MohamedAhmedAE commited on
Commit
43c615a
·
verified ·
1 Parent(s): e9ad8c9

Training in progress, step 74600

Browse files
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
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": 256,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "v_proj",
27
+ "o_proj",
28
+ "q_proj",
29
+ "up_proj",
30
+ "gate_proj",
31
+ "down_proj",
32
+ "k_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 sha256:02bcede41ae4300f8262bb94f029bc40dc0ace97e0cacc19cbd082819fdf9e6f
3
+ size 1342238560
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
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
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
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": 256,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "v_proj",
30
+ "gate_proj",
31
+ "o_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adade87829d537ad6739250c483b6706bdd890e1f0c9de83cdf06f44b32e5090
3
+ size 1342238560
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5615a410c858c99e3cf7362945f36a6e9c191706d0a029ed4b1e854e10c57b
3
+ size 683268498
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dccc9cbc468284f92a4012f3a3803f3d2cbb7abb4eeb9a6c35e73e04a7df0c1b
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73dccec2330458d52f8108cf9299eca128bc179d6d432f80a29c728273abc45
3
+ size 1064
last-checkpoint/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": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
3
+ size 17210019
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_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
+ "max_length": 4096,
2059
+ "model_input_names": [
2060
+ "input_ids",
2061
+ "attention_mask"
2062
+ ],
2063
+ "model_max_length": 4096,
2064
+ "pad_token": "<|eot_id|>",
2065
+ "padding_side": "left",
2066
+ "stride": 0,
2067
+ "tokenizer_class": "PreTrainedTokenizerFast",
2068
+ "truncation_side": "right",
2069
+ "truncation_strategy": "longest_first"
2070
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,2637 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.05174388723170899,
5
+ "eval_steps": 500,
6
+ "global_step": 74400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00013909647105298114,
13
+ "grad_norm": 3.490684747695923,
14
+ "learning_rate": 1.9999999832914018e-05,
15
+ "loss": 1.8403,
16
+ "step": 200
17
+ },
18
+ {
19
+ "epoch": 0.0002781929421059623,
20
+ "grad_norm": 3.975701332092285,
21
+ "learning_rate": 1.9999999331656075e-05,
22
+ "loss": 1.7405,
23
+ "step": 400
24
+ },
25
+ {
26
+ "epoch": 0.00041728941315894347,
27
+ "grad_norm": 1.8542802333831787,
28
+ "learning_rate": 1.9999998496226195e-05,
29
+ "loss": 1.7381,
30
+ "step": 600
31
+ },
32
+ {
33
+ "epoch": 0.0005563858842119246,
34
+ "grad_norm": 2.3053829669952393,
35
+ "learning_rate": 1.999999732662442e-05,
36
+ "loss": 1.7488,
37
+ "step": 800
38
+ },
39
+ {
40
+ "epoch": 0.0006954823552649058,
41
+ "grad_norm": 3.304736614227295,
42
+ "learning_rate": 1.99999958228508e-05,
43
+ "loss": 1.6913,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 0.0008345788263178869,
48
+ "grad_norm": 2.547065019607544,
49
+ "learning_rate": 1.999999398490542e-05,
50
+ "loss": 1.7454,
51
+ "step": 1200
52
+ },
53
+ {
54
+ "epoch": 0.0009736752973708681,
55
+ "grad_norm": 3.4149389266967773,
56
+ "learning_rate": 1.999999181278835e-05,
57
+ "loss": 1.7446,
58
+ "step": 1400
59
+ },
60
+ {
61
+ "epoch": 0.001112771768423849,
62
+ "grad_norm": 7.536021709442139,
63
+ "learning_rate": 1.999998930649971e-05,
64
+ "loss": 1.7236,
65
+ "step": 1600
66
+ },
67
+ {
68
+ "epoch": 0.0012518682394768305,
69
+ "grad_norm": 3.5668132305145264,
70
+ "learning_rate": 1.9999986466039608e-05,
71
+ "loss": 1.7183,
72
+ "step": 1800
73
+ },
74
+ {
75
+ "epoch": 0.0013909647105298116,
76
+ "grad_norm": 2.099731683731079,
77
+ "learning_rate": 1.999998329140819e-05,
78
+ "loss": 1.6953,
79
+ "step": 2000
80
+ },
81
+ {
82
+ "epoch": 0.0015300611815827927,
83
+ "grad_norm": 2.7119176387786865,
84
+ "learning_rate": 1.99999797826056e-05,
85
+ "loss": 1.7412,
86
+ "step": 2200
87
+ },
88
+ {
89
+ "epoch": 0.0016691576526357739,
90
+ "grad_norm": 3.5231118202209473,
91
+ "learning_rate": 1.9999975939632005e-05,
92
+ "loss": 1.6678,
93
+ "step": 2400
94
+ },
95
+ {
96
+ "epoch": 0.001808254123688755,
97
+ "grad_norm": 2.289564371109009,
98
+ "learning_rate": 1.9999971762487593e-05,
99
+ "loss": 1.7012,
100
+ "step": 2600
101
+ },
102
+ {
103
+ "epoch": 0.0019473505947417361,
104
+ "grad_norm": 2.248680591583252,
105
+ "learning_rate": 1.999996725117256e-05,
106
+ "loss": 1.69,
107
+ "step": 2800
108
+ },
109
+ {
110
+ "epoch": 0.0020864470657947173,
111
+ "grad_norm": 1.9502891302108765,
112
+ "learning_rate": 1.9999962405687122e-05,
113
+ "loss": 1.7891,
114
+ "step": 3000
115
+ },
116
+ {
117
+ "epoch": 0.002225543536847698,
118
+ "grad_norm": 2.609624147415161,
119
+ "learning_rate": 1.9999957226031515e-05,
120
+ "loss": 1.6898,
121
+ "step": 3200
122
+ },
123
+ {
124
+ "epoch": 0.0023646400079006796,
125
+ "grad_norm": 3.5334463119506836,
126
+ "learning_rate": 1.9999951712205977e-05,
127
+ "loss": 1.664,
128
+ "step": 3400
129
+ },
130
+ {
131
+ "epoch": 0.002503736478953661,
132
+ "grad_norm": 4.190518856048584,
133
+ "learning_rate": 1.9999945864210777e-05,
134
+ "loss": 1.7189,
135
+ "step": 3600
136
+ },
137
+ {
138
+ "epoch": 0.002642832950006642,
139
+ "grad_norm": 1.869044542312622,
140
+ "learning_rate": 1.999993968204619e-05,
141
+ "loss": 1.7454,
142
+ "step": 3800
143
+ },
144
+ {
145
+ "epoch": 0.002781929421059623,
146
+ "grad_norm": 3.599501609802246,
147
+ "learning_rate": 1.9999933165712525e-05,
148
+ "loss": 1.7142,
149
+ "step": 4000
150
+ },
151
+ {
152
+ "epoch": 0.002921025892112604,
153
+ "grad_norm": 4.190791130065918,
154
+ "learning_rate": 1.999992631521008e-05,
155
+ "loss": 1.6922,
156
+ "step": 4200
157
+ },
158
+ {
159
+ "epoch": 0.0030601223631655855,
160
+ "grad_norm": 1.6306347846984863,
161
+ "learning_rate": 1.999991913053918e-05,
162
+ "loss": 1.7296,
163
+ "step": 4400
164
+ },
165
+ {
166
+ "epoch": 0.0031992188342185664,
167
+ "grad_norm": 2.6920559406280518,
168
+ "learning_rate": 1.9999911611700172e-05,
169
+ "loss": 1.6584,
170
+ "step": 4600
171
+ },
172
+ {
173
+ "epoch": 0.0033383153052715477,
174
+ "grad_norm": 2.2550413608551025,
175
+ "learning_rate": 1.999990375869342e-05,
176
+ "loss": 1.7011,
177
+ "step": 4800
178
+ },
179
+ {
180
+ "epoch": 0.0034774117763245287,
181
+ "grad_norm": 2.0802359580993652,
182
+ "learning_rate": 1.9999895571519294e-05,
183
+ "loss": 1.7183,
184
+ "step": 5000
185
+ },
186
+ {
187
+ "epoch": 0.00361650824737751,
188
+ "grad_norm": 1.8050875663757324,
189
+ "learning_rate": 1.9999887050178187e-05,
190
+ "loss": 1.6972,
191
+ "step": 5200
192
+ },
193
+ {
194
+ "epoch": 0.003755604718430491,
195
+ "grad_norm": 1.8249893188476562,
196
+ "learning_rate": 1.99998781946705e-05,
197
+ "loss": 1.7097,
198
+ "step": 5400
199
+ },
200
+ {
201
+ "epoch": 0.0038947011894834723,
202
+ "grad_norm": 2.246152639389038,
203
+ "learning_rate": 1.9999869004996664e-05,
204
+ "loss": 1.687,
205
+ "step": 5600
206
+ },
207
+ {
208
+ "epoch": 0.004033797660536453,
209
+ "grad_norm": 2.287285089492798,
210
+ "learning_rate": 1.9999859481157112e-05,
211
+ "loss": 1.7333,
212
+ "step": 5800
213
+ },
214
+ {
215
+ "epoch": 0.004172894131589435,
216
+ "grad_norm": 3.4363529682159424,
217
+ "learning_rate": 1.99998496231523e-05,
218
+ "loss": 1.8065,
219
+ "step": 6000
220
+ },
221
+ {
222
+ "epoch": 0.004311990602642416,
223
+ "grad_norm": 1.944610834121704,
224
+ "learning_rate": 1.9999839430982698e-05,
225
+ "loss": 1.6932,
226
+ "step": 6200
227
+ },
228
+ {
229
+ "epoch": 0.004451087073695396,
230
+ "grad_norm": 6.126698017120361,
231
+ "learning_rate": 1.9999828904648794e-05,
232
+ "loss": 1.7195,
233
+ "step": 6400
234
+ },
235
+ {
236
+ "epoch": 0.004590183544748378,
237
+ "grad_norm": 5.03230619430542,
238
+ "learning_rate": 1.9999818044151088e-05,
239
+ "loss": 1.6625,
240
+ "step": 6600
241
+ },
242
+ {
243
+ "epoch": 0.004729280015801359,
244
+ "grad_norm": 1.7065147161483765,
245
+ "learning_rate": 1.9999806849490103e-05,
246
+ "loss": 1.7005,
247
+ "step": 6800
248
+ },
249
+ {
250
+ "epoch": 0.0048683764868543405,
251
+ "grad_norm": 2.811397075653076,
252
+ "learning_rate": 1.9999795320666373e-05,
253
+ "loss": 1.7432,
254
+ "step": 7000
255
+ },
256
+ {
257
+ "epoch": 0.005007472957907322,
258
+ "grad_norm": 2.421945810317993,
259
+ "learning_rate": 1.9999783457680448e-05,
260
+ "loss": 1.6493,
261
+ "step": 7200
262
+ },
263
+ {
264
+ "epoch": 0.005146569428960302,
265
+ "grad_norm": 3.027940273284912,
266
+ "learning_rate": 1.9999771260532886e-05,
267
+ "loss": 1.674,
268
+ "step": 7400
269
+ },
270
+ {
271
+ "epoch": 0.005285665900013284,
272
+ "grad_norm": 2.6853113174438477,
273
+ "learning_rate": 1.9999758729224277e-05,
274
+ "loss": 1.7261,
275
+ "step": 7600
276
+ },
277
+ {
278
+ "epoch": 0.005424762371066265,
279
+ "grad_norm": 1.7555756568908691,
280
+ "learning_rate": 1.9999745863755225e-05,
281
+ "loss": 1.6795,
282
+ "step": 7800
283
+ },
284
+ {
285
+ "epoch": 0.005563858842119246,
286
+ "grad_norm": 2.3382883071899414,
287
+ "learning_rate": 1.999973266412633e-05,
288
+ "loss": 1.7256,
289
+ "step": 8000
290
+ },
291
+ {
292
+ "epoch": 0.005702955313172227,
293
+ "grad_norm": 1.9959968328475952,
294
+ "learning_rate": 1.9999719130338235e-05,
295
+ "loss": 1.6529,
296
+ "step": 8200
297
+ },
298
+ {
299
+ "epoch": 0.005842051784225208,
300
+ "grad_norm": 3.996197462081909,
301
+ "learning_rate": 1.9999705262391574e-05,
302
+ "loss": 1.689,
303
+ "step": 8400
304
+ },
305
+ {
306
+ "epoch": 0.00598114825527819,
307
+ "grad_norm": 2.0444586277008057,
308
+ "learning_rate": 1.999969106028702e-05,
309
+ "loss": 1.6629,
310
+ "step": 8600
311
+ },
312
+ {
313
+ "epoch": 0.006120244726331171,
314
+ "grad_norm": 3.6032233238220215,
315
+ "learning_rate": 1.999967652402525e-05,
316
+ "loss": 1.6322,
317
+ "step": 8800
318
+ },
319
+ {
320
+ "epoch": 0.006259341197384151,
321
+ "grad_norm": 3.2948379516601562,
322
+ "learning_rate": 1.9999661653606947e-05,
323
+ "loss": 1.657,
324
+ "step": 9000
325
+ },
326
+ {
327
+ "epoch": 0.006398437668437133,
328
+ "grad_norm": 2.703350067138672,
329
+ "learning_rate": 1.9999646449032833e-05,
330
+ "loss": 1.7157,
331
+ "step": 9200
332
+ },
333
+ {
334
+ "epoch": 0.006537534139490114,
335
+ "grad_norm": 3.6379008293151855,
336
+ "learning_rate": 1.9999630910303628e-05,
337
+ "loss": 1.7283,
338
+ "step": 9400
339
+ },
340
+ {
341
+ "epoch": 0.0066766306105430955,
342
+ "grad_norm": 3.558755397796631,
343
+ "learning_rate": 1.9999615037420078e-05,
344
+ "loss": 1.6915,
345
+ "step": 9600
346
+ },
347
+ {
348
+ "epoch": 0.006815727081596076,
349
+ "grad_norm": 1.7843396663665771,
350
+ "learning_rate": 1.9999598830382934e-05,
351
+ "loss": 1.7236,
352
+ "step": 9800
353
+ },
354
+ {
355
+ "epoch": 0.006954823552649057,
356
+ "grad_norm": 4.09860372543335,
357
+ "learning_rate": 1.9999582289192974e-05,
358
+ "loss": 1.704,
359
+ "step": 10000
360
+ },
361
+ {
362
+ "epoch": 0.007093920023702039,
363
+ "grad_norm": 1.7402437925338745,
364
+ "learning_rate": 1.9999565413850993e-05,
365
+ "loss": 1.722,
366
+ "step": 10200
367
+ },
368
+ {
369
+ "epoch": 0.00723301649475502,
370
+ "grad_norm": 2.323296546936035,
371
+ "learning_rate": 1.9999548204357783e-05,
372
+ "loss": 1.686,
373
+ "step": 10400
374
+ },
375
+ {
376
+ "epoch": 0.007372112965808001,
377
+ "grad_norm": 2.715653419494629,
378
+ "learning_rate": 1.9999530660714175e-05,
379
+ "loss": 1.702,
380
+ "step": 10600
381
+ },
382
+ {
383
+ "epoch": 0.007511209436860982,
384
+ "grad_norm": 1.7570403814315796,
385
+ "learning_rate": 1.999951278292101e-05,
386
+ "loss": 1.7388,
387
+ "step": 10800
388
+ },
389
+ {
390
+ "epoch": 0.007650305907913963,
391
+ "grad_norm": 3.93326735496521,
392
+ "learning_rate": 1.999949457097913e-05,
393
+ "loss": 1.6729,
394
+ "step": 11000
395
+ },
396
+ {
397
+ "epoch": 0.007789402378966945,
398
+ "grad_norm": 3.1733429431915283,
399
+ "learning_rate": 1.9999476024889414e-05,
400
+ "loss": 1.6785,
401
+ "step": 11200
402
+ },
403
+ {
404
+ "epoch": 0.007928498850019925,
405
+ "grad_norm": 1.2749360799789429,
406
+ "learning_rate": 1.9999457144652746e-05,
407
+ "loss": 1.6974,
408
+ "step": 11400
409
+ },
410
+ {
411
+ "epoch": 0.008067595321072906,
412
+ "grad_norm": 1.4741085767745972,
413
+ "learning_rate": 1.999943793027002e-05,
414
+ "loss": 1.7071,
415
+ "step": 11600
416
+ },
417
+ {
418
+ "epoch": 0.008206691792125888,
419
+ "grad_norm": 1.8536938428878784,
420
+ "learning_rate": 1.999941838174216e-05,
421
+ "loss": 1.669,
422
+ "step": 11800
423
+ },
424
+ {
425
+ "epoch": 0.00834578826317887,
426
+ "grad_norm": 4.066403388977051,
427
+ "learning_rate": 1.9999398499070103e-05,
428
+ "loss": 1.6679,
429
+ "step": 12000
430
+ },
431
+ {
432
+ "epoch": 0.00848488473423185,
433
+ "grad_norm": 2.6502602100372314,
434
+ "learning_rate": 1.9999378282254787e-05,
435
+ "loss": 1.6914,
436
+ "step": 12200
437
+ },
438
+ {
439
+ "epoch": 0.008623981205284832,
440
+ "grad_norm": 1.7778935432434082,
441
+ "learning_rate": 1.999935773129719e-05,
442
+ "loss": 1.7033,
443
+ "step": 12400
444
+ },
445
+ {
446
+ "epoch": 0.008763077676337813,
447
+ "grad_norm": 5.382219314575195,
448
+ "learning_rate": 1.999933684619828e-05,
449
+ "loss": 1.6723,
450
+ "step": 12600
451
+ },
452
+ {
453
+ "epoch": 0.008902174147390793,
454
+ "grad_norm": 2.359602928161621,
455
+ "learning_rate": 1.9999315626959067e-05,
456
+ "loss": 1.7246,
457
+ "step": 12800
458
+ },
459
+ {
460
+ "epoch": 0.009041270618443774,
461
+ "grad_norm": 2.1279995441436768,
462
+ "learning_rate": 1.999929407358055e-05,
463
+ "loss": 1.7077,
464
+ "step": 13000
465
+ },
466
+ {
467
+ "epoch": 0.009180367089496756,
468
+ "grad_norm": 2.6688473224639893,
469
+ "learning_rate": 1.9999272186063767e-05,
470
+ "loss": 1.6788,
471
+ "step": 13200
472
+ },
473
+ {
474
+ "epoch": 0.009319463560549737,
475
+ "grad_norm": 1.7765421867370605,
476
+ "learning_rate": 1.9999249964409763e-05,
477
+ "loss": 1.6995,
478
+ "step": 13400
479
+ },
480
+ {
481
+ "epoch": 0.009458560031602718,
482
+ "grad_norm": 1.976920485496521,
483
+ "learning_rate": 1.9999227408619597e-05,
484
+ "loss": 1.6848,
485
+ "step": 13600
486
+ },
487
+ {
488
+ "epoch": 0.0095976565026557,
489
+ "grad_norm": 1.5781333446502686,
490
+ "learning_rate": 1.9999204518694348e-05,
491
+ "loss": 1.6838,
492
+ "step": 13800
493
+ },
494
+ {
495
+ "epoch": 0.009736752973708681,
496
+ "grad_norm": 3.1562576293945312,
497
+ "learning_rate": 1.9999181294635103e-05,
498
+ "loss": 1.697,
499
+ "step": 14000
500
+ },
501
+ {
502
+ "epoch": 0.009875849444761662,
503
+ "grad_norm": 3.2943713665008545,
504
+ "learning_rate": 1.9999157736442973e-05,
505
+ "loss": 1.6949,
506
+ "step": 14200
507
+ },
508
+ {
509
+ "epoch": 0.010014945915814644,
510
+ "grad_norm": 2.8242108821868896,
511
+ "learning_rate": 1.999913384411909e-05,
512
+ "loss": 1.6555,
513
+ "step": 14400
514
+ },
515
+ {
516
+ "epoch": 0.010154042386867623,
517
+ "grad_norm": 3.441899299621582,
518
+ "learning_rate": 1.9999109617664585e-05,
519
+ "loss": 1.717,
520
+ "step": 14600
521
+ },
522
+ {
523
+ "epoch": 0.010293138857920605,
524
+ "grad_norm": 1.9739881753921509,
525
+ "learning_rate": 1.9999085057080614e-05,
526
+ "loss": 1.6838,
527
+ "step": 14800
528
+ },
529
+ {
530
+ "epoch": 0.010432235328973586,
531
+ "grad_norm": 2.0629451274871826,
532
+ "learning_rate": 1.999906016236836e-05,
533
+ "loss": 1.6777,
534
+ "step": 15000
535
+ },
536
+ {
537
+ "epoch": 0.010571331800026567,
538
+ "grad_norm": 2.920884847640991,
539
+ "learning_rate": 1.9999034933529003e-05,
540
+ "loss": 1.7185,
541
+ "step": 15200
542
+ },
543
+ {
544
+ "epoch": 0.010710428271079549,
545
+ "grad_norm": 3.8650007247924805,
546
+ "learning_rate": 1.9999009370563746e-05,
547
+ "loss": 1.717,
548
+ "step": 15400
549
+ },
550
+ {
551
+ "epoch": 0.01084952474213253,
552
+ "grad_norm": 2.3857533931732178,
553
+ "learning_rate": 1.9998983473473816e-05,
554
+ "loss": 1.7108,
555
+ "step": 15600
556
+ },
557
+ {
558
+ "epoch": 0.010988621213185511,
559
+ "grad_norm": 1.6580150127410889,
560
+ "learning_rate": 1.9998957242260447e-05,
561
+ "loss": 1.7263,
562
+ "step": 15800
563
+ },
564
+ {
565
+ "epoch": 0.011127717684238493,
566
+ "grad_norm": 2.27158784866333,
567
+ "learning_rate": 1.9998930676924887e-05,
568
+ "loss": 1.6676,
569
+ "step": 16000
570
+ },
571
+ {
572
+ "epoch": 0.011266814155291472,
573
+ "grad_norm": 2.073591947555542,
574
+ "learning_rate": 1.999890377746841e-05,
575
+ "loss": 1.6653,
576
+ "step": 16200
577
+ },
578
+ {
579
+ "epoch": 0.011405910626344454,
580
+ "grad_norm": 2.6413662433624268,
581
+ "learning_rate": 1.9998876543892297e-05,
582
+ "loss": 1.7,
583
+ "step": 16400
584
+ },
585
+ {
586
+ "epoch": 0.011545007097397435,
587
+ "grad_norm": 1.7674572467803955,
588
+ "learning_rate": 1.9998848976197845e-05,
589
+ "loss": 1.655,
590
+ "step": 16600
591
+ },
592
+ {
593
+ "epoch": 0.011684103568450416,
594
+ "grad_norm": 3.325094699859619,
595
+ "learning_rate": 1.9998821074386376e-05,
596
+ "loss": 1.6966,
597
+ "step": 16800
598
+ },
599
+ {
600
+ "epoch": 0.011823200039503398,
601
+ "grad_norm": 4.600919246673584,
602
+ "learning_rate": 1.9998792838459226e-05,
603
+ "loss": 1.6826,
604
+ "step": 17000
605
+ },
606
+ {
607
+ "epoch": 0.01196229651055638,
608
+ "grad_norm": 2.438291072845459,
609
+ "learning_rate": 1.9998764268417728e-05,
610
+ "loss": 1.6938,
611
+ "step": 17200
612
+ },
613
+ {
614
+ "epoch": 0.01210139298160936,
615
+ "grad_norm": 3.072421073913574,
616
+ "learning_rate": 1.9998735364263257e-05,
617
+ "loss": 1.6398,
618
+ "step": 17400
619
+ },
620
+ {
621
+ "epoch": 0.012240489452662342,
622
+ "grad_norm": 3.100858688354492,
623
+ "learning_rate": 1.9998706125997193e-05,
624
+ "loss": 1.7201,
625
+ "step": 17600
626
+ },
627
+ {
628
+ "epoch": 0.012379585923715323,
629
+ "grad_norm": 1.6366045475006104,
630
+ "learning_rate": 1.9998676553620927e-05,
631
+ "loss": 1.7063,
632
+ "step": 17800
633
+ },
634
+ {
635
+ "epoch": 0.012518682394768303,
636
+ "grad_norm": 3.026857852935791,
637
+ "learning_rate": 1.9998646647135877e-05,
638
+ "loss": 1.7723,
639
+ "step": 18000
640
+ },
641
+ {
642
+ "epoch": 0.012657778865821284,
643
+ "grad_norm": 2.204956293106079,
644
+ "learning_rate": 1.9998616406543457e-05,
645
+ "loss": 1.7373,
646
+ "step": 18200
647
+ },
648
+ {
649
+ "epoch": 0.012796875336874266,
650
+ "grad_norm": 3.4815049171447754,
651
+ "learning_rate": 1.999858583184513e-05,
652
+ "loss": 1.7032,
653
+ "step": 18400
654
+ },
655
+ {
656
+ "epoch": 0.012935971807927247,
657
+ "grad_norm": 2.680816411972046,
658
+ "learning_rate": 1.9998554923042343e-05,
659
+ "loss": 1.7167,
660
+ "step": 18600
661
+ },
662
+ {
663
+ "epoch": 0.013075068278980228,
664
+ "grad_norm": 2.0747711658477783,
665
+ "learning_rate": 1.9998523680136575e-05,
666
+ "loss": 1.7054,
667
+ "step": 18800
668
+ },
669
+ {
670
+ "epoch": 0.01321416475003321,
671
+ "grad_norm": 2.943026065826416,
672
+ "learning_rate": 1.9998492103129314e-05,
673
+ "loss": 1.7296,
674
+ "step": 19000
675
+ },
676
+ {
677
+ "epoch": 0.013353261221086191,
678
+ "grad_norm": 3.2096681594848633,
679
+ "learning_rate": 1.9998460192022073e-05,
680
+ "loss": 1.7288,
681
+ "step": 19200
682
+ },
683
+ {
684
+ "epoch": 0.013492357692139172,
685
+ "grad_norm": 1.9929059743881226,
686
+ "learning_rate": 1.999842794681637e-05,
687
+ "loss": 1.6747,
688
+ "step": 19400
689
+ },
690
+ {
691
+ "epoch": 0.013631454163192152,
692
+ "grad_norm": 2.7822391986846924,
693
+ "learning_rate": 1.9998395367513753e-05,
694
+ "loss": 1.6426,
695
+ "step": 19600
696
+ },
697
+ {
698
+ "epoch": 0.013770550634245133,
699
+ "grad_norm": 2.433687686920166,
700
+ "learning_rate": 1.9998362454115767e-05,
701
+ "loss": 1.6781,
702
+ "step": 19800
703
+ },
704
+ {
705
+ "epoch": 0.013909647105298115,
706
+ "grad_norm": 2.0973353385925293,
707
+ "learning_rate": 1.999832920662399e-05,
708
+ "loss": 1.7132,
709
+ "step": 20000
710
+ },
711
+ {
712
+ "epoch": 0.014048743576351096,
713
+ "grad_norm": 1.9057769775390625,
714
+ "learning_rate": 1.9998295625040006e-05,
715
+ "loss": 1.7141,
716
+ "step": 20200
717
+ },
718
+ {
719
+ "epoch": 0.014187840047404077,
720
+ "grad_norm": 3.1140308380126953,
721
+ "learning_rate": 1.9998261709365422e-05,
722
+ "loss": 1.6266,
723
+ "step": 20400
724
+ },
725
+ {
726
+ "epoch": 0.014326936518457059,
727
+ "grad_norm": 5.554874420166016,
728
+ "learning_rate": 1.9998227459601847e-05,
729
+ "loss": 1.7396,
730
+ "step": 20600
731
+ },
732
+ {
733
+ "epoch": 0.01446603298951004,
734
+ "grad_norm": 3.160214424133301,
735
+ "learning_rate": 1.9998192875750928e-05,
736
+ "loss": 1.6973,
737
+ "step": 20800
738
+ },
739
+ {
740
+ "epoch": 0.014605129460563021,
741
+ "grad_norm": 5.784990310668945,
742
+ "learning_rate": 1.999815795781431e-05,
743
+ "loss": 1.7528,
744
+ "step": 21000
745
+ },
746
+ {
747
+ "epoch": 0.014744225931616003,
748
+ "grad_norm": 2.038553237915039,
749
+ "learning_rate": 1.9998122705793667e-05,
750
+ "loss": 1.6435,
751
+ "step": 21200
752
+ },
753
+ {
754
+ "epoch": 0.014883322402668982,
755
+ "grad_norm": 2.000013589859009,
756
+ "learning_rate": 1.9998087119690667e-05,
757
+ "loss": 1.746,
758
+ "step": 21400
759
+ },
760
+ {
761
+ "epoch": 0.015022418873721964,
762
+ "grad_norm": 4.159511566162109,
763
+ "learning_rate": 1.9998051199507023e-05,
764
+ "loss": 1.6741,
765
+ "step": 21600
766
+ },
767
+ {
768
+ "epoch": 0.015161515344774945,
769
+ "grad_norm": 4.24055814743042,
770
+ "learning_rate": 1.9998014945244445e-05,
771
+ "loss": 1.6825,
772
+ "step": 21800
773
+ },
774
+ {
775
+ "epoch": 0.015300611815827926,
776
+ "grad_norm": 2.4057905673980713,
777
+ "learning_rate": 1.9997978356904658e-05,
778
+ "loss": 1.7085,
779
+ "step": 22000
780
+ },
781
+ {
782
+ "epoch": 0.015439708286880908,
783
+ "grad_norm": 1.9155327081680298,
784
+ "learning_rate": 1.999794143448942e-05,
785
+ "loss": 1.7391,
786
+ "step": 22200
787
+ },
788
+ {
789
+ "epoch": 0.01557880475793389,
790
+ "grad_norm": 1.7514386177062988,
791
+ "learning_rate": 1.9997904178000485e-05,
792
+ "loss": 1.7169,
793
+ "step": 22400
794
+ },
795
+ {
796
+ "epoch": 0.01571790122898687,
797
+ "grad_norm": 2.172142744064331,
798
+ "learning_rate": 1.9997866587439633e-05,
799
+ "loss": 1.6361,
800
+ "step": 22600
801
+ },
802
+ {
803
+ "epoch": 0.01585699770003985,
804
+ "grad_norm": 2.026682138442993,
805
+ "learning_rate": 1.9997828662808665e-05,
806
+ "loss": 1.7017,
807
+ "step": 22800
808
+ },
809
+ {
810
+ "epoch": 0.015996094171092833,
811
+ "grad_norm": 3.7516732215881348,
812
+ "learning_rate": 1.999779040410938e-05,
813
+ "loss": 1.6982,
814
+ "step": 23000
815
+ },
816
+ {
817
+ "epoch": 0.016135190642145813,
818
+ "grad_norm": 1.6760916709899902,
819
+ "learning_rate": 1.9997751811343617e-05,
820
+ "loss": 1.6747,
821
+ "step": 23200
822
+ },
823
+ {
824
+ "epoch": 0.016274287113198796,
825
+ "grad_norm": 4.183455944061279,
826
+ "learning_rate": 1.9997712884513206e-05,
827
+ "loss": 1.6745,
828
+ "step": 23400
829
+ },
830
+ {
831
+ "epoch": 0.016413383584251776,
832
+ "grad_norm": 4.69508695602417,
833
+ "learning_rate": 1.9997673623620018e-05,
834
+ "loss": 1.6605,
835
+ "step": 23600
836
+ },
837
+ {
838
+ "epoch": 0.016552480055304755,
839
+ "grad_norm": 4.241724014282227,
840
+ "learning_rate": 1.9997634028665915e-05,
841
+ "loss": 1.6547,
842
+ "step": 23800
843
+ },
844
+ {
845
+ "epoch": 0.01669157652635774,
846
+ "grad_norm": 2.174389362335205,
847
+ "learning_rate": 1.9997594099652796e-05,
848
+ "loss": 1.6315,
849
+ "step": 24000
850
+ },
851
+ {
852
+ "epoch": 0.016830672997410718,
853
+ "grad_norm": 1.7669682502746582,
854
+ "learning_rate": 1.9997553836582564e-05,
855
+ "loss": 1.6784,
856
+ "step": 24200
857
+ },
858
+ {
859
+ "epoch": 0.0169697694684637,
860
+ "grad_norm": 1.653138279914856,
861
+ "learning_rate": 1.9997513239457138e-05,
862
+ "loss": 1.6759,
863
+ "step": 24400
864
+ },
865
+ {
866
+ "epoch": 0.01710886593951668,
867
+ "grad_norm": 3.8766541481018066,
868
+ "learning_rate": 1.999747230827846e-05,
869
+ "loss": 1.6885,
870
+ "step": 24600
871
+ },
872
+ {
873
+ "epoch": 0.017247962410569664,
874
+ "grad_norm": 1.8397940397262573,
875
+ "learning_rate": 1.999743104304849e-05,
876
+ "loss": 1.6495,
877
+ "step": 24800
878
+ },
879
+ {
880
+ "epoch": 0.017387058881622643,
881
+ "grad_norm": 2.1748106479644775,
882
+ "learning_rate": 1.9997389443769183e-05,
883
+ "loss": 1.7696,
884
+ "step": 25000
885
+ },
886
+ {
887
+ "epoch": 0.017526155352675626,
888
+ "grad_norm": 2.0195181369781494,
889
+ "learning_rate": 1.9997347510442536e-05,
890
+ "loss": 1.681,
891
+ "step": 25200
892
+ },
893
+ {
894
+ "epoch": 0.017665251823728606,
895
+ "grad_norm": 2.446232557296753,
896
+ "learning_rate": 1.9997305243070547e-05,
897
+ "loss": 1.6504,
898
+ "step": 25400
899
+ },
900
+ {
901
+ "epoch": 0.017804348294781586,
902
+ "grad_norm": 1.763822317123413,
903
+ "learning_rate": 1.999726264165524e-05,
904
+ "loss": 1.7779,
905
+ "step": 25600
906
+ },
907
+ {
908
+ "epoch": 0.01794344476583457,
909
+ "grad_norm": 4.14453125,
910
+ "learning_rate": 1.9997219706198637e-05,
911
+ "loss": 1.7237,
912
+ "step": 25800
913
+ },
914
+ {
915
+ "epoch": 0.01808254123688755,
916
+ "grad_norm": 2.8632140159606934,
917
+ "learning_rate": 1.9997176436702798e-05,
918
+ "loss": 1.7078,
919
+ "step": 26000
920
+ },
921
+ {
922
+ "epoch": 0.01822163770794053,
923
+ "grad_norm": 2.8407750129699707,
924
+ "learning_rate": 1.9997132833169782e-05,
925
+ "loss": 1.7034,
926
+ "step": 26200
927
+ },
928
+ {
929
+ "epoch": 0.01836073417899351,
930
+ "grad_norm": 2.290100574493408,
931
+ "learning_rate": 1.999708889560168e-05,
932
+ "loss": 1.6465,
933
+ "step": 26400
934
+ },
935
+ {
936
+ "epoch": 0.018499830650046494,
937
+ "grad_norm": 2.3949410915374756,
938
+ "learning_rate": 1.999704462400058e-05,
939
+ "loss": 1.6693,
940
+ "step": 26600
941
+ },
942
+ {
943
+ "epoch": 0.018638927121099474,
944
+ "grad_norm": 1.8822963237762451,
945
+ "learning_rate": 1.9997000018368592e-05,
946
+ "loss": 1.6824,
947
+ "step": 26800
948
+ },
949
+ {
950
+ "epoch": 0.018778023592152457,
951
+ "grad_norm": 2.2643373012542725,
952
+ "learning_rate": 1.9996955078707855e-05,
953
+ "loss": 1.6599,
954
+ "step": 27000
955
+ },
956
+ {
957
+ "epoch": 0.018917120063205436,
958
+ "grad_norm": 2.3489792346954346,
959
+ "learning_rate": 1.9996909805020516e-05,
960
+ "loss": 1.7212,
961
+ "step": 27200
962
+ },
963
+ {
964
+ "epoch": 0.019056216534258416,
965
+ "grad_norm": 2.2388651371002197,
966
+ "learning_rate": 1.999686419730873e-05,
967
+ "loss": 1.6677,
968
+ "step": 27400
969
+ },
970
+ {
971
+ "epoch": 0.0191953130053114,
972
+ "grad_norm": 2.217224597930908,
973
+ "learning_rate": 1.9996818255574672e-05,
974
+ "loss": 1.6785,
975
+ "step": 27600
976
+ },
977
+ {
978
+ "epoch": 0.01933440947636438,
979
+ "grad_norm": 4.4212212562561035,
980
+ "learning_rate": 1.9996771979820543e-05,
981
+ "loss": 1.6515,
982
+ "step": 27800
983
+ },
984
+ {
985
+ "epoch": 0.019473505947417362,
986
+ "grad_norm": 2.4725615978240967,
987
+ "learning_rate": 1.9996725370048545e-05,
988
+ "loss": 1.66,
989
+ "step": 28000
990
+ },
991
+ {
992
+ "epoch": 0.01961260241847034,
993
+ "grad_norm": 2.4805498123168945,
994
+ "learning_rate": 1.9996678426260905e-05,
995
+ "loss": 1.6954,
996
+ "step": 28200
997
+ },
998
+ {
999
+ "epoch": 0.019751698889523325,
1000
+ "grad_norm": 1.793663501739502,
1001
+ "learning_rate": 1.999663114845987e-05,
1002
+ "loss": 1.6956,
1003
+ "step": 28400
1004
+ },
1005
+ {
1006
+ "epoch": 0.019890795360576304,
1007
+ "grad_norm": 2.178234100341797,
1008
+ "learning_rate": 1.999658353664769e-05,
1009
+ "loss": 1.6676,
1010
+ "step": 28600
1011
+ },
1012
+ {
1013
+ "epoch": 0.020029891831629287,
1014
+ "grad_norm": 2.034973382949829,
1015
+ "learning_rate": 1.999653559082664e-05,
1016
+ "loss": 1.6977,
1017
+ "step": 28800
1018
+ },
1019
+ {
1020
+ "epoch": 0.020168988302682267,
1021
+ "grad_norm": 3.669325828552246,
1022
+ "learning_rate": 1.9996487310999007e-05,
1023
+ "loss": 1.685,
1024
+ "step": 29000
1025
+ },
1026
+ {
1027
+ "epoch": 0.020308084773735247,
1028
+ "grad_norm": 2.070687770843506,
1029
+ "learning_rate": 1.99964386971671e-05,
1030
+ "loss": 1.7383,
1031
+ "step": 29200
1032
+ },
1033
+ {
1034
+ "epoch": 0.02044718124478823,
1035
+ "grad_norm": 1.6653083562850952,
1036
+ "learning_rate": 1.999638974933324e-05,
1037
+ "loss": 1.7003,
1038
+ "step": 29400
1039
+ },
1040
+ {
1041
+ "epoch": 0.02058627771584121,
1042
+ "grad_norm": 2.3347225189208984,
1043
+ "learning_rate": 1.999634046749976e-05,
1044
+ "loss": 1.7457,
1045
+ "step": 29600
1046
+ },
1047
+ {
1048
+ "epoch": 0.020725374186894192,
1049
+ "grad_norm": 1.8311301469802856,
1050
+ "learning_rate": 1.9996290851669012e-05,
1051
+ "loss": 1.6243,
1052
+ "step": 29800
1053
+ },
1054
+ {
1055
+ "epoch": 0.020864470657947172,
1056
+ "grad_norm": 4.241110324859619,
1057
+ "learning_rate": 1.9996240901843368e-05,
1058
+ "loss": 1.7011,
1059
+ "step": 30000
1060
+ },
1061
+ {
1062
+ "epoch": 0.021003567129000155,
1063
+ "grad_norm": 3.895310878753662,
1064
+ "learning_rate": 1.9996190618025216e-05,
1065
+ "loss": 1.713,
1066
+ "step": 30200
1067
+ },
1068
+ {
1069
+ "epoch": 0.021142663600053135,
1070
+ "grad_norm": 2.71415638923645,
1071
+ "learning_rate": 1.9996140000216945e-05,
1072
+ "loss": 1.7247,
1073
+ "step": 30400
1074
+ },
1075
+ {
1076
+ "epoch": 0.021281760071106114,
1077
+ "grad_norm": 2.7343320846557617,
1078
+ "learning_rate": 1.9996089048420977e-05,
1079
+ "loss": 1.7241,
1080
+ "step": 30600
1081
+ },
1082
+ {
1083
+ "epoch": 0.021420856542159097,
1084
+ "grad_norm": 1.6846824884414673,
1085
+ "learning_rate": 1.9996037762639752e-05,
1086
+ "loss": 1.7244,
1087
+ "step": 30800
1088
+ },
1089
+ {
1090
+ "epoch": 0.021559953013212077,
1091
+ "grad_norm": 4.142380237579346,
1092
+ "learning_rate": 1.999598614287571e-05,
1093
+ "loss": 1.73,
1094
+ "step": 31000
1095
+ },
1096
+ {
1097
+ "epoch": 0.02169904948426506,
1098
+ "grad_norm": 2.5720510482788086,
1099
+ "learning_rate": 1.9995934189131313e-05,
1100
+ "loss": 1.6542,
1101
+ "step": 31200
1102
+ },
1103
+ {
1104
+ "epoch": 0.02183814595531804,
1105
+ "grad_norm": 4.803544044494629,
1106
+ "learning_rate": 1.999588190140905e-05,
1107
+ "loss": 1.6693,
1108
+ "step": 31400
1109
+ },
1110
+ {
1111
+ "epoch": 0.021977242426371023,
1112
+ "grad_norm": 1.6169124841690063,
1113
+ "learning_rate": 1.9995829279711406e-05,
1114
+ "loss": 1.7223,
1115
+ "step": 31600
1116
+ },
1117
+ {
1118
+ "epoch": 0.022116338897424002,
1119
+ "grad_norm": 2.43363618850708,
1120
+ "learning_rate": 1.999577632404091e-05,
1121
+ "loss": 1.7493,
1122
+ "step": 31800
1123
+ },
1124
+ {
1125
+ "epoch": 0.022255435368476986,
1126
+ "grad_norm": 1.6128485202789307,
1127
+ "learning_rate": 1.9995723034400073e-05,
1128
+ "loss": 1.6658,
1129
+ "step": 32000
1130
+ },
1131
+ {
1132
+ "epoch": 0.022394531839529965,
1133
+ "grad_norm": 2.0989410877227783,
1134
+ "learning_rate": 1.9995669410791448e-05,
1135
+ "loss": 1.6943,
1136
+ "step": 32200
1137
+ },
1138
+ {
1139
+ "epoch": 0.022533628310582945,
1140
+ "grad_norm": 1.8325483798980713,
1141
+ "learning_rate": 1.999561545321759e-05,
1142
+ "loss": 1.6779,
1143
+ "step": 32400
1144
+ },
1145
+ {
1146
+ "epoch": 0.022672724781635928,
1147
+ "grad_norm": 2.0416502952575684,
1148
+ "learning_rate": 1.999556116168108e-05,
1149
+ "loss": 1.6609,
1150
+ "step": 32600
1151
+ },
1152
+ {
1153
+ "epoch": 0.022811821252688907,
1154
+ "grad_norm": 1.8695884943008423,
1155
+ "learning_rate": 1.9995506536184505e-05,
1156
+ "loss": 1.7289,
1157
+ "step": 32800
1158
+ },
1159
+ {
1160
+ "epoch": 0.02295091772374189,
1161
+ "grad_norm": 1.682106614112854,
1162
+ "learning_rate": 1.999545157673047e-05,
1163
+ "loss": 1.6637,
1164
+ "step": 33000
1165
+ },
1166
+ {
1167
+ "epoch": 0.02309001419479487,
1168
+ "grad_norm": 2.3423938751220703,
1169
+ "learning_rate": 1.9995396283321612e-05,
1170
+ "loss": 1.7022,
1171
+ "step": 33200
1172
+ },
1173
+ {
1174
+ "epoch": 0.023229110665847853,
1175
+ "grad_norm": 2.1338844299316406,
1176
+ "learning_rate": 1.999534065596056e-05,
1177
+ "loss": 1.6286,
1178
+ "step": 33400
1179
+ },
1180
+ {
1181
+ "epoch": 0.023368207136900833,
1182
+ "grad_norm": 1.8180948495864868,
1183
+ "learning_rate": 1.999528469464997e-05,
1184
+ "loss": 1.6822,
1185
+ "step": 33600
1186
+ },
1187
+ {
1188
+ "epoch": 0.023507303607953816,
1189
+ "grad_norm": 4.408015727996826,
1190
+ "learning_rate": 1.999522839939252e-05,
1191
+ "loss": 1.6647,
1192
+ "step": 33800
1193
+ },
1194
+ {
1195
+ "epoch": 0.023646400079006796,
1196
+ "grad_norm": 1.913683533668518,
1197
+ "learning_rate": 1.999517177019089e-05,
1198
+ "loss": 1.662,
1199
+ "step": 34000
1200
+ },
1201
+ {
1202
+ "epoch": 0.023785496550059775,
1203
+ "grad_norm": 2.642828941345215,
1204
+ "learning_rate": 1.9995114807047784e-05,
1205
+ "loss": 1.6511,
1206
+ "step": 34200
1207
+ },
1208
+ {
1209
+ "epoch": 0.02392459302111276,
1210
+ "grad_norm": 2.2986598014831543,
1211
+ "learning_rate": 1.9995057509965927e-05,
1212
+ "loss": 1.627,
1213
+ "step": 34400
1214
+ },
1215
+ {
1216
+ "epoch": 0.024063689492165738,
1217
+ "grad_norm": 1.6629712581634521,
1218
+ "learning_rate": 1.999499987894805e-05,
1219
+ "loss": 1.6492,
1220
+ "step": 34600
1221
+ },
1222
+ {
1223
+ "epoch": 0.02420278596321872,
1224
+ "grad_norm": 3.302642583847046,
1225
+ "learning_rate": 1.9994941913996905e-05,
1226
+ "loss": 1.7311,
1227
+ "step": 34800
1228
+ },
1229
+ {
1230
+ "epoch": 0.0243418824342717,
1231
+ "grad_norm": 2.2457594871520996,
1232
+ "learning_rate": 1.9994883615115256e-05,
1233
+ "loss": 1.7053,
1234
+ "step": 35000
1235
+ },
1236
+ {
1237
+ "epoch": 0.024480978905324684,
1238
+ "grad_norm": 3.1490752696990967,
1239
+ "learning_rate": 1.9994824982305894e-05,
1240
+ "loss": 1.7145,
1241
+ "step": 35200
1242
+ },
1243
+ {
1244
+ "epoch": 0.024620075376377663,
1245
+ "grad_norm": 2.5022294521331787,
1246
+ "learning_rate": 1.9994766015571617e-05,
1247
+ "loss": 1.6747,
1248
+ "step": 35400
1249
+ },
1250
+ {
1251
+ "epoch": 0.024759171847430646,
1252
+ "grad_norm": 2.0420994758605957,
1253
+ "learning_rate": 1.999470671491523e-05,
1254
+ "loss": 1.6354,
1255
+ "step": 35600
1256
+ },
1257
+ {
1258
+ "epoch": 0.024898268318483626,
1259
+ "grad_norm": 2.904489278793335,
1260
+ "learning_rate": 1.9994647080339576e-05,
1261
+ "loss": 1.6739,
1262
+ "step": 35800
1263
+ },
1264
+ {
1265
+ "epoch": 0.025037364789536606,
1266
+ "grad_norm": 3.5906155109405518,
1267
+ "learning_rate": 1.9994587111847493e-05,
1268
+ "loss": 1.6882,
1269
+ "step": 36000
1270
+ },
1271
+ {
1272
+ "epoch": 0.02517646126058959,
1273
+ "grad_norm": 2.0279171466827393,
1274
+ "learning_rate": 1.9994526809441846e-05,
1275
+ "loss": 1.6274,
1276
+ "step": 36200
1277
+ },
1278
+ {
1279
+ "epoch": 0.02531555773164257,
1280
+ "grad_norm": 1.3273375034332275,
1281
+ "learning_rate": 1.999446617312551e-05,
1282
+ "loss": 1.6795,
1283
+ "step": 36400
1284
+ },
1285
+ {
1286
+ "epoch": 0.02545465420269555,
1287
+ "grad_norm": 3.7897446155548096,
1288
+ "learning_rate": 1.9994405202901396e-05,
1289
+ "loss": 1.6904,
1290
+ "step": 36600
1291
+ },
1292
+ {
1293
+ "epoch": 0.02559375067374853,
1294
+ "grad_norm": 2.1297788619995117,
1295
+ "learning_rate": 1.99943438987724e-05,
1296
+ "loss": 1.7057,
1297
+ "step": 36800
1298
+ },
1299
+ {
1300
+ "epoch": 0.025732847144801514,
1301
+ "grad_norm": 2.5796139240264893,
1302
+ "learning_rate": 1.9994282260741447e-05,
1303
+ "loss": 1.6695,
1304
+ "step": 37000
1305
+ },
1306
+ {
1307
+ "epoch": 0.025871943615854494,
1308
+ "grad_norm": 3.6038098335266113,
1309
+ "learning_rate": 1.9994220288811493e-05,
1310
+ "loss": 1.6608,
1311
+ "step": 37200
1312
+ },
1313
+ {
1314
+ "epoch": 0.026011040086907473,
1315
+ "grad_norm": 2.2663841247558594,
1316
+ "learning_rate": 1.9994157982985484e-05,
1317
+ "loss": 1.6834,
1318
+ "step": 37400
1319
+ },
1320
+ {
1321
+ "epoch": 0.026150136557960457,
1322
+ "grad_norm": 2.462709426879883,
1323
+ "learning_rate": 1.9994095343266396e-05,
1324
+ "loss": 1.6946,
1325
+ "step": 37600
1326
+ },
1327
+ {
1328
+ "epoch": 0.026289233029013436,
1329
+ "grad_norm": 2.082554817199707,
1330
+ "learning_rate": 1.9994032369657223e-05,
1331
+ "loss": 1.6931,
1332
+ "step": 37800
1333
+ },
1334
+ {
1335
+ "epoch": 0.02642832950006642,
1336
+ "grad_norm": 3.0539119243621826,
1337
+ "learning_rate": 1.999396906216097e-05,
1338
+ "loss": 1.6796,
1339
+ "step": 38000
1340
+ },
1341
+ {
1342
+ "epoch": 0.0265674259711194,
1343
+ "grad_norm": 2.478039026260376,
1344
+ "learning_rate": 1.9993905420780658e-05,
1345
+ "loss": 1.7081,
1346
+ "step": 38200
1347
+ },
1348
+ {
1349
+ "epoch": 0.026706522442172382,
1350
+ "grad_norm": 5.309814453125,
1351
+ "learning_rate": 1.9993841445519327e-05,
1352
+ "loss": 1.7076,
1353
+ "step": 38400
1354
+ },
1355
+ {
1356
+ "epoch": 0.02684561891322536,
1357
+ "grad_norm": 2.58223032951355,
1358
+ "learning_rate": 1.999377713638003e-05,
1359
+ "loss": 1.7193,
1360
+ "step": 38600
1361
+ },
1362
+ {
1363
+ "epoch": 0.026984715384278345,
1364
+ "grad_norm": 4.54454231262207,
1365
+ "learning_rate": 1.999371249336584e-05,
1366
+ "loss": 1.7087,
1367
+ "step": 38800
1368
+ },
1369
+ {
1370
+ "epoch": 0.027123811855331324,
1371
+ "grad_norm": 6.4016876220703125,
1372
+ "learning_rate": 1.999364751647984e-05,
1373
+ "loss": 1.6778,
1374
+ "step": 39000
1375
+ },
1376
+ {
1377
+ "epoch": 0.027262908326384304,
1378
+ "grad_norm": 2.3655877113342285,
1379
+ "learning_rate": 1.999358220572513e-05,
1380
+ "loss": 1.6927,
1381
+ "step": 39200
1382
+ },
1383
+ {
1384
+ "epoch": 0.027402004797437287,
1385
+ "grad_norm": 3.2086055278778076,
1386
+ "learning_rate": 1.9993516561104834e-05,
1387
+ "loss": 1.6915,
1388
+ "step": 39400
1389
+ },
1390
+ {
1391
+ "epoch": 0.027541101268490267,
1392
+ "grad_norm": 4.550060749053955,
1393
+ "learning_rate": 1.999345058262208e-05,
1394
+ "loss": 1.6706,
1395
+ "step": 39600
1396
+ },
1397
+ {
1398
+ "epoch": 0.02768019773954325,
1399
+ "grad_norm": 5.274898529052734,
1400
+ "learning_rate": 1.999338427028002e-05,
1401
+ "loss": 1.6722,
1402
+ "step": 39800
1403
+ },
1404
+ {
1405
+ "epoch": 0.02781929421059623,
1406
+ "grad_norm": 4.817627429962158,
1407
+ "learning_rate": 1.9993317624081818e-05,
1408
+ "loss": 1.6831,
1409
+ "step": 40000
1410
+ },
1411
+ {
1412
+ "epoch": 0.027958390681649212,
1413
+ "grad_norm": 3.387507200241089,
1414
+ "learning_rate": 1.999325064403066e-05,
1415
+ "loss": 1.6987,
1416
+ "step": 40200
1417
+ },
1418
+ {
1419
+ "epoch": 0.028097487152702192,
1420
+ "grad_norm": 5.216610431671143,
1421
+ "learning_rate": 1.999318333012974e-05,
1422
+ "loss": 1.732,
1423
+ "step": 40400
1424
+ },
1425
+ {
1426
+ "epoch": 0.028236583623755175,
1427
+ "grad_norm": 3.5860650539398193,
1428
+ "learning_rate": 1.9993115682382273e-05,
1429
+ "loss": 1.626,
1430
+ "step": 40600
1431
+ },
1432
+ {
1433
+ "epoch": 0.028375680094808155,
1434
+ "grad_norm": 3.4120900630950928,
1435
+ "learning_rate": 1.9993047700791484e-05,
1436
+ "loss": 1.6541,
1437
+ "step": 40800
1438
+ },
1439
+ {
1440
+ "epoch": 0.028514776565861134,
1441
+ "grad_norm": 2.7464821338653564,
1442
+ "learning_rate": 1.9992979385360627e-05,
1443
+ "loss": 1.6558,
1444
+ "step": 41000
1445
+ },
1446
+ {
1447
+ "epoch": 0.028653873036914117,
1448
+ "grad_norm": 2.974565267562866,
1449
+ "learning_rate": 1.9992910736092956e-05,
1450
+ "loss": 1.7827,
1451
+ "step": 41200
1452
+ },
1453
+ {
1454
+ "epoch": 0.028792969507967097,
1455
+ "grad_norm": 1.62872314453125,
1456
+ "learning_rate": 1.9992841752991746e-05,
1457
+ "loss": 1.6925,
1458
+ "step": 41400
1459
+ },
1460
+ {
1461
+ "epoch": 0.02893206597902008,
1462
+ "grad_norm": 2.0491859912872314,
1463
+ "learning_rate": 1.9992772436060303e-05,
1464
+ "loss": 1.6699,
1465
+ "step": 41600
1466
+ },
1467
+ {
1468
+ "epoch": 0.02907116245007306,
1469
+ "grad_norm": 4.282040596008301,
1470
+ "learning_rate": 1.999270278530192e-05,
1471
+ "loss": 1.6866,
1472
+ "step": 41800
1473
+ },
1474
+ {
1475
+ "epoch": 0.029210258921126043,
1476
+ "grad_norm": 1.5519753694534302,
1477
+ "learning_rate": 1.9992632800719933e-05,
1478
+ "loss": 1.734,
1479
+ "step": 42000
1480
+ },
1481
+ {
1482
+ "epoch": 0.029349355392179022,
1483
+ "grad_norm": 2.028379201889038,
1484
+ "learning_rate": 1.9992562482317682e-05,
1485
+ "loss": 1.6825,
1486
+ "step": 42200
1487
+ },
1488
+ {
1489
+ "epoch": 0.029488451863232006,
1490
+ "grad_norm": 2.8444042205810547,
1491
+ "learning_rate": 1.999249183009852e-05,
1492
+ "loss": 1.671,
1493
+ "step": 42400
1494
+ },
1495
+ {
1496
+ "epoch": 0.029627548334284985,
1497
+ "grad_norm": 2.0103445053100586,
1498
+ "learning_rate": 1.999242084406582e-05,
1499
+ "loss": 1.707,
1500
+ "step": 42600
1501
+ },
1502
+ {
1503
+ "epoch": 0.029766644805337965,
1504
+ "grad_norm": 1.7135134935379028,
1505
+ "learning_rate": 1.9992349524222974e-05,
1506
+ "loss": 1.6703,
1507
+ "step": 42800
1508
+ },
1509
+ {
1510
+ "epoch": 0.029905741276390948,
1511
+ "grad_norm": 6.601833343505859,
1512
+ "learning_rate": 1.9992277870573384e-05,
1513
+ "loss": 1.7094,
1514
+ "step": 43000
1515
+ },
1516
+ {
1517
+ "epoch": 0.030044837747443928,
1518
+ "grad_norm": 3.613133430480957,
1519
+ "learning_rate": 1.9992205883120476e-05,
1520
+ "loss": 1.66,
1521
+ "step": 43200
1522
+ },
1523
+ {
1524
+ "epoch": 0.03018393421849691,
1525
+ "grad_norm": 3.0776429176330566,
1526
+ "learning_rate": 1.999213356186768e-05,
1527
+ "loss": 1.7313,
1528
+ "step": 43400
1529
+ },
1530
+ {
1531
+ "epoch": 0.03032303068954989,
1532
+ "grad_norm": 4.370647430419922,
1533
+ "learning_rate": 1.999206090681845e-05,
1534
+ "loss": 1.6906,
1535
+ "step": 43600
1536
+ },
1537
+ {
1538
+ "epoch": 0.030462127160602873,
1539
+ "grad_norm": 3.666454315185547,
1540
+ "learning_rate": 1.999198791797625e-05,
1541
+ "loss": 1.6623,
1542
+ "step": 43800
1543
+ },
1544
+ {
1545
+ "epoch": 0.030601223631655853,
1546
+ "grad_norm": 5.570009231567383,
1547
+ "learning_rate": 1.999191459534458e-05,
1548
+ "loss": 1.6862,
1549
+ "step": 44000
1550
+ },
1551
+ {
1552
+ "epoch": 0.030740320102708833,
1553
+ "grad_norm": 8.811431884765625,
1554
+ "learning_rate": 1.9991840938926925e-05,
1555
+ "loss": 1.6893,
1556
+ "step": 44200
1557
+ },
1558
+ {
1559
+ "epoch": 0.030879416573761816,
1560
+ "grad_norm": 4.8162617683410645,
1561
+ "learning_rate": 1.999176694872681e-05,
1562
+ "loss": 1.687,
1563
+ "step": 44400
1564
+ },
1565
+ {
1566
+ "epoch": 0.031018513044814795,
1567
+ "grad_norm": 2.9438042640686035,
1568
+ "learning_rate": 1.9991692624747756e-05,
1569
+ "loss": 1.714,
1570
+ "step": 44600
1571
+ },
1572
+ {
1573
+ "epoch": 0.03115760951586778,
1574
+ "grad_norm": 5.454644680023193,
1575
+ "learning_rate": 1.9991617966993324e-05,
1576
+ "loss": 1.6707,
1577
+ "step": 44800
1578
+ },
1579
+ {
1580
+ "epoch": 0.03129670598692076,
1581
+ "grad_norm": 5.090953826904297,
1582
+ "learning_rate": 1.9991542975467074e-05,
1583
+ "loss": 1.6852,
1584
+ "step": 45000
1585
+ },
1586
+ {
1587
+ "epoch": 0.03143580245797374,
1588
+ "grad_norm": 4.892083168029785,
1589
+ "learning_rate": 1.9991467650172576e-05,
1590
+ "loss": 1.636,
1591
+ "step": 45200
1592
+ },
1593
+ {
1594
+ "epoch": 0.03157489892902672,
1595
+ "grad_norm": 5.967046737670898,
1596
+ "learning_rate": 1.9991391991113443e-05,
1597
+ "loss": 1.7314,
1598
+ "step": 45400
1599
+ },
1600
+ {
1601
+ "epoch": 0.0317139954000797,
1602
+ "grad_norm": 4.124074935913086,
1603
+ "learning_rate": 1.999131599829328e-05,
1604
+ "loss": 1.7064,
1605
+ "step": 45600
1606
+ },
1607
+ {
1608
+ "epoch": 0.03185309187113269,
1609
+ "grad_norm": 2.1032886505126953,
1610
+ "learning_rate": 1.999123967171571e-05,
1611
+ "loss": 1.6755,
1612
+ "step": 45800
1613
+ },
1614
+ {
1615
+ "epoch": 0.031992188342185666,
1616
+ "grad_norm": 2.694011688232422,
1617
+ "learning_rate": 1.9991163011384382e-05,
1618
+ "loss": 1.6889,
1619
+ "step": 46000
1620
+ },
1621
+ {
1622
+ "epoch": 0.032131284813238646,
1623
+ "grad_norm": 3.628530263900757,
1624
+ "learning_rate": 1.9991086017302953e-05,
1625
+ "loss": 1.6233,
1626
+ "step": 46200
1627
+ },
1628
+ {
1629
+ "epoch": 0.032270381284291626,
1630
+ "grad_norm": 3.5236215591430664,
1631
+ "learning_rate": 1.99910086894751e-05,
1632
+ "loss": 1.7024,
1633
+ "step": 46400
1634
+ },
1635
+ {
1636
+ "epoch": 0.032409477755344605,
1637
+ "grad_norm": 3.225529432296753,
1638
+ "learning_rate": 1.999093102790451e-05,
1639
+ "loss": 1.6857,
1640
+ "step": 46600
1641
+ },
1642
+ {
1643
+ "epoch": 0.03254857422639759,
1644
+ "grad_norm": 3.014922618865967,
1645
+ "learning_rate": 1.9990853032594902e-05,
1646
+ "loss": 1.6712,
1647
+ "step": 46800
1648
+ },
1649
+ {
1650
+ "epoch": 0.03268767069745057,
1651
+ "grad_norm": 3.654637336730957,
1652
+ "learning_rate": 1.9990774703549988e-05,
1653
+ "loss": 1.7464,
1654
+ "step": 47000
1655
+ },
1656
+ {
1657
+ "epoch": 0.03282676716850355,
1658
+ "grad_norm": 3.2240869998931885,
1659
+ "learning_rate": 1.999069604077351e-05,
1660
+ "loss": 1.6179,
1661
+ "step": 47200
1662
+ },
1663
+ {
1664
+ "epoch": 0.03296586363955653,
1665
+ "grad_norm": 2.993143081665039,
1666
+ "learning_rate": 1.9990617044269226e-05,
1667
+ "loss": 1.6679,
1668
+ "step": 47400
1669
+ },
1670
+ {
1671
+ "epoch": 0.03310496011060951,
1672
+ "grad_norm": 5.778799057006836,
1673
+ "learning_rate": 1.9990537714040906e-05,
1674
+ "loss": 1.6547,
1675
+ "step": 47600
1676
+ },
1677
+ {
1678
+ "epoch": 0.0332440565816625,
1679
+ "grad_norm": 2.6785480976104736,
1680
+ "learning_rate": 1.9990458050092335e-05,
1681
+ "loss": 1.6496,
1682
+ "step": 47800
1683
+ },
1684
+ {
1685
+ "epoch": 0.03338315305271548,
1686
+ "grad_norm": 6.086597442626953,
1687
+ "learning_rate": 1.999037805242732e-05,
1688
+ "loss": 1.6859,
1689
+ "step": 48000
1690
+ },
1691
+ {
1692
+ "epoch": 0.033522249523768456,
1693
+ "grad_norm": 2.1356918811798096,
1694
+ "learning_rate": 1.9990297721049674e-05,
1695
+ "loss": 1.6864,
1696
+ "step": 48200
1697
+ },
1698
+ {
1699
+ "epoch": 0.033661345994821436,
1700
+ "grad_norm": 5.611029624938965,
1701
+ "learning_rate": 1.999021705596324e-05,
1702
+ "loss": 1.6508,
1703
+ "step": 48400
1704
+ },
1705
+ {
1706
+ "epoch": 0.03380044246587442,
1707
+ "grad_norm": 2.953913927078247,
1708
+ "learning_rate": 1.9990136057171866e-05,
1709
+ "loss": 1.6805,
1710
+ "step": 48600
1711
+ },
1712
+ {
1713
+ "epoch": 0.0339395389369274,
1714
+ "grad_norm": 4.642039775848389,
1715
+ "learning_rate": 1.9990054724679412e-05,
1716
+ "loss": 1.6394,
1717
+ "step": 48800
1718
+ },
1719
+ {
1720
+ "epoch": 0.03407863540798038,
1721
+ "grad_norm": 4.601811408996582,
1722
+ "learning_rate": 1.9989973058489766e-05,
1723
+ "loss": 1.6854,
1724
+ "step": 49000
1725
+ },
1726
+ {
1727
+ "epoch": 0.03421773187903336,
1728
+ "grad_norm": 6.185051441192627,
1729
+ "learning_rate": 1.9989891058606835e-05,
1730
+ "loss": 1.7445,
1731
+ "step": 49200
1732
+ },
1733
+ {
1734
+ "epoch": 0.03435682835008634,
1735
+ "grad_norm": 6.0281877517700195,
1736
+ "learning_rate": 1.998980872503452e-05,
1737
+ "loss": 1.6916,
1738
+ "step": 49400
1739
+ },
1740
+ {
1741
+ "epoch": 0.03449592482113933,
1742
+ "grad_norm": 2.0409023761749268,
1743
+ "learning_rate": 1.9989726057776755e-05,
1744
+ "loss": 1.6718,
1745
+ "step": 49600
1746
+ },
1747
+ {
1748
+ "epoch": 0.03463502129219231,
1749
+ "grad_norm": 6.715494155883789,
1750
+ "learning_rate": 1.998964305683749e-05,
1751
+ "loss": 1.6913,
1752
+ "step": 49800
1753
+ },
1754
+ {
1755
+ "epoch": 0.03477411776324529,
1756
+ "grad_norm": 5.204497337341309,
1757
+ "learning_rate": 1.9989559722220688e-05,
1758
+ "loss": 1.7206,
1759
+ "step": 50000
1760
+ },
1761
+ {
1762
+ "epoch": 0.034913214234298266,
1763
+ "grad_norm": 4.236083984375,
1764
+ "learning_rate": 1.998947605393032e-05,
1765
+ "loss": 1.6304,
1766
+ "step": 50200
1767
+ },
1768
+ {
1769
+ "epoch": 0.03505231070535125,
1770
+ "grad_norm": 4.496490955352783,
1771
+ "learning_rate": 1.998939205197039e-05,
1772
+ "loss": 1.6468,
1773
+ "step": 50400
1774
+ },
1775
+ {
1776
+ "epoch": 0.03519140717640423,
1777
+ "grad_norm": 4.949439525604248,
1778
+ "learning_rate": 1.9989307716344902e-05,
1779
+ "loss": 1.6992,
1780
+ "step": 50600
1781
+ },
1782
+ {
1783
+ "epoch": 0.03533050364745721,
1784
+ "grad_norm": 4.516083240509033,
1785
+ "learning_rate": 1.9989223047057886e-05,
1786
+ "loss": 1.6655,
1787
+ "step": 50800
1788
+ },
1789
+ {
1790
+ "epoch": 0.03546960011851019,
1791
+ "grad_norm": 3.174182176589966,
1792
+ "learning_rate": 1.998913804411338e-05,
1793
+ "loss": 1.7408,
1794
+ "step": 51000
1795
+ },
1796
+ {
1797
+ "epoch": 0.03560869658956317,
1798
+ "grad_norm": 3.5125887393951416,
1799
+ "learning_rate": 1.998905270751544e-05,
1800
+ "loss": 1.6859,
1801
+ "step": 51200
1802
+ },
1803
+ {
1804
+ "epoch": 0.03574779306061616,
1805
+ "grad_norm": 3.4447836875915527,
1806
+ "learning_rate": 1.998896703726815e-05,
1807
+ "loss": 1.7248,
1808
+ "step": 51400
1809
+ },
1810
+ {
1811
+ "epoch": 0.03588688953166914,
1812
+ "grad_norm": 6.76048469543457,
1813
+ "learning_rate": 1.998888103337559e-05,
1814
+ "loss": 1.7037,
1815
+ "step": 51600
1816
+ },
1817
+ {
1818
+ "epoch": 0.03602598600272212,
1819
+ "grad_norm": 5.462390422821045,
1820
+ "learning_rate": 1.998879469584187e-05,
1821
+ "loss": 1.6771,
1822
+ "step": 51800
1823
+ },
1824
+ {
1825
+ "epoch": 0.0361650824737751,
1826
+ "grad_norm": 4.145532131195068,
1827
+ "learning_rate": 1.9988708024671108e-05,
1828
+ "loss": 1.6732,
1829
+ "step": 52000
1830
+ },
1831
+ {
1832
+ "epoch": 0.03630417894482808,
1833
+ "grad_norm": 2.3257813453674316,
1834
+ "learning_rate": 1.9988621019867444e-05,
1835
+ "loss": 1.68,
1836
+ "step": 52200
1837
+ },
1838
+ {
1839
+ "epoch": 0.03644327541588106,
1840
+ "grad_norm": 2.8310391902923584,
1841
+ "learning_rate": 1.9988533681435035e-05,
1842
+ "loss": 1.7028,
1843
+ "step": 52400
1844
+ },
1845
+ {
1846
+ "epoch": 0.03658237188693404,
1847
+ "grad_norm": 3.2486252784729004,
1848
+ "learning_rate": 1.9988446009378043e-05,
1849
+ "loss": 1.7134,
1850
+ "step": 52600
1851
+ },
1852
+ {
1853
+ "epoch": 0.03672146835798702,
1854
+ "grad_norm": 4.35382604598999,
1855
+ "learning_rate": 1.998835800370066e-05,
1856
+ "loss": 1.6279,
1857
+ "step": 52800
1858
+ },
1859
+ {
1860
+ "epoch": 0.03686056482904,
1861
+ "grad_norm": 4.6429243087768555,
1862
+ "learning_rate": 1.9988269664407082e-05,
1863
+ "loss": 1.7032,
1864
+ "step": 53000
1865
+ },
1866
+ {
1867
+ "epoch": 0.03699966130009299,
1868
+ "grad_norm": 7.826554775238037,
1869
+ "learning_rate": 1.998818099150153e-05,
1870
+ "loss": 1.7485,
1871
+ "step": 53200
1872
+ },
1873
+ {
1874
+ "epoch": 0.03713875777114597,
1875
+ "grad_norm": 3.7032411098480225,
1876
+ "learning_rate": 1.998809198498824e-05,
1877
+ "loss": 1.6475,
1878
+ "step": 53400
1879
+ },
1880
+ {
1881
+ "epoch": 0.03727785424219895,
1882
+ "grad_norm": 4.902835369110107,
1883
+ "learning_rate": 1.9988002644871453e-05,
1884
+ "loss": 1.6881,
1885
+ "step": 53600
1886
+ },
1887
+ {
1888
+ "epoch": 0.03741695071325193,
1889
+ "grad_norm": 4.872868061065674,
1890
+ "learning_rate": 1.9987912971155436e-05,
1891
+ "loss": 1.6455,
1892
+ "step": 53800
1893
+ },
1894
+ {
1895
+ "epoch": 0.037556047184304914,
1896
+ "grad_norm": 4.0793962478637695,
1897
+ "learning_rate": 1.998782296384448e-05,
1898
+ "loss": 1.7448,
1899
+ "step": 54000
1900
+ },
1901
+ {
1902
+ "epoch": 0.03769514365535789,
1903
+ "grad_norm": 3.5870656967163086,
1904
+ "learning_rate": 1.998773262294287e-05,
1905
+ "loss": 1.6967,
1906
+ "step": 54200
1907
+ },
1908
+ {
1909
+ "epoch": 0.03783424012641087,
1910
+ "grad_norm": 3.6290981769561768,
1911
+ "learning_rate": 1.9987641948454918e-05,
1912
+ "loss": 1.6429,
1913
+ "step": 54400
1914
+ },
1915
+ {
1916
+ "epoch": 0.03797333659746385,
1917
+ "grad_norm": 2.646336555480957,
1918
+ "learning_rate": 1.9987550940384965e-05,
1919
+ "loss": 1.6551,
1920
+ "step": 54600
1921
+ },
1922
+ {
1923
+ "epoch": 0.03811243306851683,
1924
+ "grad_norm": 3.4167566299438477,
1925
+ "learning_rate": 1.9987459598737344e-05,
1926
+ "loss": 1.6922,
1927
+ "step": 54800
1928
+ },
1929
+ {
1930
+ "epoch": 0.03825152953956982,
1931
+ "grad_norm": 3.9670467376708984,
1932
+ "learning_rate": 1.9987367923516418e-05,
1933
+ "loss": 1.6568,
1934
+ "step": 55000
1935
+ },
1936
+ {
1937
+ "epoch": 0.0383906260106228,
1938
+ "grad_norm": 4.334254741668701,
1939
+ "learning_rate": 1.998727591472657e-05,
1940
+ "loss": 1.7244,
1941
+ "step": 55200
1942
+ },
1943
+ {
1944
+ "epoch": 0.03852972248167578,
1945
+ "grad_norm": 4.030015468597412,
1946
+ "learning_rate": 1.998718357237218e-05,
1947
+ "loss": 1.6908,
1948
+ "step": 55400
1949
+ },
1950
+ {
1951
+ "epoch": 0.03866881895272876,
1952
+ "grad_norm": 2.921394109725952,
1953
+ "learning_rate": 1.998709089645767e-05,
1954
+ "loss": 1.6995,
1955
+ "step": 55600
1956
+ },
1957
+ {
1958
+ "epoch": 0.038807915423781744,
1959
+ "grad_norm": 4.17643928527832,
1960
+ "learning_rate": 1.9986997886987453e-05,
1961
+ "loss": 1.7459,
1962
+ "step": 55800
1963
+ },
1964
+ {
1965
+ "epoch": 0.038947011894834724,
1966
+ "grad_norm": 5.148770809173584,
1967
+ "learning_rate": 1.9986904543965983e-05,
1968
+ "loss": 1.6433,
1969
+ "step": 56000
1970
+ },
1971
+ {
1972
+ "epoch": 0.0390861083658877,
1973
+ "grad_norm": 3.664881467819214,
1974
+ "learning_rate": 1.9986810867397697e-05,
1975
+ "loss": 1.6391,
1976
+ "step": 56200
1977
+ },
1978
+ {
1979
+ "epoch": 0.03922520483694068,
1980
+ "grad_norm": 4.360840320587158,
1981
+ "learning_rate": 1.9986716857287084e-05,
1982
+ "loss": 1.7352,
1983
+ "step": 56400
1984
+ },
1985
+ {
1986
+ "epoch": 0.03936430130799366,
1987
+ "grad_norm": 4.004901885986328,
1988
+ "learning_rate": 1.9986622513638624e-05,
1989
+ "loss": 1.6717,
1990
+ "step": 56600
1991
+ },
1992
+ {
1993
+ "epoch": 0.03950339777904665,
1994
+ "grad_norm": 2.7370033264160156,
1995
+ "learning_rate": 1.9986527836456816e-05,
1996
+ "loss": 1.613,
1997
+ "step": 56800
1998
+ },
1999
+ {
2000
+ "epoch": 0.03964249425009963,
2001
+ "grad_norm": 4.080074787139893,
2002
+ "learning_rate": 1.9986432825746193e-05,
2003
+ "loss": 1.6511,
2004
+ "step": 57000
2005
+ },
2006
+ {
2007
+ "epoch": 0.03978159072115261,
2008
+ "grad_norm": 3.5836145877838135,
2009
+ "learning_rate": 1.998633748151128e-05,
2010
+ "loss": 1.6844,
2011
+ "step": 57200
2012
+ },
2013
+ {
2014
+ "epoch": 0.03992068719220559,
2015
+ "grad_norm": 8.140799522399902,
2016
+ "learning_rate": 1.9986241803756635e-05,
2017
+ "loss": 1.6506,
2018
+ "step": 57400
2019
+ },
2020
+ {
2021
+ "epoch": 0.040059783663258575,
2022
+ "grad_norm": 5.401699542999268,
2023
+ "learning_rate": 1.998614579248682e-05,
2024
+ "loss": 1.6886,
2025
+ "step": 57600
2026
+ },
2027
+ {
2028
+ "epoch": 0.040198880134311554,
2029
+ "grad_norm": 3.747342109680176,
2030
+ "learning_rate": 1.9986049447706426e-05,
2031
+ "loss": 1.7271,
2032
+ "step": 57800
2033
+ },
2034
+ {
2035
+ "epoch": 0.040337976605364534,
2036
+ "grad_norm": 3.5322844982147217,
2037
+ "learning_rate": 1.998595276942004e-05,
2038
+ "loss": 1.6014,
2039
+ "step": 58000
2040
+ },
2041
+ {
2042
+ "epoch": 0.040477073076417514,
2043
+ "grad_norm": 3.0417582988739014,
2044
+ "learning_rate": 1.9985855757632287e-05,
2045
+ "loss": 1.6338,
2046
+ "step": 58200
2047
+ },
2048
+ {
2049
+ "epoch": 0.04061616954747049,
2050
+ "grad_norm": 3.487562417984009,
2051
+ "learning_rate": 1.99857584123478e-05,
2052
+ "loss": 1.7305,
2053
+ "step": 58400
2054
+ },
2055
+ {
2056
+ "epoch": 0.04075526601852348,
2057
+ "grad_norm": 1.9068052768707275,
2058
+ "learning_rate": 1.9985660733571222e-05,
2059
+ "loss": 1.7155,
2060
+ "step": 58600
2061
+ },
2062
+ {
2063
+ "epoch": 0.04089436248957646,
2064
+ "grad_norm": 8.823533058166504,
2065
+ "learning_rate": 1.9985562721307213e-05,
2066
+ "loss": 1.6578,
2067
+ "step": 58800
2068
+ },
2069
+ {
2070
+ "epoch": 0.04103345896062944,
2071
+ "grad_norm": 5.038608551025391,
2072
+ "learning_rate": 1.9985464375560455e-05,
2073
+ "loss": 1.6595,
2074
+ "step": 59000
2075
+ },
2076
+ {
2077
+ "epoch": 0.04117255543168242,
2078
+ "grad_norm": 4.362532138824463,
2079
+ "learning_rate": 1.9985365696335646e-05,
2080
+ "loss": 1.7077,
2081
+ "step": 59200
2082
+ },
2083
+ {
2084
+ "epoch": 0.041311651902735405,
2085
+ "grad_norm": 4.135485649108887,
2086
+ "learning_rate": 1.9985266683637493e-05,
2087
+ "loss": 1.6595,
2088
+ "step": 59400
2089
+ },
2090
+ {
2091
+ "epoch": 0.041450748373788385,
2092
+ "grad_norm": 3.2375669479370117,
2093
+ "learning_rate": 1.9985167337470723e-05,
2094
+ "loss": 1.6731,
2095
+ "step": 59600
2096
+ },
2097
+ {
2098
+ "epoch": 0.041589844844841364,
2099
+ "grad_norm": 7.285531044006348,
2100
+ "learning_rate": 1.9985067657840077e-05,
2101
+ "loss": 1.6671,
2102
+ "step": 59800
2103
+ },
2104
+ {
2105
+ "epoch": 0.041728941315894344,
2106
+ "grad_norm": 5.653309345245361,
2107
+ "learning_rate": 1.998496764475032e-05,
2108
+ "loss": 1.6902,
2109
+ "step": 60000
2110
+ },
2111
+ {
2112
+ "epoch": 0.041868037786947324,
2113
+ "grad_norm": 6.675251007080078,
2114
+ "learning_rate": 1.9984867298206225e-05,
2115
+ "loss": 1.6838,
2116
+ "step": 60200
2117
+ },
2118
+ {
2119
+ "epoch": 0.04200713425800031,
2120
+ "grad_norm": 4.708273887634277,
2121
+ "learning_rate": 1.9984766618212576e-05,
2122
+ "loss": 1.615,
2123
+ "step": 60400
2124
+ },
2125
+ {
2126
+ "epoch": 0.04214623072905329,
2127
+ "grad_norm": 2.906949281692505,
2128
+ "learning_rate": 1.9984665604774185e-05,
2129
+ "loss": 1.6764,
2130
+ "step": 60600
2131
+ },
2132
+ {
2133
+ "epoch": 0.04228532720010627,
2134
+ "grad_norm": 3.628300666809082,
2135
+ "learning_rate": 1.9984564257895867e-05,
2136
+ "loss": 1.689,
2137
+ "step": 60800
2138
+ },
2139
+ {
2140
+ "epoch": 0.04242442367115925,
2141
+ "grad_norm": 3.8123619556427,
2142
+ "learning_rate": 1.9984462577582474e-05,
2143
+ "loss": 1.6421,
2144
+ "step": 61000
2145
+ },
2146
+ {
2147
+ "epoch": 0.04256352014221223,
2148
+ "grad_norm": 3.2274296283721924,
2149
+ "learning_rate": 1.9984360563838847e-05,
2150
+ "loss": 1.649,
2151
+ "step": 61200
2152
+ },
2153
+ {
2154
+ "epoch": 0.042702616613265215,
2155
+ "grad_norm": 1.9272345304489136,
2156
+ "learning_rate": 1.9984258216669862e-05,
2157
+ "loss": 1.7022,
2158
+ "step": 61400
2159
+ },
2160
+ {
2161
+ "epoch": 0.042841713084318195,
2162
+ "grad_norm": 3.6718461513519287,
2163
+ "learning_rate": 1.9984155536080404e-05,
2164
+ "loss": 1.6884,
2165
+ "step": 61600
2166
+ },
2167
+ {
2168
+ "epoch": 0.042980809555371174,
2169
+ "grad_norm": 5.313728332519531,
2170
+ "learning_rate": 1.9984052522075377e-05,
2171
+ "loss": 1.6437,
2172
+ "step": 61800
2173
+ },
2174
+ {
2175
+ "epoch": 0.043119906026424154,
2176
+ "grad_norm": 4.368004322052002,
2177
+ "learning_rate": 1.9983949174659692e-05,
2178
+ "loss": 1.7634,
2179
+ "step": 62000
2180
+ },
2181
+ {
2182
+ "epoch": 0.04325900249747714,
2183
+ "grad_norm": 2.9768130779266357,
2184
+ "learning_rate": 1.998384549383829e-05,
2185
+ "loss": 1.67,
2186
+ "step": 62200
2187
+ },
2188
+ {
2189
+ "epoch": 0.04339809896853012,
2190
+ "grad_norm": 4.6725897789001465,
2191
+ "learning_rate": 1.9983741479616118e-05,
2192
+ "loss": 1.6884,
2193
+ "step": 62400
2194
+ },
2195
+ {
2196
+ "epoch": 0.0435371954395831,
2197
+ "grad_norm": 3.639035940170288,
2198
+ "learning_rate": 1.998363713199814e-05,
2199
+ "loss": 1.6921,
2200
+ "step": 62600
2201
+ },
2202
+ {
2203
+ "epoch": 0.04367629191063608,
2204
+ "grad_norm": 4.510855197906494,
2205
+ "learning_rate": 1.998353245098934e-05,
2206
+ "loss": 1.6833,
2207
+ "step": 62800
2208
+ },
2209
+ {
2210
+ "epoch": 0.04381538838168906,
2211
+ "grad_norm": 4.581980228424072,
2212
+ "learning_rate": 1.9983427436594716e-05,
2213
+ "loss": 1.686,
2214
+ "step": 63000
2215
+ },
2216
+ {
2217
+ "epoch": 0.043954484852742046,
2218
+ "grad_norm": 4.461788654327393,
2219
+ "learning_rate": 1.9983322088819274e-05,
2220
+ "loss": 1.6919,
2221
+ "step": 63200
2222
+ },
2223
+ {
2224
+ "epoch": 0.044093581323795025,
2225
+ "grad_norm": 3.806112766265869,
2226
+ "learning_rate": 1.9983216407668053e-05,
2227
+ "loss": 1.6954,
2228
+ "step": 63400
2229
+ },
2230
+ {
2231
+ "epoch": 0.044232677794848005,
2232
+ "grad_norm": 4.456310749053955,
2233
+ "learning_rate": 1.9983110393146093e-05,
2234
+ "loss": 1.7317,
2235
+ "step": 63600
2236
+ },
2237
+ {
2238
+ "epoch": 0.044371774265900985,
2239
+ "grad_norm": 6.300820827484131,
2240
+ "learning_rate": 1.998300404525845e-05,
2241
+ "loss": 1.7097,
2242
+ "step": 63800
2243
+ },
2244
+ {
2245
+ "epoch": 0.04451087073695397,
2246
+ "grad_norm": 3.2175614833831787,
2247
+ "learning_rate": 1.9982897364010213e-05,
2248
+ "loss": 1.6765,
2249
+ "step": 64000
2250
+ },
2251
+ {
2252
+ "epoch": 0.04464996720800695,
2253
+ "grad_norm": 5.659944534301758,
2254
+ "learning_rate": 1.9982790349406468e-05,
2255
+ "loss": 1.6226,
2256
+ "step": 64200
2257
+ },
2258
+ {
2259
+ "epoch": 0.04478906367905993,
2260
+ "grad_norm": 3.648066759109497,
2261
+ "learning_rate": 1.998268300145232e-05,
2262
+ "loss": 1.6363,
2263
+ "step": 64400
2264
+ },
2265
+ {
2266
+ "epoch": 0.04492816015011291,
2267
+ "grad_norm": 6.237667083740234,
2268
+ "learning_rate": 1.99825753201529e-05,
2269
+ "loss": 1.656,
2270
+ "step": 64600
2271
+ },
2272
+ {
2273
+ "epoch": 0.04506725662116589,
2274
+ "grad_norm": 4.146718502044678,
2275
+ "learning_rate": 1.9982467305513346e-05,
2276
+ "loss": 1.6788,
2277
+ "step": 64800
2278
+ },
2279
+ {
2280
+ "epoch": 0.045206353092218876,
2281
+ "grad_norm": 3.9391887187957764,
2282
+ "learning_rate": 1.9982358957538816e-05,
2283
+ "loss": 1.7115,
2284
+ "step": 65000
2285
+ },
2286
+ {
2287
+ "epoch": 0.045345449563271856,
2288
+ "grad_norm": 4.433906555175781,
2289
+ "learning_rate": 1.9982250276234483e-05,
2290
+ "loss": 1.6697,
2291
+ "step": 65200
2292
+ },
2293
+ {
2294
+ "epoch": 0.045484546034324835,
2295
+ "grad_norm": 4.5281171798706055,
2296
+ "learning_rate": 1.998214126160553e-05,
2297
+ "loss": 1.6247,
2298
+ "step": 65400
2299
+ },
2300
+ {
2301
+ "epoch": 0.045623642505377815,
2302
+ "grad_norm": 2.758456230163574,
2303
+ "learning_rate": 1.9982031913657168e-05,
2304
+ "loss": 1.651,
2305
+ "step": 65600
2306
+ },
2307
+ {
2308
+ "epoch": 0.0457627389764308,
2309
+ "grad_norm": 4.08587121963501,
2310
+ "learning_rate": 1.9981922232394612e-05,
2311
+ "loss": 1.702,
2312
+ "step": 65800
2313
+ },
2314
+ {
2315
+ "epoch": 0.04590183544748378,
2316
+ "grad_norm": 2.943826913833618,
2317
+ "learning_rate": 1.9981812217823103e-05,
2318
+ "loss": 1.7346,
2319
+ "step": 66000
2320
+ },
2321
+ {
2322
+ "epoch": 0.04604093191853676,
2323
+ "grad_norm": 5.124936580657959,
2324
+ "learning_rate": 1.9981701869947887e-05,
2325
+ "loss": 1.6869,
2326
+ "step": 66200
2327
+ },
2328
+ {
2329
+ "epoch": 0.04618002838958974,
2330
+ "grad_norm": 5.860598087310791,
2331
+ "learning_rate": 1.9981591188774236e-05,
2332
+ "loss": 1.699,
2333
+ "step": 66400
2334
+ },
2335
+ {
2336
+ "epoch": 0.04631912486064272,
2337
+ "grad_norm": 5.8782172203063965,
2338
+ "learning_rate": 1.9981480174307434e-05,
2339
+ "loss": 1.7112,
2340
+ "step": 66600
2341
+ },
2342
+ {
2343
+ "epoch": 0.04645822133169571,
2344
+ "grad_norm": 3.9649393558502197,
2345
+ "learning_rate": 1.9981368826552775e-05,
2346
+ "loss": 1.6556,
2347
+ "step": 66800
2348
+ },
2349
+ {
2350
+ "epoch": 0.046597317802748686,
2351
+ "grad_norm": 4.633118629455566,
2352
+ "learning_rate": 1.998125714551558e-05,
2353
+ "loss": 1.6687,
2354
+ "step": 67000
2355
+ },
2356
+ {
2357
+ "epoch": 0.046736414273801666,
2358
+ "grad_norm": 2.720689535140991,
2359
+ "learning_rate": 1.9981145131201183e-05,
2360
+ "loss": 1.6155,
2361
+ "step": 67200
2362
+ },
2363
+ {
2364
+ "epoch": 0.046875510744854645,
2365
+ "grad_norm": 2.554689407348633,
2366
+ "learning_rate": 1.9981032783614928e-05,
2367
+ "loss": 1.7186,
2368
+ "step": 67400
2369
+ },
2370
+ {
2371
+ "epoch": 0.04701460721590763,
2372
+ "grad_norm": 6.52652645111084,
2373
+ "learning_rate": 1.9980920102762174e-05,
2374
+ "loss": 1.7065,
2375
+ "step": 67600
2376
+ },
2377
+ {
2378
+ "epoch": 0.04715370368696061,
2379
+ "grad_norm": 4.655409336090088,
2380
+ "learning_rate": 1.998080708864831e-05,
2381
+ "loss": 1.6714,
2382
+ "step": 67800
2383
+ },
2384
+ {
2385
+ "epoch": 0.04729280015801359,
2386
+ "grad_norm": 2.7842917442321777,
2387
+ "learning_rate": 1.998069374127872e-05,
2388
+ "loss": 1.6298,
2389
+ "step": 68000
2390
+ },
2391
+ {
2392
+ "epoch": 0.04743189662906657,
2393
+ "grad_norm": 3.6234030723571777,
2394
+ "learning_rate": 1.9980580060658826e-05,
2395
+ "loss": 1.6689,
2396
+ "step": 68200
2397
+ },
2398
+ {
2399
+ "epoch": 0.04757099310011955,
2400
+ "grad_norm": 4.62315559387207,
2401
+ "learning_rate": 1.9980466046794044e-05,
2402
+ "loss": 1.7086,
2403
+ "step": 68400
2404
+ },
2405
+ {
2406
+ "epoch": 0.04771008957117254,
2407
+ "grad_norm": 5.461521148681641,
2408
+ "learning_rate": 1.998035169968983e-05,
2409
+ "loss": 1.6662,
2410
+ "step": 68600
2411
+ },
2412
+ {
2413
+ "epoch": 0.04784918604222552,
2414
+ "grad_norm": 7.280538558959961,
2415
+ "learning_rate": 1.998023701935163e-05,
2416
+ "loss": 1.7044,
2417
+ "step": 68800
2418
+ },
2419
+ {
2420
+ "epoch": 0.047988282513278496,
2421
+ "grad_norm": 3.66982102394104,
2422
+ "learning_rate": 1.998012200578493e-05,
2423
+ "loss": 1.6707,
2424
+ "step": 69000
2425
+ },
2426
+ {
2427
+ "epoch": 0.048127378984331476,
2428
+ "grad_norm": 3.3503715991973877,
2429
+ "learning_rate": 1.998000665899521e-05,
2430
+ "loss": 1.6544,
2431
+ "step": 69200
2432
+ },
2433
+ {
2434
+ "epoch": 0.04826647545538446,
2435
+ "grad_norm": 3.640894889831543,
2436
+ "learning_rate": 1.9979890978987976e-05,
2437
+ "loss": 1.6518,
2438
+ "step": 69400
2439
+ },
2440
+ {
2441
+ "epoch": 0.04840557192643744,
2442
+ "grad_norm": 6.372598648071289,
2443
+ "learning_rate": 1.9979774965768762e-05,
2444
+ "loss": 1.6693,
2445
+ "step": 69600
2446
+ },
2447
+ {
2448
+ "epoch": 0.04854466839749042,
2449
+ "grad_norm": 4.334291458129883,
2450
+ "learning_rate": 1.99796586193431e-05,
2451
+ "loss": 1.7179,
2452
+ "step": 69800
2453
+ },
2454
+ {
2455
+ "epoch": 0.0486837648685434,
2456
+ "grad_norm": 3.7265446186065674,
2457
+ "learning_rate": 1.997954193971655e-05,
2458
+ "loss": 1.6597,
2459
+ "step": 70000
2460
+ },
2461
+ {
2462
+ "epoch": 0.04882286133959638,
2463
+ "grad_norm": 5.195233345031738,
2464
+ "learning_rate": 1.997942492689467e-05,
2465
+ "loss": 1.7107,
2466
+ "step": 70200
2467
+ },
2468
+ {
2469
+ "epoch": 0.04896195781064937,
2470
+ "grad_norm": 3.7042763233184814,
2471
+ "learning_rate": 1.9979307580883048e-05,
2472
+ "loss": 1.7004,
2473
+ "step": 70400
2474
+ },
2475
+ {
2476
+ "epoch": 0.04910105428170235,
2477
+ "grad_norm": 5.705939292907715,
2478
+ "learning_rate": 1.9979189901687298e-05,
2479
+ "loss": 1.6756,
2480
+ "step": 70600
2481
+ },
2482
+ {
2483
+ "epoch": 0.04924015075275533,
2484
+ "grad_norm": 8.152667999267578,
2485
+ "learning_rate": 1.9979071889313028e-05,
2486
+ "loss": 1.6684,
2487
+ "step": 70800
2488
+ },
2489
+ {
2490
+ "epoch": 0.049379247223808306,
2491
+ "grad_norm": 4.426294326782227,
2492
+ "learning_rate": 1.9978953543765876e-05,
2493
+ "loss": 1.7269,
2494
+ "step": 71000
2495
+ },
2496
+ {
2497
+ "epoch": 0.04951834369486129,
2498
+ "grad_norm": 3.9523568153381348,
2499
+ "learning_rate": 1.9978834865051492e-05,
2500
+ "loss": 1.7212,
2501
+ "step": 71200
2502
+ },
2503
+ {
2504
+ "epoch": 0.04965744016591427,
2505
+ "grad_norm": 4.159371376037598,
2506
+ "learning_rate": 1.9978715853175532e-05,
2507
+ "loss": 1.6869,
2508
+ "step": 71400
2509
+ },
2510
+ {
2511
+ "epoch": 0.04979653663696725,
2512
+ "grad_norm": 5.7590155601501465,
2513
+ "learning_rate": 1.997859650814369e-05,
2514
+ "loss": 1.6258,
2515
+ "step": 71600
2516
+ },
2517
+ {
2518
+ "epoch": 0.04993563310802023,
2519
+ "grad_norm": 6.574980735778809,
2520
+ "learning_rate": 1.997847682996165e-05,
2521
+ "loss": 1.7416,
2522
+ "step": 71800
2523
+ },
2524
+ {
2525
+ "epoch": 0.05007472957907321,
2526
+ "grad_norm": 2.2273080348968506,
2527
+ "learning_rate": 1.9978356818635146e-05,
2528
+ "loss": 1.6869,
2529
+ "step": 72000
2530
+ },
2531
+ {
2532
+ "epoch": 0.0502138260501262,
2533
+ "grad_norm": 2.451094150543213,
2534
+ "learning_rate": 1.997823647416989e-05,
2535
+ "loss": 1.6537,
2536
+ "step": 72200
2537
+ },
2538
+ {
2539
+ "epoch": 0.05035292252117918,
2540
+ "grad_norm": 2.1979329586029053,
2541
+ "learning_rate": 1.997811579657163e-05,
2542
+ "loss": 1.6154,
2543
+ "step": 72400
2544
+ },
2545
+ {
2546
+ "epoch": 0.05049201899223216,
2547
+ "grad_norm": 5.160410404205322,
2548
+ "learning_rate": 1.997799478584613e-05,
2549
+ "loss": 1.7159,
2550
+ "step": 72600
2551
+ },
2552
+ {
2553
+ "epoch": 0.05063111546328514,
2554
+ "grad_norm": 4.327044486999512,
2555
+ "learning_rate": 1.997787344199917e-05,
2556
+ "loss": 1.7153,
2557
+ "step": 72800
2558
+ },
2559
+ {
2560
+ "epoch": 0.050770211934338116,
2561
+ "grad_norm": 3.2752387523651123,
2562
+ "learning_rate": 1.997775176503653e-05,
2563
+ "loss": 1.6477,
2564
+ "step": 73000
2565
+ },
2566
+ {
2567
+ "epoch": 0.0509093084053911,
2568
+ "grad_norm": 3.984393358230591,
2569
+ "learning_rate": 1.9977629754964036e-05,
2570
+ "loss": 1.6563,
2571
+ "step": 73200
2572
+ },
2573
+ {
2574
+ "epoch": 0.05104840487644408,
2575
+ "grad_norm": 5.828344345092773,
2576
+ "learning_rate": 1.99775074117875e-05,
2577
+ "loss": 1.6841,
2578
+ "step": 73400
2579
+ },
2580
+ {
2581
+ "epoch": 0.05118750134749706,
2582
+ "grad_norm": 3.39604115486145,
2583
+ "learning_rate": 1.9977384735512765e-05,
2584
+ "loss": 1.6379,
2585
+ "step": 73600
2586
+ },
2587
+ {
2588
+ "epoch": 0.05132659781855004,
2589
+ "grad_norm": 4.018509387969971,
2590
+ "learning_rate": 1.9977261726145692e-05,
2591
+ "loss": 1.6195,
2592
+ "step": 73800
2593
+ },
2594
+ {
2595
+ "epoch": 0.05146569428960303,
2596
+ "grad_norm": 5.31196403503418,
2597
+ "learning_rate": 1.997713838369215e-05,
2598
+ "loss": 1.6841,
2599
+ "step": 74000
2600
+ },
2601
+ {
2602
+ "epoch": 0.05160479076065601,
2603
+ "grad_norm": 3.7980597019195557,
2604
+ "learning_rate": 1.9977014708158027e-05,
2605
+ "loss": 1.727,
2606
+ "step": 74200
2607
+ },
2608
+ {
2609
+ "epoch": 0.05174388723170899,
2610
+ "grad_norm": 4.492558479309082,
2611
+ "learning_rate": 1.997689069954923e-05,
2612
+ "loss": 1.6307,
2613
+ "step": 74400
2614
+ }
2615
+ ],
2616
+ "logging_steps": 200,
2617
+ "max_steps": 2875702,
2618
+ "num_input_tokens_seen": 0,
2619
+ "num_train_epochs": 2,
2620
+ "save_steps": 200,
2621
+ "stateful_callbacks": {
2622
+ "TrainerControl": {
2623
+ "args": {
2624
+ "should_epoch_stop": false,
2625
+ "should_evaluate": false,
2626
+ "should_log": false,
2627
+ "should_save": true,
2628
+ "should_training_stop": false
2629
+ },
2630
+ "attributes": {}
2631
+ }
2632
+ },
2633
+ "total_flos": 9.906764066420982e+17,
2634
+ "train_batch_size": 1,
2635
+ "trial_name": null,
2636
+ "trial_params": null
2637
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973554a532ca404cb4db7d5fef3755d36407a35ec7c1a90c277a7941be0f4f1e
3
+ size 6840
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6facab35ec004a0968525493064d27e9ec8f8067a270e109bb7489aa7601e279
3
+ size 6840