Ba2han commited on
Commit
9d0a35f
·
verified ·
1 Parent(s): 16cc824

Training in progress, step 474, checkpoint

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
last-checkpoint/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Ba2han/model-muontest-wsd-p2
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Ba2han/model-muontest-wsd-p2
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 0.18.0
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "Ba2han/model-muontest-wsd-p2",
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
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "k_proj",
37
+ "q_proj",
38
+ "o_proj",
39
+ "up_proj",
40
+ "down_proj",
41
+ "gate_proj",
42
+ "v_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6416b19d662d7b065eea09cf1c815ad3189cf89a506ddea7d4b667b6bacc694b
3
+ size 195125192
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>
29
+
30
+ " }}
31
+ {%- if tools is not none %}
32
+ {{- "Environment: ipython
33
+ " }}
34
+ {%- endif %}
35
+ {{- "Cutting Knowledge Date: December 2023
36
+ " }}
37
+ {{- "Today Date: " + date_string + "
38
+
39
+ " }}
40
+ {%- if tools is not none and not tools_in_user_message %}
41
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
42
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
43
+ {{- "Do not use variables.
44
+
45
+ " }}
46
+ {%- for t in tools %}
47
+ {{- t | tojson(indent=4) }}
48
+ {{- "
49
+
50
+ " }}
51
+ {%- endfor %}
52
+ {%- endif %}
53
+ {{- system_message }}
54
+ {{- "<|eot_id|>" }}
55
+
56
+ {#- Custom tools are passed in a user message with some extra guidance #}
57
+ {%- if tools_in_user_message and not tools is none %}
58
+ {#- Extract the first user message so we can plug it in here #}
59
+ {%- if messages | length != 0 %}
60
+ {%- set first_user_message = messages[0]['content']|trim %}
61
+ {%- set messages = messages[1:] %}
62
+ {%- else %}
63
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
64
+ {%- endif %}
65
+ {{- '<|start_header_id|>user<|end_header_id|>
66
+
67
+ ' -}}
68
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
69
+ {{- "with its proper arguments that best answers the given prompt.
70
+
71
+ " }}
72
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
73
+ {{- "Do not use variables.
74
+
75
+ " }}
76
+ {%- for t in tools %}
77
+ {{- t | tojson(indent=4) }}
78
+ {{- "
79
+
80
+ " }}
81
+ {%- endfor %}
82
+ {{- first_user_message + "<|eot_id|>"}}
83
+ {%- endif %}
84
+
85
+ {%- for message in messages %}
86
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
87
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>
88
+
89
+ '+ message['content'] | trim + '<|eot_id|>' }}
90
+ {%- elif 'tool_calls' in message %}
91
+ {%- if not message.tool_calls|length == 1 %}
92
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
93
+ {%- endif %}
94
+ {%- set tool_call = message.tool_calls[0].function %}
95
+ {{- '<|start_header_id|>assistant<|end_header_id|>
96
+
97
+ ' -}}
98
+ {{- '{"name": "' + tool_call.name + '", ' }}
99
+ {{- '"parameters": ' }}
100
+ {{- tool_call.arguments | tojson }}
101
+ {{- "}" }}
102
+ {{- "<|eot_id|>" }}
103
+ {%- elif message.role == "tool" or message.role == "ipython" %}
104
+ {{- "<|start_header_id|>ipython<|end_header_id|>
105
+
106
+ " }}
107
+ {%- if message.content is mapping or message.content is iterable %}
108
+ {{- message.content | tojson }}
109
+ {%- else %}
110
+ {{- message.content }}
111
+ {%- endif %}
112
+ {{- "<|eot_id|>" }}
113
+ {%- endif %}
114
+ {%- endfor %}
115
+ {%- if add_generation_prompt %}
116
+ {{- '<|start_header_id|>assistant<|end_header_id|>
117
+
118
+ ' }}
119
+ {%- endif %}
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff00ef3707a0b5c87918652a677e2aba1be61df7e6d5477f070747eb67622b10
3
+ size 99831781
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0263a76024d007bc7e6bf05e5a5774ae010f9c67a445e38f09686ebbb402f3
3
+ size 1465
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|begin_of_text|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|end_of_text|>",
7
+ "extra_special_tokens": [],
8
+ "is_local": false,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 131072,
14
+ "model_specific_special_tokens": {},
15
+ "pad_token": "<|finetune_right_pad_id|>",
16
+ "padding_side": "right",
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "unk_token": null
19
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,3360 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.23047468546769587,
6
+ "eval_steps": 474,
7
+ "global_step": 474,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.000486233513644928,
14
+ "grad_norm": 0.028895756229758263,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.13659772276878357,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.000972467027289856,
21
+ "grad_norm": 0.030222004279494286,
22
+ "learning_rate": 8.771929824561403e-06,
23
+ "loss": 0.13703468441963196,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.001458700540934784,
28
+ "grad_norm": 0.029615161940455437,
29
+ "learning_rate": 1.7543859649122806e-05,
30
+ "loss": 0.13699473440647125,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.001944934054579712,
35
+ "grad_norm": 0.0286174938082695,
36
+ "learning_rate": 2.631578947368421e-05,
37
+ "loss": 0.1324412077665329,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.00243116756822464,
42
+ "grad_norm": 0.0272593442350626,
43
+ "learning_rate": 3.508771929824561e-05,
44
+ "loss": 0.13369958102703094,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.002917401081869568,
49
+ "grad_norm": 0.02919352985918522,
50
+ "learning_rate": 4.3859649122807014e-05,
51
+ "loss": 0.13712656497955322,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.003403634595514496,
56
+ "grad_norm": 0.03263072669506073,
57
+ "learning_rate": 5.263157894736842e-05,
58
+ "loss": 0.13858309388160706,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.003889868109159424,
63
+ "grad_norm": 0.0319291353225708,
64
+ "learning_rate": 6.140350877192983e-05,
65
+ "loss": 0.13566386699676514,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.004376101622804352,
70
+ "grad_norm": 0.03151027485728264,
71
+ "learning_rate": 7.017543859649122e-05,
72
+ "loss": 0.1303359717130661,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.00486233513644928,
77
+ "grad_norm": 0.035238828510046005,
78
+ "learning_rate": 7.894736842105263e-05,
79
+ "loss": 0.13462986052036285,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.005348568650094207,
84
+ "grad_norm": 0.035420700907707214,
85
+ "learning_rate": 8.771929824561403e-05,
86
+ "loss": 0.13294978439807892,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.005834802163739136,
91
+ "grad_norm": 0.036439038813114166,
92
+ "learning_rate": 9.649122807017544e-05,
93
+ "loss": 0.13114020228385925,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.006321035677384064,
98
+ "grad_norm": 0.033923279494047165,
99
+ "learning_rate": 0.00010526315789473683,
100
+ "loss": 0.1279323399066925,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.006807269191028992,
105
+ "grad_norm": 0.03384435176849365,
106
+ "learning_rate": 0.00011403508771929824,
107
+ "loss": 0.12246227264404297,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.007293502704673919,
112
+ "grad_norm": 0.029199814423918724,
113
+ "learning_rate": 0.00012280701754385965,
114
+ "loss": 0.12107409536838531,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.007779736218318848,
119
+ "grad_norm": 0.03211691230535507,
120
+ "learning_rate": 0.00013157894736842105,
121
+ "loss": 0.118674136698246,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.008265969731963776,
126
+ "grad_norm": 0.030137386173009872,
127
+ "learning_rate": 0.00014035087719298245,
128
+ "loss": 0.11296422779560089,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.008752203245608704,
133
+ "grad_norm": 0.035055987536907196,
134
+ "learning_rate": 0.00014912280701754384,
135
+ "loss": 0.10164865106344223,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.009238436759253631,
140
+ "grad_norm": 0.03253507986664772,
141
+ "learning_rate": 0.00015789473684210527,
142
+ "loss": 0.10046166181564331,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.00972467027289856,
147
+ "grad_norm": 0.03808705881237984,
148
+ "learning_rate": 0.00016666666666666666,
149
+ "loss": 0.09389816224575043,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.010210903786543487,
154
+ "grad_norm": 0.03849140554666519,
155
+ "learning_rate": 0.00017543859649122806,
156
+ "loss": 0.09220334142446518,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.010697137300188415,
161
+ "grad_norm": 0.08741280436515808,
162
+ "learning_rate": 0.00018421052631578948,
163
+ "loss": 0.08772505074739456,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.011183370813833344,
168
+ "grad_norm": 0.05099602788686752,
169
+ "learning_rate": 0.00019298245614035088,
170
+ "loss": 0.0812835544347763,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.011669604327478272,
175
+ "grad_norm": 0.04952536150813103,
176
+ "learning_rate": 0.00020175438596491227,
177
+ "loss": 0.07532540708780289,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.0121558378411232,
182
+ "grad_norm": 0.046747561544179916,
183
+ "learning_rate": 0.00021052631578947367,
184
+ "loss": 0.07109525054693222,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.012642071354768128,
189
+ "grad_norm": 0.03680324926972389,
190
+ "learning_rate": 0.0002192982456140351,
191
+ "loss": 0.06924279034137726,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.013128304868413055,
196
+ "grad_norm": 0.02947934716939926,
197
+ "learning_rate": 0.0002280701754385965,
198
+ "loss": 0.07149061560630798,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.013614538382057983,
203
+ "grad_norm": 0.025988204404711723,
204
+ "learning_rate": 0.00023684210526315788,
205
+ "loss": 0.06618344783782959,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.014100771895702911,
210
+ "grad_norm": 0.02482382208108902,
211
+ "learning_rate": 0.0002456140350877193,
212
+ "loss": 0.07015278190374374,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.014587005409347839,
217
+ "grad_norm": 0.025846438482403755,
218
+ "learning_rate": 0.0002543859649122807,
219
+ "loss": 0.06754790246486664,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.015073238922992767,
224
+ "grad_norm": 0.023268740624189377,
225
+ "learning_rate": 0.0002631578947368421,
226
+ "loss": 0.07099650055170059,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.015559472436637696,
231
+ "grad_norm": 0.02141893468797207,
232
+ "learning_rate": 0.00027192982456140355,
233
+ "loss": 0.07017423212528229,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.016045705950282624,
238
+ "grad_norm": 0.02045714110136032,
239
+ "learning_rate": 0.0002807017543859649,
240
+ "loss": 0.06736178696155548,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.01653193946392755,
245
+ "grad_norm": 0.018981782719492912,
246
+ "learning_rate": 0.00028947368421052634,
247
+ "loss": 0.06993366777896881,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.01701817297757248,
252
+ "grad_norm": 0.018564946949481964,
253
+ "learning_rate": 0.0002982456140350877,
254
+ "loss": 0.06789343059062958,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.017504406491217407,
259
+ "grad_norm": 0.018074145540595055,
260
+ "learning_rate": 0.00030701754385964913,
261
+ "loss": 0.06210528686642647,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.017990640004862335,
266
+ "grad_norm": 0.01709425449371338,
267
+ "learning_rate": 0.00031578947368421053,
268
+ "loss": 0.0681057870388031,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.018476873518507263,
273
+ "grad_norm": 0.01714732125401497,
274
+ "learning_rate": 0.0003245614035087719,
275
+ "loss": 0.06850220263004303,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.01896310703215219,
280
+ "grad_norm": 0.018889306113123894,
281
+ "learning_rate": 0.0003333333333333333,
282
+ "loss": 0.06345199793577194,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.01944934054579712,
287
+ "grad_norm": 0.01655932515859604,
288
+ "learning_rate": 0.00034210526315789477,
289
+ "loss": 0.06525139510631561,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.019935574059442046,
294
+ "grad_norm": 0.01717725768685341,
295
+ "learning_rate": 0.0003508771929824561,
296
+ "loss": 0.0619560107588768,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.020421807573086974,
301
+ "grad_norm": 0.016549885272979736,
302
+ "learning_rate": 0.00035964912280701756,
303
+ "loss": 0.05912506580352783,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0209080410867319,
308
+ "grad_norm": 0.01718374714255333,
309
+ "learning_rate": 0.00036842105263157896,
310
+ "loss": 0.059433046728372574,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.02139427460037683,
315
+ "grad_norm": 0.016804836690425873,
316
+ "learning_rate": 0.00037719298245614036,
317
+ "loss": 0.0630156397819519,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.021880508114021757,
322
+ "grad_norm": 0.019732007756829262,
323
+ "learning_rate": 0.00038596491228070175,
324
+ "loss": 0.06205141916871071,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.02236674162766669,
329
+ "grad_norm": 0.01656733825802803,
330
+ "learning_rate": 0.00039473684210526315,
331
+ "loss": 0.060812510550022125,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.022852975141311616,
336
+ "grad_norm": 0.016429010778665543,
337
+ "learning_rate": 0.00040350877192982455,
338
+ "loss": 0.05936110019683838,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.023339208654956544,
343
+ "grad_norm": 0.017754236236214638,
344
+ "learning_rate": 0.000412280701754386,
345
+ "loss": 0.062226954847574234,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.023825442168601472,
350
+ "grad_norm": 0.016911447048187256,
351
+ "learning_rate": 0.00042105263157894734,
352
+ "loss": 0.06098425015807152,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.0243116756822464,
357
+ "grad_norm": 0.01828618347644806,
358
+ "learning_rate": 0.0004298245614035088,
359
+ "loss": 0.05728878080844879,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.024797909195891327,
364
+ "grad_norm": 0.030954457819461823,
365
+ "learning_rate": 0.0004385964912280702,
366
+ "loss": 0.05891074985265732,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.025284142709536255,
371
+ "grad_norm": 0.016399184241890907,
372
+ "learning_rate": 0.0004473684210526316,
373
+ "loss": 0.06067778170108795,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.025770376223181183,
378
+ "grad_norm": 0.01686052605509758,
379
+ "learning_rate": 0.000456140350877193,
380
+ "loss": 0.05675597861409187,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.02625660973682611,
385
+ "grad_norm": 0.015758099034428596,
386
+ "learning_rate": 0.00046491228070175437,
387
+ "loss": 0.05692098289728165,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.02674284325047104,
392
+ "grad_norm": 0.016079390421509743,
393
+ "learning_rate": 0.00047368421052631577,
394
+ "loss": 0.057123247534036636,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.027229076764115966,
399
+ "grad_norm": 0.015765707939863205,
400
+ "learning_rate": 0.0004824561403508772,
401
+ "loss": 0.05910360813140869,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.027715310277760894,
406
+ "grad_norm": 0.01575101725757122,
407
+ "learning_rate": 0.0004912280701754386,
408
+ "loss": 0.05828487500548363,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.028201543791405822,
413
+ "grad_norm": 0.01604265533387661,
414
+ "learning_rate": 0.0005,
415
+ "loss": 0.06172396242618561,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.02868777730505075,
420
+ "grad_norm": 0.014950573444366455,
421
+ "learning_rate": 0.0004997834560415764,
422
+ "loss": 0.05262353643774986,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.029174010818695677,
427
+ "grad_norm": 0.015433096326887608,
428
+ "learning_rate": 0.0004995669120831529,
429
+ "loss": 0.05562647432088852,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.029660244332340605,
434
+ "grad_norm": 0.014272174797952175,
435
+ "learning_rate": 0.0004993503681247293,
436
+ "loss": 0.055356867611408234,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.030146477845985533,
441
+ "grad_norm": 0.014692898839712143,
442
+ "learning_rate": 0.0004991338241663058,
443
+ "loss": 0.0587322860956192,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.03063271135963046,
448
+ "grad_norm": 0.014932661317288876,
449
+ "learning_rate": 0.0004989172802078822,
450
+ "loss": 0.058531951159238815,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.031118944873275392,
455
+ "grad_norm": 0.016226429492235184,
456
+ "learning_rate": 0.0004987007362494587,
457
+ "loss": 0.057049088180065155,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.03160517838692032,
462
+ "grad_norm": 0.014725301414728165,
463
+ "learning_rate": 0.0004984841922910351,
464
+ "loss": 0.05614468827843666,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.03209141190056525,
469
+ "grad_norm": 0.014913907274603844,
470
+ "learning_rate": 0.0004982676483326115,
471
+ "loss": 0.057807061821222305,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.032577645414210175,
476
+ "grad_norm": 0.015012742020189762,
477
+ "learning_rate": 0.000498051104374188,
478
+ "loss": 0.05969694256782532,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.0330638789278551,
483
+ "grad_norm": 0.013994358479976654,
484
+ "learning_rate": 0.0004978345604157644,
485
+ "loss": 0.05826937034726143,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.03355011244150003,
490
+ "grad_norm": 0.013738911598920822,
491
+ "learning_rate": 0.0004976180164573408,
492
+ "loss": 0.05600671470165253,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.03403634595514496,
497
+ "grad_norm": 0.014983505941927433,
498
+ "learning_rate": 0.0004974014724989173,
499
+ "loss": 0.05411494895815849,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.03452257946878989,
504
+ "grad_norm": 0.015372737310826778,
505
+ "learning_rate": 0.0004971849285404938,
506
+ "loss": 0.057352323085069656,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.035008812982434814,
511
+ "grad_norm": 0.014793546870350838,
512
+ "learning_rate": 0.0004969683845820702,
513
+ "loss": 0.055681560188531876,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.03549504649607974,
518
+ "grad_norm": 0.013696925714612007,
519
+ "learning_rate": 0.0004967518406236466,
520
+ "loss": 0.047928910702466965,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.03598128000972467,
525
+ "grad_norm": 0.014598103240132332,
526
+ "learning_rate": 0.0004965352966652231,
527
+ "loss": 0.054849155247211456,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.0364675135233696,
532
+ "grad_norm": 0.05080587416887283,
533
+ "learning_rate": 0.0004963187527067995,
534
+ "loss": 0.050336286425590515,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.036953747037014525,
539
+ "grad_norm": 0.016120363026857376,
540
+ "learning_rate": 0.0004961022087483759,
541
+ "loss": 0.05736556649208069,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.03743998055065945,
546
+ "grad_norm": 0.015958955511450768,
547
+ "learning_rate": 0.0004958856647899524,
548
+ "loss": 0.0565849132835865,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.03792621406430438,
553
+ "grad_norm": 0.016321755945682526,
554
+ "learning_rate": 0.0004956691208315288,
555
+ "loss": 0.05862516909837723,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.03841244757794931,
560
+ "grad_norm": 0.017314009368419647,
561
+ "learning_rate": 0.0004954525768731052,
562
+ "loss": 0.05301673710346222,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.03889868109159424,
567
+ "grad_norm": 0.01411174051463604,
568
+ "learning_rate": 0.0004952360329146816,
569
+ "loss": 0.05415857210755348,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.039384914605239164,
574
+ "grad_norm": 0.01715041510760784,
575
+ "learning_rate": 0.0004950194889562582,
576
+ "loss": 0.05468383803963661,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.03987114811888409,
581
+ "grad_norm": 0.015759341418743134,
582
+ "learning_rate": 0.0004948029449978346,
583
+ "loss": 0.052892375737428665,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.04035738163252902,
588
+ "grad_norm": 0.017158253118395805,
589
+ "learning_rate": 0.000494586401039411,
590
+ "loss": 0.052562762051820755,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.04084361514617395,
595
+ "grad_norm": 0.014684375375509262,
596
+ "learning_rate": 0.0004943698570809875,
597
+ "loss": 0.04942884296178818,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.041329848659818876,
602
+ "grad_norm": 0.015211164951324463,
603
+ "learning_rate": 0.0004941533131225639,
604
+ "loss": 0.05640285462141037,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.0418160821734638,
609
+ "grad_norm": 0.014646416530013084,
610
+ "learning_rate": 0.0004939367691641403,
611
+ "loss": 0.05714084580540657,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.04230231568710873,
616
+ "grad_norm": 0.014322340488433838,
617
+ "learning_rate": 0.0004937202252057167,
618
+ "loss": 0.04931890219449997,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.04278854920075366,
623
+ "grad_norm": 0.01420968770980835,
624
+ "learning_rate": 0.0004935036812472932,
625
+ "loss": 0.055171992629766464,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.04327478271439859,
630
+ "grad_norm": 0.01454883348196745,
631
+ "learning_rate": 0.0004932871372888696,
632
+ "loss": 0.05283398553729057,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.043761016228043514,
637
+ "grad_norm": 0.014116460457444191,
638
+ "learning_rate": 0.000493070593330446,
639
+ "loss": 0.05385218933224678,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.04424724974168845,
644
+ "grad_norm": 0.013518823310732841,
645
+ "learning_rate": 0.0004928540493720226,
646
+ "loss": 0.05461191385984421,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.04473348325533338,
651
+ "grad_norm": 0.014493877068161964,
652
+ "learning_rate": 0.000492637505413599,
653
+ "loss": 0.05393005907535553,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.045219716768978305,
658
+ "grad_norm": 0.014777368865907192,
659
+ "learning_rate": 0.0004924209614551754,
660
+ "loss": 0.05270910635590553,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.04570595028262323,
665
+ "grad_norm": 0.016071707010269165,
666
+ "learning_rate": 0.0004922044174967519,
667
+ "loss": 0.051418282091617584,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.04619218379626816,
672
+ "grad_norm": 0.015263018198311329,
673
+ "learning_rate": 0.0004919878735383283,
674
+ "loss": 0.05541301146149635,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.04667841730991309,
679
+ "grad_norm": 0.014630778692662716,
680
+ "learning_rate": 0.0004917713295799047,
681
+ "loss": 0.048078447580337524,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.047164650823558016,
686
+ "grad_norm": 0.01415814645588398,
687
+ "learning_rate": 0.0004915547856214811,
688
+ "loss": 0.050902191549539566,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.047650884337202944,
693
+ "grad_norm": 0.014978153631091118,
694
+ "learning_rate": 0.0004913382416630576,
695
+ "loss": 0.05329595506191254,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.04813711785084787,
700
+ "grad_norm": 0.015924474224448204,
701
+ "learning_rate": 0.000491121697704634,
702
+ "loss": 0.05228038877248764,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.0486233513644928,
707
+ "grad_norm": 0.016932446509599686,
708
+ "learning_rate": 0.0004909051537462105,
709
+ "loss": 0.04789048060774803,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.04910958487813773,
714
+ "grad_norm": 0.014380441047251225,
715
+ "learning_rate": 0.000490688609787787,
716
+ "loss": 0.05090918019413948,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.049595818391782655,
721
+ "grad_norm": 0.013156956993043423,
722
+ "learning_rate": 0.0004904720658293634,
723
+ "loss": 0.050421878695487976,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.05008205190542758,
728
+ "grad_norm": 0.014012029394507408,
729
+ "learning_rate": 0.0004902555218709398,
730
+ "loss": 0.051365867257118225,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.05056828541907251,
735
+ "grad_norm": 0.016230063512921333,
736
+ "learning_rate": 0.0004900389779125162,
737
+ "loss": 0.05458507314324379,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.05105451893271744,
742
+ "grad_norm": 0.016508348286151886,
743
+ "learning_rate": 0.0004898224339540927,
744
+ "loss": 0.04915777966380119,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.051540752446362366,
749
+ "grad_norm": 0.013956071808934212,
750
+ "learning_rate": 0.0004896058899956691,
751
+ "loss": 0.05078429728746414,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.052026985960007294,
756
+ "grad_norm": 0.014783553779125214,
757
+ "learning_rate": 0.0004893893460372455,
758
+ "loss": 0.055411092936992645,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.05251321947365222,
763
+ "grad_norm": 0.01457224227488041,
764
+ "learning_rate": 0.000489172802078822,
765
+ "loss": 0.05312196537852287,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.05299945298729715,
770
+ "grad_norm": 0.01438447181135416,
771
+ "learning_rate": 0.0004889562581203985,
772
+ "loss": 0.05112408846616745,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.05348568650094208,
777
+ "grad_norm": 0.013447507284581661,
778
+ "learning_rate": 0.0004887397141619749,
779
+ "loss": 0.05346091836690903,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.053971920014587005,
784
+ "grad_norm": 0.013833841308951378,
785
+ "learning_rate": 0.0004885231702035513,
786
+ "loss": 0.05139227956533432,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.05445815352823193,
791
+ "grad_norm": 0.014107326976954937,
792
+ "learning_rate": 0.0004883066262451278,
793
+ "loss": 0.05208476632833481,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.05494438704187686,
798
+ "grad_norm": 0.014210009947419167,
799
+ "learning_rate": 0.0004880900822867042,
800
+ "loss": 0.051973190158605576,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.05543062055552179,
805
+ "grad_norm": 0.013851170428097248,
806
+ "learning_rate": 0.00048787353832828066,
807
+ "loss": 0.05346987769007683,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.055916854069166716,
812
+ "grad_norm": 0.014027951285243034,
813
+ "learning_rate": 0.0004876569943698571,
814
+ "loss": 0.0536513589322567,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.056403087582811644,
819
+ "grad_norm": 0.01375369168817997,
820
+ "learning_rate": 0.00048744045041143353,
821
+ "loss": 0.046475693583488464,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.05688932109645657,
826
+ "grad_norm": 0.013953820802271366,
827
+ "learning_rate": 0.00048722390645300994,
828
+ "loss": 0.04701848700642586,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.0573755546101015,
833
+ "grad_norm": 0.013425101526081562,
834
+ "learning_rate": 0.00048700736249458645,
835
+ "loss": 0.049910061061382294,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.05786178812374643,
840
+ "grad_norm": 0.013514705933630466,
841
+ "learning_rate": 0.00048679081853616286,
842
+ "loss": 0.04916265979409218,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.058348021637391355,
847
+ "grad_norm": 0.013525016605854034,
848
+ "learning_rate": 0.00048657427457773927,
849
+ "loss": 0.051663145422935486,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.05883425515103628,
854
+ "grad_norm": 0.013960888609290123,
855
+ "learning_rate": 0.00048635773061931573,
856
+ "loss": 0.05123195797204971,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.05932048866468121,
861
+ "grad_norm": 0.013336379081010818,
862
+ "learning_rate": 0.0004861411866608922,
863
+ "loss": 0.051514942198991776,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.05980672217832614,
868
+ "grad_norm": 0.01395567785948515,
869
+ "learning_rate": 0.0004859246427024686,
870
+ "loss": 0.05156901478767395,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.060292955691971066,
875
+ "grad_norm": 0.014660103246569633,
876
+ "learning_rate": 0.000485708098744045,
877
+ "loss": 0.05552583932876587,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.060779189205615994,
882
+ "grad_norm": 0.015280052088201046,
883
+ "learning_rate": 0.0004854915547856215,
884
+ "loss": 0.05288073420524597,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.06126542271926092,
889
+ "grad_norm": 0.014118727296590805,
890
+ "learning_rate": 0.00048527501082719793,
891
+ "loss": 0.05014822259545326,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.061751656232905856,
896
+ "grad_norm": 0.012883221730589867,
897
+ "learning_rate": 0.00048505846686877434,
898
+ "loss": 0.047022633254528046,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.062237889746550784,
903
+ "grad_norm": 0.013538738712668419,
904
+ "learning_rate": 0.0004848419229103508,
905
+ "loss": 0.0478963665664196,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.0627241232601957,
910
+ "grad_norm": 0.01445820089429617,
911
+ "learning_rate": 0.00048462537895192727,
912
+ "loss": 0.05232877656817436,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.06321035677384064,
917
+ "grad_norm": 0.014887023717164993,
918
+ "learning_rate": 0.0004844088349935037,
919
+ "loss": 0.05257010459899902,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.06369659028748556,
924
+ "grad_norm": 0.012785518541932106,
925
+ "learning_rate": 0.00048419229103508014,
926
+ "loss": 0.047049641609191895,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.0641828238011305,
931
+ "grad_norm": 0.013942530378699303,
932
+ "learning_rate": 0.0004839757470766566,
933
+ "loss": 0.0465623214840889,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.06466905731477542,
938
+ "grad_norm": 0.01371311116963625,
939
+ "learning_rate": 0.000483759203118233,
940
+ "loss": 0.05197728052735329,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.06515529082842035,
945
+ "grad_norm": 0.013434289954602718,
946
+ "learning_rate": 0.0004835426591598094,
947
+ "loss": 0.052130453288555145,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.06564152434206527,
952
+ "grad_norm": 0.013716142624616623,
953
+ "learning_rate": 0.00048332611520138593,
954
+ "loss": 0.0489724799990654,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.0661277578557102,
959
+ "grad_norm": 0.014278166927397251,
960
+ "learning_rate": 0.00048310957124296234,
961
+ "loss": 0.053303975611925125,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.06661399136935513,
966
+ "grad_norm": 0.012410344555974007,
967
+ "learning_rate": 0.00048289302728453875,
968
+ "loss": 0.047432396560907364,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.06710022488300006,
973
+ "grad_norm": 0.014322999864816666,
974
+ "learning_rate": 0.0004826764833261152,
975
+ "loss": 0.044917941093444824,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.06758645839664498,
980
+ "grad_norm": 0.013892477378249168,
981
+ "learning_rate": 0.0004824599393676917,
982
+ "loss": 0.04862549155950546,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.06807269191028992,
987
+ "grad_norm": 0.014628923498094082,
988
+ "learning_rate": 0.0004822433954092681,
989
+ "loss": 0.04563949257135391,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.06855892542393484,
994
+ "grad_norm": 0.01441571768373251,
995
+ "learning_rate": 0.0004820268514508445,
996
+ "loss": 0.05193951725959778,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.06904515893757977,
1001
+ "grad_norm": 0.013662286102771759,
1002
+ "learning_rate": 0.000481810307492421,
1003
+ "loss": 0.053142473101615906,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.0695313924512247,
1008
+ "grad_norm": 0.01385200209915638,
1009
+ "learning_rate": 0.0004815937635339974,
1010
+ "loss": 0.049050040543079376,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.07001762596486963,
1015
+ "grad_norm": 0.013972636312246323,
1016
+ "learning_rate": 0.0004813772195755738,
1017
+ "loss": 0.04852229356765747,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.07050385947851456,
1022
+ "grad_norm": 0.013097552582621574,
1023
+ "learning_rate": 0.0004811606756171503,
1024
+ "loss": 0.04825061932206154,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.07099009299215948,
1029
+ "grad_norm": 0.014583770185709,
1030
+ "learning_rate": 0.00048094413165872675,
1031
+ "loss": 0.04968678206205368,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.07147632650580442,
1036
+ "grad_norm": 0.013736591674387455,
1037
+ "learning_rate": 0.00048072758770030316,
1038
+ "loss": 0.04935719817876816,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.07196256001944934,
1043
+ "grad_norm": 0.01634318009018898,
1044
+ "learning_rate": 0.0004805110437418796,
1045
+ "loss": 0.04974578693509102,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.07244879353309427,
1050
+ "grad_norm": 0.015374761074781418,
1051
+ "learning_rate": 0.0004802944997834561,
1052
+ "loss": 0.049081843346357346,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.0729350270467392,
1057
+ "grad_norm": 0.022077223286032677,
1058
+ "learning_rate": 0.0004800779558250325,
1059
+ "loss": 0.048187434673309326,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.07342126056038413,
1064
+ "grad_norm": 0.013797090388834476,
1065
+ "learning_rate": 0.0004798614118666089,
1066
+ "loss": 0.04925941675901413,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.07390749407402905,
1071
+ "grad_norm": 0.012974470853805542,
1072
+ "learning_rate": 0.00047964486790818536,
1073
+ "loss": 0.05173178389668465,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.07439372758767399,
1078
+ "grad_norm": 0.014286404475569725,
1079
+ "learning_rate": 0.0004794283239497618,
1080
+ "loss": 0.050716400146484375,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.0748799611013189,
1085
+ "grad_norm": 0.01411245297640562,
1086
+ "learning_rate": 0.00047921177999133823,
1087
+ "loss": 0.048320092260837555,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.07536619461496384,
1092
+ "grad_norm": 0.012909837998449802,
1093
+ "learning_rate": 0.0004789952360329147,
1094
+ "loss": 0.04881355166435242,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.07585242812860876,
1099
+ "grad_norm": 0.013224009424448013,
1100
+ "learning_rate": 0.00047877869207449116,
1101
+ "loss": 0.049997031688690186,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.0763386616422537,
1106
+ "grad_norm": 0.01402461901307106,
1107
+ "learning_rate": 0.00047856214811606756,
1108
+ "loss": 0.04961373656988144,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.07682489515589862,
1113
+ "grad_norm": 0.013286626897752285,
1114
+ "learning_rate": 0.00047834560415764397,
1115
+ "loss": 0.05098755285143852,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.07731112866954355,
1120
+ "grad_norm": 0.012627828866243362,
1121
+ "learning_rate": 0.0004781290601992205,
1122
+ "loss": 0.047741442918777466,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.07779736218318847,
1127
+ "grad_norm": 0.015962522476911545,
1128
+ "learning_rate": 0.0004779125162407969,
1129
+ "loss": 0.04710223153233528,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.07828359569683341,
1134
+ "grad_norm": 0.013488172553479671,
1135
+ "learning_rate": 0.0004776959722823733,
1136
+ "loss": 0.04565098136663437,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.07876982921047833,
1141
+ "grad_norm": 0.014020300470292568,
1142
+ "learning_rate": 0.00047747942832394977,
1143
+ "loss": 0.04857789725065231,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.07925606272412326,
1148
+ "grad_norm": 0.0131628243252635,
1149
+ "learning_rate": 0.00047726288436552623,
1150
+ "loss": 0.04956729710102081,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.07974229623776818,
1155
+ "grad_norm": 0.014108864590525627,
1156
+ "learning_rate": 0.00047704634040710264,
1157
+ "loss": 0.048625871539115906,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.08022852975141312,
1162
+ "grad_norm": 0.013255944475531578,
1163
+ "learning_rate": 0.0004768297964486791,
1164
+ "loss": 0.051274966448545456,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.08071476326505804,
1169
+ "grad_norm": 0.01369534432888031,
1170
+ "learning_rate": 0.00047661325249025556,
1171
+ "loss": 0.05284232646226883,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.08120099677870297,
1176
+ "grad_norm": 0.012559661641716957,
1177
+ "learning_rate": 0.00047639670853183197,
1178
+ "loss": 0.047550052404403687,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.0816872302923479,
1183
+ "grad_norm": 0.013325624167919159,
1184
+ "learning_rate": 0.0004761801645734084,
1185
+ "loss": 0.05017849802970886,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.08217346380599283,
1190
+ "grad_norm": 0.013111189007759094,
1191
+ "learning_rate": 0.00047596362061498484,
1192
+ "loss": 0.05004130303859711,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.08265969731963775,
1197
+ "grad_norm": 0.012854469940066338,
1198
+ "learning_rate": 0.0004757470766565613,
1199
+ "loss": 0.046727463603019714,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.08314593083328269,
1204
+ "grad_norm": 0.012945142574608326,
1205
+ "learning_rate": 0.0004755305326981377,
1206
+ "loss": 0.0487903356552124,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.0836321643469276,
1211
+ "grad_norm": 0.013737954199314117,
1212
+ "learning_rate": 0.0004753139887397142,
1213
+ "loss": 0.050357043743133545,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.08411839786057254,
1218
+ "grad_norm": 0.014556286856532097,
1219
+ "learning_rate": 0.00047509744478129064,
1220
+ "loss": 0.04766466096043587,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.08460463137421746,
1225
+ "grad_norm": 0.012378847226500511,
1226
+ "learning_rate": 0.00047488090082286705,
1227
+ "loss": 0.050095658749341965,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.0850908648878624,
1232
+ "grad_norm": 0.013026374392211437,
1233
+ "learning_rate": 0.0004746643568644435,
1234
+ "loss": 0.04977769777178764,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.08557709840150732,
1239
+ "grad_norm": 0.01283216942101717,
1240
+ "learning_rate": 0.0004744478129060199,
1241
+ "loss": 0.04770521819591522,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.08606333191515225,
1246
+ "grad_norm": 0.013749508187174797,
1247
+ "learning_rate": 0.0004742312689475964,
1248
+ "loss": 0.05241233855485916,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.08654956542879717,
1253
+ "grad_norm": 0.012581178918480873,
1254
+ "learning_rate": 0.0004740147249891728,
1255
+ "loss": 0.0489422082901001,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.08703579894244211,
1260
+ "grad_norm": 0.012903975322842598,
1261
+ "learning_rate": 0.00047379818103074925,
1262
+ "loss": 0.04803122952580452,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.08752203245608703,
1267
+ "grad_norm": 0.01354742981493473,
1268
+ "learning_rate": 0.0004735816370723257,
1269
+ "loss": 0.04757095128297806,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.08800826596973196,
1274
+ "grad_norm": 0.012947529554367065,
1275
+ "learning_rate": 0.0004733650931139021,
1276
+ "loss": 0.04278739169239998,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.0884944994833769,
1281
+ "grad_norm": 0.012779824435710907,
1282
+ "learning_rate": 0.0004731485491554786,
1283
+ "loss": 0.043701767921447754,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.08898073299702182,
1288
+ "grad_norm": 0.015440365299582481,
1289
+ "learning_rate": 0.00047293200519705504,
1290
+ "loss": 0.04710547626018524,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.08946696651066675,
1295
+ "grad_norm": 0.014790552668273449,
1296
+ "learning_rate": 0.00047271546123863145,
1297
+ "loss": 0.04864995926618576,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.08995320002431167,
1302
+ "grad_norm": 0.013025475665926933,
1303
+ "learning_rate": 0.00047249891728020786,
1304
+ "loss": 0.048677872866392136,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.09043943353795661,
1309
+ "grad_norm": 0.012939654290676117,
1310
+ "learning_rate": 0.0004722823733217843,
1311
+ "loss": 0.048086829483509064,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.09092566705160153,
1316
+ "grad_norm": 0.014714052900671959,
1317
+ "learning_rate": 0.0004720658293633608,
1318
+ "loss": 0.046955861151218414,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.09141190056524647,
1323
+ "grad_norm": 0.016071520745754242,
1324
+ "learning_rate": 0.0004718492854049372,
1325
+ "loss": 0.04889684543013573,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.09189813407889139,
1330
+ "grad_norm": 0.013739295303821564,
1331
+ "learning_rate": 0.00047163274144651366,
1332
+ "loss": 0.04471094533801079,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.09238436759253632,
1337
+ "grad_norm": 0.013854950666427612,
1338
+ "learning_rate": 0.0004714161974880901,
1339
+ "loss": 0.05034254863858223,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.09287060110618124,
1344
+ "grad_norm": 0.014590839855372906,
1345
+ "learning_rate": 0.0004711996535296665,
1346
+ "loss": 0.04467995837330818,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.09335683461982618,
1351
+ "grad_norm": 0.013509418815374374,
1352
+ "learning_rate": 0.000470983109571243,
1353
+ "loss": 0.04588858038187027,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.0938430681334711,
1358
+ "grad_norm": 0.013698785565793514,
1359
+ "learning_rate": 0.0004707665656128194,
1360
+ "loss": 0.047166857868433,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.09432930164711603,
1365
+ "grad_norm": 0.0140658775344491,
1366
+ "learning_rate": 0.00047055002165439586,
1367
+ "loss": 0.04402107745409012,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.09481553516076095,
1372
+ "grad_norm": 0.013415160588920116,
1373
+ "learning_rate": 0.00047033347769597227,
1374
+ "loss": 0.04619881138205528,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.09530176867440589,
1379
+ "grad_norm": 0.012797664850950241,
1380
+ "learning_rate": 0.00047011693373754873,
1381
+ "loss": 0.050395455211400986,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.09578800218805081,
1386
+ "grad_norm": 0.012887327931821346,
1387
+ "learning_rate": 0.0004699003897791252,
1388
+ "loss": 0.04903261736035347,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.09627423570169574,
1393
+ "grad_norm": 0.013623805716633797,
1394
+ "learning_rate": 0.0004696838458207016,
1395
+ "loss": 0.046161770820617676,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.09676046921534066,
1400
+ "grad_norm": 0.01358444057404995,
1401
+ "learning_rate": 0.00046946730186227806,
1402
+ "loss": 0.049518831074237823,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.0972467027289856,
1407
+ "grad_norm": 0.0119223203510046,
1408
+ "learning_rate": 0.0004692507579038545,
1409
+ "loss": 0.04992395266890526,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.09773293624263052,
1414
+ "grad_norm": 0.01385187916457653,
1415
+ "learning_rate": 0.00046903421394543093,
1416
+ "loss": 0.047110289335250854,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.09821916975627545,
1421
+ "grad_norm": 0.013527080416679382,
1422
+ "learning_rate": 0.00046881766998700734,
1423
+ "loss": 0.0463416688144207,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.09870540326992037,
1428
+ "grad_norm": 0.012739810161292553,
1429
+ "learning_rate": 0.0004686011260285838,
1430
+ "loss": 0.04933897405862808,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.09919163678356531,
1435
+ "grad_norm": 0.012938656844198704,
1436
+ "learning_rate": 0.00046838458207016027,
1437
+ "loss": 0.046786319464445114,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.09967787029721023,
1442
+ "grad_norm": 0.012762478552758694,
1443
+ "learning_rate": 0.0004681680381117367,
1444
+ "loss": 0.04662280157208443,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.10016410381085517,
1449
+ "grad_norm": 0.013727661222219467,
1450
+ "learning_rate": 0.00046795149415331314,
1451
+ "loss": 0.04554178938269615,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.10065033732450009,
1456
+ "grad_norm": 0.012557175941765308,
1457
+ "learning_rate": 0.0004677349501948896,
1458
+ "loss": 0.0443858876824379,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.10113657083814502,
1463
+ "grad_norm": 0.013734881766140461,
1464
+ "learning_rate": 0.000467518406236466,
1465
+ "loss": 0.0507718063890934,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.10162280435178994,
1470
+ "grad_norm": 0.013325158506631851,
1471
+ "learning_rate": 0.00046730186227804247,
1472
+ "loss": 0.04601585492491722,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.10210903786543488,
1477
+ "grad_norm": 0.013731631450355053,
1478
+ "learning_rate": 0.0004670853183196189,
1479
+ "loss": 0.05045069381594658,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.1025952713790798,
1484
+ "grad_norm": 0.013443227857351303,
1485
+ "learning_rate": 0.00046686877436119534,
1486
+ "loss": 0.05095263570547104,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.10308150489272473,
1491
+ "grad_norm": 0.013101069256663322,
1492
+ "learning_rate": 0.00046665223040277175,
1493
+ "loss": 0.04522746801376343,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.10356773840636965,
1498
+ "grad_norm": 0.01309758611023426,
1499
+ "learning_rate": 0.0004664356864443482,
1500
+ "loss": 0.05139251798391342,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.10405397192001459,
1505
+ "grad_norm": 0.01423716265708208,
1506
+ "learning_rate": 0.0004662191424859247,
1507
+ "loss": 0.04580753296613693,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.10454020543365951,
1512
+ "grad_norm": 0.013611307367682457,
1513
+ "learning_rate": 0.0004660025985275011,
1514
+ "loss": 0.04693499952554703,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.10502643894730444,
1519
+ "grad_norm": 0.012107494287192822,
1520
+ "learning_rate": 0.00046578605456907754,
1521
+ "loss": 0.040514662861824036,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.10551267246094938,
1526
+ "grad_norm": 0.012446893379092216,
1527
+ "learning_rate": 0.00046556951061065395,
1528
+ "loss": 0.04437100514769554,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.1059989059745943,
1533
+ "grad_norm": 0.013361264020204544,
1534
+ "learning_rate": 0.0004653529666522304,
1535
+ "loss": 0.04541579633951187,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.10648513948823923,
1540
+ "grad_norm": 0.014528200030326843,
1541
+ "learning_rate": 0.0004651364226938068,
1542
+ "loss": 0.04540681093931198,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.10697137300188415,
1547
+ "grad_norm": 0.013097711838781834,
1548
+ "learning_rate": 0.0004649198787353833,
1549
+ "loss": 0.04733249545097351,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.10745760651552909,
1554
+ "grad_norm": 0.012138712219893932,
1555
+ "learning_rate": 0.00046470333477695975,
1556
+ "loss": 0.041103072464466095,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.10794384002917401,
1561
+ "grad_norm": 0.013558696024119854,
1562
+ "learning_rate": 0.00046448679081853616,
1563
+ "loss": 0.04547586292028427,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.10843007354281894,
1568
+ "grad_norm": 0.012959490530192852,
1569
+ "learning_rate": 0.0004642702468601126,
1570
+ "loss": 0.04748288542032242,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.10891630705646387,
1575
+ "grad_norm": 0.013099278323352337,
1576
+ "learning_rate": 0.0004640537029016891,
1577
+ "loss": 0.04615773260593414,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.1094025405701088,
1582
+ "grad_norm": 0.013309430330991745,
1583
+ "learning_rate": 0.0004638371589432655,
1584
+ "loss": 0.046217963099479675,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.10988877408375372,
1589
+ "grad_norm": 0.013702673837542534,
1590
+ "learning_rate": 0.00046362061498484195,
1591
+ "loss": 0.04633708298206329,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.11037500759739866,
1596
+ "grad_norm": 0.012416890822350979,
1597
+ "learning_rate": 0.00046340407102641836,
1598
+ "loss": 0.04652000963687897,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.11086124111104358,
1603
+ "grad_norm": 0.013578424230217934,
1604
+ "learning_rate": 0.0004631875270679948,
1605
+ "loss": 0.045855749398469925,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.11134747462468851,
1610
+ "grad_norm": 0.01341484859585762,
1611
+ "learning_rate": 0.00046297098310957123,
1612
+ "loss": 0.045954007655382156,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.11183370813833343,
1617
+ "grad_norm": 0.01356878038495779,
1618
+ "learning_rate": 0.0004627544391511477,
1619
+ "loss": 0.04960376396775246,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.11231994165197837,
1624
+ "grad_norm": 0.013510368764400482,
1625
+ "learning_rate": 0.00046253789519272415,
1626
+ "loss": 0.050197429955005646,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.11280617516562329,
1631
+ "grad_norm": 0.01236965786665678,
1632
+ "learning_rate": 0.00046232135123430056,
1633
+ "loss": 0.04587166756391525,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.11329240867926822,
1638
+ "grad_norm": 0.013904470950365067,
1639
+ "learning_rate": 0.000462104807275877,
1640
+ "loss": 0.042365912348032,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.11377864219291314,
1645
+ "grad_norm": 0.013933866284787655,
1646
+ "learning_rate": 0.00046188826331745343,
1647
+ "loss": 0.04809553921222687,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.11426487570655808,
1652
+ "grad_norm": 0.01264379546046257,
1653
+ "learning_rate": 0.0004616717193590299,
1654
+ "loss": 0.04246288537979126,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.114751109220203,
1659
+ "grad_norm": 0.014554607681930065,
1660
+ "learning_rate": 0.0004614551754006063,
1661
+ "loss": 0.04417711868882179,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.11523734273384793,
1666
+ "grad_norm": 0.013950374908745289,
1667
+ "learning_rate": 0.00046123863144218277,
1668
+ "loss": 0.04846132546663284,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.11572357624749285,
1673
+ "grad_norm": 0.01437450759112835,
1674
+ "learning_rate": 0.00046102208748375923,
1675
+ "loss": 0.04603702574968338,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.11620980976113779,
1680
+ "grad_norm": 0.01343272253870964,
1681
+ "learning_rate": 0.00046080554352533564,
1682
+ "loss": 0.04540374130010605,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.11669604327478271,
1687
+ "grad_norm": 0.01439866703003645,
1688
+ "learning_rate": 0.0004605889995669121,
1689
+ "loss": 0.044120822101831436,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.11718227678842764,
1694
+ "grad_norm": 0.013281451538205147,
1695
+ "learning_rate": 0.0004603724556084885,
1696
+ "loss": 0.0447191521525383,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.11766851030207257,
1701
+ "grad_norm": 0.01365277823060751,
1702
+ "learning_rate": 0.00046015591165006497,
1703
+ "loss": 0.04392603039741516,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.1181547438157175,
1708
+ "grad_norm": 0.012808500789105892,
1709
+ "learning_rate": 0.00045993936769164143,
1710
+ "loss": 0.045375335961580276,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.11864097732936242,
1715
+ "grad_norm": 0.019573774188756943,
1716
+ "learning_rate": 0.00045972282373321784,
1717
+ "loss": 0.04594075307250023,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.11912721084300736,
1722
+ "grad_norm": 0.012512010522186756,
1723
+ "learning_rate": 0.0004595062797747943,
1724
+ "loss": 0.04253008961677551,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.11961344435665228,
1729
+ "grad_norm": 0.013517266139388084,
1730
+ "learning_rate": 0.0004592897358163707,
1731
+ "loss": 0.044225070625543594,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.12009967787029721,
1736
+ "grad_norm": 0.013940184377133846,
1737
+ "learning_rate": 0.0004590731918579472,
1738
+ "loss": 0.048725858330726624,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.12058591138394213,
1743
+ "grad_norm": 0.012305475771427155,
1744
+ "learning_rate": 0.00045885664789952364,
1745
+ "loss": 0.0423145554959774,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.12107214489758707,
1750
+ "grad_norm": 0.01465920265763998,
1751
+ "learning_rate": 0.00045864010394110004,
1752
+ "loss": 0.046329278498888016,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.12155837841123199,
1757
+ "grad_norm": 0.013230539858341217,
1758
+ "learning_rate": 0.0004584235599826765,
1759
+ "loss": 0.04509845748543739,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.12204461192487692,
1764
+ "grad_norm": 0.013825327157974243,
1765
+ "learning_rate": 0.0004582070160242529,
1766
+ "loss": 0.048688165843486786,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.12253084543852184,
1771
+ "grad_norm": 0.012687780894339085,
1772
+ "learning_rate": 0.0004579904720658294,
1773
+ "loss": 0.04412148520350456,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.12301707895216678,
1778
+ "grad_norm": 0.012400363571941853,
1779
+ "learning_rate": 0.00045777392810740584,
1780
+ "loss": 0.04364267364144325,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.12350331246581171,
1785
+ "grad_norm": 0.012946711853146553,
1786
+ "learning_rate": 0.00045755738414898225,
1787
+ "loss": 0.04309921711683273,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.12398954597945663,
1792
+ "grad_norm": 0.011557403020560741,
1793
+ "learning_rate": 0.0004573408401905587,
1794
+ "loss": 0.04354671388864517,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.12447577949310157,
1799
+ "grad_norm": 0.012404605746269226,
1800
+ "learning_rate": 0.0004571242962321351,
1801
+ "loss": 0.04381885379552841,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.12496201300674649,
1806
+ "grad_norm": 0.012919880449771881,
1807
+ "learning_rate": 0.0004569077522737116,
1808
+ "loss": 0.046965308487415314,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.1254482465203914,
1813
+ "grad_norm": 0.01323958020657301,
1814
+ "learning_rate": 0.000456691208315288,
1815
+ "loss": 0.046953219920396805,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.12593448003403634,
1820
+ "grad_norm": 0.012447348795831203,
1821
+ "learning_rate": 0.00045647466435686445,
1822
+ "loss": 0.04622210934758186,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.12642071354768128,
1827
+ "grad_norm": 0.012885344214737415,
1828
+ "learning_rate": 0.0004562581203984409,
1829
+ "loss": 0.04767267405986786,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.12690694706132621,
1834
+ "grad_norm": 0.012257659807801247,
1835
+ "learning_rate": 0.0004560415764400173,
1836
+ "loss": 0.04768814146518707,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.12739318057497112,
1841
+ "grad_norm": 0.012860888615250587,
1842
+ "learning_rate": 0.0004558250324815938,
1843
+ "loss": 0.044885408133268356,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.12787941408861606,
1848
+ "grad_norm": 0.013777688145637512,
1849
+ "learning_rate": 0.0004556084885231702,
1850
+ "loss": 0.04301109537482262,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.128365647602261,
1855
+ "grad_norm": 0.01291818730533123,
1856
+ "learning_rate": 0.00045539194456474665,
1857
+ "loss": 0.04803190380334854,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.12885188111590593,
1862
+ "grad_norm": 0.013355609960854053,
1863
+ "learning_rate": 0.0004551754006063231,
1864
+ "loss": 0.046383343636989594,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.12933811462955083,
1869
+ "grad_norm": 0.013425858691334724,
1870
+ "learning_rate": 0.0004549588566478995,
1871
+ "loss": 0.04359380900859833,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.12982434814319577,
1876
+ "grad_norm": 0.013060685247182846,
1877
+ "learning_rate": 0.000454742312689476,
1878
+ "loss": 0.042863719165325165,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.1303105816568407,
1883
+ "grad_norm": 0.012516407296061516,
1884
+ "learning_rate": 0.0004545257687310524,
1885
+ "loss": 0.044258859008550644,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.13079681517048564,
1890
+ "grad_norm": 0.013510235585272312,
1891
+ "learning_rate": 0.00045430922477262886,
1892
+ "loss": 0.04708000272512436,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.13128304868413054,
1897
+ "grad_norm": 0.013515228405594826,
1898
+ "learning_rate": 0.0004540926808142053,
1899
+ "loss": 0.04164845496416092,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.13176928219777548,
1904
+ "grad_norm": 0.013070745393633842,
1905
+ "learning_rate": 0.00045387613685578173,
1906
+ "loss": 0.042722634971141815,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.1322555157114204,
1911
+ "grad_norm": 0.013084226287901402,
1912
+ "learning_rate": 0.0004536595928973582,
1913
+ "loss": 0.04951436445116997,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.13274174922506535,
1918
+ "grad_norm": 0.013800851069390774,
1919
+ "learning_rate": 0.0004534430489389346,
1920
+ "loss": 0.04540230333805084,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.13322798273871025,
1925
+ "grad_norm": 0.013227920047938824,
1926
+ "learning_rate": 0.00045322650498051106,
1927
+ "loss": 0.04467228800058365,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.1337142162523552,
1932
+ "grad_norm": 0.013262571766972542,
1933
+ "learning_rate": 0.00045300996102208747,
1934
+ "loss": 0.047673095017671585,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.13420044976600012,
1939
+ "grad_norm": 0.013415283523499966,
1940
+ "learning_rate": 0.00045279341706366393,
1941
+ "loss": 0.04767049476504326,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.13468668327964506,
1946
+ "grad_norm": 0.013086548075079918,
1947
+ "learning_rate": 0.0004525768731052404,
1948
+ "loss": 0.04454663023352623,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.13517291679328997,
1953
+ "grad_norm": 0.01342064794152975,
1954
+ "learning_rate": 0.0004523603291468168,
1955
+ "loss": 0.04365311190485954,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.1356591503069349,
1960
+ "grad_norm": 0.012262348085641861,
1961
+ "learning_rate": 0.00045214378518839326,
1962
+ "loss": 0.0431094653904438,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.13614538382057984,
1967
+ "grad_norm": 0.01250699907541275,
1968
+ "learning_rate": 0.0004519272412299697,
1969
+ "loss": 0.047100793570280075,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.13663161733422477,
1974
+ "grad_norm": 0.013160230591893196,
1975
+ "learning_rate": 0.00045171069727154614,
1976
+ "loss": 0.04024267569184303,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.13711785084786968,
1981
+ "grad_norm": 0.012607301585376263,
1982
+ "learning_rate": 0.00045149415331312254,
1983
+ "loss": 0.045909713953733444,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.1376040843615146,
1988
+ "grad_norm": 0.012894994579255581,
1989
+ "learning_rate": 0.000451277609354699,
1990
+ "loss": 0.040540628135204315,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.13809031787515955,
1995
+ "grad_norm": 0.011799152009189129,
1996
+ "learning_rate": 0.00045106106539627547,
1997
+ "loss": 0.04241633787751198,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.13857655138880448,
2002
+ "grad_norm": 0.01336440909653902,
2003
+ "learning_rate": 0.0004508445214378519,
2004
+ "loss": 0.04232136532664299,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.1390627849024494,
2009
+ "grad_norm": 0.012081057764589787,
2010
+ "learning_rate": 0.00045062797747942834,
2011
+ "loss": 0.041226331144571304,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.13954901841609432,
2016
+ "grad_norm": 0.012889630161225796,
2017
+ "learning_rate": 0.0004504114335210048,
2018
+ "loss": 0.04249771684408188,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.14003525192973926,
2023
+ "grad_norm": 0.01271852944046259,
2024
+ "learning_rate": 0.0004501948895625812,
2025
+ "loss": 0.04003441333770752,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.1405214854433842,
2030
+ "grad_norm": 0.011959097348153591,
2031
+ "learning_rate": 0.00044997834560415767,
2032
+ "loss": 0.045840661972761154,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.14100771895702913,
2037
+ "grad_norm": 0.012321273796260357,
2038
+ "learning_rate": 0.0004497618016457341,
2039
+ "loss": 0.044145576655864716,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.14149395247067403,
2044
+ "grad_norm": 0.012649307027459145,
2045
+ "learning_rate": 0.00044954525768731054,
2046
+ "loss": 0.04709974676370621,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.14198018598431897,
2051
+ "grad_norm": 0.012173818424344063,
2052
+ "learning_rate": 0.00044932871372888695,
2053
+ "loss": 0.0444054901599884,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.1424664194979639,
2058
+ "grad_norm": 0.012172984890639782,
2059
+ "learning_rate": 0.0004491121697704634,
2060
+ "loss": 0.043884966522455215,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.14295265301160884,
2065
+ "grad_norm": 0.012437058612704277,
2066
+ "learning_rate": 0.0004488956258120399,
2067
+ "loss": 0.042075954377651215,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.14343888652525374,
2072
+ "grad_norm": 0.013454178348183632,
2073
+ "learning_rate": 0.0004486790818536163,
2074
+ "loss": 0.04017173871397972,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.14392512003889868,
2079
+ "grad_norm": 0.013156874105334282,
2080
+ "learning_rate": 0.00044846253789519275,
2081
+ "loss": 0.04575172811746597,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.14441135355254361,
2086
+ "grad_norm": 0.01319118496030569,
2087
+ "learning_rate": 0.00044824599393676915,
2088
+ "loss": 0.045236412435770035,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.14489758706618855,
2093
+ "grad_norm": 0.013993004336953163,
2094
+ "learning_rate": 0.0004480294499783456,
2095
+ "loss": 0.04502469301223755,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.14538382057983346,
2100
+ "grad_norm": 0.013321452774107456,
2101
+ "learning_rate": 0.000447812906019922,
2102
+ "loss": 0.04728579893708229,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.1458700540934784,
2107
+ "grad_norm": 0.01403715554624796,
2108
+ "learning_rate": 0.0004475963620614985,
2109
+ "loss": 0.045453399419784546,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.14635628760712333,
2114
+ "grad_norm": 0.01203235611319542,
2115
+ "learning_rate": 0.00044737981810307495,
2116
+ "loss": 0.04470015689730644,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.14684252112076826,
2121
+ "grad_norm": 0.012460272759199142,
2122
+ "learning_rate": 0.00044716327414465136,
2123
+ "loss": 0.04414396733045578,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.14732875463441317,
2128
+ "grad_norm": 0.012789933942258358,
2129
+ "learning_rate": 0.0004469467301862278,
2130
+ "loss": 0.045197367668151855,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.1478149881480581,
2135
+ "grad_norm": 0.012114706449210644,
2136
+ "learning_rate": 0.0004467301862278043,
2137
+ "loss": 0.04679146781563759,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.14830122166170304,
2142
+ "grad_norm": 0.013335728086531162,
2143
+ "learning_rate": 0.0004465136422693807,
2144
+ "loss": 0.04703502729535103,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.14878745517534797,
2149
+ "grad_norm": 0.013688938692212105,
2150
+ "learning_rate": 0.0004462970983109571,
2151
+ "loss": 0.04477003589272499,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.14927368868899288,
2156
+ "grad_norm": 0.015975935384631157,
2157
+ "learning_rate": 0.00044608055435253356,
2158
+ "loss": 0.039103079587221146,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.1497599222026378,
2163
+ "grad_norm": 0.021375538781285286,
2164
+ "learning_rate": 0.00044586401039411,
2165
+ "loss": 0.04525827243924141,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.15024615571628275,
2170
+ "grad_norm": 0.013859556056559086,
2171
+ "learning_rate": 0.00044564746643568643,
2172
+ "loss": 0.040207602083683014,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.15073238922992768,
2177
+ "grad_norm": 0.014008664526045322,
2178
+ "learning_rate": 0.0004454309224772629,
2179
+ "loss": 0.04224986582994461,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.1512186227435726,
2184
+ "grad_norm": 0.013171757571399212,
2185
+ "learning_rate": 0.00044521437851883936,
2186
+ "loss": 0.04041281342506409,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.15170485625721752,
2191
+ "grad_norm": 0.012498957104980946,
2192
+ "learning_rate": 0.00044499783456041576,
2193
+ "loss": 0.04608509689569473,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.15219108977086246,
2198
+ "grad_norm": 0.01349857822060585,
2199
+ "learning_rate": 0.0004447812906019922,
2200
+ "loss": 0.04138585925102234,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.1526773232845074,
2205
+ "grad_norm": 0.012910005636513233,
2206
+ "learning_rate": 0.0004445647466435687,
2207
+ "loss": 0.04443095251917839,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.1531635567981523,
2212
+ "grad_norm": 0.012624798342585564,
2213
+ "learning_rate": 0.0004443482026851451,
2214
+ "loss": 0.04364083707332611,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.15364979031179724,
2219
+ "grad_norm": 0.012974039651453495,
2220
+ "learning_rate": 0.0004441316587267215,
2221
+ "loss": 0.04160245135426521,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.15413602382544217,
2226
+ "grad_norm": 0.012760896235704422,
2227
+ "learning_rate": 0.00044391511476829797,
2228
+ "loss": 0.043020255863666534,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.1546222573390871,
2233
+ "grad_norm": 0.012537539005279541,
2234
+ "learning_rate": 0.00044369857080987443,
2235
+ "loss": 0.040603913366794586,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.155108490852732,
2240
+ "grad_norm": 0.013049988076090813,
2241
+ "learning_rate": 0.00044348202685145084,
2242
+ "loss": 0.04566510021686554,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.15559472436637695,
2247
+ "grad_norm": 0.013658895157277584,
2248
+ "learning_rate": 0.0004432654828930273,
2249
+ "loss": 0.04507540911436081,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.15608095788002188,
2254
+ "grad_norm": 0.013222133740782738,
2255
+ "learning_rate": 0.00044304893893460376,
2256
+ "loss": 0.043621163815259933,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.15656719139366682,
2261
+ "grad_norm": 0.01235352922230959,
2262
+ "learning_rate": 0.00044283239497618017,
2263
+ "loss": 0.03997144475579262,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.15705342490731172,
2268
+ "grad_norm": 0.014096193015575409,
2269
+ "learning_rate": 0.0004426158510177566,
2270
+ "loss": 0.04365356266498566,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.15753965842095666,
2275
+ "grad_norm": 0.015181286260485649,
2276
+ "learning_rate": 0.00044239930705933304,
2277
+ "loss": 0.04272611811757088,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.1580258919346016,
2282
+ "grad_norm": 0.013680013827979565,
2283
+ "learning_rate": 0.0004421827631009095,
2284
+ "loss": 0.04307127743959427,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.15851212544824653,
2289
+ "grad_norm": 0.014296046458184719,
2290
+ "learning_rate": 0.0004419662191424859,
2291
+ "loss": 0.04622381925582886,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.15899835896189146,
2296
+ "grad_norm": 0.012733468785881996,
2297
+ "learning_rate": 0.0004417496751840624,
2298
+ "loss": 0.03894417732954025,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.15948459247553637,
2303
+ "grad_norm": 0.01324967946857214,
2304
+ "learning_rate": 0.00044153313122563884,
2305
+ "loss": 0.041985172778367996,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.1599708259891813,
2310
+ "grad_norm": 0.013749434612691402,
2311
+ "learning_rate": 0.00044131658726721525,
2312
+ "loss": 0.04456296190619469,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.16045705950282624,
2317
+ "grad_norm": 0.013954056426882744,
2318
+ "learning_rate": 0.0004411000433087917,
2319
+ "loss": 0.03988424688577652,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.16094329301647117,
2324
+ "grad_norm": 0.013043215498328209,
2325
+ "learning_rate": 0.00044088349935036817,
2326
+ "loss": 0.043786101043224335,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.16142952653011608,
2331
+ "grad_norm": 0.013881723396480083,
2332
+ "learning_rate": 0.0004406669553919446,
2333
+ "loss": 0.042584631592035294,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.16191576004376101,
2338
+ "grad_norm": 0.024254988878965378,
2339
+ "learning_rate": 0.000440450411433521,
2340
+ "loss": 0.041385795921087265,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.16240199355740595,
2345
+ "grad_norm": 0.013241549022495747,
2346
+ "learning_rate": 0.00044023386747509745,
2347
+ "loss": 0.04577038064599037,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.16288822707105088,
2352
+ "grad_norm": 0.012925197370350361,
2353
+ "learning_rate": 0.0004400173235166739,
2354
+ "loss": 0.043533001095056534,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.1633744605846958,
2359
+ "grad_norm": 0.015469362027943134,
2360
+ "learning_rate": 0.0004398007795582503,
2361
+ "loss": 0.04057354852557182,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.16386069409834073,
2366
+ "grad_norm": 0.013349615968763828,
2367
+ "learning_rate": 0.0004395842355998268,
2368
+ "loss": 0.040556591004133224,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.16434692761198566,
2373
+ "grad_norm": 0.01400417648255825,
2374
+ "learning_rate": 0.00043936769164140324,
2375
+ "loss": 0.04649532213807106,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.1648331611256306,
2380
+ "grad_norm": 0.013481558300554752,
2381
+ "learning_rate": 0.00043915114768297965,
2382
+ "loss": 0.045361705124378204,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.1653193946392755,
2387
+ "grad_norm": 0.012619422748684883,
2388
+ "learning_rate": 0.00043893460372455606,
2389
+ "loss": 0.044229768216609955,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.16580562815292044,
2394
+ "grad_norm": 0.012794380076229572,
2395
+ "learning_rate": 0.0004387180597661325,
2396
+ "loss": 0.04291492700576782,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.16629186166656537,
2401
+ "grad_norm": 0.012707801535725594,
2402
+ "learning_rate": 0.000438501515807709,
2403
+ "loss": 0.04520220682024956,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.1667780951802103,
2408
+ "grad_norm": 0.012959362007677555,
2409
+ "learning_rate": 0.0004382849718492854,
2410
+ "loss": 0.044066332280635834,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.1672643286938552,
2415
+ "grad_norm": 0.013244127854704857,
2416
+ "learning_rate": 0.00043806842789086186,
2417
+ "loss": 0.04165942221879959,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.16775056220750015,
2422
+ "grad_norm": 0.013277621008455753,
2423
+ "learning_rate": 0.0004378518839324383,
2424
+ "loss": 0.042861152440309525,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.16823679572114508,
2429
+ "grad_norm": 0.014456474222242832,
2430
+ "learning_rate": 0.0004376353399740147,
2431
+ "loss": 0.043973326683044434,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.16872302923479002,
2436
+ "grad_norm": 0.013204771094024181,
2437
+ "learning_rate": 0.00043741879601559114,
2438
+ "loss": 0.04020939767360687,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.16920926274843492,
2443
+ "grad_norm": 0.01339389756321907,
2444
+ "learning_rate": 0.00043720225205716765,
2445
+ "loss": 0.044231537729501724,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.16969549626207986,
2450
+ "grad_norm": 0.013181479647755623,
2451
+ "learning_rate": 0.00043698570809874406,
2452
+ "loss": 0.04035132750868797,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.1701817297757248,
2457
+ "grad_norm": 0.01319100335240364,
2458
+ "learning_rate": 0.00043676916414032047,
2459
+ "loss": 0.041138630360364914,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.17066796328936973,
2464
+ "grad_norm": 0.013196668587625027,
2465
+ "learning_rate": 0.00043655262018189693,
2466
+ "loss": 0.0432586669921875,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.17115419680301464,
2471
+ "grad_norm": 0.012878959998488426,
2472
+ "learning_rate": 0.0004363360762234734,
2473
+ "loss": 0.04325208067893982,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.17164043031665957,
2478
+ "grad_norm": 0.013054635375738144,
2479
+ "learning_rate": 0.0004361195322650498,
2480
+ "loss": 0.04027051478624344,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.1721266638303045,
2485
+ "grad_norm": 0.012908203527331352,
2486
+ "learning_rate": 0.00043590298830662626,
2487
+ "loss": 0.041716594249010086,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.17261289734394944,
2492
+ "grad_norm": 0.01317793782800436,
2493
+ "learning_rate": 0.0004356864443482027,
2494
+ "loss": 0.043837547302246094,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.17309913085759435,
2499
+ "grad_norm": 0.012746147811412811,
2500
+ "learning_rate": 0.00043546990038977913,
2501
+ "loss": 0.042207542806863785,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.17358536437123928,
2506
+ "grad_norm": 0.013095092959702015,
2507
+ "learning_rate": 0.00043525335643135554,
2508
+ "loss": 0.041597478091716766,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.17407159788488422,
2513
+ "grad_norm": 0.012917965650558472,
2514
+ "learning_rate": 0.000435036812472932,
2515
+ "loss": 0.04148181900382042,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.17455783139852915,
2520
+ "grad_norm": 0.012487178668379784,
2521
+ "learning_rate": 0.00043482026851450847,
2522
+ "loss": 0.0444754958152771,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.17504406491217406,
2527
+ "grad_norm": 0.013131354004144669,
2528
+ "learning_rate": 0.0004346037245560849,
2529
+ "loss": 0.04344499856233597,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.175530298425819,
2534
+ "grad_norm": 0.01206018216907978,
2535
+ "learning_rate": 0.00043438718059766134,
2536
+ "loss": 0.0443342961370945,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.17601653193946393,
2541
+ "grad_norm": 0.012735814787447453,
2542
+ "learning_rate": 0.0004341706366392378,
2543
+ "loss": 0.04247370362281799,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.17650276545310886,
2548
+ "grad_norm": 0.013233880512416363,
2549
+ "learning_rate": 0.0004339540926808142,
2550
+ "loss": 0.04364258423447609,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.1769889989667538,
2555
+ "grad_norm": 0.011798190884292126,
2556
+ "learning_rate": 0.0004337375487223906,
2557
+ "loss": 0.04286571219563484,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.1774752324803987,
2562
+ "grad_norm": 0.013125062920153141,
2563
+ "learning_rate": 0.00043352100476396713,
2564
+ "loss": 0.042206212878227234,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.17796146599404364,
2569
+ "grad_norm": 0.01312132366001606,
2570
+ "learning_rate": 0.00043330446080554354,
2571
+ "loss": 0.04172408580780029,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.17844769950768857,
2576
+ "grad_norm": 0.013185324147343636,
2577
+ "learning_rate": 0.00043308791684711995,
2578
+ "loss": 0.04057041555643082,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.1789339330213335,
2583
+ "grad_norm": 0.01327922660857439,
2584
+ "learning_rate": 0.0004328713728886964,
2585
+ "loss": 0.04335692152380943,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.17942016653497841,
2590
+ "grad_norm": 0.012769242748618126,
2591
+ "learning_rate": 0.0004326548289302729,
2592
+ "loss": 0.04284435138106346,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.17990640004862335,
2597
+ "grad_norm": 0.01233165618032217,
2598
+ "learning_rate": 0.0004324382849718493,
2599
+ "loss": 0.04404669255018234,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.18039263356226828,
2604
+ "grad_norm": 0.013214781880378723,
2605
+ "learning_rate": 0.00043222174101342574,
2606
+ "loss": 0.04175690561532974,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.18087886707591322,
2611
+ "grad_norm": 0.01275329478085041,
2612
+ "learning_rate": 0.0004320051970550022,
2613
+ "loss": 0.041405126452445984,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.18136510058955813,
2618
+ "grad_norm": 0.01328456960618496,
2619
+ "learning_rate": 0.0004317886530965786,
2620
+ "loss": 0.041448358446359634,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.18185133410320306,
2625
+ "grad_norm": 0.012136021628975868,
2626
+ "learning_rate": 0.000431572109138155,
2627
+ "loss": 0.0412047803401947,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.182337567616848,
2632
+ "grad_norm": 0.013323111459612846,
2633
+ "learning_rate": 0.00043135556517973154,
2634
+ "loss": 0.04109674692153931,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.18282380113049293,
2639
+ "grad_norm": 0.012168524786829948,
2640
+ "learning_rate": 0.00043113902122130795,
2641
+ "loss": 0.03975171968340874,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.18331003464413784,
2646
+ "grad_norm": 0.012705015018582344,
2647
+ "learning_rate": 0.00043092247726288436,
2648
+ "loss": 0.04031871259212494,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.18379626815778277,
2653
+ "grad_norm": 0.012929301708936691,
2654
+ "learning_rate": 0.0004307059333044608,
2655
+ "loss": 0.04109346121549606,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.1842825016714277,
2660
+ "grad_norm": 0.01323498971760273,
2661
+ "learning_rate": 0.0004304893893460373,
2662
+ "loss": 0.04061099886894226,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.18476873518507264,
2667
+ "grad_norm": 0.012162365019321442,
2668
+ "learning_rate": 0.0004302728453876137,
2669
+ "loss": 0.04370151460170746,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.18525496869871755,
2674
+ "grad_norm": 0.013215114362537861,
2675
+ "learning_rate": 0.0004300563014291901,
2676
+ "loss": 0.043640945106744766,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.18574120221236248,
2681
+ "grad_norm": 0.014480505138635635,
2682
+ "learning_rate": 0.0004298397574707666,
2683
+ "loss": 0.0401332825422287,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.18622743572600742,
2688
+ "grad_norm": 0.011950782500207424,
2689
+ "learning_rate": 0.000429623213512343,
2690
+ "loss": 0.03980204835534096,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.18671366923965235,
2695
+ "grad_norm": 0.013191349804401398,
2696
+ "learning_rate": 0.00042940666955391943,
2697
+ "loss": 0.043324604630470276,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.18719990275329726,
2702
+ "grad_norm": 0.012773512862622738,
2703
+ "learning_rate": 0.0004291901255954959,
2704
+ "loss": 0.04440087080001831,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.1876861362669422,
2709
+ "grad_norm": 0.016553249210119247,
2710
+ "learning_rate": 0.00042897358163707236,
2711
+ "loss": 0.04306691139936447,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.18817236978058713,
2716
+ "grad_norm": 0.013532488606870174,
2717
+ "learning_rate": 0.00042875703767864876,
2718
+ "loss": 0.04341765493154526,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.18865860329423206,
2723
+ "grad_norm": 0.012603385373950005,
2724
+ "learning_rate": 0.00042854049372022517,
2725
+ "loss": 0.04074953496456146,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.18914483680787697,
2730
+ "grad_norm": 0.012489400804042816,
2731
+ "learning_rate": 0.0004283239497618017,
2732
+ "loss": 0.04247622191905975,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.1896310703215219,
2737
+ "grad_norm": 0.012240837328135967,
2738
+ "learning_rate": 0.0004281074058033781,
2739
+ "loss": 0.04268632456660271,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.19011730383516684,
2744
+ "grad_norm": 0.013000483624637127,
2745
+ "learning_rate": 0.0004278908618449545,
2746
+ "loss": 0.04263956472277641,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.19060353734881177,
2751
+ "grad_norm": 0.013262342661619186,
2752
+ "learning_rate": 0.000427674317886531,
2753
+ "loss": 0.04327172785997391,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.19108977086245668,
2758
+ "grad_norm": 0.012193962000310421,
2759
+ "learning_rate": 0.00042745777392810743,
2760
+ "loss": 0.04050281643867493,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.19157600437610162,
2765
+ "grad_norm": 0.01297039445489645,
2766
+ "learning_rate": 0.00042724122996968384,
2767
+ "loss": 0.043341029435396194,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.19206223788974655,
2772
+ "grad_norm": 0.012754146941006184,
2773
+ "learning_rate": 0.0004270246860112603,
2774
+ "loss": 0.04335411265492439,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.19254847140339149,
2779
+ "grad_norm": 0.012473897077143192,
2780
+ "learning_rate": 0.00042680814205283676,
2781
+ "loss": 0.047285955399274826,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.19303470491703642,
2786
+ "grad_norm": 0.013141893781721592,
2787
+ "learning_rate": 0.00042659159809441317,
2788
+ "loss": 0.04140400514006615,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.19352093843068133,
2793
+ "grad_norm": 0.013764769770205021,
2794
+ "learning_rate": 0.0004263750541359896,
2795
+ "loss": 0.04291301965713501,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.19400717194432626,
2800
+ "grad_norm": 0.012824390083551407,
2801
+ "learning_rate": 0.0004261585101775661,
2802
+ "loss": 0.04110845923423767,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.1944934054579712,
2807
+ "grad_norm": 0.01275946106761694,
2808
+ "learning_rate": 0.0004259419662191425,
2809
+ "loss": 0.040954750031232834,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.19497963897161613,
2814
+ "grad_norm": 0.01388461422175169,
2815
+ "learning_rate": 0.0004257254222607189,
2816
+ "loss": 0.04052408039569855,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.19546587248526104,
2821
+ "grad_norm": 0.01222914643585682,
2822
+ "learning_rate": 0.0004255088783022954,
2823
+ "loss": 0.04399825260043144,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.19595210599890597,
2828
+ "grad_norm": 0.014072393998503685,
2829
+ "learning_rate": 0.00042529233434387184,
2830
+ "loss": 0.04339051991701126,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 0.1964383395125509,
2835
+ "grad_norm": 0.013117542490363121,
2836
+ "learning_rate": 0.00042507579038544824,
2837
+ "loss": 0.0392363965511322,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 0.19692457302619584,
2842
+ "grad_norm": 0.013823696412146091,
2843
+ "learning_rate": 0.00042485924642702465,
2844
+ "loss": 0.041793856769800186,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 0.19741080653984075,
2849
+ "grad_norm": 0.013191847130656242,
2850
+ "learning_rate": 0.00042464270246860117,
2851
+ "loss": 0.03959915041923523,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 0.19789704005348568,
2856
+ "grad_norm": 0.013398957438766956,
2857
+ "learning_rate": 0.0004244261585101776,
2858
+ "loss": 0.04030834510922432,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 0.19838327356713062,
2863
+ "grad_norm": 0.012999581173062325,
2864
+ "learning_rate": 0.000424209614551754,
2865
+ "loss": 0.04188532754778862,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 0.19886950708077555,
2870
+ "grad_norm": 0.012906461954116821,
2871
+ "learning_rate": 0.0004239930705933305,
2872
+ "loss": 0.038475632667541504,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 0.19935574059442046,
2877
+ "grad_norm": 0.012177183292806149,
2878
+ "learning_rate": 0.0004237765266349069,
2879
+ "loss": 0.04297543317079544,
2880
+ "step": 410
2881
+ },
2882
+ {
2883
+ "epoch": 0.1998419741080654,
2884
+ "grad_norm": 0.014171319082379341,
2885
+ "learning_rate": 0.0004235599826764833,
2886
+ "loss": 0.044866181910037994,
2887
+ "step": 411
2888
+ },
2889
+ {
2890
+ "epoch": 0.20032820762171033,
2891
+ "grad_norm": 0.020065568387508392,
2892
+ "learning_rate": 0.0004233434387180597,
2893
+ "loss": 0.04507064446806908,
2894
+ "step": 412
2895
+ },
2896
+ {
2897
+ "epoch": 0.20081444113535526,
2898
+ "grad_norm": 0.013104676268994808,
2899
+ "learning_rate": 0.00042312689475963624,
2900
+ "loss": 0.04455232620239258,
2901
+ "step": 413
2902
+ },
2903
+ {
2904
+ "epoch": 0.20130067464900017,
2905
+ "grad_norm": 0.01339991670101881,
2906
+ "learning_rate": 0.00042291035080121265,
2907
+ "loss": 0.04439764842391014,
2908
+ "step": 414
2909
+ },
2910
+ {
2911
+ "epoch": 0.2017869081626451,
2912
+ "grad_norm": 0.013507516123354435,
2913
+ "learning_rate": 0.00042269380684278906,
2914
+ "loss": 0.039270710200071335,
2915
+ "step": 415
2916
+ },
2917
+ {
2918
+ "epoch": 0.20227314167629004,
2919
+ "grad_norm": 0.014201906509697437,
2920
+ "learning_rate": 0.0004224772628843656,
2921
+ "loss": 0.03916134312748909,
2922
+ "step": 416
2923
+ },
2924
+ {
2925
+ "epoch": 0.20275937518993498,
2926
+ "grad_norm": 0.013844204135239124,
2927
+ "learning_rate": 0.000422260718925942,
2928
+ "loss": 0.04250453785061836,
2929
+ "step": 417
2930
+ },
2931
+ {
2932
+ "epoch": 0.20324560870357988,
2933
+ "grad_norm": 0.013091648928821087,
2934
+ "learning_rate": 0.0004220441749675184,
2935
+ "loss": 0.03664560243487358,
2936
+ "step": 418
2937
+ },
2938
+ {
2939
+ "epoch": 0.20373184221722482,
2940
+ "grad_norm": 0.013341261073946953,
2941
+ "learning_rate": 0.00042182763100909485,
2942
+ "loss": 0.04148003086447716,
2943
+ "step": 419
2944
+ },
2945
+ {
2946
+ "epoch": 0.20421807573086975,
2947
+ "grad_norm": 0.013206852599978447,
2948
+ "learning_rate": 0.0004216110870506713,
2949
+ "loss": 0.04070326313376427,
2950
+ "step": 420
2951
+ },
2952
+ {
2953
+ "epoch": 0.2047043092445147,
2954
+ "grad_norm": 0.0128460843116045,
2955
+ "learning_rate": 0.0004213945430922477,
2956
+ "loss": 0.043242525309324265,
2957
+ "step": 421
2958
+ },
2959
+ {
2960
+ "epoch": 0.2051905427581596,
2961
+ "grad_norm": 0.01331622339785099,
2962
+ "learning_rate": 0.00042117799913382413,
2963
+ "loss": 0.041685618460178375,
2964
+ "step": 422
2965
+ },
2966
+ {
2967
+ "epoch": 0.20567677627180453,
2968
+ "grad_norm": 0.014840972609817982,
2969
+ "learning_rate": 0.00042096145517540065,
2970
+ "loss": 0.0411393828690052,
2971
+ "step": 423
2972
+ },
2973
+ {
2974
+ "epoch": 0.20616300978544946,
2975
+ "grad_norm": 0.01155391987413168,
2976
+ "learning_rate": 0.00042074491121697706,
2977
+ "loss": 0.03904912620782852,
2978
+ "step": 424
2979
+ },
2980
+ {
2981
+ "epoch": 0.2066492432990944,
2982
+ "grad_norm": 0.011980381794273853,
2983
+ "learning_rate": 0.00042052836725855347,
2984
+ "loss": 0.04043574631214142,
2985
+ "step": 425
2986
+ },
2987
+ {
2988
+ "epoch": 0.2071354768127393,
2989
+ "grad_norm": 0.014129528775811195,
2990
+ "learning_rate": 0.00042031182330013,
2991
+ "loss": 0.04233579337596893,
2992
+ "step": 426
2993
+ },
2994
+ {
2995
+ "epoch": 0.20762171032638424,
2996
+ "grad_norm": 0.01416360680013895,
2997
+ "learning_rate": 0.0004200952793417064,
2998
+ "loss": 0.04184813052415848,
2999
+ "step": 427
3000
+ },
3001
+ {
3002
+ "epoch": 0.20810794384002917,
3003
+ "grad_norm": 0.013554218225181103,
3004
+ "learning_rate": 0.0004198787353832828,
3005
+ "loss": 0.04154430329799652,
3006
+ "step": 428
3007
+ },
3008
+ {
3009
+ "epoch": 0.2085941773536741,
3010
+ "grad_norm": 0.012786404229700565,
3011
+ "learning_rate": 0.0004196621914248592,
3012
+ "loss": 0.043722089380025864,
3013
+ "step": 429
3014
+ },
3015
+ {
3016
+ "epoch": 0.20908041086731902,
3017
+ "grad_norm": 0.012765109539031982,
3018
+ "learning_rate": 0.0004194456474664357,
3019
+ "loss": 0.03943069279193878,
3020
+ "step": 430
3021
+ },
3022
+ {
3023
+ "epoch": 0.20956664438096395,
3024
+ "grad_norm": 0.012103332206606865,
3025
+ "learning_rate": 0.00041922910350801213,
3026
+ "loss": 0.03862365707755089,
3027
+ "step": 431
3028
+ },
3029
+ {
3030
+ "epoch": 0.21005287789460889,
3031
+ "grad_norm": 0.012757749296724796,
3032
+ "learning_rate": 0.00041901255954958854,
3033
+ "loss": 0.043844595551490784,
3034
+ "step": 432
3035
+ },
3036
+ {
3037
+ "epoch": 0.21053911140825382,
3038
+ "grad_norm": 0.012306474149227142,
3039
+ "learning_rate": 0.00041879601559116506,
3040
+ "loss": 0.04205210879445076,
3041
+ "step": 433
3042
+ },
3043
+ {
3044
+ "epoch": 0.21102534492189876,
3045
+ "grad_norm": 0.013826766051352024,
3046
+ "learning_rate": 0.00041857947163274147,
3047
+ "loss": 0.0428473986685276,
3048
+ "step": 434
3049
+ },
3050
+ {
3051
+ "epoch": 0.21151157843554366,
3052
+ "grad_norm": 0.013441157527267933,
3053
+ "learning_rate": 0.0004183629276743179,
3054
+ "loss": 0.042012494057416916,
3055
+ "step": 435
3056
+ },
3057
+ {
3058
+ "epoch": 0.2119978119491886,
3059
+ "grad_norm": 0.012775570154190063,
3060
+ "learning_rate": 0.00041814638371589434,
3061
+ "loss": 0.042406342923641205,
3062
+ "step": 436
3063
+ },
3064
+ {
3065
+ "epoch": 0.21248404546283353,
3066
+ "grad_norm": 0.01510821096599102,
3067
+ "learning_rate": 0.0004179298397574708,
3068
+ "loss": 0.04042791575193405,
3069
+ "step": 437
3070
+ },
3071
+ {
3072
+ "epoch": 0.21297027897647847,
3073
+ "grad_norm": 0.012814188376069069,
3074
+ "learning_rate": 0.0004177132957990472,
3075
+ "loss": 0.04460684955120087,
3076
+ "step": 438
3077
+ },
3078
+ {
3079
+ "epoch": 0.21345651249012337,
3080
+ "grad_norm": 0.011798158288002014,
3081
+ "learning_rate": 0.0004174967518406236,
3082
+ "loss": 0.041500575840473175,
3083
+ "step": 439
3084
+ },
3085
+ {
3086
+ "epoch": 0.2139427460037683,
3087
+ "grad_norm": 0.013056010007858276,
3088
+ "learning_rate": 0.00041728020788220013,
3089
+ "loss": 0.042852211743593216,
3090
+ "step": 440
3091
+ },
3092
+ {
3093
+ "epoch": 0.21442897951741324,
3094
+ "grad_norm": 0.012399810366332531,
3095
+ "learning_rate": 0.00041706366392377654,
3096
+ "loss": 0.041504647582769394,
3097
+ "step": 441
3098
+ },
3099
+ {
3100
+ "epoch": 0.21491521303105818,
3101
+ "grad_norm": 0.013165258802473545,
3102
+ "learning_rate": 0.00041684711996535295,
3103
+ "loss": 0.039765335619449615,
3104
+ "step": 442
3105
+ },
3106
+ {
3107
+ "epoch": 0.21540144654470308,
3108
+ "grad_norm": 0.012821082957088947,
3109
+ "learning_rate": 0.00041663057600692946,
3110
+ "loss": 0.04068581759929657,
3111
+ "step": 443
3112
+ },
3113
+ {
3114
+ "epoch": 0.21588768005834802,
3115
+ "grad_norm": 0.012675683945417404,
3116
+ "learning_rate": 0.00041641403204850587,
3117
+ "loss": 0.04533727839589119,
3118
+ "step": 444
3119
+ },
3120
+ {
3121
+ "epoch": 0.21637391357199295,
3122
+ "grad_norm": 0.01429657731205225,
3123
+ "learning_rate": 0.0004161974880900823,
3124
+ "loss": 0.039108868688344955,
3125
+ "step": 445
3126
+ },
3127
+ {
3128
+ "epoch": 0.2168601470856379,
3129
+ "grad_norm": 0.012523706071078777,
3130
+ "learning_rate": 0.0004159809441316587,
3131
+ "loss": 0.03865820914506912,
3132
+ "step": 446
3133
+ },
3134
+ {
3135
+ "epoch": 0.2173463805992828,
3136
+ "grad_norm": 0.013953331857919693,
3137
+ "learning_rate": 0.0004157644001732352,
3138
+ "loss": 0.03797724470496178,
3139
+ "step": 447
3140
+ },
3141
+ {
3142
+ "epoch": 0.21783261411292773,
3143
+ "grad_norm": 0.013411572203040123,
3144
+ "learning_rate": 0.0004155478562148116,
3145
+ "loss": 0.044362686574459076,
3146
+ "step": 448
3147
+ },
3148
+ {
3149
+ "epoch": 0.21831884762657267,
3150
+ "grad_norm": 0.013555505312979221,
3151
+ "learning_rate": 0.000415331312256388,
3152
+ "loss": 0.041361890733242035,
3153
+ "step": 449
3154
+ },
3155
+ {
3156
+ "epoch": 0.2188050811402176,
3157
+ "grad_norm": 0.013754409737884998,
3158
+ "learning_rate": 0.00041511476829796454,
3159
+ "loss": 0.04085294157266617,
3160
+ "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 0.2192913146538625,
3164
+ "grad_norm": 0.012228651903569698,
3165
+ "learning_rate": 0.00041489822433954095,
3166
+ "loss": 0.040388721972703934,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 0.21977754816750744,
3171
+ "grad_norm": 0.013332387432456017,
3172
+ "learning_rate": 0.00041468168038111735,
3173
+ "loss": 0.03958063945174217,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 0.22026378168115238,
3178
+ "grad_norm": 0.012905411422252655,
3179
+ "learning_rate": 0.00041446513642269376,
3180
+ "loss": 0.04133458435535431,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 0.2207500151947973,
3185
+ "grad_norm": 0.012178502976894379,
3186
+ "learning_rate": 0.0004142485924642703,
3187
+ "loss": 0.04020874947309494,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 0.22123624870844222,
3192
+ "grad_norm": 0.012072818353772163,
3193
+ "learning_rate": 0.0004140320485058467,
3194
+ "loss": 0.036105114966630936,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 0.22172248222208715,
3199
+ "grad_norm": 0.01334983017295599,
3200
+ "learning_rate": 0.0004138155045474231,
3201
+ "loss": 0.044807370752096176,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 0.2222087157357321,
3206
+ "grad_norm": 0.012763558886945248,
3207
+ "learning_rate": 0.0004135989605889996,
3208
+ "loss": 0.04130896180868149,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 0.22269494924937702,
3213
+ "grad_norm": 0.013077284209430218,
3214
+ "learning_rate": 0.000413382416630576,
3215
+ "loss": 0.03900114819407463,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 0.22318118276302193,
3220
+ "grad_norm": 0.012833717279136181,
3221
+ "learning_rate": 0.00041316587267215243,
3222
+ "loss": 0.04094377160072327,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 0.22366741627666686,
3227
+ "grad_norm": 0.013563316315412521,
3228
+ "learning_rate": 0.00041294932871372895,
3229
+ "loss": 0.040409915149211884,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 0.2241536497903118,
3234
+ "grad_norm": 0.012616271153092384,
3235
+ "learning_rate": 0.00041273278475530535,
3236
+ "loss": 0.04262936860322952,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 0.22463988330395673,
3241
+ "grad_norm": 0.012616111896932125,
3242
+ "learning_rate": 0.00041251624079688176,
3243
+ "loss": 0.03900012746453285,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 0.22512611681760164,
3248
+ "grad_norm": 0.013444248586893082,
3249
+ "learning_rate": 0.00041229969683845817,
3250
+ "loss": 0.04135546088218689,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 0.22561235033124658,
3255
+ "grad_norm": 0.01291780173778534,
3256
+ "learning_rate": 0.0004120831528800347,
3257
+ "loss": 0.04171999916434288,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 0.2260985838448915,
3262
+ "grad_norm": 0.013292920775711536,
3263
+ "learning_rate": 0.0004118666089216111,
3264
+ "loss": 0.043509792536497116,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 0.22658481735853644,
3269
+ "grad_norm": 0.01225997507572174,
3270
+ "learning_rate": 0.0004116500649631875,
3271
+ "loss": 0.03852201625704765,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 0.22707105087218135,
3276
+ "grad_norm": 0.012644794769585133,
3277
+ "learning_rate": 0.000411433521004764,
3278
+ "loss": 0.041985947638750076,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 0.2275572843858263,
3283
+ "grad_norm": 0.01383617427200079,
3284
+ "learning_rate": 0.00041121697704634043,
3285
+ "loss": 0.04247439280152321,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 0.22804351789947122,
3290
+ "grad_norm": 0.01286292728036642,
3291
+ "learning_rate": 0.00041100043308791684,
3292
+ "loss": 0.038012247532606125,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 0.22852975141311616,
3297
+ "grad_norm": 0.012515362352132797,
3298
+ "learning_rate": 0.0004107838891294933,
3299
+ "loss": 0.03735552728176117,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 0.2290159849267611,
3304
+ "grad_norm": 0.01263203751295805,
3305
+ "learning_rate": 0.00041056734517106976,
3306
+ "loss": 0.04277797415852547,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 0.229502218440406,
3311
+ "grad_norm": 0.013702447526156902,
3312
+ "learning_rate": 0.00041035080121264617,
3313
+ "loss": 0.04035373032093048,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 0.22998845195405093,
3318
+ "grad_norm": 0.014106915332376957,
3319
+ "learning_rate": 0.0004101342572542226,
3320
+ "loss": 0.044522009789943695,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 0.23047468546769587,
3325
+ "grad_norm": 0.014517098665237427,
3326
+ "learning_rate": 0.0004099177132957991,
3327
+ "loss": 0.04012403264641762,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 0.23047468546769587,
3332
+ "eval_loss": 0.04112490266561508,
3333
+ "eval_runtime": 162.2954,
3334
+ "eval_samples_per_second": 22.139,
3335
+ "eval_steps_per_second": 5.539,
3336
+ "step": 474
3337
+ }
3338
+ ],
3339
+ "logging_steps": 1,
3340
+ "max_steps": 2366,
3341
+ "num_input_tokens_seen": 0,
3342
+ "num_train_epochs": 2,
3343
+ "save_steps": 474,
3344
+ "stateful_callbacks": {
3345
+ "TrainerControl": {
3346
+ "args": {
3347
+ "should_epoch_stop": false,
3348
+ "should_evaluate": false,
3349
+ "should_log": false,
3350
+ "should_save": true,
3351
+ "should_training_stop": false
3352
+ },
3353
+ "attributes": {}
3354
+ }
3355
+ },
3356
+ "total_flos": 1.3239142240948224e+17,
3357
+ "train_batch_size": 4,
3358
+ "trial_name": null,
3359
+ "trial_params": null
3360
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42822cb03c4a073e60c32f8cfcf1cf9b83ee8a1d1a136c53659b4710cc7ceb72
3
+ size 5649