Hugging Face's logo

FroxStudio
/
Flex-Model-LoRA

Text Generation
PEFT
Safetensors
Transformers
dpo
lora
trl
conversational
Model card Files
xet
 Community
FroxAI commited on
Commit
3d709b1
·
verified ·
1 Parent(s): f411104

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-5000/README.md +207 -0
  2. checkpoint-5000/adapter_config.json +51 -0
  3. checkpoint-5000/adapter_model.safetensors +3 -0
  4. checkpoint-5000/chat_template.jinja +54 -0
  5. checkpoint-5000/optimizer.pt +3 -0
  6. checkpoint-5000/rng_state.pth +3 -0
  7. checkpoint-5000/scaler.pt +3 -0
  8. checkpoint-5000/scheduler.pt +3 -0
  9. checkpoint-5000/tokenizer.json +3 -0
  10. checkpoint-5000/tokenizer_config.json +30 -0
  11. checkpoint-5000/trainer_state.json +3534 -0
  12. checkpoint-5000/training_args.bin +3 -0
checkpoint-5000/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- 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. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ 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).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.21.2
checkpoint-5000/adapter_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "kasa_config": null,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 32,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0.05,
23
+ "lora_ga_config": null,
24
+ "megatron_config": null,
25
+ "megatron_core": "megatron.core",
26
+ "modules_to_save": null,
27
+ "monteclora_config": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.20.0",
30
+ "qalora_group_size": 16,
31
+ "r": 16,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "v_proj",
36
+ "gate_proj",
37
+ "up_proj",
38
+ "o_proj",
39
+ "down_proj",
40
+ "q_proj",
41
+ "k_proj"
42
+ ],
43
+ "target_parameters": null,
44
+ "task_type": "CAUSAL_LM",
45
+ "trainable_token_indices": null,
46
+ "use_bdlora": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false,
50
+ "velora_config": null
51
+ }
checkpoint-5000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d38c2421d002d913aae925d59a69a92a88a1287e4c339108347e782eb323d989
3
+ size 73911112
checkpoint-5000/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d466b58fd5de91a0bf24177725e16355f4d8a7e621a28598623017e84ea2634b
3
+ size 148048187
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3f2e1db60ee9eb3bc8bda80942477f3472a788379f35c5bafc30c66eea33cd
3
+ size 14645
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
3
+ size 1383
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b2845bf3b154a6f6ebd50e10c431f419888543246e38f43a31c2c18b434202
3
+ size 1465
checkpoint-5000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
3
+ size 11421991
checkpoint-5000/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,3534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.8371152962792834,
6
+ "eval_steps": 500,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008119354511316351,
14
+ "grad_norm": 1.192345380783081,
15
+ "learning_rate": 2.7272727272727273e-05,
16
+ "loss": 1.3216888427734375,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.016238709022632702,
21
+ "grad_norm": 1.2548257112503052,
22
+ "learning_rate": 5.757575757575758e-05,
23
+ "loss": 1.0566269874572753,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.02435806353394905,
28
+ "grad_norm": 0.30806204676628113,
29
+ "learning_rate": 8.787878787878789e-05,
30
+ "loss": 0.6396953582763671,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.032477418045265403,
35
+ "grad_norm": 0.25909167528152466,
36
+ "learning_rate": 0.0001181818181818182,
37
+ "loss": 0.5402174472808838,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.04059677255658175,
42
+ "grad_norm": 0.21031738817691803,
43
+ "learning_rate": 0.00014848484848484849,
44
+ "loss": 0.5005859375,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0487161270678981,
49
+ "grad_norm": 0.18716108798980713,
50
+ "learning_rate": 0.0001787878787878788,
51
+ "loss": 0.537840461730957,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.056835481579214454,
56
+ "grad_norm": 0.1792488396167755,
57
+ "learning_rate": 0.0001999990247348105,
58
+ "loss": 0.4450899600982666,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.06495483609053081,
63
+ "grad_norm": 0.21492543816566467,
64
+ "learning_rate": 0.00019998168721618701,
65
+ "loss": 0.4202279090881348,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.07307419060184715,
70
+ "grad_norm": 0.16661711037158966,
71
+ "learning_rate": 0.00019994268146276777,
72
+ "loss": 0.4485616207122803,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.0811935451131635,
77
+ "grad_norm": 0.24056391417980194,
78
+ "learning_rate": 0.0001998820159279591,
79
+ "loss": 0.44878439903259276,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.08931289962447986,
84
+ "grad_norm": 0.20612840354442596,
85
+ "learning_rate": 0.00019979970375931912,
86
+ "loss": 0.4974456787109375,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0974322541357962,
91
+ "grad_norm": 0.17296524345874786,
92
+ "learning_rate": 0.00019969576279570866,
93
+ "loss": 0.4231257438659668,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.10555160864711255,
98
+ "grad_norm": 0.20717096328735352,
99
+ "learning_rate": 0.00019957021556342495,
100
+ "loss": 0.4275392532348633,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.11367096315842891,
105
+ "grad_norm": 0.20023062825202942,
106
+ "learning_rate": 0.00019942308927131972,
107
+ "loss": 0.41733384132385254,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.12179031766974525,
112
+ "grad_norm": 0.17242860794067383,
113
+ "learning_rate": 0.00019925441580490255,
114
+ "loss": 0.41766815185546874,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.12990967218106161,
119
+ "grad_norm": 0.17718906700611115,
120
+ "learning_rate": 0.00019906423171943047,
121
+ "loss": 0.43944649696350097,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.13802902669237796,
126
+ "grad_norm": 0.1699272096157074,
127
+ "learning_rate": 0.0001988525782319856,
128
+ "loss": 0.4246710777282715,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.1461483812036943,
133
+ "grad_norm": 0.18154670298099518,
134
+ "learning_rate": 0.00019861950121254275,
135
+ "loss": 0.40392107963562013,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.15426773571501065,
140
+ "grad_norm": 0.18973930180072784,
141
+ "learning_rate": 0.00019836505117402792,
142
+ "loss": 0.4155430316925049,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.162387090226327,
147
+ "grad_norm": 0.15529297292232513,
148
+ "learning_rate": 0.00019808928326137156,
149
+ "loss": 0.430379581451416,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.17050644473764337,
154
+ "grad_norm": 0.20729880034923553,
155
+ "learning_rate": 0.00019779225723955707,
156
+ "loss": 0.42681236267089845,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.17862579924895972,
161
+ "grad_norm": 0.17007844150066376,
162
+ "learning_rate": 0.0001974740374806686,
163
+ "loss": 0.3926879644393921,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.18674515376027606,
168
+ "grad_norm": 0.1643807291984558,
169
+ "learning_rate": 0.00019713469294994012,
170
+ "loss": 0.41318230628967284,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.1948645082715924,
175
+ "grad_norm": 0.1504553258419037,
176
+ "learning_rate": 0.00019677429719080916,
177
+ "loss": 0.443330192565918,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.20298386278290875,
182
+ "grad_norm": 0.17451228201389313,
183
+ "learning_rate": 0.00019639292830897837,
184
+ "loss": 0.4365452766418457,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.2111032172942251,
189
+ "grad_norm": 0.16454367339611053,
190
+ "learning_rate": 0.0001959906689554881,
191
+ "loss": 0.45282588005065916,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.21922257180554147,
196
+ "grad_norm": 0.15446598827838898,
197
+ "learning_rate": 0.0001955676063088045,
198
+ "loss": 0.46193952560424806,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.22734192631685782,
203
+ "grad_norm": 0.17489995062351227,
204
+ "learning_rate": 0.00019512383205592552,
205
+ "loss": 0.46073436737060547,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.23546128082817416,
210
+ "grad_norm": 0.1772591769695282,
211
+ "learning_rate": 0.00019465944237251071,
212
+ "loss": 0.38799960613250734,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.2435806353394905,
217
+ "grad_norm": 0.11530005931854248,
218
+ "learning_rate": 0.00019417453790203772,
219
+ "loss": 0.4481969833374023,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.2516999898508069,
224
+ "grad_norm": 0.1683167964220047,
225
+ "learning_rate": 0.0001936692237339905,
226
+ "loss": 0.41562438011169434,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.25981934436212323,
231
+ "grad_norm": 0.16425232589244843,
232
+ "learning_rate": 0.00019314360938108425,
233
+ "loss": 0.40752553939819336,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.2679386988734396,
238
+ "grad_norm": 0.16231301426887512,
239
+ "learning_rate": 0.0001925978087555316,
240
+ "loss": 0.3947896480560303,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.2760580533847559,
245
+ "grad_norm": 0.17653369903564453,
246
+ "learning_rate": 0.00019203194014435525,
247
+ "loss": 0.4535045146942139,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.28417740789607226,
252
+ "grad_norm": 0.15756867825984955,
253
+ "learning_rate": 0.0001914461261837526,
254
+ "loss": 0.4795684814453125,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.2922967624073886,
259
+ "grad_norm": 0.1505475640296936,
260
+ "learning_rate": 0.00019084049383251783,
261
+ "loss": 0.4024923324584961,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.30041611691870496,
266
+ "grad_norm": 0.16846773028373718,
267
+ "learning_rate": 0.00019021517434452702,
268
+ "loss": 0.42346930503845215,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.3085354714300213,
273
+ "grad_norm": 0.17196664214134216,
274
+ "learning_rate": 0.0001895703032402926,
275
+ "loss": 0.38081505298614504,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.31665482594133765,
280
+ "grad_norm": 0.18256904184818268,
281
+ "learning_rate": 0.00018890602027759313,
282
+ "loss": 0.37936599254608155,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.324774180452654,
287
+ "grad_norm": 0.1385713666677475,
288
+ "learning_rate": 0.00018822246942118466,
289
+ "loss": 0.3991415977478027,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.33289353496397034,
294
+ "grad_norm": 0.15789403021335602,
295
+ "learning_rate": 0.00018751979881160029,
296
+ "loss": 0.40332279205322263,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.34101288947528674,
301
+ "grad_norm": 0.15686365962028503,
302
+ "learning_rate": 0.0001867981607330451,
303
+ "loss": 0.3878762722015381,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.3491322439866031,
308
+ "grad_norm": 0.15789690613746643,
309
+ "learning_rate": 0.00018605771158039253,
310
+ "loss": 0.3754732131958008,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.35725159849791943,
315
+ "grad_norm": 0.14583982527256012,
316
+ "learning_rate": 0.00018529861182529036,
317
+ "loss": 0.4119413375854492,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.3653709530092358,
322
+ "grad_norm": 0.16271716356277466,
323
+ "learning_rate": 0.0001845210259813829,
324
+ "loss": 0.4371773719787598,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.3734903075205521,
329
+ "grad_norm": 0.15252803266048431,
330
+ "learning_rate": 0.00018372512256865724,
331
+ "loss": 0.3985795021057129,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.38160966203186847,
336
+ "grad_norm": 0.17694011330604553,
337
+ "learning_rate": 0.00018291107407692128,
338
+ "loss": 0.40482492446899415,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.3897290165431848,
343
+ "grad_norm": 0.15677419304847717,
344
+ "learning_rate": 0.00018207905692842134,
345
+ "loss": 0.3925381898880005,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.39784837105450116,
350
+ "grad_norm": 0.15828488767147064,
351
+ "learning_rate": 0.00018122925143960775,
352
+ "loss": 0.3869333028793335,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.4059677255658175,
357
+ "grad_norm": 0.13660173118114471,
358
+ "learning_rate": 0.000180361841782056,
359
+ "loss": 0.4138071060180664,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.41408708007713385,
364
+ "grad_norm": 0.164328932762146,
365
+ "learning_rate": 0.00017947701594255299,
366
+ "loss": 0.4766359806060791,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.4222064345884502,
371
+ "grad_norm": 0.13619564473628998,
372
+ "learning_rate": 0.00017857496568235597,
373
+ "loss": 0.3740208625793457,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.43032578909976654,
378
+ "grad_norm": 0.1389133632183075,
379
+ "learning_rate": 0.00017765588649563372,
380
+ "loss": 0.4194491386413574,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.43844514361108294,
385
+ "grad_norm": 0.16105148196220398,
386
+ "learning_rate": 0.00017671997756709863,
387
+ "loss": 0.37844417095184324,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.4465644981223993,
392
+ "grad_norm": 0.1176551878452301,
393
+ "learning_rate": 0.00017576744172883899,
394
+ "loss": 0.3884027719497681,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.45468385263371563,
399
+ "grad_norm": 0.15062262117862701,
400
+ "learning_rate": 0.0001747984854163609,
401
+ "loss": 0.4128002643585205,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.462803207145032,
406
+ "grad_norm": 0.14474593102931976,
407
+ "learning_rate": 0.00017381331862384894,
408
+ "loss": 0.37835040092468264,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.4709225616563483,
413
+ "grad_norm": 0.11984218657016754,
414
+ "learning_rate": 0.00017281215485865603,
415
+ "loss": 0.3885404109954834,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.47904191616766467,
420
+ "grad_norm": 0.11157386004924774,
421
+ "learning_rate": 0.00017179521109503146,
422
+ "loss": 0.41469721794128417,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.487161270678981,
427
+ "grad_norm": 0.15861837565898895,
428
+ "learning_rate": 0.00017076270772709807,
429
+ "loss": 0.40916032791137696,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.49528062519029736,
434
+ "grad_norm": 0.16919773817062378,
435
+ "learning_rate": 0.00016971486852108763,
436
+ "loss": 0.38907546997070314,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.5033999797016138,
441
+ "grad_norm": 0.1534120887517929,
442
+ "learning_rate": 0.00016865192056684605,
443
+ "loss": 0.3835587978363037,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.51151933421293,
448
+ "grad_norm": 0.1444127857685089,
449
+ "learning_rate": 0.00016757409422861802,
450
+ "loss": 0.41408615112304686,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.5196386887242465,
455
+ "grad_norm": 0.16517969965934753,
456
+ "learning_rate": 0.00016648162309512173,
457
+ "loss": 0.3881347179412842,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.5277580432355627,
462
+ "grad_norm": 0.16764643788337708,
463
+ "learning_rate": 0.00016537474392892528,
464
+ "loss": 0.36968770027160647,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.5358773977468791,
469
+ "grad_norm": 0.15984776616096497,
470
+ "learning_rate": 0.0001642536966151349,
471
+ "loss": 0.4436800003051758,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.5439967522581954,
476
+ "grad_norm": 0.15119516849517822,
477
+ "learning_rate": 0.00016311872410940676,
478
+ "loss": 0.36648738384246826,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.5521161067695118,
483
+ "grad_norm": 0.17760701477527618,
484
+ "learning_rate": 0.00016197007238529277,
485
+ "loss": 0.43828520774841306,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.5602354612808281,
490
+ "grad_norm": 0.15702351927757263,
491
+ "learning_rate": 0.00016080799038093311,
492
+ "loss": 0.39908370971679685,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.5683548157921445,
497
+ "grad_norm": 0.16063162684440613,
498
+ "learning_rate": 0.0001596327299451054,
499
+ "loss": 0.3547415256500244,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.5764741703034608,
504
+ "grad_norm": 0.15705077350139618,
505
+ "learning_rate": 0.000158444545782644,
506
+ "loss": 0.38064041137695315,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.5845935248147772,
511
+ "grad_norm": 0.2802039086818695,
512
+ "learning_rate": 0.0001572436953992394,
513
+ "loss": 0.34356114864349363,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.5927128793260936,
518
+ "grad_norm": 0.14802053570747375,
519
+ "learning_rate": 0.00015603043904563148,
520
+ "loss": 0.44878721237182617,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.6008322338374099,
525
+ "grad_norm": 0.15852048993110657,
526
+ "learning_rate": 0.00015480503966120704,
527
+ "loss": 0.40053658485412597,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.6089515883487263,
532
+ "grad_norm": 0.15426747500896454,
533
+ "learning_rate": 0.00015356776281701538,
534
+ "loss": 0.404225492477417,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.6170709428600426,
539
+ "grad_norm": 0.1420115828514099,
540
+ "learning_rate": 0.000152318876658213,
541
+ "loss": 0.37903261184692383,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.625190297371359,
546
+ "grad_norm": 0.13923387229442596,
547
+ "learning_rate": 0.00015105865184595073,
548
+ "loss": 0.35583546161651614,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.6333096518826753,
553
+ "grad_norm": 0.14876466989517212,
554
+ "learning_rate": 0.00014978736149871545,
555
+ "loss": 0.3251772165298462,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.6414290063939917,
560
+ "grad_norm": 0.17565123736858368,
561
+ "learning_rate": 0.0001485052811331393,
562
+ "loss": 0.39765985012054444,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.649548360905308,
567
+ "grad_norm": 0.15443134307861328,
568
+ "learning_rate": 0.00014721268860428912,
569
+ "loss": 0.3529685020446777,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.6576677154166244,
574
+ "grad_norm": 0.15266218781471252,
575
+ "learning_rate": 0.00014590986404544923,
576
+ "loss": 0.4115382194519043,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.6657870699279407,
581
+ "grad_norm": 0.14183001220226288,
582
+ "learning_rate": 0.00014459708980741037,
583
+ "loss": 0.4038706302642822,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.6739064244392571,
588
+ "grad_norm": 0.20107750594615936,
589
+ "learning_rate": 0.00014327465039727785,
590
+ "loss": 0.42904024124145507,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.6820257789505735,
595
+ "grad_norm": 0.15056397020816803,
596
+ "learning_rate": 0.00014194283241681293,
597
+ "loss": 0.3807892084121704,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.6901451334618898,
602
+ "grad_norm": 0.16432157158851624,
603
+ "learning_rate": 0.00014060192450031958,
604
+ "loss": 0.40647153854370116,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.6982644879732062,
609
+ "grad_norm": 0.14384903013706207,
610
+ "learning_rate": 0.0001392522172520913,
611
+ "loss": 0.400847864151001,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.7063838424845225,
616
+ "grad_norm": 0.16257992386817932,
617
+ "learning_rate": 0.00013789400318343068,
618
+ "loss": 0.4034707069396973,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.7145031969958389,
623
+ "grad_norm": 0.1456725299358368,
624
+ "learning_rate": 0.00013652757664925572,
625
+ "loss": 0.3958974123001099,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.7226225515071552,
630
+ "grad_norm": 0.1645933985710144,
631
+ "learning_rate": 0.00013515323378430664,
632
+ "loss": 0.39889843463897706,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.7307419060184716,
637
+ "grad_norm": 0.14808154106140137,
638
+ "learning_rate": 0.00013377127243896706,
639
+ "loss": 0.39709608554840087,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.7388612605297878,
644
+ "grad_norm": 0.15682613849639893,
645
+ "learning_rate": 0.00013238199211471305,
646
+ "loss": 0.3838841199874878,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.7469806150411042,
651
+ "grad_norm": 0.15188175439834595,
652
+ "learning_rate": 0.00013098569389920488,
653
+ "loss": 0.4285408973693848,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.7550999695524205,
658
+ "grad_norm": 0.16449961066246033,
659
+ "learning_rate": 0.00012958268040103434,
660
+ "loss": 0.37526252269744875,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.7632193240637369,
665
+ "grad_norm": 0.1517837643623352,
666
+ "learning_rate": 0.00012817325568414297,
667
+ "loss": 0.40034284591674807,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.7713386785750533,
672
+ "grad_norm": 0.18229644000530243,
673
+ "learning_rate": 0.00012675772520192476,
674
+ "loss": 0.37904250621795654,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.7794580330863696,
679
+ "grad_norm": 0.15189775824546814,
680
+ "learning_rate": 0.00012533639573102754,
681
+ "loss": 0.4246711254119873,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.787577387597686,
686
+ "grad_norm": 0.15175221860408783,
687
+ "learning_rate": 0.0001239095753048678,
688
+ "loss": 0.3818449735641479,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.7956967421090023,
693
+ "grad_norm": 0.14126037061214447,
694
+ "learning_rate": 0.00012247757314687297,
695
+ "loss": 0.3847095251083374,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.8038160966203187,
700
+ "grad_norm": 0.17514625191688538,
701
+ "learning_rate": 0.00012104069960346596,
702
+ "loss": 0.40877785682678225,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.811935451131635,
707
+ "grad_norm": 0.1650720089673996,
708
+ "learning_rate": 0.00011959926607680639,
709
+ "loss": 0.40711078643798826,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.8200548056429514,
714
+ "grad_norm": 0.15258049964904785,
715
+ "learning_rate": 0.00011815358495730253,
716
+ "loss": 0.40592288970947266,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.8281741601542677,
721
+ "grad_norm": 0.14057976007461548,
722
+ "learning_rate": 0.00011670396955590974,
723
+ "loss": 0.3216592073440552,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.8362935146655841,
728
+ "grad_norm": 0.16660679876804352,
729
+ "learning_rate": 0.00011525073403622894,
730
+ "loss": 0.40019774436950684,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.8444128691769004,
735
+ "grad_norm": 0.17680172622203827,
736
+ "learning_rate": 0.0001137941933464204,
737
+ "loss": 0.4132580280303955,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.8525322236882168,
742
+ "grad_norm": 0.17041870951652527,
743
+ "learning_rate": 0.0001123346631509477,
744
+ "loss": 0.3415886878967285,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.8606515781995331,
749
+ "grad_norm": 0.15096868574619293,
750
+ "learning_rate": 0.00011087245976216607,
751
+ "loss": 0.4133938789367676,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.8687709327108495,
756
+ "grad_norm": 0.15110765397548676,
757
+ "learning_rate": 0.00010940790007177069,
758
+ "loss": 0.38502039909362795,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.8768902872221659,
763
+ "grad_norm": 0.1299409419298172,
764
+ "learning_rate": 0.00010794130148211918,
765
+ "loss": 0.36754612922668456,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.8850096417334822,
770
+ "grad_norm": 0.16098879277706146,
771
+ "learning_rate": 0.00010647298183744359,
772
+ "loss": 0.4300854206085205,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.8931289962447986,
777
+ "grad_norm": 0.18567131459712982,
778
+ "learning_rate": 0.00010500325935496654,
779
+ "loss": 0.4555531978607178,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.9012483507561149,
784
+ "grad_norm": 0.15725167095661163,
785
+ "learning_rate": 0.00010353245255593645,
786
+ "loss": 0.40347743034362793,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.9093677052674313,
791
+ "grad_norm": 0.18014128506183624,
792
+ "learning_rate": 0.0001020608801965971,
793
+ "loss": 0.43356914520263673,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.9174870597787476,
798
+ "grad_norm": 0.14646700024604797,
799
+ "learning_rate": 0.00010058886119910603,
800
+ "loss": 0.3579983949661255,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.925606414290064,
805
+ "grad_norm": 0.15054835379123688,
806
+ "learning_rate": 9.911671458241707e-05,
807
+ "loss": 0.412873363494873,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.9337257688013803,
812
+ "grad_norm": 0.1782434582710266,
813
+ "learning_rate": 9.764475939314199e-05,
814
+ "loss": 0.3661553144454956,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.9418451233126967,
819
+ "grad_norm": 0.14244233071804047,
820
+ "learning_rate": 9.6173314636406e-05,
821
+ "loss": 0.33595120906829834,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.9499644778240129,
826
+ "grad_norm": 0.15346868336200714,
827
+ "learning_rate": 9.470269920671242e-05,
828
+ "loss": 0.35301713943481444,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.9580838323353293,
833
+ "grad_norm": 0.17095577716827393,
834
+ "learning_rate": 9.323323181883093e-05,
835
+ "loss": 0.46831064224243163,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.9662031868466457,
840
+ "grad_norm": 0.16479066014289856,
841
+ "learning_rate": 9.176523093872545e-05,
842
+ "loss": 0.35177159309387207,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.974322541357962,
847
+ "grad_norm": 0.15938977897167206,
848
+ "learning_rate": 9.02990147145352e-05,
849
+ "loss": 0.40160298347473145,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.9824418958692784,
854
+ "grad_norm": 0.15273737907409668,
855
+ "learning_rate": 8.883490090762524e-05,
856
+ "loss": 0.3344574451446533,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.9905612503805947,
861
+ "grad_norm": 0.17632175981998444,
862
+ "learning_rate": 8.737320682372048e-05,
863
+ "loss": 0.3946251392364502,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.9986806048919111,
868
+ "grad_norm": 0.1546667516231537,
869
+ "learning_rate": 8.59142492441384e-05,
870
+ "loss": 0.38449108600616455,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 1.0064954836090532,
875
+ "grad_norm": 0.1582242101430893,
876
+ "learning_rate": 8.445834435713589e-05,
877
+ "loss": 0.35192313194274905,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 1.0146148381203695,
882
+ "grad_norm": 0.16060605645179749,
883
+ "learning_rate": 8.300580768938389e-05,
884
+ "loss": 0.3984487295150757,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 1.0227341926316857,
889
+ "grad_norm": 0.15913701057434082,
890
+ "learning_rate": 8.155695403758614e-05,
891
+ "loss": 0.3666527271270752,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 1.030853547143002,
896
+ "grad_norm": 0.2222735434770584,
897
+ "learning_rate": 8.011209740025568e-05,
898
+ "loss": 0.39426436424255373,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 1.0389729016543185,
903
+ "grad_norm": 0.14628788828849792,
904
+ "learning_rate": 7.867155090966429e-05,
905
+ "loss": 0.3448423147201538,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 1.0470922561656348,
910
+ "grad_norm": 0.1674235761165619,
911
+ "learning_rate": 7.723562676398017e-05,
912
+ "loss": 0.3735038280487061,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 1.0552116106769511,
917
+ "grad_norm": 0.1577482521533966,
918
+ "learning_rate": 7.580463615960731e-05,
919
+ "loss": 0.36143453121185304,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 1.0633309651882676,
924
+ "grad_norm": 0.15055105090141296,
925
+ "learning_rate": 7.437888922374276e-05,
926
+ "loss": 0.3465540647506714,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 1.071450319699584,
931
+ "grad_norm": 0.16190367937088013,
932
+ "learning_rate": 7.2958694947165e-05,
933
+ "loss": 0.3162075519561768,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 1.0795696742109002,
938
+ "grad_norm": 0.13373522460460663,
939
+ "learning_rate": 7.154436111726885e-05,
940
+ "loss": 0.2877171516418457,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 1.0876890287222165,
945
+ "grad_norm": 0.1537173092365265,
946
+ "learning_rate": 7.013619425136125e-05,
947
+ "loss": 0.371155834197998,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 1.095808383233533,
952
+ "grad_norm": 0.153018981218338,
953
+ "learning_rate": 6.873449953023205e-05,
954
+ "loss": 0.3403003454208374,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 1.1039277377448493,
959
+ "grad_norm": 0.14698824286460876,
960
+ "learning_rate": 6.733958073201484e-05,
961
+ "loss": 0.3563337802886963,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 1.1120470922561656,
966
+ "grad_norm": 0.17373280227184296,
967
+ "learning_rate": 6.595174016635132e-05,
968
+ "loss": 0.36922128200531007,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 1.120166446767482,
973
+ "grad_norm": 0.1971225142478943,
974
+ "learning_rate": 6.457127860887424e-05,
975
+ "loss": 0.40238251686096194,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 1.1282858012787984,
980
+ "grad_norm": 0.1588146984577179,
981
+ "learning_rate": 6.319849523602271e-05,
982
+ "loss": 0.38647644519805907,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 1.1364051557901147,
987
+ "grad_norm": 0.1998201310634613,
988
+ "learning_rate": 6.18336875602039e-05,
989
+ "loss": 0.3392190933227539,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 1.144524510301431,
994
+ "grad_norm": 0.1279604434967041,
995
+ "learning_rate": 6.047715136531587e-05,
996
+ "loss": 0.29073169231414797,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 1.1526438648127475,
1001
+ "grad_norm": 0.17609012126922607,
1002
+ "learning_rate": 5.9129180642644414e-05,
1003
+ "loss": 0.3901878118515015,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 1.1607632193240638,
1008
+ "grad_norm": 0.1663195639848709,
1009
+ "learning_rate": 5.779006752714868e-05,
1010
+ "loss": 0.3095200300216675,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 1.16888257383538,
1015
+ "grad_norm": 0.14723604917526245,
1016
+ "learning_rate": 5.646010223414924e-05,
1017
+ "loss": 0.3879781007766724,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 1.1770019283466964,
1022
+ "grad_norm": 0.19692786037921906,
1023
+ "learning_rate": 5.513957299643194e-05,
1024
+ "loss": 0.3436476469039917,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 1.1851212828580129,
1029
+ "grad_norm": 0.14053191244602203,
1030
+ "learning_rate": 5.382876600178155e-05,
1031
+ "loss": 0.32699582576751707,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 1.1932406373693292,
1036
+ "grad_norm": 0.18614161014556885,
1037
+ "learning_rate": 5.25279653309584e-05,
1038
+ "loss": 0.3756012201309204,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 1.2013599918806455,
1043
+ "grad_norm": 0.17593547701835632,
1044
+ "learning_rate": 5.1237452896132067e-05,
1045
+ "loss": 0.4036771297454834,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 1.2094793463919618,
1050
+ "grad_norm": 0.1469552218914032,
1051
+ "learning_rate": 4.9957508379784704e-05,
1052
+ "loss": 0.35532774925231936,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 1.2175987009032783,
1057
+ "grad_norm": 0.1465003490447998,
1058
+ "learning_rate": 4.86884091740975e-05,
1059
+ "loss": 0.3272955656051636,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 1.2257180554145946,
1064
+ "grad_norm": 0.16992369294166565,
1065
+ "learning_rate": 4.7430430320834e-05,
1066
+ "loss": 0.3861941576004028,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 1.2338374099259108,
1071
+ "grad_norm": 0.19381046295166016,
1072
+ "learning_rate": 4.618384445173228e-05,
1073
+ "loss": 0.36703226566314695,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 1.2419567644372274,
1078
+ "grad_norm": 0.1563887596130371,
1079
+ "learning_rate": 4.494892172941965e-05,
1080
+ "loss": 0.40213809013366697,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 1.2500761189485436,
1085
+ "grad_norm": 0.145489901304245,
1086
+ "learning_rate": 4.372592978886254e-05,
1087
+ "loss": 0.344010591506958,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 1.25819547345986,
1092
+ "grad_norm": 0.16564379632472992,
1093
+ "learning_rate": 4.2515133679364116e-05,
1094
+ "loss": 0.3600982904434204,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 1.2663148279711762,
1099
+ "grad_norm": 0.12342356890439987,
1100
+ "learning_rate": 4.13167958071221e-05,
1101
+ "loss": 0.32795798778533936,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 1.2744341824824925,
1106
+ "grad_norm": 0.18176662921905518,
1107
+ "learning_rate": 4.013117587835978e-05,
1108
+ "loss": 0.36577463150024414,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 1.282553536993809,
1113
+ "grad_norm": 0.1916268765926361,
1114
+ "learning_rate": 3.895853084304176e-05,
1115
+ "loss": 0.39234256744384766,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 1.2906728915051253,
1120
+ "grad_norm": 0.1897222399711609,
1121
+ "learning_rate": 3.779911483918739e-05,
1122
+ "loss": 0.41258983612060546,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 1.2987922460164416,
1127
+ "grad_norm": 0.15678349137306213,
1128
+ "learning_rate": 3.665317913779337e-05,
1129
+ "loss": 0.3665084600448608,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 1.3069116005277581,
1134
+ "grad_norm": 0.16308161616325378,
1135
+ "learning_rate": 3.552097208837775e-05,
1136
+ "loss": 0.3931357622146606,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 1.3150309550390744,
1141
+ "grad_norm": 0.1778445839881897,
1142
+ "learning_rate": 3.4402739065157266e-05,
1143
+ "loss": 0.3759305477142334,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 1.3231503095503907,
1148
+ "grad_norm": 0.1780257523059845,
1149
+ "learning_rate": 3.3298722413869155e-05,
1150
+ "loss": 0.3472525358200073,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 1.3312696640617072,
1155
+ "grad_norm": 0.14955449104309082,
1156
+ "learning_rate": 3.2209161399249674e-05,
1157
+ "loss": 0.34793896675109864,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 1.3393890185730235,
1162
+ "grad_norm": 0.20207709074020386,
1163
+ "learning_rate": 3.1134292153180056e-05,
1164
+ "loss": 0.3454656362533569,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 1.3475083730843398,
1169
+ "grad_norm": 0.18875418603420258,
1170
+ "learning_rate": 3.007434762351147e-05,
1171
+ "loss": 0.3456529140472412,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 1.355627727595656,
1176
+ "grad_norm": 0.18712455034255981,
1177
+ "learning_rate": 2.9029557523580253e-05,
1178
+ "loss": 0.33401539325714114,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 1.3637470821069724,
1183
+ "grad_norm": 0.16952762007713318,
1184
+ "learning_rate": 2.800014828242381e-05,
1185
+ "loss": 0.3649503231048584,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 1.3718664366182889,
1190
+ "grad_norm": 0.19082432985305786,
1191
+ "learning_rate": 2.698634299570857e-05,
1192
+ "loss": 0.3909872770309448,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 1.3799857911296052,
1197
+ "grad_norm": 0.16776010394096375,
1198
+ "learning_rate": 2.5988361377380188e-05,
1199
+ "loss": 0.3379994869232178,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 1.3881051456409215,
1204
+ "grad_norm": 0.19785159826278687,
1205
+ "learning_rate": 2.5006419712046636e-05,
1206
+ "loss": 0.3403695821762085,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 1.396224500152238,
1211
+ "grad_norm": 0.12651121616363525,
1212
+ "learning_rate": 2.4040730808104706e-05,
1213
+ "loss": 0.37059574127197265,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 1.4043438546635543,
1218
+ "grad_norm": 0.18700380623340607,
1219
+ "learning_rate": 2.3091503951619543e-05,
1220
+ "loss": 0.4034583568572998,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 1.4124632091748706,
1225
+ "grad_norm": 0.1756463646888733,
1226
+ "learning_rate": 2.2158944860967946e-05,
1227
+ "loss": 0.3308366060256958,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 1.420582563686187,
1232
+ "grad_norm": 0.19831162691116333,
1233
+ "learning_rate": 2.1243255642254578e-05,
1234
+ "loss": 0.3691343069076538,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 1.4287019181975034,
1239
+ "grad_norm": 0.1685105711221695,
1240
+ "learning_rate": 2.0344634745511015e-05,
1241
+ "loss": 0.3646685600280762,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 1.4368212727088197,
1246
+ "grad_norm": 0.1513417512178421,
1247
+ "learning_rate": 1.9463276921687458e-05,
1248
+ "loss": 0.3358032464981079,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 1.444940627220136,
1253
+ "grad_norm": 0.21079151332378387,
1254
+ "learning_rate": 1.8599373180445688e-05,
1255
+ "loss": 0.38408379554748534,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 1.4530599817314522,
1260
+ "grad_norm": 0.1852787733078003,
1261
+ "learning_rate": 1.775311074876329e-05,
1262
+ "loss": 0.3572732925415039,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 1.4611793362427687,
1267
+ "grad_norm": 0.18594121932983398,
1268
+ "learning_rate": 1.6924673030357285e-05,
1269
+ "loss": 0.34491288661956787,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 1.469298690754085,
1274
+ "grad_norm": 0.16469211876392365,
1275
+ "learning_rate": 1.6114239565936484e-05,
1276
+ "loss": 0.3106041193008423,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 1.4774180452654013,
1281
+ "grad_norm": 0.146048441529274,
1282
+ "learning_rate": 1.532198599429122e-05,
1283
+ "loss": 0.3674412965774536,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 1.4855373997767178,
1288
+ "grad_norm": 0.18818271160125732,
1289
+ "learning_rate": 1.454808401422837e-05,
1290
+ "loss": 0.3938064336776733,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 1.4936567542880341,
1295
+ "grad_norm": 0.20953674614429474,
1296
+ "learning_rate": 1.379270134736057e-05,
1297
+ "loss": 0.30992081165313723,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 1.5017761087993504,
1302
+ "grad_norm": 0.21023158729076385,
1303
+ "learning_rate": 1.3056001701757226e-05,
1304
+ "loss": 0.3922957181930542,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 1.509895463310667,
1309
+ "grad_norm": 0.18391859531402588,
1310
+ "learning_rate": 1.233814473646524e-05,
1311
+ "loss": 0.3312171459197998,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 1.518014817821983,
1316
+ "grad_norm": 0.20905567705631256,
1317
+ "learning_rate": 1.1639286026907581e-05,
1318
+ "loss": 0.33843116760253905,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 1.5261341723332995,
1323
+ "grad_norm": 0.2057563066482544,
1324
+ "learning_rate": 1.0959577031166513e-05,
1325
+ "loss": 0.32880287170410155,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 1.5342535268446158,
1330
+ "grad_norm": 0.16004444658756256,
1331
+ "learning_rate": 1.0299165057159332e-05,
1332
+ "loss": 0.3609264850616455,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 1.542372881355932,
1337
+ "grad_norm": 0.18283307552337646,
1338
+ "learning_rate": 9.658193230713509e-06,
1339
+ "loss": 0.36747682094573975,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 1.5504922358672486,
1344
+ "grad_norm": 0.13987980782985687,
1345
+ "learning_rate": 9.036800464548157e-06,
1346
+ "loss": 0.3149809598922729,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 1.558611590378565,
1351
+ "grad_norm": 0.20485147833824158,
1352
+ "learning_rate": 8.435121428168613e-06,
1353
+ "loss": 0.3814858436584473,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 1.5667309448898812,
1358
+ "grad_norm": 0.19381378591060638,
1359
+ "learning_rate": 7.853286518680503e-06,
1360
+ "loss": 0.3389918565750122,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 1.5748502994011977,
1365
+ "grad_norm": 0.1762656271457672,
1366
+ "learning_rate": 7.291421832529921e-06,
1367
+ "loss": 0.3758829355239868,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 1.582969653912514,
1372
+ "grad_norm": 0.18566051125526428,
1373
+ "learning_rate": 6.749649138175518e-06,
1374
+ "loss": 0.361565375328064,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 1.5910890084238303,
1379
+ "grad_norm": 0.1679965704679489,
1380
+ "learning_rate": 6.228085849698495e-06,
1381
+ "loss": 0.3467693567276001,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 1.5992083629351468,
1386
+ "grad_norm": 0.19734881818294525,
1387
+ "learning_rate": 5.726845001356573e-06,
1388
+ "loss": 0.41715250015258787,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 1.6073277174464629,
1393
+ "grad_norm": 0.20948296785354614,
1394
+ "learning_rate": 5.246035223086821e-06,
1395
+ "loss": 0.3086181879043579,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 1.6154470719577794,
1400
+ "grad_norm": 0.2349746823310852,
1401
+ "learning_rate": 4.785760716963205e-06,
1402
+ "loss": 0.2819353580474854,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 1.6235664264690957,
1407
+ "grad_norm": 0.15716052055358887,
1408
+ "learning_rate": 4.346121234613732e-06,
1409
+ "loss": 0.4032479763031006,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 1.631685780980412,
1414
+ "grad_norm": 0.1870564967393875,
1415
+ "learning_rate": 3.927212055602003e-06,
1416
+ "loss": 0.3259021759033203,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 1.6398051354917285,
1421
+ "grad_norm": 0.1917184740304947,
1422
+ "learning_rate": 3.5291239667781253e-06,
1423
+ "loss": 0.3619376182556152,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 1.6479244900030448,
1428
+ "grad_norm": 0.15155203640460968,
1429
+ "learning_rate": 3.1519432426031504e-06,
1430
+ "loss": 0.3836283445358276,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 1.656043844514361,
1435
+ "grad_norm": 0.18562212586402893,
1436
+ "learning_rate": 2.7957516264514593e-06,
1437
+ "loss": 0.35469727516174315,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 1.6641631990256776,
1442
+ "grad_norm": 0.23471137881278992,
1443
+ "learning_rate": 2.4606263128952646e-06,
1444
+ "loss": 0.4092714309692383,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 1.6722825535369938,
1449
+ "grad_norm": 0.19046807289123535,
1450
+ "learning_rate": 2.1466399309747364e-06,
1451
+ "loss": 0.37486720085144043,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 1.6804019080483101,
1456
+ "grad_norm": 0.18093442916870117,
1457
+ "learning_rate": 1.8538605284577848e-06,
1458
+ "loss": 0.3519495248794556,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 1.6885212625596266,
1463
+ "grad_norm": 0.17989413440227509,
1464
+ "learning_rate": 1.5823515570925763e-06,
1465
+ "loss": 0.36248462200164794,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 1.6966406170709427,
1470
+ "grad_norm": 0.18000203371047974,
1471
+ "learning_rate": 1.3321718588561128e-06,
1472
+ "loss": 0.377717113494873,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 1.7047599715822592,
1477
+ "grad_norm": 0.1857496201992035,
1478
+ "learning_rate": 1.1033756532019102e-06,
1479
+ "loss": 0.3373147964477539,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 1.7128793260935755,
1484
+ "grad_norm": 0.15915660560131073,
1485
+ "learning_rate": 8.96012525309442e-07,
1486
+ "loss": 0.35358049869537356,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 1.7209986806048918,
1491
+ "grad_norm": 0.18095794320106506,
1492
+ "learning_rate": 7.101274153379244e-07,
1493
+ "loss": 0.34168615341186526,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 1.7291180351162083,
1498
+ "grad_norm": 0.13066989183425903,
1499
+ "learning_rate": 5.457606086868406e-07,
1500
+ "loss": 0.31731865406036375,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 1.7372373896275246,
1505
+ "grad_norm": 0.15085873007774353,
1506
+ "learning_rate": 4.0294772726511274e-07,
1507
+ "loss": 0.3172720193862915,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 1.745356744138841,
1512
+ "grad_norm": 0.1692853718996048,
1513
+ "learning_rate": 2.817197217711565e-07,
1514
+ "loss": 0.3663973808288574,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 1.7534760986501574,
1519
+ "grad_norm": 0.1765965223312378,
1520
+ "learning_rate": 1.8210286498512307e-07,
1521
+ "loss": 0.3134049415588379,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 1.7615954531614737,
1526
+ "grad_norm": 0.17754477262496948,
1527
+ "learning_rate": 1.0411874607501038e-07,
1528
+ "loss": 0.32787179946899414,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 1.76971480767279,
1533
+ "grad_norm": 0.2181764841079712,
1534
+ "learning_rate": 4.778426591781626e-08,
1535
+ "loss": 0.40297679901123046,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 1.7778341621841065,
1540
+ "grad_norm": 0.14845119416713715,
1541
+ "learning_rate": 1.3111633436779791e-08,
1542
+ "loss": 0.3253025054931641,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 1.7859535166954226,
1547
+ "grad_norm": 0.16625212132930756,
1548
+ "learning_rate": 1.083629553977339e-10,
1549
+ "loss": 0.3306998014450073,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.8465405793631793,
1554
+ "grad_norm": 0.31709548830986023,
1555
+ "learning_rate": 0.0001457833924251086,
1556
+ "loss": 0.6895709991455078,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.8503710797222888,
1561
+ "grad_norm": 0.22089441120624542,
1562
+ "learning_rate": 0.0001453028317991183,
1563
+ "loss": 0.6232875347137451,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.8542015800813981,
1568
+ "grad_norm": 0.22472961246967316,
1569
+ "learning_rate": 0.00014482095116054422,
1570
+ "loss": 0.580645751953125,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.8580320804405075,
1575
+ "grad_norm": 0.18781282007694244,
1576
+ "learning_rate": 0.0001443377645501975,
1577
+ "loss": 0.5852691173553467,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.861862580799617,
1582
+ "grad_norm": 0.3779642581939697,
1583
+ "learning_rate": 0.00014385328604694212,
1584
+ "loss": 0.5722718238830566,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.8656930811587263,
1589
+ "grad_norm": 0.23427145183086395,
1590
+ "learning_rate": 0.0001433675297672846,
1591
+ "loss": 0.566037940979004,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.8695235815178358,
1596
+ "grad_norm": 0.2183203548192978,
1597
+ "learning_rate": 0.00014288050986496268,
1598
+ "loss": 0.6243879795074463,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.8733540818769452,
1603
+ "grad_norm": 0.2532879412174225,
1604
+ "learning_rate": 0.00014239224053053302,
1605
+ "loss": 0.5365942001342774,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.8771845822360546,
1610
+ "grad_norm": 0.20788337290287018,
1611
+ "learning_rate": 0.00014190273599095762,
1612
+ "loss": 0.5467002868652344,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.881015082595164,
1617
+ "grad_norm": 0.2582492232322693,
1618
+ "learning_rate": 0.00014141201050918922,
1619
+ "loss": 0.567399263381958,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.8848455829542734,
1624
+ "grad_norm": 0.19094614684581757,
1625
+ "learning_rate": 0.00014092007838375592,
1626
+ "loss": 0.563731336593628,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.8886760833133828,
1631
+ "grad_norm": 0.24398261308670044,
1632
+ "learning_rate": 0.00014042695394834436,
1633
+ "loss": 0.5930374145507813,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.8925065836724922,
1638
+ "grad_norm": 0.1616758406162262,
1639
+ "learning_rate": 0.0001399326515713822,
1640
+ "loss": 0.5320866584777832,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.8963370840316016,
1645
+ "grad_norm": 0.19463369250297546,
1646
+ "learning_rate": 0.00013943718565561936,
1647
+ "loss": 0.5593301296234131,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.900167584390711,
1652
+ "grad_norm": 0.2512662410736084,
1653
+ "learning_rate": 0.0001389405706377084,
1654
+ "loss": 0.5519943237304688,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.9039980847498205,
1659
+ "grad_norm": 0.24107597768306732,
1660
+ "learning_rate": 0.00013844282098778393,
1661
+ "loss": 0.5739433765411377,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.9078285851089298,
1666
+ "grad_norm": 0.18342378735542297,
1667
+ "learning_rate": 0.00013794395120904089,
1668
+ "loss": 0.5859064102172852,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9116590854680393,
1673
+ "grad_norm": 0.20521777868270874,
1674
+ "learning_rate": 0.00013744397583731203,
1675
+ "loss": 0.5629020214080811,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9154895858271487,
1680
+ "grad_norm": 0.17162705957889557,
1681
+ "learning_rate": 0.00013694290944064435,
1682
+ "loss": 0.5632124900817871,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.919320086186258,
1687
+ "grad_norm": 0.18732701241970062,
1688
+ "learning_rate": 0.00013644076661887452,
1689
+ "loss": 0.5588642120361328,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9231505865453675,
1694
+ "grad_norm": 0.21033287048339844,
1695
+ "learning_rate": 0.00013593756200320372,
1696
+ "loss": 0.5421002864837646,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9269810869044769,
1701
+ "grad_norm": 0.18077102303504944,
1702
+ "learning_rate": 0.0001354333102557712,
1703
+ "loss": 0.5636842727661133,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.9308115872635863,
1708
+ "grad_norm": 0.19449454545974731,
1709
+ "learning_rate": 0.0001349280260692269,
1710
+ "loss": 0.5634388446807861,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.9346420876226957,
1715
+ "grad_norm": 0.21519041061401367,
1716
+ "learning_rate": 0.00013442172416630355,
1717
+ "loss": 0.552568769454956,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.9384725879818051,
1722
+ "grad_norm": 0.21668848395347595,
1723
+ "learning_rate": 0.0001339144192993876,
1724
+ "loss": 0.5575977325439453,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.9423030883409146,
1729
+ "grad_norm": 0.20259518921375275,
1730
+ "learning_rate": 0.00013340612625008946,
1731
+ "loss": 0.5953729629516602,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.946133588700024,
1736
+ "grad_norm": 0.22012926638126373,
1737
+ "learning_rate": 0.0001328968598288127,
1738
+ "loss": 0.5506711006164551,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.9499640890591333,
1743
+ "grad_norm": 0.18549343943595886,
1744
+ "learning_rate": 0.0001323866348743225,
1745
+ "loss": 0.5871614456176758,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.9537945894182428,
1750
+ "grad_norm": 0.1908208429813385,
1751
+ "learning_rate": 0.00013187546625331335,
1752
+ "loss": 0.5431451320648193,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.9576250897773522,
1757
+ "grad_norm": 0.18781603872776031,
1758
+ "learning_rate": 0.0001313633688599759,
1759
+ "loss": 0.5061774730682373,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.9614555901364615,
1764
+ "grad_norm": 0.2165912687778473,
1765
+ "learning_rate": 0.0001308503576155629,
1766
+ "loss": 0.5560242652893066,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.965286090495571,
1771
+ "grad_norm": 0.21473945677280426,
1772
+ "learning_rate": 0.00013033644746795445,
1773
+ "loss": 0.5335087776184082,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.9691165908546804,
1778
+ "grad_norm": 0.2197163999080658,
1779
+ "learning_rate": 0.00012982165339122246,
1780
+ "loss": 0.5561465263366699,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.9729470912137897,
1785
+ "grad_norm": 0.21780231595039368,
1786
+ "learning_rate": 0.00012930599038519434,
1787
+ "loss": 0.5662136554718018,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.9767775915728992,
1792
+ "grad_norm": 0.1910906732082367,
1793
+ "learning_rate": 0.00012878947347501606,
1794
+ "loss": 0.5577693462371827,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.9806080919320086,
1799
+ "grad_norm": 0.18059995770454407,
1800
+ "learning_rate": 0.0001282721177107141,
1801
+ "loss": 0.531907606124878,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.9844385922911181,
1806
+ "grad_norm": 0.24920019507408142,
1807
+ "learning_rate": 0.00012775393816675718,
1808
+ "loss": 0.497232723236084,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.9882690926502274,
1813
+ "grad_norm": 0.2506183385848999,
1814
+ "learning_rate": 0.00012723494994161682,
1815
+ "loss": 0.5702355384826661,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.9920995930093368,
1820
+ "grad_norm": 0.207411989569664,
1821
+ "learning_rate": 0.00012671516815732767,
1822
+ "loss": 0.5431533813476562,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.9959300933684463,
1827
+ "grad_norm": 0.20407091081142426,
1828
+ "learning_rate": 0.00012619460795904657,
1829
+ "loss": 0.5356565952301026,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.9997605937275557,
1834
+ "grad_norm": 0.19829393923282623,
1835
+ "learning_rate": 0.00012567328451461152,
1836
+ "loss": 0.5477075576782227,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 1.0034474503231985,
1841
+ "grad_norm": 0.2388325333595276,
1842
+ "learning_rate": 0.0001251512130140996,
1843
+ "loss": 0.6198837280273437,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 1.007277950682308,
1848
+ "grad_norm": 0.18306539952754974,
1849
+ "learning_rate": 0.00012462840866938436,
1850
+ "loss": 0.5606157779693604,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 1.0111084510414172,
1855
+ "grad_norm": 0.19269554316997528,
1856
+ "learning_rate": 0.00012410488671369275,
1857
+ "loss": 0.5489321231842041,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 1.0149389514005267,
1862
+ "grad_norm": 0.21272292733192444,
1863
+ "learning_rate": 0.00012358066240116092,
1864
+ "loss": 0.5239657878875732,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 1.0187694517596362,
1869
+ "grad_norm": 0.18628379702568054,
1870
+ "learning_rate": 0.00012305575100639014,
1871
+ "loss": 0.4884448528289795,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 1.0225999521187454,
1876
+ "grad_norm": 0.20898866653442383,
1877
+ "learning_rate": 0.00012253016782400148,
1878
+ "loss": 0.5124496459960938,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 1.026430452477855,
1883
+ "grad_norm": 0.20223310589790344,
1884
+ "learning_rate": 0.00012200392816819022,
1885
+ "loss": 0.5053596019744873,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 1.0302609528369644,
1890
+ "grad_norm": 0.20589347183704376,
1891
+ "learning_rate": 0.00012147704737227971,
1892
+ "loss": 0.5432235717773437,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 1.0340914531960737,
1897
+ "grad_norm": 0.19833305478096008,
1898
+ "learning_rate": 0.0001209495407882746,
1899
+ "loss": 0.507619047164917,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 1.0379219535551831,
1904
+ "grad_norm": 0.21857035160064697,
1905
+ "learning_rate": 0.0001204214237864133,
1906
+ "loss": 0.5090025901794434,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 1.0417524539142926,
1911
+ "grad_norm": 0.23668751120567322,
1912
+ "learning_rate": 0.00011989271175472037,
1913
+ "loss": 0.5485597610473633,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 1.0455829542734019,
1918
+ "grad_norm": 0.19491468369960785,
1919
+ "learning_rate": 0.00011936342009855805,
1920
+ "loss": 0.5889732360839843,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 1.0494134546325113,
1925
+ "grad_norm": 0.23975807428359985,
1926
+ "learning_rate": 0.00011883356424017748,
1927
+ "loss": 0.5385537624359131,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 1.0532439549916208,
1932
+ "grad_norm": 0.22210931777954102,
1933
+ "learning_rate": 0.00011830315961826917,
1934
+ "loss": 0.5223836898803711,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 1.05707445535073,
1939
+ "grad_norm": 0.23908647894859314,
1940
+ "learning_rate": 0.00011777222168751325,
1941
+ "loss": 0.5172951221466064,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 1.0609049557098396,
1946
+ "grad_norm": 0.19327178597450256,
1947
+ "learning_rate": 0.00011724076591812918,
1948
+ "loss": 0.5314321517944336,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 1.064735456068949,
1953
+ "grad_norm": 0.1691632866859436,
1954
+ "learning_rate": 0.00011670880779542495,
1955
+ "loss": 0.5226422786712647,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 1.0685659564280585,
1960
+ "grad_norm": 0.21012499928474426,
1961
+ "learning_rate": 0.00011617636281934592,
1962
+ "loss": 0.5367197513580322,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 1.0723964567871678,
1967
+ "grad_norm": 0.22527191042900085,
1968
+ "learning_rate": 0.0001156434465040231,
1969
+ "loss": 0.5030739784240723,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 1.0762269571462773,
1974
+ "grad_norm": 0.2014586478471756,
1975
+ "learning_rate": 0.00011511007437732117,
1976
+ "loss": 0.5275944232940674,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 1.0800574575053867,
1981
+ "grad_norm": 0.21319256722927094,
1982
+ "learning_rate": 0.00011457626198038604,
1983
+ "loss": 0.5280105113983155,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 1.083887957864496,
1988
+ "grad_norm": 0.20912741124629974,
1989
+ "learning_rate": 0.00011404202486719205,
1990
+ "loss": 0.5142996311187744,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 1.0877184582236055,
1995
+ "grad_norm": 0.2093651294708252,
1996
+ "learning_rate": 0.00011350737860408864,
1997
+ "loss": 0.539802885055542,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 1.091548958582715,
2002
+ "grad_norm": 0.23947930335998535,
2003
+ "learning_rate": 0.0001129723387693469,
2004
+ "loss": 0.5196691036224366,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 1.0953794589418242,
2009
+ "grad_norm": 0.21143850684165955,
2010
+ "learning_rate": 0.00011243692095270564,
2011
+ "loss": 0.5398859500885009,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 1.0992099593009337,
2016
+ "grad_norm": 0.27163559198379517,
2017
+ "learning_rate": 0.00011190114075491709,
2018
+ "loss": 0.5032851696014404,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 1.1030404596600432,
2023
+ "grad_norm": 0.1733262985944748,
2024
+ "learning_rate": 0.00011136501378729248,
2025
+ "loss": 0.539389181137085,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 1.1068709600191524,
2030
+ "grad_norm": 0.17658951878547668,
2031
+ "learning_rate": 0.00011082855567124692,
2032
+ "loss": 0.5478601455688477,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 1.110701460378262,
2037
+ "grad_norm": 0.19091221690177917,
2038
+ "learning_rate": 0.00011029178203784443,
2039
+ "loss": 0.5334963321685791,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 1.1145319607373714,
2044
+ "grad_norm": 0.21165837347507477,
2045
+ "learning_rate": 0.00010975470852734242,
2046
+ "loss": 0.554966926574707,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 1.1183624610964806,
2051
+ "grad_norm": 0.19263046979904175,
2052
+ "learning_rate": 0.00010921735078873598,
2053
+ "loss": 0.5330226421356201,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 1.12219296145559,
2058
+ "grad_norm": 0.18461711704730988,
2059
+ "learning_rate": 0.00010867972447930193,
2060
+ "loss": 0.5291602611541748,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 1.1260234618146996,
2065
+ "grad_norm": 0.18377310037612915,
2066
+ "learning_rate": 0.0001081418452641425,
2067
+ "loss": 0.5406131267547607,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 1.1298539621738088,
2072
+ "grad_norm": 0.23681478202342987,
2073
+ "learning_rate": 0.00010760372881572905,
2074
+ "loss": 0.5551674365997314,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 1.1336844625329183,
2079
+ "grad_norm": 0.19873519241809845,
2080
+ "learning_rate": 0.00010706539081344529,
2081
+ "loss": 0.5545490264892579,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 1.1375149628920278,
2086
+ "grad_norm": 0.17395852506160736,
2087
+ "learning_rate": 0.00010652684694313051,
2088
+ "loss": 0.5141590118408204,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 1.1413454632511373,
2093
+ "grad_norm": 0.21609513461589813,
2094
+ "learning_rate": 0.00010598811289662243,
2095
+ "loss": 0.49283924102783205,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 1.1451759636102465,
2100
+ "grad_norm": 0.23576237261295319,
2101
+ "learning_rate": 0.00010544920437130003,
2102
+ "loss": 0.5531333446502685,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 1.149006463969356,
2107
+ "grad_norm": 0.20940575003623962,
2108
+ "learning_rate": 0.00010491013706962622,
2109
+ "loss": 0.5683028221130371,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 1.1528369643284655,
2114
+ "grad_norm": 0.24417303502559662,
2115
+ "learning_rate": 0.00010437092669869024,
2116
+ "loss": 0.5033949851989746,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 1.1566674646875748,
2121
+ "grad_norm": 0.18906274437904358,
2122
+ "learning_rate": 0.00010383158896974998,
2123
+ "loss": 0.5204009532928466,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 1.1604979650466842,
2128
+ "grad_norm": 0.20773115754127502,
2129
+ "learning_rate": 0.00010329213959777431,
2130
+ "loss": 0.5497435092926025,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 1.1643284654057937,
2135
+ "grad_norm": 0.21606457233428955,
2136
+ "learning_rate": 0.000102752594300985,
2137
+ "loss": 0.5554033279418945,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 1.168158965764903,
2142
+ "grad_norm": 0.24872884154319763,
2143
+ "learning_rate": 0.00010221296880039888,
2144
+ "loss": 0.520789384841919,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 1.1719894661240124,
2149
+ "grad_norm": 0.23239879310131073,
2150
+ "learning_rate": 0.00010167327881936979,
2151
+ "loss": 0.554888916015625,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 1.175819966483122,
2156
+ "grad_norm": 0.194828063249588,
2157
+ "learning_rate": 0.00010113354008313025,
2158
+ "loss": 0.5161662101745605,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 1.1796504668422312,
2163
+ "grad_norm": 0.19345180690288544,
2164
+ "learning_rate": 0.00010059376831833347,
2165
+ "loss": 0.5281338691711426,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 1.1834809672013407,
2170
+ "grad_norm": 0.2391313910484314,
2171
+ "learning_rate": 0.00010005397925259496,
2172
+ "loss": 0.5351935863494873,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 1.1873114675604501,
2177
+ "grad_norm": 0.1873185932636261,
2178
+ "learning_rate": 9.95141886140344e-05,
2179
+ "loss": 0.47800097465515134,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 1.1911419679195594,
2184
+ "grad_norm": 0.21092236042022705,
2185
+ "learning_rate": 9.89744121308173e-05,
2186
+ "loss": 0.5321640014648438,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 1.1949724682786689,
2191
+ "grad_norm": 0.1895597130060196,
2192
+ "learning_rate": 9.843466553069666e-05,
2193
+ "loss": 0.5259033679962158,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 1.1988029686377784,
2198
+ "grad_norm": 0.22822576761245728,
2199
+ "learning_rate": 9.789496454055482e-05,
2200
+ "loss": 0.5021588325500488,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 1.2026334689968876,
2205
+ "grad_norm": 0.1812424212694168,
2206
+ "learning_rate": 9.735532488594507e-05,
2207
+ "loss": 0.5383275032043457,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 1.206463969355997,
2212
+ "grad_norm": 0.21432311832904816,
2213
+ "learning_rate": 9.681576229063369e-05,
2214
+ "loss": 0.4902031898498535,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 1.2102944697151066,
2219
+ "grad_norm": 0.2118760645389557,
2220
+ "learning_rate": 9.627629247614152e-05,
2221
+ "loss": 0.5405004978179931,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 1.214124970074216,
2226
+ "grad_norm": 0.17781169712543488,
2227
+ "learning_rate": 9.5736931161286e-05,
2228
+ "loss": 0.5332688808441162,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 1.2179554704333253,
2233
+ "grad_norm": 0.19811245799064636,
2234
+ "learning_rate": 9.519769406172315e-05,
2235
+ "loss": 0.5008315563201904,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 1.2217859707924348,
2240
+ "grad_norm": 0.21972911059856415,
2241
+ "learning_rate": 9.465859688948977e-05,
2242
+ "loss": 0.5292376518249512,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 1.2256164711515443,
2247
+ "grad_norm": 0.23009081184864044,
2248
+ "learning_rate": 9.411965535254541e-05,
2249
+ "loss": 0.5621660709381103,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 1.2294469715106535,
2254
+ "grad_norm": 0.21291089057922363,
2255
+ "learning_rate": 9.358088515431487e-05,
2256
+ "loss": 0.5500400543212891,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 1.233277471869763,
2261
+ "grad_norm": 0.19430555403232574,
2262
+ "learning_rate": 9.304230199323049e-05,
2263
+ "loss": 0.5366146564483643,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 1.2371079722288725,
2268
+ "grad_norm": 0.18103627860546112,
2269
+ "learning_rate": 9.250392156227489e-05,
2270
+ "loss": 0.5162454128265381,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 1.2409384725879817,
2275
+ "grad_norm": 0.1706976294517517,
2276
+ "learning_rate": 9.196575954852351e-05,
2277
+ "loss": 0.5634176731109619,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 1.2447689729470912,
2282
+ "grad_norm": 0.1886712908744812,
2283
+ "learning_rate": 9.142783163268781e-05,
2284
+ "loss": 0.5125929832458496,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 1.2485994733062007,
2289
+ "grad_norm": 0.2378716766834259,
2290
+ "learning_rate": 9.089015348865811e-05,
2291
+ "loss": 0.5268106460571289,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 1.25242997366531,
2296
+ "grad_norm": 0.21824203431606293,
2297
+ "learning_rate": 9.035274078304702e-05,
2298
+ "loss": 0.5469632148742676,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 1.2562604740244194,
2303
+ "grad_norm": 0.19580702483654022,
2304
+ "learning_rate": 8.981560917473293e-05,
2305
+ "loss": 0.5463891983032226,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 1.260090974383529,
2310
+ "grad_norm": 0.24418896436691284,
2311
+ "learning_rate": 8.92787743144038e-05,
2312
+ "loss": 0.4903553485870361,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 1.2639214747426384,
2317
+ "grad_norm": 0.1831478625535965,
2318
+ "learning_rate": 8.874225184410098e-05,
2319
+ "loss": 0.545778226852417,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 1.2677519751017476,
2324
+ "grad_norm": 0.1959410458803177,
2325
+ "learning_rate": 8.820605739676363e-05,
2326
+ "loss": 0.49173221588134763,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 1.2715824754608571,
2331
+ "grad_norm": 0.2172957807779312,
2332
+ "learning_rate": 8.76702065957731e-05,
2333
+ "loss": 0.5537460327148438,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 1.2754129758199664,
2338
+ "grad_norm": 0.23475711047649384,
2339
+ "learning_rate": 8.71347150544978e-05,
2340
+ "loss": 0.5206586837768554,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 1.2792434761790759,
2345
+ "grad_norm": 0.17950321733951569,
2346
+ "learning_rate": 8.659959837583807e-05,
2347
+ "loss": 0.5183176517486572,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 1.2830739765381853,
2352
+ "grad_norm": 0.26022428274154663,
2353
+ "learning_rate": 8.60648721517718e-05,
2354
+ "loss": 0.5329340934753418,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 1.2869044768972948,
2359
+ "grad_norm": 0.21860136091709137,
2360
+ "learning_rate": 8.553055196289992e-05,
2361
+ "loss": 0.5420422554016113,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 1.290734977256404,
2366
+ "grad_norm": 0.20065219700336456,
2367
+ "learning_rate": 8.499665337799254e-05,
2368
+ "loss": 0.4903436183929443,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 1.2945654776155135,
2373
+ "grad_norm": 0.2057187706232071,
2374
+ "learning_rate": 8.446319195353524e-05,
2375
+ "loss": 0.5572310447692871,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 1.2983959779746228,
2380
+ "grad_norm": 0.17702226340770721,
2381
+ "learning_rate": 8.393018323327591e-05,
2382
+ "loss": 0.5058128833770752,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 1.3022264783337323,
2387
+ "grad_norm": 0.19724802672863007,
2388
+ "learning_rate": 8.339764274777165e-05,
2389
+ "loss": 0.5044569969177246,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 1.3060569786928418,
2394
+ "grad_norm": 0.1853686422109604,
2395
+ "learning_rate": 8.286558601393642e-05,
2396
+ "loss": 0.5192684173583985,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 1.3098874790519512,
2401
+ "grad_norm": 0.2165904939174652,
2402
+ "learning_rate": 8.233402853458877e-05,
2403
+ "loss": 0.5493855476379395,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 1.3137179794110605,
2408
+ "grad_norm": 0.18439316749572754,
2409
+ "learning_rate": 8.180298579800035e-05,
2410
+ "loss": 0.500330924987793,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 1.31754847977017,
2415
+ "grad_norm": 0.1958782970905304,
2416
+ "learning_rate": 8.127247327744434e-05,
2417
+ "loss": 0.5382319450378418,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 1.3213789801292795,
2422
+ "grad_norm": 0.1947711557149887,
2423
+ "learning_rate": 8.074250643074484e-05,
2424
+ "loss": 0.5128917217254638,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 1.3252094804883887,
2429
+ "grad_norm": 0.17371414601802826,
2430
+ "learning_rate": 8.021310069982624e-05,
2431
+ "loss": 0.5215467929840087,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 1.3290399808474982,
2436
+ "grad_norm": 0.19855856895446777,
2437
+ "learning_rate": 7.968427151026355e-05,
2438
+ "loss": 0.5010844230651855,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 1.3328704812066077,
2443
+ "grad_norm": 0.18040011823177338,
2444
+ "learning_rate": 7.915603427083268e-05,
2445
+ "loss": 0.51223783493042,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 1.3367009815657172,
2450
+ "grad_norm": 0.21727366745471954,
2451
+ "learning_rate": 7.862840437306165e-05,
2452
+ "loss": 0.5380761623382568,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 1.3405314819248264,
2457
+ "grad_norm": 0.17868368327617645,
2458
+ "learning_rate": 7.810139719078195e-05,
2459
+ "loss": 0.543517017364502,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 1.3443619822839359,
2464
+ "grad_norm": 0.23797963559627533,
2465
+ "learning_rate": 7.757502807968075e-05,
2466
+ "loss": 0.5299440860748291,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 1.3481924826430451,
2471
+ "grad_norm": 0.20597504079341888,
2472
+ "learning_rate": 7.704931237685342e-05,
2473
+ "loss": 0.5269464969635009,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 1.3520229830021546,
2478
+ "grad_norm": 0.21105614304542542,
2479
+ "learning_rate": 7.652426540035657e-05,
2480
+ "loss": 0.5518492221832275,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 1.355853483361264,
2485
+ "grad_norm": 0.2271437793970108,
2486
+ "learning_rate": 7.599990244876183e-05,
2487
+ "loss": 0.5539456844329834,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 1.3596839837203736,
2492
+ "grad_norm": 0.20776766538619995,
2493
+ "learning_rate": 7.547623880070993e-05,
2494
+ "loss": 0.5296282291412353,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 1.3079467156637574,
2499
+ "grad_norm": 0.2367064505815506,
2500
+ "learning_rate": 7.495328971446578e-05,
2501
+ "loss": 0.6062966346740722,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 1.3116214974735876,
2506
+ "grad_norm": 0.2572702169418335,
2507
+ "learning_rate": 7.44310704274736e-05,
2508
+ "loss": 0.6122443199157714,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 1.3152962792834175,
2513
+ "grad_norm": 0.19573259353637695,
2514
+ "learning_rate": 7.390959615591316e-05,
2515
+ "loss": 0.6494469165802002,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 1.3189710610932477,
2520
+ "grad_norm": 0.22986537218093872,
2521
+ "learning_rate": 7.338888209425622e-05,
2522
+ "loss": 0.6188368797302246,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 1.3226458429030776,
2527
+ "grad_norm": 0.22328007221221924,
2528
+ "learning_rate": 7.286894341482397e-05,
2529
+ "loss": 0.6440567970275879,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 1.3263206247129076,
2534
+ "grad_norm": 0.21681271493434906,
2535
+ "learning_rate": 7.234979526734482e-05,
2536
+ "loss": 0.6130101680755615,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 1.3299954065227377,
2541
+ "grad_norm": 0.23429043591022491,
2542
+ "learning_rate": 7.183145277851313e-05,
2543
+ "loss": 0.5713854312896729,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 1.3336701883325677,
2548
+ "grad_norm": 0.22499820590019226,
2549
+ "learning_rate": 7.131393105154826e-05,
2550
+ "loss": 0.6435183048248291,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 1.3373449701423978,
2555
+ "grad_norm": 0.23204010725021362,
2556
+ "learning_rate": 7.079724516575466e-05,
2557
+ "loss": 0.5970840930938721,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 1.3410197519522278,
2562
+ "grad_norm": 0.22594687342643738,
2563
+ "learning_rate": 7.028141017608234e-05,
2564
+ "loss": 0.6086468696594238,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 1.344694533762058,
2569
+ "grad_norm": 0.23983144760131836,
2570
+ "learning_rate": 6.976644111268845e-05,
2571
+ "loss": 0.6677327632904053,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 1.3483693155718879,
2576
+ "grad_norm": 0.2365673929452896,
2577
+ "learning_rate": 6.925235298049906e-05,
2578
+ "loss": 0.6098092555999756,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 1.352044097381718,
2583
+ "grad_norm": 0.24905718863010406,
2584
+ "learning_rate": 6.873916075877216e-05,
2585
+ "loss": 0.6216807842254639,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 1.355718879191548,
2590
+ "grad_norm": 0.23672564327716827,
2591
+ "learning_rate": 6.822687940066102e-05,
2592
+ "loss": 0.6090316295623779,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 1.359393661001378,
2597
+ "grad_norm": 0.20575745403766632,
2598
+ "learning_rate": 6.771552383277875e-05,
2599
+ "loss": 0.6467265129089356,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 1.363068442811208,
2604
+ "grad_norm": 0.23861850798130035,
2605
+ "learning_rate": 6.720510895476309e-05,
2606
+ "loss": 0.5875473022460938,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 1.3667432246210383,
2611
+ "grad_norm": 0.2574703097343445,
2612
+ "learning_rate": 6.669564963884245e-05,
2613
+ "loss": 0.622504186630249,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 1.3704180064308682,
2618
+ "grad_norm": 0.25036099553108215,
2619
+ "learning_rate": 6.618716072940248e-05,
2620
+ "loss": 0.6222783088684082,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 1.3740927882406981,
2625
+ "grad_norm": 0.23848992586135864,
2626
+ "learning_rate": 6.56796570425537e-05,
2627
+ "loss": 0.6142213821411133,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 1.3777675700505283,
2632
+ "grad_norm": 0.22312362492084503,
2633
+ "learning_rate": 6.517315336569953e-05,
2634
+ "loss": 0.633341121673584,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 1.3814423518603582,
2639
+ "grad_norm": 0.24296629428863525,
2640
+ "learning_rate": 6.466766445710568e-05,
2641
+ "loss": 0.6525699138641358,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 1.3851171336701884,
2646
+ "grad_norm": 0.2250729650259018,
2647
+ "learning_rate": 6.416320504546997e-05,
2648
+ "loss": 0.6627958297729493,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 1.3887919154800183,
2653
+ "grad_norm": 0.2684767246246338,
2654
+ "learning_rate": 6.365978982949324e-05,
2655
+ "loss": 0.6367505550384521,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 1.3924666972898483,
2660
+ "grad_norm": 0.21995939314365387,
2661
+ "learning_rate": 6.315743347745097e-05,
2662
+ "loss": 0.6509771347045898,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 1.3961414790996785,
2667
+ "grad_norm": 0.24876751005649567,
2668
+ "learning_rate": 6.265615062676612e-05,
2669
+ "loss": 0.588352108001709,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 1.3998162609095086,
2674
+ "grad_norm": 0.2845150828361511,
2675
+ "learning_rate": 6.215595588358233e-05,
2676
+ "loss": 0.5724838733673095,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 1.4034910427193386,
2681
+ "grad_norm": 0.22122569382190704,
2682
+ "learning_rate": 6.165686382233855e-05,
2683
+ "loss": 0.621783971786499,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 1.4071658245291685,
2688
+ "grad_norm": 0.23665687441825867,
2689
+ "learning_rate": 6.115888898534427e-05,
2690
+ "loss": 0.5714973449707031,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 1.4108406063389987,
2695
+ "grad_norm": 0.26456931233406067,
2696
+ "learning_rate": 6.066204588235585e-05,
2697
+ "loss": 0.5998946189880371,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 1.4145153881488286,
2702
+ "grad_norm": 0.21921156346797943,
2703
+ "learning_rate": 6.016634899015369e-05,
2704
+ "loss": 0.6019998550415039,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 1.4181901699586588,
2709
+ "grad_norm": 0.2688063681125641,
2710
+ "learning_rate": 5.967181275212046e-05,
2711
+ "loss": 0.584591293334961,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 1.4218649517684887,
2716
+ "grad_norm": 0.26307207345962524,
2717
+ "learning_rate": 5.917845157782025e-05,
2718
+ "loss": 0.592690896987915,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 1.4255397335783189,
2723
+ "grad_norm": 0.28062573075294495,
2724
+ "learning_rate": 5.8686279842578615e-05,
2725
+ "loss": 0.5952250480651855,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 1.4292145153881488,
2730
+ "grad_norm": 0.24920772016048431,
2731
+ "learning_rate": 5.819531188706393e-05,
2732
+ "loss": 0.6023118972778321,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 1.432889297197979,
2737
+ "grad_norm": 0.2551993429660797,
2738
+ "learning_rate": 5.770556201686927e-05,
2739
+ "loss": 0.5991564750671386,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 1.436564079007809,
2744
+ "grad_norm": 0.225216805934906,
2745
+ "learning_rate": 5.7217044502095806e-05,
2746
+ "loss": 0.5858877182006836,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 1.4402388608176389,
2751
+ "grad_norm": 0.24253210425376892,
2752
+ "learning_rate": 5.6729773576936874e-05,
2753
+ "loss": 0.5954824924468994,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 1.443913642627469,
2758
+ "grad_norm": 0.22022658586502075,
2759
+ "learning_rate": 5.624376343926332e-05,
2760
+ "loss": 0.625191593170166,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 1.447588424437299,
2765
+ "grad_norm": 0.22758881747722626,
2766
+ "learning_rate": 5.575902825020962e-05,
2767
+ "loss": 0.5991941928863526,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 1.4512632062471291,
2772
+ "grad_norm": 0.22000859677791595,
2773
+ "learning_rate": 5.527558213376161e-05,
2774
+ "loss": 0.6294786930084229,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 1.454937988056959,
2779
+ "grad_norm": 0.22377276420593262,
2780
+ "learning_rate": 5.479343917634451e-05,
2781
+ "loss": 0.6242120742797852,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 1.4586127698667892,
2786
+ "grad_norm": 0.27151235938072205,
2787
+ "learning_rate": 5.431261342641286e-05,
2788
+ "loss": 0.5964043617248536,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 1.4622875516766192,
2793
+ "grad_norm": 0.22597825527191162,
2794
+ "learning_rate": 5.383311889404103e-05,
2795
+ "loss": 0.6154329299926757,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 1.4659623334864493,
2800
+ "grad_norm": 0.21540269255638123,
2801
+ "learning_rate": 5.3354969550514856e-05,
2802
+ "loss": 0.6018314361572266,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 1.4696371152962793,
2807
+ "grad_norm": 0.23756641149520874,
2808
+ "learning_rate": 5.287817932792485e-05,
2809
+ "loss": 0.6373420715332031,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 1.4733118971061092,
2814
+ "grad_norm": 0.24588297307491302,
2815
+ "learning_rate": 5.240276211876005e-05,
2816
+ "loss": 0.6303625583648682,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 1.4769866789159394,
2821
+ "grad_norm": 0.23921391367912292,
2822
+ "learning_rate": 5.192873177550321e-05,
2823
+ "loss": 0.6234454154968262,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 1.4806614607257695,
2828
+ "grad_norm": 0.268675833940506,
2829
+ "learning_rate": 5.1456102110227375e-05,
2830
+ "loss": 0.5861053943634034,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 1.4843362425355995,
2835
+ "grad_norm": 0.23049448430538177,
2836
+ "learning_rate": 5.098488689419313e-05,
2837
+ "loss": 0.6783847332000732,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 1.4880110243454294,
2842
+ "grad_norm": 0.2512610852718353,
2843
+ "learning_rate": 5.0515099857447615e-05,
2844
+ "loss": 0.6114784717559815,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 1.4916858061552596,
2849
+ "grad_norm": 0.21778461337089539,
2850
+ "learning_rate": 5.004675468842436e-05,
2851
+ "loss": 0.6642892360687256,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 1.4953605879650895,
2856
+ "grad_norm": 0.2870982885360718,
2857
+ "learning_rate": 4.957986503354433e-05,
2858
+ "loss": 0.6069085121154785,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 1.4990353697749197,
2863
+ "grad_norm": 0.2539427876472473,
2864
+ "learning_rate": 4.91144444968185e-05,
2865
+ "loss": 0.5883574485778809,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 1.5027101515847496,
2870
+ "grad_norm": 0.2666284739971161,
2871
+ "learning_rate": 4.865050663945139e-05,
2872
+ "loss": 0.64878249168396,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 1.5063849333945796,
2877
+ "grad_norm": 0.2161935567855835,
2878
+ "learning_rate": 4.818806497944575e-05,
2879
+ "loss": 0.6164711952209473,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 1.5100597152044097,
2884
+ "grad_norm": 0.270613431930542,
2885
+ "learning_rate": 4.772713299120909e-05,
2886
+ "loss": 0.5953383922576905,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 1.51373449701424,
2891
+ "grad_norm": 0.22387981414794922,
2892
+ "learning_rate": 4.726772410516055e-05,
2893
+ "loss": 0.6686501026153564,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 1.5174092788240698,
2898
+ "grad_norm": 0.21915844082832336,
2899
+ "learning_rate": 4.680985170734005e-05,
2900
+ "loss": 0.6070637702941895,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 1.5210840606338998,
2905
+ "grad_norm": 0.25814303755760193,
2906
+ "learning_rate": 4.635352913901785e-05,
2907
+ "loss": 0.5802205562591553,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 1.52475884244373,
2912
+ "grad_norm": 0.2502751648426056,
2913
+ "learning_rate": 4.5898769696306155e-05,
2914
+ "loss": 0.606569766998291,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 1.52843362425356,
2919
+ "grad_norm": 0.29439958930015564,
2920
+ "learning_rate": 4.544558662977154e-05,
2921
+ "loss": 0.5848165988922119,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 1.53210840606339,
2926
+ "grad_norm": 0.2533748745918274,
2927
+ "learning_rate": 4.499399314404874e-05,
2928
+ "loss": 0.6226361751556396,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 1.53578318787322,
2933
+ "grad_norm": 0.20448249578475952,
2934
+ "learning_rate": 4.454400239745619e-05,
2935
+ "loss": 0.6301614284515381,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 1.53945796968305,
2940
+ "grad_norm": 0.21227025985717773,
2941
+ "learning_rate": 4.4095627501612416e-05,
2942
+ "loss": 0.635749626159668,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 1.54313275149288,
2947
+ "grad_norm": 0.23682698607444763,
2948
+ "learning_rate": 4.364888152105397e-05,
2949
+ "loss": 0.6260458946228027,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 1.5468075333027103,
2954
+ "grad_norm": 0.19529347121715546,
2955
+ "learning_rate": 4.320377747285497e-05,
2956
+ "loss": 0.6009593963623047,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 1.5504823151125402,
2961
+ "grad_norm": 0.2707568109035492,
2962
+ "learning_rate": 4.2760328326247534e-05,
2963
+ "loss": 0.5838070869445801,
2964
+ "step": 4220
2965
+ },
2966
+ {
2967
+ "epoch": 1.5541570969223701,
2968
+ "grad_norm": 0.26869723200798035,
2969
+ "learning_rate": 4.231854700224417e-05,
2970
+ "loss": 0.5800216674804688,
2971
+ "step": 4230
2972
+ },
2973
+ {
2974
+ "epoch": 1.5578318787322003,
2975
+ "grad_norm": 0.2252606600522995,
2976
+ "learning_rate": 4.18784463732611e-05,
2977
+ "loss": 0.6049102306365967,
2978
+ "step": 4240
2979
+ },
2980
+ {
2981
+ "epoch": 1.5615066605420305,
2982
+ "grad_norm": 0.2604488730430603,
2983
+ "learning_rate": 4.1440039262743227e-05,
2984
+ "loss": 0.6492654323577881,
2985
+ "step": 4250
2986
+ },
2987
+ {
2988
+ "epoch": 1.5651814423518604,
2989
+ "grad_norm": 0.25955140590667725,
2990
+ "learning_rate": 4.100333844479055e-05,
2991
+ "loss": 0.5918104171752929,
2992
+ "step": 4260
2993
+ },
2994
+ {
2995
+ "epoch": 1.5688562241616903,
2996
+ "grad_norm": 0.2388666868209839,
2997
+ "learning_rate": 4.0568356643785856e-05,
2998
+ "loss": 0.6321864128112793,
2999
+ "step": 4270
3000
+ },
3001
+ {
3002
+ "epoch": 1.5725310059715203,
3003
+ "grad_norm": 0.26732930541038513,
3004
+ "learning_rate": 4.0135106534024056e-05,
3005
+ "loss": 0.6065220832824707,
3006
+ "step": 4280
3007
+ },
3008
+ {
3009
+ "epoch": 1.5762057877813505,
3010
+ "grad_norm": 0.2281692773103714,
3011
+ "learning_rate": 3.9703600739342985e-05,
3012
+ "loss": 0.5991446495056152,
3013
+ "step": 4290
3014
+ },
3015
+ {
3016
+ "epoch": 1.5798805695911806,
3017
+ "grad_norm": 0.23855754733085632,
3018
+ "learning_rate": 3.9273851832755214e-05,
3019
+ "loss": 0.5810461044311523,
3020
+ "step": 4300
3021
+ },
3022
+ {
3023
+ "epoch": 1.5835553514010106,
3024
+ "grad_norm": 0.30157583951950073,
3025
+ "learning_rate": 3.8845872336082125e-05,
3026
+ "loss": 0.5769465923309326,
3027
+ "step": 4310
3028
+ },
3029
+ {
3030
+ "epoch": 1.5872301332108405,
3031
+ "grad_norm": 0.2254714071750641,
3032
+ "learning_rate": 3.8419674719588725e-05,
3033
+ "loss": 0.6204625129699707,
3034
+ "step": 4320
3035
+ },
3036
+ {
3037
+ "epoch": 1.5909049150206707,
3038
+ "grad_norm": 0.22155548632144928,
3039
+ "learning_rate": 3.799527140162055e-05,
3040
+ "loss": 0.583667516708374,
3041
+ "step": 4330
3042
+ },
3043
+ {
3044
+ "epoch": 1.5945796968305008,
3045
+ "grad_norm": 0.24007032811641693,
3046
+ "learning_rate": 3.7572674748241674e-05,
3047
+ "loss": 0.6734154224395752,
3048
+ "step": 4340
3049
+ },
3050
+ {
3051
+ "epoch": 1.5982544786403308,
3052
+ "grad_norm": 0.24698472023010254,
3053
+ "learning_rate": 3.715189707287436e-05,
3054
+ "loss": 0.5612778663635254,
3055
+ "step": 4350
3056
+ },
3057
+ {
3058
+ "epoch": 1.6019292604501607,
3059
+ "grad_norm": 0.23125363886356354,
3060
+ "learning_rate": 3.673295063594049e-05,
3061
+ "loss": 0.6097794532775879,
3062
+ "step": 4360
3063
+ },
3064
+ {
3065
+ "epoch": 1.6056040422599906,
3066
+ "grad_norm": 0.2623499035835266,
3067
+ "learning_rate": 3.631584764450402e-05,
3068
+ "loss": 0.6135641098022461,
3069
+ "step": 4370
3070
+ },
3071
+ {
3072
+ "epoch": 1.6092788240698208,
3073
+ "grad_norm": 0.3083759844303131,
3074
+ "learning_rate": 3.590060025191556e-05,
3075
+ "loss": 0.623767614364624,
3076
+ "step": 4380
3077
+ },
3078
+ {
3079
+ "epoch": 1.612953605879651,
3080
+ "grad_norm": 0.21405094861984253,
3081
+ "learning_rate": 3.5487220557458176e-05,
3082
+ "loss": 0.580271863937378,
3083
+ "step": 4390
3084
+ },
3085
+ {
3086
+ "epoch": 1.616628387689481,
3087
+ "grad_norm": 0.27044427394866943,
3088
+ "learning_rate": 3.507572060599471e-05,
3089
+ "loss": 0.60565185546875,
3090
+ "step": 4400
3091
+ },
3092
+ {
3093
+ "epoch": 1.6203031694993109,
3094
+ "grad_norm": 0.2213546633720398,
3095
+ "learning_rate": 3.4666112387617045e-05,
3096
+ "loss": 0.6188304424285889,
3097
+ "step": 4410
3098
+ },
3099
+ {
3100
+ "epoch": 1.623977951309141,
3101
+ "grad_norm": 0.236136794090271,
3102
+ "learning_rate": 3.425840783729664e-05,
3103
+ "loss": 0.5975236892700195,
3104
+ "step": 4420
3105
+ },
3106
+ {
3107
+ "epoch": 1.6276527331189712,
3108
+ "grad_norm": 0.2937586009502411,
3109
+ "learning_rate": 3.385261883453664e-05,
3110
+ "loss": 0.6132159233093262,
3111
+ "step": 4430
3112
+ },
3113
+ {
3114
+ "epoch": 1.6313275149288011,
3115
+ "grad_norm": 0.26236283779144287,
3116
+ "learning_rate": 3.344875720302604e-05,
3117
+ "loss": 0.6577489852905274,
3118
+ "step": 4440
3119
+ },
3120
+ {
3121
+ "epoch": 1.635002296738631,
3122
+ "grad_norm": 0.21058732271194458,
3123
+ "learning_rate": 3.304683471029485e-05,
3124
+ "loss": 0.630679988861084,
3125
+ "step": 4450
3126
+ },
3127
+ {
3128
+ "epoch": 1.6386770785484612,
3129
+ "grad_norm": 0.24456511437892914,
3130
+ "learning_rate": 3.264686306737147e-05,
3131
+ "loss": 0.5711773872375489,
3132
+ "step": 4460
3133
+ },
3134
+ {
3135
+ "epoch": 1.6423518603582912,
3136
+ "grad_norm": 0.28906679153442383,
3137
+ "learning_rate": 3.2248853928441304e-05,
3138
+ "loss": 0.6463574409484864,
3139
+ "step": 4470
3140
+ },
3141
+ {
3142
+ "epoch": 1.6460266421681213,
3143
+ "grad_norm": 0.2541700005531311,
3144
+ "learning_rate": 3.185281889050725e-05,
3145
+ "loss": 0.5943029880523681,
3146
+ "step": 4480
3147
+ },
3148
+ {
3149
+ "epoch": 1.6497014239779513,
3150
+ "grad_norm": 0.20259977877140045,
3151
+ "learning_rate": 3.1458769493051854e-05,
3152
+ "loss": 0.5949666023254394,
3153
+ "step": 4490
3154
+ },
3155
+ {
3156
+ "epoch": 1.6533762057877812,
3157
+ "grad_norm": 0.20865267515182495,
3158
+ "learning_rate": 3.1066717217700835e-05,
3159
+ "loss": 0.622490930557251,
3160
+ "step": 4500
3161
+ },
3162
+ {
3163
+ "epoch": 1.6570509875976114,
3164
+ "grad_norm": 0.2103072702884674,
3165
+ "learning_rate": 3.067667348788885e-05,
3166
+ "loss": 0.596876859664917,
3167
+ "step": 4510
3168
+ },
3169
+ {
3170
+ "epoch": 1.6607257694074415,
3171
+ "grad_norm": 0.2789931297302246,
3172
+ "learning_rate": 3.0288649668526504e-05,
3173
+ "loss": 0.6100345134735108,
3174
+ "step": 4520
3175
+ },
3176
+ {
3177
+ "epoch": 1.6644005512172715,
3178
+ "grad_norm": 0.2407047599554062,
3179
+ "learning_rate": 2.9902657065669082e-05,
3180
+ "loss": 0.5866603374481201,
3181
+ "step": 4530
3182
+ },
3183
+ {
3184
+ "epoch": 1.6680753330271014,
3185
+ "grad_norm": 0.23293636739253998,
3186
+ "learning_rate": 2.951870692618739e-05,
3187
+ "loss": 0.6044306755065918,
3188
+ "step": 4540
3189
+ },
3190
+ {
3191
+ "epoch": 1.6717501148369316,
3192
+ "grad_norm": 0.26319974660873413,
3193
+ "learning_rate": 2.9136810437439743e-05,
3194
+ "loss": 0.6011191844940186,
3195
+ "step": 4550
3196
+ },
3197
+ {
3198
+ "epoch": 1.6754248966467618,
3199
+ "grad_norm": 0.266152024269104,
3200
+ "learning_rate": 2.8756978726946283e-05,
3201
+ "loss": 0.6181775569915772,
3202
+ "step": 4560
3203
+ },
3204
+ {
3205
+ "epoch": 1.6790996784565917,
3206
+ "grad_norm": 0.22137150168418884,
3207
+ "learning_rate": 2.8379222862064568e-05,
3208
+ "loss": 0.5735309600830079,
3209
+ "step": 4570
3210
+ },
3211
+ {
3212
+ "epoch": 1.6827744602664216,
3213
+ "grad_norm": 0.19313573837280273,
3214
+ "learning_rate": 2.8003553849667097e-05,
3215
+ "loss": 0.5909959316253662,
3216
+ "step": 4580
3217
+ },
3218
+ {
3219
+ "epoch": 1.6864492420762516,
3220
+ "grad_norm": 0.2427615523338318,
3221
+ "learning_rate": 2.7629982635820707e-05,
3222
+ "loss": 0.6190264225006104,
3223
+ "step": 4590
3224
+ },
3225
+ {
3226
+ "epoch": 1.6901240238860817,
3227
+ "grad_norm": 0.2528453469276428,
3228
+ "learning_rate": 2.7258520105467567e-05,
3229
+ "loss": 0.5556782245635986,
3230
+ "step": 4600
3231
+ },
3232
+ {
3233
+ "epoch": 1.693798805695912,
3234
+ "grad_norm": 0.21333430707454681,
3235
+ "learning_rate": 2.6889177082107942e-05,
3236
+ "loss": 0.6259308815002441,
3237
+ "step": 4610
3238
+ },
3239
+ {
3240
+ "epoch": 1.6974735875057418,
3241
+ "grad_norm": 0.2462078183889389,
3242
+ "learning_rate": 2.6521964327485017e-05,
3243
+ "loss": 0.6408613681793213,
3244
+ "step": 4620
3245
+ },
3246
+ {
3247
+ "epoch": 1.7011483693155718,
3248
+ "grad_norm": 0.22960656881332397,
3249
+ "learning_rate": 2.6156892541271084e-05,
3250
+ "loss": 0.5830319881439209,
3251
+ "step": 4630
3252
+ },
3253
+ {
3254
+ "epoch": 1.704823151125402,
3255
+ "grad_norm": 0.23370933532714844,
3256
+ "learning_rate": 2.5793972360756002e-05,
3257
+ "loss": 0.6464344978332519,
3258
+ "step": 4640
3259
+ },
3260
+ {
3261
+ "epoch": 1.708497932935232,
3262
+ "grad_norm": 0.25368574261665344,
3263
+ "learning_rate": 2.543321436053713e-05,
3264
+ "loss": 0.5802364826202393,
3265
+ "step": 4650
3266
+ },
3267
+ {
3268
+ "epoch": 1.712172714745062,
3269
+ "grad_norm": 0.23351016640663147,
3270
+ "learning_rate": 2.5074629052211217e-05,
3271
+ "loss": 0.6773637294769287,
3272
+ "step": 4660
3273
+ },
3274
+ {
3275
+ "epoch": 1.715847496554892,
3276
+ "grad_norm": 0.23634305596351624,
3277
+ "learning_rate": 2.4718226884068187e-05,
3278
+ "loss": 0.6070538997650147,
3279
+ "step": 4670
3280
+ },
3281
+ {
3282
+ "epoch": 1.719522278364722,
3283
+ "grad_norm": 0.23648826777935028,
3284
+ "learning_rate": 2.4364018240786546e-05,
3285
+ "loss": 0.63211030960083,
3286
+ "step": 4680
3287
+ },
3288
+ {
3289
+ "epoch": 1.723197060174552,
3290
+ "grad_norm": 0.2305329442024231,
3291
+ "learning_rate": 2.401201344313102e-05,
3292
+ "loss": 0.5770946502685547,
3293
+ "step": 4690
3294
+ },
3295
+ {
3296
+ "epoch": 1.7268718419843823,
3297
+ "grad_norm": 0.20384910702705383,
3298
+ "learning_rate": 2.3662222747651695e-05,
3299
+ "loss": 0.578916597366333,
3300
+ "step": 4700
3301
+ },
3302
+ {
3303
+ "epoch": 1.7305466237942122,
3304
+ "grad_norm": 0.21320855617523193,
3305
+ "learning_rate": 2.3314656346385134e-05,
3306
+ "loss": 0.5877019882202148,
3307
+ "step": 4710
3308
+ },
3309
+ {
3310
+ "epoch": 1.7342214056040421,
3311
+ "grad_norm": 0.24065816402435303,
3312
+ "learning_rate": 2.2969324366557522e-05,
3313
+ "loss": 0.6320582866668701,
3314
+ "step": 4720
3315
+ },
3316
+ {
3317
+ "epoch": 1.7378961874138723,
3318
+ "grad_norm": 0.21492637693881989,
3319
+ "learning_rate": 2.2626236870289452e-05,
3320
+ "loss": 0.6050594806671142,
3321
+ "step": 4730
3322
+ },
3323
+ {
3324
+ "epoch": 1.7415709692237025,
3325
+ "grad_norm": 0.23171354830265045,
3326
+ "learning_rate": 2.2285403854302912e-05,
3327
+ "loss": 0.6136460304260254,
3328
+ "step": 4740
3329
+ },
3330
+ {
3331
+ "epoch": 1.7452457510335324,
3332
+ "grad_norm": 0.23479370772838593,
3333
+ "learning_rate": 2.194683524962986e-05,
3334
+ "loss": 0.5907188892364502,
3335
+ "step": 4750
3336
+ },
3337
+ {
3338
+ "epoch": 1.7489205328433624,
3339
+ "grad_norm": 0.21812178194522858,
3340
+ "learning_rate": 2.161054092132284e-05,
3341
+ "loss": 0.6049327850341797,
3342
+ "step": 4760
3343
+ },
3344
+ {
3345
+ "epoch": 1.7525953146531925,
3346
+ "grad_norm": 0.22398284077644348,
3347
+ "learning_rate": 2.1276530668167728e-05,
3348
+ "loss": 0.6184739112854004,
3349
+ "step": 4770
3350
+ },
3351
+ {
3352
+ "epoch": 1.7562700964630225,
3353
+ "grad_norm": 0.28541100025177,
3354
+ "learning_rate": 2.0944814222397944e-05,
3355
+ "loss": 0.594030237197876,
3356
+ "step": 4780
3357
+ },
3358
+ {
3359
+ "epoch": 1.7599448782728526,
3360
+ "grad_norm": 0.2562128007411957,
3361
+ "learning_rate": 2.061540124941117e-05,
3362
+ "loss": 0.6142899513244628,
3363
+ "step": 4790
3364
+ },
3365
+ {
3366
+ "epoch": 1.7636196600826826,
3367
+ "grad_norm": 0.2420058250427246,
3368
+ "learning_rate": 2.0288301347487528e-05,
3369
+ "loss": 0.6153490543365479,
3370
+ "step": 4800
3371
+ },
3372
+ {
3373
+ "epoch": 1.7672944418925125,
3374
+ "grad_norm": 0.30034923553466797,
3375
+ "learning_rate": 1.9963524047509897e-05,
3376
+ "loss": 0.5961874008178711,
3377
+ "step": 4810
3378
+ },
3379
+ {
3380
+ "epoch": 1.7709692237023427,
3381
+ "grad_norm": 0.3149788975715637,
3382
+ "learning_rate": 1.9641078812686375e-05,
3383
+ "loss": 0.6012597560882569,
3384
+ "step": 4820
3385
+ },
3386
+ {
3387
+ "epoch": 1.7746440055121728,
3388
+ "grad_norm": 0.2160654366016388,
3389
+ "learning_rate": 1.9320975038274402e-05,
3390
+ "loss": 0.5875374794006347,
3391
+ "step": 4830
3392
+ },
3393
+ {
3394
+ "epoch": 1.7783187873220028,
3395
+ "grad_norm": 0.25491863489151,
3396
+ "learning_rate": 1.9003222051307047e-05,
3397
+ "loss": 0.5735582828521728,
3398
+ "step": 4840
3399
+ },
3400
+ {
3401
+ "epoch": 1.7819935691318327,
3402
+ "grad_norm": 0.2498500943183899,
3403
+ "learning_rate": 1.8687829110321254e-05,
3404
+ "loss": 0.6238004684448242,
3405
+ "step": 4850
3406
+ },
3407
+ {
3408
+ "epoch": 1.7856683509416629,
3409
+ "grad_norm": 0.23228974640369415,
3410
+ "learning_rate": 1.8374805405088014e-05,
3411
+ "loss": 0.6190362930297851,
3412
+ "step": 4860
3413
+ },
3414
+ {
3415
+ "epoch": 1.789343132751493,
3416
+ "grad_norm": 0.248588427901268,
3417
+ "learning_rate": 1.8064160056344716e-05,
3418
+ "loss": 0.6250235080718994,
3419
+ "step": 4870
3420
+ },
3421
+ {
3422
+ "epoch": 1.793017914561323,
3423
+ "grad_norm": 0.22170130908489227,
3424
+ "learning_rate": 1.7755902115529222e-05,
3425
+ "loss": 0.6499590873718262,
3426
+ "step": 4880
3427
+ },
3428
+ {
3429
+ "epoch": 1.796692696371153,
3430
+ "grad_norm": 0.242046058177948,
3431
+ "learning_rate": 1.7450040564516322e-05,
3432
+ "loss": 0.6411127567291259,
3433
+ "step": 4890
3434
+ },
3435
+ {
3436
+ "epoch": 1.8003674781809829,
3437
+ "grad_norm": 0.24742132425308228,
3438
+ "learning_rate": 1.7146584315355885e-05,
3439
+ "loss": 0.5813017368316651,
3440
+ "step": 4900
3441
+ },
3442
+ {
3443
+ "epoch": 1.804042259990813,
3444
+ "grad_norm": 0.25267845392227173,
3445
+ "learning_rate": 1.6845542210013198e-05,
3446
+ "loss": 0.5960687637329102,
3447
+ "step": 4910
3448
+ },
3449
+ {
3450
+ "epoch": 1.8077170418006432,
3451
+ "grad_norm": 0.23756426572799683,
3452
+ "learning_rate": 1.6546923020111417e-05,
3453
+ "loss": 0.5912890911102295,
3454
+ "step": 4920
3455
+ },
3456
+ {
3457
+ "epoch": 1.8113918236104731,
3458
+ "grad_norm": 0.22568336129188538,
3459
+ "learning_rate": 1.6250735446675912e-05,
3460
+ "loss": 0.6352333068847656,
3461
+ "step": 4930
3462
+ },
3463
+ {
3464
+ "epoch": 1.815066605420303,
3465
+ "grad_norm": 0.24231384694576263,
3466
+ "learning_rate": 1.5956988119880712e-05,
3467
+ "loss": 0.6327116966247559,
3468
+ "step": 4940
3469
+ },
3470
+ {
3471
+ "epoch": 1.8187413872301332,
3472
+ "grad_norm": 0.2860916554927826,
3473
+ "learning_rate": 1.5665689598797174e-05,
3474
+ "loss": 0.6136715888977051,
3475
+ "step": 4950
3476
+ },
3477
+ {
3478
+ "epoch": 1.8224161690399634,
3479
+ "grad_norm": 0.27555617690086365,
3480
+ "learning_rate": 1.5376848371144402e-05,
3481
+ "loss": 0.6523287773132325,
3482
+ "step": 4960
3483
+ },
3484
+ {
3485
+ "epoch": 1.8260909508497933,
3486
+ "grad_norm": 0.23608949780464172,
3487
+ "learning_rate": 1.5090472853042137e-05,
3488
+ "loss": 0.5987821578979492,
3489
+ "step": 4970
3490
+ },
3491
+ {
3492
+ "epoch": 1.8297657326596233,
3493
+ "grad_norm": 0.26431113481521606,
3494
+ "learning_rate": 1.48065713887654e-05,
3495
+ "loss": 0.6213451385498047,
3496
+ "step": 4980
3497
+ },
3498
+ {
3499
+ "epoch": 1.8334405144694532,
3500
+ "grad_norm": 0.26088884472846985,
3501
+ "learning_rate": 1.4525152250501361e-05,
3502
+ "loss": 0.6668256282806396,
3503
+ "step": 4990
3504
+ },
3505
+ {
3506
+ "epoch": 1.8371152962792834,
3507
+ "grad_norm": 0.2662504017353058,
3508
+ "learning_rate": 1.424622363810838e-05,
3509
+ "loss": 0.6278341770172119,
3510
+ "step": 5000
3511
+ }
3512
+ ],
3513
+ "logging_steps": 10,
3514
+ "max_steps": 6000,
3515
+ "num_input_tokens_seen": 0,
3516
+ "num_train_epochs": 3,
3517
+ "save_steps": 25,
3518
+ "stateful_callbacks": {
3519
+ "TrainerControl": {
3520
+ "args": {
3521
+ "should_epoch_stop": false,
3522
+ "should_evaluate": false,
3523
+ "should_log": false,
3524
+ "should_save": true,
3525
+ "should_training_stop": false
3526
+ },
3527
+ "attributes": {}
3528
+ }
3529
+ },
3530
+ "total_flos": 7.715959081590129e+17,
3531
+ "train_batch_size": 4,
3532
+ "trial_name": null,
3533
+ "trial_params": null
3534
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd737ade882c002f79b2b055bb95bc81c6f63b8dc1ed4dd502ccc03fccd30d5
3
+ size 5201