.7144120247568524,
713
+ "grad_norm": 0.4487530291080475,
714
+ "learning_rate": 0.0003,
715
+ "loss": 0.5638,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.7214854111405835,
720
+ "grad_norm": 0.34299322962760925,
721
+ "learning_rate": 0.0003,
722
+ "loss": 0.4268,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.7285587975243147,
727
+ "grad_norm": 0.4325425624847412,
728
+ "learning_rate": 0.0003,
729
+ "loss": 0.7195,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.735632183908046,
734
+ "grad_norm": 0.3857167959213257,
735
+ "learning_rate": 0.0003,
736
+ "loss": 0.5525,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.7427055702917772,
741
+ "grad_norm": 0.5439281463623047,
742
+ "learning_rate": 0.0003,
743
+ "loss": 0.8488,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.7497789566755084,
748
+ "grad_norm": 0.5054299831390381,
749
+ "learning_rate": 0.0003,
750
+ "loss": 0.5801,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.7568523430592397,
755
+ "grad_norm": 0.5152317881584167,
756
+ "learning_rate": 0.0003,
757
+ "loss": 0.6918,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.7639257294429708,
762
+ "grad_norm": 0.32669249176979065,
763
+ "learning_rate": 0.0003,
764
+ "loss": 0.5322,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.770999115826702,
769
+ "grad_norm": 0.4302417039871216,
770
+ "learning_rate": 0.0003,
771
+ "loss": 0.6439,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.7780725022104332,
776
+ "grad_norm": 0.4388223886489868,
777
+ "learning_rate": 0.0003,
778
+ "loss": 0.6196,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.7851458885941645,
783
+ "grad_norm": 0.42924442887306213,
784
+ "learning_rate": 0.0003,
785
+ "loss": 0.5175,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.7922192749778957,
790
+ "grad_norm": 0.4361798167228699,
791
+ "learning_rate": 0.0003,
792
+ "loss": 0.5342,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.7992926613616269,
797
+ "grad_norm": 0.4133489429950714,
798
+ "learning_rate": 0.0003,
799
+ "loss": 0.5639,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.8063660477453581,
804
+ "grad_norm": 0.34224194288253784,
805
+ "learning_rate": 0.0003,
806
+ "loss": 0.4695,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.8134394341290893,
811
+ "grad_norm": 0.4219891428947449,
812
+ "learning_rate": 0.0003,
813
+ "loss": 0.6307,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.8205128205128205,
818
+ "grad_norm": 0.44273802638053894,
819
+ "learning_rate": 0.0003,
820
+ "loss": 0.5475,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.8275862068965517,
825
+ "grad_norm": 0.42054426670074463,
826
+ "learning_rate": 0.0003,
827
+ "loss": 0.827,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.8346595932802829,
832
+ "grad_norm": 0.4792965054512024,
833
+ "learning_rate": 0.0003,
834
+ "loss": 0.6,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.8417329796640142,
839
+ "grad_norm": 0.5182773470878601,
840
+ "learning_rate": 0.0003,
841
+ "loss": 0.8832,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.8488063660477454,
846
+ "grad_norm": 0.41087284684181213,
847
+ "learning_rate": 0.0003,
848
+ "loss": 0.5825,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.8558797524314765,
853
+ "grad_norm": 0.36328765749931335,
854
+ "learning_rate": 0.0003,
855
+ "loss": 0.4198,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.8629531388152077,
860
+ "grad_norm": 0.43922775983810425,
861
+ "learning_rate": 0.0003,
862
+ "loss": 0.5495,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.870026525198939,
867
+ "grad_norm": 0.5079771876335144,
868
+ "learning_rate": 0.0003,
869
+ "loss": 0.6814,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.8770999115826702,
874
+ "grad_norm": 0.3167728781700134,
875
+ "learning_rate": 0.0003,
876
+ "loss": 0.5706,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.8841732979664014,
881
+ "grad_norm": 0.45660603046417236,
882
+ "learning_rate": 0.0003,
883
+ "loss": 0.7102,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.8912466843501327,
888
+ "grad_norm": 0.42243629693984985,
889
+ "learning_rate": 0.0003,
890
+ "loss": 0.5449,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.8983200707338639,
895
+ "grad_norm": 0.32169416546821594,
896
+ "learning_rate": 0.0003,
897
+ "loss": 0.3933,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.905393457117595,
902
+ "grad_norm": 0.32228872179985046,
903
+ "learning_rate": 0.0003,
904
+ "loss": 0.6444,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.9124668435013262,
909
+ "grad_norm": 0.47969621419906616,
910
+ "learning_rate": 0.0003,
911
+ "loss": 0.7959,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.9195402298850575,
916
+ "grad_norm": 0.35543474555015564,
917
+ "learning_rate": 0.0003,
918
+ "loss": 0.6535,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.9266136162687887,
923
+ "grad_norm": 0.4273511469364166,
924
+ "learning_rate": 0.0003,
925
+ "loss": 0.6058,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.9336870026525199,
930
+ "grad_norm": 0.3400624692440033,
931
+ "learning_rate": 0.0003,
932
+ "loss": 0.6066,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.9407603890362511,
937
+ "grad_norm": 0.3195785582065582,
938
+ "learning_rate": 0.0003,
939
+ "loss": 0.5878,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.9478337754199824,
944
+ "grad_norm": 0.34657567739486694,
945
+ "learning_rate": 0.0003,
946
+ "loss": 0.6462,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.9549071618037135,
951
+ "grad_norm": 0.4706454873085022,
952
+ "learning_rate": 0.0003,
953
+ "loss": 0.8299,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.9619805481874447,
958
+ "grad_norm": 0.41353291273117065,
959
+ "learning_rate": 0.0003,
960
+ "loss": 0.6372,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.969053934571176,
965
+ "grad_norm": 0.34282562136650085,
966
+ "learning_rate": 0.0003,
967
+ "loss": 0.5901,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.9761273209549072,
972
+ "grad_norm": 0.4154914617538452,
973
+ "learning_rate": 0.0003,
974
+ "loss": 0.6213,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.9832007073386384,
979
+ "grad_norm": 0.2933409810066223,
980
+ "learning_rate": 0.0003,
981
+ "loss": 0.4435,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.9902740937223696,
986
+ "grad_norm": 0.3763149082660675,
987
+ "learning_rate": 0.0003,
988
+ "loss": 0.4754,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.9973474801061007,
993
+ "grad_norm": 0.4369047284126282,
994
+ "learning_rate": 0.0003,
995
+ "loss": 0.6313,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.004420866489832,
1000
+ "grad_norm": 0.40332600474357605,
1001
+ "learning_rate": 0.0003,
1002
+ "loss": 0.4778,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.0114942528735633,
1007
+ "grad_norm": 0.31336432695388794,
1008
+ "learning_rate": 0.0003,
1009
+ "loss": 0.4599,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.0185676392572944,
1014
+ "grad_norm": 0.3116231858730316,
1015
+ "learning_rate": 0.0003,
1016
+ "loss": 0.3823,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.0256410256410255,
1021
+ "grad_norm": 0.47887638211250305,
1022
+ "learning_rate": 0.0003,
1023
+ "loss": 0.4838,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.032714412024757,
1028
+ "grad_norm": 0.3979848325252533,
1029
+ "learning_rate": 0.0003,
1030
+ "loss": 0.3765,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.039787798408488,
1035
+ "grad_norm": 0.3911687433719635,
1036
+ "learning_rate": 0.0003,
1037
+ "loss": 0.379,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.0468611847922193,
1042
+ "grad_norm": 0.41035008430480957,
1043
+ "learning_rate": 0.0003,
1044
+ "loss": 0.4544,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.0539345711759505,
1049
+ "grad_norm": 0.3448046147823334,
1050
+ "learning_rate": 0.0003,
1051
+ "loss": 0.3809,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.0610079575596818,
1056
+ "grad_norm": 0.3258429765701294,
1057
+ "learning_rate": 0.0003,
1058
+ "loss": 0.3027,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.068081343943413,
1063
+ "grad_norm": 0.4393693208694458,
1064
+ "learning_rate": 0.0003,
1065
+ "loss": 0.4825,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.075154730327144,
1070
+ "grad_norm": 0.29749980568885803,
1071
+ "learning_rate": 0.0003,
1072
+ "loss": 0.2696,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.0822281167108754,
1077
+ "grad_norm": 0.3464600741863251,
1078
+ "learning_rate": 0.0003,
1079
+ "loss": 0.2812,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.0893015030946065,
1084
+ "grad_norm": 0.3517362177371979,
1085
+ "learning_rate": 0.0003,
1086
+ "loss": 0.4352,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.0963748894783378,
1091
+ "grad_norm": 0.3475998640060425,
1092
+ "learning_rate": 0.0003,
1093
+ "loss": 0.3298,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.103448275862069,
1098
+ "grad_norm": 0.41514718532562256,
1099
+ "learning_rate": 0.0003,
1100
+ "loss": 0.2779,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.1105216622458003,
1105
+ "grad_norm": 0.38064250349998474,
1106
+ "learning_rate": 0.0003,
1107
+ "loss": 0.3552,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.1175950486295314,
1112
+ "grad_norm": 0.48406025767326355,
1113
+ "learning_rate": 0.0003,
1114
+ "loss": 0.4691,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.1246684350132625,
1119
+ "grad_norm": 0.3856564462184906,
1120
+ "learning_rate": 0.0003,
1121
+ "loss": 0.3817,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.1317418213969939,
1126
+ "grad_norm": 0.40879660844802856,
1127
+ "learning_rate": 0.0003,
1128
+ "loss": 0.3555,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.138815207780725,
1133
+ "grad_norm": 0.4073532223701477,
1134
+ "learning_rate": 0.0003,
1135
+ "loss": 0.3218,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.1458885941644563,
1140
+ "grad_norm": 0.5433499217033386,
1141
+ "learning_rate": 0.0003,
1142
+ "loss": 0.4749,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.1529619805481874,
1147
+ "grad_norm": 0.47047749161720276,
1148
+ "learning_rate": 0.0003,
1149
+ "loss": 0.3945,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.1600353669319188,
1154
+ "grad_norm": 0.3000759184360504,
1155
+ "learning_rate": 0.0003,
1156
+ "loss": 0.3944,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.16710875331565,
1161
+ "grad_norm": 0.38655105233192444,
1162
+ "learning_rate": 0.0003,
1163
+ "loss": 0.458,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.174182139699381,
1168
+ "grad_norm": 0.3441111743450165,
1169
+ "learning_rate": 0.0003,
1170
+ "loss": 0.3388,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.1812555260831124,
1175
+ "grad_norm": 0.5380314588546753,
1176
+ "learning_rate": 0.0003,
1177
+ "loss": 0.5506,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.1883289124668435,
1182
+ "grad_norm": 0.2528212070465088,
1183
+ "learning_rate": 0.0003,
1184
+ "loss": 0.3144,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.1954022988505748,
1189
+ "grad_norm": 0.3783420920372009,
1190
+ "learning_rate": 0.0003,
1191
+ "loss": 0.5596,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.202475685234306,
1196
+ "grad_norm": 0.3812076449394226,
1197
+ "learning_rate": 0.0003,
1198
+ "loss": 0.42,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.209549071618037,
1203
+ "grad_norm": 0.43172749876976013,
1204
+ "learning_rate": 0.0003,
1205
+ "loss": 0.4931,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.2166224580017684,
1210
+ "grad_norm": 0.41426223516464233,
1211
+ "learning_rate": 0.0003,
1212
+ "loss": 0.2998,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.2236958443854995,
1217
+ "grad_norm": 0.35829058289527893,
1218
+ "learning_rate": 0.0003,
1219
+ "loss": 0.4243,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.2307692307692308,
1224
+ "grad_norm": 0.4014543294906616,
1225
+ "learning_rate": 0.0003,
1226
+ "loss": 0.3049,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.237842617152962,
1231
+ "grad_norm": 0.3007238507270813,
1232
+ "learning_rate": 0.0003,
1233
+ "loss": 0.2005,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.244916003536693,
1238
+ "grad_norm": 0.3595844507217407,
1239
+ "learning_rate": 0.0003,
1240
+ "loss": 0.344,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.2519893899204244,
1245
+ "grad_norm": 0.34730204939842224,
1246
+ "learning_rate": 0.0003,
1247
+ "loss": 0.2573,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.2590627763041558,
1252
+ "grad_norm": 0.39390042424201965,
1253
+ "learning_rate": 0.0003,
1254
+ "loss": 0.3177,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.2661361626878869,
1259
+ "grad_norm": 0.41631364822387695,
1260
+ "learning_rate": 0.0003,
1261
+ "loss": 0.4541,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.273209549071618,
1266
+ "grad_norm": 0.4117166996002197,
1267
+ "learning_rate": 0.0003,
1268
+ "loss": 0.4597,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.2802829354553493,
1273
+ "grad_norm": 0.46357792615890503,
1274
+ "learning_rate": 0.0003,
1275
+ "loss": 0.3166,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.2873563218390804,
1280
+ "grad_norm": 0.31492120027542114,
1281
+ "learning_rate": 0.0003,
1282
+ "loss": 0.2183,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.2944297082228116,
1287
+ "grad_norm": 0.31738027930259705,
1288
+ "learning_rate": 0.0003,
1289
+ "loss": 0.3114,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.301503094606543,
1294
+ "grad_norm": 0.37768757343292236,
1295
+ "learning_rate": 0.0003,
1296
+ "loss": 0.2977,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.308576480990274,
1301
+ "grad_norm": 0.45224347710609436,
1302
+ "learning_rate": 0.0003,
1303
+ "loss": 0.3788,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.3156498673740054,
1308
+ "grad_norm": 0.42707428336143494,
1309
+ "learning_rate": 0.0003,
1310
+ "loss": 0.3065,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.3227232537577365,
1315
+ "grad_norm": 0.359110027551651,
1316
+ "learning_rate": 0.0003,
1317
+ "loss": 0.3916,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.3297966401414678,
1322
+ "grad_norm": 0.4212663173675537,
1323
+ "learning_rate": 0.0003,
1324
+ "loss": 0.592,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.336870026525199,
1329
+ "grad_norm": 0.4227355122566223,
1330
+ "learning_rate": 0.0003,
1331
+ "loss": 0.4278,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.34394341290893,
1336
+ "grad_norm": 0.45795100927352905,
1337
+ "learning_rate": 0.0003,
1338
+ "loss": 0.4068,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.3510167992926614,
1343
+ "grad_norm": 0.47883355617523193,
1344
+ "learning_rate": 0.0003,
1345
+ "loss": 0.5285,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.3580901856763925,
1350
+ "grad_norm": 0.36151745915412903,
1351
+ "learning_rate": 0.0003,
1352
+ "loss": 0.365,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.3651635720601238,
1357
+ "grad_norm": 0.38841187953948975,
1358
+ "learning_rate": 0.0003,
1359
+ "loss": 0.4783,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.372236958443855,
1364
+ "grad_norm": 0.3572918772697449,
1365
+ "learning_rate": 0.0003,
1366
+ "loss": 0.4407,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.3793103448275863,
1371
+ "grad_norm": 0.36447620391845703,
1372
+ "learning_rate": 0.0003,
1373
+ "loss": 0.3111,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.3863837312113174,
1378
+ "grad_norm": 0.31043165922164917,
1379
+ "learning_rate": 0.0003,
1380
+ "loss": 0.3809,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.3934571175950485,
1385
+ "grad_norm": 0.4331524670124054,
1386
+ "learning_rate": 0.0003,
1387
+ "loss": 0.3464,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.4005305039787799,
1392
+ "grad_norm": 0.5187276005744934,
1393
+ "learning_rate": 0.0003,
1394
+ "loss": 0.4041,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.407603890362511,
1399
+ "grad_norm": 0.3016161322593689,
1400
+ "learning_rate": 0.0003,
1401
+ "loss": 0.1315,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.4146772767462423,
1406
+ "grad_norm": 0.3778589069843292,
1407
+ "learning_rate": 0.0003,
1408
+ "loss": 0.2563,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.4217506631299734,
1413
+ "grad_norm": 0.4542739987373352,
1414
+ "learning_rate": 0.0003,
1415
+ "loss": 0.3676,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.4288240495137048,
1420
+ "grad_norm": 0.37201106548309326,
1421
+ "learning_rate": 0.0003,
1422
+ "loss": 0.4023,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.435897435897436,
1427
+ "grad_norm": 0.3098253607749939,
1428
+ "learning_rate": 0.0003,
1429
+ "loss": 0.2013,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.442970822281167,
1434
+ "grad_norm": 0.41762611269950867,
1435
+ "learning_rate": 0.0003,
1436
+ "loss": 0.2562,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.4500442086648984,
1441
+ "grad_norm": 0.3805309534072876,
1442
+ "learning_rate": 0.0003,
1443
+ "loss": 0.2091,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.4571175950486295,
1448
+ "grad_norm": 0.30562469363212585,
1449
+ "learning_rate": 0.0003,
1450
+ "loss": 0.3204,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.4641909814323608,
1455
+ "grad_norm": 0.40833625197410583,
1456
+ "learning_rate": 0.0003,
1457
+ "loss": 0.3828,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.471264367816092,
1462
+ "grad_norm": 0.44443726539611816,
1463
+ "learning_rate": 0.0003,
1464
+ "loss": 0.3023,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.4783377541998233,
1469
+ "grad_norm": 0.3216983675956726,
1470
+ "learning_rate": 0.0003,
1471
+ "loss": 0.148,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.4854111405835544,
1476
+ "grad_norm": 0.49379777908325195,
1477
+ "learning_rate": 0.0003,
1478
+ "loss": 0.3597,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.4924845269672855,
1483
+ "grad_norm": 0.41881895065307617,
1484
+ "learning_rate": 0.0003,
1485
+ "loss": 0.3724,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.4995579133510168,
1490
+ "grad_norm": 0.37855106592178345,
1491
+ "learning_rate": 0.0003,
1492
+ "loss": 0.2177,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.506631299734748,
1497
+ "grad_norm": 0.4481782615184784,
1498
+ "learning_rate": 0.0003,
1499
+ "loss": 0.4668,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.513704686118479,
1504
+ "grad_norm": 0.45132726430892944,
1505
+ "learning_rate": 0.0003,
1506
+ "loss": 0.5844,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.5207780725022104,
1511
+ "grad_norm": 0.4039032459259033,
1512
+ "learning_rate": 0.0003,
1513
+ "loss": 0.411,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.5278514588859418,
1518
+ "grad_norm": 0.3423170745372772,
1519
+ "learning_rate": 0.0003,
1520
+ "loss": 0.3069,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.5349248452696729,
1525
+ "grad_norm": 0.3927661180496216,
1526
+ "learning_rate": 0.0003,
1527
+ "loss": 0.5008,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.541998231653404,
1532
+ "grad_norm": 0.43571972846984863,
1533
+ "learning_rate": 0.0003,
1534
+ "loss": 0.4626,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.5490716180371353,
1539
+ "grad_norm": 0.370449423789978,
1540
+ "learning_rate": 0.0003,
1541
+ "loss": 0.2882,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.5561450044208665,
1546
+ "grad_norm": 0.3305343687534332,
1547
+ "learning_rate": 0.0003,
1548
+ "loss": 0.2781,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.5632183908045976,
1553
+ "grad_norm": 0.40083616971969604,
1554
+ "learning_rate": 0.0003,
1555
+ "loss": 0.2652,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.570291777188329,
1560
+ "grad_norm": 0.38695937395095825,
1561
+ "learning_rate": 0.0003,
1562
+ "loss": 0.4565,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.5773651635720602,
1567
+ "grad_norm": 0.5376386046409607,
1568
+ "learning_rate": 0.0003,
1569
+ "loss": 0.4184,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.5844385499557914,
1574
+ "grad_norm": 0.5290461182594299,
1575
+ "learning_rate": 0.0003,
1576
+ "loss": 0.3836,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.5915119363395225,
1581
+ "grad_norm": 0.39294925332069397,
1582
+ "learning_rate": 0.0003,
1583
+ "loss": 0.446,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.5985853227232538,
1588
+ "grad_norm": 0.3946995139122009,
1589
+ "learning_rate": 0.0003,
1590
+ "loss": 0.3433,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.605658709106985,
1595
+ "grad_norm": 0.3850666880607605,
1596
+ "learning_rate": 0.0003,
1597
+ "loss": 0.515,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.612732095490716,
1602
+ "grad_norm": 0.3812507688999176,
1603
+ "learning_rate": 0.0003,
1604
+ "loss": 0.4666,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.6198054818744474,
1609
+ "grad_norm": 0.34343773126602173,
1610
+ "learning_rate": 0.0003,
1611
+ "loss": 0.3437,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.6268788682581787,
1616
+ "grad_norm": 0.42423132061958313,
1617
+ "learning_rate": 0.0003,
1618
+ "loss": 0.2998,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.6339522546419099,
1623
+ "grad_norm": 0.36676838994026184,
1624
+ "learning_rate": 0.0003,
1625
+ "loss": 0.381,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.641025641025641,
1630
+ "grad_norm": 0.45891061425209045,
1631
+ "learning_rate": 0.0003,
1632
+ "loss": 0.4426,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.6480990274093723,
1637
+ "grad_norm": 0.4290439188480377,
1638
+ "learning_rate": 0.0003,
1639
+ "loss": 0.3475,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 1.6551724137931034,
1644
+ "grad_norm": 0.3556974232196808,
1645
+ "learning_rate": 0.0003,
1646
+ "loss": 0.328,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 1.6622458001768345,
1651
+ "grad_norm": 0.30578428506851196,
1652
+ "learning_rate": 0.0003,
1653
+ "loss": 0.2591,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 1.6693191865605659,
1658
+ "grad_norm": 0.3522488474845886,
1659
+ "learning_rate": 0.0003,
1660
+ "loss": 0.416,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 1.6763925729442972,
1665
+ "grad_norm": 0.3940620720386505,
1666
+ "learning_rate": 0.0003,
1667
+ "loss": 0.548,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 1.6834659593280283,
1672
+ "grad_norm": 0.4076889455318451,
1673
+ "learning_rate": 0.0003,
1674
+ "loss": 0.5044,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 1.6905393457117595,
1679
+ "grad_norm": 0.49337613582611084,
1680
+ "learning_rate": 0.0003,
1681
+ "loss": 0.4355,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 1.6976127320954908,
1686
+ "grad_norm": 0.37077927589416504,
1687
+ "learning_rate": 0.0003,
1688
+ "loss": 0.4739,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 1.704686118479222,
1693
+ "grad_norm": 0.4110550880432129,
1694
+ "learning_rate": 0.0003,
1695
+ "loss": 0.428,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 1.711759504862953,
1700
+ "grad_norm": 0.49631252884864807,
1701
+ "learning_rate": 0.0003,
1702
+ "loss": 0.4227,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 1.7188328912466844,
1707
+ "grad_norm": 0.3230995535850525,
1708
+ "learning_rate": 0.0003,
1709
+ "loss": 0.3451,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 1.7259062776304157,
1714
+ "grad_norm": 0.36575183272361755,
1715
+ "learning_rate": 0.0003,
1716
+ "loss": 0.2817,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 1.7329796640141468,
1721
+ "grad_norm": 0.4187852740287781,
1722
+ "learning_rate": 0.0003,
1723
+ "loss": 0.319,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 1.740053050397878,
1728
+ "grad_norm": 0.3224227726459503,
1729
+ "learning_rate": 0.0003,
1730
+ "loss": 0.3406,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 1.7471264367816093,
1735
+ "grad_norm": 0.379561185836792,
1736
+ "learning_rate": 0.0003,
1737
+ "loss": 0.3817,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.7541998231653404,
1742
+ "grad_norm": 0.44703027606010437,
1743
+ "learning_rate": 0.0003,
1744
+ "loss": 0.3879,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.7612732095490715,
1749
+ "grad_norm": 0.34053027629852295,
1750
+ "learning_rate": 0.0003,
1751
+ "loss": 0.2767,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.7683465959328029,
1756
+ "grad_norm": 0.48519593477249146,
1757
+ "learning_rate": 0.0003,
1758
+ "loss": 0.5043,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 1.7754199823165342,
1763
+ "grad_norm": 0.3466756045818329,
1764
+ "learning_rate": 0.0003,
1765
+ "loss": 0.2593,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 1.782493368700265,
1770
+ "grad_norm": 0.5155137777328491,
1771
+ "learning_rate": 0.0003,
1772
+ "loss": 0.3529,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.7895667550839964,
1777
+ "grad_norm": 0.4184979796409607,
1778
+ "learning_rate": 0.0003,
1779
+ "loss": 0.535,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.7966401414677278,
1784
+ "grad_norm": 0.3188352882862091,
1785
+ "learning_rate": 0.0003,
1786
+ "loss": 0.2358,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.8037135278514589,
1791
+ "grad_norm": 0.42813432216644287,
1792
+ "learning_rate": 0.0003,
1793
+ "loss": 0.374,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.81078691423519,
1798
+ "grad_norm": 0.40070992708206177,
1799
+ "learning_rate": 0.0003,
1800
+ "loss": 0.4326,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.8178603006189213,
1805
+ "grad_norm": 0.45408982038497925,
1806
+ "learning_rate": 0.0003,
1807
+ "loss": 0.4945,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.8249336870026527,
1812
+ "grad_norm": 0.42870137095451355,
1813
+ "learning_rate": 0.0003,
1814
+ "loss": 0.4528,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.8320070733863836,
1819
+ "grad_norm": 0.3272749185562134,
1820
+ "learning_rate": 0.0003,
1821
+ "loss": 0.2587,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.839080459770115,
1826
+ "grad_norm": 0.4601209759712219,
1827
+ "learning_rate": 0.0003,
1828
+ "loss": 0.5043,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.8461538461538463,
1833
+ "grad_norm": 0.48971623182296753,
1834
+ "learning_rate": 0.0003,
1835
+ "loss": 0.4837,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.8532272325375774,
1840
+ "grad_norm": 0.37702813744544983,
1841
+ "learning_rate": 0.0003,
1842
+ "loss": 0.421,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.8603006189213085,
1847
+ "grad_norm": 0.37648722529411316,
1848
+ "learning_rate": 0.0003,
1849
+ "loss": 0.2666,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.8673740053050398,
1854
+ "grad_norm": 0.5787553787231445,
1855
+ "learning_rate": 0.0003,
1856
+ "loss": 0.2987,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.874447391688771,
1861
+ "grad_norm": 0.4249975085258484,
1862
+ "learning_rate": 0.0003,
1863
+ "loss": 0.5577,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.881520778072502,
1868
+ "grad_norm": 0.3846690356731415,
1869
+ "learning_rate": 0.0003,
1870
+ "loss": 0.3106,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.8885941644562334,
1875
+ "grad_norm": 0.37595272064208984,
1876
+ "learning_rate": 0.0003,
1877
+ "loss": 0.3638,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.8956675508399647,
1882
+ "grad_norm": 0.4609120190143585,
1883
+ "learning_rate": 0.0003,
1884
+ "loss": 0.4356,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.9027409372236959,
1889
+ "grad_norm": 0.3405689299106598,
1890
+ "learning_rate": 0.0003,
1891
+ "loss": 0.3113,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.909814323607427,
1896
+ "grad_norm": 0.30769774317741394,
1897
+ "learning_rate": 0.0003,
1898
+ "loss": 0.2626,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.9168877099911583,
1903
+ "grad_norm": 0.36806437373161316,
1904
+ "learning_rate": 0.0003,
1905
+ "loss": 0.401,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.9239610963748894,
1910
+ "grad_norm": 0.45491501688957214,
1911
+ "learning_rate": 0.0003,
1912
+ "loss": 0.4295,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.9310344827586206,
1917
+ "grad_norm": 0.3272283971309662,
1918
+ "learning_rate": 0.0003,
1919
+ "loss": 0.3143,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.938107869142352,
1924
+ "grad_norm": 0.32763826847076416,
1925
+ "learning_rate": 0.0003,
1926
+ "loss": 0.246,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.9451812555260832,
1931
+ "grad_norm": 0.43065381050109863,
1932
+ "learning_rate": 0.0003,
1933
+ "loss": 0.3338,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.9522546419098143,
1938
+ "grad_norm": 0.43713968992233276,
1939
+ "learning_rate": 0.0003,
1940
+ "loss": 0.3136,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.9593280282935455,
1945
+ "grad_norm": 0.2735891342163086,
1946
+ "learning_rate": 0.0003,
1947
+ "loss": 0.2381,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.9664014146772768,
1952
+ "grad_norm": 0.3156580626964569,
1953
+ "learning_rate": 0.0003,
1954
+ "loss": 0.3336,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.973474801061008,
1959
+ "grad_norm": 0.4958134591579437,
1960
+ "learning_rate": 0.0003,
1961
+ "loss": 0.5279,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.980548187444739,
1966
+ "grad_norm": 0.41325512528419495,
1967
+ "learning_rate": 0.0003,
1968
+ "loss": 0.3997,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.9876215738284704,
1973
+ "grad_norm": 0.29986992478370667,
1974
+ "learning_rate": 0.0003,
1975
+ "loss": 0.2996,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.9946949602122017,
1980
+ "grad_norm": 0.3219819962978363,
1981
+ "learning_rate": 0.0003,
1982
+ "loss": 0.2875,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.9946949602122017,
1987
+ "step": 282,
1988
+ "total_flos": 1.061363392708608e+16,
1989
+ "train_loss": 0.5953954255327265,
1990
+ "train_runtime": 9564.3104,
1991
+ "train_samples_per_second": 0.473,
1992
+ "train_steps_per_second": 0.029
1993
+ }
1994
+ ],
1995
+ "logging_steps": 1.0,
1996
+ "max_steps": 282,
1997
+ "num_input_tokens_seen": 0,
1998
+ "num_train_epochs": 2,
1999
+ "save_steps": 1000,
2000
+ "total_flos": 1.061363392708608e+16,
2001
+ "train_batch_size": 2,
2002
+ "trial_name": null,
2003
+ "trial_params": null
2004
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b9703a0f08a877c615f271bc5b1a049eb013ff713b98bd3ca4d9709b6e9a6c
3
+ size 6648