galakenya commited on
Commit
07f944d
·
verified ·
1 Parent(s): 25b3912

ver1 checkpoint step 3500

Browse files
.gitattributes CHANGED
@@ -83,3 +83,4 @@ ver1_チェックポイント_003100/tokenizer.json filter=lfs diff=lfs merge=lf
83
  ver1_チェックポイント_003200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
  ver1_チェックポイント_003300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
  ver1_チェックポイント_003400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
83
  ver1_チェックポイント_003200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
  ver1_チェックポイント_003300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
  ver1_チェックポイント_003400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
+ ver1_チェックポイント_003500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ver1_チェックポイント_003500/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/gemma-4-E4B-it-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/gemma-4-E4B-it-unsloth-bnb-4bit
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.21.2
ver1_チェックポイント_003500/adapter_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Gemma4ForConditionalGeneration",
7
+ "parent_library": "unsloth_compiled_module_gemma4",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/gemma-4-E4B-it-unsloth-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "kasa_config": null,
20
+ "layer_replication": null,
21
+ "layers_pattern": null,
22
+ "layers_to_transform": null,
23
+ "loftq_config": {},
24
+ "lora_alpha": 32,
25
+ "lora_bias": false,
26
+ "lora_dropout": 0.05,
27
+ "lora_ga_config": null,
28
+ "megatron_config": null,
29
+ "megatron_core": "megatron.core",
30
+ "modules_to_save": null,
31
+ "monteclora_config": null,
32
+ "peft_type": "LORA",
33
+ "peft_version": "0.21.2",
34
+ "qalora_group_size": 16,
35
+ "r": 16,
36
+ "rank_pattern": {},
37
+ "revision": null,
38
+ "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}(?!.*\\.experts\\.\\d)\\..*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
39
+ "target_parameters": null,
40
+ "task_type": "CAUSAL_LM",
41
+ "trainable_token_indices": null,
42
+ "use_bdlora": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false,
46
+ "velora_config": null
47
+ }
ver1_チェックポイント_003500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd74f12db13ec8cd9a4216f07edb3e6d8f4ab2007dd10847f96346117ada8ba
3
+ size 139602808
ver1_チェックポイント_003500/chat_template.jinja ADDED
@@ -0,0 +1,385 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- macro format_parameters(properties, required, filter_keys=false) -%}
2
+ {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
3
+ {%- set ns = namespace(found_first=false) -%}
4
+ {%- for key, value in properties | dictsort -%}
5
+ {%- set add_comma = false -%}
6
+ {%- if not filter_keys or key not in standard_keys -%}
7
+ {%- if ns.found_first %},{% endif -%}
8
+ {%- set ns.found_first = true -%}
9
+ {{ key }}:{
10
+ {%- if value['description'] -%}
11
+ description:<|"|>{{ value['description'] }}<|"|>
12
+ {%- set add_comma = true -%}
13
+ {%- endif -%}
14
+ {%- if value['type'] | upper == 'STRING' -%}
15
+ {%- if value['enum'] -%}
16
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
17
+ enum:{{ format_argument(value['enum']) }}
18
+ {%- endif -%}
19
+ {%- elif value['type'] | upper == 'ARRAY' -%}
20
+ {%- if value['items'] is mapping and value['items'] -%}
21
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
22
+ items:{
23
+ {%- set ns_items = namespace(found_first=false) -%}
24
+ {%- for item_key, item_value in value['items'] | dictsort -%}
25
+ {%- if item_value is not none -%}
26
+ {%- if ns_items.found_first %},{% endif -%}
27
+ {%- set ns_items.found_first = true -%}
28
+ {%- if item_key == 'properties' -%}
29
+ properties:{
30
+ {%- if item_value is mapping -%}
31
+ {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
32
+ {%- endif -%}
33
+ }
34
+ {%- elif item_key == 'required' -%}
35
+ required:[
36
+ {%- for req_item in item_value -%}
37
+ <|"|>{{- req_item -}}<|"|>
38
+ {%- if not loop.last %},{% endif -%}
39
+ {%- endfor -%}
40
+ ]
41
+ {%- elif item_key == 'type' -%}
42
+ {%- if item_value is string -%}
43
+ type:{{ format_argument(item_value | upper) }}
44
+ {%- else -%}
45
+ type:{{ format_argument(item_value | map('upper') | list) }}
46
+ {%- endif -%}
47
+ {%- else -%}
48
+ {{ item_key }}:{{ format_argument(item_value) }}
49
+ {%- endif -%}
50
+ {%- endif -%}
51
+ {%- endfor -%}
52
+ }
53
+ {%- endif -%}
54
+ {%- endif -%}
55
+ {%- if value['nullable'] %}
56
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
57
+ nullable:true
58
+ {%- endif -%}
59
+ {%- if value['type'] | upper == 'OBJECT' -%}
60
+ {%- if value['properties'] is defined and value['properties'] is mapping -%}
61
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
62
+ properties:{
63
+ {{- format_parameters(value['properties'], value['required'] | default([])) -}}
64
+ }
65
+ {%- elif value is mapping -%}
66
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
67
+ properties:{
68
+ {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
69
+ }
70
+ {%- endif -%}
71
+ {%- if value['required'] -%}
72
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
73
+ required:[
74
+ {%- for item in value['required'] | default([]) -%}
75
+ <|"|>{{- item -}}<|"|>
76
+ {%- if not loop.last %},{% endif -%}
77
+ {%- endfor -%}
78
+ ]
79
+ {%- endif -%}
80
+ {%- endif -%}
81
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
82
+ type:<|"|>{{ value['type'] | upper }}<|"|>}
83
+ {%- endif -%}
84
+ {%- endfor -%}
85
+ {%- endmacro -%}
86
+ {%- macro format_function_declaration(tool_data) -%}
87
+ declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
88
+ {%- set params = tool_data['function']['parameters'] -%}
89
+ {%- if params -%}
90
+ ,parameters:{
91
+ {%- if params['properties'] -%}
92
+ properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
93
+ {%- endif -%}
94
+ {%- if params['required'] -%}
95
+ required:[
96
+ {%- for item in params['required'] -%}
97
+ <|"|>{{- item -}}<|"|>
98
+ {{- ',' if not loop.last -}}
99
+ {%- endfor -%}
100
+ ],
101
+ {%- endif -%}
102
+ {%- if params['type'] -%}
103
+ type:<|"|>{{- params['type'] | upper -}}<|"|>}
104
+ {%- endif -%}
105
+ {%- endif -%}
106
+ {%- if 'response' in tool_data['function'] -%}
107
+ {%- set response_declaration = tool_data['function']['response'] -%}
108
+ ,response:{
109
+ {%- if response_declaration['description'] -%}
110
+ description:<|"|>{{- response_declaration['description'] -}}<|"|>,
111
+ {%- endif -%}
112
+ {%- if response_declaration['type'] | upper == 'OBJECT' -%}
113
+ type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
114
+ {%- endif -%}
115
+ {%- endif -%}
116
+ }
117
+ {%- endmacro -%}
118
+ {%- macro format_argument(argument, escape_keys=True) -%}
119
+ {%- if argument is none -%}
120
+ {{- 'null' -}}
121
+ {%- elif argument is string -%}
122
+ {{- '<|"|>' + argument + '<|"|>' -}}
123
+ {%- elif argument is boolean -%}
124
+ {{- 'true' if argument else 'false' -}}
125
+ {%- elif argument is mapping -%}
126
+ {{- '{' -}}
127
+ {%- set ns = namespace(found_first=false) -%}
128
+ {%- for key, value in argument | dictsort -%}
129
+ {%- if ns.found_first %},{% endif -%}
130
+ {%- set ns.found_first = true -%}
131
+ {%- if escape_keys -%}
132
+ {{- '<|"|>' + key + '<|"|>' -}}
133
+ {%- else -%}
134
+ {{- key -}}
135
+ {%- endif -%}
136
+ :{{- format_argument(value, escape_keys=escape_keys) -}}
137
+ {%- endfor -%}
138
+ {{- '}' -}}
139
+ {%- elif argument is sequence -%}
140
+ {{- '[' -}}
141
+ {%- for item in argument -%}
142
+ {{- format_argument(item, escape_keys=escape_keys) -}}
143
+ {%- if not loop.last %},{% endif -%}
144
+ {%- endfor -%}
145
+ {{- ']' -}}
146
+ {%- else -%}
147
+ {{- argument -}}
148
+ {%- endif -%}
149
+ {%- endmacro -%}
150
+ {%- macro strip_thinking(text) -%}
151
+ {%- set ns = namespace(result='') -%}
152
+ {%- for part in text.split('<channel|>') -%}
153
+ {%- if '<|channel>' in part -%}
154
+ {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
155
+ {%- else -%}
156
+ {%- set ns.result = ns.result + part -%}
157
+ {%- endif -%}
158
+ {%- endfor -%}
159
+ {{- ns.result | trim -}}
160
+ {%- endmacro -%}
161
+
162
+ {%- macro format_tool_response_block(tool_name, response) -%}
163
+ {{- '<|tool_response>' -}}
164
+ {%- if response is mapping -%}
165
+ {{- 'response:' + tool_name + '{' -}}
166
+ {%- for key, value in response | dictsort -%}
167
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
168
+ {%- if not loop.last %},{% endif -%}
169
+ {%- endfor -%}
170
+ {{- '}' -}}
171
+ {%- else -%}
172
+ {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
173
+ {%- endif -%}
174
+ {{- '<tool_response|>' -}}
175
+ {%- endmacro -%}
176
+
177
+ {#- ===== SETUP ===== -#}
178
+ {%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
179
+ {%- set loop_messages = messages -%}
180
+ {%- set enable_thinking = enable_thinking | default(false) -%}
181
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
182
+ {{- bos_token -}}
183
+ {#- Handle System/Tool Definitions Block -#}
184
+ {%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
185
+ {{- '<|turn>system\n' -}}
186
+ {#- Inject Thinking token at the very top of the FIRST system turn -#}
187
+ {%- if enable_thinking -%}
188
+ {{- '<|think|>\n' -}}
189
+ {%- set ns.prev_message_type = 'think' -%}
190
+ {%- endif -%}
191
+ {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
192
+ {%- if messages[0]['content'] is string -%}
193
+ {{- messages[0]['content'] | trim -}}
194
+ {%- elif messages[0]['content'] is sequence -%}
195
+ {%- for item in messages[0]['content'] -%}
196
+ {{- item['text'] | trim + ' '-}}
197
+ {%- endfor -%}
198
+ {%- endif -%}
199
+ {%- set loop_messages = messages[1:] -%}
200
+ {%- endif -%}
201
+ {%- if tools -%}
202
+ {%- for tool in tools %}
203
+ {{- '<|tool>' -}}
204
+ {{- format_function_declaration(tool) | trim -}}
205
+ {{- '<tool|>' -}}
206
+ {%- endfor %}
207
+ {%- set ns.prev_message_type = 'tool' -%}
208
+ {%- endif -%}
209
+ {{- '<turn|>\n' -}}
210
+ {%- endif %}
211
+
212
+ {#- Pre-scan: find last user message index for reasoning guard -#}
213
+ {%- set ns_turn = namespace(last_user_idx=-1) -%}
214
+ {%- for i in range(loop_messages | length) -%}
215
+ {%- if loop_messages[i]['role'] == 'user' -%}
216
+ {%- set ns_turn.last_user_idx = i -%}
217
+ {%- endif -%}
218
+ {%- endfor -%}
219
+
220
+ {#- Loop through messages -#}
221
+ {%- for message in loop_messages -%}
222
+ {%- if message['role'] != 'tool' -%}
223
+ {%- set ns.prev_message_type = None -%}
224
+ {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
225
+ {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
226
+ {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
227
+ {%- if not continue_same_model_turn -%}
228
+ {{- '<|turn>' + role + '\n' }}
229
+ {%- endif -%}
230
+
231
+ {#- Render reasoning/reasoning_content as thinking channel -#}
232
+ {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
233
+ {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
234
+ {%- if thinking_text and thinking_gate -%}
235
+ {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
236
+ {%- endif -%}
237
+
238
+ {%- if message.get('tool_calls') -%}
239
+ {%- for tool_call in message.get('tool_calls') -%}
240
+ {%- set function = tool_call['function'] -%}
241
+ {{- '<|tool_call>call:' + function['name'] + '{' -}}
242
+ {%- if function['arguments'] is mapping -%}
243
+ {%- set ns_args = namespace(found_first=false) -%}
244
+ {%- for key, value in function['arguments'] | dictsort -%}
245
+ {%- if ns_args.found_first %},{% endif -%}
246
+ {%- set ns_args.found_first = true -%}
247
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
248
+ {%- endfor -%}
249
+ {%- elif function['arguments'] is none -%}
250
+ {%- elif function['arguments'] is string -%}
251
+ {#- Pre-serialized args (e.g. an OpenAI JSON string). We cannot JSON-parse
252
+ portably in-template, so render non-fatally instead of erroring. Strip an
253
+ outer {...} so it composes with the DSL braces rather than double-wrapping.
254
+ Prefer passing arguments as a mapping for exact Gemma DSL. -#}
255
+ {%- set argstr = function['arguments'] | trim -%}
256
+ {%- if argstr[:1] == '{' and argstr[-1:] == '}' -%}
257
+ {{- argstr[1:-1] -}}
258
+ {%- else -%}
259
+ {{- function['arguments'] -}}
260
+ {%- endif -%}
261
+ {%- endif -%}
262
+ {{- '}<tool_call|>' -}}
263
+ {%- endfor -%}
264
+ {%- set ns.prev_message_type = 'tool_call' -%}
265
+ {%- endif -%}
266
+
267
+ {%- set ns_tr_out = namespace(flag=false) -%}
268
+ {%- if message.get('tool_responses') -%}
269
+ {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
270
+ {%- for tool_response in message.get('tool_responses') -%}
271
+ {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
272
+ {%- set ns_tr_out.flag = true -%}
273
+ {%- set ns.prev_message_type = 'tool_response' -%}
274
+ {%- endfor -%}
275
+ {%- elif message.get('tool_calls') -%}
276
+ {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
277
+ {%- set ns_tool_scan = namespace(stopped=false) -%}
278
+ {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
279
+ {%- if ns_tool_scan.stopped -%}
280
+ {%- elif loop_messages[k]['role'] != 'tool' -%}
281
+ {%- set ns_tool_scan.stopped = true -%}
282
+ {%- else -%}
283
+ {%- set follow = loop_messages[k] -%}
284
+ {#- Resolve tool_call_id to function name -#}
285
+ {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
286
+ {%- for tc in message.get('tool_calls') -%}
287
+ {%- if tc.get('id') == follow.get('tool_call_id') -%}
288
+ {%- set ns_tname.name = tc['function']['name'] -%}
289
+ {%- endif -%}
290
+ {%- endfor -%}
291
+ {#- Handle content as string or content-parts array -#}
292
+ {%- set tool_body = follow.get('content') -%}
293
+ {%- if tool_body is string -%}
294
+ {{- format_tool_response_block(ns_tname.name, tool_body) -}}
295
+ {%- elif tool_body is sequence and tool_body is not string -%}
296
+ {%- set ns_txt = namespace(s='') -%}
297
+ {%- for part in tool_body -%}
298
+ {%- if part.get('type') == 'text' -%}
299
+ {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
300
+ {%- endif -%}
301
+ {%- endfor -%}
302
+ {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
303
+ {%- for part in tool_body -%}
304
+ {%- if part.get('type') in ['image', 'image_url'] -%}
305
+ {{- '<|image|>' -}}
306
+ {%- elif part.get('type') in ['audio', 'input_audio'] -%}
307
+ {{- '<|audio|>' -}}
308
+ {%- elif part.get('type') == 'video' -%}
309
+ {{- '<|video|>' -}}
310
+ {%- endif -%}
311
+ {%- endfor -%}
312
+ {%- else -%}
313
+ {{- format_tool_response_block(ns_tname.name, tool_body) -}}
314
+ {%- endif -%}
315
+ {%- set ns_tr_out.flag = true -%}
316
+ {%- set ns.prev_message_type = 'tool_response' -%}
317
+ {%- endif -%}
318
+ {%- endfor -%}
319
+ {%- endif -%}
320
+
321
+ {%- set captured_content -%}
322
+ {%- if message.get('content') is string -%}
323
+ {%- if role == 'model' -%}
324
+ {{- strip_thinking(message['content']) -}}
325
+ {%- else -%}
326
+ {{- message['content'] | trim -}}
327
+ {%- endif -%}
328
+ {%- elif message.get('content') is sequence -%}
329
+ {%- for item in message['content'] -%}
330
+ {%- if item.get('type') == 'text' -%}
331
+ {%- if role == 'model' -%}
332
+ {{- strip_thinking(item['text']) -}}
333
+ {%- else -%}
334
+ {{- item['text'] | trim -}}
335
+ {%- endif -%}
336
+ {%- elif item.get('type') in ['image', 'image_url'] -%}
337
+ {{- '<|image|>' -}}
338
+ {%- elif item.get('type') in ['audio', 'input_audio'] -%}
339
+ {{- '<|audio|>' -}}
340
+ {%- elif item.get('type') == 'video' -%}
341
+ {{- '<|video|>' -}}
342
+ {%- endif -%}
343
+ {%- endfor -%}
344
+ {%- endif -%}
345
+ {%- endset -%}
346
+
347
+ {{- captured_content -}}
348
+ {%- set has_content = captured_content | trim | length > 0 -%}
349
+
350
+ {#- Forward-scan: find next non-tool message role for continuation detection -#}
351
+ {%- set next_nt = namespace(role=None, found=false) -%}
352
+ {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
353
+ {%- if not next_nt.found -%}
354
+ {%- if loop_messages[j]['role'] != 'tool' -%}
355
+ {%- set next_nt.role = loop_messages[j]['role'] -%}
356
+ {%- set next_nt.found = true -%}
357
+ {%- endif -%}
358
+ {%- endif -%}
359
+ {%- endfor -%}
360
+
361
+ {%- set continues_into_next = (
362
+ role == 'model'
363
+ and next_nt.role == 'assistant'
364
+ and (not message.get('tool_calls') or ns_tr_out.flag)
365
+ ) -%}
366
+
367
+ {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
368
+ {{- '<|tool_response>' -}}
369
+ {%- elif continues_into_next -%}
370
+ {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
371
+ {{- '<turn|>\n' -}}
372
+ {%- endif -%}
373
+
374
+ {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
375
+ {%- set ns.prev_non_tool_role = message['role'] -%}
376
+ {%- endif -%}
377
+ {%- endfor -%}
378
+
379
+ {%- if add_generation_prompt -%}
380
+ {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
381
+ {{- '<|turn>model\n' -}}
382
+ {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
383
+ {{- '<|channel>thought\n' -}}
384
+ {%- endif -%}
385
+ {%- endif -%}
ver1_チェックポイント_003500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa8c4aad343064b1d8afed3b9a6afd84891c5b42b8db5a989c40a624fd53371
3
+ size 71476221
ver1_チェックポイント_003500/processor_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_ms_per_token": 40,
3
+ "audio_seq_length": 750,
4
+ "feature_extractor": {
5
+ "dither": 0.0,
6
+ "feature_extractor_type": "Gemma4AudioFeatureExtractor",
7
+ "feature_size": 128,
8
+ "fft_length": 512,
9
+ "fft_overdrive": false,
10
+ "frame_length": 320,
11
+ "hop_length": 160,
12
+ "input_scale_factor": 1.0,
13
+ "max_frequency": 8000.0,
14
+ "mel_floor": 0.001,
15
+ "min_frequency": 0.0,
16
+ "padding_side": "right",
17
+ "padding_value": 0.0,
18
+ "per_bin_mean": null,
19
+ "per_bin_stddev": null,
20
+ "preemphasis": 0.0,
21
+ "preemphasis_htk_flavor": true,
22
+ "return_attention_mask": true,
23
+ "sampling_rate": 16000
24
+ },
25
+ "image_processor": {
26
+ "do_convert_rgb": true,
27
+ "do_normalize": false,
28
+ "do_rescale": true,
29
+ "do_resize": true,
30
+ "image_mean": [
31
+ 0.0,
32
+ 0.0,
33
+ 0.0
34
+ ],
35
+ "image_processor_type": "Gemma4ImageProcessor",
36
+ "image_seq_length": 280,
37
+ "image_std": [
38
+ 1.0,
39
+ 1.0,
40
+ 1.0
41
+ ],
42
+ "max_soft_tokens": 280,
43
+ "patch_size": 16,
44
+ "pooling_kernel_size": 3,
45
+ "resample": 3,
46
+ "rescale_factor": 0.00392156862745098
47
+ },
48
+ "image_seq_length": 280,
49
+ "processor_class": "Gemma4Processor",
50
+ "video_processor": {
51
+ "do_convert_rgb": true,
52
+ "do_normalize": true,
53
+ "do_rescale": true,
54
+ "do_resize": true,
55
+ "do_sample_frames": true,
56
+ "image_mean": [
57
+ 0.0,
58
+ 0.0,
59
+ 0.0
60
+ ],
61
+ "image_std": [
62
+ 1.0,
63
+ 1.0,
64
+ 1.0
65
+ ],
66
+ "max_soft_tokens": 70,
67
+ "num_frames": 32,
68
+ "patch_size": 16,
69
+ "pooling_kernel_size": 3,
70
+ "resample": 3,
71
+ "rescale_factor": 0.00392156862745098,
72
+ "return_metadata": false,
73
+ "video_processor_type": "Gemma4VideoProcessor"
74
+ }
75
+ }
ver1_チェックポイント_003500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff429fd4f4ed331299fec94976f55f10ec1c3ebc3aa2549edae32395bf76a3f
3
+ size 14645
ver1_チェックポイント_003500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8313d764f477e7f93b448daf4f9ddd62c1e5877d004145696a631f708683cef
3
+ size 1465
ver1_チェックポイント_003500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
+ size 32169626
ver1_チェックポイント_003500/tokenizer_config.json ADDED
@@ -0,0 +1,290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|audio|>",
3
+ "backend": "tokenizers",
4
+ "boa_token": "<|audio>",
5
+ "boi_token": "<|image>",
6
+ "bos_token": "<bos>",
7
+ "eoa_token": "<audio|>",
8
+ "eoc_token": "<channel|>",
9
+ "eoi_token": "<image|>",
10
+ "eos_token": "<eos>",
11
+ "eot_token": "<turn|>",
12
+ "escape_token": "<|\"|>",
13
+ "etc_token": "<tool_call|>",
14
+ "etd_token": "<tool|>",
15
+ "etr_token": "<tool_response|>",
16
+ "extra_special_tokens": [
17
+ "<|video|>"
18
+ ],
19
+ "image_token": "<|image|>",
20
+ "is_local": false,
21
+ "local_files_only": false,
22
+ "mask_token": "<mask>",
23
+ "model_max_length": 131072,
24
+ "model_specific_special_tokens": {
25
+ "audio_token": "<|audio|>",
26
+ "boa_token": "<|audio>",
27
+ "boi_token": "<|image>",
28
+ "eoa_token": "<audio|>",
29
+ "eoc_token": "<channel|>",
30
+ "eoi_token": "<image|>",
31
+ "eot_token": "<turn|>",
32
+ "escape_token": "<|\"|>",
33
+ "etc_token": "<tool_call|>",
34
+ "etd_token": "<tool|>",
35
+ "etr_token": "<tool_response|>",
36
+ "image_token": "<|image|>",
37
+ "soc_token": "<|channel>",
38
+ "sot_token": "<|turn>",
39
+ "stc_token": "<|tool_call>",
40
+ "std_token": "<|tool>",
41
+ "str_token": "<|tool_response>",
42
+ "think_token": "<|think|>"
43
+ },
44
+ "pad_token": "<pad>",
45
+ "padding_side": "right",
46
+ "processor_class": "Gemma4Processor",
47
+ "response_schema": {
48
+ "properties": {
49
+ "content": {
50
+ "type": "string"
51
+ },
52
+ "role": {
53
+ "const": "assistant"
54
+ },
55
+ "thinking": {
56
+ "type": "string"
57
+ },
58
+ "tool_calls": {
59
+ "items": {
60
+ "properties": {
61
+ "function": {
62
+ "properties": {
63
+ "arguments": {
64
+ "additionalProperties": {},
65
+ "type": "object",
66
+ "x-parser": "gemma4-tool-call"
67
+ },
68
+ "name": {
69
+ "type": "string"
70
+ }
71
+ },
72
+ "type": "object",
73
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
74
+ },
75
+ "type": {
76
+ "const": "function"
77
+ }
78
+ },
79
+ "type": "object"
80
+ },
81
+ "type": "array",
82
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
83
+ }
84
+ },
85
+ "type": "object",
86
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
87
+ },
88
+ "soc_token": "<|channel>",
89
+ "sot_token": "<|turn>",
90
+ "stc_token": "<|tool_call>",
91
+ "std_token": "<|tool>",
92
+ "str_token": "<|tool_response>",
93
+ "think_token": "<|think|>",
94
+ "tokenizer_class": "GemmaTokenizer",
95
+ "unk_token": "<unk>",
96
+ "added_tokens_decoder": {
97
+ "0": {
98
+ "content": "<pad>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "1": {
106
+ "content": "<eos>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "2": {
114
+ "content": "<bos>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "3": {
122
+ "content": "<unk>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "4": {
130
+ "content": "<mask>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": true
136
+ },
137
+ "46": {
138
+ "content": "<|tool>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": true
144
+ },
145
+ "47": {
146
+ "content": "<tool|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": true
152
+ },
153
+ "48": {
154
+ "content": "<|tool_call>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": true
160
+ },
161
+ "49": {
162
+ "content": "<tool_call|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": true
168
+ },
169
+ "50": {
170
+ "content": "<|tool_response>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ "51": {
178
+ "content": "<tool_response|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": true
184
+ },
185
+ "52": {
186
+ "content": "<|\"|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": true
192
+ },
193
+ "98": {
194
+ "content": "<|think|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ },
201
+ "100": {
202
+ "content": "<|channel>",
203
+ "single_word": false,
204
+ "lstrip": false,
205
+ "rstrip": false,
206
+ "normalized": false,
207
+ "special": true
208
+ },
209
+ "101": {
210
+ "content": "<channel|>",
211
+ "single_word": false,
212
+ "lstrip": false,
213
+ "rstrip": false,
214
+ "normalized": false,
215
+ "special": true
216
+ },
217
+ "105": {
218
+ "content": "<|turn>",
219
+ "single_word": false,
220
+ "lstrip": false,
221
+ "rstrip": false,
222
+ "normalized": false,
223
+ "special": true
224
+ },
225
+ "106": {
226
+ "content": "<turn|>",
227
+ "single_word": false,
228
+ "lstrip": false,
229
+ "rstrip": false,
230
+ "normalized": false,
231
+ "special": true
232
+ },
233
+ "255999": {
234
+ "content": "<|image>",
235
+ "single_word": false,
236
+ "lstrip": false,
237
+ "rstrip": false,
238
+ "normalized": false,
239
+ "special": true
240
+ },
241
+ "256000": {
242
+ "content": "<|audio>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ "258880": {
250
+ "content": "<|image|>",
251
+ "single_word": false,
252
+ "lstrip": false,
253
+ "rstrip": false,
254
+ "normalized": false,
255
+ "special": true
256
+ },
257
+ "258881": {
258
+ "content": "<|audio|>",
259
+ "single_word": false,
260
+ "lstrip": false,
261
+ "rstrip": false,
262
+ "normalized": false,
263
+ "special": true
264
+ },
265
+ "258882": {
266
+ "content": "<image|>",
267
+ "single_word": false,
268
+ "lstrip": false,
269
+ "rstrip": false,
270
+ "normalized": false,
271
+ "special": true
272
+ },
273
+ "258883": {
274
+ "content": "<audio|>",
275
+ "single_word": false,
276
+ "lstrip": false,
277
+ "rstrip": false,
278
+ "normalized": false,
279
+ "special": true
280
+ },
281
+ "258884": {
282
+ "content": "<|video|>",
283
+ "single_word": false,
284
+ "lstrip": false,
285
+ "rstrip": false,
286
+ "normalized": false,
287
+ "special": true
288
+ }
289
+ }
290
+ }
ver1_チェックポイント_003500/trainer_state.json ADDED
@@ -0,0 +1,2484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.434011476264997,
6
+ "eval_steps": 500,
7
+ "global_step": 3500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006955312119631368,
14
+ "grad_norm": 2.5689611434936523,
15
+ "learning_rate": 1.2e-05,
16
+ "loss": 3.2736179351806642,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.013910624239262736,
21
+ "grad_norm": 2.358407497406006,
22
+ "learning_rate": 2.5333333333333337e-05,
23
+ "loss": 2.7794118881225587,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.020865936358894107,
28
+ "grad_norm": 1.2953909635543823,
29
+ "learning_rate": 3.866666666666667e-05,
30
+ "loss": 1.995354461669922,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.027821248478525473,
35
+ "grad_norm": 0.9204198718070984,
36
+ "learning_rate": 5.2000000000000004e-05,
37
+ "loss": 1.4715784072875977,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03477656059815684,
42
+ "grad_norm": 0.8389095067977905,
43
+ "learning_rate": 6.533333333333334e-05,
44
+ "loss": 1.274854564666748,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.041731872717788214,
49
+ "grad_norm": 0.8222324848175049,
50
+ "learning_rate": 7.866666666666666e-05,
51
+ "loss": 1.1893898963928222,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.04868718483741958,
56
+ "grad_norm": 0.7203124761581421,
57
+ "learning_rate": 9.200000000000001e-05,
58
+ "loss": 1.2164156913757325,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.055642496957050945,
63
+ "grad_norm": 0.819334089756012,
64
+ "learning_rate": 0.00010533333333333332,
65
+ "loss": 1.1143546104431152,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.06259780907668232,
70
+ "grad_norm": 0.8617242574691772,
71
+ "learning_rate": 0.00011866666666666669,
72
+ "loss": 1.1660587310791015,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.06955312119631368,
77
+ "grad_norm": 0.7527297139167786,
78
+ "learning_rate": 0.000132,
79
+ "loss": 1.1674225807189942,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.07650843331594505,
84
+ "grad_norm": 0.685824453830719,
85
+ "learning_rate": 0.00014533333333333333,
86
+ "loss": 1.1638391494750977,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.08346374543557643,
91
+ "grad_norm": 0.7432055473327637,
92
+ "learning_rate": 0.00015866666666666668,
93
+ "loss": 1.0316104888916016,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.0904190575552078,
98
+ "grad_norm": 0.7189971804618835,
99
+ "learning_rate": 0.000172,
100
+ "loss": 1.137915802001953,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.09737436967483916,
105
+ "grad_norm": 0.650836706161499,
106
+ "learning_rate": 0.00018533333333333333,
107
+ "loss": 1.1198050498962402,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.10432968179447052,
112
+ "grad_norm": 0.7262141108512878,
113
+ "learning_rate": 0.00019866666666666668,
114
+ "loss": 1.107395076751709,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.11128499391410189,
119
+ "grad_norm": 0.7656242251396179,
120
+ "learning_rate": 0.0001998481012658228,
121
+ "loss": 1.0943047523498535,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.11824030603373327,
126
+ "grad_norm": 0.6663755178451538,
127
+ "learning_rate": 0.00019967932489451477,
128
+ "loss": 1.1017122268676758,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.12519561815336464,
133
+ "grad_norm": 0.7338438630104065,
134
+ "learning_rate": 0.00019951054852320677,
135
+ "loss": 1.1233152389526366,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.13215093027299601,
140
+ "grad_norm": 0.6965685486793518,
141
+ "learning_rate": 0.00019934177215189875,
142
+ "loss": 1.0628890991210938,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.13910624239262737,
147
+ "grad_norm": 0.7198728322982788,
148
+ "learning_rate": 0.00019917299578059073,
149
+ "loss": 1.0607861518859862,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.14606155451225875,
154
+ "grad_norm": 0.6506631374359131,
155
+ "learning_rate": 0.0001990042194092827,
156
+ "loss": 1.1210803985595703,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.1530168666318901,
161
+ "grad_norm": 0.742662787437439,
162
+ "learning_rate": 0.0001988354430379747,
163
+ "loss": 1.055866813659668,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.15997217875152148,
168
+ "grad_norm": 0.6656678318977356,
169
+ "learning_rate": 0.00019866666666666668,
170
+ "loss": 1.0802669525146484,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.16692749087115286,
175
+ "grad_norm": 0.7158327102661133,
176
+ "learning_rate": 0.00019849789029535866,
177
+ "loss": 1.0285625457763672,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.1738828029907842,
182
+ "grad_norm": 0.6634556651115417,
183
+ "learning_rate": 0.00019832911392405066,
184
+ "loss": 1.1023624420166016,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.1808381151104156,
189
+ "grad_norm": 0.6905118823051453,
190
+ "learning_rate": 0.00019816033755274263,
191
+ "loss": 1.0354464530944825,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.18779342723004694,
196
+ "grad_norm": 0.6574810147285461,
197
+ "learning_rate": 0.0001979915611814346,
198
+ "loss": 1.062155532836914,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.19474873934967832,
203
+ "grad_norm": 0.6632050275802612,
204
+ "learning_rate": 0.00019782278481012659,
205
+ "loss": 1.0544384956359862,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.2017040514693097,
210
+ "grad_norm": 0.7181679606437683,
211
+ "learning_rate": 0.0001976540084388186,
212
+ "loss": 1.0690808296203613,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.20865936358894105,
217
+ "grad_norm": 0.711899995803833,
218
+ "learning_rate": 0.00019748523206751054,
219
+ "loss": 1.045906162261963,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.21561467570857243,
224
+ "grad_norm": 0.7319942712783813,
225
+ "learning_rate": 0.00019731645569620254,
226
+ "loss": 1.0785978317260743,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.22256998782820378,
231
+ "grad_norm": 0.6403973698616028,
232
+ "learning_rate": 0.00019714767932489454,
233
+ "loss": 1.0231115341186523,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.22952529994783516,
238
+ "grad_norm": 0.7108656167984009,
239
+ "learning_rate": 0.0001969789029535865,
240
+ "loss": 1.064862060546875,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.23648061206746654,
245
+ "grad_norm": 0.7077785134315491,
246
+ "learning_rate": 0.0001968101265822785,
247
+ "loss": 1.0418540954589843,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.2434359241870979,
252
+ "grad_norm": 0.6278745532035828,
253
+ "learning_rate": 0.00019664135021097047,
254
+ "loss": 1.0774271011352539,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.25039123630672927,
259
+ "grad_norm": 0.6913341879844666,
260
+ "learning_rate": 0.00019647257383966247,
261
+ "loss": 1.0205010414123534,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.2573465484263606,
266
+ "grad_norm": 0.7633867859840393,
267
+ "learning_rate": 0.00019630379746835442,
268
+ "loss": 1.0541458129882812,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.26430186054599203,
273
+ "grad_norm": 0.654975175857544,
274
+ "learning_rate": 0.00019613502109704642,
275
+ "loss": 1.0823522567749024,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.2712571726656234,
280
+ "grad_norm": 0.699618399143219,
281
+ "learning_rate": 0.0001959662447257384,
282
+ "loss": 1.0542631149291992,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.27821248478525473,
287
+ "grad_norm": 0.7587635517120361,
288
+ "learning_rate": 0.00019579746835443038,
289
+ "loss": 1.0430459022521972,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.2851677969048861,
294
+ "grad_norm": 0.6308871507644653,
295
+ "learning_rate": 0.00019562869198312238,
296
+ "loss": 1.0504680633544923,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.2921231090245175,
301
+ "grad_norm": 0.6859050989151001,
302
+ "learning_rate": 0.00019545991561181435,
303
+ "loss": 1.0914113998413086,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.29907842114414884,
308
+ "grad_norm": 0.8366039395332336,
309
+ "learning_rate": 0.00019529113924050636,
310
+ "loss": 1.0526187896728516,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.3060337332637802,
315
+ "grad_norm": 0.7210771441459656,
316
+ "learning_rate": 0.0001951223628691983,
317
+ "loss": 1.0170553207397461,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.3129890453834116,
322
+ "grad_norm": 0.6550219655036926,
323
+ "learning_rate": 0.0001949535864978903,
324
+ "loss": 1.055061435699463,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.31994435750304295,
329
+ "grad_norm": 0.6426383852958679,
330
+ "learning_rate": 0.00019478481012658228,
331
+ "loss": 1.068690013885498,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.3268996696226743,
336
+ "grad_norm": 0.7324220538139343,
337
+ "learning_rate": 0.00019461603375527426,
338
+ "loss": 1.0737545967102051,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.3338549817423057,
343
+ "grad_norm": 0.6725090146064758,
344
+ "learning_rate": 0.00019444725738396626,
345
+ "loss": 1.039157009124756,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.34081029386193706,
350
+ "grad_norm": 0.7014487385749817,
351
+ "learning_rate": 0.00019427848101265824,
352
+ "loss": 1.0449015617370605,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.3477656059815684,
357
+ "grad_norm": 0.6932429075241089,
358
+ "learning_rate": 0.00019410970464135021,
359
+ "loss": 1.0267159461975097,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.35472091810119977,
364
+ "grad_norm": 0.7019017338752747,
365
+ "learning_rate": 0.0001939409282700422,
366
+ "loss": 1.0293694496154786,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.3616762302208312,
371
+ "grad_norm": 0.79600989818573,
372
+ "learning_rate": 0.0001937721518987342,
373
+ "loss": 1.0764266014099122,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.3686315423404625,
378
+ "grad_norm": 0.6795210838317871,
379
+ "learning_rate": 0.00019360337552742617,
380
+ "loss": 1.0452237129211426,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.3755868544600939,
385
+ "grad_norm": 0.6737793684005737,
386
+ "learning_rate": 0.00019343459915611814,
387
+ "loss": 0.9874402046203613,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.3825421665797253,
392
+ "grad_norm": 0.6975118517875671,
393
+ "learning_rate": 0.00019326582278481015,
394
+ "loss": 0.9805720329284668,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.38949747869935664,
399
+ "grad_norm": 0.6965228915214539,
400
+ "learning_rate": 0.00019309704641350212,
401
+ "loss": 1.0688130378723144,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.396452790818988,
406
+ "grad_norm": 0.7011892199516296,
407
+ "learning_rate": 0.0001929282700421941,
408
+ "loss": 1.0480402946472167,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.4034081029386194,
413
+ "grad_norm": 0.7129418253898621,
414
+ "learning_rate": 0.00019275949367088607,
415
+ "loss": 1.0300256729125976,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.41036341505825075,
420
+ "grad_norm": 0.7415669560432434,
421
+ "learning_rate": 0.00019259071729957808,
422
+ "loss": 1.0135790824890136,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.4173187271778821,
427
+ "grad_norm": 0.6726159453392029,
428
+ "learning_rate": 0.00019242194092827005,
429
+ "loss": 1.0762321472167968,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.42427403929751345,
434
+ "grad_norm": 0.7908839583396912,
435
+ "learning_rate": 0.00019225316455696203,
436
+ "loss": 1.0107322692871095,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.43122935141714486,
441
+ "grad_norm": 0.7176574468612671,
442
+ "learning_rate": 0.00019208438818565403,
443
+ "loss": 1.018742561340332,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.4381846635367762,
448
+ "grad_norm": 0.7431163191795349,
449
+ "learning_rate": 0.000191915611814346,
450
+ "loss": 1.007265567779541,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.44513997565640756,
455
+ "grad_norm": 0.6880275011062622,
456
+ "learning_rate": 0.00019174683544303798,
457
+ "loss": 0.9858497619628906,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.45209528777603897,
462
+ "grad_norm": 0.6775235533714294,
463
+ "learning_rate": 0.00019157805907172996,
464
+ "loss": 1.0272439956665038,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.4590505998956703,
469
+ "grad_norm": 0.6979907751083374,
470
+ "learning_rate": 0.00019140928270042196,
471
+ "loss": 1.0002799034118652,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.46600591201530167,
476
+ "grad_norm": 0.7133551239967346,
477
+ "learning_rate": 0.00019124050632911394,
478
+ "loss": 1.0333858489990235,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.4729612241349331,
483
+ "grad_norm": 0.7361565828323364,
484
+ "learning_rate": 0.0001910717299578059,
485
+ "loss": 1.037066650390625,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.47991653625456443,
490
+ "grad_norm": 0.6671329736709595,
491
+ "learning_rate": 0.00019090295358649791,
492
+ "loss": 1.0284708976745605,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.4868718483741958,
497
+ "grad_norm": 0.6883540153503418,
498
+ "learning_rate": 0.0001907341772151899,
499
+ "loss": 1.0641100883483887,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.49382716049382713,
504
+ "grad_norm": 0.6723079681396484,
505
+ "learning_rate": 0.00019056540084388187,
506
+ "loss": 0.9844527244567871,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.5007824726134585,
511
+ "grad_norm": 0.6597151756286621,
512
+ "learning_rate": 0.00019039662447257384,
513
+ "loss": 1.0208508491516113,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.50773778473309,
518
+ "grad_norm": 0.7929419875144958,
519
+ "learning_rate": 0.00019022784810126584,
520
+ "loss": 1.0609599113464356,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.5146930968527212,
525
+ "grad_norm": 0.699404239654541,
526
+ "learning_rate": 0.0001900590717299578,
527
+ "loss": 0.9934878349304199,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.5216484089723527,
532
+ "grad_norm": 0.6972230672836304,
533
+ "learning_rate": 0.0001898902953586498,
534
+ "loss": 1.0086451530456544,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.5286037210919841,
539
+ "grad_norm": 0.7111150622367859,
540
+ "learning_rate": 0.00018972151898734177,
541
+ "loss": 1.0285116195678712,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.5355590332116154,
546
+ "grad_norm": 0.6716212630271912,
547
+ "learning_rate": 0.00018955274261603377,
548
+ "loss": 1.004267978668213,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.5425143453312468,
553
+ "grad_norm": 0.7217034101486206,
554
+ "learning_rate": 0.00018938396624472575,
555
+ "loss": 0.9815131187438965,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.5494696574508781,
560
+ "grad_norm": 0.7378183603286743,
561
+ "learning_rate": 0.00018921518987341773,
562
+ "loss": 1.0401283264160157,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.5564249695705095,
567
+ "grad_norm": 0.7384382486343384,
568
+ "learning_rate": 0.00018904641350210973,
569
+ "loss": 1.0970406532287598,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.5633802816901409,
574
+ "grad_norm": 0.6921862959861755,
575
+ "learning_rate": 0.00018887763713080168,
576
+ "loss": 1.0254897117614745,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.5703355938097722,
581
+ "grad_norm": 0.7535673379898071,
582
+ "learning_rate": 0.00018870886075949368,
583
+ "loss": 1.0314074516296388,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.5772909059294036,
588
+ "grad_norm": 0.652815580368042,
589
+ "learning_rate": 0.00018854008438818566,
590
+ "loss": 1.0131328582763672,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.584246218049035,
595
+ "grad_norm": 0.7734778523445129,
596
+ "learning_rate": 0.00018837130801687766,
597
+ "loss": 1.0127121925354003,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.5912015301686663,
602
+ "grad_norm": 0.6989406943321228,
603
+ "learning_rate": 0.00018820253164556963,
604
+ "loss": 0.9736420631408691,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.5981568422882977,
609
+ "grad_norm": 0.7227122783660889,
610
+ "learning_rate": 0.0001880337552742616,
611
+ "loss": 0.9589074134826661,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.6051121544079291,
616
+ "grad_norm": 0.7336807250976562,
617
+ "learning_rate": 0.0001878649789029536,
618
+ "loss": 0.9796842575073242,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.6120674665275604,
623
+ "grad_norm": 0.737108051776886,
624
+ "learning_rate": 0.00018769620253164556,
625
+ "loss": 0.9858989715576172,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.6190227786471918,
630
+ "grad_norm": 0.6772929430007935,
631
+ "learning_rate": 0.00018752742616033756,
632
+ "loss": 0.9919609069824219,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.6259780907668232,
637
+ "grad_norm": 0.6902018189430237,
638
+ "learning_rate": 0.00018735864978902954,
639
+ "loss": 1.095651626586914,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.6329334028864545,
644
+ "grad_norm": 0.6939515471458435,
645
+ "learning_rate": 0.00018718987341772152,
646
+ "loss": 1.0111848831176757,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.6398887150060859,
651
+ "grad_norm": 0.658412516117096,
652
+ "learning_rate": 0.00018702109704641352,
653
+ "loss": 1.035792636871338,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.6468440271257173,
658
+ "grad_norm": 0.6250536441802979,
659
+ "learning_rate": 0.0001868523206751055,
660
+ "loss": 0.9496813774108886,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.6537993392453486,
665
+ "grad_norm": 0.7852034568786621,
666
+ "learning_rate": 0.0001866835443037975,
667
+ "loss": 0.9743531227111817,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.66075465136498,
672
+ "grad_norm": 0.6914832592010498,
673
+ "learning_rate": 0.00018651476793248945,
674
+ "loss": 0.967257308959961,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.6677099634846114,
679
+ "grad_norm": 0.6870492100715637,
680
+ "learning_rate": 0.00018634599156118145,
681
+ "loss": 0.9862551689147949,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.6746652756042427,
686
+ "grad_norm": 0.7478212118148804,
687
+ "learning_rate": 0.00018617721518987342,
688
+ "loss": 0.9838774681091309,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.6816205877238741,
693
+ "grad_norm": 0.7431444525718689,
694
+ "learning_rate": 0.0001860084388185654,
695
+ "loss": 1.0186484336853028,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.6885758998435054,
700
+ "grad_norm": 0.778145968914032,
701
+ "learning_rate": 0.0001858396624472574,
702
+ "loss": 0.9847902297973633,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.6955312119631368,
707
+ "grad_norm": 0.7628706097602844,
708
+ "learning_rate": 0.00018567088607594938,
709
+ "loss": 0.9746822357177735,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.7024865240827682,
714
+ "grad_norm": 0.7503296732902527,
715
+ "learning_rate": 0.00018550210970464138,
716
+ "loss": 0.9667131423950195,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.7094418362023995,
721
+ "grad_norm": 0.6973724961280823,
722
+ "learning_rate": 0.00018533333333333333,
723
+ "loss": 0.983030128479004,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.7163971483220309,
728
+ "grad_norm": 0.8070515394210815,
729
+ "learning_rate": 0.00018516455696202533,
730
+ "loss": 1.012954330444336,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.7233524604416623,
735
+ "grad_norm": 0.7381730675697327,
736
+ "learning_rate": 0.0001849957805907173,
737
+ "loss": 1.021426296234131,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.7303077725612936,
742
+ "grad_norm": 0.6866867542266846,
743
+ "learning_rate": 0.00018482700421940928,
744
+ "loss": 1.0031105995178222,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.737263084680925,
749
+ "grad_norm": 0.7017723917961121,
750
+ "learning_rate": 0.00018465822784810126,
751
+ "loss": 0.9910454750061035,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.7442183968005565,
756
+ "grad_norm": 0.7817910313606262,
757
+ "learning_rate": 0.00018448945147679326,
758
+ "loss": 1.0011183738708496,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.7511737089201878,
763
+ "grad_norm": 0.7518728375434875,
764
+ "learning_rate": 0.00018432067510548524,
765
+ "loss": 0.959147834777832,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.7581290210398192,
770
+ "grad_norm": 0.6951069235801697,
771
+ "learning_rate": 0.00018415189873417721,
772
+ "loss": 1.0057799339294433,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.7650843331594506,
777
+ "grad_norm": 0.7310563325881958,
778
+ "learning_rate": 0.00018398312236286922,
779
+ "loss": 0.977109718322754,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.7720396452790819,
784
+ "grad_norm": 0.6902674436569214,
785
+ "learning_rate": 0.0001838143459915612,
786
+ "loss": 0.9848337173461914,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.7789949573987133,
791
+ "grad_norm": 0.7025310397148132,
792
+ "learning_rate": 0.00018364556962025317,
793
+ "loss": 0.9895707130432129,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.7859502695183447,
798
+ "grad_norm": 0.7787452340126038,
799
+ "learning_rate": 0.00018347679324894514,
800
+ "loss": 1.0414064407348633,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.792905581637976,
805
+ "grad_norm": 0.7418888807296753,
806
+ "learning_rate": 0.00018330801687763715,
807
+ "loss": 1.0119781494140625,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.7998608937576074,
812
+ "grad_norm": 0.7811972498893738,
813
+ "learning_rate": 0.00018313924050632912,
814
+ "loss": 0.9952075004577636,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.8068162058772388,
819
+ "grad_norm": 0.6702955365180969,
820
+ "learning_rate": 0.0001829704641350211,
821
+ "loss": 1.0394928932189942,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.8137715179968701,
826
+ "grad_norm": 0.8013330101966858,
827
+ "learning_rate": 0.0001828016877637131,
828
+ "loss": 0.9788262367248535,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.8207268301165015,
833
+ "grad_norm": 0.8121411204338074,
834
+ "learning_rate": 0.00018263291139240508,
835
+ "loss": 0.9843114852905274,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.8276821422361329,
840
+ "grad_norm": 0.6926175951957703,
841
+ "learning_rate": 0.00018246413502109705,
842
+ "loss": 1.0314296722412108,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.8346374543557642,
847
+ "grad_norm": 0.7113053202629089,
848
+ "learning_rate": 0.00018229535864978903,
849
+ "loss": 1.0438224792480468,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.8415927664753956,
854
+ "grad_norm": 0.7747524380683899,
855
+ "learning_rate": 0.00018212658227848103,
856
+ "loss": 1.0086687088012696,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.8485480785950269,
861
+ "grad_norm": 0.7961917519569397,
862
+ "learning_rate": 0.000181957805907173,
863
+ "loss": 0.9518073081970215,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.8555033907146583,
868
+ "grad_norm": 0.7584196329116821,
869
+ "learning_rate": 0.00018178902953586498,
870
+ "loss": 0.9608857154846191,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.8624587028342897,
875
+ "grad_norm": 0.7338631749153137,
876
+ "learning_rate": 0.00018162025316455698,
877
+ "loss": 0.9861344337463379,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.869414014953921,
882
+ "grad_norm": 0.7941583395004272,
883
+ "learning_rate": 0.00018145147679324896,
884
+ "loss": 0.9655341148376465,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.8763693270735524,
889
+ "grad_norm": 0.7326560616493225,
890
+ "learning_rate": 0.00018128270042194094,
891
+ "loss": 0.9644174575805664,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.8833246391931838,
896
+ "grad_norm": 0.7826064825057983,
897
+ "learning_rate": 0.0001811139240506329,
898
+ "loss": 0.9907812118530274,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.8902799513128151,
903
+ "grad_norm": 0.7436262369155884,
904
+ "learning_rate": 0.00018094514767932491,
905
+ "loss": 1.033156394958496,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.8972352634324465,
910
+ "grad_norm": 0.7738462686538696,
911
+ "learning_rate": 0.0001807763713080169,
912
+ "loss": 0.9792445182800293,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.9041905755520779,
917
+ "grad_norm": 0.7430145740509033,
918
+ "learning_rate": 0.00018060759493670887,
919
+ "loss": 1.0043703079223634,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.9111458876717092,
924
+ "grad_norm": 0.7590253353118896,
925
+ "learning_rate": 0.00018043881856540087,
926
+ "loss": 0.9803367614746094,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.9181011997913406,
931
+ "grad_norm": 0.7409432530403137,
932
+ "learning_rate": 0.00018027004219409282,
933
+ "loss": 0.975667667388916,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.925056511910972,
938
+ "grad_norm": 0.7286746501922607,
939
+ "learning_rate": 0.00018010126582278482,
940
+ "loss": 0.9613946914672852,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.9320118240306033,
945
+ "grad_norm": 0.709457516670227,
946
+ "learning_rate": 0.0001799324894514768,
947
+ "loss": 0.9674567222595215,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.9389671361502347,
952
+ "grad_norm": 0.7827386260032654,
953
+ "learning_rate": 0.0001797637130801688,
954
+ "loss": 0.9480515480041504,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.9459224482698662,
959
+ "grad_norm": 0.693313717842102,
960
+ "learning_rate": 0.00017959493670886077,
961
+ "loss": 0.9328170776367187,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.9528777603894975,
966
+ "grad_norm": 0.7720127701759338,
967
+ "learning_rate": 0.00017942616033755275,
968
+ "loss": 0.9636541366577148,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.9598330725091289,
973
+ "grad_norm": 0.7765918970108032,
974
+ "learning_rate": 0.00017925738396624475,
975
+ "loss": 0.961695384979248,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.9667883846287603,
980
+ "grad_norm": 0.7541974186897278,
981
+ "learning_rate": 0.0001790886075949367,
982
+ "loss": 0.9822391510009766,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.9737436967483916,
987
+ "grad_norm": 0.7650076746940613,
988
+ "learning_rate": 0.0001789198312236287,
989
+ "loss": 0.9929092407226563,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.980699008868023,
994
+ "grad_norm": 0.6961168646812439,
995
+ "learning_rate": 0.00017875105485232068,
996
+ "loss": 0.9876113891601562,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.9876543209876543,
1001
+ "grad_norm": 0.7307097911834717,
1002
+ "learning_rate": 0.00017858227848101268,
1003
+ "loss": 1.0374473571777343,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.9946096331072857,
1008
+ "grad_norm": 0.7132730484008789,
1009
+ "learning_rate": 0.00017841350210970463,
1010
+ "loss": 0.9325342178344727,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 1.0013910624239262,
1015
+ "grad_norm": 0.6697813272476196,
1016
+ "learning_rate": 0.00017824472573839663,
1017
+ "loss": 0.9953948974609375,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 1.0083463745435577,
1022
+ "grad_norm": 0.766901969909668,
1023
+ "learning_rate": 0.0001780759493670886,
1024
+ "loss": 0.8017763137817383,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 1.015301686663189,
1029
+ "grad_norm": 0.8726602792739868,
1030
+ "learning_rate": 0.00017790717299578059,
1031
+ "loss": 0.8333577156066895,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 1.0222569987828203,
1036
+ "grad_norm": 0.8348997831344604,
1037
+ "learning_rate": 0.0001777383966244726,
1038
+ "loss": 0.8269458770751953,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 1.0292123109024518,
1043
+ "grad_norm": 0.7410646677017212,
1044
+ "learning_rate": 0.00017756962025316456,
1045
+ "loss": 0.8066329956054688,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 1.036167623022083,
1050
+ "grad_norm": 0.7894912362098694,
1051
+ "learning_rate": 0.00017740084388185654,
1052
+ "loss": 0.8469079017639161,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 1.0431229351417144,
1057
+ "grad_norm": 0.8192129731178284,
1058
+ "learning_rate": 0.00017723206751054852,
1059
+ "loss": 0.8130620002746582,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 1.050078247261346,
1064
+ "grad_norm": 0.8328220844268799,
1065
+ "learning_rate": 0.00017706329113924052,
1066
+ "loss": 0.8314303398132324,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 1.0570335593809772,
1071
+ "grad_norm": 0.8115274310112,
1072
+ "learning_rate": 0.0001768945147679325,
1073
+ "loss": 0.8550017356872559,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 1.0639888715006085,
1078
+ "grad_norm": 0.7510120868682861,
1079
+ "learning_rate": 0.00017672573839662447,
1080
+ "loss": 0.8596973419189453,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 1.07094418362024,
1085
+ "grad_norm": 0.8435187339782715,
1086
+ "learning_rate": 0.00017655696202531647,
1087
+ "loss": 0.8373047828674316,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 1.0778994957398713,
1092
+ "grad_norm": 0.7115764021873474,
1093
+ "learning_rate": 0.00017638818565400845,
1094
+ "loss": 0.8354406356811523,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 1.0848548078595026,
1099
+ "grad_norm": 0.7882176637649536,
1100
+ "learning_rate": 0.00017621940928270042,
1101
+ "loss": 0.7872240543365479,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 1.0918101199791341,
1106
+ "grad_norm": 0.7871888875961304,
1107
+ "learning_rate": 0.0001760506329113924,
1108
+ "loss": 0.8628718376159668,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 1.0987654320987654,
1113
+ "grad_norm": 0.7301794290542603,
1114
+ "learning_rate": 0.0001758818565400844,
1115
+ "loss": 0.831816291809082,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 1.1057207442183967,
1120
+ "grad_norm": 0.9122150540351868,
1121
+ "learning_rate": 0.00017571308016877638,
1122
+ "loss": 0.7959841728210449,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 1.1126760563380282,
1127
+ "grad_norm": 0.7667823433876038,
1128
+ "learning_rate": 0.00017554430379746835,
1129
+ "loss": 0.8162220001220704,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 1.1196313684576595,
1134
+ "grad_norm": 0.8881914615631104,
1135
+ "learning_rate": 0.00017537552742616036,
1136
+ "loss": 0.8113079071044922,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 1.1265866805772908,
1141
+ "grad_norm": 0.8066163063049316,
1142
+ "learning_rate": 0.00017520675105485233,
1143
+ "loss": 0.8882118225097656,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 1.1335419926969224,
1148
+ "grad_norm": 0.7834956645965576,
1149
+ "learning_rate": 0.0001750379746835443,
1150
+ "loss": 0.8253085136413574,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 1.1404973048165536,
1155
+ "grad_norm": 0.8007387518882751,
1156
+ "learning_rate": 0.00017486919831223628,
1157
+ "loss": 0.8184085845947265,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 1.147452616936185,
1162
+ "grad_norm": 0.8243253231048584,
1163
+ "learning_rate": 0.0001747004219409283,
1164
+ "loss": 0.8456280708312989,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 1.1544079290558165,
1169
+ "grad_norm": 0.877406895160675,
1170
+ "learning_rate": 0.00017453164556962026,
1171
+ "loss": 0.8649235725402832,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 1.1613632411754478,
1176
+ "grad_norm": 0.7477782964706421,
1177
+ "learning_rate": 0.00017436286919831224,
1178
+ "loss": 0.8237474441528321,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 1.168318553295079,
1183
+ "grad_norm": 0.8198301196098328,
1184
+ "learning_rate": 0.00017419409282700424,
1185
+ "loss": 0.8542666435241699,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 1.1752738654147106,
1190
+ "grad_norm": 0.9303598403930664,
1191
+ "learning_rate": 0.00017402531645569622,
1192
+ "loss": 0.8114500045776367,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 1.1822291775343419,
1197
+ "grad_norm": 0.8575146794319153,
1198
+ "learning_rate": 0.0001738565400843882,
1199
+ "loss": 0.8645087242126465,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 1.1891844896539732,
1204
+ "grad_norm": 0.7672931551933289,
1205
+ "learning_rate": 0.00017368776371308017,
1206
+ "loss": 0.859369945526123,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 1.1961398017736047,
1211
+ "grad_norm": 0.7352429628372192,
1212
+ "learning_rate": 0.00017351898734177217,
1213
+ "loss": 0.8559775352478027,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 1.203095113893236,
1218
+ "grad_norm": 0.816206157207489,
1219
+ "learning_rate": 0.00017335021097046412,
1220
+ "loss": 0.8009737968444824,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 1.2100504260128673,
1225
+ "grad_norm": 0.7859639525413513,
1226
+ "learning_rate": 0.00017318143459915612,
1227
+ "loss": 0.8644287109375,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 1.2170057381324986,
1232
+ "grad_norm": 0.9356649518013,
1233
+ "learning_rate": 0.00017301265822784813,
1234
+ "loss": 0.8834044456481933,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 1.22396105025213,
1239
+ "grad_norm": 0.8392632007598877,
1240
+ "learning_rate": 0.0001728438818565401,
1241
+ "loss": 0.8621941566467285,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 1.2309163623717614,
1246
+ "grad_norm": 0.8166247606277466,
1247
+ "learning_rate": 0.00017267510548523208,
1248
+ "loss": 0.849600887298584,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 1.2378716744913927,
1253
+ "grad_norm": 0.8207784295082092,
1254
+ "learning_rate": 0.00017250632911392405,
1255
+ "loss": 0.8497565269470215,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 1.2448269866110242,
1260
+ "grad_norm": 0.854336142539978,
1261
+ "learning_rate": 0.00017233755274261606,
1262
+ "loss": 0.8464045524597168,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 1.2517822987306555,
1267
+ "grad_norm": 0.7762853503227234,
1268
+ "learning_rate": 0.000172168776371308,
1269
+ "loss": 0.8548982620239258,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 1.2587376108502868,
1274
+ "grad_norm": 0.8769254088401794,
1275
+ "learning_rate": 0.000172,
1276
+ "loss": 0.7925784111022949,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 1.2656929229699183,
1281
+ "grad_norm": 0.8688540458679199,
1282
+ "learning_rate": 0.00017183122362869198,
1283
+ "loss": 0.8124382019042968,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 1.2726482350895496,
1288
+ "grad_norm": 0.8691960573196411,
1289
+ "learning_rate": 0.00017166244725738399,
1290
+ "loss": 0.8208071708679199,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 1.279603547209181,
1295
+ "grad_norm": 0.8795132637023926,
1296
+ "learning_rate": 0.00017149367088607596,
1297
+ "loss": 0.8139394760131836,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 1.2865588593288124,
1302
+ "grad_norm": 0.729501485824585,
1303
+ "learning_rate": 0.00017132489451476794,
1304
+ "loss": 0.8601320266723633,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 1.2935141714484437,
1309
+ "grad_norm": 0.7909119725227356,
1310
+ "learning_rate": 0.00017115611814345994,
1311
+ "loss": 0.8286827087402344,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 1.300469483568075,
1316
+ "grad_norm": 0.8067646622657776,
1317
+ "learning_rate": 0.0001709873417721519,
1318
+ "loss": 0.8656349182128906,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 1.3074247956877065,
1323
+ "grad_norm": 0.8472056984901428,
1324
+ "learning_rate": 0.0001708185654008439,
1325
+ "loss": 0.8064226150512696,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 1.3143801078073378,
1330
+ "grad_norm": 0.7201762795448303,
1331
+ "learning_rate": 0.00017064978902953587,
1332
+ "loss": 0.7900961399078369,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 1.3213354199269691,
1337
+ "grad_norm": 0.8812959790229797,
1338
+ "learning_rate": 0.00017048101265822784,
1339
+ "loss": 0.8703582763671875,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 1.3282907320466006,
1344
+ "grad_norm": 0.9451256394386292,
1345
+ "learning_rate": 0.00017031223628691984,
1346
+ "loss": 0.82720947265625,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 1.335246044166232,
1351
+ "grad_norm": 0.8077909350395203,
1352
+ "learning_rate": 0.00017014345991561182,
1353
+ "loss": 0.870479965209961,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 1.3422013562858632,
1358
+ "grad_norm": 0.7945935130119324,
1359
+ "learning_rate": 0.00016997468354430382,
1360
+ "loss": 0.8795977592468261,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 1.3491566684054948,
1365
+ "grad_norm": 0.8349176645278931,
1366
+ "learning_rate": 0.00016980590717299577,
1367
+ "loss": 0.8160754203796386,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 1.356111980525126,
1372
+ "grad_norm": 0.8306617140769958,
1373
+ "learning_rate": 0.00016963713080168777,
1374
+ "loss": 0.8054557800292969,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 1.3630672926447573,
1379
+ "grad_norm": 0.9334973096847534,
1380
+ "learning_rate": 0.00016946835443037975,
1381
+ "loss": 0.8172202110290527,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 1.3700226047643889,
1386
+ "grad_norm": 0.7852619290351868,
1387
+ "learning_rate": 0.00016929957805907173,
1388
+ "loss": 0.8508659362792969,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 1.3769779168840202,
1393
+ "grad_norm": 0.8396855592727661,
1394
+ "learning_rate": 0.00016913080168776373,
1395
+ "loss": 0.8553260803222656,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 1.3839332290036515,
1400
+ "grad_norm": 0.8172199726104736,
1401
+ "learning_rate": 0.0001689620253164557,
1402
+ "loss": 0.850562858581543,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 1.390888541123283,
1407
+ "grad_norm": 0.9590676426887512,
1408
+ "learning_rate": 0.0001687932489451477,
1409
+ "loss": 0.842772102355957,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 1.3978438532429143,
1414
+ "grad_norm": 0.8945585489273071,
1415
+ "learning_rate": 0.00016862447257383966,
1416
+ "loss": 0.8389938354492188,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 1.4047991653625456,
1421
+ "grad_norm": 0.8871139883995056,
1422
+ "learning_rate": 0.00016845569620253166,
1423
+ "loss": 0.8277386665344239,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 1.411754477482177,
1428
+ "grad_norm": 0.7622798681259155,
1429
+ "learning_rate": 0.00016828691983122363,
1430
+ "loss": 0.8776716232299805,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 1.4187097896018084,
1435
+ "grad_norm": 0.806749701499939,
1436
+ "learning_rate": 0.0001681181434599156,
1437
+ "loss": 0.8619850158691407,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 1.4256651017214397,
1442
+ "grad_norm": 0.7858820557594299,
1443
+ "learning_rate": 0.0001679493670886076,
1444
+ "loss": 0.858952522277832,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 1.4326204138410712,
1449
+ "grad_norm": 0.8000185489654541,
1450
+ "learning_rate": 0.0001677805907172996,
1451
+ "loss": 0.8301751136779785,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 1.4395757259607025,
1456
+ "grad_norm": 0.8979250192642212,
1457
+ "learning_rate": 0.0001676118143459916,
1458
+ "loss": 0.8660969734191895,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 1.4465310380803338,
1463
+ "grad_norm": 0.8358721137046814,
1464
+ "learning_rate": 0.00016744303797468354,
1465
+ "loss": 0.8113519668579101,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 1.4534863501999653,
1470
+ "grad_norm": 0.7582055330276489,
1471
+ "learning_rate": 0.00016727426160337554,
1472
+ "loss": 0.8481269836425781,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 1.4604416623195966,
1477
+ "grad_norm": 0.8319411873817444,
1478
+ "learning_rate": 0.00016710548523206752,
1479
+ "loss": 0.8612960815429688,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 1.467396974439228,
1484
+ "grad_norm": 0.7864130139350891,
1485
+ "learning_rate": 0.0001669367088607595,
1486
+ "loss": 0.844143009185791,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 1.4743522865588594,
1491
+ "grad_norm": 0.9045956134796143,
1492
+ "learning_rate": 0.0001667679324894515,
1493
+ "loss": 0.887512493133545,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 1.4813075986784907,
1498
+ "grad_norm": 0.790422260761261,
1499
+ "learning_rate": 0.00016659915611814347,
1500
+ "loss": 0.8565003395080566,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 1.488262910798122,
1505
+ "grad_norm": 0.8825517296791077,
1506
+ "learning_rate": 0.00016643037974683545,
1507
+ "loss": 0.7867041110992432,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 1.4952182229177535,
1512
+ "grad_norm": 0.8180622458457947,
1513
+ "learning_rate": 0.00016626160337552742,
1514
+ "loss": 0.8420925140380859,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 1.5021735350373848,
1519
+ "grad_norm": 0.7987875938415527,
1520
+ "learning_rate": 0.00016609282700421943,
1521
+ "loss": 0.8637572288513183,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 1.5091288471570161,
1526
+ "grad_norm": 0.8511167168617249,
1527
+ "learning_rate": 0.0001659240506329114,
1528
+ "loss": 0.8413339614868164,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 1.5160841592766476,
1533
+ "grad_norm": 0.8097606301307678,
1534
+ "learning_rate": 0.00016575527426160338,
1535
+ "loss": 0.903419303894043,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 1.523039471396279,
1540
+ "grad_norm": 0.79250168800354,
1541
+ "learning_rate": 0.00016558649789029535,
1542
+ "loss": 0.8391342163085938,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 1.5299947835159102,
1547
+ "grad_norm": 0.9454454183578491,
1548
+ "learning_rate": 0.00016541772151898736,
1549
+ "loss": 0.8559894561767578,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 1.5369500956355417,
1554
+ "grad_norm": 0.7894321084022522,
1555
+ "learning_rate": 0.00016524894514767933,
1556
+ "loss": 0.8035475730895996,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 1.543905407755173,
1561
+ "grad_norm": 0.8864350914955139,
1562
+ "learning_rate": 0.0001650801687763713,
1563
+ "loss": 0.8680961608886719,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 1.5508607198748043,
1568
+ "grad_norm": 0.891108512878418,
1569
+ "learning_rate": 0.0001649113924050633,
1570
+ "loss": 0.8588712692260743,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 1.5578160319944359,
1575
+ "grad_norm": 0.9062578082084656,
1576
+ "learning_rate": 0.0001647426160337553,
1577
+ "loss": 0.8700797080993652,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 1.5647713441140672,
1582
+ "grad_norm": 0.7826262712478638,
1583
+ "learning_rate": 0.00016457383966244726,
1584
+ "loss": 0.8155851364135742,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 1.5717266562336984,
1589
+ "grad_norm": 0.9333315491676331,
1590
+ "learning_rate": 0.00016440506329113924,
1591
+ "loss": 0.8439507484436035,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 1.57868196835333,
1596
+ "grad_norm": 0.8170693516731262,
1597
+ "learning_rate": 0.00016423628691983124,
1598
+ "loss": 0.8662002563476563,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 1.5856372804729613,
1603
+ "grad_norm": 0.8592401146888733,
1604
+ "learning_rate": 0.00016406751054852322,
1605
+ "loss": 0.8293574333190918,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 1.5925925925925926,
1610
+ "grad_norm": 0.8538609147071838,
1611
+ "learning_rate": 0.0001638987341772152,
1612
+ "loss": 0.8495461463928222,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 1.599547904712224,
1617
+ "grad_norm": 0.8533386588096619,
1618
+ "learning_rate": 0.0001637299578059072,
1619
+ "loss": 0.8541274070739746,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 1.6065032168318554,
1624
+ "grad_norm": 0.8268742561340332,
1625
+ "learning_rate": 0.00016356118143459914,
1626
+ "loss": 0.8548798561096191,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 1.6134585289514867,
1631
+ "grad_norm": 0.720944344997406,
1632
+ "learning_rate": 0.00016339240506329115,
1633
+ "loss": 0.7975351333618164,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 1.6204138410711182,
1638
+ "grad_norm": 0.8315446972846985,
1639
+ "learning_rate": 0.00016322362869198312,
1640
+ "loss": 0.8515398979187012,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 1.6273691531907495,
1645
+ "grad_norm": 0.7796456217765808,
1646
+ "learning_rate": 0.00016305485232067513,
1647
+ "loss": 0.8540250778198242,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 1.6343244653103808,
1652
+ "grad_norm": 0.7828388214111328,
1653
+ "learning_rate": 0.0001628860759493671,
1654
+ "loss": 0.8106023788452148,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 1.6412797774300123,
1659
+ "grad_norm": 0.8646306991577148,
1660
+ "learning_rate": 0.00016271729957805908,
1661
+ "loss": 0.8224319458007813,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 1.6482350895496436,
1666
+ "grad_norm": 0.8681850433349609,
1667
+ "learning_rate": 0.00016254852320675108,
1668
+ "loss": 0.8723241806030273,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 1.655190401669275,
1673
+ "grad_norm": 0.9010337591171265,
1674
+ "learning_rate": 0.00016237974683544303,
1675
+ "loss": 0.8411337852478027,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 1.6621457137889064,
1680
+ "grad_norm": 0.8576914072036743,
1681
+ "learning_rate": 0.00016221097046413503,
1682
+ "loss": 0.8763635635375977,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 1.6691010259085375,
1687
+ "grad_norm": 0.8342429399490356,
1688
+ "learning_rate": 0.000162042194092827,
1689
+ "loss": 0.8336827278137207,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 1.676056338028169,
1694
+ "grad_norm": 0.8843962550163269,
1695
+ "learning_rate": 0.000161873417721519,
1696
+ "loss": 0.8175349235534668,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 1.6830116501478005,
1701
+ "grad_norm": 0.8862879276275635,
1702
+ "learning_rate": 0.00016170464135021099,
1703
+ "loss": 0.8639119148254395,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 1.6899669622674316,
1708
+ "grad_norm": 0.8375465869903564,
1709
+ "learning_rate": 0.00016153586497890296,
1710
+ "loss": 0.826177978515625,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 1.6969222743870631,
1715
+ "grad_norm": 0.8170318603515625,
1716
+ "learning_rate": 0.00016136708860759496,
1717
+ "loss": 0.8408175468444824,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 1.7038775865066946,
1722
+ "grad_norm": 0.8448211550712585,
1723
+ "learning_rate": 0.0001611983122362869,
1724
+ "loss": 0.8227148056030273,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 1.7108328986263257,
1729
+ "grad_norm": 0.847463846206665,
1730
+ "learning_rate": 0.00016102953586497892,
1731
+ "loss": 0.8292852401733398,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 1.7177882107459572,
1736
+ "grad_norm": 0.9028883576393127,
1737
+ "learning_rate": 0.0001608607594936709,
1738
+ "loss": 0.8060542106628418,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 1.7247435228655887,
1743
+ "grad_norm": 0.9025176167488098,
1744
+ "learning_rate": 0.0001606919831223629,
1745
+ "loss": 0.8417590141296387,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 1.7316988349852198,
1750
+ "grad_norm": 0.8089222311973572,
1751
+ "learning_rate": 0.00016052320675105484,
1752
+ "loss": 0.830894660949707,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 1.7386541471048513,
1757
+ "grad_norm": 0.8767738938331604,
1758
+ "learning_rate": 0.00016035443037974685,
1759
+ "loss": 0.8725847244262696,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 1.7456094592244829,
1764
+ "grad_norm": 0.8535524010658264,
1765
+ "learning_rate": 0.00016018565400843885,
1766
+ "loss": 0.795355224609375,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 1.752564771344114,
1771
+ "grad_norm": 0.8336608409881592,
1772
+ "learning_rate": 0.0001600168776371308,
1773
+ "loss": 0.7953724384307861,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 1.7595200834637454,
1778
+ "grad_norm": 0.9168136715888977,
1779
+ "learning_rate": 0.0001598481012658228,
1780
+ "loss": 0.8600534439086914,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 1.766475395583377,
1785
+ "grad_norm": 0.8533674478530884,
1786
+ "learning_rate": 0.00015967932489451478,
1787
+ "loss": 0.8831576347351074,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 1.773430707703008,
1792
+ "grad_norm": 0.8148391246795654,
1793
+ "learning_rate": 0.00015951054852320675,
1794
+ "loss": 0.8559511184692383,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 1.7803860198226396,
1799
+ "grad_norm": 0.8034229874610901,
1800
+ "learning_rate": 0.00015934177215189873,
1801
+ "loss": 0.8530157089233399,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 1.787341331942271,
1806
+ "grad_norm": 0.8190781474113464,
1807
+ "learning_rate": 0.00015917299578059073,
1808
+ "loss": 0.8549043655395507,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 1.7942966440619021,
1813
+ "grad_norm": 0.9302302002906799,
1814
+ "learning_rate": 0.0001590042194092827,
1815
+ "loss": 0.8237882614135742,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 1.8012519561815337,
1820
+ "grad_norm": 0.8223699331283569,
1821
+ "learning_rate": 0.00015883544303797468,
1822
+ "loss": 0.8245153427124023,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 1.808207268301165,
1827
+ "grad_norm": 0.9003870487213135,
1828
+ "learning_rate": 0.00015866666666666668,
1829
+ "loss": 0.9052456855773926,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 1.8151625804207963,
1834
+ "grad_norm": 0.8372247815132141,
1835
+ "learning_rate": 0.00015849789029535866,
1836
+ "loss": 0.8585317611694336,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 1.8221178925404278,
1841
+ "grad_norm": 0.864454984664917,
1842
+ "learning_rate": 0.00015832911392405063,
1843
+ "loss": 0.8330329895019531,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 1.829073204660059,
1848
+ "grad_norm": 0.8524348139762878,
1849
+ "learning_rate": 0.0001581603375527426,
1850
+ "loss": 0.8251937866210938,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 1.8360285167796904,
1855
+ "grad_norm": 0.8346612453460693,
1856
+ "learning_rate": 0.0001579915611814346,
1857
+ "loss": 0.8435157775878906,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 1.8429838288993219,
1862
+ "grad_norm": 0.8321895003318787,
1863
+ "learning_rate": 0.0001578227848101266,
1864
+ "loss": 0.8158946990966797,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 1.8499391410189532,
1869
+ "grad_norm": 0.8137014508247375,
1870
+ "learning_rate": 0.00015765400843881856,
1871
+ "loss": 0.7897966384887696,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 1.8568944531385845,
1876
+ "grad_norm": 0.8836292624473572,
1877
+ "learning_rate": 0.00015748523206751057,
1878
+ "loss": 0.8417540550231933,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 1.863849765258216,
1883
+ "grad_norm": 0.936339795589447,
1884
+ "learning_rate": 0.00015731645569620254,
1885
+ "loss": 0.8401059150695801,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 1.8708050773778473,
1890
+ "grad_norm": 0.8627587556838989,
1891
+ "learning_rate": 0.00015714767932489452,
1892
+ "loss": 0.8373717308044434,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 1.8777603894974786,
1897
+ "grad_norm": 0.8423882722854614,
1898
+ "learning_rate": 0.0001569789029535865,
1899
+ "loss": 0.8373703002929688,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 1.88471570161711,
1904
+ "grad_norm": 0.9717828631401062,
1905
+ "learning_rate": 0.0001568101265822785,
1906
+ "loss": 0.8398172378540039,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 1.8916710137367414,
1911
+ "grad_norm": 0.8474680781364441,
1912
+ "learning_rate": 0.00015664135021097047,
1913
+ "loss": 0.8799395561218262,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 1.8986263258563727,
1918
+ "grad_norm": 0.8715893030166626,
1919
+ "learning_rate": 0.00015647257383966245,
1920
+ "loss": 0.8474602699279785,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 1.9055816379760042,
1925
+ "grad_norm": 0.9425509572029114,
1926
+ "learning_rate": 0.00015630379746835445,
1927
+ "loss": 0.8683322906494141,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 1.9125369500956355,
1932
+ "grad_norm": 0.8553449511528015,
1933
+ "learning_rate": 0.00015613502109704643,
1934
+ "loss": 0.8526237487792969,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 1.9194922622152668,
1939
+ "grad_norm": 0.8043725490570068,
1940
+ "learning_rate": 0.0001559662447257384,
1941
+ "loss": 0.8437747955322266,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 1.9264475743348983,
1946
+ "grad_norm": 0.8966366648674011,
1947
+ "learning_rate": 0.00015579746835443038,
1948
+ "loss": 0.8588647842407227,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 1.9334028864545296,
1953
+ "grad_norm": 0.892979085445404,
1954
+ "learning_rate": 0.00015562869198312238,
1955
+ "loss": 0.8752643585205078,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 1.940358198574161,
1960
+ "grad_norm": 0.8884108066558838,
1961
+ "learning_rate": 0.00015545991561181436,
1962
+ "loss": 0.8153524398803711,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 1.9473135106937924,
1967
+ "grad_norm": 0.9366549253463745,
1968
+ "learning_rate": 0.00015529113924050633,
1969
+ "loss": 0.8739970207214356,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 1.9542688228134237,
1974
+ "grad_norm": 0.8856159448623657,
1975
+ "learning_rate": 0.00015512236286919834,
1976
+ "loss": 0.8203553199768067,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 1.961224134933055,
1981
+ "grad_norm": 0.8499979376792908,
1982
+ "learning_rate": 0.0001549535864978903,
1983
+ "loss": 0.800433349609375,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 1.9681794470526865,
1988
+ "grad_norm": 0.840398371219635,
1989
+ "learning_rate": 0.0001547848101265823,
1990
+ "loss": 0.8384733200073242,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 1.9751347591723178,
1995
+ "grad_norm": 0.8293272852897644,
1996
+ "learning_rate": 0.00015461603375527426,
1997
+ "loss": 0.8640399932861328,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 1.9820900712919491,
2002
+ "grad_norm": 0.8705354928970337,
2003
+ "learning_rate": 0.00015444725738396627,
2004
+ "loss": 0.8627267837524414,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 1.9890453834115807,
2009
+ "grad_norm": 0.8676750063896179,
2010
+ "learning_rate": 0.00015427848101265821,
2011
+ "loss": 0.8136070251464844,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 1.996000695531212,
2016
+ "grad_norm": 0.9643317461013794,
2017
+ "learning_rate": 0.00015410970464135022,
2018
+ "loss": 0.8474054336547852,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 2.0027821248478523,
2023
+ "grad_norm": 0.8110275864601135,
2024
+ "learning_rate": 0.0001539409282700422,
2025
+ "loss": 0.7731066226959229,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 2.009737436967484,
2030
+ "grad_norm": 0.9357481598854065,
2031
+ "learning_rate": 0.00015377215189873417,
2032
+ "loss": 0.5927461147308349,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 2.0166927490871154,
2037
+ "grad_norm": 0.9144616723060608,
2038
+ "learning_rate": 0.00015360337552742617,
2039
+ "loss": 0.6439071655273437,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 2.0236480612067465,
2044
+ "grad_norm": 0.9185596108436584,
2045
+ "learning_rate": 0.00015343459915611815,
2046
+ "loss": 0.6101229667663575,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 2.030603373326378,
2051
+ "grad_norm": 0.9005320072174072,
2052
+ "learning_rate": 0.00015326582278481015,
2053
+ "loss": 0.6393587112426757,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 2.0375586854460095,
2058
+ "grad_norm": 1.015763521194458,
2059
+ "learning_rate": 0.0001530970464135021,
2060
+ "loss": 0.6238693714141845,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 2.0445139975656406,
2065
+ "grad_norm": 0.960231602191925,
2066
+ "learning_rate": 0.0001529282700421941,
2067
+ "loss": 0.6013807773590087,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 2.051469309685272,
2072
+ "grad_norm": 0.8943541049957275,
2073
+ "learning_rate": 0.00015275949367088608,
2074
+ "loss": 0.6379226684570313,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 2.0584246218049036,
2079
+ "grad_norm": 0.9429047107696533,
2080
+ "learning_rate": 0.00015259071729957805,
2081
+ "loss": 0.5979090213775635,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 2.0653799339245347,
2086
+ "grad_norm": 0.9675496220588684,
2087
+ "learning_rate": 0.00015242194092827006,
2088
+ "loss": 0.6232080459594727,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 2.072335246044166,
2093
+ "grad_norm": 0.995304524898529,
2094
+ "learning_rate": 0.00015225316455696203,
2095
+ "loss": 0.6817082405090332,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 2.0792905581637977,
2100
+ "grad_norm": 1.051934003829956,
2101
+ "learning_rate": 0.00015208438818565403,
2102
+ "loss": 0.6690094470977783,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 2.086245870283429,
2107
+ "grad_norm": 0.8924301266670227,
2108
+ "learning_rate": 0.00015191561181434598,
2109
+ "loss": 0.6292377948760987,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 2.0932011824030603,
2114
+ "grad_norm": 0.9204551577568054,
2115
+ "learning_rate": 0.00015174683544303799,
2116
+ "loss": 0.627526044845581,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 2.100156494522692,
2121
+ "grad_norm": 0.9752632975578308,
2122
+ "learning_rate": 0.00015157805907172996,
2123
+ "loss": 0.6261420726776123,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 2.107111806642323,
2128
+ "grad_norm": 1.0073333978652954,
2129
+ "learning_rate": 0.00015140928270042194,
2130
+ "loss": 0.6157436370849609,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 2.1140671187619544,
2135
+ "grad_norm": 0.9689323306083679,
2136
+ "learning_rate": 0.00015124050632911394,
2137
+ "loss": 0.590775442123413,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 2.121022430881586,
2142
+ "grad_norm": 1.0536748170852661,
2143
+ "learning_rate": 0.00015107172995780592,
2144
+ "loss": 0.6779862880706787,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 2.127977743001217,
2149
+ "grad_norm": 0.9073647260665894,
2150
+ "learning_rate": 0.00015090295358649792,
2151
+ "loss": 0.6256875991821289,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 2.1349330551208485,
2156
+ "grad_norm": 0.9082266092300415,
2157
+ "learning_rate": 0.00015073417721518987,
2158
+ "loss": 0.6227253437042236,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 2.14188836724048,
2163
+ "grad_norm": 1.1173062324523926,
2164
+ "learning_rate": 0.00015056540084388187,
2165
+ "loss": 0.6266400814056396,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 2.148843679360111,
2170
+ "grad_norm": 1.031101942062378,
2171
+ "learning_rate": 0.00015039662447257385,
2172
+ "loss": 0.6497706890106201,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 2.1557989914797426,
2177
+ "grad_norm": 1.1058653593063354,
2178
+ "learning_rate": 0.00015022784810126582,
2179
+ "loss": 0.6651206016540527,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 2.162754303599374,
2184
+ "grad_norm": 1.0694655179977417,
2185
+ "learning_rate": 0.00015005907172995782,
2186
+ "loss": 0.6398143291473388,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 2.1697096157190052,
2191
+ "grad_norm": 1.086735725402832,
2192
+ "learning_rate": 0.0001498902953586498,
2193
+ "loss": 0.6639479637145996,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 2.1766649278386367,
2198
+ "grad_norm": 0.9783734679222107,
2199
+ "learning_rate": 0.00014972151898734178,
2200
+ "loss": 0.6653146266937255,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 2.1836202399582683,
2205
+ "grad_norm": 1.101665735244751,
2206
+ "learning_rate": 0.00014955274261603375,
2207
+ "loss": 0.649967622756958,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 2.1905755520778993,
2212
+ "grad_norm": 0.9247400164604187,
2213
+ "learning_rate": 0.00014938396624472575,
2214
+ "loss": 0.6428372383117675,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 2.197530864197531,
2219
+ "grad_norm": 1.0135854482650757,
2220
+ "learning_rate": 0.00014921518987341773,
2221
+ "loss": 0.5819164276123047,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 2.2044861763171624,
2226
+ "grad_norm": 1.0484477281570435,
2227
+ "learning_rate": 0.0001490464135021097,
2228
+ "loss": 0.6144848823547363,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 2.2114414884367934,
2233
+ "grad_norm": 1.1365951299667358,
2234
+ "learning_rate": 0.0001488776371308017,
2235
+ "loss": 0.6432332515716552,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 2.218396800556425,
2240
+ "grad_norm": 1.1562445163726807,
2241
+ "learning_rate": 0.00014870886075949368,
2242
+ "loss": 0.5995328426361084,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 2.2253521126760565,
2247
+ "grad_norm": 0.9003695249557495,
2248
+ "learning_rate": 0.00014854008438818566,
2249
+ "loss": 0.642880630493164,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 2.2323074247956876,
2254
+ "grad_norm": 0.9424404501914978,
2255
+ "learning_rate": 0.00014837130801687764,
2256
+ "loss": 0.6388212203979492,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 2.239262736915319,
2261
+ "grad_norm": 1.0001310110092163,
2262
+ "learning_rate": 0.00014820253164556964,
2263
+ "loss": 0.6416466236114502,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 2.2462180490349506,
2268
+ "grad_norm": 1.0921766757965088,
2269
+ "learning_rate": 0.00014803375527426161,
2270
+ "loss": 0.6218269348144532,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 2.2531733611545817,
2275
+ "grad_norm": 1.0368902683258057,
2276
+ "learning_rate": 0.0001478649789029536,
2277
+ "loss": 0.6399544239044189,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 2.260128673274213,
2282
+ "grad_norm": 1.0035440921783447,
2283
+ "learning_rate": 0.00014769620253164556,
2284
+ "loss": 0.608824634552002,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 2.2670839853938447,
2289
+ "grad_norm": 0.9262093901634216,
2290
+ "learning_rate": 0.00014752742616033757,
2291
+ "loss": 0.647667407989502,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 2.2740392975134758,
2296
+ "grad_norm": 0.9650372862815857,
2297
+ "learning_rate": 0.00014735864978902954,
2298
+ "loss": 0.6364543914794922,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 2.2809946096331073,
2303
+ "grad_norm": 1.0061427354812622,
2304
+ "learning_rate": 0.00014718987341772152,
2305
+ "loss": 0.6616278648376465,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 2.287949921752739,
2310
+ "grad_norm": 1.122926115989685,
2311
+ "learning_rate": 0.00014702109704641352,
2312
+ "loss": 0.6674659252166748,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 2.29490523387237,
2317
+ "grad_norm": 1.0123682022094727,
2318
+ "learning_rate": 0.00014685232067510547,
2319
+ "loss": 0.659001636505127,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 2.3018605459920014,
2324
+ "grad_norm": 1.0010204315185547,
2325
+ "learning_rate": 0.00014668354430379747,
2326
+ "loss": 0.6224476814270019,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 2.308815858111633,
2331
+ "grad_norm": 1.02507483959198,
2332
+ "learning_rate": 0.00014651476793248945,
2333
+ "loss": 0.6400227546691895,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 2.315771170231264,
2338
+ "grad_norm": 1.009433388710022,
2339
+ "learning_rate": 0.00014634599156118145,
2340
+ "loss": 0.6417963981628418,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 2.3227264823508955,
2345
+ "grad_norm": 1.0174036026000977,
2346
+ "learning_rate": 0.00014617721518987343,
2347
+ "loss": 0.6334123134613037,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 2.329681794470527,
2352
+ "grad_norm": 0.973960280418396,
2353
+ "learning_rate": 0.0001460084388185654,
2354
+ "loss": 0.6006657123565674,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 2.336637106590158,
2359
+ "grad_norm": 0.9980184435844421,
2360
+ "learning_rate": 0.0001458396624472574,
2361
+ "loss": 0.6164235591888427,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 2.3435924187097896,
2366
+ "grad_norm": 0.9642781615257263,
2367
+ "learning_rate": 0.00014567088607594935,
2368
+ "loss": 0.6624460220336914,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 2.350547730829421,
2373
+ "grad_norm": 0.947239875793457,
2374
+ "learning_rate": 0.00014550210970464136,
2375
+ "loss": 0.653458833694458,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 2.357503042949052,
2380
+ "grad_norm": 1.0991953611373901,
2381
+ "learning_rate": 0.00014533333333333333,
2382
+ "loss": 0.6557422161102295,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 2.3644583550686837,
2387
+ "grad_norm": 0.9711103439331055,
2388
+ "learning_rate": 0.00014516455696202534,
2389
+ "loss": 0.6298813819885254,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 2.3714136671883153,
2394
+ "grad_norm": 1.0146737098693848,
2395
+ "learning_rate": 0.0001449957805907173,
2396
+ "loss": 0.6305426597595215,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 2.3783689793079463,
2401
+ "grad_norm": 0.9894322752952576,
2402
+ "learning_rate": 0.0001448270042194093,
2403
+ "loss": 0.6244983196258544,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 2.385324291427578,
2408
+ "grad_norm": 1.076114535331726,
2409
+ "learning_rate": 0.0001446582278481013,
2410
+ "loss": 0.6709982872009277,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 2.3922796035472094,
2415
+ "grad_norm": 1.0809930562973022,
2416
+ "learning_rate": 0.00014448945147679324,
2417
+ "loss": 0.6563718318939209,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 2.3992349156668404,
2422
+ "grad_norm": 0.9109380841255188,
2423
+ "learning_rate": 0.00014432067510548524,
2424
+ "loss": 0.6541102409362793,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 2.406190227786472,
2429
+ "grad_norm": 0.9546862840652466,
2430
+ "learning_rate": 0.00014415189873417722,
2431
+ "loss": 0.6555162906646729,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 2.4131455399061035,
2436
+ "grad_norm": 1.0797473192214966,
2437
+ "learning_rate": 0.00014398312236286922,
2438
+ "loss": 0.6419790267944336,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 2.4201008520257346,
2443
+ "grad_norm": 1.0414495468139648,
2444
+ "learning_rate": 0.0001438143459915612,
2445
+ "loss": 0.6333636283874512,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 2.427056164145366,
2450
+ "grad_norm": 0.991815984249115,
2451
+ "learning_rate": 0.00014364556962025317,
2452
+ "loss": 0.6770966529846192,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 2.434011476264997,
2457
+ "grad_norm": 1.0610934495925903,
2458
+ "learning_rate": 0.00014347679324894517,
2459
+ "loss": 0.6442631244659424,
2460
+ "step": 3500
2461
+ }
2462
+ ],
2463
+ "logging_steps": 10,
2464
+ "max_steps": 12000,
2465
+ "num_input_tokens_seen": 0,
2466
+ "num_train_epochs": 9,
2467
+ "save_steps": 100,
2468
+ "stateful_callbacks": {
2469
+ "TrainerControl": {
2470
+ "args": {
2471
+ "should_epoch_stop": false,
2472
+ "should_evaluate": false,
2473
+ "should_log": false,
2474
+ "should_save": true,
2475
+ "should_training_stop": false
2476
+ },
2477
+ "attributes": {}
2478
+ }
2479
+ },
2480
+ "total_flos": 1.4136133267210752e+17,
2481
+ "train_batch_size": 1,
2482
+ "trial_name": null,
2483
+ "trial_params": null
2484
+ }
ver1_チェックポイント_003500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee554cf92aad478c6c61d2a452074e98f0c12bfbfc6712ab9588e93dfc922b0
3
+ size 6097