Chaew00n commited on
Commit
b3a2e63
·
verified ·
1 Parent(s): 4bd6758

Training in progress, step 200, checkpoint

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-1.7B
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 0.15.2
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen3-1.7B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "up_proj",
28
+ "q_proj",
29
+ "down_proj",
30
+ "v_proj",
31
+ "k_proj",
32
+ "gate_proj",
33
+ "o_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a14de41340baf1199edb1bd4a60982282a33130c56d342b73c228368dfc5023
3
+ size 69782384
checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
checkpoint-200/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575835d7d9f0ebb79e180d36d805ad7ffd26f25500e580884a495b8ebe47d32c
3
+ size 139790651
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a872848c4c0170cdae18529cdff1a7e25fab75315b06e87561fecc1409255d
3
+ size 14709
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b687cd81189b233e088a5400f7d704014a686ad0b2064a54aed92470b0caf93
3
+ size 1465
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|im_end|>"
25
+ }
checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3693e8d4feea9af769307430ebff24aa6c1e2b57f8199cb932a7887af67bba3c
3
+ size 11422929
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|im_end|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.32,
6
+ "eval_steps": 500,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0016,
14
+ "grad_norm": 18.498022079467773,
15
+ "learning_rate": 0.0,
16
+ "loss": 11.9034,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0032,
21
+ "grad_norm": 19.59610366821289,
22
+ "learning_rate": 7.142857142857143e-07,
23
+ "loss": 12.361,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0048,
28
+ "grad_norm": 19.05824089050293,
29
+ "learning_rate": 1.4285714285714286e-06,
30
+ "loss": 12.3027,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0064,
35
+ "grad_norm": 18.656831741333008,
36
+ "learning_rate": 2.1428571428571427e-06,
37
+ "loss": 11.9369,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.008,
42
+ "grad_norm": 19.260093688964844,
43
+ "learning_rate": 2.8571428571428573e-06,
44
+ "loss": 12.0124,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0096,
49
+ "grad_norm": 18.27457046508789,
50
+ "learning_rate": 3.5714285714285718e-06,
51
+ "loss": 11.8957,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0112,
56
+ "grad_norm": 18.090967178344727,
57
+ "learning_rate": 4.2857142857142855e-06,
58
+ "loss": 12.0549,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0128,
63
+ "grad_norm": 18.144412994384766,
64
+ "learning_rate": 5e-06,
65
+ "loss": 12.0455,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0144,
70
+ "grad_norm": 17.77107048034668,
71
+ "learning_rate": 4.999967697817016e-06,
72
+ "loss": 12.0381,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.016,
77
+ "grad_norm": 19.326251983642578,
78
+ "learning_rate": 4.9998707921028104e-06,
79
+ "loss": 12.2511,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.0176,
84
+ "grad_norm": 20.007396697998047,
85
+ "learning_rate": 4.999709285361594e-06,
86
+ "loss": 12.5214,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0192,
91
+ "grad_norm": 18.9156551361084,
92
+ "learning_rate": 4.999483181766986e-06,
93
+ "loss": 12.226,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.0208,
98
+ "grad_norm": 16.71934700012207,
99
+ "learning_rate": 4.999192487161895e-06,
100
+ "loss": 11.63,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0224,
105
+ "grad_norm": 16.819419860839844,
106
+ "learning_rate": 4.998837209058379e-06,
107
+ "loss": 11.8643,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.024,
112
+ "grad_norm": 17.38993263244629,
113
+ "learning_rate": 4.998417356637445e-06,
114
+ "loss": 12.0876,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0256,
119
+ "grad_norm": 17.411874771118164,
120
+ "learning_rate": 4.997932940748811e-06,
121
+ "loss": 11.9954,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.0272,
126
+ "grad_norm": 17.002464294433594,
127
+ "learning_rate": 4.997383973910631e-06,
128
+ "loss": 12.0872,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0288,
133
+ "grad_norm": 16.964523315429688,
134
+ "learning_rate": 4.996770470309167e-06,
135
+ "loss": 11.9659,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.0304,
140
+ "grad_norm": 17.12218475341797,
141
+ "learning_rate": 4.9960924457984225e-06,
142
+ "loss": 11.9041,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.032,
147
+ "grad_norm": 15.89167308807373,
148
+ "learning_rate": 4.995349917899735e-06,
149
+ "loss": 11.5677,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.0336,
154
+ "grad_norm": 17.404312133789062,
155
+ "learning_rate": 4.994542905801323e-06,
156
+ "loss": 12.0405,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0352,
161
+ "grad_norm": 17.553056716918945,
162
+ "learning_rate": 4.993671430357788e-06,
163
+ "loss": 11.9337,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.0368,
168
+ "grad_norm": 17.339885711669922,
169
+ "learning_rate": 4.9927355140895775e-06,
170
+ "loss": 11.9247,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0384,
175
+ "grad_norm": 16.14508056640625,
176
+ "learning_rate": 4.991735181182401e-06,
177
+ "loss": 11.5418,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.04,
182
+ "grad_norm": 14.626124382019043,
183
+ "learning_rate": 4.9906704574866105e-06,
184
+ "loss": 11.4515,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.0416,
189
+ "grad_norm": 17.168630599975586,
190
+ "learning_rate": 4.989541370516523e-06,
191
+ "loss": 11.9094,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.0432,
196
+ "grad_norm": 15.818598747253418,
197
+ "learning_rate": 4.98834794944972e-06,
198
+ "loss": 11.7249,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.0448,
203
+ "grad_norm": 15.550960540771484,
204
+ "learning_rate": 4.987090225126285e-06,
205
+ "loss": 11.3948,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.0464,
210
+ "grad_norm": 15.328129768371582,
211
+ "learning_rate": 4.985768230048011e-06,
212
+ "loss": 11.3551,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.048,
217
+ "grad_norm": 13.792865753173828,
218
+ "learning_rate": 4.9843819983775575e-06,
219
+ "loss": 11.1959,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.0496,
224
+ "grad_norm": 15.154494285583496,
225
+ "learning_rate": 4.982931565937575e-06,
226
+ "loss": 11.7186,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.0512,
231
+ "grad_norm": 14.210274696350098,
232
+ "learning_rate": 4.98141697020977e-06,
233
+ "loss": 11.3324,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.0528,
238
+ "grad_norm": 14.419412612915039,
239
+ "learning_rate": 4.979838250333941e-06,
240
+ "loss": 11.0964,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.0544,
245
+ "grad_norm": 14.476765632629395,
246
+ "learning_rate": 4.978195447106965e-06,
247
+ "loss": 11.4052,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.056,
252
+ "grad_norm": 13.166458129882812,
253
+ "learning_rate": 4.976488602981748e-06,
254
+ "loss": 11.1172,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.0576,
259
+ "grad_norm": 13.77320384979248,
260
+ "learning_rate": 4.974717762066123e-06,
261
+ "loss": 11.2174,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.0592,
266
+ "grad_norm": 13.610458374023438,
267
+ "learning_rate": 4.972882970121711e-06,
268
+ "loss": 11.0993,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.0608,
273
+ "grad_norm": 13.38510513305664,
274
+ "learning_rate": 4.970984274562741e-06,
275
+ "loss": 11.0244,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.0624,
280
+ "grad_norm": 13.513715744018555,
281
+ "learning_rate": 4.969021724454821e-06,
282
+ "loss": 11.0893,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.064,
287
+ "grad_norm": 12.476004600524902,
288
+ "learning_rate": 4.966995370513675e-06,
289
+ "loss": 10.9256,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.0656,
294
+ "grad_norm": 13.007659912109375,
295
+ "learning_rate": 4.9649052651038255e-06,
296
+ "loss": 10.897,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.0672,
301
+ "grad_norm": 12.74197006225586,
302
+ "learning_rate": 4.962751462237248e-06,
303
+ "loss": 10.9702,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0688,
308
+ "grad_norm": 11.668892860412598,
309
+ "learning_rate": 4.9605340175719686e-06,
310
+ "loss": 10.6871,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.0704,
315
+ "grad_norm": 12.722009658813477,
316
+ "learning_rate": 4.958252988410631e-06,
317
+ "loss": 10.7933,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.072,
322
+ "grad_norm": 10.594651222229004,
323
+ "learning_rate": 4.955908433699013e-06,
324
+ "loss": 10.2903,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.0736,
329
+ "grad_norm": 12.946322441101074,
330
+ "learning_rate": 4.9535004140245005e-06,
331
+ "loss": 11.141,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.0752,
336
+ "grad_norm": 12.783811569213867,
337
+ "learning_rate": 4.9510289916145295e-06,
338
+ "loss": 10.779,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.0768,
343
+ "grad_norm": 11.354564666748047,
344
+ "learning_rate": 4.94849423033497e-06,
345
+ "loss": 10.5837,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.0784,
350
+ "grad_norm": 11.848569869995117,
351
+ "learning_rate": 4.94589619568848e-06,
352
+ "loss": 10.5706,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.08,
357
+ "grad_norm": 9.897051811218262,
358
+ "learning_rate": 4.943234954812812e-06,
359
+ "loss": 10.2364,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.0816,
364
+ "grad_norm": 11.316352844238281,
365
+ "learning_rate": 4.940510576479079e-06,
366
+ "loss": 10.6149,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.0832,
371
+ "grad_norm": 11.829602241516113,
372
+ "learning_rate": 4.937723131089974e-06,
373
+ "loss": 10.5496,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.0848,
378
+ "grad_norm": 10.069260597229004,
379
+ "learning_rate": 4.934872690677953e-06,
380
+ "loss": 10.0925,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.0864,
385
+ "grad_norm": 11.005655288696289,
386
+ "learning_rate": 4.931959328903376e-06,
387
+ "loss": 10.3874,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.088,
392
+ "grad_norm": 10.913771629333496,
393
+ "learning_rate": 4.928983121052597e-06,
394
+ "loss": 10.3699,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.0896,
399
+ "grad_norm": 10.943140983581543,
400
+ "learning_rate": 4.925944144036027e-06,
401
+ "loss": 10.3604,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.0912,
406
+ "grad_norm": 11.520155906677246,
407
+ "learning_rate": 4.922842476386137e-06,
408
+ "loss": 10.45,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.0928,
413
+ "grad_norm": 11.597639083862305,
414
+ "learning_rate": 4.919678198255438e-06,
415
+ "loss": 10.6551,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.0944,
420
+ "grad_norm": 11.26528549194336,
421
+ "learning_rate": 4.9164513914144005e-06,
422
+ "loss": 10.3729,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.096,
427
+ "grad_norm": 11.043292045593262,
428
+ "learning_rate": 4.91316213924935e-06,
429
+ "loss": 10.2723,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.0976,
434
+ "grad_norm": 10.670892715454102,
435
+ "learning_rate": 4.909810526760307e-06,
436
+ "loss": 10.3842,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.0992,
441
+ "grad_norm": 12.231328010559082,
442
+ "learning_rate": 4.90639664055879e-06,
443
+ "loss": 10.4897,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.1008,
448
+ "grad_norm": 10.968878746032715,
449
+ "learning_rate": 4.902920568865582e-06,
450
+ "loss": 10.225,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.1024,
455
+ "grad_norm": 10.761625289916992,
456
+ "learning_rate": 4.899382401508446e-06,
457
+ "loss": 10.0817,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.104,
462
+ "grad_norm": 9.868699073791504,
463
+ "learning_rate": 4.8957822299198045e-06,
464
+ "loss": 9.9514,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.1056,
469
+ "grad_norm": 10.76175308227539,
470
+ "learning_rate": 4.892120147134378e-06,
471
+ "loss": 10.2281,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.1072,
476
+ "grad_norm": 10.531647682189941,
477
+ "learning_rate": 4.888396247786784e-06,
478
+ "loss": 10.0424,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.1088,
483
+ "grad_norm": 9.720768928527832,
484
+ "learning_rate": 4.884610628109082e-06,
485
+ "loss": 9.8735,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.1104,
490
+ "grad_norm": 10.765035629272461,
491
+ "learning_rate": 4.880763385928298e-06,
492
+ "loss": 10.1977,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.112,
497
+ "grad_norm": 10.57542896270752,
498
+ "learning_rate": 4.876854620663887e-06,
499
+ "loss": 9.9432,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.1136,
504
+ "grad_norm": 10.321698188781738,
505
+ "learning_rate": 4.872884433325169e-06,
506
+ "loss": 9.9563,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.1152,
511
+ "grad_norm": 10.044979095458984,
512
+ "learning_rate": 4.868852926508721e-06,
513
+ "loss": 9.9412,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.1168,
518
+ "grad_norm": 10.604913711547852,
519
+ "learning_rate": 4.864760204395717e-06,
520
+ "loss": 10.0144,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.1184,
525
+ "grad_norm": 9.378023147583008,
526
+ "learning_rate": 4.860606372749247e-06,
527
+ "loss": 9.8055,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.12,
532
+ "grad_norm": 9.08212947845459,
533
+ "learning_rate": 4.856391538911572e-06,
534
+ "loss": 9.7179,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.1216,
539
+ "grad_norm": 10.120437622070312,
540
+ "learning_rate": 4.8521158118013605e-06,
541
+ "loss": 9.7055,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.1232,
546
+ "grad_norm": 9.448174476623535,
547
+ "learning_rate": 4.847779301910868e-06,
548
+ "loss": 9.7753,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.1248,
553
+ "grad_norm": 9.994352340698242,
554
+ "learning_rate": 4.843382121303082e-06,
555
+ "loss": 9.8005,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.1264,
560
+ "grad_norm": 10.175590515136719,
561
+ "learning_rate": 4.83892438360883e-06,
562
+ "loss": 9.7149,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.128,
567
+ "grad_norm": 9.187248229980469,
568
+ "learning_rate": 4.83440620402384e-06,
569
+ "loss": 9.5077,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.1296,
574
+ "grad_norm": 8.287508964538574,
575
+ "learning_rate": 4.829827699305759e-06,
576
+ "loss": 9.2745,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.1312,
581
+ "grad_norm": 9.502992630004883,
582
+ "learning_rate": 4.825188987771149e-06,
583
+ "loss": 9.7212,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.1328,
588
+ "grad_norm": 9.398665428161621,
589
+ "learning_rate": 4.820490189292415e-06,
590
+ "loss": 9.4711,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.1344,
595
+ "grad_norm": 9.67027473449707,
596
+ "learning_rate": 4.815731425294716e-06,
597
+ "loss": 9.6444,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.136,
602
+ "grad_norm": 9.999480247497559,
603
+ "learning_rate": 4.810912818752825e-06,
604
+ "loss": 9.6473,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.1376,
609
+ "grad_norm": 10.192490577697754,
610
+ "learning_rate": 4.806034494187949e-06,
611
+ "loss": 9.5,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.1392,
616
+ "grad_norm": 10.132280349731445,
617
+ "learning_rate": 4.8010965776645145e-06,
618
+ "loss": 9.5879,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.1408,
623
+ "grad_norm": 10.07225227355957,
624
+ "learning_rate": 4.796099196786908e-06,
625
+ "loss": 9.4842,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.1424,
630
+ "grad_norm": 9.903701782226562,
631
+ "learning_rate": 4.791042480696179e-06,
632
+ "loss": 9.5136,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.144,
637
+ "grad_norm": 9.270772933959961,
638
+ "learning_rate": 4.785926560066703e-06,
639
+ "loss": 9.367,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.1456,
644
+ "grad_norm": 8.604142189025879,
645
+ "learning_rate": 4.780751567102801e-06,
646
+ "loss": 9.1618,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.1472,
651
+ "grad_norm": 9.69423770904541,
652
+ "learning_rate": 4.775517635535332e-06,
653
+ "loss": 9.2597,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.1488,
658
+ "grad_norm": 10.679227828979492,
659
+ "learning_rate": 4.770224900618226e-06,
660
+ "loss": 9.3722,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.1504,
665
+ "grad_norm": 9.498805046081543,
666
+ "learning_rate": 4.764873499124997e-06,
667
+ "loss": 9.2149,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.152,
672
+ "grad_norm": 10.133721351623535,
673
+ "learning_rate": 4.759463569345205e-06,
674
+ "loss": 9.211,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.1536,
679
+ "grad_norm": 10.703787803649902,
680
+ "learning_rate": 4.753995251080884e-06,
681
+ "loss": 9.2456,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.1552,
686
+ "grad_norm": 9.839086532592773,
687
+ "learning_rate": 4.748468685642926e-06,
688
+ "loss": 9.0973,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.1568,
693
+ "grad_norm": 8.186079978942871,
694
+ "learning_rate": 4.742884015847436e-06,
695
+ "loss": 8.9378,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.1584,
700
+ "grad_norm": 9.491665840148926,
701
+ "learning_rate": 4.737241386012032e-06,
702
+ "loss": 9.0209,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.16,
707
+ "grad_norm": 9.313272476196289,
708
+ "learning_rate": 4.731540941952126e-06,
709
+ "loss": 9.0591,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.1616,
714
+ "grad_norm": 9.365504264831543,
715
+ "learning_rate": 4.725782830977145e-06,
716
+ "loss": 9.0187,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.1632,
721
+ "grad_norm": 9.761168479919434,
722
+ "learning_rate": 4.719967201886734e-06,
723
+ "loss": 8.9663,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.1648,
728
+ "grad_norm": 10.886737823486328,
729
+ "learning_rate": 4.714094204966903e-06,
730
+ "loss": 9.0523,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.1664,
735
+ "grad_norm": 11.529026985168457,
736
+ "learning_rate": 4.708163991986152e-06,
737
+ "loss": 8.9862,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.168,
742
+ "grad_norm": 11.003949165344238,
743
+ "learning_rate": 4.702176716191539e-06,
744
+ "loss": 8.9944,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.1696,
749
+ "grad_norm": 10.637957572937012,
750
+ "learning_rate": 4.696132532304727e-06,
751
+ "loss": 8.7661,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.1712,
756
+ "grad_norm": 10.600850105285645,
757
+ "learning_rate": 4.690031596517984e-06,
758
+ "loss": 8.6939,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.1728,
763
+ "grad_norm": 10.38036823272705,
764
+ "learning_rate": 4.683874066490143e-06,
765
+ "loss": 8.8789,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.1744,
770
+ "grad_norm": 10.32800006866455,
771
+ "learning_rate": 4.677660101342536e-06,
772
+ "loss": 8.7128,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.176,
777
+ "grad_norm": 9.01140022277832,
778
+ "learning_rate": 4.671389861654873e-06,
779
+ "loss": 8.5539,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.1776,
784
+ "grad_norm": 10.66911792755127,
785
+ "learning_rate": 4.665063509461098e-06,
786
+ "loss": 8.6381,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.1792,
791
+ "grad_norm": 12.453883171081543,
792
+ "learning_rate": 4.658681208245198e-06,
793
+ "loss": 8.744,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.1808,
798
+ "grad_norm": 10.25079345703125,
799
+ "learning_rate": 4.652243122936987e-06,
800
+ "loss": 8.4376,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.1824,
805
+ "grad_norm": 13.820728302001953,
806
+ "learning_rate": 4.645749419907829e-06,
807
+ "loss": 8.7434,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.184,
812
+ "grad_norm": 9.763056755065918,
813
+ "learning_rate": 4.639200266966351e-06,
814
+ "loss": 8.5522,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.1856,
819
+ "grad_norm": 12.80479907989502,
820
+ "learning_rate": 4.632595833354105e-06,
821
+ "loss": 8.5777,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.1872,
826
+ "grad_norm": 11.518301963806152,
827
+ "learning_rate": 4.625936289741187e-06,
828
+ "loss": 8.2751,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.1888,
833
+ "grad_norm": 13.24626350402832,
834
+ "learning_rate": 4.619221808221833e-06,
835
+ "loss": 8.4951,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.1904,
840
+ "grad_norm": 14.117487907409668,
841
+ "learning_rate": 4.612452562309975e-06,
842
+ "loss": 8.3492,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.192,
847
+ "grad_norm": 12.98033618927002,
848
+ "learning_rate": 4.605628726934747e-06,
849
+ "loss": 8.2238,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.1936,
854
+ "grad_norm": 11.61721420288086,
855
+ "learning_rate": 4.598750478435973e-06,
856
+ "loss": 8.2197,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.1952,
861
+ "grad_norm": 12.619826316833496,
862
+ "learning_rate": 4.5918179945596055e-06,
863
+ "loss": 8.2005,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.1968,
868
+ "grad_norm": 11.586774826049805,
869
+ "learning_rate": 4.584831454453135e-06,
870
+ "loss": 8.0181,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.1984,
875
+ "grad_norm": 11.792032241821289,
876
+ "learning_rate": 4.577791038660959e-06,
877
+ "loss": 8.1414,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.2,
882
+ "grad_norm": 14.116670608520508,
883
+ "learning_rate": 4.570696929119717e-06,
884
+ "loss": 7.9288,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.2016,
889
+ "grad_norm": 13.249540328979492,
890
+ "learning_rate": 4.563549309153589e-06,
891
+ "loss": 7.8991,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.2032,
896
+ "grad_norm": 13.10855770111084,
897
+ "learning_rate": 4.556348363469556e-06,
898
+ "loss": 7.7997,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.2048,
903
+ "grad_norm": 13.13003921508789,
904
+ "learning_rate": 4.549094278152631e-06,
905
+ "loss": 7.7856,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.2064,
910
+ "grad_norm": 11.22130012512207,
911
+ "learning_rate": 4.541787240661049e-06,
912
+ "loss": 7.8092,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.208,
917
+ "grad_norm": 12.641518592834473,
918
+ "learning_rate": 4.534427439821416e-06,
919
+ "loss": 7.6641,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.2096,
924
+ "grad_norm": 12.413702964782715,
925
+ "learning_rate": 4.527015065823841e-06,
926
+ "loss": 7.6125,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.2112,
931
+ "grad_norm": 12.156352043151855,
932
+ "learning_rate": 4.519550310217013e-06,
933
+ "loss": 7.5519,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.2128,
938
+ "grad_norm": 11.665326118469238,
939
+ "learning_rate": 4.512033365903251e-06,
940
+ "loss": 7.5902,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.2144,
945
+ "grad_norm": 12.924529075622559,
946
+ "learning_rate": 4.504464427133527e-06,
947
+ "loss": 7.5706,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.216,
952
+ "grad_norm": 15.648908615112305,
953
+ "learning_rate": 4.496843689502435e-06,
954
+ "loss": 7.3488,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.2176,
959
+ "grad_norm": 13.633544921875,
960
+ "learning_rate": 4.489171349943144e-06,
961
+ "loss": 7.2841,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.2192,
966
+ "grad_norm": 14.129197120666504,
967
+ "learning_rate": 4.481447606722309e-06,
968
+ "loss": 7.2605,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.2208,
973
+ "grad_norm": 15.414569854736328,
974
+ "learning_rate": 4.473672659434941e-06,
975
+ "loss": 7.1375,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.2224,
980
+ "grad_norm": 15.15605640411377,
981
+ "learning_rate": 4.465846708999258e-06,
982
+ "loss": 7.3157,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.224,
987
+ "grad_norm": 13.083776473999023,
988
+ "learning_rate": 4.457969957651485e-06,
989
+ "loss": 7.1391,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.2256,
994
+ "grad_norm": 14.658546447753906,
995
+ "learning_rate": 4.450042608940632e-06,
996
+ "loss": 6.8354,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.2272,
1001
+ "grad_norm": 13.068192481994629,
1002
+ "learning_rate": 4.442064867723236e-06,
1003
+ "loss": 6.9534,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.2288,
1008
+ "grad_norm": 13.683319091796875,
1009
+ "learning_rate": 4.434036940158062e-06,
1010
+ "loss": 6.7263,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.2304,
1015
+ "grad_norm": 12.352782249450684,
1016
+ "learning_rate": 4.425959033700776e-06,
1017
+ "loss": 6.9508,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.232,
1022
+ "grad_norm": 12.934060096740723,
1023
+ "learning_rate": 4.417831357098591e-06,
1024
+ "loss": 6.7608,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.2336,
1029
+ "grad_norm": 10.694926261901855,
1030
+ "learning_rate": 4.409654120384863e-06,
1031
+ "loss": 6.9133,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.2352,
1036
+ "grad_norm": 13.42801570892334,
1037
+ "learning_rate": 4.401427534873669e-06,
1038
+ "loss": 6.2184,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.2368,
1043
+ "grad_norm": 12.629581451416016,
1044
+ "learning_rate": 4.393151813154345e-06,
1045
+ "loss": 6.1405,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.2384,
1050
+ "grad_norm": 9.909472465515137,
1051
+ "learning_rate": 4.384827169085993e-06,
1052
+ "loss": 6.376,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.24,
1057
+ "grad_norm": 9.083218574523926,
1058
+ "learning_rate": 4.3764538177919555e-06,
1059
+ "loss": 6.387,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.2416,
1064
+ "grad_norm": 8.383381843566895,
1065
+ "learning_rate": 4.3680319756542525e-06,
1066
+ "loss": 6.7282,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.2432,
1071
+ "grad_norm": 8.961660385131836,
1072
+ "learning_rate": 4.35956186030799e-06,
1073
+ "loss": 6.2623,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.2448,
1078
+ "grad_norm": 9.286286354064941,
1079
+ "learning_rate": 4.351043690635744e-06,
1080
+ "loss": 6.0499,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.2464,
1085
+ "grad_norm": 9.719377517700195,
1086
+ "learning_rate": 4.3424776867618935e-06,
1087
+ "loss": 6.4369,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.248,
1092
+ "grad_norm": 7.7872700691223145,
1093
+ "learning_rate": 4.333864070046938e-06,
1094
+ "loss": 6.0176,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.2496,
1099
+ "grad_norm": 8.78665828704834,
1100
+ "learning_rate": 4.325203063081776e-06,
1101
+ "loss": 6.0201,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.2512,
1106
+ "grad_norm": 7.898557186126709,
1107
+ "learning_rate": 4.3164948896819535e-06,
1108
+ "loss": 6.1595,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.2528,
1113
+ "grad_norm": 9.21320629119873,
1114
+ "learning_rate": 4.307739774881878e-06,
1115
+ "loss": 6.3917,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.2544,
1120
+ "grad_norm": 6.031705379486084,
1121
+ "learning_rate": 4.298937944929007e-06,
1122
+ "loss": 5.6134,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.256,
1127
+ "grad_norm": 7.0851006507873535,
1128
+ "learning_rate": 4.290089627277998e-06,
1129
+ "loss": 5.4909,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.2576,
1134
+ "grad_norm": 7.172662258148193,
1135
+ "learning_rate": 4.28119505058483e-06,
1136
+ "loss": 6.1213,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.2592,
1141
+ "grad_norm": 7.241125583648682,
1142
+ "learning_rate": 4.2722544447008995e-06,
1143
+ "loss": 5.9029,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.2608,
1148
+ "grad_norm": 6.174571514129639,
1149
+ "learning_rate": 4.263268040667075e-06,
1150
+ "loss": 5.9515,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.2624,
1155
+ "grad_norm": 5.6988935470581055,
1156
+ "learning_rate": 4.254236070707734e-06,
1157
+ "loss": 5.8603,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.264,
1162
+ "grad_norm": 5.242663383483887,
1163
+ "learning_rate": 4.245158768224748e-06,
1164
+ "loss": 5.6214,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.2656,
1169
+ "grad_norm": 5.694828987121582,
1170
+ "learning_rate": 4.236036367791471e-06,
1171
+ "loss": 6.3081,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.2672,
1176
+ "grad_norm": 7.1838788986206055,
1177
+ "learning_rate": 4.226869105146658e-06,
1178
+ "loss": 5.4577,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.2688,
1183
+ "grad_norm": 8.755837440490723,
1184
+ "learning_rate": 4.2176572171883865e-06,
1185
+ "loss": 5.5286,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.2704,
1190
+ "grad_norm": 4.821361064910889,
1191
+ "learning_rate": 4.208400941967928e-06,
1192
+ "loss": 5.8776,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.272,
1197
+ "grad_norm": 5.043092250823975,
1198
+ "learning_rate": 4.199100518683601e-06,
1199
+ "loss": 5.6913,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.2736,
1204
+ "grad_norm": 5.266634941101074,
1205
+ "learning_rate": 4.189756187674584e-06,
1206
+ "loss": 5.8228,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.2752,
1211
+ "grad_norm": 5.798868179321289,
1212
+ "learning_rate": 4.18036819041471e-06,
1213
+ "loss": 5.6908,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.2768,
1218
+ "grad_norm": 5.337583065032959,
1219
+ "learning_rate": 4.170936769506222e-06,
1220
+ "loss": 6.0907,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.2784,
1225
+ "grad_norm": 4.3411102294921875,
1226
+ "learning_rate": 4.161462168673508e-06,
1227
+ "loss": 5.8087,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.28,
1232
+ "grad_norm": 6.649768829345703,
1233
+ "learning_rate": 4.1519446327567995e-06,
1234
+ "loss": 5.2901,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.2816,
1239
+ "grad_norm": 6.4602556228637695,
1240
+ "learning_rate": 4.142384407705846e-06,
1241
+ "loss": 5.274,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.2832,
1246
+ "grad_norm": 5.464128017425537,
1247
+ "learning_rate": 4.132781740573559e-06,
1248
+ "loss": 6.0373,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.2848,
1253
+ "grad_norm": 6.308886528015137,
1254
+ "learning_rate": 4.123136879509626e-06,
1255
+ "loss": 5.2471,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.2864,
1260
+ "grad_norm": 4.4718828201293945,
1261
+ "learning_rate": 4.1134500737541026e-06,
1262
+ "loss": 5.3702,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.288,
1267
+ "grad_norm": 3.863276958465576,
1268
+ "learning_rate": 4.103721573630965e-06,
1269
+ "loss": 5.3922,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.2896,
1274
+ "grad_norm": 4.226170063018799,
1275
+ "learning_rate": 4.093951630541646e-06,
1276
+ "loss": 5.4302,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.2912,
1281
+ "grad_norm": 3.5398764610290527,
1282
+ "learning_rate": 4.084140496958539e-06,
1283
+ "loss": 5.3444,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.2928,
1288
+ "grad_norm": 3.5163183212280273,
1289
+ "learning_rate": 4.074288426418467e-06,
1290
+ "loss": 5.3247,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.2944,
1295
+ "grad_norm": 5.308356761932373,
1296
+ "learning_rate": 4.06439567351614e-06,
1297
+ "loss": 5.6837,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.296,
1302
+ "grad_norm": 3.6820993423461914,
1303
+ "learning_rate": 4.054462493897569e-06,
1304
+ "loss": 5.1638,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.2976,
1309
+ "grad_norm": 3.9401638507843018,
1310
+ "learning_rate": 4.0444891442534615e-06,
1311
+ "loss": 5.498,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.2992,
1316
+ "grad_norm": 5.141748428344727,
1317
+ "learning_rate": 4.034475882312593e-06,
1318
+ "loss": 5.1034,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.3008,
1323
+ "grad_norm": 3.4670636653900146,
1324
+ "learning_rate": 4.024422966835137e-06,
1325
+ "loss": 5.2071,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.3024,
1330
+ "grad_norm": 3.7121994495391846,
1331
+ "learning_rate": 4.014330657605984e-06,
1332
+ "loss": 5.3885,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.304,
1337
+ "grad_norm": 5.863914489746094,
1338
+ "learning_rate": 4.004199215428032e-06,
1339
+ "loss": 5.5361,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.3056,
1344
+ "grad_norm": 3.343780517578125,
1345
+ "learning_rate": 3.994028902115439e-06,
1346
+ "loss": 5.4439,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.3072,
1351
+ "grad_norm": 4.041346073150635,
1352
+ "learning_rate": 3.9838199804868635e-06,
1353
+ "loss": 5.6031,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.3088,
1358
+ "grad_norm": 2.9033005237579346,
1359
+ "learning_rate": 3.973572714358668e-06,
1360
+ "loss": 5.3807,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.3104,
1365
+ "grad_norm": 3.026655435562134,
1366
+ "learning_rate": 3.963287368538105e-06,
1367
+ "loss": 5.6681,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.312,
1372
+ "grad_norm": 5.9403862953186035,
1373
+ "learning_rate": 3.9529642088164736e-06,
1374
+ "loss": 5.1567,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.3136,
1379
+ "grad_norm": 4.5110883712768555,
1380
+ "learning_rate": 3.942603501962249e-06,
1381
+ "loss": 5.3055,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.3152,
1386
+ "grad_norm": 4.24874210357666,
1387
+ "learning_rate": 3.932205515714189e-06,
1388
+ "loss": 5.3806,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.3168,
1393
+ "grad_norm": 4.06620979309082,
1394
+ "learning_rate": 3.92177051877442e-06,
1395
+ "loss": 5.5074,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.3184,
1400
+ "grad_norm": 3.4436845779418945,
1401
+ "learning_rate": 3.9112987808014824e-06,
1402
+ "loss": 5.3936,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.32,
1407
+ "grad_norm": 3.5736324787139893,
1408
+ "learning_rate": 3.900790572403376e-06,
1409
+ "loss": 5.3905,
1410
+ "step": 200
1411
+ }
1412
+ ],
1413
+ "logging_steps": 1,
1414
+ "max_steps": 625,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 1,
1417
+ "save_steps": 200,
1418
+ "stateful_callbacks": {
1419
+ "TrainerControl": {
1420
+ "args": {
1421
+ "should_epoch_stop": false,
1422
+ "should_evaluate": false,
1423
+ "should_log": false,
1424
+ "should_save": true,
1425
+ "should_training_stop": false
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 1.40264337309696e+16,
1431
+ "train_batch_size": 16,
1432
+ "trial_name": null,
1433
+ "trial_params": null
1434
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9c131ec82b7036d80ac9ed64508f14e94126d4e636677cdd51924e8f7bcc41
3
+ size 5905
checkpoint-200/vocab.json ADDED
The diff for this file is too large to render. See raw diff