lubocido
commited on
Upload 11 files
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +2471 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b23468fb689f08218e8190a2ff3dc46a2603785bf1d484bcd10eaf34b8cb7a2e
|
| 3 |
+
size 251748704
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad94129b079ed59ba1280e5411adfa10dd44bd9f2e59534fa2e832ae6e12909f
|
| 3 |
+
size 503720658
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f70b77cc195a3f598765730dd04ed398766e99cbf2c8fd1016958927b5367c8
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e47417f136640a6648ba1176d3e9f3e6911a762420c231217d9e064fd5c9b9e
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": true
|
| 43 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2471 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.6455026455026456,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 1.7509137392044067,
|
| 14 |
+
"learning_rate": 9.974804736709499e-06,
|
| 15 |
+
"loss": 1.9586,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 1.5435916185379028,
|
| 21 |
+
"learning_rate": 9.949609473418998e-06,
|
| 22 |
+
"loss": 1.764,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02,
|
| 27 |
+
"grad_norm": 1.209004521369934,
|
| 28 |
+
"learning_rate": 9.924414210128497e-06,
|
| 29 |
+
"loss": 1.5738,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03,
|
| 34 |
+
"grad_norm": 1.036686897277832,
|
| 35 |
+
"learning_rate": 9.899218946837995e-06,
|
| 36 |
+
"loss": 1.456,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"grad_norm": 0.8039250373840332,
|
| 42 |
+
"learning_rate": 9.874023683547493e-06,
|
| 43 |
+
"loss": 1.3517,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05,
|
| 48 |
+
"grad_norm": 0.668268620967865,
|
| 49 |
+
"learning_rate": 9.848828420256992e-06,
|
| 50 |
+
"loss": 1.2773,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"grad_norm": 0.6465680003166199,
|
| 56 |
+
"learning_rate": 9.823633156966492e-06,
|
| 57 |
+
"loss": 1.2494,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06,
|
| 62 |
+
"grad_norm": 0.669222891330719,
|
| 63 |
+
"learning_rate": 9.79843789367599e-06,
|
| 64 |
+
"loss": 1.2465,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07,
|
| 69 |
+
"grad_norm": 0.7393785715103149,
|
| 70 |
+
"learning_rate": 9.773242630385489e-06,
|
| 71 |
+
"loss": 1.2073,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08,
|
| 76 |
+
"grad_norm": 0.6821632385253906,
|
| 77 |
+
"learning_rate": 9.748047367094986e-06,
|
| 78 |
+
"loss": 1.1725,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"grad_norm": 0.698268711566925,
|
| 84 |
+
"learning_rate": 9.722852103804486e-06,
|
| 85 |
+
"loss": 1.1724,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.09,
|
| 90 |
+
"grad_norm": 0.6640620231628418,
|
| 91 |
+
"learning_rate": 9.697656840513983e-06,
|
| 92 |
+
"loss": 1.1656,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1,
|
| 97 |
+
"grad_norm": 0.8017461895942688,
|
| 98 |
+
"learning_rate": 9.672461577223483e-06,
|
| 99 |
+
"loss": 1.1764,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.11,
|
| 104 |
+
"grad_norm": 0.6652551293373108,
|
| 105 |
+
"learning_rate": 9.64726631393298e-06,
|
| 106 |
+
"loss": 1.1706,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.11,
|
| 111 |
+
"grad_norm": 0.8237988352775574,
|
| 112 |
+
"learning_rate": 9.62207105064248e-06,
|
| 113 |
+
"loss": 1.1231,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.12,
|
| 118 |
+
"grad_norm": 0.8982694149017334,
|
| 119 |
+
"learning_rate": 9.59687578735198e-06,
|
| 120 |
+
"loss": 1.1417,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13,
|
| 125 |
+
"grad_norm": 0.7859475016593933,
|
| 126 |
+
"learning_rate": 9.571680524061477e-06,
|
| 127 |
+
"loss": 1.1382,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"grad_norm": 0.9249159693717957,
|
| 133 |
+
"learning_rate": 9.546485260770976e-06,
|
| 134 |
+
"loss": 1.1363,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.14,
|
| 139 |
+
"grad_norm": 1.221252202987671,
|
| 140 |
+
"learning_rate": 9.521289997480474e-06,
|
| 141 |
+
"loss": 1.1382,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.15,
|
| 146 |
+
"grad_norm": 4.636524200439453,
|
| 147 |
+
"learning_rate": 9.498614260519024e-06,
|
| 148 |
+
"loss": 1.0979,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.16,
|
| 153 |
+
"grad_norm": 0.7521413564682007,
|
| 154 |
+
"learning_rate": 9.473418997228522e-06,
|
| 155 |
+
"loss": 1.0645,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.17,
|
| 160 |
+
"grad_norm": 0.8328731060028076,
|
| 161 |
+
"learning_rate": 9.44822373393802e-06,
|
| 162 |
+
"loss": 1.0585,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.17,
|
| 167 |
+
"grad_norm": 0.8342303037643433,
|
| 168 |
+
"learning_rate": 9.423028470647519e-06,
|
| 169 |
+
"loss": 1.0655,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.18,
|
| 174 |
+
"grad_norm": 0.8196636438369751,
|
| 175 |
+
"learning_rate": 9.397833207357018e-06,
|
| 176 |
+
"loss": 1.0221,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.19,
|
| 181 |
+
"grad_norm": 0.7511851787567139,
|
| 182 |
+
"learning_rate": 9.372637944066516e-06,
|
| 183 |
+
"loss": 1.046,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2,
|
| 188 |
+
"grad_norm": 0.8341330885887146,
|
| 189 |
+
"learning_rate": 9.347442680776014e-06,
|
| 190 |
+
"loss": 1.0331,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2,
|
| 195 |
+
"grad_norm": 0.9003998637199402,
|
| 196 |
+
"learning_rate": 9.322247417485513e-06,
|
| 197 |
+
"loss": 1.0386,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.21,
|
| 202 |
+
"grad_norm": 0.79107266664505,
|
| 203 |
+
"learning_rate": 9.297052154195013e-06,
|
| 204 |
+
"loss": 1.0152,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.22,
|
| 209 |
+
"grad_norm": 0.7756459712982178,
|
| 210 |
+
"learning_rate": 9.27185689090451e-06,
|
| 211 |
+
"loss": 1.0224,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.23,
|
| 216 |
+
"grad_norm": 0.762424647808075,
|
| 217 |
+
"learning_rate": 9.24666162761401e-06,
|
| 218 |
+
"loss": 1.0517,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.23,
|
| 223 |
+
"grad_norm": 0.7143459916114807,
|
| 224 |
+
"learning_rate": 9.221466364323507e-06,
|
| 225 |
+
"loss": 1.0106,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.24,
|
| 230 |
+
"grad_norm": 0.7883962988853455,
|
| 231 |
+
"learning_rate": 9.196271101033007e-06,
|
| 232 |
+
"loss": 1.0004,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.25,
|
| 237 |
+
"grad_norm": 0.7985430359840393,
|
| 238 |
+
"learning_rate": 9.171075837742504e-06,
|
| 239 |
+
"loss": 1.0171,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.26,
|
| 244 |
+
"grad_norm": 0.8012735247612,
|
| 245 |
+
"learning_rate": 9.145880574452004e-06,
|
| 246 |
+
"loss": 1.0106,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.26,
|
| 251 |
+
"grad_norm": 0.7331275939941406,
|
| 252 |
+
"learning_rate": 9.120685311161502e-06,
|
| 253 |
+
"loss": 1.0044,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.27,
|
| 258 |
+
"grad_norm": 0.8667876124382019,
|
| 259 |
+
"learning_rate": 9.095490047871001e-06,
|
| 260 |
+
"loss": 1.0195,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.28,
|
| 265 |
+
"grad_norm": 0.8839796781539917,
|
| 266 |
+
"learning_rate": 9.0702947845805e-06,
|
| 267 |
+
"loss": 1.0145,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.29,
|
| 272 |
+
"grad_norm": 0.8900341391563416,
|
| 273 |
+
"learning_rate": 9.045099521289998e-06,
|
| 274 |
+
"loss": 1.0171,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.29,
|
| 279 |
+
"grad_norm": 0.8628876805305481,
|
| 280 |
+
"learning_rate": 9.019904257999496e-06,
|
| 281 |
+
"loss": 1.0039,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3,
|
| 286 |
+
"grad_norm": 0.8550145626068115,
|
| 287 |
+
"learning_rate": 8.994708994708995e-06,
|
| 288 |
+
"loss": 1.015,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.31,
|
| 293 |
+
"grad_norm": 0.8471419215202332,
|
| 294 |
+
"learning_rate": 8.969513731418495e-06,
|
| 295 |
+
"loss": 1.0114,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.32,
|
| 300 |
+
"grad_norm": 0.8051427006721497,
|
| 301 |
+
"learning_rate": 8.944318468127992e-06,
|
| 302 |
+
"loss": 0.9998,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.33,
|
| 307 |
+
"grad_norm": 0.8776746392250061,
|
| 308 |
+
"learning_rate": 8.919123204837492e-06,
|
| 309 |
+
"loss": 1.0109,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.33,
|
| 314 |
+
"grad_norm": 0.9933453798294067,
|
| 315 |
+
"learning_rate": 8.893927941546991e-06,
|
| 316 |
+
"loss": 1.0099,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.34,
|
| 321 |
+
"grad_norm": 0.8829633593559265,
|
| 322 |
+
"learning_rate": 8.868732678256489e-06,
|
| 323 |
+
"loss": 1.0201,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.35,
|
| 328 |
+
"grad_norm": 0.8752363324165344,
|
| 329 |
+
"learning_rate": 8.843537414965987e-06,
|
| 330 |
+
"loss": 1.0022,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.36,
|
| 335 |
+
"grad_norm": 0.9361273050308228,
|
| 336 |
+
"learning_rate": 8.818342151675486e-06,
|
| 337 |
+
"loss": 1.0075,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.36,
|
| 342 |
+
"grad_norm": 0.8231716156005859,
|
| 343 |
+
"learning_rate": 8.793146888384985e-06,
|
| 344 |
+
"loss": 0.984,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.37,
|
| 349 |
+
"grad_norm": 0.8183861374855042,
|
| 350 |
+
"learning_rate": 8.767951625094483e-06,
|
| 351 |
+
"loss": 0.9871,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.38,
|
| 356 |
+
"grad_norm": 0.9514871835708618,
|
| 357 |
+
"learning_rate": 8.74275636180398e-06,
|
| 358 |
+
"loss": 1.024,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.39,
|
| 363 |
+
"grad_norm": 0.9753857254981995,
|
| 364 |
+
"learning_rate": 8.71756109851348e-06,
|
| 365 |
+
"loss": 0.9926,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.39,
|
| 370 |
+
"grad_norm": 0.9237353205680847,
|
| 371 |
+
"learning_rate": 8.69236583522298e-06,
|
| 372 |
+
"loss": 0.9709,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.4,
|
| 377 |
+
"grad_norm": 0.9065663814544678,
|
| 378 |
+
"learning_rate": 8.667170571932477e-06,
|
| 379 |
+
"loss": 0.9848,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.41,
|
| 384 |
+
"grad_norm": 0.8715184926986694,
|
| 385 |
+
"learning_rate": 8.641975308641975e-06,
|
| 386 |
+
"loss": 1.0091,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.42,
|
| 391 |
+
"grad_norm": 0.8322390913963318,
|
| 392 |
+
"learning_rate": 8.616780045351474e-06,
|
| 393 |
+
"loss": 0.9876,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.42,
|
| 398 |
+
"grad_norm": 0.9560284614562988,
|
| 399 |
+
"learning_rate": 8.591584782060974e-06,
|
| 400 |
+
"loss": 1.0234,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.43,
|
| 405 |
+
"grad_norm": 0.8381783366203308,
|
| 406 |
+
"learning_rate": 8.566389518770471e-06,
|
| 407 |
+
"loss": 0.9788,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.44,
|
| 412 |
+
"grad_norm": 0.8607673645019531,
|
| 413 |
+
"learning_rate": 8.541194255479971e-06,
|
| 414 |
+
"loss": 0.9816,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.45,
|
| 419 |
+
"grad_norm": 0.8169811367988586,
|
| 420 |
+
"learning_rate": 8.515998992189469e-06,
|
| 421 |
+
"loss": 1.0092,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.45,
|
| 426 |
+
"grad_norm": 0.9223540425300598,
|
| 427 |
+
"learning_rate": 8.490803728898968e-06,
|
| 428 |
+
"loss": 0.9885,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.46,
|
| 433 |
+
"grad_norm": 0.7612660527229309,
|
| 434 |
+
"learning_rate": 8.465608465608466e-06,
|
| 435 |
+
"loss": 0.97,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.47,
|
| 440 |
+
"grad_norm": 0.860916256904602,
|
| 441 |
+
"learning_rate": 8.440413202317965e-06,
|
| 442 |
+
"loss": 0.9921,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.48,
|
| 447 |
+
"grad_norm": 0.807750403881073,
|
| 448 |
+
"learning_rate": 8.415217939027463e-06,
|
| 449 |
+
"loss": 0.987,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.48,
|
| 454 |
+
"grad_norm": 0.7962011694908142,
|
| 455 |
+
"learning_rate": 8.390022675736962e-06,
|
| 456 |
+
"loss": 1.0134,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.49,
|
| 461 |
+
"grad_norm": 0.8323624730110168,
|
| 462 |
+
"learning_rate": 8.364827412446462e-06,
|
| 463 |
+
"loss": 0.9769,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.5,
|
| 468 |
+
"grad_norm": 0.9545472860336304,
|
| 469 |
+
"learning_rate": 8.33963214915596e-06,
|
| 470 |
+
"loss": 0.9862,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.51,
|
| 475 |
+
"grad_norm": 1.0507547855377197,
|
| 476 |
+
"learning_rate": 8.314436885865457e-06,
|
| 477 |
+
"loss": 0.9977,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.51,
|
| 482 |
+
"grad_norm": 0.9005000591278076,
|
| 483 |
+
"learning_rate": 8.289241622574956e-06,
|
| 484 |
+
"loss": 0.9897,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.52,
|
| 489 |
+
"grad_norm": 0.8091966509819031,
|
| 490 |
+
"learning_rate": 8.264046359284456e-06,
|
| 491 |
+
"loss": 1.0188,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.53,
|
| 496 |
+
"grad_norm": 0.8602038025856018,
|
| 497 |
+
"learning_rate": 8.238851095993954e-06,
|
| 498 |
+
"loss": 0.9997,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.54,
|
| 503 |
+
"grad_norm": 0.9347642660140991,
|
| 504 |
+
"learning_rate": 8.213655832703453e-06,
|
| 505 |
+
"loss": 0.9904,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.54,
|
| 510 |
+
"grad_norm": 0.8802648782730103,
|
| 511 |
+
"learning_rate": 8.188460569412952e-06,
|
| 512 |
+
"loss": 0.9765,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.55,
|
| 517 |
+
"grad_norm": 0.8487595915794373,
|
| 518 |
+
"learning_rate": 8.16326530612245e-06,
|
| 519 |
+
"loss": 1.0184,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.56,
|
| 524 |
+
"grad_norm": 0.9282223582267761,
|
| 525 |
+
"learning_rate": 8.138070042831948e-06,
|
| 526 |
+
"loss": 1.0047,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.57,
|
| 531 |
+
"grad_norm": 1.0162054300308228,
|
| 532 |
+
"learning_rate": 8.112874779541447e-06,
|
| 533 |
+
"loss": 0.9909,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.57,
|
| 538 |
+
"grad_norm": 0.8241488337516785,
|
| 539 |
+
"learning_rate": 8.087679516250947e-06,
|
| 540 |
+
"loss": 0.9976,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.58,
|
| 545 |
+
"grad_norm": 1.069097638130188,
|
| 546 |
+
"learning_rate": 8.062484252960444e-06,
|
| 547 |
+
"loss": 0.9874,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.59,
|
| 552 |
+
"grad_norm": 0.9084659218788147,
|
| 553 |
+
"learning_rate": 8.037288989669942e-06,
|
| 554 |
+
"loss": 0.9751,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.6,
|
| 559 |
+
"grad_norm": 0.9863806962966919,
|
| 560 |
+
"learning_rate": 8.012093726379441e-06,
|
| 561 |
+
"loss": 0.9815,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6,
|
| 566 |
+
"grad_norm": 0.9838799834251404,
|
| 567 |
+
"learning_rate": 7.98689846308894e-06,
|
| 568 |
+
"loss": 1.0019,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.61,
|
| 573 |
+
"grad_norm": 1.0254228115081787,
|
| 574 |
+
"learning_rate": 7.961703199798438e-06,
|
| 575 |
+
"loss": 0.9918,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.62,
|
| 580 |
+
"grad_norm": 0.9409896731376648,
|
| 581 |
+
"learning_rate": 7.936507936507936e-06,
|
| 582 |
+
"loss": 0.9899,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.63,
|
| 587 |
+
"grad_norm": 0.9909108281135559,
|
| 588 |
+
"learning_rate": 7.911312673217436e-06,
|
| 589 |
+
"loss": 0.9666,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.63,
|
| 594 |
+
"grad_norm": 0.9930652976036072,
|
| 595 |
+
"learning_rate": 7.886117409926935e-06,
|
| 596 |
+
"loss": 0.9643,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.64,
|
| 601 |
+
"grad_norm": 0.983561098575592,
|
| 602 |
+
"learning_rate": 7.860922146636433e-06,
|
| 603 |
+
"loss": 0.9895,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.65,
|
| 608 |
+
"grad_norm": 0.9257413148880005,
|
| 609 |
+
"learning_rate": 7.835726883345932e-06,
|
| 610 |
+
"loss": 0.9933,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.66,
|
| 615 |
+
"grad_norm": 0.9350329041481018,
|
| 616 |
+
"learning_rate": 7.81053162005543e-06,
|
| 617 |
+
"loss": 0.9725,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.67,
|
| 622 |
+
"grad_norm": 1.0069069862365723,
|
| 623 |
+
"learning_rate": 7.78533635676493e-06,
|
| 624 |
+
"loss": 0.9739,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.67,
|
| 629 |
+
"grad_norm": 0.9367712736129761,
|
| 630 |
+
"learning_rate": 7.760141093474427e-06,
|
| 631 |
+
"loss": 0.9835,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.68,
|
| 636 |
+
"grad_norm": 0.867667555809021,
|
| 637 |
+
"learning_rate": 7.734945830183926e-06,
|
| 638 |
+
"loss": 0.9937,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.69,
|
| 643 |
+
"grad_norm": 0.9225870370864868,
|
| 644 |
+
"learning_rate": 7.709750566893424e-06,
|
| 645 |
+
"loss": 0.9771,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7,
|
| 650 |
+
"grad_norm": 0.9846392869949341,
|
| 651 |
+
"learning_rate": 7.684555303602923e-06,
|
| 652 |
+
"loss": 0.9988,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.7,
|
| 657 |
+
"grad_norm": 0.8313792943954468,
|
| 658 |
+
"learning_rate": 7.659360040312423e-06,
|
| 659 |
+
"loss": 0.9594,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.71,
|
| 664 |
+
"grad_norm": 0.9007426500320435,
|
| 665 |
+
"learning_rate": 7.63416477702192e-06,
|
| 666 |
+
"loss": 0.9641,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.72,
|
| 671 |
+
"grad_norm": 0.9949538111686707,
|
| 672 |
+
"learning_rate": 7.608969513731419e-06,
|
| 673 |
+
"loss": 0.9981,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.73,
|
| 678 |
+
"grad_norm": 1.0600723028182983,
|
| 679 |
+
"learning_rate": 7.583774250440918e-06,
|
| 680 |
+
"loss": 0.9799,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.73,
|
| 685 |
+
"grad_norm": 1.124242901802063,
|
| 686 |
+
"learning_rate": 7.558578987150417e-06,
|
| 687 |
+
"loss": 0.9923,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.74,
|
| 692 |
+
"grad_norm": 1.1153829097747803,
|
| 693 |
+
"learning_rate": 7.533383723859915e-06,
|
| 694 |
+
"loss": 0.976,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.75,
|
| 699 |
+
"grad_norm": 0.996911346912384,
|
| 700 |
+
"learning_rate": 7.508188460569413e-06,
|
| 701 |
+
"loss": 0.9952,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.76,
|
| 706 |
+
"grad_norm": 0.866919219493866,
|
| 707 |
+
"learning_rate": 7.482993197278913e-06,
|
| 708 |
+
"loss": 0.9708,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.76,
|
| 713 |
+
"grad_norm": 1.0361676216125488,
|
| 714 |
+
"learning_rate": 7.457797933988411e-06,
|
| 715 |
+
"loss": 0.9757,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.77,
|
| 720 |
+
"grad_norm": 1.0245063304901123,
|
| 721 |
+
"learning_rate": 7.432602670697909e-06,
|
| 722 |
+
"loss": 0.9879,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.78,
|
| 727 |
+
"grad_norm": 0.9136086106300354,
|
| 728 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 729 |
+
"loss": 0.962,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.79,
|
| 734 |
+
"grad_norm": 1.1000611782073975,
|
| 735 |
+
"learning_rate": 7.382212144116907e-06,
|
| 736 |
+
"loss": 0.9743,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.79,
|
| 741 |
+
"grad_norm": 1.0377795696258545,
|
| 742 |
+
"learning_rate": 7.3570168808264054e-06,
|
| 743 |
+
"loss": 0.9392,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.8,
|
| 748 |
+
"grad_norm": 0.9714633226394653,
|
| 749 |
+
"learning_rate": 7.331821617535904e-06,
|
| 750 |
+
"loss": 0.964,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.81,
|
| 755 |
+
"grad_norm": 1.027772068977356,
|
| 756 |
+
"learning_rate": 7.306626354245403e-06,
|
| 757 |
+
"loss": 0.9784,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.82,
|
| 762 |
+
"grad_norm": 0.9620116949081421,
|
| 763 |
+
"learning_rate": 7.281431090954901e-06,
|
| 764 |
+
"loss": 0.9803,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.82,
|
| 769 |
+
"grad_norm": 1.0313563346862793,
|
| 770 |
+
"learning_rate": 7.2562358276644e-06,
|
| 771 |
+
"loss": 0.9816,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.83,
|
| 776 |
+
"grad_norm": 1.058566927909851,
|
| 777 |
+
"learning_rate": 7.231040564373898e-06,
|
| 778 |
+
"loss": 0.9692,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.84,
|
| 783 |
+
"grad_norm": 0.9281766414642334,
|
| 784 |
+
"learning_rate": 7.205845301083398e-06,
|
| 785 |
+
"loss": 0.9508,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.85,
|
| 790 |
+
"grad_norm": 0.960678219795227,
|
| 791 |
+
"learning_rate": 7.180650037792895e-06,
|
| 792 |
+
"loss": 0.9437,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.85,
|
| 797 |
+
"grad_norm": 0.9975042343139648,
|
| 798 |
+
"learning_rate": 7.155454774502394e-06,
|
| 799 |
+
"loss": 0.97,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.86,
|
| 804 |
+
"grad_norm": 0.9827629327774048,
|
| 805 |
+
"learning_rate": 7.130259511211892e-06,
|
| 806 |
+
"loss": 0.9709,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.87,
|
| 811 |
+
"grad_norm": 1.084519386291504,
|
| 812 |
+
"learning_rate": 7.105064247921392e-06,
|
| 813 |
+
"loss": 0.9736,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.88,
|
| 818 |
+
"grad_norm": 1.1209474802017212,
|
| 819 |
+
"learning_rate": 7.0798689846308895e-06,
|
| 820 |
+
"loss": 0.9722,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.88,
|
| 825 |
+
"grad_norm": 1.0013864040374756,
|
| 826 |
+
"learning_rate": 7.054673721340388e-06,
|
| 827 |
+
"loss": 0.9671,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.89,
|
| 832 |
+
"grad_norm": 0.9566646218299866,
|
| 833 |
+
"learning_rate": 7.0294784580498875e-06,
|
| 834 |
+
"loss": 0.9767,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.9,
|
| 839 |
+
"grad_norm": 0.9742752909660339,
|
| 840 |
+
"learning_rate": 7.004283194759386e-06,
|
| 841 |
+
"loss": 0.9703,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.91,
|
| 846 |
+
"grad_norm": 1.1095930337905884,
|
| 847 |
+
"learning_rate": 6.979087931468885e-06,
|
| 848 |
+
"loss": 0.9817,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.91,
|
| 853 |
+
"grad_norm": 1.0295912027359009,
|
| 854 |
+
"learning_rate": 6.953892668178382e-06,
|
| 855 |
+
"loss": 0.9756,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.92,
|
| 860 |
+
"grad_norm": 1.0642352104187012,
|
| 861 |
+
"learning_rate": 6.928697404887882e-06,
|
| 862 |
+
"loss": 0.9503,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.93,
|
| 867 |
+
"grad_norm": 1.157819390296936,
|
| 868 |
+
"learning_rate": 6.90350214159738e-06,
|
| 869 |
+
"loss": 0.9765,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.94,
|
| 874 |
+
"grad_norm": 1.0977922677993774,
|
| 875 |
+
"learning_rate": 6.878306878306879e-06,
|
| 876 |
+
"loss": 0.9706,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.94,
|
| 881 |
+
"grad_norm": 0.9640308022499084,
|
| 882 |
+
"learning_rate": 6.853111615016378e-06,
|
| 883 |
+
"loss": 0.9578,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.95,
|
| 888 |
+
"grad_norm": 1.0732492208480835,
|
| 889 |
+
"learning_rate": 6.827916351725876e-06,
|
| 890 |
+
"loss": 0.9455,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.96,
|
| 895 |
+
"grad_norm": 0.9846688508987427,
|
| 896 |
+
"learning_rate": 6.8027210884353745e-06,
|
| 897 |
+
"loss": 0.9764,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.97,
|
| 902 |
+
"grad_norm": 0.8813304901123047,
|
| 903 |
+
"learning_rate": 6.777525825144873e-06,
|
| 904 |
+
"loss": 0.9842,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.98,
|
| 909 |
+
"grad_norm": 0.9812163710594177,
|
| 910 |
+
"learning_rate": 6.752330561854372e-06,
|
| 911 |
+
"loss": 0.9593,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.98,
|
| 916 |
+
"grad_norm": 1.0121666193008423,
|
| 917 |
+
"learning_rate": 6.72713529856387e-06,
|
| 918 |
+
"loss": 0.9623,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.99,
|
| 923 |
+
"grad_norm": 1.0399516820907593,
|
| 924 |
+
"learning_rate": 6.701940035273369e-06,
|
| 925 |
+
"loss": 0.9665,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.0,
|
| 930 |
+
"grad_norm": 0.9701886773109436,
|
| 931 |
+
"learning_rate": 6.676744771982868e-06,
|
| 932 |
+
"loss": 0.978,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.01,
|
| 937 |
+
"grad_norm": 1.0398330688476562,
|
| 938 |
+
"learning_rate": 6.651549508692367e-06,
|
| 939 |
+
"loss": 0.9515,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.01,
|
| 944 |
+
"grad_norm": 1.038935661315918,
|
| 945 |
+
"learning_rate": 6.626354245401865e-06,
|
| 946 |
+
"loss": 0.958,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.02,
|
| 951 |
+
"grad_norm": 1.0119668245315552,
|
| 952 |
+
"learning_rate": 6.601158982111363e-06,
|
| 953 |
+
"loss": 0.9347,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.03,
|
| 958 |
+
"grad_norm": 0.9660181403160095,
|
| 959 |
+
"learning_rate": 6.575963718820862e-06,
|
| 960 |
+
"loss": 0.9577,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.04,
|
| 965 |
+
"grad_norm": 0.9453220963478088,
|
| 966 |
+
"learning_rate": 6.550768455530361e-06,
|
| 967 |
+
"loss": 0.9375,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.04,
|
| 972 |
+
"grad_norm": 0.9495384693145752,
|
| 973 |
+
"learning_rate": 6.525573192239859e-06,
|
| 974 |
+
"loss": 0.9311,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.05,
|
| 979 |
+
"grad_norm": 1.1077016592025757,
|
| 980 |
+
"learning_rate": 6.500377928949359e-06,
|
| 981 |
+
"loss": 0.9489,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.06,
|
| 986 |
+
"grad_norm": 1.0165854692459106,
|
| 987 |
+
"learning_rate": 6.4751826656588565e-06,
|
| 988 |
+
"loss": 0.958,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.07,
|
| 993 |
+
"grad_norm": 1.3001985549926758,
|
| 994 |
+
"learning_rate": 6.449987402368355e-06,
|
| 995 |
+
"loss": 0.9325,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.07,
|
| 1000 |
+
"grad_norm": 1.0839056968688965,
|
| 1001 |
+
"learning_rate": 6.424792139077854e-06,
|
| 1002 |
+
"loss": 0.9769,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.08,
|
| 1007 |
+
"grad_norm": 1.0319207906723022,
|
| 1008 |
+
"learning_rate": 6.399596875787353e-06,
|
| 1009 |
+
"loss": 0.9574,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.09,
|
| 1014 |
+
"grad_norm": 1.0123823881149292,
|
| 1015 |
+
"learning_rate": 6.374401612496851e-06,
|
| 1016 |
+
"loss": 0.9315,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.1,
|
| 1021 |
+
"grad_norm": 1.1985503435134888,
|
| 1022 |
+
"learning_rate": 6.349206349206349e-06,
|
| 1023 |
+
"loss": 0.9354,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.1,
|
| 1028 |
+
"grad_norm": 1.1550285816192627,
|
| 1029 |
+
"learning_rate": 6.324011085915849e-06,
|
| 1030 |
+
"loss": 0.9344,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.11,
|
| 1035 |
+
"grad_norm": 1.0712833404541016,
|
| 1036 |
+
"learning_rate": 6.298815822625347e-06,
|
| 1037 |
+
"loss": 0.9444,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.12,
|
| 1042 |
+
"grad_norm": 1.0778782367706299,
|
| 1043 |
+
"learning_rate": 6.273620559334846e-06,
|
| 1044 |
+
"loss": 0.935,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.13,
|
| 1049 |
+
"grad_norm": 1.0286056995391846,
|
| 1050 |
+
"learning_rate": 6.2484252960443435e-06,
|
| 1051 |
+
"loss": 0.9606,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.13,
|
| 1056 |
+
"grad_norm": 1.1475175619125366,
|
| 1057 |
+
"learning_rate": 6.223230032753843e-06,
|
| 1058 |
+
"loss": 0.9354,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.14,
|
| 1063 |
+
"grad_norm": 1.1092008352279663,
|
| 1064 |
+
"learning_rate": 6.1980347694633414e-06,
|
| 1065 |
+
"loss": 0.9556,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.15,
|
| 1070 |
+
"grad_norm": 1.0508161783218384,
|
| 1071 |
+
"learning_rate": 6.17283950617284e-06,
|
| 1072 |
+
"loss": 0.9388,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.16,
|
| 1077 |
+
"grad_norm": 1.0714831352233887,
|
| 1078 |
+
"learning_rate": 6.147644242882339e-06,
|
| 1079 |
+
"loss": 0.9334,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.16,
|
| 1084 |
+
"grad_norm": 1.0550581216812134,
|
| 1085 |
+
"learning_rate": 6.122448979591837e-06,
|
| 1086 |
+
"loss": 0.9398,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.17,
|
| 1091 |
+
"grad_norm": 1.1077096462249756,
|
| 1092 |
+
"learning_rate": 6.097253716301336e-06,
|
| 1093 |
+
"loss": 0.9486,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.18,
|
| 1098 |
+
"grad_norm": 1.0329755544662476,
|
| 1099 |
+
"learning_rate": 6.072058453010834e-06,
|
| 1100 |
+
"loss": 0.9635,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.19,
|
| 1105 |
+
"grad_norm": 1.085105061531067,
|
| 1106 |
+
"learning_rate": 6.046863189720334e-06,
|
| 1107 |
+
"loss": 0.9394,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.19,
|
| 1112 |
+
"grad_norm": 1.0389838218688965,
|
| 1113 |
+
"learning_rate": 6.021667926429831e-06,
|
| 1114 |
+
"loss": 0.9474,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.2,
|
| 1119 |
+
"grad_norm": 1.1028958559036255,
|
| 1120 |
+
"learning_rate": 5.99647266313933e-06,
|
| 1121 |
+
"loss": 0.9364,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.21,
|
| 1126 |
+
"grad_norm": 1.0558817386627197,
|
| 1127 |
+
"learning_rate": 5.971277399848829e-06,
|
| 1128 |
+
"loss": 0.9276,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.22,
|
| 1133 |
+
"grad_norm": 1.0861153602600098,
|
| 1134 |
+
"learning_rate": 5.946082136558328e-06,
|
| 1135 |
+
"loss": 0.9375,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.22,
|
| 1140 |
+
"grad_norm": 1.1104577779769897,
|
| 1141 |
+
"learning_rate": 5.920886873267826e-06,
|
| 1142 |
+
"loss": 0.948,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.23,
|
| 1147 |
+
"grad_norm": 1.0775477886199951,
|
| 1148 |
+
"learning_rate": 5.895691609977324e-06,
|
| 1149 |
+
"loss": 0.9334,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.24,
|
| 1154 |
+
"grad_norm": 1.0878546237945557,
|
| 1155 |
+
"learning_rate": 5.8704963466868235e-06,
|
| 1156 |
+
"loss": 0.952,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.25,
|
| 1161 |
+
"grad_norm": 1.0840810537338257,
|
| 1162 |
+
"learning_rate": 5.845301083396322e-06,
|
| 1163 |
+
"loss": 0.9312,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.25,
|
| 1168 |
+
"grad_norm": 1.2151501178741455,
|
| 1169 |
+
"learning_rate": 5.820105820105821e-06,
|
| 1170 |
+
"loss": 0.9549,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.26,
|
| 1175 |
+
"grad_norm": 1.0833278894424438,
|
| 1176 |
+
"learning_rate": 5.79491055681532e-06,
|
| 1177 |
+
"loss": 0.9557,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.27,
|
| 1182 |
+
"grad_norm": 1.0161901712417603,
|
| 1183 |
+
"learning_rate": 5.769715293524818e-06,
|
| 1184 |
+
"loss": 0.9312,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.28,
|
| 1189 |
+
"grad_norm": 1.075750708580017,
|
| 1190 |
+
"learning_rate": 5.744520030234316e-06,
|
| 1191 |
+
"loss": 0.9501,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.28,
|
| 1196 |
+
"grad_norm": 1.042380928993225,
|
| 1197 |
+
"learning_rate": 5.719324766943815e-06,
|
| 1198 |
+
"loss": 0.9381,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.29,
|
| 1203 |
+
"grad_norm": 1.009562373161316,
|
| 1204 |
+
"learning_rate": 5.694129503653314e-06,
|
| 1205 |
+
"loss": 0.9305,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.3,
|
| 1210 |
+
"grad_norm": 1.1201280355453491,
|
| 1211 |
+
"learning_rate": 5.668934240362812e-06,
|
| 1212 |
+
"loss": 0.9318,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.31,
|
| 1217 |
+
"grad_norm": 1.1156421899795532,
|
| 1218 |
+
"learning_rate": 5.6437389770723105e-06,
|
| 1219 |
+
"loss": 0.9445,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.32,
|
| 1224 |
+
"grad_norm": 1.0913002490997314,
|
| 1225 |
+
"learning_rate": 5.61854371378181e-06,
|
| 1226 |
+
"loss": 0.9537,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.32,
|
| 1231 |
+
"grad_norm": 1.041400671005249,
|
| 1232 |
+
"learning_rate": 5.593348450491308e-06,
|
| 1233 |
+
"loss": 0.9464,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.33,
|
| 1238 |
+
"grad_norm": 1.0327285528182983,
|
| 1239 |
+
"learning_rate": 5.568153187200807e-06,
|
| 1240 |
+
"loss": 0.9361,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.34,
|
| 1245 |
+
"grad_norm": 1.1421902179718018,
|
| 1246 |
+
"learning_rate": 5.542957923910305e-06,
|
| 1247 |
+
"loss": 0.9764,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.35,
|
| 1252 |
+
"grad_norm": 1.202650785446167,
|
| 1253 |
+
"learning_rate": 5.517762660619804e-06,
|
| 1254 |
+
"loss": 0.9553,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.35,
|
| 1259 |
+
"grad_norm": 1.0642273426055908,
|
| 1260 |
+
"learning_rate": 5.492567397329303e-06,
|
| 1261 |
+
"loss": 0.9485,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.36,
|
| 1266 |
+
"grad_norm": 1.0749919414520264,
|
| 1267 |
+
"learning_rate": 5.467372134038801e-06,
|
| 1268 |
+
"loss": 0.9418,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.37,
|
| 1273 |
+
"grad_norm": 1.0974488258361816,
|
| 1274 |
+
"learning_rate": 5.442176870748301e-06,
|
| 1275 |
+
"loss": 0.9539,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.38,
|
| 1280 |
+
"grad_norm": 1.1204264163970947,
|
| 1281 |
+
"learning_rate": 5.416981607457798e-06,
|
| 1282 |
+
"loss": 0.9357,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.38,
|
| 1287 |
+
"grad_norm": 1.268764853477478,
|
| 1288 |
+
"learning_rate": 5.391786344167297e-06,
|
| 1289 |
+
"loss": 0.9512,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.39,
|
| 1294 |
+
"grad_norm": 1.159050703048706,
|
| 1295 |
+
"learning_rate": 5.366591080876795e-06,
|
| 1296 |
+
"loss": 0.9402,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.4,
|
| 1301 |
+
"grad_norm": 1.2613215446472168,
|
| 1302 |
+
"learning_rate": 5.341395817586295e-06,
|
| 1303 |
+
"loss": 0.9411,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.41,
|
| 1308 |
+
"grad_norm": 1.1373072862625122,
|
| 1309 |
+
"learning_rate": 5.3162005542957925e-06,
|
| 1310 |
+
"loss": 0.9752,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.41,
|
| 1315 |
+
"grad_norm": 1.144242763519287,
|
| 1316 |
+
"learning_rate": 5.291005291005291e-06,
|
| 1317 |
+
"loss": 0.9471,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.42,
|
| 1322 |
+
"grad_norm": 1.0989221334457397,
|
| 1323 |
+
"learning_rate": 5.2658100277147905e-06,
|
| 1324 |
+
"loss": 0.9348,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.43,
|
| 1329 |
+
"grad_norm": 1.0864170789718628,
|
| 1330 |
+
"learning_rate": 5.240614764424289e-06,
|
| 1331 |
+
"loss": 0.9435,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.44,
|
| 1336 |
+
"grad_norm": 1.1140406131744385,
|
| 1337 |
+
"learning_rate": 5.2154195011337876e-06,
|
| 1338 |
+
"loss": 0.9541,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.44,
|
| 1343 |
+
"grad_norm": 1.1856478452682495,
|
| 1344 |
+
"learning_rate": 5.190224237843285e-06,
|
| 1345 |
+
"loss": 0.9151,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.45,
|
| 1350 |
+
"grad_norm": 1.2324665784835815,
|
| 1351 |
+
"learning_rate": 5.165028974552785e-06,
|
| 1352 |
+
"loss": 0.9411,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.46,
|
| 1357 |
+
"grad_norm": 1.038913369178772,
|
| 1358 |
+
"learning_rate": 5.139833711262283e-06,
|
| 1359 |
+
"loss": 0.9487,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.47,
|
| 1364 |
+
"grad_norm": 1.040578842163086,
|
| 1365 |
+
"learning_rate": 5.114638447971782e-06,
|
| 1366 |
+
"loss": 0.943,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.47,
|
| 1371 |
+
"grad_norm": 1.289865493774414,
|
| 1372 |
+
"learning_rate": 5.089443184681281e-06,
|
| 1373 |
+
"loss": 0.9382,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.48,
|
| 1378 |
+
"grad_norm": 1.1952651739120483,
|
| 1379 |
+
"learning_rate": 5.064247921390779e-06,
|
| 1380 |
+
"loss": 0.9453,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.49,
|
| 1385 |
+
"grad_norm": 1.1922310590744019,
|
| 1386 |
+
"learning_rate": 5.0390526581002774e-06,
|
| 1387 |
+
"loss": 0.9242,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.5,
|
| 1392 |
+
"grad_norm": 1.1691875457763672,
|
| 1393 |
+
"learning_rate": 5.013857394809776e-06,
|
| 1394 |
+
"loss": 0.932,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.5,
|
| 1399 |
+
"grad_norm": 1.254301905632019,
|
| 1400 |
+
"learning_rate": 4.9886621315192745e-06,
|
| 1401 |
+
"loss": 0.9341,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.51,
|
| 1406 |
+
"grad_norm": 1.0548466444015503,
|
| 1407 |
+
"learning_rate": 4.963466868228773e-06,
|
| 1408 |
+
"loss": 0.9496,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.52,
|
| 1413 |
+
"grad_norm": 1.2470088005065918,
|
| 1414 |
+
"learning_rate": 4.938271604938272e-06,
|
| 1415 |
+
"loss": 0.9488,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.53,
|
| 1420 |
+
"grad_norm": 1.2311805486679077,
|
| 1421 |
+
"learning_rate": 4.91307634164777e-06,
|
| 1422 |
+
"loss": 0.942,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.53,
|
| 1427 |
+
"grad_norm": 1.1870156526565552,
|
| 1428 |
+
"learning_rate": 4.88788107835727e-06,
|
| 1429 |
+
"loss": 0.94,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.54,
|
| 1434 |
+
"grad_norm": 1.060556173324585,
|
| 1435 |
+
"learning_rate": 4.862685815066767e-06,
|
| 1436 |
+
"loss": 0.9223,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.55,
|
| 1441 |
+
"grad_norm": 1.1396002769470215,
|
| 1442 |
+
"learning_rate": 4.837490551776267e-06,
|
| 1443 |
+
"loss": 0.9588,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.56,
|
| 1448 |
+
"grad_norm": 1.2042090892791748,
|
| 1449 |
+
"learning_rate": 4.812295288485765e-06,
|
| 1450 |
+
"loss": 0.9534,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.56,
|
| 1455 |
+
"grad_norm": 1.1195515394210815,
|
| 1456 |
+
"learning_rate": 4.787100025195264e-06,
|
| 1457 |
+
"loss": 0.9528,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.57,
|
| 1462 |
+
"grad_norm": 1.290823221206665,
|
| 1463 |
+
"learning_rate": 4.761904761904762e-06,
|
| 1464 |
+
"loss": 0.9514,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.58,
|
| 1469 |
+
"grad_norm": 1.0271083116531372,
|
| 1470 |
+
"learning_rate": 4.736709498614261e-06,
|
| 1471 |
+
"loss": 0.9699,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.59,
|
| 1476 |
+
"grad_norm": 1.2110365629196167,
|
| 1477 |
+
"learning_rate": 4.7115142353237595e-06,
|
| 1478 |
+
"loss": 0.9358,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.59,
|
| 1483 |
+
"grad_norm": 1.1250057220458984,
|
| 1484 |
+
"learning_rate": 4.686318972033258e-06,
|
| 1485 |
+
"loss": 0.9491,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.6,
|
| 1490 |
+
"grad_norm": 1.1912841796875,
|
| 1491 |
+
"learning_rate": 4.661123708742757e-06,
|
| 1492 |
+
"loss": 0.9332,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.61,
|
| 1497 |
+
"grad_norm": 1.0299352407455444,
|
| 1498 |
+
"learning_rate": 4.635928445452255e-06,
|
| 1499 |
+
"loss": 0.9577,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.62,
|
| 1504 |
+
"grad_norm": 1.0603456497192383,
|
| 1505 |
+
"learning_rate": 4.610733182161754e-06,
|
| 1506 |
+
"loss": 0.9332,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.63,
|
| 1511 |
+
"grad_norm": 1.1462222337722778,
|
| 1512 |
+
"learning_rate": 4.585537918871252e-06,
|
| 1513 |
+
"loss": 0.9343,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.63,
|
| 1518 |
+
"grad_norm": 1.0181183815002441,
|
| 1519 |
+
"learning_rate": 4.560342655580751e-06,
|
| 1520 |
+
"loss": 0.9365,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.64,
|
| 1525 |
+
"grad_norm": 1.2271602153778076,
|
| 1526 |
+
"learning_rate": 4.53514739229025e-06,
|
| 1527 |
+
"loss": 0.9171,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.65,
|
| 1532 |
+
"grad_norm": 1.1205991506576538,
|
| 1533 |
+
"learning_rate": 4.509952128999748e-06,
|
| 1534 |
+
"loss": 0.9299,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.66,
|
| 1539 |
+
"grad_norm": 1.1556931734085083,
|
| 1540 |
+
"learning_rate": 4.484756865709247e-06,
|
| 1541 |
+
"loss": 0.9652,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.66,
|
| 1546 |
+
"grad_norm": 1.0930700302124023,
|
| 1547 |
+
"learning_rate": 4.459561602418746e-06,
|
| 1548 |
+
"loss": 0.9259,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.67,
|
| 1553 |
+
"grad_norm": 1.207714319229126,
|
| 1554 |
+
"learning_rate": 4.434366339128244e-06,
|
| 1555 |
+
"loss": 0.9529,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.68,
|
| 1560 |
+
"grad_norm": 1.1223605871200562,
|
| 1561 |
+
"learning_rate": 4.409171075837743e-06,
|
| 1562 |
+
"loss": 0.9397,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.69,
|
| 1567 |
+
"grad_norm": 1.2369412183761597,
|
| 1568 |
+
"learning_rate": 4.3839758125472415e-06,
|
| 1569 |
+
"loss": 0.9246,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.69,
|
| 1574 |
+
"grad_norm": 1.232971429824829,
|
| 1575 |
+
"learning_rate": 4.35878054925674e-06,
|
| 1576 |
+
"loss": 0.9349,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.7,
|
| 1581 |
+
"grad_norm": 1.1932899951934814,
|
| 1582 |
+
"learning_rate": 4.333585285966239e-06,
|
| 1583 |
+
"loss": 0.9495,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.71,
|
| 1588 |
+
"grad_norm": 1.2230783700942993,
|
| 1589 |
+
"learning_rate": 4.308390022675737e-06,
|
| 1590 |
+
"loss": 0.9205,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.72,
|
| 1595 |
+
"grad_norm": 1.2365373373031616,
|
| 1596 |
+
"learning_rate": 4.283194759385236e-06,
|
| 1597 |
+
"loss": 0.9214,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.72,
|
| 1602 |
+
"grad_norm": 1.132912278175354,
|
| 1603 |
+
"learning_rate": 4.257999496094734e-06,
|
| 1604 |
+
"loss": 0.9154,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.73,
|
| 1609 |
+
"grad_norm": 1.2143046855926514,
|
| 1610 |
+
"learning_rate": 4.232804232804233e-06,
|
| 1611 |
+
"loss": 0.9485,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.74,
|
| 1616 |
+
"grad_norm": 1.2785279750823975,
|
| 1617 |
+
"learning_rate": 4.207608969513731e-06,
|
| 1618 |
+
"loss": 0.9462,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.75,
|
| 1623 |
+
"grad_norm": 1.3493692874908447,
|
| 1624 |
+
"learning_rate": 4.182413706223231e-06,
|
| 1625 |
+
"loss": 0.9382,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.75,
|
| 1630 |
+
"grad_norm": 1.1612365245819092,
|
| 1631 |
+
"learning_rate": 4.1572184429327285e-06,
|
| 1632 |
+
"loss": 0.9407,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.76,
|
| 1637 |
+
"grad_norm": 1.2210137844085693,
|
| 1638 |
+
"learning_rate": 4.132023179642228e-06,
|
| 1639 |
+
"loss": 0.9196,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.77,
|
| 1644 |
+
"grad_norm": 1.1422805786132812,
|
| 1645 |
+
"learning_rate": 4.1068279163517265e-06,
|
| 1646 |
+
"loss": 0.9426,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.78,
|
| 1651 |
+
"grad_norm": 1.1776541471481323,
|
| 1652 |
+
"learning_rate": 4.081632653061225e-06,
|
| 1653 |
+
"loss": 0.9436,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.78,
|
| 1658 |
+
"grad_norm": 1.2455426454544067,
|
| 1659 |
+
"learning_rate": 4.0564373897707236e-06,
|
| 1660 |
+
"loss": 0.9299,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.79,
|
| 1665 |
+
"grad_norm": 1.146103858947754,
|
| 1666 |
+
"learning_rate": 4.031242126480222e-06,
|
| 1667 |
+
"loss": 0.9353,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.8,
|
| 1672 |
+
"grad_norm": 1.1490944623947144,
|
| 1673 |
+
"learning_rate": 4.006046863189721e-06,
|
| 1674 |
+
"loss": 0.9373,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.81,
|
| 1679 |
+
"grad_norm": 1.1841084957122803,
|
| 1680 |
+
"learning_rate": 3.980851599899219e-06,
|
| 1681 |
+
"loss": 0.9214,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.81,
|
| 1686 |
+
"grad_norm": 1.360938310623169,
|
| 1687 |
+
"learning_rate": 3.955656336608718e-06,
|
| 1688 |
+
"loss": 0.9233,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.82,
|
| 1693 |
+
"grad_norm": 1.1501877307891846,
|
| 1694 |
+
"learning_rate": 3.930461073318216e-06,
|
| 1695 |
+
"loss": 0.9149,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.83,
|
| 1700 |
+
"grad_norm": 1.3008352518081665,
|
| 1701 |
+
"learning_rate": 3.905265810027715e-06,
|
| 1702 |
+
"loss": 0.9592,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.84,
|
| 1707 |
+
"grad_norm": 1.2323644161224365,
|
| 1708 |
+
"learning_rate": 3.8800705467372134e-06,
|
| 1709 |
+
"loss": 0.9295,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.84,
|
| 1714 |
+
"grad_norm": 1.1721792221069336,
|
| 1715 |
+
"learning_rate": 3.854875283446712e-06,
|
| 1716 |
+
"loss": 0.9431,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.85,
|
| 1721 |
+
"grad_norm": 1.2879486083984375,
|
| 1722 |
+
"learning_rate": 3.829680020156211e-06,
|
| 1723 |
+
"loss": 0.9463,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.86,
|
| 1728 |
+
"grad_norm": 1.1511075496673584,
|
| 1729 |
+
"learning_rate": 3.8044847568657095e-06,
|
| 1730 |
+
"loss": 0.9664,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.87,
|
| 1735 |
+
"grad_norm": 1.3236780166625977,
|
| 1736 |
+
"learning_rate": 3.7792894935752085e-06,
|
| 1737 |
+
"loss": 0.9368,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.87,
|
| 1742 |
+
"grad_norm": 1.1940069198608398,
|
| 1743 |
+
"learning_rate": 3.7540942302847066e-06,
|
| 1744 |
+
"loss": 0.9548,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.88,
|
| 1749 |
+
"grad_norm": 1.1677494049072266,
|
| 1750 |
+
"learning_rate": 3.7288989669942056e-06,
|
| 1751 |
+
"loss": 0.9592,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.89,
|
| 1756 |
+
"grad_norm": 1.1518640518188477,
|
| 1757 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1758 |
+
"loss": 0.9497,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.9,
|
| 1763 |
+
"grad_norm": 1.159209966659546,
|
| 1764 |
+
"learning_rate": 3.6785084404132027e-06,
|
| 1765 |
+
"loss": 0.9368,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.9,
|
| 1770 |
+
"grad_norm": 1.2133903503417969,
|
| 1771 |
+
"learning_rate": 3.6533131771227017e-06,
|
| 1772 |
+
"loss": 0.9257,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.91,
|
| 1777 |
+
"grad_norm": 1.329829454421997,
|
| 1778 |
+
"learning_rate": 3.6281179138322e-06,
|
| 1779 |
+
"loss": 0.9544,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.92,
|
| 1784 |
+
"grad_norm": 1.264733910560608,
|
| 1785 |
+
"learning_rate": 3.602922650541699e-06,
|
| 1786 |
+
"loss": 0.9525,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.93,
|
| 1791 |
+
"grad_norm": 1.2355499267578125,
|
| 1792 |
+
"learning_rate": 3.577727387251197e-06,
|
| 1793 |
+
"loss": 0.95,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.93,
|
| 1798 |
+
"grad_norm": 1.1711816787719727,
|
| 1799 |
+
"learning_rate": 3.552532123960696e-06,
|
| 1800 |
+
"loss": 0.9443,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.94,
|
| 1805 |
+
"grad_norm": 1.1221129894256592,
|
| 1806 |
+
"learning_rate": 3.527336860670194e-06,
|
| 1807 |
+
"loss": 0.9422,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.95,
|
| 1812 |
+
"grad_norm": 1.154335379600525,
|
| 1813 |
+
"learning_rate": 3.502141597379693e-06,
|
| 1814 |
+
"loss": 0.9462,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.96,
|
| 1819 |
+
"grad_norm": 1.2431056499481201,
|
| 1820 |
+
"learning_rate": 3.476946334089191e-06,
|
| 1821 |
+
"loss": 0.9305,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.97,
|
| 1826 |
+
"grad_norm": 1.1966361999511719,
|
| 1827 |
+
"learning_rate": 3.45175107079869e-06,
|
| 1828 |
+
"loss": 0.9537,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.97,
|
| 1833 |
+
"grad_norm": 1.2401050329208374,
|
| 1834 |
+
"learning_rate": 3.426555807508189e-06,
|
| 1835 |
+
"loss": 0.9262,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.98,
|
| 1840 |
+
"grad_norm": 1.1483770608901978,
|
| 1841 |
+
"learning_rate": 3.4013605442176872e-06,
|
| 1842 |
+
"loss": 0.9515,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.99,
|
| 1847 |
+
"grad_norm": 1.1387736797332764,
|
| 1848 |
+
"learning_rate": 3.376165280927186e-06,
|
| 1849 |
+
"loss": 0.9293,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.0,
|
| 1854 |
+
"grad_norm": 1.2311975955963135,
|
| 1855 |
+
"learning_rate": 3.3509700176366843e-06,
|
| 1856 |
+
"loss": 0.9201,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.0,
|
| 1861 |
+
"grad_norm": 1.1818970441818237,
|
| 1862 |
+
"learning_rate": 3.3257747543461833e-06,
|
| 1863 |
+
"loss": 0.9439,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.01,
|
| 1868 |
+
"grad_norm": 1.3574014902114868,
|
| 1869 |
+
"learning_rate": 3.3005794910556814e-06,
|
| 1870 |
+
"loss": 0.9235,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.02,
|
| 1875 |
+
"grad_norm": 1.1797312498092651,
|
| 1876 |
+
"learning_rate": 3.2753842277651804e-06,
|
| 1877 |
+
"loss": 0.9235,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.03,
|
| 1882 |
+
"grad_norm": 1.225716233253479,
|
| 1883 |
+
"learning_rate": 3.2501889644746794e-06,
|
| 1884 |
+
"loss": 0.9363,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.03,
|
| 1889 |
+
"grad_norm": 1.1875022649765015,
|
| 1890 |
+
"learning_rate": 3.2249937011841775e-06,
|
| 1891 |
+
"loss": 0.9155,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.04,
|
| 1896 |
+
"grad_norm": 1.2818158864974976,
|
| 1897 |
+
"learning_rate": 3.1997984378936765e-06,
|
| 1898 |
+
"loss": 0.9189,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.05,
|
| 1903 |
+
"grad_norm": 1.0735368728637695,
|
| 1904 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 1905 |
+
"loss": 0.9183,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.06,
|
| 1910 |
+
"grad_norm": 1.2235422134399414,
|
| 1911 |
+
"learning_rate": 3.1494079113126736e-06,
|
| 1912 |
+
"loss": 0.9383,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.06,
|
| 1917 |
+
"grad_norm": 1.2761168479919434,
|
| 1918 |
+
"learning_rate": 3.1242126480221717e-06,
|
| 1919 |
+
"loss": 0.9161,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.07,
|
| 1924 |
+
"grad_norm": 1.1925853490829468,
|
| 1925 |
+
"learning_rate": 3.0990173847316707e-06,
|
| 1926 |
+
"loss": 0.9133,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.08,
|
| 1931 |
+
"grad_norm": 1.1860272884368896,
|
| 1932 |
+
"learning_rate": 3.0738221214411697e-06,
|
| 1933 |
+
"loss": 0.9317,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.09,
|
| 1938 |
+
"grad_norm": 1.285198450088501,
|
| 1939 |
+
"learning_rate": 3.048626858150668e-06,
|
| 1940 |
+
"loss": 0.9332,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.09,
|
| 1945 |
+
"grad_norm": 1.220641851425171,
|
| 1946 |
+
"learning_rate": 3.023431594860167e-06,
|
| 1947 |
+
"loss": 0.9464,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 2.1,
|
| 1952 |
+
"grad_norm": 1.31607186794281,
|
| 1953 |
+
"learning_rate": 2.998236331569665e-06,
|
| 1954 |
+
"loss": 0.9233,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 2.11,
|
| 1959 |
+
"grad_norm": 1.2238725423812866,
|
| 1960 |
+
"learning_rate": 2.973041068279164e-06,
|
| 1961 |
+
"loss": 0.9359,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 2.12,
|
| 1966 |
+
"grad_norm": 1.1632503271102905,
|
| 1967 |
+
"learning_rate": 2.947845804988662e-06,
|
| 1968 |
+
"loss": 0.9117,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 2.12,
|
| 1973 |
+
"grad_norm": 1.3732521533966064,
|
| 1974 |
+
"learning_rate": 2.922650541698161e-06,
|
| 1975 |
+
"loss": 0.9068,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.13,
|
| 1980 |
+
"grad_norm": 1.2329943180084229,
|
| 1981 |
+
"learning_rate": 2.89745527840766e-06,
|
| 1982 |
+
"loss": 0.9208,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 2.14,
|
| 1987 |
+
"grad_norm": 1.331434726715088,
|
| 1988 |
+
"learning_rate": 2.872260015117158e-06,
|
| 1989 |
+
"loss": 0.9353,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.15,
|
| 1994 |
+
"grad_norm": 1.3423517942428589,
|
| 1995 |
+
"learning_rate": 2.847064751826657e-06,
|
| 1996 |
+
"loss": 0.9216,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 2.15,
|
| 2001 |
+
"grad_norm": 1.2505260705947876,
|
| 2002 |
+
"learning_rate": 2.8218694885361552e-06,
|
| 2003 |
+
"loss": 0.9267,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 2.16,
|
| 2008 |
+
"grad_norm": 1.1538835763931274,
|
| 2009 |
+
"learning_rate": 2.796674225245654e-06,
|
| 2010 |
+
"loss": 0.9195,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 2.17,
|
| 2015 |
+
"grad_norm": 1.3361774682998657,
|
| 2016 |
+
"learning_rate": 2.7714789619551523e-06,
|
| 2017 |
+
"loss": 0.9252,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 2.18,
|
| 2022 |
+
"grad_norm": 1.2870272397994995,
|
| 2023 |
+
"learning_rate": 2.7462836986646513e-06,
|
| 2024 |
+
"loss": 0.9011,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 2.18,
|
| 2029 |
+
"grad_norm": 1.238709807395935,
|
| 2030 |
+
"learning_rate": 2.7210884353741503e-06,
|
| 2031 |
+
"loss": 0.9203,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 2.19,
|
| 2036 |
+
"grad_norm": 1.1434613466262817,
|
| 2037 |
+
"learning_rate": 2.6958931720836484e-06,
|
| 2038 |
+
"loss": 0.9263,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 2.2,
|
| 2043 |
+
"grad_norm": 1.2599645853042603,
|
| 2044 |
+
"learning_rate": 2.6706979087931474e-06,
|
| 2045 |
+
"loss": 0.9224,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 2.21,
|
| 2050 |
+
"grad_norm": 1.3294990062713623,
|
| 2051 |
+
"learning_rate": 2.6455026455026455e-06,
|
| 2052 |
+
"loss": 0.9116,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 2.21,
|
| 2057 |
+
"grad_norm": 1.2516047954559326,
|
| 2058 |
+
"learning_rate": 2.6203073822121445e-06,
|
| 2059 |
+
"loss": 0.9287,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.22,
|
| 2064 |
+
"grad_norm": 1.2115424871444702,
|
| 2065 |
+
"learning_rate": 2.5951121189216426e-06,
|
| 2066 |
+
"loss": 0.9384,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 2.23,
|
| 2071 |
+
"grad_norm": 1.1633473634719849,
|
| 2072 |
+
"learning_rate": 2.5699168556311416e-06,
|
| 2073 |
+
"loss": 0.9211,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 2.24,
|
| 2078 |
+
"grad_norm": 1.181342363357544,
|
| 2079 |
+
"learning_rate": 2.5447215923406406e-06,
|
| 2080 |
+
"loss": 0.9122,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 2.24,
|
| 2085 |
+
"grad_norm": 1.2719746828079224,
|
| 2086 |
+
"learning_rate": 2.5195263290501387e-06,
|
| 2087 |
+
"loss": 0.9302,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 2.25,
|
| 2092 |
+
"grad_norm": 1.292691707611084,
|
| 2093 |
+
"learning_rate": 2.4943310657596373e-06,
|
| 2094 |
+
"loss": 0.9226,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 2.26,
|
| 2099 |
+
"grad_norm": 1.1643900871276855,
|
| 2100 |
+
"learning_rate": 2.469135802469136e-06,
|
| 2101 |
+
"loss": 0.903,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 2.27,
|
| 2106 |
+
"grad_norm": 1.2362549304962158,
|
| 2107 |
+
"learning_rate": 2.443940539178635e-06,
|
| 2108 |
+
"loss": 0.9238,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 2.28,
|
| 2113 |
+
"grad_norm": 1.1967755556106567,
|
| 2114 |
+
"learning_rate": 2.4187452758881334e-06,
|
| 2115 |
+
"loss": 0.9372,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 2.28,
|
| 2120 |
+
"grad_norm": 1.1664007902145386,
|
| 2121 |
+
"learning_rate": 2.393550012597632e-06,
|
| 2122 |
+
"loss": 0.9249,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.29,
|
| 2127 |
+
"grad_norm": 1.39642333984375,
|
| 2128 |
+
"learning_rate": 2.3683547493071305e-06,
|
| 2129 |
+
"loss": 0.9381,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.3,
|
| 2134 |
+
"grad_norm": 1.2738609313964844,
|
| 2135 |
+
"learning_rate": 2.343159486016629e-06,
|
| 2136 |
+
"loss": 0.9345,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 2.31,
|
| 2141 |
+
"grad_norm": 1.2925204038619995,
|
| 2142 |
+
"learning_rate": 2.3179642227261276e-06,
|
| 2143 |
+
"loss": 0.9156,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.31,
|
| 2148 |
+
"grad_norm": 1.470628261566162,
|
| 2149 |
+
"learning_rate": 2.292768959435626e-06,
|
| 2150 |
+
"loss": 0.9128,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 2.32,
|
| 2155 |
+
"grad_norm": 1.280967354774475,
|
| 2156 |
+
"learning_rate": 2.267573696145125e-06,
|
| 2157 |
+
"loss": 0.9225,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 2.33,
|
| 2162 |
+
"grad_norm": 1.3174177408218384,
|
| 2163 |
+
"learning_rate": 2.2423784328546237e-06,
|
| 2164 |
+
"loss": 0.9138,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 2.34,
|
| 2169 |
+
"grad_norm": 1.3123756647109985,
|
| 2170 |
+
"learning_rate": 2.217183169564122e-06,
|
| 2171 |
+
"loss": 0.9284,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 2.34,
|
| 2176 |
+
"grad_norm": 1.232643723487854,
|
| 2177 |
+
"learning_rate": 2.1919879062736208e-06,
|
| 2178 |
+
"loss": 0.9201,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 2.35,
|
| 2183 |
+
"grad_norm": 1.207700490951538,
|
| 2184 |
+
"learning_rate": 2.1667926429831193e-06,
|
| 2185 |
+
"loss": 0.9061,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 2.36,
|
| 2190 |
+
"grad_norm": 1.2038023471832275,
|
| 2191 |
+
"learning_rate": 2.141597379692618e-06,
|
| 2192 |
+
"loss": 0.9437,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.37,
|
| 2197 |
+
"grad_norm": 1.4127525091171265,
|
| 2198 |
+
"learning_rate": 2.1164021164021164e-06,
|
| 2199 |
+
"loss": 0.9142,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.37,
|
| 2204 |
+
"grad_norm": 1.3315386772155762,
|
| 2205 |
+
"learning_rate": 2.0912068531116154e-06,
|
| 2206 |
+
"loss": 0.9217,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.38,
|
| 2211 |
+
"grad_norm": 1.3743528127670288,
|
| 2212 |
+
"learning_rate": 2.066011589821114e-06,
|
| 2213 |
+
"loss": 0.8931,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.39,
|
| 2218 |
+
"grad_norm": 1.2260786294937134,
|
| 2219 |
+
"learning_rate": 2.0408163265306125e-06,
|
| 2220 |
+
"loss": 0.9224,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.4,
|
| 2225 |
+
"grad_norm": 1.3002612590789795,
|
| 2226 |
+
"learning_rate": 2.015621063240111e-06,
|
| 2227 |
+
"loss": 0.9371,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.4,
|
| 2232 |
+
"grad_norm": 1.1567788124084473,
|
| 2233 |
+
"learning_rate": 1.9904257999496096e-06,
|
| 2234 |
+
"loss": 0.9244,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 2.41,
|
| 2239 |
+
"grad_norm": 1.2505953311920166,
|
| 2240 |
+
"learning_rate": 1.965230536659108e-06,
|
| 2241 |
+
"loss": 0.8985,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.42,
|
| 2246 |
+
"grad_norm": 1.3488541841506958,
|
| 2247 |
+
"learning_rate": 1.9400352733686067e-06,
|
| 2248 |
+
"loss": 0.9111,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 2.43,
|
| 2253 |
+
"grad_norm": 1.371126651763916,
|
| 2254 |
+
"learning_rate": 1.9148400100781057e-06,
|
| 2255 |
+
"loss": 0.9094,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 2.43,
|
| 2260 |
+
"grad_norm": 1.3531619310379028,
|
| 2261 |
+
"learning_rate": 1.8896447467876043e-06,
|
| 2262 |
+
"loss": 0.9353,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.44,
|
| 2267 |
+
"grad_norm": 1.261234998703003,
|
| 2268 |
+
"learning_rate": 1.8644494834971028e-06,
|
| 2269 |
+
"loss": 0.9635,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.45,
|
| 2274 |
+
"grad_norm": 1.2285544872283936,
|
| 2275 |
+
"learning_rate": 1.8392542202066014e-06,
|
| 2276 |
+
"loss": 0.9104,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 2.46,
|
| 2281 |
+
"grad_norm": 1.2340446710586548,
|
| 2282 |
+
"learning_rate": 1.8140589569161e-06,
|
| 2283 |
+
"loss": 0.9275,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 2.46,
|
| 2288 |
+
"grad_norm": 1.1888856887817383,
|
| 2289 |
+
"learning_rate": 1.7888636936255985e-06,
|
| 2290 |
+
"loss": 0.8929,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 2.47,
|
| 2295 |
+
"grad_norm": 1.3445130586624146,
|
| 2296 |
+
"learning_rate": 1.763668430335097e-06,
|
| 2297 |
+
"loss": 0.9233,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 2.48,
|
| 2302 |
+
"grad_norm": 1.2736765146255493,
|
| 2303 |
+
"learning_rate": 1.7384731670445956e-06,
|
| 2304 |
+
"loss": 0.9143,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 2.49,
|
| 2309 |
+
"grad_norm": 1.1950249671936035,
|
| 2310 |
+
"learning_rate": 1.7132779037540945e-06,
|
| 2311 |
+
"loss": 0.8981,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.49,
|
| 2316 |
+
"grad_norm": 1.3372317552566528,
|
| 2317 |
+
"learning_rate": 1.688082640463593e-06,
|
| 2318 |
+
"loss": 0.9149,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 2.5,
|
| 2323 |
+
"grad_norm": 1.2550235986709595,
|
| 2324 |
+
"learning_rate": 1.6628873771730917e-06,
|
| 2325 |
+
"loss": 0.9448,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 2.51,
|
| 2330 |
+
"grad_norm": 1.3083131313323975,
|
| 2331 |
+
"learning_rate": 1.6376921138825902e-06,
|
| 2332 |
+
"loss": 0.926,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 2.52,
|
| 2337 |
+
"grad_norm": 1.2111276388168335,
|
| 2338 |
+
"learning_rate": 1.6124968505920888e-06,
|
| 2339 |
+
"loss": 0.9237,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.52,
|
| 2344 |
+
"grad_norm": 1.1683611869812012,
|
| 2345 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 2346 |
+
"loss": 0.9265,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 2.53,
|
| 2351 |
+
"grad_norm": 1.2934691905975342,
|
| 2352 |
+
"learning_rate": 1.5621063240110859e-06,
|
| 2353 |
+
"loss": 0.8935,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.54,
|
| 2358 |
+
"grad_norm": 1.2122243642807007,
|
| 2359 |
+
"learning_rate": 1.5369110607205848e-06,
|
| 2360 |
+
"loss": 0.9184,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.55,
|
| 2365 |
+
"grad_norm": 1.318337321281433,
|
| 2366 |
+
"learning_rate": 1.5117157974300834e-06,
|
| 2367 |
+
"loss": 0.919,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.55,
|
| 2372 |
+
"grad_norm": 1.2197314500808716,
|
| 2373 |
+
"learning_rate": 1.486520534139582e-06,
|
| 2374 |
+
"loss": 0.9118,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 2.56,
|
| 2379 |
+
"grad_norm": 1.1137281656265259,
|
| 2380 |
+
"learning_rate": 1.4613252708490805e-06,
|
| 2381 |
+
"loss": 0.9312,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 2.57,
|
| 2386 |
+
"grad_norm": 1.2075839042663574,
|
| 2387 |
+
"learning_rate": 1.436130007558579e-06,
|
| 2388 |
+
"loss": 0.9258,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 2.58,
|
| 2393 |
+
"grad_norm": 1.379468321800232,
|
| 2394 |
+
"learning_rate": 1.4109347442680776e-06,
|
| 2395 |
+
"loss": 0.9163,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.59,
|
| 2400 |
+
"grad_norm": 1.3524144887924194,
|
| 2401 |
+
"learning_rate": 1.3857394809775762e-06,
|
| 2402 |
+
"loss": 0.9211,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.59,
|
| 2407 |
+
"grad_norm": 1.342460036277771,
|
| 2408 |
+
"learning_rate": 1.3605442176870751e-06,
|
| 2409 |
+
"loss": 0.9107,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 2.6,
|
| 2414 |
+
"grad_norm": 1.3853424787521362,
|
| 2415 |
+
"learning_rate": 1.3353489543965737e-06,
|
| 2416 |
+
"loss": 0.9367,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 2.61,
|
| 2421 |
+
"grad_norm": 1.397850513458252,
|
| 2422 |
+
"learning_rate": 1.3101536911060723e-06,
|
| 2423 |
+
"loss": 0.9173,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 2.62,
|
| 2428 |
+
"grad_norm": 1.439322590827942,
|
| 2429 |
+
"learning_rate": 1.2849584278155708e-06,
|
| 2430 |
+
"loss": 0.9158,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.62,
|
| 2435 |
+
"grad_norm": 1.199365258216858,
|
| 2436 |
+
"learning_rate": 1.2597631645250694e-06,
|
| 2437 |
+
"loss": 0.9167,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 2.63,
|
| 2442 |
+
"grad_norm": 1.323708415031433,
|
| 2443 |
+
"learning_rate": 1.234567901234568e-06,
|
| 2444 |
+
"loss": 0.9087,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.64,
|
| 2449 |
+
"grad_norm": 1.323588252067566,
|
| 2450 |
+
"learning_rate": 1.2093726379440667e-06,
|
| 2451 |
+
"loss": 0.9217,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.65,
|
| 2456 |
+
"grad_norm": 1.3864338397979736,
|
| 2457 |
+
"learning_rate": 1.1841773746535652e-06,
|
| 2458 |
+
"loss": 0.9202,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
}
|
| 2461 |
+
],
|
| 2462 |
+
"logging_steps": 10,
|
| 2463 |
+
"max_steps": 3969,
|
| 2464 |
+
"num_input_tokens_seen": 0,
|
| 2465 |
+
"num_train_epochs": 3,
|
| 2466 |
+
"save_steps": 500,
|
| 2467 |
+
"total_flos": 3.1042768180419625e+18,
|
| 2468 |
+
"train_batch_size": 16,
|
| 2469 |
+
"trial_name": null,
|
| 2470 |
+
"trial_params": null
|
| 2471 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eba3424d23abb83c09f4f1790ac92b6b1d81ea3c602423d54af18418589432c
|
| 3 |
+
size 4984
|