leedahyeon commited on
Commit
90e0d54
·
verified ·
1 Parent(s): 2039232

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bit
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 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "down_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "gate_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea8ed43cd1e27461050d3414d07bc10586bd4a697a9d226ebeceb875de02728
3
+ size 167832240
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad019f1393d7dd21c8b472d42655b3b0daa88063b2a1df8df68b85441aeddde
3
+ size 85723732
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7e06a1de8e9852db7ac94a9dc1256353c61c343896baab7bd91dbb227a15a6
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbc7133e614ccba6cc6b91ebcfbc9c31214e6ffe9a5606289e2f4fee1d0aed0
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2067 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|finetune_right_pad_id|>",
2064
+ "padding_side": "right",
2065
+ "tokenizer_class": "PreTrainedTokenizerFast",
2066
+ "unk_token": null
2067
+ }
trainer_state.json ADDED
@@ -0,0 +1,2181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 11.208358764648438,
3
+ "best_model_checkpoint": "./FT_models/[LDH]0219_all_llama31_docs_nodocs/checkpoint-1000",
4
+ "epoch": 2.716904276985743,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009051821679112922,
13
+ "grad_norm": 0.874797523021698,
14
+ "learning_rate": 0.0001999995055317446,
15
+ "loss": 1.9293,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.018103643358225844,
20
+ "grad_norm": 0.5239140391349792,
21
+ "learning_rate": 0.0001999955498150411,
22
+ "loss": 1.1773,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.027155465037338764,
27
+ "grad_norm": 0.49293628334999084,
28
+ "learning_rate": 0.00019998763853811184,
29
+ "loss": 1.1369,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.03620728671645169,
34
+ "grad_norm": 0.4514484405517578,
35
+ "learning_rate": 0.00019997577201390606,
36
+ "loss": 1.1049,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.04525910839556461,
41
+ "grad_norm": 0.480444073677063,
42
+ "learning_rate": 0.0001999599507118322,
43
+ "loss": 1.0472,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.05431093007467753,
48
+ "grad_norm": 0.6258535385131836,
49
+ "learning_rate": 0.00019994017525773913,
50
+ "loss": 1.0656,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.06336275175379046,
55
+ "grad_norm": 0.5886121392250061,
56
+ "learning_rate": 0.0001999164464338918,
57
+ "loss": 0.9311,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.07241457343290338,
62
+ "grad_norm": 0.6107162833213806,
63
+ "learning_rate": 0.0001998887651789398,
64
+ "loss": 1.0476,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.0814663951120163,
69
+ "grad_norm": 0.5811272859573364,
70
+ "learning_rate": 0.0001998571325878806,
71
+ "loss": 0.9568,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.09051821679112922,
76
+ "grad_norm": 0.6300623416900635,
77
+ "learning_rate": 0.00019982154991201608,
78
+ "loss": 0.9121,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.09957003847024214,
83
+ "grad_norm": 0.6835796236991882,
84
+ "learning_rate": 0.00019978201855890308,
85
+ "loss": 0.8682,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.10862186014935506,
90
+ "grad_norm": 0.5953958034515381,
91
+ "learning_rate": 0.00019973854009229763,
92
+ "loss": 0.9708,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.11767368182846798,
97
+ "grad_norm": 0.6399095058441162,
98
+ "learning_rate": 0.00019969111623209323,
99
+ "loss": 0.9063,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.1267255035075809,
104
+ "grad_norm": 0.5774116516113281,
105
+ "learning_rate": 0.00019963974885425266,
106
+ "loss": 0.9571,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.13577732518669383,
111
+ "grad_norm": 0.6394885182380676,
112
+ "learning_rate": 0.00019958443999073397,
113
+ "loss": 0.9187,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.14482914686580675,
118
+ "grad_norm": 0.6276863813400269,
119
+ "learning_rate": 0.00019952519182940993,
120
+ "loss": 0.9531,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.15388096854491967,
125
+ "grad_norm": 0.6715622544288635,
126
+ "learning_rate": 0.0001994620067139815,
127
+ "loss": 0.8558,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.1629327902240326,
132
+ "grad_norm": 0.7086506485939026,
133
+ "learning_rate": 0.00019939488714388524,
134
+ "loss": 0.8611,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.1719846119031455,
139
+ "grad_norm": 0.614281177520752,
140
+ "learning_rate": 0.00019932383577419432,
141
+ "loss": 0.7985,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.18103643358225843,
146
+ "grad_norm": 0.6501333117485046,
147
+ "learning_rate": 0.0001992488554155135,
148
+ "loss": 0.8663,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.19008825526137135,
153
+ "grad_norm": 0.59181809425354,
154
+ "learning_rate": 0.0001991699490338681,
155
+ "loss": 0.7611,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.19914007694048427,
160
+ "grad_norm": 0.6414404511451721,
161
+ "learning_rate": 0.00019908711975058637,
162
+ "loss": 0.7952,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2081918986195972,
167
+ "grad_norm": 0.5972408056259155,
168
+ "learning_rate": 0.00019900037084217637,
169
+ "loss": 0.7415,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.2172437202987101,
174
+ "grad_norm": 0.6564370393753052,
175
+ "learning_rate": 0.00019890970574019617,
176
+ "loss": 0.7951,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.22629554197782303,
181
+ "grad_norm": 0.7463496327400208,
182
+ "learning_rate": 0.00019881512803111796,
183
+ "loss": 0.7421,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.23534736365693595,
188
+ "grad_norm": 0.6890644431114197,
189
+ "learning_rate": 0.00019871664145618657,
190
+ "loss": 0.7929,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.24439918533604887,
195
+ "grad_norm": 0.5937248468399048,
196
+ "learning_rate": 0.00019861424991127115,
197
+ "loss": 0.7801,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.2534510070151618,
202
+ "grad_norm": 0.7962441444396973,
203
+ "learning_rate": 0.00019850795744671116,
204
+ "loss": 0.7889,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.2625028286942747,
209
+ "grad_norm": 0.5598044991493225,
210
+ "learning_rate": 0.00019839776826715614,
211
+ "loss": 0.773,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.27155465037338766,
216
+ "grad_norm": 0.743926465511322,
217
+ "learning_rate": 0.00019828368673139947,
218
+ "loss": 0.7739,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.28060647205250056,
223
+ "grad_norm": 0.5907182693481445,
224
+ "learning_rate": 0.00019816571735220583,
225
+ "loss": 0.7472,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.2896582937316135,
230
+ "grad_norm": 0.7143293619155884,
231
+ "learning_rate": 0.0001980438647961327,
232
+ "loss": 0.723,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.2987101154107264,
237
+ "grad_norm": 0.6375603079795837,
238
+ "learning_rate": 0.00019791813388334581,
239
+ "loss": 0.7454,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.30776193708983934,
244
+ "grad_norm": 0.7762064933776855,
245
+ "learning_rate": 0.00019778852958742853,
246
+ "loss": 0.6882,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.31681375876895224,
251
+ "grad_norm": 0.5525858998298645,
252
+ "learning_rate": 0.00019765505703518496,
253
+ "loss": 0.6642,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.3258655804480652,
258
+ "grad_norm": 0.6317685842514038,
259
+ "learning_rate": 0.00019751772150643722,
260
+ "loss": 0.6965,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.3349174021271781,
265
+ "grad_norm": 0.664470374584198,
266
+ "learning_rate": 0.0001973765284338167,
267
+ "loss": 0.7218,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.343969223806291,
272
+ "grad_norm": 0.587965190410614,
273
+ "learning_rate": 0.00019723148340254892,
274
+ "loss": 0.7628,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.3530210454854039,
279
+ "grad_norm": 0.6755478978157043,
280
+ "learning_rate": 0.0001970825921502328,
281
+ "loss": 0.6277,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.36207286716451687,
286
+ "grad_norm": 0.6129139065742493,
287
+ "learning_rate": 0.00019692986056661356,
288
+ "loss": 0.7238,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.37112468884362976,
293
+ "grad_norm": 0.6757403612136841,
294
+ "learning_rate": 0.0001967732946933499,
295
+ "loss": 0.6568,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.3801765105227427,
300
+ "grad_norm": 0.7164187431335449,
301
+ "learning_rate": 0.00019661290072377482,
302
+ "loss": 0.6963,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.3892283322018556,
307
+ "grad_norm": 0.6669524908065796,
308
+ "learning_rate": 0.0001964486850026507,
309
+ "loss": 0.6931,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.39828015388096855,
314
+ "grad_norm": 0.6036201119422913,
315
+ "learning_rate": 0.00019628065402591845,
316
+ "loss": 0.6989,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.4073319755600815,
321
+ "grad_norm": 0.6022247076034546,
322
+ "learning_rate": 0.0001961088144404403,
323
+ "loss": 0.7669,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.4163837972391944,
328
+ "grad_norm": 0.6327004432678223,
329
+ "learning_rate": 0.00019593317304373705,
330
+ "loss": 0.6673,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.42543561891830733,
335
+ "grad_norm": 0.6826880574226379,
336
+ "learning_rate": 0.00019575373678371909,
337
+ "loss": 0.6965,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.4344874405974202,
342
+ "grad_norm": 0.6268287897109985,
343
+ "learning_rate": 0.0001955705127584117,
344
+ "loss": 0.6468,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.4435392622765332,
349
+ "grad_norm": 0.6102762818336487,
350
+ "learning_rate": 0.00019538350821567404,
351
+ "loss": 0.6302,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.45259108395564607,
356
+ "grad_norm": 0.672012448310852,
357
+ "learning_rate": 0.00019519273055291266,
358
+ "loss": 0.6529,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.45259108395564607,
363
+ "eval_loss": 11.249969482421875,
364
+ "eval_runtime": 42.473,
365
+ "eval_samples_per_second": 7.464,
366
+ "eval_steps_per_second": 3.744,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 0.461642905634759,
371
+ "grad_norm": 0.6281114220619202,
372
+ "learning_rate": 0.00019499818731678873,
373
+ "loss": 0.705,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 0.4706947273138719,
378
+ "grad_norm": 0.6248394250869751,
379
+ "learning_rate": 0.00019479988620291956,
380
+ "loss": 0.6999,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 0.47974654899298486,
385
+ "grad_norm": 0.5792989134788513,
386
+ "learning_rate": 0.00019459783505557424,
387
+ "loss": 0.6166,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 0.48879837067209775,
392
+ "grad_norm": 0.6465005278587341,
393
+ "learning_rate": 0.0001943920418673633,
394
+ "loss": 0.5985,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 0.4978501923512107,
399
+ "grad_norm": 0.7002309560775757,
400
+ "learning_rate": 0.0001941825147789225,
401
+ "loss": 0.7327,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 0.5069020140303236,
406
+ "grad_norm": 0.6550771594047546,
407
+ "learning_rate": 0.00019396926207859084,
408
+ "loss": 0.6097,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 0.5159538357094365,
413
+ "grad_norm": 0.6645638942718506,
414
+ "learning_rate": 0.00019375229220208276,
415
+ "loss": 0.6032,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 0.5250056573885494,
420
+ "grad_norm": 0.6332526803016663,
421
+ "learning_rate": 0.0001935316137321543,
422
+ "loss": 0.647,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 0.5340574790676623,
427
+ "grad_norm": 0.6539055705070496,
428
+ "learning_rate": 0.00019330723539826375,
429
+ "loss": 0.5964,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 0.5431093007467753,
434
+ "grad_norm": 0.616939902305603,
435
+ "learning_rate": 0.0001930791660762262,
436
+ "loss": 0.6331,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 0.5521611224258882,
441
+ "grad_norm": 0.6726529598236084,
442
+ "learning_rate": 0.0001928474147878626,
443
+ "loss": 0.6395,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 0.5612129441050011,
448
+ "grad_norm": 0.6520217061042786,
449
+ "learning_rate": 0.0001926119907006426,
450
+ "loss": 0.5835,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 0.570264765784114,
455
+ "grad_norm": 0.6048600077629089,
456
+ "learning_rate": 0.00019237290312732226,
457
+ "loss": 0.5824,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 0.579316587463227,
462
+ "grad_norm": 0.6220108270645142,
463
+ "learning_rate": 0.0001921301615255754,
464
+ "loss": 0.638,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 0.5883684091423399,
469
+ "grad_norm": 0.6199471354484558,
470
+ "learning_rate": 0.00019188377549761963,
471
+ "loss": 0.591,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 0.5974202308214528,
476
+ "grad_norm": 0.6387749910354614,
477
+ "learning_rate": 0.00019163375478983632,
478
+ "loss": 0.5934,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 0.6064720525005657,
483
+ "grad_norm": 0.6121918559074402,
484
+ "learning_rate": 0.00019138010929238534,
485
+ "loss": 0.5164,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 0.6155238741796787,
490
+ "grad_norm": 0.5336770415306091,
491
+ "learning_rate": 0.0001911228490388136,
492
+ "loss": 0.5644,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 0.6245756958587916,
497
+ "grad_norm": 0.6676989793777466,
498
+ "learning_rate": 0.00019086198420565823,
499
+ "loss": 0.6162,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 0.6336275175379045,
504
+ "grad_norm": 0.7787268161773682,
505
+ "learning_rate": 0.000190597525112044,
506
+ "loss": 0.5458,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 0.6426793392170175,
511
+ "grad_norm": 0.5786814093589783,
512
+ "learning_rate": 0.00019032948221927524,
513
+ "loss": 0.6159,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 0.6517311608961304,
518
+ "grad_norm": 0.5182745456695557,
519
+ "learning_rate": 0.00019005786613042185,
520
+ "loss": 0.5528,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 0.6607829825752433,
525
+ "grad_norm": 0.6106360554695129,
526
+ "learning_rate": 0.00018978268758989991,
527
+ "loss": 0.5792,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 0.6698348042543562,
532
+ "grad_norm": 0.6614301800727844,
533
+ "learning_rate": 0.00018950395748304678,
534
+ "loss": 0.5251,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 0.6788866259334692,
539
+ "grad_norm": 0.4879720211029053,
540
+ "learning_rate": 0.0001892216868356904,
541
+ "loss": 0.5596,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 0.687938447612582,
546
+ "grad_norm": 0.7061878442764282,
547
+ "learning_rate": 0.00018893588681371303,
548
+ "loss": 0.5517,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 0.6969902692916949,
553
+ "grad_norm": 0.7787359952926636,
554
+ "learning_rate": 0.00018864656872260985,
555
+ "loss": 0.5813,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 0.7060420909708078,
560
+ "grad_norm": 0.5743793845176697,
561
+ "learning_rate": 0.00018835374400704154,
562
+ "loss": 0.56,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 0.7150939126499208,
567
+ "grad_norm": 0.5919637680053711,
568
+ "learning_rate": 0.00018805742425038145,
569
+ "loss": 0.5429,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 0.7241457343290337,
574
+ "grad_norm": 0.5750169157981873,
575
+ "learning_rate": 0.00018775762117425777,
576
+ "loss": 0.5303,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 0.7331975560081466,
581
+ "grad_norm": 0.5034388899803162,
582
+ "learning_rate": 0.00018745434663808942,
583
+ "loss": 0.554,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 0.7422493776872595,
588
+ "grad_norm": 0.6673147678375244,
589
+ "learning_rate": 0.00018714761263861728,
590
+ "loss": 0.5769,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 0.7513011993663725,
595
+ "grad_norm": 0.6599574089050293,
596
+ "learning_rate": 0.00018683743130942928,
597
+ "loss": 0.5316,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 0.7603530210454854,
602
+ "grad_norm": 0.6396362781524658,
603
+ "learning_rate": 0.00018652381492048083,
604
+ "loss": 0.5061,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 0.7694048427245983,
609
+ "grad_norm": 0.5517466068267822,
610
+ "learning_rate": 0.00018620677587760916,
611
+ "loss": 0.5951,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 0.7784566644037112,
616
+ "grad_norm": 0.5412144064903259,
617
+ "learning_rate": 0.00018588632672204264,
618
+ "loss": 0.4929,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 0.7875084860828242,
623
+ "grad_norm": 0.5431721210479736,
624
+ "learning_rate": 0.00018556248012990468,
625
+ "loss": 0.5358,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 0.7965603077619371,
630
+ "grad_norm": 0.5506939888000488,
631
+ "learning_rate": 0.0001852352489117124,
632
+ "loss": 0.4487,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 0.80561212944105,
637
+ "grad_norm": 0.5743805766105652,
638
+ "learning_rate": 0.0001849046460118698,
639
+ "loss": 0.5725,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 0.814663951120163,
644
+ "grad_norm": 0.573427677154541,
645
+ "learning_rate": 0.00018457068450815562,
646
+ "loss": 0.5078,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 0.8237157727992759,
651
+ "grad_norm": 0.6854224801063538,
652
+ "learning_rate": 0.00018423337761120618,
653
+ "loss": 0.4688,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 0.8327675944783888,
658
+ "grad_norm": 0.6372252702713013,
659
+ "learning_rate": 0.00018389273866399275,
660
+ "loss": 0.5169,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 0.8418194161575017,
665
+ "grad_norm": 0.6130049228668213,
666
+ "learning_rate": 0.00018354878114129367,
667
+ "loss": 0.5089,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 0.8508712378366147,
672
+ "grad_norm": 0.5654692649841309,
673
+ "learning_rate": 0.00018320151864916135,
674
+ "loss": 0.5492,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 0.8599230595157276,
679
+ "grad_norm": 0.548478901386261,
680
+ "learning_rate": 0.00018285096492438424,
681
+ "loss": 0.5218,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 0.8689748811948405,
686
+ "grad_norm": 0.5212107300758362,
687
+ "learning_rate": 0.00018249713383394303,
688
+ "loss": 0.5803,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 0.8780267028739533,
693
+ "grad_norm": 0.5414544939994812,
694
+ "learning_rate": 0.00018214003937446253,
695
+ "loss": 0.5677,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 0.8870785245530663,
700
+ "grad_norm": 0.58649742603302,
701
+ "learning_rate": 0.0001817796956716578,
702
+ "loss": 0.5331,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 0.8961303462321792,
707
+ "grad_norm": 0.5166681408882141,
708
+ "learning_rate": 0.00018141611697977529,
709
+ "loss": 0.5032,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 0.9051821679112921,
714
+ "grad_norm": 0.6174758076667786,
715
+ "learning_rate": 0.0001810493176810292,
716
+ "loss": 0.5148,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 0.9051821679112921,
721
+ "eval_loss": 11.208358764648438,
722
+ "eval_runtime": 42.0152,
723
+ "eval_samples_per_second": 7.545,
724
+ "eval_steps_per_second": 3.784,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 0.914233989590405,
729
+ "grad_norm": 0.6219255924224854,
730
+ "learning_rate": 0.00018067931228503246,
731
+ "loss": 0.5486,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 0.923285811269518,
736
+ "grad_norm": 0.5557869672775269,
737
+ "learning_rate": 0.00018030611542822257,
738
+ "loss": 0.4645,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 0.9323376329486309,
743
+ "grad_norm": 0.6376787424087524,
744
+ "learning_rate": 0.00017992974187328305,
745
+ "loss": 0.5582,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 0.9413894546277438,
750
+ "grad_norm": 0.6127185821533203,
751
+ "learning_rate": 0.000179550206508559,
752
+ "loss": 0.5878,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 0.9504412763068567,
757
+ "grad_norm": 1.0581947565078735,
758
+ "learning_rate": 0.00017916752434746856,
759
+ "loss": 0.5113,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 0.9594930979859697,
764
+ "grad_norm": 0.6159986257553101,
765
+ "learning_rate": 0.00017878171052790868,
766
+ "loss": 0.5226,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 0.9685449196650826,
771
+ "grad_norm": 0.6697051525115967,
772
+ "learning_rate": 0.00017839278031165658,
773
+ "loss": 0.5011,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 0.9775967413441955,
778
+ "grad_norm": 0.6310513019561768,
779
+ "learning_rate": 0.00017800074908376584,
780
+ "loss": 0.4599,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 0.9866485630233084,
785
+ "grad_norm": 0.5671334266662598,
786
+ "learning_rate": 0.0001776056323519579,
787
+ "loss": 0.4455,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 0.9957003847024214,
792
+ "grad_norm": 0.5935373902320862,
793
+ "learning_rate": 0.00017720744574600863,
794
+ "loss": 0.472,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 1.0054310930074677,
799
+ "grad_norm": 0.4842943251132965,
800
+ "learning_rate": 0.00017680620501712996,
801
+ "loss": 0.4619,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 1.0144829146865806,
806
+ "grad_norm": 0.5976426601409912,
807
+ "learning_rate": 0.00017640192603734692,
808
+ "loss": 0.4535,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 1.0235347363656937,
813
+ "grad_norm": 0.5157873630523682,
814
+ "learning_rate": 0.00017599462479886974,
815
+ "loss": 0.3832,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 1.0325865580448066,
820
+ "grad_norm": 0.6044872403144836,
821
+ "learning_rate": 0.00017558431741346122,
822
+ "loss": 0.4133,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 1.0416383797239195,
827
+ "grad_norm": 0.6488142013549805,
828
+ "learning_rate": 0.00017517102011179933,
829
+ "loss": 0.4391,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 1.0506902014030324,
834
+ "grad_norm": 0.5446122884750366,
835
+ "learning_rate": 0.00017475474924283536,
836
+ "loss": 0.3626,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 1.0597420230821453,
841
+ "grad_norm": 0.4834959805011749,
842
+ "learning_rate": 0.000174335521273147,
843
+ "loss": 0.3712,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 1.0687938447612582,
848
+ "grad_norm": 0.506747305393219,
849
+ "learning_rate": 0.00017391335278628712,
850
+ "loss": 0.3985,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 1.077845666440371,
855
+ "grad_norm": 0.5550024509429932,
856
+ "learning_rate": 0.0001734882604821276,
857
+ "loss": 0.4201,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 1.086897488119484,
862
+ "grad_norm": 0.5207591652870178,
863
+ "learning_rate": 0.00017306026117619889,
864
+ "loss": 0.3782,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 1.095949309798597,
869
+ "grad_norm": 0.6619957089424133,
870
+ "learning_rate": 0.00017262937179902472,
871
+ "loss": 0.4203,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 1.10500113147771,
876
+ "grad_norm": 0.6261160969734192,
877
+ "learning_rate": 0.00017219560939545246,
878
+ "loss": 0.3877,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 1.1140529531568228,
883
+ "grad_norm": 0.6254423260688782,
884
+ "learning_rate": 0.0001717589911239788,
885
+ "loss": 0.4245,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 1.1231047748359357,
890
+ "grad_norm": 0.5006200671195984,
891
+ "learning_rate": 0.00017131953425607104,
892
+ "loss": 0.399,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 1.1321565965150486,
897
+ "grad_norm": 0.5162988305091858,
898
+ "learning_rate": 0.00017087725617548385,
899
+ "loss": 0.4325,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 1.1412084181941615,
904
+ "grad_norm": 0.5567941665649414,
905
+ "learning_rate": 0.00017043217437757164,
906
+ "loss": 0.4391,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 1.1502602398732744,
911
+ "grad_norm": 0.6780401468276978,
912
+ "learning_rate": 0.00016998430646859654,
913
+ "loss": 0.4388,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 1.1593120615523875,
918
+ "grad_norm": 0.6121058464050293,
919
+ "learning_rate": 0.00016953367016503182,
920
+ "loss": 0.4216,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 1.1683638832315004,
925
+ "grad_norm": 0.6004344820976257,
926
+ "learning_rate": 0.00016908028329286112,
927
+ "loss": 0.4171,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 1.1774157049106133,
932
+ "grad_norm": 0.46892327070236206,
933
+ "learning_rate": 0.0001686241637868734,
934
+ "loss": 0.3628,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 1.1864675265897262,
939
+ "grad_norm": 0.6038176417350769,
940
+ "learning_rate": 0.00016816532968995328,
941
+ "loss": 0.3771,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 1.195519348268839,
946
+ "grad_norm": 0.5433237552642822,
947
+ "learning_rate": 0.00016770379915236766,
948
+ "loss": 0.4029,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 1.204571169947952,
953
+ "grad_norm": 0.6447364091873169,
954
+ "learning_rate": 0.00016723959043104728,
955
+ "loss": 0.4154,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 1.2136229916270649,
960
+ "grad_norm": 0.45961570739746094,
961
+ "learning_rate": 0.00016677272188886483,
962
+ "loss": 0.412,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 1.2226748133061778,
967
+ "grad_norm": 0.5007642507553101,
968
+ "learning_rate": 0.00016630321199390867,
969
+ "loss": 0.4137,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 1.2317266349852907,
974
+ "grad_norm": 0.4964968264102936,
975
+ "learning_rate": 0.00016583107931875192,
976
+ "loss": 0.3922,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 1.2407784566644038,
981
+ "grad_norm": 0.573707640171051,
982
+ "learning_rate": 0.00016535634253971794,
983
+ "loss": 0.3778,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 1.2498302783435167,
988
+ "grad_norm": 0.5992773771286011,
989
+ "learning_rate": 0.00016487902043614173,
990
+ "loss": 0.4528,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 1.2588821000226296,
995
+ "grad_norm": 0.650651216506958,
996
+ "learning_rate": 0.00016439913188962685,
997
+ "loss": 0.3915,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 1.2679339217017425,
1002
+ "grad_norm": 0.5636417865753174,
1003
+ "learning_rate": 0.0001639166958832985,
1004
+ "loss": 0.3947,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 1.2769857433808554,
1009
+ "grad_norm": 0.5544995665550232,
1010
+ "learning_rate": 0.00016343173150105278,
1011
+ "loss": 0.4252,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 1.2860375650599682,
1016
+ "grad_norm": 0.5746600031852722,
1017
+ "learning_rate": 0.0001629442579268016,
1018
+ "loss": 0.4127,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 1.2950893867390811,
1023
+ "grad_norm": 0.5972291231155396,
1024
+ "learning_rate": 0.0001624542944437139,
1025
+ "loss": 0.3918,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 1.3041412084181943,
1030
+ "grad_norm": 0.6181298494338989,
1031
+ "learning_rate": 0.00016196186043345288,
1032
+ "loss": 0.3615,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 1.3131930300973071,
1037
+ "grad_norm": 0.5114730000495911,
1038
+ "learning_rate": 0.00016146697537540924,
1039
+ "loss": 0.3966,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 1.32224485177642,
1044
+ "grad_norm": 0.5740589499473572,
1045
+ "learning_rate": 0.0001609696588459307,
1046
+ "loss": 0.4061,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 1.331296673455533,
1051
+ "grad_norm": 0.6494064927101135,
1052
+ "learning_rate": 0.00016046993051754756,
1053
+ "loss": 0.3979,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 1.3403484951346458,
1058
+ "grad_norm": 0.6532962322235107,
1059
+ "learning_rate": 0.0001599678101581945,
1060
+ "loss": 0.4531,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 1.3494003168137587,
1065
+ "grad_norm": 0.7263498306274414,
1066
+ "learning_rate": 0.00015946331763042867,
1067
+ "loss": 0.3788,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 1.3584521384928716,
1072
+ "grad_norm": 0.8316817879676819,
1073
+ "learning_rate": 0.00015895647289064396,
1074
+ "loss": 0.4298,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 1.3584521384928716,
1079
+ "eval_loss": 11.852625846862793,
1080
+ "eval_runtime": 42.2271,
1081
+ "eval_samples_per_second": 7.507,
1082
+ "eval_steps_per_second": 3.765,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 1.3675039601719847,
1087
+ "grad_norm": 0.4995158314704895,
1088
+ "learning_rate": 0.0001584472959882815,
1089
+ "loss": 0.4021,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 1.3765557818510976,
1094
+ "grad_norm": 0.6390697360038757,
1095
+ "learning_rate": 0.0001579358070650367,
1096
+ "loss": 0.3633,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 1.3856076035302105,
1101
+ "grad_norm": 0.5589749217033386,
1102
+ "learning_rate": 0.00015742202635406235,
1103
+ "loss": 0.3524,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 1.3946594252093234,
1108
+ "grad_norm": 0.5728365778923035,
1109
+ "learning_rate": 0.0001569059741791684,
1110
+ "loss": 0.3456,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 1.4037112468884363,
1115
+ "grad_norm": 0.45577678084373474,
1116
+ "learning_rate": 0.0001563876709540178,
1117
+ "loss": 0.3706,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 1.4127630685675492,
1122
+ "grad_norm": 0.7161752581596375,
1123
+ "learning_rate": 0.00015586713718131922,
1124
+ "loss": 0.362,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 1.421814890246662,
1129
+ "grad_norm": 0.530432403087616,
1130
+ "learning_rate": 0.0001553443934520159,
1131
+ "loss": 0.3798,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 1.4308667119257752,
1136
+ "grad_norm": 0.5991781949996948,
1137
+ "learning_rate": 0.00015481946044447099,
1138
+ "loss": 0.3965,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 1.4399185336048879,
1143
+ "grad_norm": 0.5994631052017212,
1144
+ "learning_rate": 0.00015429235892364994,
1145
+ "loss": 0.3855,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 1.448970355284001,
1150
+ "grad_norm": 0.5677673816680908,
1151
+ "learning_rate": 0.00015376310974029873,
1152
+ "loss": 0.3773,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 1.4580221769631139,
1157
+ "grad_norm": 0.4799586236476898,
1158
+ "learning_rate": 0.0001532317338301192,
1159
+ "loss": 0.3466,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 1.4670739986422268,
1164
+ "grad_norm": 0.5448312163352966,
1165
+ "learning_rate": 0.00015269825221294098,
1166
+ "loss": 0.3664,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 1.4761258203213397,
1171
+ "grad_norm": 0.5199277400970459,
1172
+ "learning_rate": 0.0001521626859918898,
1173
+ "loss": 0.3838,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 1.4851776420004525,
1178
+ "grad_norm": 0.4976363778114319,
1179
+ "learning_rate": 0.00015162505635255287,
1180
+ "loss": 0.3811,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 1.4942294636795654,
1185
+ "grad_norm": 0.6075541377067566,
1186
+ "learning_rate": 0.0001510853845621409,
1187
+ "loss": 0.3756,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 1.5032812853586783,
1192
+ "grad_norm": 0.5979759097099304,
1193
+ "learning_rate": 0.00015054369196864644,
1194
+ "loss": 0.3973,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 1.5123331070377914,
1199
+ "grad_norm": 0.9770258665084839,
1200
+ "learning_rate": 0.00015000000000000001,
1201
+ "loss": 0.4124,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 1.5213849287169041,
1206
+ "grad_norm": 0.580491840839386,
1207
+ "learning_rate": 0.0001494543301632219,
1208
+ "loss": 0.3827,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 1.5304367503960172,
1213
+ "grad_norm": 0.6543178558349609,
1214
+ "learning_rate": 0.0001489067040435717,
1215
+ "loss": 0.4009,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 1.5394885720751301,
1220
+ "grad_norm": 0.5909605622291565,
1221
+ "learning_rate": 0.00014835714330369446,
1222
+ "loss": 0.4272,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 1.548540393754243,
1227
+ "grad_norm": 0.4959102272987366,
1228
+ "learning_rate": 0.0001478056696827636,
1229
+ "loss": 0.3536,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 1.557592215433356,
1234
+ "grad_norm": 0.5864228010177612,
1235
+ "learning_rate": 0.00014725230499562119,
1236
+ "loss": 0.3657,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 1.5666440371124688,
1241
+ "grad_norm": 0.6094350814819336,
1242
+ "learning_rate": 0.00014669707113191483,
1243
+ "loss": 0.3889,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 1.575695858791582,
1248
+ "grad_norm": 0.45741668343544006,
1249
+ "learning_rate": 0.00014613999005523174,
1250
+ "loss": 0.37,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 1.5847476804706946,
1255
+ "grad_norm": 0.5069059729576111,
1256
+ "learning_rate": 0.00014558108380223012,
1257
+ "loss": 0.3992,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 1.5937995021498077,
1262
+ "grad_norm": 0.535524845123291,
1263
+ "learning_rate": 0.00014502037448176734,
1264
+ "loss": 0.3763,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 1.6028513238289206,
1269
+ "grad_norm": 0.5067459940910339,
1270
+ "learning_rate": 0.00014445788427402528,
1271
+ "loss": 0.3409,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 1.6119031455080335,
1276
+ "grad_norm": 0.5375223159790039,
1277
+ "learning_rate": 0.00014389363542963306,
1278
+ "loss": 0.3778,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 1.6209549671871464,
1283
+ "grad_norm": 0.5057679414749146,
1284
+ "learning_rate": 0.00014332765026878687,
1285
+ "loss": 0.362,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 1.6300067888662593,
1290
+ "grad_norm": 0.5510945320129395,
1291
+ "learning_rate": 0.00014275995118036693,
1292
+ "loss": 0.374,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 1.6390586105453724,
1297
+ "grad_norm": 0.619204580783844,
1298
+ "learning_rate": 0.00014219056062105193,
1299
+ "loss": 0.4279,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 1.648110432224485,
1304
+ "grad_norm": 0.5340638160705566,
1305
+ "learning_rate": 0.00014161950111443077,
1306
+ "loss": 0.3675,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 1.6571622539035982,
1311
+ "grad_norm": 0.6182312965393066,
1312
+ "learning_rate": 0.0001410467952501114,
1313
+ "loss": 0.3686,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 1.666214075582711,
1318
+ "grad_norm": 0.5214246511459351,
1319
+ "learning_rate": 0.00014047246568282736,
1320
+ "loss": 0.4001,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 1.675265897261824,
1325
+ "grad_norm": 0.4987814128398895,
1326
+ "learning_rate": 0.00013989653513154165,
1327
+ "loss": 0.357,
1328
+ "step": 1850
1329
+ },
1330
+ {
1331
+ "epoch": 1.6843177189409368,
1332
+ "grad_norm": 0.6497951149940491,
1333
+ "learning_rate": 0.0001393190263785479,
1334
+ "loss": 0.3722,
1335
+ "step": 1860
1336
+ },
1337
+ {
1338
+ "epoch": 1.6933695406200497,
1339
+ "grad_norm": 0.4140976667404175,
1340
+ "learning_rate": 0.00013873996226856933,
1341
+ "loss": 0.316,
1342
+ "step": 1870
1343
+ },
1344
+ {
1345
+ "epoch": 1.7024213622991629,
1346
+ "grad_norm": 0.5191941857337952,
1347
+ "learning_rate": 0.00013815936570785487,
1348
+ "loss": 0.3865,
1349
+ "step": 1880
1350
+ },
1351
+ {
1352
+ "epoch": 1.7114731839782755,
1353
+ "grad_norm": 0.5386790037155151,
1354
+ "learning_rate": 0.00013757725966327322,
1355
+ "loss": 0.3499,
1356
+ "step": 1890
1357
+ },
1358
+ {
1359
+ "epoch": 1.7205250056573886,
1360
+ "grad_norm": 0.5060738921165466,
1361
+ "learning_rate": 0.00013699366716140435,
1362
+ "loss": 0.3481,
1363
+ "step": 1900
1364
+ },
1365
+ {
1366
+ "epoch": 1.7295768273365013,
1367
+ "grad_norm": 0.5718989968299866,
1368
+ "learning_rate": 0.0001364086112876284,
1369
+ "loss": 0.3713,
1370
+ "step": 1910
1371
+ },
1372
+ {
1373
+ "epoch": 1.7386286490156144,
1374
+ "grad_norm": 0.5812616348266602,
1375
+ "learning_rate": 0.00013582211518521273,
1376
+ "loss": 0.3651,
1377
+ "step": 1920
1378
+ },
1379
+ {
1380
+ "epoch": 1.7476804706947273,
1381
+ "grad_norm": 0.42051294445991516,
1382
+ "learning_rate": 0.00013523420205439646,
1383
+ "loss": 0.3581,
1384
+ "step": 1930
1385
+ },
1386
+ {
1387
+ "epoch": 1.7567322923738402,
1388
+ "grad_norm": 0.6224139928817749,
1389
+ "learning_rate": 0.00013464489515147238,
1390
+ "loss": 0.3663,
1391
+ "step": 1940
1392
+ },
1393
+ {
1394
+ "epoch": 1.765784114052953,
1395
+ "grad_norm": 0.5418313145637512,
1396
+ "learning_rate": 0.00013405421778786737,
1397
+ "loss": 0.3521,
1398
+ "step": 1950
1399
+ },
1400
+ {
1401
+ "epoch": 1.774835935732066,
1402
+ "grad_norm": 0.5429657101631165,
1403
+ "learning_rate": 0.00013346219332922016,
1404
+ "loss": 0.3946,
1405
+ "step": 1960
1406
+ },
1407
+ {
1408
+ "epoch": 1.783887757411179,
1409
+ "grad_norm": 0.5962104797363281,
1410
+ "learning_rate": 0.0001328688451944569,
1411
+ "loss": 0.4121,
1412
+ "step": 1970
1413
+ },
1414
+ {
1415
+ "epoch": 1.7929395790902918,
1416
+ "grad_norm": 0.5818737745285034,
1417
+ "learning_rate": 0.00013227419685486492,
1418
+ "loss": 0.3209,
1419
+ "step": 1980
1420
+ },
1421
+ {
1422
+ "epoch": 1.801991400769405,
1423
+ "grad_norm": 0.4606368839740753,
1424
+ "learning_rate": 0.0001316782718331643,
1425
+ "loss": 0.316,
1426
+ "step": 1990
1427
+ },
1428
+ {
1429
+ "epoch": 1.8110432224485178,
1430
+ "grad_norm": 0.49896928668022156,
1431
+ "learning_rate": 0.00013108109370257712,
1432
+ "loss": 0.3538,
1433
+ "step": 2000
1434
+ },
1435
+ {
1436
+ "epoch": 1.8110432224485178,
1437
+ "eval_loss": 11.89608383178711,
1438
+ "eval_runtime": 41.6812,
1439
+ "eval_samples_per_second": 7.605,
1440
+ "eval_steps_per_second": 3.815,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 1.8200950441276307,
1445
+ "grad_norm": 0.4855138659477234,
1446
+ "learning_rate": 0.00013048268608589533,
1447
+ "loss": 0.3578,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 1.8291468658067436,
1452
+ "grad_norm": 0.577150285243988,
1453
+ "learning_rate": 0.00012988307265454597,
1454
+ "loss": 0.3644,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 1.8381986874858565,
1459
+ "grad_norm": 0.5089125037193298,
1460
+ "learning_rate": 0.00012928227712765504,
1461
+ "loss": 0.398,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 1.8472505091649696,
1466
+ "grad_norm": 0.44641053676605225,
1467
+ "learning_rate": 0.00012868032327110904,
1468
+ "loss": 0.3656,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 1.8563023308440822,
1473
+ "grad_norm": 0.5212085247039795,
1474
+ "learning_rate": 0.00012807723489661495,
1475
+ "loss": 0.3396,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 1.8653541525231954,
1480
+ "grad_norm": 0.48269546031951904,
1481
+ "learning_rate": 0.0001274730358607583,
1482
+ "loss": 0.3649,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 1.8744059742023083,
1487
+ "grad_norm": 0.5938083529472351,
1488
+ "learning_rate": 0.00012686775006405946,
1489
+ "loss": 0.3318,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 1.8834577958814211,
1494
+ "grad_norm": 0.46941766142845154,
1495
+ "learning_rate": 0.0001262614014500282,
1496
+ "loss": 0.3625,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 1.892509617560534,
1501
+ "grad_norm": 0.6015097498893738,
1502
+ "learning_rate": 0.00012565401400421651,
1503
+ "loss": 0.4174,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 1.901561439239647,
1508
+ "grad_norm": 0.6819751858711243,
1509
+ "learning_rate": 0.00012504561175326985,
1510
+ "loss": 0.351,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 1.91061326091876,
1515
+ "grad_norm": 0.4607352018356323,
1516
+ "learning_rate": 0.0001244362187639767,
1517
+ "loss": 0.3488,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 1.9196650825978727,
1522
+ "grad_norm": 0.7872518301010132,
1523
+ "learning_rate": 0.0001238258591423165,
1524
+ "loss": 0.3719,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 1.9287169042769858,
1529
+ "grad_norm": 0.49948009848594666,
1530
+ "learning_rate": 0.00012321455703250616,
1531
+ "loss": 0.3415,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 1.9377687259560985,
1536
+ "grad_norm": 0.513294517993927,
1537
+ "learning_rate": 0.0001226023366160449,
1538
+ "loss": 0.3575,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 1.9468205476352116,
1543
+ "grad_norm": 0.7481987476348877,
1544
+ "learning_rate": 0.00012198922211075778,
1545
+ "loss": 0.3465,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 1.9558723693143245,
1550
+ "grad_norm": 0.4865647852420807,
1551
+ "learning_rate": 0.00012137523776983757,
1552
+ "loss": 0.3246,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 1.9649241909934374,
1557
+ "grad_norm": 0.35988450050354004,
1558
+ "learning_rate": 0.00012076040788088554,
1559
+ "loss": 0.3506,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 1.9739760126725503,
1564
+ "grad_norm": 0.46516749262809753,
1565
+ "learning_rate": 0.00012014475676495052,
1566
+ "loss": 0.3077,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 1.9830278343516632,
1571
+ "grad_norm": 0.5179293751716614,
1572
+ "learning_rate": 0.000119528308775567,
1573
+ "loss": 0.375,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 1.9920796560307763,
1578
+ "grad_norm": 0.5721428394317627,
1579
+ "learning_rate": 0.00011891108829779165,
1580
+ "loss": 0.3503,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 2.0018103643358227,
1585
+ "grad_norm": 0.4291672706604004,
1586
+ "learning_rate": 0.00011829311974723867,
1587
+ "loss": 0.3745,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 2.0108621860149354,
1592
+ "grad_norm": 0.4879133701324463,
1593
+ "learning_rate": 0.00011767442756911417,
1594
+ "loss": 0.2479,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 2.0199140076940485,
1599
+ "grad_norm": 0.5393707752227783,
1600
+ "learning_rate": 0.00011705503623724898,
1601
+ "loss": 0.222,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 2.028965829373161,
1606
+ "grad_norm": 0.5438636541366577,
1607
+ "learning_rate": 0.00011643497025313061,
1608
+ "loss": 0.2726,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 2.0380176510522743,
1613
+ "grad_norm": 0.5499648451805115,
1614
+ "learning_rate": 0.0001158142541449341,
1615
+ "loss": 0.2583,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 2.0470694727313874,
1620
+ "grad_norm": 0.5354553461074829,
1621
+ "learning_rate": 0.0001151929124665516,
1622
+ "loss": 0.2365,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 2.0561212944105,
1627
+ "grad_norm": 0.586413562297821,
1628
+ "learning_rate": 0.00011457096979662114,
1629
+ "loss": 0.243,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 2.065173116089613,
1634
+ "grad_norm": 0.48880791664123535,
1635
+ "learning_rate": 0.00011394845073755455,
1636
+ "loss": 0.2534,
1637
+ "step": 2280
1638
+ },
1639
+ {
1640
+ "epoch": 2.074224937768726,
1641
+ "grad_norm": 0.5162414908409119,
1642
+ "learning_rate": 0.00011332537991456398,
1643
+ "loss": 0.2279,
1644
+ "step": 2290
1645
+ },
1646
+ {
1647
+ "epoch": 2.083276759447839,
1648
+ "grad_norm": 0.6083577871322632,
1649
+ "learning_rate": 0.00011270178197468789,
1650
+ "loss": 0.2353,
1651
+ "step": 2300
1652
+ },
1653
+ {
1654
+ "epoch": 2.0923285811269516,
1655
+ "grad_norm": 0.5396526455879211,
1656
+ "learning_rate": 0.00011207768158581613,
1657
+ "loss": 0.2396,
1658
+ "step": 2310
1659
+ },
1660
+ {
1661
+ "epoch": 2.1013804028060648,
1662
+ "grad_norm": 0.5191901326179504,
1663
+ "learning_rate": 0.00011145310343571411,
1664
+ "loss": 0.2557,
1665
+ "step": 2320
1666
+ },
1667
+ {
1668
+ "epoch": 2.1104322244851774,
1669
+ "grad_norm": 0.4944523572921753,
1670
+ "learning_rate": 0.0001108280722310462,
1671
+ "loss": 0.2332,
1672
+ "step": 2330
1673
+ },
1674
+ {
1675
+ "epoch": 2.1194840461642905,
1676
+ "grad_norm": 0.49368587136268616,
1677
+ "learning_rate": 0.00011020261269639842,
1678
+ "loss": 0.2395,
1679
+ "step": 2340
1680
+ },
1681
+ {
1682
+ "epoch": 2.1285358678434037,
1683
+ "grad_norm": 0.5858927369117737,
1684
+ "learning_rate": 0.00010957674957330042,
1685
+ "loss": 0.27,
1686
+ "step": 2350
1687
+ },
1688
+ {
1689
+ "epoch": 2.1375876895225163,
1690
+ "grad_norm": 0.5289851427078247,
1691
+ "learning_rate": 0.00010895050761924668,
1692
+ "loss": 0.2777,
1693
+ "step": 2360
1694
+ },
1695
+ {
1696
+ "epoch": 2.1466395112016294,
1697
+ "grad_norm": 0.5512372851371765,
1698
+ "learning_rate": 0.00010832391160671729,
1699
+ "loss": 0.257,
1700
+ "step": 2370
1701
+ },
1702
+ {
1703
+ "epoch": 2.155691332880742,
1704
+ "grad_norm": 0.48882365226745605,
1705
+ "learning_rate": 0.00010769698632219794,
1706
+ "loss": 0.2513,
1707
+ "step": 2380
1708
+ },
1709
+ {
1710
+ "epoch": 2.164743154559855,
1711
+ "grad_norm": 0.4982316792011261,
1712
+ "learning_rate": 0.00010706975656519946,
1713
+ "loss": 0.2265,
1714
+ "step": 2390
1715
+ },
1716
+ {
1717
+ "epoch": 2.173794976238968,
1718
+ "grad_norm": 0.5512099266052246,
1719
+ "learning_rate": 0.00010644224714727681,
1720
+ "loss": 0.2586,
1721
+ "step": 2400
1722
+ },
1723
+ {
1724
+ "epoch": 2.182846797918081,
1725
+ "grad_norm": 0.5546220541000366,
1726
+ "learning_rate": 0.00010581448289104758,
1727
+ "loss": 0.2494,
1728
+ "step": 2410
1729
+ },
1730
+ {
1731
+ "epoch": 2.191898619597194,
1732
+ "grad_norm": 0.6402847170829773,
1733
+ "learning_rate": 0.00010518648862921012,
1734
+ "loss": 0.2467,
1735
+ "step": 2420
1736
+ },
1737
+ {
1738
+ "epoch": 2.200950441276307,
1739
+ "grad_norm": 0.4461919665336609,
1740
+ "learning_rate": 0.00010455828920356115,
1741
+ "loss": 0.2248,
1742
+ "step": 2430
1743
+ },
1744
+ {
1745
+ "epoch": 2.21000226295542,
1746
+ "grad_norm": 0.562235951423645,
1747
+ "learning_rate": 0.00010392990946401313,
1748
+ "loss": 0.2196,
1749
+ "step": 2440
1750
+ },
1751
+ {
1752
+ "epoch": 2.2190540846345326,
1753
+ "grad_norm": 0.49623265862464905,
1754
+ "learning_rate": 0.00010330137426761135,
1755
+ "loss": 0.2572,
1756
+ "step": 2450
1757
+ },
1758
+ {
1759
+ "epoch": 2.2281059063136457,
1760
+ "grad_norm": 0.5660530924797058,
1761
+ "learning_rate": 0.00010267270847755048,
1762
+ "loss": 0.2523,
1763
+ "step": 2460
1764
+ },
1765
+ {
1766
+ "epoch": 2.2371577279927584,
1767
+ "grad_norm": 0.5315167307853699,
1768
+ "learning_rate": 0.00010204393696219117,
1769
+ "loss": 0.2489,
1770
+ "step": 2470
1771
+ },
1772
+ {
1773
+ "epoch": 2.2462095496718715,
1774
+ "grad_norm": 0.530099093914032,
1775
+ "learning_rate": 0.00010141508459407623,
1776
+ "loss": 0.2603,
1777
+ "step": 2480
1778
+ },
1779
+ {
1780
+ "epoch": 2.2552613713509846,
1781
+ "grad_norm": 0.6275547742843628,
1782
+ "learning_rate": 0.00010078617624894684,
1783
+ "loss": 0.2338,
1784
+ "step": 2490
1785
+ },
1786
+ {
1787
+ "epoch": 2.2643131930300973,
1788
+ "grad_norm": 0.5999734997749329,
1789
+ "learning_rate": 0.00010015723680475846,
1790
+ "loss": 0.2418,
1791
+ "step": 2500
1792
+ },
1793
+ {
1794
+ "epoch": 2.2643131930300973,
1795
+ "eval_loss": 12.012301445007324,
1796
+ "eval_runtime": 42.3048,
1797
+ "eval_samples_per_second": 7.493,
1798
+ "eval_steps_per_second": 3.758,
1799
+ "step": 2500
1800
+ },
1801
+ {
1802
+ "epoch": 2.2733650147092104,
1803
+ "grad_norm": 0.5600557327270508,
1804
+ "learning_rate": 9.95282911406968e-05,
1805
+ "loss": 0.2394,
1806
+ "step": 2510
1807
+ },
1808
+ {
1809
+ "epoch": 2.282416836388323,
1810
+ "grad_norm": 0.383777379989624,
1811
+ "learning_rate": 9.889936413619356e-05,
1812
+ "loss": 0.2331,
1813
+ "step": 2520
1814
+ },
1815
+ {
1816
+ "epoch": 2.291468658067436,
1817
+ "grad_norm": 0.5634308457374573,
1818
+ "learning_rate": 9.827048066994225e-05,
1819
+ "loss": 0.2492,
1820
+ "step": 2530
1821
+ },
1822
+ {
1823
+ "epoch": 2.300520479746549,
1824
+ "grad_norm": 0.5783660411834717,
1825
+ "learning_rate": 9.764166561891432e-05,
1826
+ "loss": 0.2524,
1827
+ "step": 2540
1828
+ },
1829
+ {
1830
+ "epoch": 2.309572301425662,
1831
+ "grad_norm": 0.6156514286994934,
1832
+ "learning_rate": 9.70129438573747e-05,
1833
+ "loss": 0.2655,
1834
+ "step": 2550
1835
+ },
1836
+ {
1837
+ "epoch": 2.318624123104775,
1838
+ "grad_norm": 0.3963329493999481,
1839
+ "learning_rate": 9.63843402558981e-05,
1840
+ "loss": 0.2459,
1841
+ "step": 2560
1842
+ },
1843
+ {
1844
+ "epoch": 2.3276759447838877,
1845
+ "grad_norm": 0.4392152726650238,
1846
+ "learning_rate": 9.57558796803852e-05,
1847
+ "loss": 0.2579,
1848
+ "step": 2570
1849
+ },
1850
+ {
1851
+ "epoch": 2.336727766463001,
1852
+ "grad_norm": 0.5545589327812195,
1853
+ "learning_rate": 9.512758699107879e-05,
1854
+ "loss": 0.2716,
1855
+ "step": 2580
1856
+ },
1857
+ {
1858
+ "epoch": 2.3457795881421135,
1859
+ "grad_norm": 0.6256219744682312,
1860
+ "learning_rate": 9.449948704158071e-05,
1861
+ "loss": 0.2644,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 2.3548314098212266,
1866
+ "grad_norm": 0.5015664100646973,
1867
+ "learning_rate": 9.38716046778684e-05,
1868
+ "loss": 0.2603,
1869
+ "step": 2600
1870
+ },
1871
+ {
1872
+ "epoch": 2.3638832315003393,
1873
+ "grad_norm": 0.5921751260757446,
1874
+ "learning_rate": 9.324396473731217e-05,
1875
+ "loss": 0.2713,
1876
+ "step": 2610
1877
+ },
1878
+ {
1879
+ "epoch": 2.3729350531794524,
1880
+ "grad_norm": 0.4421112835407257,
1881
+ "learning_rate": 9.261659204769284e-05,
1882
+ "loss": 0.2663,
1883
+ "step": 2620
1884
+ },
1885
+ {
1886
+ "epoch": 2.3819868748585655,
1887
+ "grad_norm": 0.5723668336868286,
1888
+ "learning_rate": 9.198951142621929e-05,
1889
+ "loss": 0.2757,
1890
+ "step": 2630
1891
+ },
1892
+ {
1893
+ "epoch": 2.391038696537678,
1894
+ "grad_norm": 0.5875786542892456,
1895
+ "learning_rate": 9.136274767854716e-05,
1896
+ "loss": 0.2764,
1897
+ "step": 2640
1898
+ },
1899
+ {
1900
+ "epoch": 2.4000905182167913,
1901
+ "grad_norm": 0.6496031284332275,
1902
+ "learning_rate": 9.07363255977973e-05,
1903
+ "loss": 0.273,
1904
+ "step": 2650
1905
+ },
1906
+ {
1907
+ "epoch": 2.409142339895904,
1908
+ "grad_norm": 0.39376866817474365,
1909
+ "learning_rate": 9.011026996357503e-05,
1910
+ "loss": 0.23,
1911
+ "step": 2660
1912
+ },
1913
+ {
1914
+ "epoch": 2.418194161575017,
1915
+ "grad_norm": 0.6112829446792603,
1916
+ "learning_rate": 8.948460554099018e-05,
1917
+ "loss": 0.2605,
1918
+ "step": 2670
1919
+ },
1920
+ {
1921
+ "epoch": 2.4272459832541298,
1922
+ "grad_norm": 0.519059419631958,
1923
+ "learning_rate": 8.885935707967716e-05,
1924
+ "loss": 0.2501,
1925
+ "step": 2680
1926
+ },
1927
+ {
1928
+ "epoch": 2.436297804933243,
1929
+ "grad_norm": 0.8110079765319824,
1930
+ "learning_rate": 8.823454931281616e-05,
1931
+ "loss": 0.2387,
1932
+ "step": 2690
1933
+ },
1934
+ {
1935
+ "epoch": 2.4453496266123556,
1936
+ "grad_norm": 0.7474923133850098,
1937
+ "learning_rate": 8.76102069561545e-05,
1938
+ "loss": 0.2655,
1939
+ "step": 2700
1940
+ },
1941
+ {
1942
+ "epoch": 2.4544014482914687,
1943
+ "grad_norm": 0.44778284430503845,
1944
+ "learning_rate": 8.698635470702923e-05,
1945
+ "loss": 0.2285,
1946
+ "step": 2710
1947
+ },
1948
+ {
1949
+ "epoch": 2.4634532699705813,
1950
+ "grad_norm": 0.5677033066749573,
1951
+ "learning_rate": 8.636301724339004e-05,
1952
+ "loss": 0.2433,
1953
+ "step": 2720
1954
+ },
1955
+ {
1956
+ "epoch": 2.4725050916496945,
1957
+ "grad_norm": 0.5416902303695679,
1958
+ "learning_rate": 8.574021922282292e-05,
1959
+ "loss": 0.238,
1960
+ "step": 2730
1961
+ },
1962
+ {
1963
+ "epoch": 2.4815569133288076,
1964
+ "grad_norm": 0.5404213666915894,
1965
+ "learning_rate": 8.511798528157512e-05,
1966
+ "loss": 0.2682,
1967
+ "step": 2740
1968
+ },
1969
+ {
1970
+ "epoch": 2.4906087350079202,
1971
+ "grad_norm": 0.4115196168422699,
1972
+ "learning_rate": 8.449634003358022e-05,
1973
+ "loss": 0.2486,
1974
+ "step": 2750
1975
+ },
1976
+ {
1977
+ "epoch": 2.4996605566870334,
1978
+ "grad_norm": 0.40759924054145813,
1979
+ "learning_rate": 8.387530806948476e-05,
1980
+ "loss": 0.2381,
1981
+ "step": 2760
1982
+ },
1983
+ {
1984
+ "epoch": 2.508712378366146,
1985
+ "grad_norm": 0.5902087092399597,
1986
+ "learning_rate": 8.325491395567541e-05,
1987
+ "loss": 0.2364,
1988
+ "step": 2770
1989
+ },
1990
+ {
1991
+ "epoch": 2.517764200045259,
1992
+ "grad_norm": 0.5643983483314514,
1993
+ "learning_rate": 8.263518223330697e-05,
1994
+ "loss": 0.2322,
1995
+ "step": 2780
1996
+ },
1997
+ {
1998
+ "epoch": 2.526816021724372,
1999
+ "grad_norm": 0.55036860704422,
2000
+ "learning_rate": 8.201613741733203e-05,
2001
+ "loss": 0.2697,
2002
+ "step": 2790
2003
+ },
2004
+ {
2005
+ "epoch": 2.535867843403485,
2006
+ "grad_norm": 0.5846819877624512,
2007
+ "learning_rate": 8.13978039955308e-05,
2008
+ "loss": 0.2648,
2009
+ "step": 2800
2010
+ },
2011
+ {
2012
+ "epoch": 2.544919665082598,
2013
+ "grad_norm": 0.6239003539085388,
2014
+ "learning_rate": 8.078020642754274e-05,
2015
+ "loss": 0.244,
2016
+ "step": 2810
2017
+ },
2018
+ {
2019
+ "epoch": 2.5539714867617107,
2020
+ "grad_norm": 0.49254196882247925,
2021
+ "learning_rate": 8.016336914389874e-05,
2022
+ "loss": 0.2475,
2023
+ "step": 2820
2024
+ },
2025
+ {
2026
+ "epoch": 2.563023308440824,
2027
+ "grad_norm": 0.737869381904602,
2028
+ "learning_rate": 7.954731654505491e-05,
2029
+ "loss": 0.2694,
2030
+ "step": 2830
2031
+ },
2032
+ {
2033
+ "epoch": 2.5720751301199365,
2034
+ "grad_norm": 0.5183305144309998,
2035
+ "learning_rate": 7.89320730004274e-05,
2036
+ "loss": 0.234,
2037
+ "step": 2840
2038
+ },
2039
+ {
2040
+ "epoch": 2.5811269517990496,
2041
+ "grad_norm": 0.4777659773826599,
2042
+ "learning_rate": 7.831766284742807e-05,
2043
+ "loss": 0.2552,
2044
+ "step": 2850
2045
+ },
2046
+ {
2047
+ "epoch": 2.5901787734781623,
2048
+ "grad_norm": 0.553449809551239,
2049
+ "learning_rate": 7.77041103905023e-05,
2050
+ "loss": 0.2275,
2051
+ "step": 2860
2052
+ },
2053
+ {
2054
+ "epoch": 2.5992305951572754,
2055
+ "grad_norm": 0.542242169380188,
2056
+ "learning_rate": 7.709143990016702e-05,
2057
+ "loss": 0.2736,
2058
+ "step": 2870
2059
+ },
2060
+ {
2061
+ "epoch": 2.6082824168363885,
2062
+ "grad_norm": 0.564593493938446,
2063
+ "learning_rate": 7.6479675612051e-05,
2064
+ "loss": 0.2469,
2065
+ "step": 2880
2066
+ },
2067
+ {
2068
+ "epoch": 2.617334238515501,
2069
+ "grad_norm": 0.37938451766967773,
2070
+ "learning_rate": 7.586884172593609e-05,
2071
+ "loss": 0.2362,
2072
+ "step": 2890
2073
+ },
2074
+ {
2075
+ "epoch": 2.6263860601946143,
2076
+ "grad_norm": 0.6128523945808411,
2077
+ "learning_rate": 7.525896240479976e-05,
2078
+ "loss": 0.2456,
2079
+ "step": 2900
2080
+ },
2081
+ {
2082
+ "epoch": 2.635437881873727,
2083
+ "grad_norm": 0.6073201894760132,
2084
+ "learning_rate": 7.465006177385953e-05,
2085
+ "loss": 0.2413,
2086
+ "step": 2910
2087
+ },
2088
+ {
2089
+ "epoch": 2.64448970355284,
2090
+ "grad_norm": 0.4320588707923889,
2091
+ "learning_rate": 7.404216391961847e-05,
2092
+ "loss": 0.243,
2093
+ "step": 2920
2094
+ },
2095
+ {
2096
+ "epoch": 2.6535415252319527,
2097
+ "grad_norm": 0.40451350808143616,
2098
+ "learning_rate": 7.343529288891239e-05,
2099
+ "loss": 0.265,
2100
+ "step": 2930
2101
+ },
2102
+ {
2103
+ "epoch": 2.662593346911066,
2104
+ "grad_norm": 0.43473196029663086,
2105
+ "learning_rate": 7.282947268795877e-05,
2106
+ "loss": 0.2267,
2107
+ "step": 2940
2108
+ },
2109
+ {
2110
+ "epoch": 2.671645168590179,
2111
+ "grad_norm": 0.6388351917266846,
2112
+ "learning_rate": 7.222472728140695e-05,
2113
+ "loss": 0.2745,
2114
+ "step": 2950
2115
+ },
2116
+ {
2117
+ "epoch": 2.6806969902692916,
2118
+ "grad_norm": 0.5615083575248718,
2119
+ "learning_rate": 7.162108059139032e-05,
2120
+ "loss": 0.25,
2121
+ "step": 2960
2122
+ },
2123
+ {
2124
+ "epoch": 2.6897488119484048,
2125
+ "grad_norm": 0.6018364429473877,
2126
+ "learning_rate": 7.101855649657991e-05,
2127
+ "loss": 0.2601,
2128
+ "step": 2970
2129
+ },
2130
+ {
2131
+ "epoch": 2.6988006336275174,
2132
+ "grad_norm": 0.5931141376495361,
2133
+ "learning_rate": 7.041717883123977e-05,
2134
+ "loss": 0.2455,
2135
+ "step": 2980
2136
+ },
2137
+ {
2138
+ "epoch": 2.7078524553066305,
2139
+ "grad_norm": 0.4409467875957489,
2140
+ "learning_rate": 6.981697138428434e-05,
2141
+ "loss": 0.2584,
2142
+ "step": 2990
2143
+ },
2144
+ {
2145
+ "epoch": 2.716904276985743,
2146
+ "grad_norm": 0.6161777377128601,
2147
+ "learning_rate": 6.921795789833723e-05,
2148
+ "loss": 0.2364,
2149
+ "step": 3000
2150
+ },
2151
+ {
2152
+ "epoch": 2.716904276985743,
2153
+ "eval_loss": 11.997015953063965,
2154
+ "eval_runtime": 42.4537,
2155
+ "eval_samples_per_second": 7.467,
2156
+ "eval_steps_per_second": 3.745,
2157
+ "step": 3000
2158
+ }
2159
+ ],
2160
+ "logging_steps": 10,
2161
+ "max_steps": 5000,
2162
+ "num_input_tokens_seen": 0,
2163
+ "num_train_epochs": 5,
2164
+ "save_steps": 500,
2165
+ "stateful_callbacks": {
2166
+ "TrainerControl": {
2167
+ "args": {
2168
+ "should_epoch_stop": false,
2169
+ "should_evaluate": false,
2170
+ "should_log": false,
2171
+ "should_save": true,
2172
+ "should_training_stop": false
2173
+ },
2174
+ "attributes": {}
2175
+ }
2176
+ },
2177
+ "total_flos": 3.6779958650393395e+17,
2178
+ "train_batch_size": 2,
2179
+ "trial_name": null,
2180
+ "trial_params": null
2181
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc0b248b0698ef8c72a221306819165296af454387598889d7f2f9507784994
3
+ size 5688