Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- trainer_state.json +1890 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 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 0.9.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 128,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 256,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adadcf21d4682bd65e146aa45b0113da5a9436e2c85696a3b84df33e917857a8
|
| 3 |
+
size 2558587064
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:692821d5c3911ab190d565d9093a0df73deff248e73be37a2c1b0045aeb6f22c
|
| 3 |
+
size 1282290004
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fbb40ce992670fb616d9b8f9adb153ecaa93849d405319102e1c8af86942c08
|
| 3 |
+
size 14512
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2eb93c64d5291ab1cb420ea7d1d20c3876eee37246869e4b0836acc38ddbe4b8
|
| 3 |
+
size 14512
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:232ed0aa36eba0b49bab9f931603d38429aa7f1a42e67f5469c47983616a34cf
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false,
|
| 43 |
+
"use_fast": true
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1890 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.30042194092827,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 267,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.33328112959861755,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 0.9029,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 0.341234415769577,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 0.9276,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0,
|
| 27 |
+
"grad_norm": 0.3182106614112854,
|
| 28 |
+
"learning_rate": 6e-05,
|
| 29 |
+
"loss": 0.9148,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0,
|
| 34 |
+
"grad_norm": 0.22865141928195953,
|
| 35 |
+
"learning_rate": 8e-05,
|
| 36 |
+
"loss": 0.8421,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"grad_norm": 0.29670122265815735,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.7984,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"grad_norm": 0.28762516379356384,
|
| 49 |
+
"learning_rate": 0.00012,
|
| 50 |
+
"loss": 0.7625,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"grad_norm": 0.23907965421676636,
|
| 56 |
+
"learning_rate": 0.00014,
|
| 57 |
+
"loss": 0.7226,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.01,
|
| 62 |
+
"grad_norm": 0.19532263278961182,
|
| 63 |
+
"learning_rate": 0.00016,
|
| 64 |
+
"loss": 0.7043,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01,
|
| 69 |
+
"grad_norm": 0.1425202488899231,
|
| 70 |
+
"learning_rate": 0.00018,
|
| 71 |
+
"loss": 0.6784,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.01,
|
| 76 |
+
"grad_norm": 0.10882167518138885,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.6579,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.01,
|
| 83 |
+
"grad_norm": 0.11275648325681686,
|
| 84 |
+
"learning_rate": 0.00019999935985220405,
|
| 85 |
+
"loss": 0.6592,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.01,
|
| 90 |
+
"grad_norm": 0.10155748575925827,
|
| 91 |
+
"learning_rate": 0.00019999743941701188,
|
| 92 |
+
"loss": 0.6554,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01,
|
| 97 |
+
"grad_norm": 0.0845816433429718,
|
| 98 |
+
"learning_rate": 0.0001999942387190108,
|
| 99 |
+
"loss": 0.6513,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.02,
|
| 104 |
+
"grad_norm": 0.09046202898025513,
|
| 105 |
+
"learning_rate": 0.0001999897577991792,
|
| 106 |
+
"loss": 0.6267,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.02,
|
| 111 |
+
"grad_norm": 0.08296829462051392,
|
| 112 |
+
"learning_rate": 0.00019998399671488612,
|
| 113 |
+
"loss": 0.6434,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.02,
|
| 118 |
+
"grad_norm": 0.07594181597232819,
|
| 119 |
+
"learning_rate": 0.00019997695553989042,
|
| 120 |
+
"loss": 0.6096,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.02,
|
| 125 |
+
"grad_norm": 0.0683172270655632,
|
| 126 |
+
"learning_rate": 0.00019996863436433997,
|
| 127 |
+
"loss": 0.6143,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.02,
|
| 132 |
+
"grad_norm": 0.05627186596393585,
|
| 133 |
+
"learning_rate": 0.0001999590332947704,
|
| 134 |
+
"loss": 0.6024,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02,
|
| 139 |
+
"grad_norm": 0.05644279345870018,
|
| 140 |
+
"learning_rate": 0.00019994815245410384,
|
| 141 |
+
"loss": 0.595,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.02,
|
| 146 |
+
"grad_norm": 0.05661479011178017,
|
| 147 |
+
"learning_rate": 0.00019993599198164715,
|
| 148 |
+
"loss": 0.5759,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.02,
|
| 153 |
+
"grad_norm": 0.04077177122235298,
|
| 154 |
+
"learning_rate": 0.00019992255203309033,
|
| 155 |
+
"loss": 0.582,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.02,
|
| 160 |
+
"grad_norm": 0.04510512948036194,
|
| 161 |
+
"learning_rate": 0.00019990783278050448,
|
| 162 |
+
"loss": 0.5751,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.03,
|
| 167 |
+
"grad_norm": 0.0470162108540535,
|
| 168 |
+
"learning_rate": 0.00019989183441233952,
|
| 169 |
+
"loss": 0.5716,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.03,
|
| 174 |
+
"grad_norm": 0.04402562975883484,
|
| 175 |
+
"learning_rate": 0.00019987455713342187,
|
| 176 |
+
"loss": 0.564,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.03,
|
| 181 |
+
"grad_norm": 0.045594893395900726,
|
| 182 |
+
"learning_rate": 0.00019985600116495173,
|
| 183 |
+
"loss": 0.5657,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.03,
|
| 188 |
+
"grad_norm": 0.037670280784368515,
|
| 189 |
+
"learning_rate": 0.0001998361667445004,
|
| 190 |
+
"loss": 0.5619,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.03,
|
| 195 |
+
"grad_norm": 0.034366946667432785,
|
| 196 |
+
"learning_rate": 0.00019981505412600706,
|
| 197 |
+
"loss": 0.554,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.03,
|
| 202 |
+
"grad_norm": 0.044084370136260986,
|
| 203 |
+
"learning_rate": 0.00019979266357977564,
|
| 204 |
+
"loss": 0.5527,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.03,
|
| 209 |
+
"grad_norm": 0.04839107394218445,
|
| 210 |
+
"learning_rate": 0.0001997689953924713,
|
| 211 |
+
"loss": 0.5534,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.03,
|
| 216 |
+
"grad_norm": 0.04943666234612465,
|
| 217 |
+
"learning_rate": 0.0001997440498671168,
|
| 218 |
+
"loss": 0.5357,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03,
|
| 223 |
+
"grad_norm": 0.05644814297556877,
|
| 224 |
+
"learning_rate": 0.00019971782732308867,
|
| 225 |
+
"loss": 0.5388,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.04,
|
| 230 |
+
"grad_norm": 0.05796538665890694,
|
| 231 |
+
"learning_rate": 0.00019969032809611287,
|
| 232 |
+
"loss": 0.5327,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.04,
|
| 237 |
+
"grad_norm": 0.05399211496114731,
|
| 238 |
+
"learning_rate": 0.0001996615525382609,
|
| 239 |
+
"loss": 0.5447,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.04,
|
| 244 |
+
"grad_norm": 0.03574652597308159,
|
| 245 |
+
"learning_rate": 0.0001996315010179449,
|
| 246 |
+
"loss": 0.5213,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.04,
|
| 251 |
+
"grad_norm": 0.04394914582371712,
|
| 252 |
+
"learning_rate": 0.00019960017391991314,
|
| 253 |
+
"loss": 0.5247,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04,
|
| 258 |
+
"grad_norm": 0.05197073519229889,
|
| 259 |
+
"learning_rate": 0.00019956757164524516,
|
| 260 |
+
"loss": 0.5253,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.04,
|
| 265 |
+
"grad_norm": 0.05605654790997505,
|
| 266 |
+
"learning_rate": 0.00019953369461134634,
|
| 267 |
+
"loss": 0.5289,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.04,
|
| 272 |
+
"grad_norm": 0.05167644843459129,
|
| 273 |
+
"learning_rate": 0.00019949854325194294,
|
| 274 |
+
"loss": 0.5223,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.04,
|
| 279 |
+
"grad_norm": 0.04118728265166283,
|
| 280 |
+
"learning_rate": 0.0001994621180170762,
|
| 281 |
+
"loss": 0.52,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.05,
|
| 286 |
+
"grad_norm": 0.0373263917863369,
|
| 287 |
+
"learning_rate": 0.00019942441937309684,
|
| 288 |
+
"loss": 0.5076,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.05,
|
| 293 |
+
"grad_norm": 0.04870600998401642,
|
| 294 |
+
"learning_rate": 0.0001993854478026589,
|
| 295 |
+
"loss": 0.5287,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.05,
|
| 300 |
+
"grad_norm": 0.05014103651046753,
|
| 301 |
+
"learning_rate": 0.00019934520380471372,
|
| 302 |
+
"loss": 0.5048,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.05,
|
| 307 |
+
"grad_norm": 0.04807833209633827,
|
| 308 |
+
"learning_rate": 0.0001993036878945034,
|
| 309 |
+
"loss": 0.5075,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.05,
|
| 314 |
+
"grad_norm": 0.040045421570539474,
|
| 315 |
+
"learning_rate": 0.0001992609006035543,
|
| 316 |
+
"loss": 0.4954,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.05,
|
| 321 |
+
"grad_norm": 0.04202349856495857,
|
| 322 |
+
"learning_rate": 0.00019921684247967028,
|
| 323 |
+
"loss": 0.4953,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.05,
|
| 328 |
+
"grad_norm": 0.041629109531641006,
|
| 329 |
+
"learning_rate": 0.0001991715140869255,
|
| 330 |
+
"loss": 0.501,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.05,
|
| 335 |
+
"grad_norm": 0.04767894372344017,
|
| 336 |
+
"learning_rate": 0.0001991249160056574,
|
| 337 |
+
"loss": 0.4878,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.05,
|
| 342 |
+
"grad_norm": 0.05395263060927391,
|
| 343 |
+
"learning_rate": 0.00019907704883245916,
|
| 344 |
+
"loss": 0.5014,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.06,
|
| 349 |
+
"grad_norm": 0.06040235981345177,
|
| 350 |
+
"learning_rate": 0.00019902791318017205,
|
| 351 |
+
"loss": 0.5043,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.06,
|
| 356 |
+
"grad_norm": 0.06749273091554642,
|
| 357 |
+
"learning_rate": 0.0001989775096778777,
|
| 358 |
+
"loss": 0.4931,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.06,
|
| 363 |
+
"grad_norm": 0.06482889503240585,
|
| 364 |
+
"learning_rate": 0.00019892583897088994,
|
| 365 |
+
"loss": 0.4869,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.06,
|
| 370 |
+
"grad_norm": 0.045358914881944656,
|
| 371 |
+
"learning_rate": 0.0001988729017207465,
|
| 372 |
+
"loss": 0.479,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.06,
|
| 377 |
+
"grad_norm": 0.043360061943531036,
|
| 378 |
+
"learning_rate": 0.00019881869860520073,
|
| 379 |
+
"loss": 0.4953,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.06,
|
| 384 |
+
"grad_norm": 0.060205183923244476,
|
| 385 |
+
"learning_rate": 0.00019876323031821266,
|
| 386 |
+
"loss": 0.4705,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.06,
|
| 391 |
+
"grad_norm": 0.05729120969772339,
|
| 392 |
+
"learning_rate": 0.00019870649756994037,
|
| 393 |
+
"loss": 0.4887,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.06,
|
| 398 |
+
"grad_norm": 0.03843148052692413,
|
| 399 |
+
"learning_rate": 0.00019864850108673073,
|
| 400 |
+
"loss": 0.4737,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.06,
|
| 405 |
+
"grad_norm": 0.053673889487981796,
|
| 406 |
+
"learning_rate": 0.00019858924161111015,
|
| 407 |
+
"loss": 0.4817,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.07,
|
| 412 |
+
"grad_norm": 0.05148368701338768,
|
| 413 |
+
"learning_rate": 0.00019852871990177503,
|
| 414 |
+
"loss": 0.4763,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.07,
|
| 419 |
+
"grad_norm": 0.05371672287583351,
|
| 420 |
+
"learning_rate": 0.00019846693673358226,
|
| 421 |
+
"loss": 0.4751,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.07,
|
| 426 |
+
"grad_norm": 0.05490916967391968,
|
| 427 |
+
"learning_rate": 0.00019840389289753896,
|
| 428 |
+
"loss": 0.457,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.07,
|
| 433 |
+
"grad_norm": 0.04629400372505188,
|
| 434 |
+
"learning_rate": 0.00019833958920079255,
|
| 435 |
+
"loss": 0.4692,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.07,
|
| 440 |
+
"grad_norm": 0.051137253642082214,
|
| 441 |
+
"learning_rate": 0.00019827402646662047,
|
| 442 |
+
"loss": 0.4614,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.07,
|
| 447 |
+
"grad_norm": 0.051790811121463776,
|
| 448 |
+
"learning_rate": 0.0001982072055344195,
|
| 449 |
+
"loss": 0.4594,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.07,
|
| 454 |
+
"grad_norm": 0.0445956289768219,
|
| 455 |
+
"learning_rate": 0.00019813912725969509,
|
| 456 |
+
"loss": 0.4601,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.07,
|
| 461 |
+
"grad_norm": 0.04766576737165451,
|
| 462 |
+
"learning_rate": 0.0001980697925140504,
|
| 463 |
+
"loss": 0.4631,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.07,
|
| 468 |
+
"grad_norm": 0.04839074984192848,
|
| 469 |
+
"learning_rate": 0.0001979992021851751,
|
| 470 |
+
"loss": 0.4605,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.08,
|
| 475 |
+
"grad_norm": 0.04736727103590965,
|
| 476 |
+
"learning_rate": 0.0001979273571768341,
|
| 477 |
+
"loss": 0.4617,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.08,
|
| 482 |
+
"grad_norm": 0.057293377816677094,
|
| 483 |
+
"learning_rate": 0.0001978542584088558,
|
| 484 |
+
"loss": 0.4621,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.08,
|
| 489 |
+
"grad_norm": 0.05025665834546089,
|
| 490 |
+
"learning_rate": 0.0001977799068171206,
|
| 491 |
+
"loss": 0.4671,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.08,
|
| 496 |
+
"grad_norm": 0.057366687804460526,
|
| 497 |
+
"learning_rate": 0.0001977043033535486,
|
| 498 |
+
"loss": 0.4521,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.08,
|
| 503 |
+
"grad_norm": 0.07595837116241455,
|
| 504 |
+
"learning_rate": 0.00019762744898608762,
|
| 505 |
+
"loss": 0.4671,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.08,
|
| 510 |
+
"grad_norm": 0.07574213296175003,
|
| 511 |
+
"learning_rate": 0.0001975493446987007,
|
| 512 |
+
"loss": 0.4664,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.08,
|
| 517 |
+
"grad_norm": 0.06472938507795334,
|
| 518 |
+
"learning_rate": 0.00019746999149135362,
|
| 519 |
+
"loss": 0.456,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.08,
|
| 524 |
+
"grad_norm": 0.05983012542128563,
|
| 525 |
+
"learning_rate": 0.00019738939038000205,
|
| 526 |
+
"loss": 0.4459,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.08,
|
| 531 |
+
"grad_norm": 0.05136057734489441,
|
| 532 |
+
"learning_rate": 0.00019730754239657842,
|
| 533 |
+
"loss": 0.4486,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.09,
|
| 538 |
+
"grad_norm": 0.06191498041152954,
|
| 539 |
+
"learning_rate": 0.00019722444858897878,
|
| 540 |
+
"loss": 0.4424,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.09,
|
| 545 |
+
"grad_norm": 0.06742191314697266,
|
| 546 |
+
"learning_rate": 0.0001971401100210496,
|
| 547 |
+
"loss": 0.458,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.09,
|
| 552 |
+
"grad_norm": 0.06019548326730728,
|
| 553 |
+
"learning_rate": 0.00019705452777257377,
|
| 554 |
+
"loss": 0.4423,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.09,
|
| 559 |
+
"grad_norm": 0.05012982338666916,
|
| 560 |
+
"learning_rate": 0.0001969677029392571,
|
| 561 |
+
"loss": 0.4466,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.09,
|
| 566 |
+
"grad_norm": 0.0552060566842556,
|
| 567 |
+
"learning_rate": 0.00019687963663271409,
|
| 568 |
+
"loss": 0.4534,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.09,
|
| 573 |
+
"grad_norm": 0.05883748456835747,
|
| 574 |
+
"learning_rate": 0.00019679032998045376,
|
| 575 |
+
"loss": 0.4409,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.09,
|
| 580 |
+
"grad_norm": 0.07146705687046051,
|
| 581 |
+
"learning_rate": 0.00019669978412586528,
|
| 582 |
+
"loss": 0.4582,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.09,
|
| 587 |
+
"grad_norm": 0.054095230996608734,
|
| 588 |
+
"learning_rate": 0.00019660800022820317,
|
| 589 |
+
"loss": 0.4487,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.09,
|
| 594 |
+
"grad_norm": 0.04927053675055504,
|
| 595 |
+
"learning_rate": 0.00019651497946257266,
|
| 596 |
+
"loss": 0.4429,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.1,
|
| 601 |
+
"grad_norm": 0.06037526577711105,
|
| 602 |
+
"learning_rate": 0.00019642072301991455,
|
| 603 |
+
"loss": 0.4456,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.1,
|
| 608 |
+
"grad_norm": 0.05555957555770874,
|
| 609 |
+
"learning_rate": 0.00019632523210698987,
|
| 610 |
+
"loss": 0.4382,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.1,
|
| 615 |
+
"grad_norm": 0.04606284573674202,
|
| 616 |
+
"learning_rate": 0.00019622850794636455,
|
| 617 |
+
"loss": 0.4411,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.1,
|
| 622 |
+
"grad_norm": 0.04605920985341072,
|
| 623 |
+
"learning_rate": 0.00019613055177639384,
|
| 624 |
+
"loss": 0.4326,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.1,
|
| 629 |
+
"grad_norm": 0.050325632095336914,
|
| 630 |
+
"learning_rate": 0.0001960313648512062,
|
| 631 |
+
"loss": 0.4338,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.1,
|
| 636 |
+
"grad_norm": 0.04921424016356468,
|
| 637 |
+
"learning_rate": 0.00019593094844068748,
|
| 638 |
+
"loss": 0.4316,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.1,
|
| 643 |
+
"grad_norm": 0.04333706200122833,
|
| 644 |
+
"learning_rate": 0.00019582930383046457,
|
| 645 |
+
"loss": 0.4441,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.1,
|
| 650 |
+
"grad_norm": 0.048454612493515015,
|
| 651 |
+
"learning_rate": 0.0001957264323218889,
|
| 652 |
+
"loss": 0.4382,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.1,
|
| 657 |
+
"grad_norm": 0.0541059784591198,
|
| 658 |
+
"learning_rate": 0.00019562233523201986,
|
| 659 |
+
"loss": 0.4328,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.11,
|
| 664 |
+
"grad_norm": 0.043696511536836624,
|
| 665 |
+
"learning_rate": 0.00019551701389360795,
|
| 666 |
+
"loss": 0.4335,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.11,
|
| 671 |
+
"grad_norm": 0.04407835751771927,
|
| 672 |
+
"learning_rate": 0.00019541046965507758,
|
| 673 |
+
"loss": 0.4327,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.11,
|
| 678 |
+
"grad_norm": 0.05477238819003105,
|
| 679 |
+
"learning_rate": 0.00019530270388050998,
|
| 680 |
+
"loss": 0.4294,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.11,
|
| 685 |
+
"grad_norm": 0.05609311908483505,
|
| 686 |
+
"learning_rate": 0.00019519371794962556,
|
| 687 |
+
"loss": 0.4305,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.11,
|
| 692 |
+
"grad_norm": 0.045145273208618164,
|
| 693 |
+
"learning_rate": 0.00019508351325776642,
|
| 694 |
+
"loss": 0.4395,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.11,
|
| 699 |
+
"grad_norm": 0.04475285857915878,
|
| 700 |
+
"learning_rate": 0.00019497209121587837,
|
| 701 |
+
"loss": 0.4284,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.11,
|
| 706 |
+
"grad_norm": 0.04405711591243744,
|
| 707 |
+
"learning_rate": 0.00019485945325049288,
|
| 708 |
+
"loss": 0.4214,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.11,
|
| 713 |
+
"grad_norm": 0.04461454227566719,
|
| 714 |
+
"learning_rate": 0.0001947456008037089,
|
| 715 |
+
"loss": 0.4154,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.11,
|
| 720 |
+
"grad_norm": 0.04791221395134926,
|
| 721 |
+
"learning_rate": 0.00019463053533317425,
|
| 722 |
+
"loss": 0.4248,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.12,
|
| 727 |
+
"grad_norm": 0.05543987452983856,
|
| 728 |
+
"learning_rate": 0.00019451425831206706,
|
| 729 |
+
"loss": 0.4303,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.12,
|
| 734 |
+
"grad_norm": 0.06330578774213791,
|
| 735 |
+
"learning_rate": 0.00019439677122907697,
|
| 736 |
+
"loss": 0.4274,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.12,
|
| 741 |
+
"grad_norm": 0.05569112300872803,
|
| 742 |
+
"learning_rate": 0.00019427807558838588,
|
| 743 |
+
"loss": 0.4234,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.12,
|
| 748 |
+
"grad_norm": 0.047680530697107315,
|
| 749 |
+
"learning_rate": 0.00019415817290964883,
|
| 750 |
+
"loss": 0.4155,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.12,
|
| 755 |
+
"grad_norm": 0.05214262008666992,
|
| 756 |
+
"learning_rate": 0.0001940370647279746,
|
| 757 |
+
"loss": 0.4224,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.12,
|
| 762 |
+
"grad_norm": 0.06332990527153015,
|
| 763 |
+
"learning_rate": 0.00019391475259390584,
|
| 764 |
+
"loss": 0.4233,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.12,
|
| 769 |
+
"grad_norm": 0.05726313218474388,
|
| 770 |
+
"learning_rate": 0.00019379123807339942,
|
| 771 |
+
"loss": 0.4118,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.12,
|
| 776 |
+
"grad_norm": 0.044936031103134155,
|
| 777 |
+
"learning_rate": 0.00019366652274780628,
|
| 778 |
+
"loss": 0.4296,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.12,
|
| 783 |
+
"grad_norm": 0.05117325484752655,
|
| 784 |
+
"learning_rate": 0.0001935406082138513,
|
| 785 |
+
"loss": 0.4287,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.13,
|
| 790 |
+
"grad_norm": 0.058542776852846146,
|
| 791 |
+
"learning_rate": 0.00019341349608361267,
|
| 792 |
+
"loss": 0.4213,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.13,
|
| 797 |
+
"grad_norm": 0.056066304445266724,
|
| 798 |
+
"learning_rate": 0.00019328518798450138,
|
| 799 |
+
"loss": 0.4174,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.13,
|
| 804 |
+
"grad_norm": 0.049762677401304245,
|
| 805 |
+
"learning_rate": 0.00019315568555924035,
|
| 806 |
+
"loss": 0.418,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.13,
|
| 811 |
+
"grad_norm": 0.043821126222610474,
|
| 812 |
+
"learning_rate": 0.00019302499046584348,
|
| 813 |
+
"loss": 0.4012,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.13,
|
| 818 |
+
"grad_norm": 0.05036221817135811,
|
| 819 |
+
"learning_rate": 0.00019289310437759427,
|
| 820 |
+
"loss": 0.4237,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.13,
|
| 825 |
+
"grad_norm": 0.050889529287815094,
|
| 826 |
+
"learning_rate": 0.00019276002898302447,
|
| 827 |
+
"loss": 0.4144,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.13,
|
| 832 |
+
"grad_norm": 0.04269757494330406,
|
| 833 |
+
"learning_rate": 0.0001926257659858925,
|
| 834 |
+
"loss": 0.4078,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.13,
|
| 839 |
+
"grad_norm": 0.04927165433764458,
|
| 840 |
+
"learning_rate": 0.00019249031710516162,
|
| 841 |
+
"loss": 0.4155,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.14,
|
| 846 |
+
"grad_norm": 0.05124311521649361,
|
| 847 |
+
"learning_rate": 0.00019235368407497788,
|
| 848 |
+
"loss": 0.3966,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.14,
|
| 853 |
+
"grad_norm": 0.04073040187358856,
|
| 854 |
+
"learning_rate": 0.00019221586864464786,
|
| 855 |
+
"loss": 0.4064,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.14,
|
| 860 |
+
"grad_norm": 0.04988453537225723,
|
| 861 |
+
"learning_rate": 0.00019207687257861655,
|
| 862 |
+
"loss": 0.4197,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.14,
|
| 867 |
+
"grad_norm": 0.05227258801460266,
|
| 868 |
+
"learning_rate": 0.0001919366976564444,
|
| 869 |
+
"loss": 0.414,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.14,
|
| 874 |
+
"grad_norm": 0.0466819666326046,
|
| 875 |
+
"learning_rate": 0.00019179534567278475,
|
| 876 |
+
"loss": 0.4173,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.14,
|
| 881 |
+
"grad_norm": 0.047633491456508636,
|
| 882 |
+
"learning_rate": 0.00019165281843736085,
|
| 883 |
+
"loss": 0.4085,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.14,
|
| 888 |
+
"grad_norm": 0.05280464142560959,
|
| 889 |
+
"learning_rate": 0.00019150911777494258,
|
| 890 |
+
"loss": 0.4051,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.14,
|
| 895 |
+
"grad_norm": 0.052302148193120956,
|
| 896 |
+
"learning_rate": 0.00019136424552532318,
|
| 897 |
+
"loss": 0.42,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.14,
|
| 902 |
+
"grad_norm": 0.04875241965055466,
|
| 903 |
+
"learning_rate": 0.00019121820354329577,
|
| 904 |
+
"loss": 0.4258,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.15,
|
| 909 |
+
"grad_norm": 0.04654408246278763,
|
| 910 |
+
"learning_rate": 0.0001910709936986293,
|
| 911 |
+
"loss": 0.409,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.15,
|
| 916 |
+
"grad_norm": 0.05745020881295204,
|
| 917 |
+
"learning_rate": 0.00019092261787604492,
|
| 918 |
+
"loss": 0.4059,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.15,
|
| 923 |
+
"grad_norm": 0.06945241987705231,
|
| 924 |
+
"learning_rate": 0.00019077307797519183,
|
| 925 |
+
"loss": 0.4038,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.15,
|
| 930 |
+
"grad_norm": 0.06346461176872253,
|
| 931 |
+
"learning_rate": 0.00019062237591062272,
|
| 932 |
+
"loss": 0.4031,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.15,
|
| 937 |
+
"grad_norm": 0.058026187121868134,
|
| 938 |
+
"learning_rate": 0.00019047051361176953,
|
| 939 |
+
"loss": 0.4126,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.15,
|
| 944 |
+
"grad_norm": 0.04755179584026337,
|
| 945 |
+
"learning_rate": 0.0001903174930229185,
|
| 946 |
+
"loss": 0.4209,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.15,
|
| 951 |
+
"grad_norm": 0.05765068158507347,
|
| 952 |
+
"learning_rate": 0.0001901633161031856,
|
| 953 |
+
"loss": 0.4067,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.15,
|
| 958 |
+
"grad_norm": 0.05687811225652695,
|
| 959 |
+
"learning_rate": 0.000190007984826491,
|
| 960 |
+
"loss": 0.3975,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.15,
|
| 965 |
+
"grad_norm": 0.04930473491549492,
|
| 966 |
+
"learning_rate": 0.0001898515011815343,
|
| 967 |
+
"loss": 0.4146,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.16,
|
| 972 |
+
"grad_norm": 0.05147051811218262,
|
| 973 |
+
"learning_rate": 0.0001896938671717687,
|
| 974 |
+
"loss": 0.4035,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.16,
|
| 979 |
+
"grad_norm": 0.05680418014526367,
|
| 980 |
+
"learning_rate": 0.0001895350848153754,
|
| 981 |
+
"loss": 0.4049,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.16,
|
| 986 |
+
"grad_norm": 0.0444297268986702,
|
| 987 |
+
"learning_rate": 0.00018937515614523797,
|
| 988 |
+
"loss": 0.4085,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.16,
|
| 993 |
+
"grad_norm": 0.05083802342414856,
|
| 994 |
+
"learning_rate": 0.00018921408320891612,
|
| 995 |
+
"loss": 0.4036,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.16,
|
| 1000 |
+
"grad_norm": 0.04978756606578827,
|
| 1001 |
+
"learning_rate": 0.00018905186806861957,
|
| 1002 |
+
"loss": 0.4058,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.16,
|
| 1007 |
+
"grad_norm": 0.04963681101799011,
|
| 1008 |
+
"learning_rate": 0.00018888851280118155,
|
| 1009 |
+
"loss": 0.3977,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.16,
|
| 1014 |
+
"grad_norm": 0.0466095507144928,
|
| 1015 |
+
"learning_rate": 0.00018872401949803237,
|
| 1016 |
+
"loss": 0.3945,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.16,
|
| 1021 |
+
"grad_norm": 0.04972768574953079,
|
| 1022 |
+
"learning_rate": 0.00018855839026517257,
|
| 1023 |
+
"loss": 0.4151,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.16,
|
| 1028 |
+
"grad_norm": 0.054370637983083725,
|
| 1029 |
+
"learning_rate": 0.0001883916272231459,
|
| 1030 |
+
"loss": 0.3944,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.17,
|
| 1035 |
+
"grad_norm": 0.054699357599020004,
|
| 1036 |
+
"learning_rate": 0.00018822373250701224,
|
| 1037 |
+
"loss": 0.3989,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.17,
|
| 1042 |
+
"grad_norm": 0.054452769458293915,
|
| 1043 |
+
"learning_rate": 0.00018805470826632024,
|
| 1044 |
+
"loss": 0.3984,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.17,
|
| 1049 |
+
"grad_norm": 0.04596908017992973,
|
| 1050 |
+
"learning_rate": 0.00018788455666507981,
|
| 1051 |
+
"loss": 0.4018,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.17,
|
| 1056 |
+
"grad_norm": 0.054354868829250336,
|
| 1057 |
+
"learning_rate": 0.00018771327988173435,
|
| 1058 |
+
"loss": 0.3985,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.17,
|
| 1063 |
+
"grad_norm": 0.05570242181420326,
|
| 1064 |
+
"learning_rate": 0.00018754088010913304,
|
| 1065 |
+
"loss": 0.3818,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.17,
|
| 1070 |
+
"grad_norm": 0.054722048342227936,
|
| 1071 |
+
"learning_rate": 0.00018736735955450251,
|
| 1072 |
+
"loss": 0.4111,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.17,
|
| 1077 |
+
"grad_norm": 0.04620000347495079,
|
| 1078 |
+
"learning_rate": 0.00018719272043941882,
|
| 1079 |
+
"loss": 0.3949,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.17,
|
| 1084 |
+
"grad_norm": 0.048443205654621124,
|
| 1085 |
+
"learning_rate": 0.00018701696499977884,
|
| 1086 |
+
"loss": 0.3856,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.17,
|
| 1091 |
+
"grad_norm": 0.06628945469856262,
|
| 1092 |
+
"learning_rate": 0.00018684009548577168,
|
| 1093 |
+
"loss": 0.4048,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.18,
|
| 1098 |
+
"grad_norm": 0.05339967459440231,
|
| 1099 |
+
"learning_rate": 0.00018666211416184999,
|
| 1100 |
+
"loss": 0.3894,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.18,
|
| 1105 |
+
"grad_norm": 0.04650304839015007,
|
| 1106 |
+
"learning_rate": 0.00018648302330670082,
|
| 1107 |
+
"loss": 0.4004,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.18,
|
| 1112 |
+
"grad_norm": 0.05634591728448868,
|
| 1113 |
+
"learning_rate": 0.00018630282521321645,
|
| 1114 |
+
"loss": 0.4033,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.18,
|
| 1119 |
+
"grad_norm": 0.048666685819625854,
|
| 1120 |
+
"learning_rate": 0.00018612152218846513,
|
| 1121 |
+
"loss": 0.399,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.18,
|
| 1126 |
+
"grad_norm": 0.04597772657871246,
|
| 1127 |
+
"learning_rate": 0.0001859391165536615,
|
| 1128 |
+
"loss": 0.3931,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.18,
|
| 1133 |
+
"grad_norm": 0.0526028610765934,
|
| 1134 |
+
"learning_rate": 0.00018575561064413689,
|
| 1135 |
+
"loss": 0.3879,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.18,
|
| 1140 |
+
"grad_norm": 0.05867009237408638,
|
| 1141 |
+
"learning_rate": 0.00018557100680930937,
|
| 1142 |
+
"loss": 0.3905,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.18,
|
| 1147 |
+
"grad_norm": 0.05077454075217247,
|
| 1148 |
+
"learning_rate": 0.00018538530741265364,
|
| 1149 |
+
"loss": 0.395,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.18,
|
| 1154 |
+
"grad_norm": 0.0461389385163784,
|
| 1155 |
+
"learning_rate": 0.00018519851483167097,
|
| 1156 |
+
"loss": 0.4016,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.19,
|
| 1161 |
+
"grad_norm": 0.059010252356529236,
|
| 1162 |
+
"learning_rate": 0.00018501063145785846,
|
| 1163 |
+
"loss": 0.3823,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.19,
|
| 1168 |
+
"grad_norm": 0.06437338888645172,
|
| 1169 |
+
"learning_rate": 0.00018482165969667874,
|
| 1170 |
+
"loss": 0.3918,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.19,
|
| 1175 |
+
"grad_norm": 0.04585932940244675,
|
| 1176 |
+
"learning_rate": 0.00018463160196752887,
|
| 1177 |
+
"loss": 0.3808,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.19,
|
| 1182 |
+
"grad_norm": 0.05361521616578102,
|
| 1183 |
+
"learning_rate": 0.00018444046070370963,
|
| 1184 |
+
"loss": 0.3858,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.19,
|
| 1189 |
+
"grad_norm": 0.05653822794556618,
|
| 1190 |
+
"learning_rate": 0.00018424823835239417,
|
| 1191 |
+
"loss": 0.3785,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.19,
|
| 1196 |
+
"grad_norm": 0.04439689964056015,
|
| 1197 |
+
"learning_rate": 0.0001840549373745968,
|
| 1198 |
+
"loss": 0.3894,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.19,
|
| 1203 |
+
"grad_norm": 0.05564529448747635,
|
| 1204 |
+
"learning_rate": 0.00018386056024514137,
|
| 1205 |
+
"loss": 0.3883,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.19,
|
| 1210 |
+
"grad_norm": 0.06035888195037842,
|
| 1211 |
+
"learning_rate": 0.00018366510945262972,
|
| 1212 |
+
"loss": 0.3855,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.19,
|
| 1217 |
+
"grad_norm": 0.044238511472940445,
|
| 1218 |
+
"learning_rate": 0.0001834685874994098,
|
| 1219 |
+
"loss": 0.3934,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.2,
|
| 1224 |
+
"grad_norm": 0.050235260277986526,
|
| 1225 |
+
"learning_rate": 0.00018327099690154344,
|
| 1226 |
+
"loss": 0.3819,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.2,
|
| 1231 |
+
"grad_norm": 0.051336683332920074,
|
| 1232 |
+
"learning_rate": 0.00018307234018877434,
|
| 1233 |
+
"loss": 0.3897,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.2,
|
| 1238 |
+
"grad_norm": 0.045052576810121536,
|
| 1239 |
+
"learning_rate": 0.0001828726199044957,
|
| 1240 |
+
"loss": 0.3822,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.2,
|
| 1245 |
+
"grad_norm": 0.05162283405661583,
|
| 1246 |
+
"learning_rate": 0.00018267183860571753,
|
| 1247 |
+
"loss": 0.4047,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.2,
|
| 1252 |
+
"grad_norm": 0.0488157793879509,
|
| 1253 |
+
"learning_rate": 0.00018246999886303383,
|
| 1254 |
+
"loss": 0.3947,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.2,
|
| 1259 |
+
"grad_norm": 0.04454487934708595,
|
| 1260 |
+
"learning_rate": 0.00018226710326059006,
|
| 1261 |
+
"loss": 0.3942,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.2,
|
| 1266 |
+
"grad_norm": 0.0500001423060894,
|
| 1267 |
+
"learning_rate": 0.0001820631543960496,
|
| 1268 |
+
"loss": 0.3826,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.2,
|
| 1273 |
+
"grad_norm": 0.04919865354895592,
|
| 1274 |
+
"learning_rate": 0.00018185815488056076,
|
| 1275 |
+
"loss": 0.3791,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.2,
|
| 1280 |
+
"grad_norm": 0.04547140747308731,
|
| 1281 |
+
"learning_rate": 0.00018165210733872336,
|
| 1282 |
+
"loss": 0.3879,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.21,
|
| 1287 |
+
"grad_norm": 0.044622063636779785,
|
| 1288 |
+
"learning_rate": 0.00018144501440855496,
|
| 1289 |
+
"loss": 0.3778,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.21,
|
| 1294 |
+
"grad_norm": 0.04467932507395744,
|
| 1295 |
+
"learning_rate": 0.00018123687874145721,
|
| 1296 |
+
"loss": 0.3994,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.21,
|
| 1301 |
+
"grad_norm": 0.04281982406973839,
|
| 1302 |
+
"learning_rate": 0.0001810277030021819,
|
| 1303 |
+
"loss": 0.3817,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.21,
|
| 1308 |
+
"grad_norm": 0.05303504317998886,
|
| 1309 |
+
"learning_rate": 0.00018081748986879679,
|
| 1310 |
+
"loss": 0.3749,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.21,
|
| 1315 |
+
"grad_norm": 0.046573616564273834,
|
| 1316 |
+
"learning_rate": 0.00018060624203265134,
|
| 1317 |
+
"loss": 0.3866,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.21,
|
| 1322 |
+
"grad_norm": 0.044320229440927505,
|
| 1323 |
+
"learning_rate": 0.00018039396219834237,
|
| 1324 |
+
"loss": 0.3732,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.21,
|
| 1329 |
+
"grad_norm": 0.05708359181880951,
|
| 1330 |
+
"learning_rate": 0.00018018065308367912,
|
| 1331 |
+
"loss": 0.3863,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.21,
|
| 1336 |
+
"grad_norm": 0.045029208064079285,
|
| 1337 |
+
"learning_rate": 0.00017996631741964888,
|
| 1338 |
+
"loss": 0.3862,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.21,
|
| 1343 |
+
"grad_norm": 0.055195923894643784,
|
| 1344 |
+
"learning_rate": 0.00017975095795038165,
|
| 1345 |
+
"loss": 0.3835,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.22,
|
| 1350 |
+
"grad_norm": 0.048293352127075195,
|
| 1351 |
+
"learning_rate": 0.00017953457743311523,
|
| 1352 |
+
"loss": 0.374,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.22,
|
| 1357 |
+
"grad_norm": 0.04677055403590202,
|
| 1358 |
+
"learning_rate": 0.00017931717863815987,
|
| 1359 |
+
"loss": 0.377,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.22,
|
| 1364 |
+
"grad_norm": 0.04955766722559929,
|
| 1365 |
+
"learning_rate": 0.00017909876434886273,
|
| 1366 |
+
"loss": 0.3808,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.22,
|
| 1371 |
+
"grad_norm": 0.04526973515748978,
|
| 1372 |
+
"learning_rate": 0.00017887933736157233,
|
| 1373 |
+
"loss": 0.3796,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.22,
|
| 1378 |
+
"grad_norm": 0.043622203171253204,
|
| 1379 |
+
"learning_rate": 0.00017865890048560277,
|
| 1380 |
+
"loss": 0.376,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.22,
|
| 1385 |
+
"grad_norm": 0.046581387519836426,
|
| 1386 |
+
"learning_rate": 0.0001784374565431976,
|
| 1387 |
+
"loss": 0.3716,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.22,
|
| 1392 |
+
"grad_norm": 0.04433497413992882,
|
| 1393 |
+
"learning_rate": 0.00017821500836949386,
|
| 1394 |
+
"loss": 0.3715,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.22,
|
| 1399 |
+
"grad_norm": 0.04146367311477661,
|
| 1400 |
+
"learning_rate": 0.00017799155881248572,
|
| 1401 |
+
"loss": 0.3809,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.23,
|
| 1406 |
+
"grad_norm": 0.045288585126399994,
|
| 1407 |
+
"learning_rate": 0.000177767110732988,
|
| 1408 |
+
"loss": 0.3885,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.23,
|
| 1413 |
+
"grad_norm": 0.04070120304822922,
|
| 1414 |
+
"learning_rate": 0.00017754166700459958,
|
| 1415 |
+
"loss": 0.3713,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.23,
|
| 1420 |
+
"grad_norm": 0.042820919305086136,
|
| 1421 |
+
"learning_rate": 0.00017731523051366658,
|
| 1422 |
+
"loss": 0.3839,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.23,
|
| 1427 |
+
"grad_norm": 0.04416365176439285,
|
| 1428 |
+
"learning_rate": 0.00017708780415924539,
|
| 1429 |
+
"loss": 0.3728,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.23,
|
| 1434 |
+
"grad_norm": 0.04461952671408653,
|
| 1435 |
+
"learning_rate": 0.00017685939085306562,
|
| 1436 |
+
"loss": 0.373,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.23,
|
| 1441 |
+
"grad_norm": 0.04675828292965889,
|
| 1442 |
+
"learning_rate": 0.00017662999351949278,
|
| 1443 |
+
"loss": 0.3711,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.23,
|
| 1448 |
+
"grad_norm": 0.04258272796869278,
|
| 1449 |
+
"learning_rate": 0.00017639961509549078,
|
| 1450 |
+
"loss": 0.3782,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.23,
|
| 1455 |
+
"grad_norm": 0.04638506844639778,
|
| 1456 |
+
"learning_rate": 0.00017616825853058443,
|
| 1457 |
+
"loss": 0.3592,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.23,
|
| 1462 |
+
"grad_norm": 0.04781416058540344,
|
| 1463 |
+
"learning_rate": 0.00017593592678682166,
|
| 1464 |
+
"loss": 0.383,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.24,
|
| 1469 |
+
"grad_norm": 0.04813629388809204,
|
| 1470 |
+
"learning_rate": 0.00017570262283873552,
|
| 1471 |
+
"loss": 0.3775,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.24,
|
| 1476 |
+
"grad_norm": 0.046996332705020905,
|
| 1477 |
+
"learning_rate": 0.00017546834967330617,
|
| 1478 |
+
"loss": 0.3815,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.24,
|
| 1483 |
+
"grad_norm": 0.04889595881104469,
|
| 1484 |
+
"learning_rate": 0.00017523311028992268,
|
| 1485 |
+
"loss": 0.3636,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.24,
|
| 1490 |
+
"grad_norm": 0.04298345744609833,
|
| 1491 |
+
"learning_rate": 0.00017499690770034443,
|
| 1492 |
+
"loss": 0.3672,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.24,
|
| 1497 |
+
"grad_norm": 0.04219110682606697,
|
| 1498 |
+
"learning_rate": 0.00017475974492866278,
|
| 1499 |
+
"loss": 0.3801,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.24,
|
| 1504 |
+
"grad_norm": 0.051573265343904495,
|
| 1505 |
+
"learning_rate": 0.00017452162501126227,
|
| 1506 |
+
"loss": 0.3778,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.24,
|
| 1511 |
+
"grad_norm": 0.048954349011182785,
|
| 1512 |
+
"learning_rate": 0.00017428255099678167,
|
| 1513 |
+
"loss": 0.3849,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.24,
|
| 1518 |
+
"grad_norm": 0.042610183358192444,
|
| 1519 |
+
"learning_rate": 0.0001740425259460751,
|
| 1520 |
+
"loss": 0.3682,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.24,
|
| 1525 |
+
"grad_norm": 0.04517417773604393,
|
| 1526 |
+
"learning_rate": 0.00017380155293217264,
|
| 1527 |
+
"loss": 0.3827,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.25,
|
| 1532 |
+
"grad_norm": 0.04968888312578201,
|
| 1533 |
+
"learning_rate": 0.00017355963504024123,
|
| 1534 |
+
"loss": 0.3821,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.25,
|
| 1539 |
+
"grad_norm": 0.051313381642103195,
|
| 1540 |
+
"learning_rate": 0.0001733167753675449,
|
| 1541 |
+
"loss": 0.381,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.25,
|
| 1546 |
+
"grad_norm": 0.044351302087306976,
|
| 1547 |
+
"learning_rate": 0.0001730729770234054,
|
| 1548 |
+
"loss": 0.381,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.25,
|
| 1553 |
+
"grad_norm": 0.03970547392964363,
|
| 1554 |
+
"learning_rate": 0.00017282824312916218,
|
| 1555 |
+
"loss": 0.3698,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.25,
|
| 1560 |
+
"grad_norm": 0.04822370782494545,
|
| 1561 |
+
"learning_rate": 0.00017258257681813244,
|
| 1562 |
+
"loss": 0.3838,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.25,
|
| 1567 |
+
"grad_norm": 0.045927174389362335,
|
| 1568 |
+
"learning_rate": 0.0001723359812355712,
|
| 1569 |
+
"loss": 0.3662,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.25,
|
| 1574 |
+
"grad_norm": 0.042983219027519226,
|
| 1575 |
+
"learning_rate": 0.00017208845953863076,
|
| 1576 |
+
"loss": 0.3574,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.25,
|
| 1581 |
+
"grad_norm": 0.0422198586165905,
|
| 1582 |
+
"learning_rate": 0.0001718400148963206,
|
| 1583 |
+
"loss": 0.3559,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.25,
|
| 1588 |
+
"grad_norm": 0.042307570576667786,
|
| 1589 |
+
"learning_rate": 0.00017159065048946644,
|
| 1590 |
+
"loss": 0.3834,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.26,
|
| 1595 |
+
"grad_norm": 0.04701109230518341,
|
| 1596 |
+
"learning_rate": 0.0001713403695106698,
|
| 1597 |
+
"loss": 0.3718,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.26,
|
| 1602 |
+
"grad_norm": 0.04007503017783165,
|
| 1603 |
+
"learning_rate": 0.00017108917516426704,
|
| 1604 |
+
"loss": 0.3785,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.26,
|
| 1609 |
+
"grad_norm": 0.04560061916708946,
|
| 1610 |
+
"learning_rate": 0.00017083707066628832,
|
| 1611 |
+
"loss": 0.3713,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.26,
|
| 1616 |
+
"grad_norm": 0.04315731301903725,
|
| 1617 |
+
"learning_rate": 0.00017058405924441636,
|
| 1618 |
+
"loss": 0.3702,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.26,
|
| 1623 |
+
"grad_norm": 0.040260497480630875,
|
| 1624 |
+
"learning_rate": 0.0001703301441379453,
|
| 1625 |
+
"loss": 0.367,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.26,
|
| 1630 |
+
"grad_norm": 0.04882992431521416,
|
| 1631 |
+
"learning_rate": 0.000170075328597739,
|
| 1632 |
+
"loss": 0.3737,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.26,
|
| 1637 |
+
"grad_norm": 0.04410382732748985,
|
| 1638 |
+
"learning_rate": 0.0001698196158861896,
|
| 1639 |
+
"loss": 0.3625,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.26,
|
| 1644 |
+
"grad_norm": 0.04889338091015816,
|
| 1645 |
+
"learning_rate": 0.00016956300927717575,
|
| 1646 |
+
"loss": 0.3697,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.26,
|
| 1651 |
+
"grad_norm": 0.044603537768125534,
|
| 1652 |
+
"learning_rate": 0.00016930551205602043,
|
| 1653 |
+
"loss": 0.3729,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.27,
|
| 1658 |
+
"grad_norm": 0.0539550743997097,
|
| 1659 |
+
"learning_rate": 0.00016904712751944931,
|
| 1660 |
+
"loss": 0.3625,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.27,
|
| 1665 |
+
"grad_norm": 0.04753349721431732,
|
| 1666 |
+
"learning_rate": 0.00016878785897554818,
|
| 1667 |
+
"loss": 0.3662,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.27,
|
| 1672 |
+
"grad_norm": 0.04425463080406189,
|
| 1673 |
+
"learning_rate": 0.0001685277097437208,
|
| 1674 |
+
"loss": 0.3595,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.27,
|
| 1679 |
+
"grad_norm": 0.04160892590880394,
|
| 1680 |
+
"learning_rate": 0.0001682666831546463,
|
| 1681 |
+
"loss": 0.3679,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.27,
|
| 1686 |
+
"grad_norm": 0.04600003361701965,
|
| 1687 |
+
"learning_rate": 0.0001680047825502366,
|
| 1688 |
+
"loss": 0.3702,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.27,
|
| 1693 |
+
"grad_norm": 0.03887678310275078,
|
| 1694 |
+
"learning_rate": 0.00016774201128359357,
|
| 1695 |
+
"loss": 0.3633,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.27,
|
| 1700 |
+
"grad_norm": 0.0477156862616539,
|
| 1701 |
+
"learning_rate": 0.00016747837271896622,
|
| 1702 |
+
"loss": 0.3702,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.27,
|
| 1707 |
+
"grad_norm": 0.04244072362780571,
|
| 1708 |
+
"learning_rate": 0.00016721387023170737,
|
| 1709 |
+
"loss": 0.3668,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.27,
|
| 1714 |
+
"grad_norm": 0.04049496725201607,
|
| 1715 |
+
"learning_rate": 0.0001669485072082308,
|
| 1716 |
+
"loss": 0.3785,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.28,
|
| 1721 |
+
"grad_norm": 0.04432998597621918,
|
| 1722 |
+
"learning_rate": 0.00016668228704596756,
|
| 1723 |
+
"loss": 0.3703,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.28,
|
| 1728 |
+
"grad_norm": 0.0432085320353508,
|
| 1729 |
+
"learning_rate": 0.00016641521315332265,
|
| 1730 |
+
"loss": 0.3615,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.28,
|
| 1735 |
+
"grad_norm": 0.03820549696683884,
|
| 1736 |
+
"learning_rate": 0.00016614728894963135,
|
| 1737 |
+
"loss": 0.3483,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.28,
|
| 1742 |
+
"grad_norm": 0.04436295107007027,
|
| 1743 |
+
"learning_rate": 0.00016587851786511543,
|
| 1744 |
+
"loss": 0.3661,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.28,
|
| 1749 |
+
"grad_norm": 0.04371733218431473,
|
| 1750 |
+
"learning_rate": 0.00016560890334083926,
|
| 1751 |
+
"loss": 0.3503,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.28,
|
| 1756 |
+
"grad_norm": 0.039205193519592285,
|
| 1757 |
+
"learning_rate": 0.00016533844882866568,
|
| 1758 |
+
"loss": 0.3482,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.28,
|
| 1763 |
+
"grad_norm": 0.04308384284377098,
|
| 1764 |
+
"learning_rate": 0.00016506715779121187,
|
| 1765 |
+
"loss": 0.373,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.28,
|
| 1770 |
+
"grad_norm": 0.040143441408872604,
|
| 1771 |
+
"learning_rate": 0.00016479503370180507,
|
| 1772 |
+
"loss": 0.3609,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.28,
|
| 1777 |
+
"grad_norm": 0.03845199570059776,
|
| 1778 |
+
"learning_rate": 0.000164522080044438,
|
| 1779 |
+
"loss": 0.3644,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.29,
|
| 1784 |
+
"grad_norm": 0.039730221033096313,
|
| 1785 |
+
"learning_rate": 0.00016424830031372425,
|
| 1786 |
+
"loss": 0.3514,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.29,
|
| 1791 |
+
"grad_norm": 0.04021477699279785,
|
| 1792 |
+
"learning_rate": 0.00016397369801485366,
|
| 1793 |
+
"loss": 0.3566,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.29,
|
| 1798 |
+
"grad_norm": 0.03929613530635834,
|
| 1799 |
+
"learning_rate": 0.00016369827666354745,
|
| 1800 |
+
"loss": 0.3649,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.29,
|
| 1805 |
+
"grad_norm": 0.040966227650642395,
|
| 1806 |
+
"learning_rate": 0.0001634220397860129,
|
| 1807 |
+
"loss": 0.3661,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.29,
|
| 1812 |
+
"grad_norm": 0.036787159740924835,
|
| 1813 |
+
"learning_rate": 0.0001631449909188987,
|
| 1814 |
+
"loss": 0.3572,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.29,
|
| 1819 |
+
"grad_norm": 0.039864350110292435,
|
| 1820 |
+
"learning_rate": 0.00016286713360924918,
|
| 1821 |
+
"loss": 0.3593,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.29,
|
| 1826 |
+
"grad_norm": 0.039622630923986435,
|
| 1827 |
+
"learning_rate": 0.00016258847141445928,
|
| 1828 |
+
"loss": 0.3711,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.29,
|
| 1833 |
+
"grad_norm": 0.03840857744216919,
|
| 1834 |
+
"learning_rate": 0.00016230900790222878,
|
| 1835 |
+
"loss": 0.3537,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.29,
|
| 1840 |
+
"grad_norm": 0.03800921142101288,
|
| 1841 |
+
"learning_rate": 0.00016202874665051674,
|
| 1842 |
+
"loss": 0.3662,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.3,
|
| 1847 |
+
"grad_norm": 0.03894530236721039,
|
| 1848 |
+
"learning_rate": 0.0001617476912474956,
|
| 1849 |
+
"loss": 0.3633,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.3,
|
| 1854 |
+
"grad_norm": 0.04486812278628349,
|
| 1855 |
+
"learning_rate": 0.00016146584529150526,
|
| 1856 |
+
"loss": 0.3594,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.3,
|
| 1861 |
+
"grad_norm": 0.0394977331161499,
|
| 1862 |
+
"learning_rate": 0.00016118321239100712,
|
| 1863 |
+
"loss": 0.3473,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.3,
|
| 1868 |
+
"grad_norm": 0.03960977867245674,
|
| 1869 |
+
"learning_rate": 0.0001608997961645377,
|
| 1870 |
+
"loss": 0.363,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.3,
|
| 1875 |
+
"grad_norm": 0.04547852650284767,
|
| 1876 |
+
"learning_rate": 0.00016061560024066248,
|
| 1877 |
+
"loss": 0.3698,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
}
|
| 1880 |
+
],
|
| 1881 |
+
"logging_steps": 1,
|
| 1882 |
+
"max_steps": 888,
|
| 1883 |
+
"num_input_tokens_seen": 0,
|
| 1884 |
+
"num_train_epochs": 1,
|
| 1885 |
+
"save_steps": 89,
|
| 1886 |
+
"total_flos": 5.32595180788777e+18,
|
| 1887 |
+
"train_batch_size": 14,
|
| 1888 |
+
"trial_name": null,
|
| 1889 |
+
"trial_params": null
|
| 1890 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0441fddfec498f33a86d551b67802f8f8fbf45a9463d322464e8ee1ed737775
|
| 3 |
+
size 5688
|