Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +22 -0
- trainer_state.json +2217 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: gpt2-medium
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "GPT2LMHeadModel",
|
| 5 |
+
"parent_library": "transformers.models.gpt2.modeling_gpt2"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "gpt2-medium",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": true,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 128,
|
| 17 |
+
"lora_dropout": 0.0,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 64,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"c_attn"
|
| 27 |
+
],
|
| 28 |
+
"task_type": null,
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39118f7368d7b390b9e48c4e9a09b46e6fcdee5e50be90f61bfd90db2c637fa8
|
| 3 |
+
size 25172088
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b60f982069b7054a7c3e41818e87b3ee2a8d276881f8d520b1f0c0d70d36309
|
| 3 |
+
size 50372538
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5994634e90ce1b45d012a45568063be05fea876e791cd66b48a4efc924164b2
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:392855cc9cbe029377262097ef598767921e2a3bc6937822c989a7603ee182c3
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": false,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"model_max_length": 1024,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
| 22 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3125,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0032,
|
| 13 |
+
"grad_norm": 10.0,
|
| 14 |
+
"learning_rate": 2.132196162046908e-06,
|
| 15 |
+
"loss": 22.4733,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0064,
|
| 20 |
+
"grad_norm": 9.999999046325684,
|
| 21 |
+
"learning_rate": 4.264392324093816e-06,
|
| 22 |
+
"loss": 18.8042,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0096,
|
| 27 |
+
"grad_norm": 10.000001907348633,
|
| 28 |
+
"learning_rate": 6.396588486140726e-06,
|
| 29 |
+
"loss": 19.6935,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0128,
|
| 34 |
+
"grad_norm": 9.999999046325684,
|
| 35 |
+
"learning_rate": 8.528784648187633e-06,
|
| 36 |
+
"loss": 19.4804,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016,
|
| 41 |
+
"grad_norm": 10.000000953674316,
|
| 42 |
+
"learning_rate": 1.0660980810234541e-05,
|
| 43 |
+
"loss": 17.4569,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0192,
|
| 48 |
+
"grad_norm": 10.0,
|
| 49 |
+
"learning_rate": 1.2793176972281452e-05,
|
| 50 |
+
"loss": 18.3143,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0224,
|
| 55 |
+
"grad_norm": 10.0,
|
| 56 |
+
"learning_rate": 1.4925373134328357e-05,
|
| 57 |
+
"loss": 16.6743,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0256,
|
| 62 |
+
"grad_norm": 9.999999046325684,
|
| 63 |
+
"learning_rate": 1.7057569296375266e-05,
|
| 64 |
+
"loss": 14.7713,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0288,
|
| 69 |
+
"grad_norm": 9.999999046325684,
|
| 70 |
+
"learning_rate": 1.9189765458422178e-05,
|
| 71 |
+
"loss": 14.883,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.032,
|
| 76 |
+
"grad_norm": 9.999999046325684,
|
| 77 |
+
"learning_rate": 2.1321961620469083e-05,
|
| 78 |
+
"loss": 14.1393,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0352,
|
| 83 |
+
"grad_norm": 9.999999046325684,
|
| 84 |
+
"learning_rate": 2.345415778251599e-05,
|
| 85 |
+
"loss": 11.5208,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0384,
|
| 90 |
+
"grad_norm": 10.0,
|
| 91 |
+
"learning_rate": 2.5586353944562904e-05,
|
| 92 |
+
"loss": 12.865,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0416,
|
| 97 |
+
"grad_norm": 10.0,
|
| 98 |
+
"learning_rate": 2.771855010660981e-05,
|
| 99 |
+
"loss": 10.3148,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0448,
|
| 104 |
+
"grad_norm": 9.999998092651367,
|
| 105 |
+
"learning_rate": 2.9850746268656714e-05,
|
| 106 |
+
"loss": 9.7127,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.048,
|
| 111 |
+
"grad_norm": 9.999998092651367,
|
| 112 |
+
"learning_rate": 3.1982942430703626e-05,
|
| 113 |
+
"loss": 8.3006,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0512,
|
| 118 |
+
"grad_norm": 9.999999046325684,
|
| 119 |
+
"learning_rate": 3.411513859275053e-05,
|
| 120 |
+
"loss": 7.292,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0544,
|
| 125 |
+
"grad_norm": 9.999999046325684,
|
| 126 |
+
"learning_rate": 3.624733475479744e-05,
|
| 127 |
+
"loss": 6.0268,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0576,
|
| 132 |
+
"grad_norm": 9.999998092651367,
|
| 133 |
+
"learning_rate": 3.8379530916844355e-05,
|
| 134 |
+
"loss": 5.7297,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0608,
|
| 139 |
+
"grad_norm": 10.0,
|
| 140 |
+
"learning_rate": 4.051172707889126e-05,
|
| 141 |
+
"loss": 4.6862,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.064,
|
| 146 |
+
"grad_norm": 9.999999046325684,
|
| 147 |
+
"learning_rate": 4.2643923240938166e-05,
|
| 148 |
+
"loss": 4.0643,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.0672,
|
| 153 |
+
"grad_norm": 9.999998092651367,
|
| 154 |
+
"learning_rate": 4.477611940298508e-05,
|
| 155 |
+
"loss": 3.3502,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0704,
|
| 160 |
+
"grad_norm": 9.999998092651367,
|
| 161 |
+
"learning_rate": 4.690831556503198e-05,
|
| 162 |
+
"loss": 2.6549,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0736,
|
| 167 |
+
"grad_norm": 8.796483039855957,
|
| 168 |
+
"learning_rate": 4.904051172707889e-05,
|
| 169 |
+
"loss": 2.883,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0768,
|
| 174 |
+
"grad_norm": 8.624096870422363,
|
| 175 |
+
"learning_rate": 5.117270788912581e-05,
|
| 176 |
+
"loss": 2.3625,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"grad_norm": 4.12373161315918,
|
| 182 |
+
"learning_rate": 5.330490405117271e-05,
|
| 183 |
+
"loss": 2.0516,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.0832,
|
| 188 |
+
"grad_norm": 6.344674110412598,
|
| 189 |
+
"learning_rate": 5.543710021321962e-05,
|
| 190 |
+
"loss": 1.8814,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0864,
|
| 195 |
+
"grad_norm": 5.940646171569824,
|
| 196 |
+
"learning_rate": 5.756929637526652e-05,
|
| 197 |
+
"loss": 1.8997,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0896,
|
| 202 |
+
"grad_norm": 4.136787414550781,
|
| 203 |
+
"learning_rate": 5.970149253731343e-05,
|
| 204 |
+
"loss": 1.6641,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0928,
|
| 209 |
+
"grad_norm": 3.336697578430176,
|
| 210 |
+
"learning_rate": 6.183368869936035e-05,
|
| 211 |
+
"loss": 1.5741,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.096,
|
| 216 |
+
"grad_norm": 4.003772735595703,
|
| 217 |
+
"learning_rate": 6.396588486140725e-05,
|
| 218 |
+
"loss": 1.4759,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0992,
|
| 223 |
+
"grad_norm": 5.183838367462158,
|
| 224 |
+
"learning_rate": 6.609808102345416e-05,
|
| 225 |
+
"loss": 1.5434,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1024,
|
| 230 |
+
"grad_norm": 4.6075849533081055,
|
| 231 |
+
"learning_rate": 6.823027718550106e-05,
|
| 232 |
+
"loss": 1.5185,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1056,
|
| 237 |
+
"grad_norm": 4.707767486572266,
|
| 238 |
+
"learning_rate": 7.036247334754798e-05,
|
| 239 |
+
"loss": 1.3706,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1088,
|
| 244 |
+
"grad_norm": 3.7312469482421875,
|
| 245 |
+
"learning_rate": 7.249466950959489e-05,
|
| 246 |
+
"loss": 1.3455,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.112,
|
| 251 |
+
"grad_norm": 3.605818033218384,
|
| 252 |
+
"learning_rate": 7.46268656716418e-05,
|
| 253 |
+
"loss": 1.2145,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.1152,
|
| 258 |
+
"grad_norm": 4.285920143127441,
|
| 259 |
+
"learning_rate": 7.675906183368871e-05,
|
| 260 |
+
"loss": 1.303,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1184,
|
| 265 |
+
"grad_norm": 3.215698480606079,
|
| 266 |
+
"learning_rate": 7.889125799573562e-05,
|
| 267 |
+
"loss": 1.168,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1216,
|
| 272 |
+
"grad_norm": 4.043213844299316,
|
| 273 |
+
"learning_rate": 8.102345415778252e-05,
|
| 274 |
+
"loss": 1.0962,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1248,
|
| 279 |
+
"grad_norm": 4.1487555503845215,
|
| 280 |
+
"learning_rate": 8.315565031982943e-05,
|
| 281 |
+
"loss": 1.1853,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.128,
|
| 286 |
+
"grad_norm": 3.942502498626709,
|
| 287 |
+
"learning_rate": 8.528784648187633e-05,
|
| 288 |
+
"loss": 1.0418,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.1312,
|
| 293 |
+
"grad_norm": 4.188830852508545,
|
| 294 |
+
"learning_rate": 8.742004264392325e-05,
|
| 295 |
+
"loss": 1.0992,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.1344,
|
| 300 |
+
"grad_norm": 4.130038738250732,
|
| 301 |
+
"learning_rate": 8.955223880597016e-05,
|
| 302 |
+
"loss": 0.976,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1376,
|
| 307 |
+
"grad_norm": 3.643944501876831,
|
| 308 |
+
"learning_rate": 9.168443496801706e-05,
|
| 309 |
+
"loss": 1.0592,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.1408,
|
| 314 |
+
"grad_norm": 3.760075092315674,
|
| 315 |
+
"learning_rate": 9.381663113006397e-05,
|
| 316 |
+
"loss": 1.0115,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.144,
|
| 321 |
+
"grad_norm": 2.4692914485931396,
|
| 322 |
+
"learning_rate": 9.594882729211087e-05,
|
| 323 |
+
"loss": 1.0096,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.1472,
|
| 328 |
+
"grad_norm": 3.1593716144561768,
|
| 329 |
+
"learning_rate": 9.808102345415778e-05,
|
| 330 |
+
"loss": 0.9181,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.1504,
|
| 335 |
+
"grad_norm": 3.6118807792663574,
|
| 336 |
+
"learning_rate": 9.998877161464182e-05,
|
| 337 |
+
"loss": 0.921,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.1536,
|
| 342 |
+
"grad_norm": 3.3329732418060303,
|
| 343 |
+
"learning_rate": 9.987648776105997e-05,
|
| 344 |
+
"loss": 0.8714,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1568,
|
| 349 |
+
"grad_norm": 2.9491333961486816,
|
| 350 |
+
"learning_rate": 9.97642039074781e-05,
|
| 351 |
+
"loss": 0.8553,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16,
|
| 356 |
+
"grad_norm": 3.0345425605773926,
|
| 357 |
+
"learning_rate": 9.965192005389625e-05,
|
| 358 |
+
"loss": 0.9232,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.1632,
|
| 363 |
+
"grad_norm": 3.3396542072296143,
|
| 364 |
+
"learning_rate": 9.95396362003144e-05,
|
| 365 |
+
"loss": 0.8112,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1664,
|
| 370 |
+
"grad_norm": 3.1262471675872803,
|
| 371 |
+
"learning_rate": 9.942735234673256e-05,
|
| 372 |
+
"loss": 0.8252,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.1696,
|
| 377 |
+
"grad_norm": 2.431586742401123,
|
| 378 |
+
"learning_rate": 9.931506849315069e-05,
|
| 379 |
+
"loss": 0.7863,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.1728,
|
| 384 |
+
"grad_norm": 3.4569954872131348,
|
| 385 |
+
"learning_rate": 9.920278463956883e-05,
|
| 386 |
+
"loss": 0.7916,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.176,
|
| 391 |
+
"grad_norm": 3.2024927139282227,
|
| 392 |
+
"learning_rate": 9.909050078598698e-05,
|
| 393 |
+
"loss": 0.8355,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1792,
|
| 398 |
+
"grad_norm": 3.4040327072143555,
|
| 399 |
+
"learning_rate": 9.897821693240512e-05,
|
| 400 |
+
"loss": 0.8548,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.1824,
|
| 405 |
+
"grad_norm": 2.5302040576934814,
|
| 406 |
+
"learning_rate": 9.886593307882327e-05,
|
| 407 |
+
"loss": 0.7237,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.1856,
|
| 412 |
+
"grad_norm": 3.6245014667510986,
|
| 413 |
+
"learning_rate": 9.875364922524142e-05,
|
| 414 |
+
"loss": 0.7395,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.1888,
|
| 419 |
+
"grad_norm": 2.6966214179992676,
|
| 420 |
+
"learning_rate": 9.864136537165956e-05,
|
| 421 |
+
"loss": 0.7004,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.192,
|
| 426 |
+
"grad_norm": 3.207789421081543,
|
| 427 |
+
"learning_rate": 9.852908151807771e-05,
|
| 428 |
+
"loss": 0.7419,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.1952,
|
| 433 |
+
"grad_norm": 3.4613256454467773,
|
| 434 |
+
"learning_rate": 9.841679766449586e-05,
|
| 435 |
+
"loss": 0.7264,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1984,
|
| 440 |
+
"grad_norm": 3.311279058456421,
|
| 441 |
+
"learning_rate": 9.8304513810914e-05,
|
| 442 |
+
"loss": 0.6852,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2016,
|
| 447 |
+
"grad_norm": 2.7546231746673584,
|
| 448 |
+
"learning_rate": 9.819222995733213e-05,
|
| 449 |
+
"loss": 0.6922,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2048,
|
| 454 |
+
"grad_norm": 3.5927953720092773,
|
| 455 |
+
"learning_rate": 9.807994610375028e-05,
|
| 456 |
+
"loss": 0.7391,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.208,
|
| 461 |
+
"grad_norm": 2.975539207458496,
|
| 462 |
+
"learning_rate": 9.796766225016843e-05,
|
| 463 |
+
"loss": 0.699,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.2112,
|
| 468 |
+
"grad_norm": 3.653235673904419,
|
| 469 |
+
"learning_rate": 9.785537839658657e-05,
|
| 470 |
+
"loss": 0.6669,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.2144,
|
| 475 |
+
"grad_norm": 3.6133604049682617,
|
| 476 |
+
"learning_rate": 9.774309454300472e-05,
|
| 477 |
+
"loss": 0.7107,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.2176,
|
| 482 |
+
"grad_norm": 2.855388641357422,
|
| 483 |
+
"learning_rate": 9.763081068942287e-05,
|
| 484 |
+
"loss": 0.6938,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.2208,
|
| 489 |
+
"grad_norm": 2.790356159210205,
|
| 490 |
+
"learning_rate": 9.751852683584101e-05,
|
| 491 |
+
"loss": 0.6208,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.224,
|
| 496 |
+
"grad_norm": 3.2559432983398438,
|
| 497 |
+
"learning_rate": 9.740624298225916e-05,
|
| 498 |
+
"loss": 0.6327,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.2272,
|
| 503 |
+
"grad_norm": 2.8997764587402344,
|
| 504 |
+
"learning_rate": 9.729395912867731e-05,
|
| 505 |
+
"loss": 0.6176,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2304,
|
| 510 |
+
"grad_norm": 3.3574609756469727,
|
| 511 |
+
"learning_rate": 9.718167527509545e-05,
|
| 512 |
+
"loss": 0.601,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2336,
|
| 517 |
+
"grad_norm": 2.94797945022583,
|
| 518 |
+
"learning_rate": 9.706939142151358e-05,
|
| 519 |
+
"loss": 0.5904,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.2368,
|
| 524 |
+
"grad_norm": 2.8964426517486572,
|
| 525 |
+
"learning_rate": 9.695710756793174e-05,
|
| 526 |
+
"loss": 0.5889,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.24,
|
| 531 |
+
"grad_norm": 2.505166530609131,
|
| 532 |
+
"learning_rate": 9.684482371434989e-05,
|
| 533 |
+
"loss": 0.5491,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.2432,
|
| 538 |
+
"grad_norm": 2.8895745277404785,
|
| 539 |
+
"learning_rate": 9.673253986076802e-05,
|
| 540 |
+
"loss": 0.5751,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2464,
|
| 545 |
+
"grad_norm": 2.348055601119995,
|
| 546 |
+
"learning_rate": 9.662025600718617e-05,
|
| 547 |
+
"loss": 0.5702,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.2496,
|
| 552 |
+
"grad_norm": 3.0331923961639404,
|
| 553 |
+
"learning_rate": 9.650797215360432e-05,
|
| 554 |
+
"loss": 0.5299,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2528,
|
| 559 |
+
"grad_norm": 2.881728172302246,
|
| 560 |
+
"learning_rate": 9.639568830002246e-05,
|
| 561 |
+
"loss": 0.4772,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.256,
|
| 566 |
+
"grad_norm": 2.9465715885162354,
|
| 567 |
+
"learning_rate": 9.628340444644061e-05,
|
| 568 |
+
"loss": 0.5137,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.2592,
|
| 573 |
+
"grad_norm": 2.664348602294922,
|
| 574 |
+
"learning_rate": 9.617112059285875e-05,
|
| 575 |
+
"loss": 0.4398,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.2624,
|
| 580 |
+
"grad_norm": 2.931985378265381,
|
| 581 |
+
"learning_rate": 9.605883673927689e-05,
|
| 582 |
+
"loss": 0.4969,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.2656,
|
| 587 |
+
"grad_norm": 2.953338861465454,
|
| 588 |
+
"learning_rate": 9.594655288569504e-05,
|
| 589 |
+
"loss": 0.4829,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2688,
|
| 594 |
+
"grad_norm": 3.0215139389038086,
|
| 595 |
+
"learning_rate": 9.583426903211319e-05,
|
| 596 |
+
"loss": 0.463,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.272,
|
| 601 |
+
"grad_norm": 3.6885106563568115,
|
| 602 |
+
"learning_rate": 9.572198517853134e-05,
|
| 603 |
+
"loss": 0.4601,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.2752,
|
| 608 |
+
"grad_norm": 3.8273849487304688,
|
| 609 |
+
"learning_rate": 9.560970132494948e-05,
|
| 610 |
+
"loss": 0.5616,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2784,
|
| 615 |
+
"grad_norm": 3.266014337539673,
|
| 616 |
+
"learning_rate": 9.549741747136763e-05,
|
| 617 |
+
"loss": 0.4581,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2816,
|
| 622 |
+
"grad_norm": 2.304288387298584,
|
| 623 |
+
"learning_rate": 9.538513361778578e-05,
|
| 624 |
+
"loss": 0.4192,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2848,
|
| 629 |
+
"grad_norm": 2.7526509761810303,
|
| 630 |
+
"learning_rate": 9.527284976420391e-05,
|
| 631 |
+
"loss": 0.3809,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.288,
|
| 636 |
+
"grad_norm": 3.033849000930786,
|
| 637 |
+
"learning_rate": 9.516056591062205e-05,
|
| 638 |
+
"loss": 0.3865,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2912,
|
| 643 |
+
"grad_norm": 2.9246816635131836,
|
| 644 |
+
"learning_rate": 9.50482820570402e-05,
|
| 645 |
+
"loss": 0.3565,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.2944,
|
| 650 |
+
"grad_norm": 2.111208438873291,
|
| 651 |
+
"learning_rate": 9.493599820345834e-05,
|
| 652 |
+
"loss": 0.3507,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.2976,
|
| 657 |
+
"grad_norm": 3.193631172180176,
|
| 658 |
+
"learning_rate": 9.482371434987649e-05,
|
| 659 |
+
"loss": 0.3136,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3008,
|
| 664 |
+
"grad_norm": 2.647897481918335,
|
| 665 |
+
"learning_rate": 9.471143049629464e-05,
|
| 666 |
+
"loss": 0.3034,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.304,
|
| 671 |
+
"grad_norm": 4.482762813568115,
|
| 672 |
+
"learning_rate": 9.459914664271278e-05,
|
| 673 |
+
"loss": 0.3168,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.3072,
|
| 678 |
+
"grad_norm": 2.408997058868408,
|
| 679 |
+
"learning_rate": 9.448686278913093e-05,
|
| 680 |
+
"loss": 0.2838,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3104,
|
| 685 |
+
"grad_norm": 2.701946496963501,
|
| 686 |
+
"learning_rate": 9.437457893554908e-05,
|
| 687 |
+
"loss": 0.2945,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.3136,
|
| 692 |
+
"grad_norm": 2.5696310997009277,
|
| 693 |
+
"learning_rate": 9.426229508196722e-05,
|
| 694 |
+
"loss": 0.2483,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.3168,
|
| 699 |
+
"grad_norm": 1.9443378448486328,
|
| 700 |
+
"learning_rate": 9.415001122838537e-05,
|
| 701 |
+
"loss": 0.2379,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.32,
|
| 706 |
+
"grad_norm": 2.137860059738159,
|
| 707 |
+
"learning_rate": 9.40377273748035e-05,
|
| 708 |
+
"loss": 0.2396,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.3232,
|
| 713 |
+
"grad_norm": 2.6493215560913086,
|
| 714 |
+
"learning_rate": 9.392544352122165e-05,
|
| 715 |
+
"loss": 0.2294,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.3264,
|
| 720 |
+
"grad_norm": 3.381498336791992,
|
| 721 |
+
"learning_rate": 9.381315966763979e-05,
|
| 722 |
+
"loss": 0.2162,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.3296,
|
| 727 |
+
"grad_norm": 2.907684564590454,
|
| 728 |
+
"learning_rate": 9.370087581405794e-05,
|
| 729 |
+
"loss": 0.194,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.3328,
|
| 734 |
+
"grad_norm": 2.3227946758270264,
|
| 735 |
+
"learning_rate": 9.358859196047609e-05,
|
| 736 |
+
"loss": 0.2071,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.336,
|
| 741 |
+
"grad_norm": 2.3173024654388428,
|
| 742 |
+
"learning_rate": 9.347630810689423e-05,
|
| 743 |
+
"loss": 0.2018,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.3392,
|
| 748 |
+
"grad_norm": 2.9500386714935303,
|
| 749 |
+
"learning_rate": 9.336402425331238e-05,
|
| 750 |
+
"loss": 0.1987,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.3424,
|
| 755 |
+
"grad_norm": 5.206624984741211,
|
| 756 |
+
"learning_rate": 9.325174039973053e-05,
|
| 757 |
+
"loss": 0.2036,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.3456,
|
| 762 |
+
"grad_norm": 1.9075260162353516,
|
| 763 |
+
"learning_rate": 9.313945654614867e-05,
|
| 764 |
+
"loss": 0.1785,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.3488,
|
| 769 |
+
"grad_norm": 1.7478675842285156,
|
| 770 |
+
"learning_rate": 9.30271726925668e-05,
|
| 771 |
+
"loss": 0.1956,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.352,
|
| 776 |
+
"grad_norm": 2.1234798431396484,
|
| 777 |
+
"learning_rate": 9.291488883898496e-05,
|
| 778 |
+
"loss": 0.175,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.3552,
|
| 783 |
+
"grad_norm": 1.828234076499939,
|
| 784 |
+
"learning_rate": 9.280260498540311e-05,
|
| 785 |
+
"loss": 0.1591,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.3584,
|
| 790 |
+
"grad_norm": 1.8341890573501587,
|
| 791 |
+
"learning_rate": 9.269032113182124e-05,
|
| 792 |
+
"loss": 0.1649,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3616,
|
| 797 |
+
"grad_norm": 1.3575913906097412,
|
| 798 |
+
"learning_rate": 9.25780372782394e-05,
|
| 799 |
+
"loss": 0.1694,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.3648,
|
| 804 |
+
"grad_norm": 2.1410560607910156,
|
| 805 |
+
"learning_rate": 9.246575342465755e-05,
|
| 806 |
+
"loss": 0.1659,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.368,
|
| 811 |
+
"grad_norm": 1.7794946432113647,
|
| 812 |
+
"learning_rate": 9.235346957107568e-05,
|
| 813 |
+
"loss": 0.1479,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.3712,
|
| 818 |
+
"grad_norm": 2.1806530952453613,
|
| 819 |
+
"learning_rate": 9.224118571749383e-05,
|
| 820 |
+
"loss": 0.151,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3744,
|
| 825 |
+
"grad_norm": 1.5767009258270264,
|
| 826 |
+
"learning_rate": 9.212890186391197e-05,
|
| 827 |
+
"loss": 0.1541,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.3776,
|
| 832 |
+
"grad_norm": 1.453840970993042,
|
| 833 |
+
"learning_rate": 9.201661801033011e-05,
|
| 834 |
+
"loss": 0.1368,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.3808,
|
| 839 |
+
"grad_norm": 1.8884810209274292,
|
| 840 |
+
"learning_rate": 9.190433415674826e-05,
|
| 841 |
+
"loss": 0.1394,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.384,
|
| 846 |
+
"grad_norm": 1.6665995121002197,
|
| 847 |
+
"learning_rate": 9.179205030316641e-05,
|
| 848 |
+
"loss": 0.1356,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.3872,
|
| 853 |
+
"grad_norm": 1.6958074569702148,
|
| 854 |
+
"learning_rate": 9.167976644958456e-05,
|
| 855 |
+
"loss": 0.1468,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.3904,
|
| 860 |
+
"grad_norm": 1.609466552734375,
|
| 861 |
+
"learning_rate": 9.15674825960027e-05,
|
| 862 |
+
"loss": 0.1396,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3936,
|
| 867 |
+
"grad_norm": 2.045232057571411,
|
| 868 |
+
"learning_rate": 9.145519874242085e-05,
|
| 869 |
+
"loss": 0.1234,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.3968,
|
| 874 |
+
"grad_norm": 1.8025046586990356,
|
| 875 |
+
"learning_rate": 9.1342914888839e-05,
|
| 876 |
+
"loss": 0.1335,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.4,
|
| 881 |
+
"grad_norm": 1.4416459798812866,
|
| 882 |
+
"learning_rate": 9.123063103525713e-05,
|
| 883 |
+
"loss": 0.1325,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.4032,
|
| 888 |
+
"grad_norm": 2.590508460998535,
|
| 889 |
+
"learning_rate": 9.111834718167527e-05,
|
| 890 |
+
"loss": 0.1258,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.4064,
|
| 895 |
+
"grad_norm": 1.7362828254699707,
|
| 896 |
+
"learning_rate": 9.100606332809342e-05,
|
| 897 |
+
"loss": 0.1337,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.4096,
|
| 902 |
+
"grad_norm": 1.726511836051941,
|
| 903 |
+
"learning_rate": 9.089377947451156e-05,
|
| 904 |
+
"loss": 0.1274,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.4128,
|
| 909 |
+
"grad_norm": 1.3185865879058838,
|
| 910 |
+
"learning_rate": 9.078149562092971e-05,
|
| 911 |
+
"loss": 0.1244,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.416,
|
| 916 |
+
"grad_norm": 1.6214089393615723,
|
| 917 |
+
"learning_rate": 9.066921176734786e-05,
|
| 918 |
+
"loss": 0.1002,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.4192,
|
| 923 |
+
"grad_norm": 1.206648826599121,
|
| 924 |
+
"learning_rate": 9.055692791376601e-05,
|
| 925 |
+
"loss": 0.1169,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.4224,
|
| 930 |
+
"grad_norm": 1.020280122756958,
|
| 931 |
+
"learning_rate": 9.044464406018415e-05,
|
| 932 |
+
"loss": 0.1036,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.4256,
|
| 937 |
+
"grad_norm": 1.86745285987854,
|
| 938 |
+
"learning_rate": 9.03323602066023e-05,
|
| 939 |
+
"loss": 0.1163,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.4288,
|
| 944 |
+
"grad_norm": 1.2367403507232666,
|
| 945 |
+
"learning_rate": 9.022007635302045e-05,
|
| 946 |
+
"loss": 0.1166,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.432,
|
| 951 |
+
"grad_norm": 1.3708258867263794,
|
| 952 |
+
"learning_rate": 9.010779249943859e-05,
|
| 953 |
+
"loss": 0.0956,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.4352,
|
| 958 |
+
"grad_norm": 1.9553757905960083,
|
| 959 |
+
"learning_rate": 8.999550864585672e-05,
|
| 960 |
+
"loss": 0.1139,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.4384,
|
| 965 |
+
"grad_norm": 2.1358702182769775,
|
| 966 |
+
"learning_rate": 8.988322479227488e-05,
|
| 967 |
+
"loss": 0.1094,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.4416,
|
| 972 |
+
"grad_norm": 3.4062862396240234,
|
| 973 |
+
"learning_rate": 8.977094093869301e-05,
|
| 974 |
+
"loss": 0.1017,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.4448,
|
| 979 |
+
"grad_norm": 1.4105799198150635,
|
| 980 |
+
"learning_rate": 8.965865708511116e-05,
|
| 981 |
+
"loss": 0.1008,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.448,
|
| 986 |
+
"grad_norm": 1.713500738143921,
|
| 987 |
+
"learning_rate": 8.954637323152931e-05,
|
| 988 |
+
"loss": 0.1078,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.4512,
|
| 993 |
+
"grad_norm": 1.128848671913147,
|
| 994 |
+
"learning_rate": 8.943408937794746e-05,
|
| 995 |
+
"loss": 0.093,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.4544,
|
| 1000 |
+
"grad_norm": 1.3671025037765503,
|
| 1001 |
+
"learning_rate": 8.93218055243656e-05,
|
| 1002 |
+
"loss": 0.1093,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.4576,
|
| 1007 |
+
"grad_norm": 1.8151606321334839,
|
| 1008 |
+
"learning_rate": 8.920952167078375e-05,
|
| 1009 |
+
"loss": 0.1088,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4608,
|
| 1014 |
+
"grad_norm": 1.1207199096679688,
|
| 1015 |
+
"learning_rate": 8.909723781720189e-05,
|
| 1016 |
+
"loss": 0.1051,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.464,
|
| 1021 |
+
"grad_norm": 1.0649629831314087,
|
| 1022 |
+
"learning_rate": 8.898495396362003e-05,
|
| 1023 |
+
"loss": 0.1,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.4672,
|
| 1028 |
+
"grad_norm": 1.4365625381469727,
|
| 1029 |
+
"learning_rate": 8.887267011003818e-05,
|
| 1030 |
+
"loss": 0.0861,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.4704,
|
| 1035 |
+
"grad_norm": 1.1462955474853516,
|
| 1036 |
+
"learning_rate": 8.876038625645633e-05,
|
| 1037 |
+
"loss": 0.0866,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.4736,
|
| 1042 |
+
"grad_norm": 1.3217401504516602,
|
| 1043 |
+
"learning_rate": 8.864810240287447e-05,
|
| 1044 |
+
"loss": 0.0979,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.4768,
|
| 1049 |
+
"grad_norm": 1.3830331563949585,
|
| 1050 |
+
"learning_rate": 8.853581854929262e-05,
|
| 1051 |
+
"loss": 0.0792,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.48,
|
| 1056 |
+
"grad_norm": 1.777252435684204,
|
| 1057 |
+
"learning_rate": 8.842353469571077e-05,
|
| 1058 |
+
"loss": 0.0727,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4832,
|
| 1063 |
+
"grad_norm": 1.220021367073059,
|
| 1064 |
+
"learning_rate": 8.83112508421289e-05,
|
| 1065 |
+
"loss": 0.0836,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4864,
|
| 1070 |
+
"grad_norm": 2.3963851928710938,
|
| 1071 |
+
"learning_rate": 8.819896698854705e-05,
|
| 1072 |
+
"loss": 0.0851,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.4896,
|
| 1077 |
+
"grad_norm": 1.1223018169403076,
|
| 1078 |
+
"learning_rate": 8.808668313496519e-05,
|
| 1079 |
+
"loss": 0.082,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.4928,
|
| 1084 |
+
"grad_norm": 1.148827314376831,
|
| 1085 |
+
"learning_rate": 8.797439928138334e-05,
|
| 1086 |
+
"loss": 0.0758,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.496,
|
| 1091 |
+
"grad_norm": 0.8612151145935059,
|
| 1092 |
+
"learning_rate": 8.786211542780148e-05,
|
| 1093 |
+
"loss": 0.0783,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.4992,
|
| 1098 |
+
"grad_norm": 1.1042686700820923,
|
| 1099 |
+
"learning_rate": 8.774983157421963e-05,
|
| 1100 |
+
"loss": 0.0846,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.5024,
|
| 1105 |
+
"grad_norm": 1.3059678077697754,
|
| 1106 |
+
"learning_rate": 8.763754772063778e-05,
|
| 1107 |
+
"loss": 0.0842,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.5056,
|
| 1112 |
+
"grad_norm": 1.976445198059082,
|
| 1113 |
+
"learning_rate": 8.752526386705592e-05,
|
| 1114 |
+
"loss": 0.0811,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.5088,
|
| 1119 |
+
"grad_norm": 1.7577661275863647,
|
| 1120 |
+
"learning_rate": 8.741298001347407e-05,
|
| 1121 |
+
"loss": 0.0848,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.512,
|
| 1126 |
+
"grad_norm": 1.2085758447647095,
|
| 1127 |
+
"learning_rate": 8.730069615989222e-05,
|
| 1128 |
+
"loss": 0.077,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.5152,
|
| 1133 |
+
"grad_norm": 1.1045840978622437,
|
| 1134 |
+
"learning_rate": 8.718841230631036e-05,
|
| 1135 |
+
"loss": 0.0794,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.5184,
|
| 1140 |
+
"grad_norm": 2.760986328125,
|
| 1141 |
+
"learning_rate": 8.70761284527285e-05,
|
| 1142 |
+
"loss": 0.0887,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.5216,
|
| 1147 |
+
"grad_norm": 1.1649103164672852,
|
| 1148 |
+
"learning_rate": 8.696384459914664e-05,
|
| 1149 |
+
"loss": 0.0806,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.5248,
|
| 1154 |
+
"grad_norm": 2.1718943119049072,
|
| 1155 |
+
"learning_rate": 8.68515607455648e-05,
|
| 1156 |
+
"loss": 0.0774,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.528,
|
| 1161 |
+
"grad_norm": 5.1032586097717285,
|
| 1162 |
+
"learning_rate": 8.673927689198293e-05,
|
| 1163 |
+
"loss": 0.0823,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.5312,
|
| 1168 |
+
"grad_norm": 1.3188016414642334,
|
| 1169 |
+
"learning_rate": 8.662699303840108e-05,
|
| 1170 |
+
"loss": 0.0723,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.5344,
|
| 1175 |
+
"grad_norm": 1.1091735363006592,
|
| 1176 |
+
"learning_rate": 8.651470918481923e-05,
|
| 1177 |
+
"loss": 0.0801,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.5376,
|
| 1182 |
+
"grad_norm": 1.944667935371399,
|
| 1183 |
+
"learning_rate": 8.640242533123737e-05,
|
| 1184 |
+
"loss": 0.0656,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.5408,
|
| 1189 |
+
"grad_norm": 1.409705400466919,
|
| 1190 |
+
"learning_rate": 8.629014147765552e-05,
|
| 1191 |
+
"loss": 0.0783,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.544,
|
| 1196 |
+
"grad_norm": 1.0202471017837524,
|
| 1197 |
+
"learning_rate": 8.617785762407367e-05,
|
| 1198 |
+
"loss": 0.0698,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.5472,
|
| 1203 |
+
"grad_norm": 0.8339371681213379,
|
| 1204 |
+
"learning_rate": 8.606557377049181e-05,
|
| 1205 |
+
"loss": 0.0646,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.5504,
|
| 1210 |
+
"grad_norm": 1.0416721105575562,
|
| 1211 |
+
"learning_rate": 8.595328991690995e-05,
|
| 1212 |
+
"loss": 0.0631,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.5536,
|
| 1217 |
+
"grad_norm": 0.812588632106781,
|
| 1218 |
+
"learning_rate": 8.58410060633281e-05,
|
| 1219 |
+
"loss": 0.0718,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.5568,
|
| 1224 |
+
"grad_norm": 1.2019861936569214,
|
| 1225 |
+
"learning_rate": 8.572872220974623e-05,
|
| 1226 |
+
"loss": 0.0766,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.56,
|
| 1231 |
+
"grad_norm": 0.8724514842033386,
|
| 1232 |
+
"learning_rate": 8.561643835616438e-05,
|
| 1233 |
+
"loss": 0.066,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5632,
|
| 1238 |
+
"grad_norm": 0.9269486665725708,
|
| 1239 |
+
"learning_rate": 8.550415450258253e-05,
|
| 1240 |
+
"loss": 0.0711,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.5664,
|
| 1245 |
+
"grad_norm": 1.1435014009475708,
|
| 1246 |
+
"learning_rate": 8.539187064900069e-05,
|
| 1247 |
+
"loss": 0.0649,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.5696,
|
| 1252 |
+
"grad_norm": 0.9017223119735718,
|
| 1253 |
+
"learning_rate": 8.527958679541882e-05,
|
| 1254 |
+
"loss": 0.0743,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.5728,
|
| 1259 |
+
"grad_norm": 1.5114269256591797,
|
| 1260 |
+
"learning_rate": 8.516730294183697e-05,
|
| 1261 |
+
"loss": 0.0711,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.576,
|
| 1266 |
+
"grad_norm": 1.1478126049041748,
|
| 1267 |
+
"learning_rate": 8.505501908825511e-05,
|
| 1268 |
+
"loss": 0.0749,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.5792,
|
| 1273 |
+
"grad_norm": 1.3925341367721558,
|
| 1274 |
+
"learning_rate": 8.494273523467325e-05,
|
| 1275 |
+
"loss": 0.0623,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.5824,
|
| 1280 |
+
"grad_norm": 0.7855392098426819,
|
| 1281 |
+
"learning_rate": 8.48304513810914e-05,
|
| 1282 |
+
"loss": 0.0568,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.5856,
|
| 1287 |
+
"grad_norm": 0.7520506381988525,
|
| 1288 |
+
"learning_rate": 8.471816752750955e-05,
|
| 1289 |
+
"loss": 0.0654,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5888,
|
| 1294 |
+
"grad_norm": 0.8448010087013245,
|
| 1295 |
+
"learning_rate": 8.460588367392769e-05,
|
| 1296 |
+
"loss": 0.0624,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.592,
|
| 1301 |
+
"grad_norm": 0.7805534601211548,
|
| 1302 |
+
"learning_rate": 8.449359982034584e-05,
|
| 1303 |
+
"loss": 0.0676,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.5952,
|
| 1308 |
+
"grad_norm": 1.1754975318908691,
|
| 1309 |
+
"learning_rate": 8.438131596676399e-05,
|
| 1310 |
+
"loss": 0.0609,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5984,
|
| 1315 |
+
"grad_norm": 0.7776190638542175,
|
| 1316 |
+
"learning_rate": 8.426903211318214e-05,
|
| 1317 |
+
"loss": 0.0601,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.6016,
|
| 1322 |
+
"grad_norm": 1.610683560371399,
|
| 1323 |
+
"learning_rate": 8.415674825960028e-05,
|
| 1324 |
+
"loss": 0.0618,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.6048,
|
| 1329 |
+
"grad_norm": 0.8926658630371094,
|
| 1330 |
+
"learning_rate": 8.404446440601843e-05,
|
| 1331 |
+
"loss": 0.0582,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.608,
|
| 1336 |
+
"grad_norm": 1.2540363073349,
|
| 1337 |
+
"learning_rate": 8.393218055243656e-05,
|
| 1338 |
+
"loss": 0.0623,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.6112,
|
| 1343 |
+
"grad_norm": 1.463120937347412,
|
| 1344 |
+
"learning_rate": 8.38198966988547e-05,
|
| 1345 |
+
"loss": 0.0595,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.6144,
|
| 1350 |
+
"grad_norm": 1.3101223707199097,
|
| 1351 |
+
"learning_rate": 8.370761284527285e-05,
|
| 1352 |
+
"loss": 0.0653,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.6176,
|
| 1357 |
+
"grad_norm": 1.1716495752334595,
|
| 1358 |
+
"learning_rate": 8.3595328991691e-05,
|
| 1359 |
+
"loss": 0.0518,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.6208,
|
| 1364 |
+
"grad_norm": 1.539556860923767,
|
| 1365 |
+
"learning_rate": 8.348304513810914e-05,
|
| 1366 |
+
"loss": 0.0496,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.624,
|
| 1371 |
+
"grad_norm": 0.8535395264625549,
|
| 1372 |
+
"learning_rate": 8.337076128452729e-05,
|
| 1373 |
+
"loss": 0.0581,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.6272,
|
| 1378 |
+
"grad_norm": 0.9112345576286316,
|
| 1379 |
+
"learning_rate": 8.325847743094544e-05,
|
| 1380 |
+
"loss": 0.0568,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.6304,
|
| 1385 |
+
"grad_norm": 0.9361368417739868,
|
| 1386 |
+
"learning_rate": 8.314619357736358e-05,
|
| 1387 |
+
"loss": 0.0507,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.6336,
|
| 1392 |
+
"grad_norm": 1.4482288360595703,
|
| 1393 |
+
"learning_rate": 8.303390972378173e-05,
|
| 1394 |
+
"loss": 0.0521,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.6368,
|
| 1399 |
+
"grad_norm": 0.9236279129981995,
|
| 1400 |
+
"learning_rate": 8.292162587019986e-05,
|
| 1401 |
+
"loss": 0.0512,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.64,
|
| 1406 |
+
"grad_norm": 1.238692045211792,
|
| 1407 |
+
"learning_rate": 8.280934201661802e-05,
|
| 1408 |
+
"loss": 0.0538,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.6432,
|
| 1413 |
+
"grad_norm": 0.9093800187110901,
|
| 1414 |
+
"learning_rate": 8.269705816303615e-05,
|
| 1415 |
+
"loss": 0.054,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.6464,
|
| 1420 |
+
"grad_norm": 0.7657427787780762,
|
| 1421 |
+
"learning_rate": 8.25847743094543e-05,
|
| 1422 |
+
"loss": 0.049,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.6496,
|
| 1427 |
+
"grad_norm": 1.5526565313339233,
|
| 1428 |
+
"learning_rate": 8.247249045587245e-05,
|
| 1429 |
+
"loss": 0.0524,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.6528,
|
| 1434 |
+
"grad_norm": 0.7204543352127075,
|
| 1435 |
+
"learning_rate": 8.236020660229059e-05,
|
| 1436 |
+
"loss": 0.0555,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.656,
|
| 1441 |
+
"grad_norm": 0.8594505190849304,
|
| 1442 |
+
"learning_rate": 8.224792274870874e-05,
|
| 1443 |
+
"loss": 0.0529,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.6592,
|
| 1448 |
+
"grad_norm": 1.0530890226364136,
|
| 1449 |
+
"learning_rate": 8.213563889512689e-05,
|
| 1450 |
+
"loss": 0.0621,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.6624,
|
| 1455 |
+
"grad_norm": 0.92835533618927,
|
| 1456 |
+
"learning_rate": 8.202335504154503e-05,
|
| 1457 |
+
"loss": 0.0434,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.6656,
|
| 1462 |
+
"grad_norm": 1.0584304332733154,
|
| 1463 |
+
"learning_rate": 8.191107118796317e-05,
|
| 1464 |
+
"loss": 0.0515,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.6688,
|
| 1469 |
+
"grad_norm": 0.7033383250236511,
|
| 1470 |
+
"learning_rate": 8.179878733438132e-05,
|
| 1471 |
+
"loss": 0.0451,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.672,
|
| 1476 |
+
"grad_norm": 1.09385085105896,
|
| 1477 |
+
"learning_rate": 8.168650348079947e-05,
|
| 1478 |
+
"loss": 0.0486,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.6752,
|
| 1483 |
+
"grad_norm": 1.0709513425827026,
|
| 1484 |
+
"learning_rate": 8.15742196272176e-05,
|
| 1485 |
+
"loss": 0.0571,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.6784,
|
| 1490 |
+
"grad_norm": 0.7316601276397705,
|
| 1491 |
+
"learning_rate": 8.146193577363576e-05,
|
| 1492 |
+
"loss": 0.0496,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.6816,
|
| 1497 |
+
"grad_norm": 0.9458874464035034,
|
| 1498 |
+
"learning_rate": 8.13496519200539e-05,
|
| 1499 |
+
"loss": 0.054,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.6848,
|
| 1504 |
+
"grad_norm": 2.1238739490509033,
|
| 1505 |
+
"learning_rate": 8.123736806647204e-05,
|
| 1506 |
+
"loss": 0.0535,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.688,
|
| 1511 |
+
"grad_norm": 1.011391520500183,
|
| 1512 |
+
"learning_rate": 8.11250842128902e-05,
|
| 1513 |
+
"loss": 0.0527,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.6912,
|
| 1518 |
+
"grad_norm": 0.8783167004585266,
|
| 1519 |
+
"learning_rate": 8.101280035930835e-05,
|
| 1520 |
+
"loss": 0.0424,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.6944,
|
| 1525 |
+
"grad_norm": 0.9206530451774597,
|
| 1526 |
+
"learning_rate": 8.090051650572648e-05,
|
| 1527 |
+
"loss": 0.0588,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.6976,
|
| 1532 |
+
"grad_norm": 0.5304967164993286,
|
| 1533 |
+
"learning_rate": 8.078823265214462e-05,
|
| 1534 |
+
"loss": 0.0574,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.7008,
|
| 1539 |
+
"grad_norm": 0.5870644450187683,
|
| 1540 |
+
"learning_rate": 8.067594879856277e-05,
|
| 1541 |
+
"loss": 0.0512,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.704,
|
| 1546 |
+
"grad_norm": 0.7831016182899475,
|
| 1547 |
+
"learning_rate": 8.056366494498092e-05,
|
| 1548 |
+
"loss": 0.0485,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.7072,
|
| 1553 |
+
"grad_norm": 2.5291478633880615,
|
| 1554 |
+
"learning_rate": 8.045138109139906e-05,
|
| 1555 |
+
"loss": 0.058,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.7104,
|
| 1560 |
+
"grad_norm": 0.705797553062439,
|
| 1561 |
+
"learning_rate": 8.033909723781721e-05,
|
| 1562 |
+
"loss": 0.0534,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.7136,
|
| 1567 |
+
"grad_norm": 0.7620034217834473,
|
| 1568 |
+
"learning_rate": 8.022681338423536e-05,
|
| 1569 |
+
"loss": 0.0466,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.7168,
|
| 1574 |
+
"grad_norm": 2.0571022033691406,
|
| 1575 |
+
"learning_rate": 8.01145295306535e-05,
|
| 1576 |
+
"loss": 0.0469,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.72,
|
| 1581 |
+
"grad_norm": 1.094312310218811,
|
| 1582 |
+
"learning_rate": 8.000224567707165e-05,
|
| 1583 |
+
"loss": 0.0482,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.7232,
|
| 1588 |
+
"grad_norm": 0.857584536075592,
|
| 1589 |
+
"learning_rate": 7.988996182348978e-05,
|
| 1590 |
+
"loss": 0.044,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.7264,
|
| 1595 |
+
"grad_norm": 0.7637543082237244,
|
| 1596 |
+
"learning_rate": 7.977767796990792e-05,
|
| 1597 |
+
"loss": 0.0493,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.7296,
|
| 1602 |
+
"grad_norm": 0.6703894138336182,
|
| 1603 |
+
"learning_rate": 7.966539411632607e-05,
|
| 1604 |
+
"loss": 0.0462,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.7328,
|
| 1609 |
+
"grad_norm": 0.7242295145988464,
|
| 1610 |
+
"learning_rate": 7.955311026274422e-05,
|
| 1611 |
+
"loss": 0.044,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.736,
|
| 1616 |
+
"grad_norm": 1.0875325202941895,
|
| 1617 |
+
"learning_rate": 7.944082640916236e-05,
|
| 1618 |
+
"loss": 0.0458,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.7392,
|
| 1623 |
+
"grad_norm": 0.8322548270225525,
|
| 1624 |
+
"learning_rate": 7.932854255558051e-05,
|
| 1625 |
+
"loss": 0.0471,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.7424,
|
| 1630 |
+
"grad_norm": 1.6921989917755127,
|
| 1631 |
+
"learning_rate": 7.921625870199866e-05,
|
| 1632 |
+
"loss": 0.0481,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.7456,
|
| 1637 |
+
"grad_norm": 0.9339900612831116,
|
| 1638 |
+
"learning_rate": 7.910397484841681e-05,
|
| 1639 |
+
"loss": 0.0438,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.7488,
|
| 1644 |
+
"grad_norm": 0.9007784724235535,
|
| 1645 |
+
"learning_rate": 7.899169099483495e-05,
|
| 1646 |
+
"loss": 0.051,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.752,
|
| 1651 |
+
"grad_norm": 0.7366623282432556,
|
| 1652 |
+
"learning_rate": 7.887940714125309e-05,
|
| 1653 |
+
"loss": 0.0488,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.7552,
|
| 1658 |
+
"grad_norm": 1.0581986904144287,
|
| 1659 |
+
"learning_rate": 7.876712328767124e-05,
|
| 1660 |
+
"loss": 0.0465,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.7584,
|
| 1665 |
+
"grad_norm": 0.8398572206497192,
|
| 1666 |
+
"learning_rate": 7.865483943408937e-05,
|
| 1667 |
+
"loss": 0.0444,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.7616,
|
| 1672 |
+
"grad_norm": 0.829765796661377,
|
| 1673 |
+
"learning_rate": 7.854255558050752e-05,
|
| 1674 |
+
"loss": 0.0468,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.7648,
|
| 1679 |
+
"grad_norm": 0.8922726511955261,
|
| 1680 |
+
"learning_rate": 7.843027172692568e-05,
|
| 1681 |
+
"loss": 0.0429,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.768,
|
| 1686 |
+
"grad_norm": 0.9981004595756531,
|
| 1687 |
+
"learning_rate": 7.831798787334381e-05,
|
| 1688 |
+
"loss": 0.0425,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.7712,
|
| 1693 |
+
"grad_norm": 1.1781072616577148,
|
| 1694 |
+
"learning_rate": 7.820570401976196e-05,
|
| 1695 |
+
"loss": 0.0467,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.7744,
|
| 1700 |
+
"grad_norm": 1.295114517211914,
|
| 1701 |
+
"learning_rate": 7.809342016618011e-05,
|
| 1702 |
+
"loss": 0.0429,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.7776,
|
| 1707 |
+
"grad_norm": 1.2923245429992676,
|
| 1708 |
+
"learning_rate": 7.798113631259825e-05,
|
| 1709 |
+
"loss": 0.0411,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.7808,
|
| 1714 |
+
"grad_norm": 0.9972735643386841,
|
| 1715 |
+
"learning_rate": 7.78688524590164e-05,
|
| 1716 |
+
"loss": 0.0392,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.784,
|
| 1721 |
+
"grad_norm": 0.7741293907165527,
|
| 1722 |
+
"learning_rate": 7.775656860543454e-05,
|
| 1723 |
+
"loss": 0.0432,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.7872,
|
| 1728 |
+
"grad_norm": 0.5855127573013306,
|
| 1729 |
+
"learning_rate": 7.764428475185269e-05,
|
| 1730 |
+
"loss": 0.0468,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.7904,
|
| 1735 |
+
"grad_norm": 0.6745654940605164,
|
| 1736 |
+
"learning_rate": 7.753200089827083e-05,
|
| 1737 |
+
"loss": 0.0394,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.7936,
|
| 1742 |
+
"grad_norm": 1.2831262350082397,
|
| 1743 |
+
"learning_rate": 7.741971704468898e-05,
|
| 1744 |
+
"loss": 0.037,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.7968,
|
| 1749 |
+
"grad_norm": 0.6621804237365723,
|
| 1750 |
+
"learning_rate": 7.730743319110713e-05,
|
| 1751 |
+
"loss": 0.0413,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.8,
|
| 1756 |
+
"grad_norm": 0.5354174375534058,
|
| 1757 |
+
"learning_rate": 7.719514933752526e-05,
|
| 1758 |
+
"loss": 0.0375,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.8032,
|
| 1763 |
+
"grad_norm": 0.9441866278648376,
|
| 1764 |
+
"learning_rate": 7.708286548394342e-05,
|
| 1765 |
+
"loss": 0.0364,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.8064,
|
| 1770 |
+
"grad_norm": 0.6830460429191589,
|
| 1771 |
+
"learning_rate": 7.697058163036157e-05,
|
| 1772 |
+
"loss": 0.042,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.8096,
|
| 1777 |
+
"grad_norm": 0.6004045605659485,
|
| 1778 |
+
"learning_rate": 7.68582977767797e-05,
|
| 1779 |
+
"loss": 0.04,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.8128,
|
| 1784 |
+
"grad_norm": 0.6852745413780212,
|
| 1785 |
+
"learning_rate": 7.674601392319784e-05,
|
| 1786 |
+
"loss": 0.0404,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.816,
|
| 1791 |
+
"grad_norm": 1.0080032348632812,
|
| 1792 |
+
"learning_rate": 7.663373006961599e-05,
|
| 1793 |
+
"loss": 0.043,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.8192,
|
| 1798 |
+
"grad_norm": 0.7791699767112732,
|
| 1799 |
+
"learning_rate": 7.652144621603414e-05,
|
| 1800 |
+
"loss": 0.0411,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.8224,
|
| 1805 |
+
"grad_norm": 1.192091464996338,
|
| 1806 |
+
"learning_rate": 7.640916236245228e-05,
|
| 1807 |
+
"loss": 0.0413,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.8256,
|
| 1812 |
+
"grad_norm": 0.744788646697998,
|
| 1813 |
+
"learning_rate": 7.629687850887043e-05,
|
| 1814 |
+
"loss": 0.0401,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.8288,
|
| 1819 |
+
"grad_norm": 0.6732345223426819,
|
| 1820 |
+
"learning_rate": 7.618459465528858e-05,
|
| 1821 |
+
"loss": 0.0426,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.832,
|
| 1826 |
+
"grad_norm": 1.0868829488754272,
|
| 1827 |
+
"learning_rate": 7.607231080170672e-05,
|
| 1828 |
+
"loss": 0.0368,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.8352,
|
| 1833 |
+
"grad_norm": 1.4248939752578735,
|
| 1834 |
+
"learning_rate": 7.596002694812487e-05,
|
| 1835 |
+
"loss": 0.0369,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.8384,
|
| 1840 |
+
"grad_norm": 0.7218601107597351,
|
| 1841 |
+
"learning_rate": 7.5847743094543e-05,
|
| 1842 |
+
"loss": 0.0415,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.8416,
|
| 1847 |
+
"grad_norm": 0.803717851638794,
|
| 1848 |
+
"learning_rate": 7.573545924096114e-05,
|
| 1849 |
+
"loss": 0.0352,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.8448,
|
| 1854 |
+
"grad_norm": 0.821607768535614,
|
| 1855 |
+
"learning_rate": 7.562317538737929e-05,
|
| 1856 |
+
"loss": 0.039,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.848,
|
| 1861 |
+
"grad_norm": 1.1404283046722412,
|
| 1862 |
+
"learning_rate": 7.551089153379744e-05,
|
| 1863 |
+
"loss": 0.0369,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.8512,
|
| 1868 |
+
"grad_norm": 1.2288737297058105,
|
| 1869 |
+
"learning_rate": 7.53986076802156e-05,
|
| 1870 |
+
"loss": 0.0417,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.8544,
|
| 1875 |
+
"grad_norm": 1.0263468027114868,
|
| 1876 |
+
"learning_rate": 7.528632382663373e-05,
|
| 1877 |
+
"loss": 0.0423,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.8576,
|
| 1882 |
+
"grad_norm": 0.8517736196517944,
|
| 1883 |
+
"learning_rate": 7.517403997305188e-05,
|
| 1884 |
+
"loss": 0.0364,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.8608,
|
| 1889 |
+
"grad_norm": 0.8727993369102478,
|
| 1890 |
+
"learning_rate": 7.506175611947003e-05,
|
| 1891 |
+
"loss": 0.0382,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.864,
|
| 1896 |
+
"grad_norm": 0.7277560234069824,
|
| 1897 |
+
"learning_rate": 7.494947226588817e-05,
|
| 1898 |
+
"loss": 0.0368,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.8672,
|
| 1903 |
+
"grad_norm": 0.854989230632782,
|
| 1904 |
+
"learning_rate": 7.483718841230631e-05,
|
| 1905 |
+
"loss": 0.0431,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.8704,
|
| 1910 |
+
"grad_norm": 0.47089987993240356,
|
| 1911 |
+
"learning_rate": 7.472490455872446e-05,
|
| 1912 |
+
"loss": 0.0372,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.8736,
|
| 1917 |
+
"grad_norm": 0.716643750667572,
|
| 1918 |
+
"learning_rate": 7.46126207051426e-05,
|
| 1919 |
+
"loss": 0.0348,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.8768,
|
| 1924 |
+
"grad_norm": 0.8277871012687683,
|
| 1925 |
+
"learning_rate": 7.450033685156075e-05,
|
| 1926 |
+
"loss": 0.0369,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.88,
|
| 1931 |
+
"grad_norm": 0.9618933796882629,
|
| 1932 |
+
"learning_rate": 7.43880529979789e-05,
|
| 1933 |
+
"loss": 0.0377,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.8832,
|
| 1938 |
+
"grad_norm": 0.6898852586746216,
|
| 1939 |
+
"learning_rate": 7.427576914439703e-05,
|
| 1940 |
+
"loss": 0.0543,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.8864,
|
| 1945 |
+
"grad_norm": 1.4362825155258179,
|
| 1946 |
+
"learning_rate": 7.416348529081518e-05,
|
| 1947 |
+
"loss": 0.0397,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.8896,
|
| 1952 |
+
"grad_norm": 1.1972767114639282,
|
| 1953 |
+
"learning_rate": 7.405120143723333e-05,
|
| 1954 |
+
"loss": 0.0324,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.8928,
|
| 1959 |
+
"grad_norm": 0.5438815355300903,
|
| 1960 |
+
"learning_rate": 7.393891758365149e-05,
|
| 1961 |
+
"loss": 0.0397,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.896,
|
| 1966 |
+
"grad_norm": 0.513469398021698,
|
| 1967 |
+
"learning_rate": 7.382663373006962e-05,
|
| 1968 |
+
"loss": 0.0338,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.8992,
|
| 1973 |
+
"grad_norm": 0.5743911266326904,
|
| 1974 |
+
"learning_rate": 7.371434987648776e-05,
|
| 1975 |
+
"loss": 0.0313,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.9024,
|
| 1980 |
+
"grad_norm": 1.011957049369812,
|
| 1981 |
+
"learning_rate": 7.360206602290591e-05,
|
| 1982 |
+
"loss": 0.0374,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.9056,
|
| 1987 |
+
"grad_norm": 0.6926620602607727,
|
| 1988 |
+
"learning_rate": 7.348978216932405e-05,
|
| 1989 |
+
"loss": 0.0392,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.9088,
|
| 1994 |
+
"grad_norm": 0.6338510513305664,
|
| 1995 |
+
"learning_rate": 7.33774983157422e-05,
|
| 1996 |
+
"loss": 0.0359,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.912,
|
| 2001 |
+
"grad_norm": 0.7649824023246765,
|
| 2002 |
+
"learning_rate": 7.326521446216035e-05,
|
| 2003 |
+
"loss": 0.0353,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.9152,
|
| 2008 |
+
"grad_norm": 0.8123289346694946,
|
| 2009 |
+
"learning_rate": 7.315293060857849e-05,
|
| 2010 |
+
"loss": 0.0322,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.9184,
|
| 2015 |
+
"grad_norm": 0.8033359050750732,
|
| 2016 |
+
"learning_rate": 7.304064675499664e-05,
|
| 2017 |
+
"loss": 0.0331,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.9216,
|
| 2022 |
+
"grad_norm": 0.8859496116638184,
|
| 2023 |
+
"learning_rate": 7.292836290141479e-05,
|
| 2024 |
+
"loss": 0.0352,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.9248,
|
| 2029 |
+
"grad_norm": 0.7962930202484131,
|
| 2030 |
+
"learning_rate": 7.281607904783292e-05,
|
| 2031 |
+
"loss": 0.0373,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.928,
|
| 2036 |
+
"grad_norm": 0.746497392654419,
|
| 2037 |
+
"learning_rate": 7.270379519425106e-05,
|
| 2038 |
+
"loss": 0.0426,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.9312,
|
| 2043 |
+
"grad_norm": 0.8344641327857971,
|
| 2044 |
+
"learning_rate": 7.259151134066921e-05,
|
| 2045 |
+
"loss": 0.0349,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.9344,
|
| 2050 |
+
"grad_norm": 0.8275250792503357,
|
| 2051 |
+
"learning_rate": 7.247922748708736e-05,
|
| 2052 |
+
"loss": 0.0358,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.9376,
|
| 2057 |
+
"grad_norm": 0.5994471907615662,
|
| 2058 |
+
"learning_rate": 7.23669436335055e-05,
|
| 2059 |
+
"loss": 0.0344,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.9408,
|
| 2064 |
+
"grad_norm": 0.6452350616455078,
|
| 2065 |
+
"learning_rate": 7.225465977992365e-05,
|
| 2066 |
+
"loss": 0.0358,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.944,
|
| 2071 |
+
"grad_norm": 1.0141571760177612,
|
| 2072 |
+
"learning_rate": 7.21423759263418e-05,
|
| 2073 |
+
"loss": 0.0347,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.9472,
|
| 2078 |
+
"grad_norm": 0.832384467124939,
|
| 2079 |
+
"learning_rate": 7.203009207275994e-05,
|
| 2080 |
+
"loss": 0.0332,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.9504,
|
| 2085 |
+
"grad_norm": 0.7129203677177429,
|
| 2086 |
+
"learning_rate": 7.191780821917809e-05,
|
| 2087 |
+
"loss": 0.0313,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.9536,
|
| 2092 |
+
"grad_norm": 0.7890746593475342,
|
| 2093 |
+
"learning_rate": 7.180552436559623e-05,
|
| 2094 |
+
"loss": 0.0331,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.9568,
|
| 2099 |
+
"grad_norm": 1.432335615158081,
|
| 2100 |
+
"learning_rate": 7.169324051201438e-05,
|
| 2101 |
+
"loss": 0.0353,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.96,
|
| 2106 |
+
"grad_norm": 1.0536537170410156,
|
| 2107 |
+
"learning_rate": 7.158095665843251e-05,
|
| 2108 |
+
"loss": 0.039,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.9632,
|
| 2113 |
+
"grad_norm": 0.7935389280319214,
|
| 2114 |
+
"learning_rate": 7.146867280485066e-05,
|
| 2115 |
+
"loss": 0.0334,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.9664,
|
| 2120 |
+
"grad_norm": 1.4054580926895142,
|
| 2121 |
+
"learning_rate": 7.135638895126882e-05,
|
| 2122 |
+
"loss": 0.033,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.9696,
|
| 2127 |
+
"grad_norm": 0.6271975040435791,
|
| 2128 |
+
"learning_rate": 7.124410509768695e-05,
|
| 2129 |
+
"loss": 0.0327,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.9728,
|
| 2134 |
+
"grad_norm": 0.5951416492462158,
|
| 2135 |
+
"learning_rate": 7.11318212441051e-05,
|
| 2136 |
+
"loss": 0.0325,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.976,
|
| 2141 |
+
"grad_norm": 0.6794223785400391,
|
| 2142 |
+
"learning_rate": 7.101953739052325e-05,
|
| 2143 |
+
"loss": 0.0336,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.9792,
|
| 2148 |
+
"grad_norm": 1.084647536277771,
|
| 2149 |
+
"learning_rate": 7.090725353694139e-05,
|
| 2150 |
+
"loss": 0.035,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.9824,
|
| 2155 |
+
"grad_norm": 0.40548598766326904,
|
| 2156 |
+
"learning_rate": 7.079496968335954e-05,
|
| 2157 |
+
"loss": 0.0277,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.9856,
|
| 2162 |
+
"grad_norm": 0.6343255043029785,
|
| 2163 |
+
"learning_rate": 7.068268582977768e-05,
|
| 2164 |
+
"loss": 0.0282,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.9888,
|
| 2169 |
+
"grad_norm": 0.53138667345047,
|
| 2170 |
+
"learning_rate": 7.057040197619582e-05,
|
| 2171 |
+
"loss": 0.032,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.992,
|
| 2176 |
+
"grad_norm": 0.7178220748901367,
|
| 2177 |
+
"learning_rate": 7.045811812261397e-05,
|
| 2178 |
+
"loss": 0.0323,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.9952,
|
| 2183 |
+
"grad_norm": 0.5384820103645325,
|
| 2184 |
+
"learning_rate": 7.034583426903212e-05,
|
| 2185 |
+
"loss": 0.0319,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.9984,
|
| 2190 |
+
"grad_norm": 1.4491897821426392,
|
| 2191 |
+
"learning_rate": 7.023355041545027e-05,
|
| 2192 |
+
"loss": 0.0345,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
}
|
| 2195 |
+
],
|
| 2196 |
+
"logging_steps": 10,
|
| 2197 |
+
"max_steps": 9375,
|
| 2198 |
+
"num_input_tokens_seen": 0,
|
| 2199 |
+
"num_train_epochs": 3,
|
| 2200 |
+
"save_steps": 500,
|
| 2201 |
+
"stateful_callbacks": {
|
| 2202 |
+
"TrainerControl": {
|
| 2203 |
+
"args": {
|
| 2204 |
+
"should_epoch_stop": false,
|
| 2205 |
+
"should_evaluate": false,
|
| 2206 |
+
"should_log": false,
|
| 2207 |
+
"should_save": true,
|
| 2208 |
+
"should_training_stop": false
|
| 2209 |
+
},
|
| 2210 |
+
"attributes": {}
|
| 2211 |
+
}
|
| 2212 |
+
},
|
| 2213 |
+
"total_flos": 0.0,
|
| 2214 |
+
"train_batch_size": 32,
|
| 2215 |
+
"trial_name": null,
|
| 2216 |
+
"trial_params": null
|
| 2217 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58dc4832b9ecbedb58e177e8210247010a0ec93903efa66a51b87b3bc91d64e4
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|