Training in progress, step 385, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +31 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +23 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +73 -0
- last-checkpoint/trainer_state.json +2744 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: beomi/polyglot-ko-12.8b-safetensors
|
| 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
|
last-checkpoint/adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "beomi/polyglot-ko-12.8b-safetensors",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"query_key_value",
|
| 24 |
+
"dense_4h_to_h",
|
| 25 |
+
"dense_h_to_4h",
|
| 26 |
+
"dense"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0675a27ef3d96ab44e6ebd079be5530168710017a48f3e2e02053473cf990f8
|
| 3 |
+
size 104902272
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1fd95ea42653b72693d47208698df28b2357bf072eddac771f7a93233f994c1
|
| 3 |
+
size 53623316
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d46c42c306f63e31b60c47c81a26311528b02cfebf6f431748382e6ff5912c6
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7907d50db90844f248b22e6ade47b806b24b4ec4aa7121507687d73e6c6190
|
| 3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|sep|>",
|
| 5 |
+
"<|acc|>",
|
| 6 |
+
"<|tel|>",
|
| 7 |
+
"<|rrn|>"
|
| 8 |
+
],
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<|unused0|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|unused1|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<|endoftext|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<|sep|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"30000": {
|
| 36 |
+
"content": "<|acc|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30001": {
|
| 44 |
+
"content": "<|tel|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"30002": {
|
| 52 |
+
"content": "<|rrn|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"<|endoftext|>",
|
| 62 |
+
"<|sep|>",
|
| 63 |
+
"<|acc|>",
|
| 64 |
+
"<|tel|>",
|
| 65 |
+
"<|rrn|>"
|
| 66 |
+
],
|
| 67 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 68 |
+
"clean_up_tokenization_spaces": true,
|
| 69 |
+
"eos_token": "<|endoftext|>",
|
| 70 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 71 |
+
"pad_token": "<|endoftext|>",
|
| 72 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 73 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,2744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03079384123175365,
|
| 5 |
+
"eval_steps": 385,
|
| 6 |
+
"global_step": 385,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 7.998400319936013e-05,
|
| 13 |
+
"grad_norm": 1.0834295749664307,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 8.3241,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 7.998400319936013e-05,
|
| 20 |
+
"eval_loss": 1.843304991722107,
|
| 21 |
+
"eval_runtime": 289.2804,
|
| 22 |
+
"eval_samples_per_second": 18.2,
|
| 23 |
+
"eval_steps_per_second": 9.102,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00015996800639872026,
|
| 28 |
+
"grad_norm": 1.1767560243606567,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 7.4616,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0002399520095980804,
|
| 35 |
+
"grad_norm": 1.1885181665420532,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 9.0656,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0003199360127974405,
|
| 42 |
+
"grad_norm": 0.9075803756713867,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 7.0921,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0003999200159968006,
|
| 49 |
+
"grad_norm": 1.4569883346557617,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 9.2885,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0004799040191961608,
|
| 56 |
+
"grad_norm": 1.3345720767974854,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 6.484,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0005598880223955209,
|
| 63 |
+
"grad_norm": 1.5282152891159058,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 6.8528,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.000639872025594881,
|
| 70 |
+
"grad_norm": 2.0517117977142334,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 6.8443,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0007198560287942411,
|
| 77 |
+
"grad_norm": 2.188291311264038,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 7.3742,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0007998400319936012,
|
| 84 |
+
"grad_norm": 2.3675291538238525,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 7.1504,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0008798240351929614,
|
| 91 |
+
"grad_norm": 2.468874931335449,
|
| 92 |
+
"learning_rate": 0.0001999997891921711,
|
| 93 |
+
"loss": 4.3571,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0009598080383923216,
|
| 98 |
+
"grad_norm": 3.100978136062622,
|
| 99 |
+
"learning_rate": 0.0001999991567695732,
|
| 100 |
+
"loss": 5.447,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0010397920415916816,
|
| 105 |
+
"grad_norm": 3.456265687942505,
|
| 106 |
+
"learning_rate": 0.0001999981027348727,
|
| 107 |
+
"loss": 6.7931,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0011197760447910418,
|
| 112 |
+
"grad_norm": 3.2227530479431152,
|
| 113 |
+
"learning_rate": 0.00019999662709251355,
|
| 114 |
+
"loss": 5.6123,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0011997600479904018,
|
| 119 |
+
"grad_norm": 4.164862632751465,
|
| 120 |
+
"learning_rate": 0.00019999472984871732,
|
| 121 |
+
"loss": 5.619,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.001279744051189762,
|
| 126 |
+
"grad_norm": 4.771204471588135,
|
| 127 |
+
"learning_rate": 0.00019999241101148306,
|
| 128 |
+
"loss": 6.6284,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0013597280543891223,
|
| 133 |
+
"grad_norm": 5.408437728881836,
|
| 134 |
+
"learning_rate": 0.00019998967059058737,
|
| 135 |
+
"loss": 6.9675,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.0014397120575884823,
|
| 140 |
+
"grad_norm": 4.746880531311035,
|
| 141 |
+
"learning_rate": 0.0001999865085975843,
|
| 142 |
+
"loss": 5.3069,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0015196960607878425,
|
| 147 |
+
"grad_norm": 3.782351493835449,
|
| 148 |
+
"learning_rate": 0.00019998292504580528,
|
| 149 |
+
"loss": 4.9249,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0015996800639872025,
|
| 154 |
+
"grad_norm": 4.084463119506836,
|
| 155 |
+
"learning_rate": 0.00019997891995035912,
|
| 156 |
+
"loss": 4.7503,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0016796640671865627,
|
| 161 |
+
"grad_norm": 4.680345058441162,
|
| 162 |
+
"learning_rate": 0.00019997449332813201,
|
| 163 |
+
"loss": 5.6088,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.0017596480703859227,
|
| 168 |
+
"grad_norm": 4.239553451538086,
|
| 169 |
+
"learning_rate": 0.0001999696451977872,
|
| 170 |
+
"loss": 6.5651,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.001839632073585283,
|
| 175 |
+
"grad_norm": 3.8252408504486084,
|
| 176 |
+
"learning_rate": 0.00019996437557976516,
|
| 177 |
+
"loss": 3.6374,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0019196160767846432,
|
| 182 |
+
"grad_norm": 4.3223114013671875,
|
| 183 |
+
"learning_rate": 0.00019995868449628346,
|
| 184 |
+
"loss": 5.379,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.001999600079984003,
|
| 189 |
+
"grad_norm": 4.155852794647217,
|
| 190 |
+
"learning_rate": 0.0001999525719713366,
|
| 191 |
+
"loss": 4.4252,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.002079584083183363,
|
| 196 |
+
"grad_norm": 4.038774490356445,
|
| 197 |
+
"learning_rate": 0.00019994603803069594,
|
| 198 |
+
"loss": 3.8126,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0021595680863827236,
|
| 203 |
+
"grad_norm": 4.452616214752197,
|
| 204 |
+
"learning_rate": 0.0001999390827019096,
|
| 205 |
+
"loss": 4.3482,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.0022395520895820836,
|
| 210 |
+
"grad_norm": 4.7611212730407715,
|
| 211 |
+
"learning_rate": 0.0001999317060143023,
|
| 212 |
+
"loss": 5.3983,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0023195360927814436,
|
| 217 |
+
"grad_norm": 3.455153465270996,
|
| 218 |
+
"learning_rate": 0.00019992390799897534,
|
| 219 |
+
"loss": 4.5008,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.0023995200959808036,
|
| 224 |
+
"grad_norm": 4.436529636383057,
|
| 225 |
+
"learning_rate": 0.0001999156886888064,
|
| 226 |
+
"loss": 5.7692,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.002479504099180164,
|
| 231 |
+
"grad_norm": 5.176506996154785,
|
| 232 |
+
"learning_rate": 0.00019990704811844934,
|
| 233 |
+
"loss": 5.2556,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.002559488102379524,
|
| 238 |
+
"grad_norm": 4.376233100891113,
|
| 239 |
+
"learning_rate": 0.00019989798632433415,
|
| 240 |
+
"loss": 4.9445,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.002639472105578884,
|
| 245 |
+
"grad_norm": 4.30057430267334,
|
| 246 |
+
"learning_rate": 0.0001998885033446668,
|
| 247 |
+
"loss": 5.1481,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0027194561087782445,
|
| 252 |
+
"grad_norm": 4.3144330978393555,
|
| 253 |
+
"learning_rate": 0.00019987859921942903,
|
| 254 |
+
"loss": 5.6733,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0027994401119776045,
|
| 259 |
+
"grad_norm": 4.325514316558838,
|
| 260 |
+
"learning_rate": 0.00019986827399037812,
|
| 261 |
+
"loss": 4.7508,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0028794241151769645,
|
| 266 |
+
"grad_norm": 3.4611852169036865,
|
| 267 |
+
"learning_rate": 0.0001998575277010469,
|
| 268 |
+
"loss": 4.2926,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0029594081183763245,
|
| 273 |
+
"grad_norm": 4.122291564941406,
|
| 274 |
+
"learning_rate": 0.0001998463603967434,
|
| 275 |
+
"loss": 5.5432,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.003039392121575685,
|
| 280 |
+
"grad_norm": 3.8572282791137695,
|
| 281 |
+
"learning_rate": 0.00019983477212455074,
|
| 282 |
+
"loss": 3.6934,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.003119376124775045,
|
| 287 |
+
"grad_norm": 4.3047943115234375,
|
| 288 |
+
"learning_rate": 0.00019982276293332686,
|
| 289 |
+
"loss": 5.3475,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.003199360127974405,
|
| 294 |
+
"grad_norm": 3.8791322708129883,
|
| 295 |
+
"learning_rate": 0.00019981033287370443,
|
| 296 |
+
"loss": 4.9571,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0032793441311737654,
|
| 301 |
+
"grad_norm": 4.470249176025391,
|
| 302 |
+
"learning_rate": 0.00019979748199809049,
|
| 303 |
+
"loss": 5.1785,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0033593281343731254,
|
| 308 |
+
"grad_norm": 3.4192795753479004,
|
| 309 |
+
"learning_rate": 0.00019978421036066633,
|
| 310 |
+
"loss": 4.6074,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0034393121375724854,
|
| 315 |
+
"grad_norm": 3.722909927368164,
|
| 316 |
+
"learning_rate": 0.0001997705180173873,
|
| 317 |
+
"loss": 3.9538,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0035192961407718455,
|
| 322 |
+
"grad_norm": 3.8294920921325684,
|
| 323 |
+
"learning_rate": 0.00019975640502598244,
|
| 324 |
+
"loss": 4.7456,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.003599280143971206,
|
| 329 |
+
"grad_norm": 3.147818088531494,
|
| 330 |
+
"learning_rate": 0.00019974187144595432,
|
| 331 |
+
"loss": 4.2381,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.003679264147170566,
|
| 336 |
+
"grad_norm": 4.7630109786987305,
|
| 337 |
+
"learning_rate": 0.00019972691733857883,
|
| 338 |
+
"loss": 4.5834,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.003759248150369926,
|
| 343 |
+
"grad_norm": 3.569880485534668,
|
| 344 |
+
"learning_rate": 0.00019971154276690478,
|
| 345 |
+
"loss": 3.8295,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.0038392321535692863,
|
| 350 |
+
"grad_norm": 5.48881196975708,
|
| 351 |
+
"learning_rate": 0.00019969574779575376,
|
| 352 |
+
"loss": 5.0891,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.003919216156768646,
|
| 357 |
+
"grad_norm": 3.903329849243164,
|
| 358 |
+
"learning_rate": 0.0001996795324917199,
|
| 359 |
+
"loss": 5.4285,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.003999200159968006,
|
| 364 |
+
"grad_norm": 3.75028395652771,
|
| 365 |
+
"learning_rate": 0.00019966289692316944,
|
| 366 |
+
"loss": 3.8204,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.004079184163167366,
|
| 371 |
+
"grad_norm": 4.618161678314209,
|
| 372 |
+
"learning_rate": 0.00019964584116024053,
|
| 373 |
+
"loss": 4.5384,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.004159168166366726,
|
| 378 |
+
"grad_norm": 4.52060604095459,
|
| 379 |
+
"learning_rate": 0.00019962836527484296,
|
| 380 |
+
"loss": 4.5576,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.004239152169566086,
|
| 385 |
+
"grad_norm": 4.482393264770508,
|
| 386 |
+
"learning_rate": 0.00019961046934065778,
|
| 387 |
+
"loss": 4.3975,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.004319136172765447,
|
| 392 |
+
"grad_norm": 4.1788411140441895,
|
| 393 |
+
"learning_rate": 0.00019959215343313703,
|
| 394 |
+
"loss": 4.1852,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.004399120175964807,
|
| 399 |
+
"grad_norm": 4.333094120025635,
|
| 400 |
+
"learning_rate": 0.00019957341762950344,
|
| 401 |
+
"loss": 4.7889,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.004479104179164167,
|
| 406 |
+
"grad_norm": 4.460629463195801,
|
| 407 |
+
"learning_rate": 0.00019955426200875018,
|
| 408 |
+
"loss": 4.0291,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.004559088182363527,
|
| 413 |
+
"grad_norm": 3.434190511703491,
|
| 414 |
+
"learning_rate": 0.00019953468665164024,
|
| 415 |
+
"loss": 5.1293,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.004639072185562887,
|
| 420 |
+
"grad_norm": 3.6340487003326416,
|
| 421 |
+
"learning_rate": 0.00019951469164070646,
|
| 422 |
+
"loss": 4.3983,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.004719056188762247,
|
| 427 |
+
"grad_norm": 3.3554069995880127,
|
| 428 |
+
"learning_rate": 0.0001994942770602509,
|
| 429 |
+
"loss": 4.3103,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.004799040191961607,
|
| 434 |
+
"grad_norm": 3.730646848678589,
|
| 435 |
+
"learning_rate": 0.00019947344299634464,
|
| 436 |
+
"loss": 4.2136,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.004879024195160968,
|
| 441 |
+
"grad_norm": 3.0557665824890137,
|
| 442 |
+
"learning_rate": 0.00019945218953682734,
|
| 443 |
+
"loss": 4.6209,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.004959008198360328,
|
| 448 |
+
"grad_norm": 4.148006916046143,
|
| 449 |
+
"learning_rate": 0.00019943051677130696,
|
| 450 |
+
"loss": 4.6885,
|
| 451 |
+
"step": 62
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.005038992201559688,
|
| 455 |
+
"grad_norm": 4.280196189880371,
|
| 456 |
+
"learning_rate": 0.0001994084247911592,
|
| 457 |
+
"loss": 6.0293,
|
| 458 |
+
"step": 63
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.005118976204759048,
|
| 462 |
+
"grad_norm": 4.3163371086120605,
|
| 463 |
+
"learning_rate": 0.0001993859136895274,
|
| 464 |
+
"loss": 5.3148,
|
| 465 |
+
"step": 64
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.005198960207958408,
|
| 469 |
+
"grad_norm": 3.7306902408599854,
|
| 470 |
+
"learning_rate": 0.00019936298356132176,
|
| 471 |
+
"loss": 5.5089,
|
| 472 |
+
"step": 65
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.005278944211157768,
|
| 476 |
+
"grad_norm": 3.655566453933716,
|
| 477 |
+
"learning_rate": 0.00019933963450321945,
|
| 478 |
+
"loss": 5.4979,
|
| 479 |
+
"step": 66
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.005358928214357128,
|
| 483 |
+
"grad_norm": 3.5753936767578125,
|
| 484 |
+
"learning_rate": 0.00019931586661366363,
|
| 485 |
+
"loss": 5.0488,
|
| 486 |
+
"step": 67
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.005438912217556489,
|
| 490 |
+
"grad_norm": 3.427351713180542,
|
| 491 |
+
"learning_rate": 0.0001992916799928635,
|
| 492 |
+
"loss": 4.4419,
|
| 493 |
+
"step": 68
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.005518896220755849,
|
| 497 |
+
"grad_norm": 3.284907341003418,
|
| 498 |
+
"learning_rate": 0.0001992670747427936,
|
| 499 |
+
"loss": 4.1645,
|
| 500 |
+
"step": 69
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.005598880223955209,
|
| 504 |
+
"grad_norm": 3.8085391521453857,
|
| 505 |
+
"learning_rate": 0.0001992420509671936,
|
| 506 |
+
"loss": 6.0662,
|
| 507 |
+
"step": 70
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.005678864227154569,
|
| 511 |
+
"grad_norm": 3.331713914871216,
|
| 512 |
+
"learning_rate": 0.00019921660877156755,
|
| 513 |
+
"loss": 3.8283,
|
| 514 |
+
"step": 71
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.005758848230353929,
|
| 518 |
+
"grad_norm": 3.343092441558838,
|
| 519 |
+
"learning_rate": 0.0001991907482631838,
|
| 520 |
+
"loss": 4.5758,
|
| 521 |
+
"step": 72
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.005838832233553289,
|
| 525 |
+
"grad_norm": 3.283320188522339,
|
| 526 |
+
"learning_rate": 0.00019916446955107428,
|
| 527 |
+
"loss": 5.102,
|
| 528 |
+
"step": 73
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.005918816236752649,
|
| 532 |
+
"grad_norm": 3.636723756790161,
|
| 533 |
+
"learning_rate": 0.00019913777274603418,
|
| 534 |
+
"loss": 4.2686,
|
| 535 |
+
"step": 74
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.00599880023995201,
|
| 539 |
+
"grad_norm": 3.107661485671997,
|
| 540 |
+
"learning_rate": 0.00019911065796062135,
|
| 541 |
+
"loss": 4.1827,
|
| 542 |
+
"step": 75
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.00607878424315137,
|
| 546 |
+
"grad_norm": 4.445980072021484,
|
| 547 |
+
"learning_rate": 0.00019908312530915603,
|
| 548 |
+
"loss": 4.568,
|
| 549 |
+
"step": 76
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.00615876824635073,
|
| 553 |
+
"grad_norm": 3.0102596282958984,
|
| 554 |
+
"learning_rate": 0.00019905517490772015,
|
| 555 |
+
"loss": 4.0638,
|
| 556 |
+
"step": 77
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.00623875224955009,
|
| 560 |
+
"grad_norm": 4.667107105255127,
|
| 561 |
+
"learning_rate": 0.00019902680687415705,
|
| 562 |
+
"loss": 4.9191,
|
| 563 |
+
"step": 78
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.00631873625274945,
|
| 567 |
+
"grad_norm": 4.729066848754883,
|
| 568 |
+
"learning_rate": 0.0001989980213280707,
|
| 569 |
+
"loss": 4.5239,
|
| 570 |
+
"step": 79
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.00639872025594881,
|
| 574 |
+
"grad_norm": 4.467210292816162,
|
| 575 |
+
"learning_rate": 0.00019896881839082556,
|
| 576 |
+
"loss": 5.3754,
|
| 577 |
+
"step": 80
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.00647870425914817,
|
| 581 |
+
"grad_norm": 4.176740646362305,
|
| 582 |
+
"learning_rate": 0.0001989391981855457,
|
| 583 |
+
"loss": 5.5159,
|
| 584 |
+
"step": 81
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.006558688262347531,
|
| 588 |
+
"grad_norm": 4.937440395355225,
|
| 589 |
+
"learning_rate": 0.0001989091608371146,
|
| 590 |
+
"loss": 4.9222,
|
| 591 |
+
"step": 82
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.006638672265546891,
|
| 595 |
+
"grad_norm": 3.6677310466766357,
|
| 596 |
+
"learning_rate": 0.00019887870647217442,
|
| 597 |
+
"loss": 3.5926,
|
| 598 |
+
"step": 83
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.006718656268746251,
|
| 602 |
+
"grad_norm": 4.629709243774414,
|
| 603 |
+
"learning_rate": 0.00019884783521912554,
|
| 604 |
+
"loss": 4.0758,
|
| 605 |
+
"step": 84
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.006798640271945611,
|
| 609 |
+
"grad_norm": 4.480130672454834,
|
| 610 |
+
"learning_rate": 0.00019881654720812594,
|
| 611 |
+
"loss": 4.2366,
|
| 612 |
+
"step": 85
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.006878624275144971,
|
| 616 |
+
"grad_norm": 4.163790225982666,
|
| 617 |
+
"learning_rate": 0.00019878484257109083,
|
| 618 |
+
"loss": 4.1109,
|
| 619 |
+
"step": 86
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.006958608278344331,
|
| 623 |
+
"grad_norm": 4.017063617706299,
|
| 624 |
+
"learning_rate": 0.00019875272144169193,
|
| 625 |
+
"loss": 4.599,
|
| 626 |
+
"step": 87
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.007038592281543691,
|
| 630 |
+
"grad_norm": 4.747475624084473,
|
| 631 |
+
"learning_rate": 0.0001987201839553569,
|
| 632 |
+
"loss": 4.0236,
|
| 633 |
+
"step": 88
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.007118576284743052,
|
| 637 |
+
"grad_norm": 4.168716907501221,
|
| 638 |
+
"learning_rate": 0.00019868723024926891,
|
| 639 |
+
"loss": 3.9595,
|
| 640 |
+
"step": 89
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.007198560287942412,
|
| 644 |
+
"grad_norm": 4.3506011962890625,
|
| 645 |
+
"learning_rate": 0.00019865386046236596,
|
| 646 |
+
"loss": 4.4328,
|
| 647 |
+
"step": 90
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.007278544291141772,
|
| 651 |
+
"grad_norm": 4.0267839431762695,
|
| 652 |
+
"learning_rate": 0.00019862007473534025,
|
| 653 |
+
"loss": 4.749,
|
| 654 |
+
"step": 91
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.007358528294341132,
|
| 658 |
+
"grad_norm": 5.045677185058594,
|
| 659 |
+
"learning_rate": 0.00019858587321063776,
|
| 660 |
+
"loss": 4.7425,
|
| 661 |
+
"step": 92
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.007438512297540492,
|
| 665 |
+
"grad_norm": 4.732039451599121,
|
| 666 |
+
"learning_rate": 0.00019855125603245738,
|
| 667 |
+
"loss": 4.1719,
|
| 668 |
+
"step": 93
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.007518496300739852,
|
| 672 |
+
"grad_norm": 3.6055307388305664,
|
| 673 |
+
"learning_rate": 0.00019851622334675066,
|
| 674 |
+
"loss": 3.3813,
|
| 675 |
+
"step": 94
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.007598480303939212,
|
| 679 |
+
"grad_norm": 4.301301002502441,
|
| 680 |
+
"learning_rate": 0.00019848077530122083,
|
| 681 |
+
"loss": 4.7025,
|
| 682 |
+
"step": 95
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.007678464307138573,
|
| 686 |
+
"grad_norm": 4.625269889831543,
|
| 687 |
+
"learning_rate": 0.00019844491204532236,
|
| 688 |
+
"loss": 5.462,
|
| 689 |
+
"step": 96
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.007758448310337933,
|
| 693 |
+
"grad_norm": 4.291022300720215,
|
| 694 |
+
"learning_rate": 0.00019840863373026045,
|
| 695 |
+
"loss": 4.4898,
|
| 696 |
+
"step": 97
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.007838432313537293,
|
| 700 |
+
"grad_norm": 4.237590312957764,
|
| 701 |
+
"learning_rate": 0.0001983719405089901,
|
| 702 |
+
"loss": 4.578,
|
| 703 |
+
"step": 98
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.007918416316736652,
|
| 707 |
+
"grad_norm": 5.464932441711426,
|
| 708 |
+
"learning_rate": 0.00019833483253621568,
|
| 709 |
+
"loss": 4.622,
|
| 710 |
+
"step": 99
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.007998400319936013,
|
| 714 |
+
"grad_norm": 4.568652629852295,
|
| 715 |
+
"learning_rate": 0.0001982973099683902,
|
| 716 |
+
"loss": 3.8691,
|
| 717 |
+
"step": 100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.008078384323135374,
|
| 721 |
+
"grad_norm": 3.8946774005889893,
|
| 722 |
+
"learning_rate": 0.00019825937296371468,
|
| 723 |
+
"loss": 3.707,
|
| 724 |
+
"step": 101
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.008158368326334733,
|
| 728 |
+
"grad_norm": 4.361711502075195,
|
| 729 |
+
"learning_rate": 0.00019822102168213753,
|
| 730 |
+
"loss": 4.472,
|
| 731 |
+
"step": 102
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.008238352329534094,
|
| 735 |
+
"grad_norm": 4.38311767578125,
|
| 736 |
+
"learning_rate": 0.0001981822562853537,
|
| 737 |
+
"loss": 4.7478,
|
| 738 |
+
"step": 103
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.008318336332733453,
|
| 742 |
+
"grad_norm": 4.354578018188477,
|
| 743 |
+
"learning_rate": 0.0001981430769368042,
|
| 744 |
+
"loss": 5.8493,
|
| 745 |
+
"step": 104
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.008398320335932814,
|
| 749 |
+
"grad_norm": 4.7935590744018555,
|
| 750 |
+
"learning_rate": 0.00019810348380167527,
|
| 751 |
+
"loss": 5.5214,
|
| 752 |
+
"step": 105
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.008478304339132173,
|
| 756 |
+
"grad_norm": 4.473304271697998,
|
| 757 |
+
"learning_rate": 0.00019806347704689778,
|
| 758 |
+
"loss": 4.4084,
|
| 759 |
+
"step": 106
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.008558288342331534,
|
| 763 |
+
"grad_norm": 3.7808096408843994,
|
| 764 |
+
"learning_rate": 0.00019802305684114648,
|
| 765 |
+
"loss": 4.8573,
|
| 766 |
+
"step": 107
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.008638272345530894,
|
| 770 |
+
"grad_norm": 4.11630392074585,
|
| 771 |
+
"learning_rate": 0.00019798222335483932,
|
| 772 |
+
"loss": 3.9953,
|
| 773 |
+
"step": 108
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.008718256348730254,
|
| 777 |
+
"grad_norm": 3.9533166885375977,
|
| 778 |
+
"learning_rate": 0.0001979409767601366,
|
| 779 |
+
"loss": 3.9655,
|
| 780 |
+
"step": 109
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.008798240351929614,
|
| 784 |
+
"grad_norm": 4.105170249938965,
|
| 785 |
+
"learning_rate": 0.00019789931723094046,
|
| 786 |
+
"loss": 3.9458,
|
| 787 |
+
"step": 110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.008878224355128974,
|
| 791 |
+
"grad_norm": 5.170469284057617,
|
| 792 |
+
"learning_rate": 0.00019785724494289402,
|
| 793 |
+
"loss": 4.3416,
|
| 794 |
+
"step": 111
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.008958208358328335,
|
| 798 |
+
"grad_norm": 5.103896141052246,
|
| 799 |
+
"learning_rate": 0.00019781476007338058,
|
| 800 |
+
"loss": 4.6881,
|
| 801 |
+
"step": 112
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.009038192361527694,
|
| 805 |
+
"grad_norm": 5.349043369293213,
|
| 806 |
+
"learning_rate": 0.00019777186280152303,
|
| 807 |
+
"loss": 5.3737,
|
| 808 |
+
"step": 113
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.009118176364727055,
|
| 812 |
+
"grad_norm": 5.156305313110352,
|
| 813 |
+
"learning_rate": 0.000197728553308183,
|
| 814 |
+
"loss": 4.1623,
|
| 815 |
+
"step": 114
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.009198160367926415,
|
| 819 |
+
"grad_norm": 4.510937213897705,
|
| 820 |
+
"learning_rate": 0.0001976848317759601,
|
| 821 |
+
"loss": 6.1072,
|
| 822 |
+
"step": 115
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.009278144371125775,
|
| 826 |
+
"grad_norm": 6.212741851806641,
|
| 827 |
+
"learning_rate": 0.0001976406983891911,
|
| 828 |
+
"loss": 5.0148,
|
| 829 |
+
"step": 116
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.009358128374325135,
|
| 833 |
+
"grad_norm": 4.464901447296143,
|
| 834 |
+
"learning_rate": 0.00019759615333394932,
|
| 835 |
+
"loss": 4.0828,
|
| 836 |
+
"step": 117
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.009438112377524495,
|
| 840 |
+
"grad_norm": 5.239302158355713,
|
| 841 |
+
"learning_rate": 0.00019755119679804367,
|
| 842 |
+
"loss": 4.649,
|
| 843 |
+
"step": 118
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.009518096380723855,
|
| 847 |
+
"grad_norm": 4.33208703994751,
|
| 848 |
+
"learning_rate": 0.00019750582897101797,
|
| 849 |
+
"loss": 3.6407,
|
| 850 |
+
"step": 119
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.009598080383923215,
|
| 854 |
+
"grad_norm": 3.9181249141693115,
|
| 855 |
+
"learning_rate": 0.00019746005004415005,
|
| 856 |
+
"loss": 3.5174,
|
| 857 |
+
"step": 120
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.009678064387122575,
|
| 861 |
+
"grad_norm": 5.414444923400879,
|
| 862 |
+
"learning_rate": 0.00019741386021045104,
|
| 863 |
+
"loss": 4.3238,
|
| 864 |
+
"step": 121
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.009758048390321936,
|
| 868 |
+
"grad_norm": 5.03347635269165,
|
| 869 |
+
"learning_rate": 0.0001973672596646645,
|
| 870 |
+
"loss": 4.0335,
|
| 871 |
+
"step": 122
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.009838032393521295,
|
| 875 |
+
"grad_norm": 4.60539436340332,
|
| 876 |
+
"learning_rate": 0.00019732024860326565,
|
| 877 |
+
"loss": 4.4081,
|
| 878 |
+
"step": 123
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.009918016396720656,
|
| 882 |
+
"grad_norm": 4.669139862060547,
|
| 883 |
+
"learning_rate": 0.00019727282722446047,
|
| 884 |
+
"loss": 4.7103,
|
| 885 |
+
"step": 124
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.009998000399920015,
|
| 889 |
+
"grad_norm": 4.479554653167725,
|
| 890 |
+
"learning_rate": 0.00019722499572818496,
|
| 891 |
+
"loss": 4.5797,
|
| 892 |
+
"step": 125
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.010077984403119376,
|
| 896 |
+
"grad_norm": 4.219813346862793,
|
| 897 |
+
"learning_rate": 0.00019717675431610415,
|
| 898 |
+
"loss": 3.3457,
|
| 899 |
+
"step": 126
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.010157968406318735,
|
| 903 |
+
"grad_norm": 4.138061046600342,
|
| 904 |
+
"learning_rate": 0.0001971281031916114,
|
| 905 |
+
"loss": 4.4678,
|
| 906 |
+
"step": 127
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.010237952409518096,
|
| 910 |
+
"grad_norm": 4.0591230392456055,
|
| 911 |
+
"learning_rate": 0.00019707904255982745,
|
| 912 |
+
"loss": 3.4897,
|
| 913 |
+
"step": 128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.010317936412717457,
|
| 917 |
+
"grad_norm": 5.270677089691162,
|
| 918 |
+
"learning_rate": 0.00019702957262759965,
|
| 919 |
+
"loss": 4.8912,
|
| 920 |
+
"step": 129
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.010397920415916816,
|
| 924 |
+
"grad_norm": 4.547000408172607,
|
| 925 |
+
"learning_rate": 0.00019697969360350098,
|
| 926 |
+
"loss": 4.3903,
|
| 927 |
+
"step": 130
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.010477904419116177,
|
| 931 |
+
"grad_norm": 4.9797139167785645,
|
| 932 |
+
"learning_rate": 0.00019692940569782913,
|
| 933 |
+
"loss": 4.5133,
|
| 934 |
+
"step": 131
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.010557888422315536,
|
| 938 |
+
"grad_norm": 6.008891582489014,
|
| 939 |
+
"learning_rate": 0.0001968787091226059,
|
| 940 |
+
"loss": 4.8437,
|
| 941 |
+
"step": 132
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.010637872425514897,
|
| 945 |
+
"grad_norm": 6.226869583129883,
|
| 946 |
+
"learning_rate": 0.0001968276040915759,
|
| 947 |
+
"loss": 4.9427,
|
| 948 |
+
"step": 133
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.010717856428714256,
|
| 952 |
+
"grad_norm": 5.999492168426514,
|
| 953 |
+
"learning_rate": 0.00019677609082020597,
|
| 954 |
+
"loss": 5.0577,
|
| 955 |
+
"step": 134
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.010797840431913617,
|
| 959 |
+
"grad_norm": 6.069042682647705,
|
| 960 |
+
"learning_rate": 0.00019672416952568416,
|
| 961 |
+
"loss": 5.8394,
|
| 962 |
+
"step": 135
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.010877824435112978,
|
| 966 |
+
"grad_norm": 4.348324775695801,
|
| 967 |
+
"learning_rate": 0.00019667184042691875,
|
| 968 |
+
"loss": 3.7166,
|
| 969 |
+
"step": 136
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.010957808438312337,
|
| 973 |
+
"grad_norm": 4.531675815582275,
|
| 974 |
+
"learning_rate": 0.00019661910374453744,
|
| 975 |
+
"loss": 5.053,
|
| 976 |
+
"step": 137
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.011037792441511698,
|
| 980 |
+
"grad_norm": 5.470901966094971,
|
| 981 |
+
"learning_rate": 0.00019656595970088628,
|
| 982 |
+
"loss": 4.7888,
|
| 983 |
+
"step": 138
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.011117776444711057,
|
| 987 |
+
"grad_norm": 4.40546989440918,
|
| 988 |
+
"learning_rate": 0.0001965124085200289,
|
| 989 |
+
"loss": 4.6627,
|
| 990 |
+
"step": 139
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.011197760447910418,
|
| 994 |
+
"grad_norm": 4.321747303009033,
|
| 995 |
+
"learning_rate": 0.00019645845042774553,
|
| 996 |
+
"loss": 3.2058,
|
| 997 |
+
"step": 140
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.011277744451109777,
|
| 1001 |
+
"grad_norm": 4.924249649047852,
|
| 1002 |
+
"learning_rate": 0.00019640408565153186,
|
| 1003 |
+
"loss": 5.0648,
|
| 1004 |
+
"step": 141
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.011357728454309138,
|
| 1008 |
+
"grad_norm": 5.039271831512451,
|
| 1009 |
+
"learning_rate": 0.00019634931442059832,
|
| 1010 |
+
"loss": 5.2905,
|
| 1011 |
+
"step": 142
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.011437712457508499,
|
| 1015 |
+
"grad_norm": 4.569279193878174,
|
| 1016 |
+
"learning_rate": 0.00019629413696586903,
|
| 1017 |
+
"loss": 6.2246,
|
| 1018 |
+
"step": 143
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.011517696460707858,
|
| 1022 |
+
"grad_norm": 4.1219401359558105,
|
| 1023 |
+
"learning_rate": 0.00019623855351998072,
|
| 1024 |
+
"loss": 4.0549,
|
| 1025 |
+
"step": 144
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.011597680463907219,
|
| 1029 |
+
"grad_norm": 4.945868492126465,
|
| 1030 |
+
"learning_rate": 0.00019618256431728194,
|
| 1031 |
+
"loss": 3.6012,
|
| 1032 |
+
"step": 145
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.011677664467106578,
|
| 1036 |
+
"grad_norm": 5.271925926208496,
|
| 1037 |
+
"learning_rate": 0.0001961261695938319,
|
| 1038 |
+
"loss": 3.9763,
|
| 1039 |
+
"step": 146
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.011757648470305939,
|
| 1043 |
+
"grad_norm": 4.197992324829102,
|
| 1044 |
+
"learning_rate": 0.00019606936958739963,
|
| 1045 |
+
"loss": 4.2189,
|
| 1046 |
+
"step": 147
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.011837632473505298,
|
| 1050 |
+
"grad_norm": 7.92578649520874,
|
| 1051 |
+
"learning_rate": 0.00019601216453746283,
|
| 1052 |
+
"loss": 4.5706,
|
| 1053 |
+
"step": 148
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.011917616476704659,
|
| 1057 |
+
"grad_norm": 4.556253910064697,
|
| 1058 |
+
"learning_rate": 0.00019595455468520695,
|
| 1059 |
+
"loss": 3.3737,
|
| 1060 |
+
"step": 149
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.01199760047990402,
|
| 1064 |
+
"grad_norm": 4.560910224914551,
|
| 1065 |
+
"learning_rate": 0.00019589654027352414,
|
| 1066 |
+
"loss": 2.9566,
|
| 1067 |
+
"step": 150
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.012077584483103379,
|
| 1071 |
+
"grad_norm": 5.795867919921875,
|
| 1072 |
+
"learning_rate": 0.00019583812154701225,
|
| 1073 |
+
"loss": 4.4294,
|
| 1074 |
+
"step": 151
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.01215756848630274,
|
| 1078 |
+
"grad_norm": 5.964183330535889,
|
| 1079 |
+
"learning_rate": 0.00019577929875197377,
|
| 1080 |
+
"loss": 3.7239,
|
| 1081 |
+
"step": 152
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.012237552489502099,
|
| 1085 |
+
"grad_norm": 4.3232102394104,
|
| 1086 |
+
"learning_rate": 0.00019572007213641485,
|
| 1087 |
+
"loss": 3.0652,
|
| 1088 |
+
"step": 153
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.01231753649270146,
|
| 1092 |
+
"grad_norm": 4.781129360198975,
|
| 1093 |
+
"learning_rate": 0.0001956604419500441,
|
| 1094 |
+
"loss": 3.6271,
|
| 1095 |
+
"step": 154
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.012397520495900819,
|
| 1099 |
+
"grad_norm": 8.637353897094727,
|
| 1100 |
+
"learning_rate": 0.0001956004084442718,
|
| 1101 |
+
"loss": 5.0342,
|
| 1102 |
+
"step": 155
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.01247750449910018,
|
| 1106 |
+
"grad_norm": 4.655914306640625,
|
| 1107 |
+
"learning_rate": 0.00019553997187220855,
|
| 1108 |
+
"loss": 3.2862,
|
| 1109 |
+
"step": 156
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.01255748850229954,
|
| 1113 |
+
"grad_norm": 5.187161922454834,
|
| 1114 |
+
"learning_rate": 0.00019547913248866444,
|
| 1115 |
+
"loss": 5.0299,
|
| 1116 |
+
"step": 157
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.0126374725054989,
|
| 1120 |
+
"grad_norm": 6.352967739105225,
|
| 1121 |
+
"learning_rate": 0.00019541789055014784,
|
| 1122 |
+
"loss": 5.49,
|
| 1123 |
+
"step": 158
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.01271745650869826,
|
| 1127 |
+
"grad_norm": 4.698216915130615,
|
| 1128 |
+
"learning_rate": 0.00019535624631486433,
|
| 1129 |
+
"loss": 4.1956,
|
| 1130 |
+
"step": 159
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.01279744051189762,
|
| 1134 |
+
"grad_norm": 4.389121055603027,
|
| 1135 |
+
"learning_rate": 0.00019529420004271567,
|
| 1136 |
+
"loss": 3.7758,
|
| 1137 |
+
"step": 160
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.01287742451509698,
|
| 1141 |
+
"grad_norm": 4.86370849609375,
|
| 1142 |
+
"learning_rate": 0.00019523175199529863,
|
| 1143 |
+
"loss": 4.4053,
|
| 1144 |
+
"step": 161
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.01295740851829634,
|
| 1148 |
+
"grad_norm": 5.030034065246582,
|
| 1149 |
+
"learning_rate": 0.000195168902435904,
|
| 1150 |
+
"loss": 3.5576,
|
| 1151 |
+
"step": 162
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.0130373925214957,
|
| 1155 |
+
"grad_norm": 4.813689231872559,
|
| 1156 |
+
"learning_rate": 0.00019510565162951537,
|
| 1157 |
+
"loss": 3.9392,
|
| 1158 |
+
"step": 163
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.013117376524695062,
|
| 1162 |
+
"grad_norm": 4.899305820465088,
|
| 1163 |
+
"learning_rate": 0.00019504199984280799,
|
| 1164 |
+
"loss": 4.3442,
|
| 1165 |
+
"step": 164
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.013197360527894421,
|
| 1169 |
+
"grad_norm": 4.388523578643799,
|
| 1170 |
+
"learning_rate": 0.0001949779473441478,
|
| 1171 |
+
"loss": 3.5577,
|
| 1172 |
+
"step": 165
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.013277344531093782,
|
| 1176 |
+
"grad_norm": 5.756633758544922,
|
| 1177 |
+
"learning_rate": 0.00019491349440359015,
|
| 1178 |
+
"loss": 4.0196,
|
| 1179 |
+
"step": 166
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.013357328534293141,
|
| 1183 |
+
"grad_norm": 4.173125267028809,
|
| 1184 |
+
"learning_rate": 0.0001948486412928787,
|
| 1185 |
+
"loss": 3.4954,
|
| 1186 |
+
"step": 167
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.013437312537492502,
|
| 1190 |
+
"grad_norm": 4.68442964553833,
|
| 1191 |
+
"learning_rate": 0.00019478338828544435,
|
| 1192 |
+
"loss": 3.6734,
|
| 1193 |
+
"step": 168
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.013517296540691861,
|
| 1197 |
+
"grad_norm": 4.491235733032227,
|
| 1198 |
+
"learning_rate": 0.00019471773565640403,
|
| 1199 |
+
"loss": 2.8435,
|
| 1200 |
+
"step": 169
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.013597280543891222,
|
| 1204 |
+
"grad_norm": 5.267945289611816,
|
| 1205 |
+
"learning_rate": 0.00019465168368255946,
|
| 1206 |
+
"loss": 4.3094,
|
| 1207 |
+
"step": 170
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.013677264547090583,
|
| 1211 |
+
"grad_norm": 3.776217460632324,
|
| 1212 |
+
"learning_rate": 0.00019458523264239612,
|
| 1213 |
+
"loss": 2.9521,
|
| 1214 |
+
"step": 171
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.013757248550289942,
|
| 1218 |
+
"grad_norm": 5.366693019866943,
|
| 1219 |
+
"learning_rate": 0.00019451838281608197,
|
| 1220 |
+
"loss": 4.4226,
|
| 1221 |
+
"step": 172
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.013837232553489303,
|
| 1225 |
+
"grad_norm": 5.224587917327881,
|
| 1226 |
+
"learning_rate": 0.00019445113448546638,
|
| 1227 |
+
"loss": 4.0713,
|
| 1228 |
+
"step": 173
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.013917216556688662,
|
| 1232 |
+
"grad_norm": 5.798890113830566,
|
| 1233 |
+
"learning_rate": 0.00019438348793407881,
|
| 1234 |
+
"loss": 5.7135,
|
| 1235 |
+
"step": 174
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.013997200559888023,
|
| 1239 |
+
"grad_norm": 4.861985206604004,
|
| 1240 |
+
"learning_rate": 0.00019431544344712776,
|
| 1241 |
+
"loss": 4.3844,
|
| 1242 |
+
"step": 175
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.014077184563087382,
|
| 1246 |
+
"grad_norm": 4.904694557189941,
|
| 1247 |
+
"learning_rate": 0.0001942470013114994,
|
| 1248 |
+
"loss": 4.2836,
|
| 1249 |
+
"step": 176
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.014157168566286743,
|
| 1253 |
+
"grad_norm": 5.404961109161377,
|
| 1254 |
+
"learning_rate": 0.0001941781618157565,
|
| 1255 |
+
"loss": 4.0793,
|
| 1256 |
+
"step": 177
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.014237152569486104,
|
| 1260 |
+
"grad_norm": 3.9328558444976807,
|
| 1261 |
+
"learning_rate": 0.0001941089252501372,
|
| 1262 |
+
"loss": 3.4638,
|
| 1263 |
+
"step": 178
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.014317136572685463,
|
| 1267 |
+
"grad_norm": 7.811837196350098,
|
| 1268 |
+
"learning_rate": 0.00019403929190655358,
|
| 1269 |
+
"loss": 5.4092,
|
| 1270 |
+
"step": 179
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.014397120575884824,
|
| 1274 |
+
"grad_norm": 4.343170642852783,
|
| 1275 |
+
"learning_rate": 0.00019396926207859084,
|
| 1276 |
+
"loss": 4.003,
|
| 1277 |
+
"step": 180
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.014477104579084183,
|
| 1281 |
+
"grad_norm": 4.674137115478516,
|
| 1282 |
+
"learning_rate": 0.00019389883606150566,
|
| 1283 |
+
"loss": 3.613,
|
| 1284 |
+
"step": 181
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.014557088582283544,
|
| 1288 |
+
"grad_norm": 5.229063510894775,
|
| 1289 |
+
"learning_rate": 0.00019382801415222516,
|
| 1290 |
+
"loss": 4.1551,
|
| 1291 |
+
"step": 182
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.014637072585482903,
|
| 1295 |
+
"grad_norm": 4.8597493171691895,
|
| 1296 |
+
"learning_rate": 0.00019375679664934556,
|
| 1297 |
+
"loss": 3.1254,
|
| 1298 |
+
"step": 183
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.014717056588682264,
|
| 1302 |
+
"grad_norm": 4.986814498901367,
|
| 1303 |
+
"learning_rate": 0.00019368518385313107,
|
| 1304 |
+
"loss": 3.7172,
|
| 1305 |
+
"step": 184
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.014797040591881624,
|
| 1309 |
+
"grad_norm": 4.790543079376221,
|
| 1310 |
+
"learning_rate": 0.00019361317606551238,
|
| 1311 |
+
"loss": 4.4556,
|
| 1312 |
+
"step": 185
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.014877024595080984,
|
| 1316 |
+
"grad_norm": 4.165306568145752,
|
| 1317 |
+
"learning_rate": 0.0001935407735900857,
|
| 1318 |
+
"loss": 3.7351,
|
| 1319 |
+
"step": 186
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.014957008598280344,
|
| 1323 |
+
"grad_norm": 3.8044018745422363,
|
| 1324 |
+
"learning_rate": 0.00019346797673211108,
|
| 1325 |
+
"loss": 2.7252,
|
| 1326 |
+
"step": 187
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.015036992601479704,
|
| 1330 |
+
"grad_norm": 3.905625581741333,
|
| 1331 |
+
"learning_rate": 0.00019339478579851155,
|
| 1332 |
+
"loss": 3.4771,
|
| 1333 |
+
"step": 188
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.015116976604679064,
|
| 1337 |
+
"grad_norm": 3.9782605171203613,
|
| 1338 |
+
"learning_rate": 0.0001933212010978715,
|
| 1339 |
+
"loss": 3.2635,
|
| 1340 |
+
"step": 189
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.015196960607878424,
|
| 1344 |
+
"grad_norm": 5.697634696960449,
|
| 1345 |
+
"learning_rate": 0.00019324722294043558,
|
| 1346 |
+
"loss": 4.5356,
|
| 1347 |
+
"step": 190
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.015276944611077784,
|
| 1351 |
+
"grad_norm": 4.195896148681641,
|
| 1352 |
+
"learning_rate": 0.0001931728516381073,
|
| 1353 |
+
"loss": 3.6118,
|
| 1354 |
+
"step": 191
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.015356928614277145,
|
| 1358 |
+
"grad_norm": 4.738584518432617,
|
| 1359 |
+
"learning_rate": 0.0001930980875044477,
|
| 1360 |
+
"loss": 4.2477,
|
| 1361 |
+
"step": 192
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.015436912617476505,
|
| 1365 |
+
"grad_norm": 4.4908623695373535,
|
| 1366 |
+
"learning_rate": 0.00019302293085467405,
|
| 1367 |
+
"loss": 3.6161,
|
| 1368 |
+
"step": 193
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.015516896620675865,
|
| 1372 |
+
"grad_norm": 3.800361394882202,
|
| 1373 |
+
"learning_rate": 0.00019294738200565856,
|
| 1374 |
+
"loss": 3.952,
|
| 1375 |
+
"step": 194
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.015596880623875225,
|
| 1379 |
+
"grad_norm": 4.386847972869873,
|
| 1380 |
+
"learning_rate": 0.00019287144127592704,
|
| 1381 |
+
"loss": 4.3552,
|
| 1382 |
+
"step": 195
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.015676864627074585,
|
| 1386 |
+
"grad_norm": 5.358420372009277,
|
| 1387 |
+
"learning_rate": 0.0001927951089856575,
|
| 1388 |
+
"loss": 4.2666,
|
| 1389 |
+
"step": 196
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.015756848630273945,
|
| 1393 |
+
"grad_norm": 5.825019359588623,
|
| 1394 |
+
"learning_rate": 0.00019271838545667876,
|
| 1395 |
+
"loss": 3.5997,
|
| 1396 |
+
"step": 197
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.015836832633473304,
|
| 1400 |
+
"grad_norm": 5.260373592376709,
|
| 1401 |
+
"learning_rate": 0.0001926412710124693,
|
| 1402 |
+
"loss": 4.0126,
|
| 1403 |
+
"step": 198
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.015916816636672666,
|
| 1407 |
+
"grad_norm": 5.913776874542236,
|
| 1408 |
+
"learning_rate": 0.00019256376597815564,
|
| 1409 |
+
"loss": 4.1883,
|
| 1410 |
+
"step": 199
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.015996800639872025,
|
| 1414 |
+
"grad_norm": 4.220345497131348,
|
| 1415 |
+
"learning_rate": 0.0001924858706805112,
|
| 1416 |
+
"loss": 3.3007,
|
| 1417 |
+
"step": 200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.016076784643071385,
|
| 1421 |
+
"grad_norm": 5.506844520568848,
|
| 1422 |
+
"learning_rate": 0.0001924075854479547,
|
| 1423 |
+
"loss": 4.8178,
|
| 1424 |
+
"step": 201
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.016156768646270747,
|
| 1428 |
+
"grad_norm": 4.918891906738281,
|
| 1429 |
+
"learning_rate": 0.00019232891061054895,
|
| 1430 |
+
"loss": 3.23,
|
| 1431 |
+
"step": 202
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.016236752649470106,
|
| 1435 |
+
"grad_norm": 5.011964797973633,
|
| 1436 |
+
"learning_rate": 0.0001922498464999994,
|
| 1437 |
+
"loss": 4.1303,
|
| 1438 |
+
"step": 203
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.016316736652669465,
|
| 1442 |
+
"grad_norm": 4.176311492919922,
|
| 1443 |
+
"learning_rate": 0.0001921703934496527,
|
| 1444 |
+
"loss": 3.845,
|
| 1445 |
+
"step": 204
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.016396720655868825,
|
| 1449 |
+
"grad_norm": 4.5768537521362305,
|
| 1450 |
+
"learning_rate": 0.0001920905517944954,
|
| 1451 |
+
"loss": 3.6125,
|
| 1452 |
+
"step": 205
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.016476704659068187,
|
| 1456 |
+
"grad_norm": 4.338911533355713,
|
| 1457 |
+
"learning_rate": 0.00019201032187115234,
|
| 1458 |
+
"loss": 3.5755,
|
| 1459 |
+
"step": 206
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.016556688662267546,
|
| 1463 |
+
"grad_norm": 4.148381233215332,
|
| 1464 |
+
"learning_rate": 0.0001919297040178855,
|
| 1465 |
+
"loss": 3.1388,
|
| 1466 |
+
"step": 207
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.016636672665466905,
|
| 1470 |
+
"grad_norm": 4.2749199867248535,
|
| 1471 |
+
"learning_rate": 0.00019184869857459232,
|
| 1472 |
+
"loss": 3.1602,
|
| 1473 |
+
"step": 208
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.016716656668666268,
|
| 1477 |
+
"grad_norm": 4.980453968048096,
|
| 1478 |
+
"learning_rate": 0.00019176730588280446,
|
| 1479 |
+
"loss": 5.2039,
|
| 1480 |
+
"step": 209
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.016796640671865627,
|
| 1484 |
+
"grad_norm": 3.6742446422576904,
|
| 1485 |
+
"learning_rate": 0.00019168552628568631,
|
| 1486 |
+
"loss": 3.8579,
|
| 1487 |
+
"step": 210
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.016876624675064986,
|
| 1491 |
+
"grad_norm": 5.142124176025391,
|
| 1492 |
+
"learning_rate": 0.00019160336012803337,
|
| 1493 |
+
"loss": 3.8598,
|
| 1494 |
+
"step": 211
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.016956608678264345,
|
| 1498 |
+
"grad_norm": 3.8903112411499023,
|
| 1499 |
+
"learning_rate": 0.00019152080775627103,
|
| 1500 |
+
"loss": 3.3726,
|
| 1501 |
+
"step": 212
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.017036592681463708,
|
| 1505 |
+
"grad_norm": 3.7564847469329834,
|
| 1506 |
+
"learning_rate": 0.0001914378695184531,
|
| 1507 |
+
"loss": 3.2007,
|
| 1508 |
+
"step": 213
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.017116576684663067,
|
| 1512 |
+
"grad_norm": 7.749126434326172,
|
| 1513 |
+
"learning_rate": 0.0001913545457642601,
|
| 1514 |
+
"loss": 3.9879,
|
| 1515 |
+
"step": 214
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.017196560687862426,
|
| 1519 |
+
"grad_norm": 3.9350130558013916,
|
| 1520 |
+
"learning_rate": 0.00019127083684499806,
|
| 1521 |
+
"loss": 2.8209,
|
| 1522 |
+
"step": 215
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.01727654469106179,
|
| 1526 |
+
"grad_norm": 4.431557655334473,
|
| 1527 |
+
"learning_rate": 0.00019118674311359684,
|
| 1528 |
+
"loss": 4.0645,
|
| 1529 |
+
"step": 216
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.017356528694261148,
|
| 1533 |
+
"grad_norm": 6.666266441345215,
|
| 1534 |
+
"learning_rate": 0.00019110226492460885,
|
| 1535 |
+
"loss": 5.2874,
|
| 1536 |
+
"step": 217
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.017436512697460507,
|
| 1540 |
+
"grad_norm": 4.859610080718994,
|
| 1541 |
+
"learning_rate": 0.0001910174026342073,
|
| 1542 |
+
"loss": 3.3933,
|
| 1543 |
+
"step": 218
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.017516496700659866,
|
| 1547 |
+
"grad_norm": 6.4448676109313965,
|
| 1548 |
+
"learning_rate": 0.00019093215660018493,
|
| 1549 |
+
"loss": 2.8147,
|
| 1550 |
+
"step": 219
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.01759648070385923,
|
| 1554 |
+
"grad_norm": 4.527115821838379,
|
| 1555 |
+
"learning_rate": 0.00019084652718195238,
|
| 1556 |
+
"loss": 4.2256,
|
| 1557 |
+
"step": 220
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.017676464707058588,
|
| 1561 |
+
"grad_norm": 5.745115280151367,
|
| 1562 |
+
"learning_rate": 0.00019076051474053665,
|
| 1563 |
+
"loss": 3.204,
|
| 1564 |
+
"step": 221
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.017756448710257947,
|
| 1568 |
+
"grad_norm": 5.867636680603027,
|
| 1569 |
+
"learning_rate": 0.00019067411963857967,
|
| 1570 |
+
"loss": 4.5293,
|
| 1571 |
+
"step": 222
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.01783643271345731,
|
| 1575 |
+
"grad_norm": 4.640747547149658,
|
| 1576 |
+
"learning_rate": 0.00019058734224033672,
|
| 1577 |
+
"loss": 4.6124,
|
| 1578 |
+
"step": 223
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.01791641671665667,
|
| 1582 |
+
"grad_norm": 3.6582233905792236,
|
| 1583 |
+
"learning_rate": 0.0001905001829116749,
|
| 1584 |
+
"loss": 2.5253,
|
| 1585 |
+
"step": 224
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.017996400719856028,
|
| 1589 |
+
"grad_norm": 5.60170841217041,
|
| 1590 |
+
"learning_rate": 0.0001904126420200716,
|
| 1591 |
+
"loss": 4.8805,
|
| 1592 |
+
"step": 225
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.018076384723055387,
|
| 1596 |
+
"grad_norm": 6.315110683441162,
|
| 1597 |
+
"learning_rate": 0.0001903247199346129,
|
| 1598 |
+
"loss": 4.0317,
|
| 1599 |
+
"step": 226
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.01815636872625475,
|
| 1603 |
+
"grad_norm": 3.8886184692382812,
|
| 1604 |
+
"learning_rate": 0.0001902364170259921,
|
| 1605 |
+
"loss": 4.6138,
|
| 1606 |
+
"step": 227
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.01823635272945411,
|
| 1610 |
+
"grad_norm": 5.318291664123535,
|
| 1611 |
+
"learning_rate": 0.00019014773366650807,
|
| 1612 |
+
"loss": 4.1923,
|
| 1613 |
+
"step": 228
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.018316336732653468,
|
| 1617 |
+
"grad_norm": 4.346369743347168,
|
| 1618 |
+
"learning_rate": 0.00019005867023006375,
|
| 1619 |
+
"loss": 3.8385,
|
| 1620 |
+
"step": 229
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.01839632073585283,
|
| 1624 |
+
"grad_norm": 6.551377296447754,
|
| 1625 |
+
"learning_rate": 0.00018996922709216455,
|
| 1626 |
+
"loss": 3.8002,
|
| 1627 |
+
"step": 230
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.01847630473905219,
|
| 1631 |
+
"grad_norm": 4.525792121887207,
|
| 1632 |
+
"learning_rate": 0.0001898794046299167,
|
| 1633 |
+
"loss": 2.9745,
|
| 1634 |
+
"step": 231
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.01855628874225155,
|
| 1638 |
+
"grad_norm": 4.6721625328063965,
|
| 1639 |
+
"learning_rate": 0.00018978920322202582,
|
| 1640 |
+
"loss": 4.3312,
|
| 1641 |
+
"step": 232
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.018636272745450908,
|
| 1645 |
+
"grad_norm": 6.13138484954834,
|
| 1646 |
+
"learning_rate": 0.00018969862324879513,
|
| 1647 |
+
"loss": 3.5232,
|
| 1648 |
+
"step": 233
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.01871625674865027,
|
| 1652 |
+
"grad_norm": 3.9804527759552,
|
| 1653 |
+
"learning_rate": 0.000189607665092124,
|
| 1654 |
+
"loss": 3.8828,
|
| 1655 |
+
"step": 234
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.01879624075184963,
|
| 1659 |
+
"grad_norm": 3.796212911605835,
|
| 1660 |
+
"learning_rate": 0.00018951632913550626,
|
| 1661 |
+
"loss": 3.4832,
|
| 1662 |
+
"step": 235
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.01887622475504899,
|
| 1666 |
+
"grad_norm": 3.9256110191345215,
|
| 1667 |
+
"learning_rate": 0.00018942461576402857,
|
| 1668 |
+
"loss": 4.0118,
|
| 1669 |
+
"step": 236
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.01895620875824835,
|
| 1673 |
+
"grad_norm": 4.6217474937438965,
|
| 1674 |
+
"learning_rate": 0.0001893325253643689,
|
| 1675 |
+
"loss": 3.6662,
|
| 1676 |
+
"step": 237
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.01903619276144771,
|
| 1680 |
+
"grad_norm": 7.017457485198975,
|
| 1681 |
+
"learning_rate": 0.00018924005832479478,
|
| 1682 |
+
"loss": 4.5404,
|
| 1683 |
+
"step": 238
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.01911617676464707,
|
| 1687 |
+
"grad_norm": 7.708695411682129,
|
| 1688 |
+
"learning_rate": 0.00018914721503516177,
|
| 1689 |
+
"loss": 5.2304,
|
| 1690 |
+
"step": 239
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.01919616076784643,
|
| 1694 |
+
"grad_norm": 4.276139736175537,
|
| 1695 |
+
"learning_rate": 0.00018905399588691163,
|
| 1696 |
+
"loss": 4.0688,
|
| 1697 |
+
"step": 240
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.01927614477104579,
|
| 1701 |
+
"grad_norm": 3.8450303077697754,
|
| 1702 |
+
"learning_rate": 0.00018896040127307098,
|
| 1703 |
+
"loss": 4.257,
|
| 1704 |
+
"step": 241
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.01935612877424515,
|
| 1708 |
+
"grad_norm": 5.30068826675415,
|
| 1709 |
+
"learning_rate": 0.0001888664315882493,
|
| 1710 |
+
"loss": 5.0476,
|
| 1711 |
+
"step": 242
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.01943611277744451,
|
| 1715 |
+
"grad_norm": 5.693291664123535,
|
| 1716 |
+
"learning_rate": 0.0001887720872286375,
|
| 1717 |
+
"loss": 3.6242,
|
| 1718 |
+
"step": 243
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.019516096780643873,
|
| 1722 |
+
"grad_norm": 4.2235426902771,
|
| 1723 |
+
"learning_rate": 0.0001886773685920062,
|
| 1724 |
+
"loss": 4.0089,
|
| 1725 |
+
"step": 244
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.019596080783843232,
|
| 1729 |
+
"grad_norm": 3.830811023712158,
|
| 1730 |
+
"learning_rate": 0.00018858227607770398,
|
| 1731 |
+
"loss": 3.2782,
|
| 1732 |
+
"step": 245
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.01967606478704259,
|
| 1736 |
+
"grad_norm": 4.885007381439209,
|
| 1737 |
+
"learning_rate": 0.00018848681008665582,
|
| 1738 |
+
"loss": 4.5444,
|
| 1739 |
+
"step": 246
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.01975604879024195,
|
| 1743 |
+
"grad_norm": 4.123133659362793,
|
| 1744 |
+
"learning_rate": 0.0001883909710213612,
|
| 1745 |
+
"loss": 3.8321,
|
| 1746 |
+
"step": 247
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.019836032793441313,
|
| 1750 |
+
"grad_norm": 4.4161553382873535,
|
| 1751 |
+
"learning_rate": 0.00018829475928589271,
|
| 1752 |
+
"loss": 3.9976,
|
| 1753 |
+
"step": 248
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.019916016796640672,
|
| 1757 |
+
"grad_norm": 4.6640119552612305,
|
| 1758 |
+
"learning_rate": 0.00018819817528589402,
|
| 1759 |
+
"loss": 5.2068,
|
| 1760 |
+
"step": 249
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.01999600079984003,
|
| 1764 |
+
"grad_norm": 3.815941572189331,
|
| 1765 |
+
"learning_rate": 0.00018810121942857845,
|
| 1766 |
+
"loss": 3.5509,
|
| 1767 |
+
"step": 250
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.020075984803039394,
|
| 1771 |
+
"grad_norm": 4.366556167602539,
|
| 1772 |
+
"learning_rate": 0.00018800389212272707,
|
| 1773 |
+
"loss": 4.0747,
|
| 1774 |
+
"step": 251
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.020155968806238753,
|
| 1778 |
+
"grad_norm": 4.601415157318115,
|
| 1779 |
+
"learning_rate": 0.00018790619377868703,
|
| 1780 |
+
"loss": 4.1809,
|
| 1781 |
+
"step": 252
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.020235952809438112,
|
| 1785 |
+
"grad_norm": 3.5466244220733643,
|
| 1786 |
+
"learning_rate": 0.0001878081248083698,
|
| 1787 |
+
"loss": 3.5347,
|
| 1788 |
+
"step": 253
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.02031593681263747,
|
| 1792 |
+
"grad_norm": 4.740442752838135,
|
| 1793 |
+
"learning_rate": 0.0001877096856252496,
|
| 1794 |
+
"loss": 4.3345,
|
| 1795 |
+
"step": 254
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.020395920815836834,
|
| 1799 |
+
"grad_norm": 4.473808288574219,
|
| 1800 |
+
"learning_rate": 0.00018761087664436138,
|
| 1801 |
+
"loss": 3.6354,
|
| 1802 |
+
"step": 255
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.020475904819036193,
|
| 1806 |
+
"grad_norm": 5.302408695220947,
|
| 1807 |
+
"learning_rate": 0.00018751169828229927,
|
| 1808 |
+
"loss": 4.7978,
|
| 1809 |
+
"step": 256
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.020555888822235552,
|
| 1813 |
+
"grad_norm": 4.8885698318481445,
|
| 1814 |
+
"learning_rate": 0.00018741215095721483,
|
| 1815 |
+
"loss": 4.3185,
|
| 1816 |
+
"step": 257
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.020635872825434914,
|
| 1820 |
+
"grad_norm": 4.722813129425049,
|
| 1821 |
+
"learning_rate": 0.0001873122350888151,
|
| 1822 |
+
"loss": 4.2099,
|
| 1823 |
+
"step": 258
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.020715856828634274,
|
| 1827 |
+
"grad_norm": 4.454716205596924,
|
| 1828 |
+
"learning_rate": 0.0001872119510983611,
|
| 1829 |
+
"loss": 3.6928,
|
| 1830 |
+
"step": 259
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.020795840831833633,
|
| 1834 |
+
"grad_norm": 4.948916435241699,
|
| 1835 |
+
"learning_rate": 0.00018711129940866575,
|
| 1836 |
+
"loss": 4.193,
|
| 1837 |
+
"step": 260
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.020875824835032992,
|
| 1841 |
+
"grad_norm": 4.173530578613281,
|
| 1842 |
+
"learning_rate": 0.00018701028044409244,
|
| 1843 |
+
"loss": 3.6785,
|
| 1844 |
+
"step": 261
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.020955808838232354,
|
| 1848 |
+
"grad_norm": 4.344187259674072,
|
| 1849 |
+
"learning_rate": 0.00018690889463055283,
|
| 1850 |
+
"loss": 4.2572,
|
| 1851 |
+
"step": 262
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.021035792841431714,
|
| 1855 |
+
"grad_norm": 4.657215595245361,
|
| 1856 |
+
"learning_rate": 0.00018680714239550548,
|
| 1857 |
+
"loss": 4.4998,
|
| 1858 |
+
"step": 263
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.021115776844631073,
|
| 1862 |
+
"grad_norm": 4.247788906097412,
|
| 1863 |
+
"learning_rate": 0.00018670502416795367,
|
| 1864 |
+
"loss": 3.063,
|
| 1865 |
+
"step": 264
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.021195760847830435,
|
| 1869 |
+
"grad_norm": 3.5779287815093994,
|
| 1870 |
+
"learning_rate": 0.00018660254037844388,
|
| 1871 |
+
"loss": 3.5982,
|
| 1872 |
+
"step": 265
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.021275744851029794,
|
| 1876 |
+
"grad_norm": 6.588551044464111,
|
| 1877 |
+
"learning_rate": 0.0001864996914590638,
|
| 1878 |
+
"loss": 4.7009,
|
| 1879 |
+
"step": 266
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.021355728854229154,
|
| 1883 |
+
"grad_norm": 6.7050395011901855,
|
| 1884 |
+
"learning_rate": 0.00018639647784344057,
|
| 1885 |
+
"loss": 4.9945,
|
| 1886 |
+
"step": 267
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.021435712857428513,
|
| 1890 |
+
"grad_norm": 4.874384880065918,
|
| 1891 |
+
"learning_rate": 0.00018629289996673897,
|
| 1892 |
+
"loss": 3.8558,
|
| 1893 |
+
"step": 268
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.021515696860627875,
|
| 1897 |
+
"grad_norm": 4.827778339385986,
|
| 1898 |
+
"learning_rate": 0.00018618895826565956,
|
| 1899 |
+
"loss": 3.3468,
|
| 1900 |
+
"step": 269
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.021595680863827234,
|
| 1904 |
+
"grad_norm": 3.7480504512786865,
|
| 1905 |
+
"learning_rate": 0.00018608465317843678,
|
| 1906 |
+
"loss": 2.802,
|
| 1907 |
+
"step": 270
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.021675664867026594,
|
| 1911 |
+
"grad_norm": 3.7615654468536377,
|
| 1912 |
+
"learning_rate": 0.00018597998514483725,
|
| 1913 |
+
"loss": 3.4261,
|
| 1914 |
+
"step": 271
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.021755648870225956,
|
| 1918 |
+
"grad_norm": 4.826491355895996,
|
| 1919 |
+
"learning_rate": 0.00018587495460615778,
|
| 1920 |
+
"loss": 4.5241,
|
| 1921 |
+
"step": 272
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.021835632873425315,
|
| 1925 |
+
"grad_norm": 4.077682018280029,
|
| 1926 |
+
"learning_rate": 0.00018576956200522354,
|
| 1927 |
+
"loss": 3.3679,
|
| 1928 |
+
"step": 273
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.021915616876624675,
|
| 1932 |
+
"grad_norm": 4.723017692565918,
|
| 1933 |
+
"learning_rate": 0.00018566380778638628,
|
| 1934 |
+
"loss": 4.3965,
|
| 1935 |
+
"step": 274
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.021995600879824034,
|
| 1939 |
+
"grad_norm": 4.252414703369141,
|
| 1940 |
+
"learning_rate": 0.00018555769239552233,
|
| 1941 |
+
"loss": 3.0784,
|
| 1942 |
+
"step": 275
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.022075584883023396,
|
| 1946 |
+
"grad_norm": 5.542708396911621,
|
| 1947 |
+
"learning_rate": 0.00018545121628003077,
|
| 1948 |
+
"loss": 4.9838,
|
| 1949 |
+
"step": 276
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.022155568886222755,
|
| 1953 |
+
"grad_norm": 5.040409088134766,
|
| 1954 |
+
"learning_rate": 0.0001853443798888316,
|
| 1955 |
+
"loss": 4.732,
|
| 1956 |
+
"step": 277
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.022235552889422115,
|
| 1960 |
+
"grad_norm": 5.463371276855469,
|
| 1961 |
+
"learning_rate": 0.0001852371836723638,
|
| 1962 |
+
"loss": 3.2822,
|
| 1963 |
+
"step": 278
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.022315536892621477,
|
| 1967 |
+
"grad_norm": 4.664473056793213,
|
| 1968 |
+
"learning_rate": 0.0001851296280825833,
|
| 1969 |
+
"loss": 4.2588,
|
| 1970 |
+
"step": 279
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.022395520895820836,
|
| 1974 |
+
"grad_norm": 3.489403009414673,
|
| 1975 |
+
"learning_rate": 0.00018502171357296144,
|
| 1976 |
+
"loss": 2.7776,
|
| 1977 |
+
"step": 280
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.022475504899020195,
|
| 1981 |
+
"grad_norm": 4.194101810455322,
|
| 1982 |
+
"learning_rate": 0.00018491344059848257,
|
| 1983 |
+
"loss": 3.9611,
|
| 1984 |
+
"step": 281
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.022555488902219555,
|
| 1988 |
+
"grad_norm": 3.926426887512207,
|
| 1989 |
+
"learning_rate": 0.0001848048096156426,
|
| 1990 |
+
"loss": 4.4041,
|
| 1991 |
+
"step": 282
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.022635472905418917,
|
| 1995 |
+
"grad_norm": 4.642327308654785,
|
| 1996 |
+
"learning_rate": 0.0001846958210824467,
|
| 1997 |
+
"loss": 3.755,
|
| 1998 |
+
"step": 283
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.022715456908618276,
|
| 2002 |
+
"grad_norm": 4.824521064758301,
|
| 2003 |
+
"learning_rate": 0.00018458647545840763,
|
| 2004 |
+
"loss": 3.2453,
|
| 2005 |
+
"step": 284
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.022795440911817635,
|
| 2009 |
+
"grad_norm": 4.623475074768066,
|
| 2010 |
+
"learning_rate": 0.00018447677320454367,
|
| 2011 |
+
"loss": 3.9445,
|
| 2012 |
+
"step": 285
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.022875424915016998,
|
| 2016 |
+
"grad_norm": 5.094510555267334,
|
| 2017 |
+
"learning_rate": 0.00018436671478337666,
|
| 2018 |
+
"loss": 4.0939,
|
| 2019 |
+
"step": 286
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.022955408918216357,
|
| 2023 |
+
"grad_norm": 4.4365339279174805,
|
| 2024 |
+
"learning_rate": 0.00018425630065893014,
|
| 2025 |
+
"loss": 3.676,
|
| 2026 |
+
"step": 287
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.023035392921415716,
|
| 2030 |
+
"grad_norm": 4.2287187576293945,
|
| 2031 |
+
"learning_rate": 0.00018414553129672732,
|
| 2032 |
+
"loss": 4.9768,
|
| 2033 |
+
"step": 288
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.023115376924615075,
|
| 2037 |
+
"grad_norm": 4.334507465362549,
|
| 2038 |
+
"learning_rate": 0.00018403440716378928,
|
| 2039 |
+
"loss": 3.5081,
|
| 2040 |
+
"step": 289
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.023195360927814438,
|
| 2044 |
+
"grad_norm": 4.643796443939209,
|
| 2045 |
+
"learning_rate": 0.00018392292872863267,
|
| 2046 |
+
"loss": 2.7211,
|
| 2047 |
+
"step": 290
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.023275344931013797,
|
| 2051 |
+
"grad_norm": 5.521508693695068,
|
| 2052 |
+
"learning_rate": 0.00018381109646126807,
|
| 2053 |
+
"loss": 3.4703,
|
| 2054 |
+
"step": 291
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.023355328934213156,
|
| 2058 |
+
"grad_norm": 18.558773040771484,
|
| 2059 |
+
"learning_rate": 0.00018369891083319778,
|
| 2060 |
+
"loss": 4.6301,
|
| 2061 |
+
"step": 292
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.02343531293741252,
|
| 2065 |
+
"grad_norm": 4.116851806640625,
|
| 2066 |
+
"learning_rate": 0.00018358637231741405,
|
| 2067 |
+
"loss": 2.6934,
|
| 2068 |
+
"step": 293
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.023515296940611878,
|
| 2072 |
+
"grad_norm": 3.7274317741394043,
|
| 2073 |
+
"learning_rate": 0.00018347348138839683,
|
| 2074 |
+
"loss": 3.3539,
|
| 2075 |
+
"step": 294
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.023595280943811237,
|
| 2079 |
+
"grad_norm": 4.779667854309082,
|
| 2080 |
+
"learning_rate": 0.00018336023852211195,
|
| 2081 |
+
"loss": 4.4736,
|
| 2082 |
+
"step": 295
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.023675264947010596,
|
| 2086 |
+
"grad_norm": 3.460465669631958,
|
| 2087 |
+
"learning_rate": 0.0001832466441960091,
|
| 2088 |
+
"loss": 3.0599,
|
| 2089 |
+
"step": 296
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.02375524895020996,
|
| 2093 |
+
"grad_norm": 5.266543388366699,
|
| 2094 |
+
"learning_rate": 0.0001831326988890197,
|
| 2095 |
+
"loss": 4.399,
|
| 2096 |
+
"step": 297
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.023835232953409318,
|
| 2100 |
+
"grad_norm": 5.425334453582764,
|
| 2101 |
+
"learning_rate": 0.00018301840308155507,
|
| 2102 |
+
"loss": 4.8967,
|
| 2103 |
+
"step": 298
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.023915216956608677,
|
| 2107 |
+
"grad_norm": 4.659543037414551,
|
| 2108 |
+
"learning_rate": 0.00018290375725550417,
|
| 2109 |
+
"loss": 3.5647,
|
| 2110 |
+
"step": 299
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.02399520095980804,
|
| 2114 |
+
"grad_norm": 4.593050956726074,
|
| 2115 |
+
"learning_rate": 0.00018278876189423179,
|
| 2116 |
+
"loss": 4.2569,
|
| 2117 |
+
"step": 300
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.0240751849630074,
|
| 2121 |
+
"grad_norm": 5.206689357757568,
|
| 2122 |
+
"learning_rate": 0.00018267341748257635,
|
| 2123 |
+
"loss": 4.7223,
|
| 2124 |
+
"step": 301
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.024155168966206758,
|
| 2128 |
+
"grad_norm": 5.0191650390625,
|
| 2129 |
+
"learning_rate": 0.00018255772450684798,
|
| 2130 |
+
"loss": 3.9914,
|
| 2131 |
+
"step": 302
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.024235152969406117,
|
| 2135 |
+
"grad_norm": 5.315042018890381,
|
| 2136 |
+
"learning_rate": 0.00018244168345482635,
|
| 2137 |
+
"loss": 3.8242,
|
| 2138 |
+
"step": 303
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.02431513697260548,
|
| 2142 |
+
"grad_norm": 3.8089730739593506,
|
| 2143 |
+
"learning_rate": 0.00018232529481575872,
|
| 2144 |
+
"loss": 3.3759,
|
| 2145 |
+
"step": 304
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.02439512097580484,
|
| 2149 |
+
"grad_norm": 4.05519962310791,
|
| 2150 |
+
"learning_rate": 0.00018220855908035783,
|
| 2151 |
+
"loss": 4.3841,
|
| 2152 |
+
"step": 305
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.024475104979004198,
|
| 2156 |
+
"grad_norm": 4.002076148986816,
|
| 2157 |
+
"learning_rate": 0.00018209147674079983,
|
| 2158 |
+
"loss": 2.8373,
|
| 2159 |
+
"step": 306
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.02455508898220356,
|
| 2163 |
+
"grad_norm": 7.781075954437256,
|
| 2164 |
+
"learning_rate": 0.00018197404829072215,
|
| 2165 |
+
"loss": 4.7255,
|
| 2166 |
+
"step": 307
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.02463507298540292,
|
| 2170 |
+
"grad_norm": 4.209305286407471,
|
| 2171 |
+
"learning_rate": 0.00018185627422522148,
|
| 2172 |
+
"loss": 4.07,
|
| 2173 |
+
"step": 308
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.02471505698860228,
|
| 2177 |
+
"grad_norm": 5.018499374389648,
|
| 2178 |
+
"learning_rate": 0.00018173815504085185,
|
| 2179 |
+
"loss": 5.1119,
|
| 2180 |
+
"step": 309
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.024795040991801638,
|
| 2184 |
+
"grad_norm": 4.057737350463867,
|
| 2185 |
+
"learning_rate": 0.0001816196912356222,
|
| 2186 |
+
"loss": 3.4909,
|
| 2187 |
+
"step": 310
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.024875024995001,
|
| 2191 |
+
"grad_norm": 3.992469549179077,
|
| 2192 |
+
"learning_rate": 0.00018150088330899438,
|
| 2193 |
+
"loss": 3.5484,
|
| 2194 |
+
"step": 311
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.02495500899820036,
|
| 2198 |
+
"grad_norm": 3.899209499359131,
|
| 2199 |
+
"learning_rate": 0.00018138173176188133,
|
| 2200 |
+
"loss": 3.4713,
|
| 2201 |
+
"step": 312
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.02503499300139972,
|
| 2205 |
+
"grad_norm": 3.767697334289551,
|
| 2206 |
+
"learning_rate": 0.00018126223709664458,
|
| 2207 |
+
"loss": 3.6896,
|
| 2208 |
+
"step": 313
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.02511497700459908,
|
| 2212 |
+
"grad_norm": 4.881612300872803,
|
| 2213 |
+
"learning_rate": 0.00018114239981709232,
|
| 2214 |
+
"loss": 5.9193,
|
| 2215 |
+
"step": 314
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.02519496100779844,
|
| 2219 |
+
"grad_norm": 4.717601299285889,
|
| 2220 |
+
"learning_rate": 0.00018102222042847737,
|
| 2221 |
+
"loss": 3.0861,
|
| 2222 |
+
"step": 315
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.0252749450109978,
|
| 2226 |
+
"grad_norm": 4.3629655838012695,
|
| 2227 |
+
"learning_rate": 0.00018090169943749476,
|
| 2228 |
+
"loss": 3.9999,
|
| 2229 |
+
"step": 316
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.02535492901419716,
|
| 2233 |
+
"grad_norm": 3.4362242221832275,
|
| 2234 |
+
"learning_rate": 0.0001807808373522799,
|
| 2235 |
+
"loss": 2.9295,
|
| 2236 |
+
"step": 317
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.02543491301739652,
|
| 2240 |
+
"grad_norm": 4.793106555938721,
|
| 2241 |
+
"learning_rate": 0.00018065963468240625,
|
| 2242 |
+
"loss": 4.5639,
|
| 2243 |
+
"step": 318
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.02551489702059588,
|
| 2247 |
+
"grad_norm": 4.6200995445251465,
|
| 2248 |
+
"learning_rate": 0.00018053809193888326,
|
| 2249 |
+
"loss": 4.0014,
|
| 2250 |
+
"step": 319
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.02559488102379524,
|
| 2254 |
+
"grad_norm": 4.23821496963501,
|
| 2255 |
+
"learning_rate": 0.00018041620963415417,
|
| 2256 |
+
"loss": 3.8532,
|
| 2257 |
+
"step": 320
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.025674865026994603,
|
| 2261 |
+
"grad_norm": 3.4566526412963867,
|
| 2262 |
+
"learning_rate": 0.00018029398828209385,
|
| 2263 |
+
"loss": 3.0738,
|
| 2264 |
+
"step": 321
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.02575484903019396,
|
| 2268 |
+
"grad_norm": 4.199108123779297,
|
| 2269 |
+
"learning_rate": 0.00018017142839800668,
|
| 2270 |
+
"loss": 3.502,
|
| 2271 |
+
"step": 322
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.02583483303339332,
|
| 2275 |
+
"grad_norm": 5.139927864074707,
|
| 2276 |
+
"learning_rate": 0.00018004853049862426,
|
| 2277 |
+
"loss": 4.6712,
|
| 2278 |
+
"step": 323
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.02591481703659268,
|
| 2282 |
+
"grad_norm": 3.8838582038879395,
|
| 2283 |
+
"learning_rate": 0.00017992529510210348,
|
| 2284 |
+
"loss": 3.6336,
|
| 2285 |
+
"step": 324
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.025994801039792043,
|
| 2289 |
+
"grad_norm": 4.37532377243042,
|
| 2290 |
+
"learning_rate": 0.000179801722728024,
|
| 2291 |
+
"loss": 3.3539,
|
| 2292 |
+
"step": 325
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.0260747850429914,
|
| 2296 |
+
"grad_norm": 3.94706392288208,
|
| 2297 |
+
"learning_rate": 0.00017967781389738625,
|
| 2298 |
+
"loss": 3.2856,
|
| 2299 |
+
"step": 326
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.02615476904619076,
|
| 2303 |
+
"grad_norm": 4.521001815795898,
|
| 2304 |
+
"learning_rate": 0.00017955356913260933,
|
| 2305 |
+
"loss": 3.8893,
|
| 2306 |
+
"step": 327
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.026234753049390123,
|
| 2310 |
+
"grad_norm": 5.034095764160156,
|
| 2311 |
+
"learning_rate": 0.0001794289889575286,
|
| 2312 |
+
"loss": 3.3198,
|
| 2313 |
+
"step": 328
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.026314737052589483,
|
| 2317 |
+
"grad_norm": 5.225372791290283,
|
| 2318 |
+
"learning_rate": 0.00017930407389739363,
|
| 2319 |
+
"loss": 3.2792,
|
| 2320 |
+
"step": 329
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.026394721055788842,
|
| 2324 |
+
"grad_norm": 4.562963962554932,
|
| 2325 |
+
"learning_rate": 0.00017917882447886582,
|
| 2326 |
+
"loss": 4.2738,
|
| 2327 |
+
"step": 330
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.0264747050589882,
|
| 2331 |
+
"grad_norm": 4.397261142730713,
|
| 2332 |
+
"learning_rate": 0.00017905324123001633,
|
| 2333 |
+
"loss": 3.7458,
|
| 2334 |
+
"step": 331
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.026554689062187564,
|
| 2338 |
+
"grad_norm": 4.76125955581665,
|
| 2339 |
+
"learning_rate": 0.00017892732468032386,
|
| 2340 |
+
"loss": 3.6008,
|
| 2341 |
+
"step": 332
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.026634673065386923,
|
| 2345 |
+
"grad_norm": 4.582405090332031,
|
| 2346 |
+
"learning_rate": 0.00017880107536067218,
|
| 2347 |
+
"loss": 3.7548,
|
| 2348 |
+
"step": 333
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.026714657068586282,
|
| 2352 |
+
"grad_norm": 4.324102401733398,
|
| 2353 |
+
"learning_rate": 0.00017867449380334834,
|
| 2354 |
+
"loss": 3.357,
|
| 2355 |
+
"step": 334
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.026794641071785644,
|
| 2359 |
+
"grad_norm": 5.060311317443848,
|
| 2360 |
+
"learning_rate": 0.00017854758054203988,
|
| 2361 |
+
"loss": 4.4687,
|
| 2362 |
+
"step": 335
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.026874625074985004,
|
| 2366 |
+
"grad_norm": 3.645390033721924,
|
| 2367 |
+
"learning_rate": 0.00017842033611183307,
|
| 2368 |
+
"loss": 3.6036,
|
| 2369 |
+
"step": 336
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.026954609078184363,
|
| 2373 |
+
"grad_norm": 4.807192325592041,
|
| 2374 |
+
"learning_rate": 0.00017829276104921028,
|
| 2375 |
+
"loss": 4.1459,
|
| 2376 |
+
"step": 337
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.027034593081383722,
|
| 2380 |
+
"grad_norm": 5.273848056793213,
|
| 2381 |
+
"learning_rate": 0.00017816485589204801,
|
| 2382 |
+
"loss": 3.9517,
|
| 2383 |
+
"step": 338
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.027114577084583084,
|
| 2387 |
+
"grad_norm": 3.860368013381958,
|
| 2388 |
+
"learning_rate": 0.00017803662117961438,
|
| 2389 |
+
"loss": 3.0302,
|
| 2390 |
+
"step": 339
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.027194561087782444,
|
| 2394 |
+
"grad_norm": 4.04617977142334,
|
| 2395 |
+
"learning_rate": 0.00017790805745256704,
|
| 2396 |
+
"loss": 3.5597,
|
| 2397 |
+
"step": 340
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.027274545090981803,
|
| 2401 |
+
"grad_norm": 4.716963768005371,
|
| 2402 |
+
"learning_rate": 0.0001777791652529508,
|
| 2403 |
+
"loss": 3.8941,
|
| 2404 |
+
"step": 341
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.027354529094181165,
|
| 2408 |
+
"grad_norm": 5.491020202636719,
|
| 2409 |
+
"learning_rate": 0.00017764994512419534,
|
| 2410 |
+
"loss": 4.2495,
|
| 2411 |
+
"step": 342
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.027434513097380524,
|
| 2415 |
+
"grad_norm": 4.510169982910156,
|
| 2416 |
+
"learning_rate": 0.00017752039761111297,
|
| 2417 |
+
"loss": 3.5249,
|
| 2418 |
+
"step": 343
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.027514497100579884,
|
| 2422 |
+
"grad_norm": 7.709770202636719,
|
| 2423 |
+
"learning_rate": 0.0001773905232598963,
|
| 2424 |
+
"loss": 4.3635,
|
| 2425 |
+
"step": 344
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.027594481103779243,
|
| 2429 |
+
"grad_norm": 4.040260314941406,
|
| 2430 |
+
"learning_rate": 0.0001772603226181159,
|
| 2431 |
+
"loss": 3.3084,
|
| 2432 |
+
"step": 345
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.027674465106978605,
|
| 2436 |
+
"grad_norm": 10.078537940979004,
|
| 2437 |
+
"learning_rate": 0.00017712979623471807,
|
| 2438 |
+
"loss": 4.2793,
|
| 2439 |
+
"step": 346
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.027754449110177964,
|
| 2443 |
+
"grad_norm": 4.819201469421387,
|
| 2444 |
+
"learning_rate": 0.0001769989446600225,
|
| 2445 |
+
"loss": 4.2297,
|
| 2446 |
+
"step": 347
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.027834433113377324,
|
| 2450 |
+
"grad_norm": 3.5136406421661377,
|
| 2451 |
+
"learning_rate": 0.00017686776844571988,
|
| 2452 |
+
"loss": 3.05,
|
| 2453 |
+
"step": 348
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.027914417116576686,
|
| 2457 |
+
"grad_norm": 5.069991111755371,
|
| 2458 |
+
"learning_rate": 0.0001767362681448697,
|
| 2459 |
+
"loss": 4.6393,
|
| 2460 |
+
"step": 349
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.027994401119776045,
|
| 2464 |
+
"grad_norm": 5.238731384277344,
|
| 2465 |
+
"learning_rate": 0.0001766044443118978,
|
| 2466 |
+
"loss": 4.2915,
|
| 2467 |
+
"step": 350
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.028074385122975404,
|
| 2471 |
+
"grad_norm": 7.37299919128418,
|
| 2472 |
+
"learning_rate": 0.00017647229750259412,
|
| 2473 |
+
"loss": 4.3018,
|
| 2474 |
+
"step": 351
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.028154369126174764,
|
| 2478 |
+
"grad_norm": 4.723372459411621,
|
| 2479 |
+
"learning_rate": 0.00017633982827411032,
|
| 2480 |
+
"loss": 2.7848,
|
| 2481 |
+
"step": 352
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.028234353129374126,
|
| 2485 |
+
"grad_norm": 4.730043411254883,
|
| 2486 |
+
"learning_rate": 0.00017620703718495735,
|
| 2487 |
+
"loss": 4.3046,
|
| 2488 |
+
"step": 353
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.028314337132573485,
|
| 2492 |
+
"grad_norm": 5.053976535797119,
|
| 2493 |
+
"learning_rate": 0.00017607392479500325,
|
| 2494 |
+
"loss": 3.5784,
|
| 2495 |
+
"step": 354
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.028394321135772844,
|
| 2499 |
+
"grad_norm": 3.9743452072143555,
|
| 2500 |
+
"learning_rate": 0.00017594049166547073,
|
| 2501 |
+
"loss": 3.5196,
|
| 2502 |
+
"step": 355
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.028474305138972207,
|
| 2506 |
+
"grad_norm": 3.9845669269561768,
|
| 2507 |
+
"learning_rate": 0.00017580673835893473,
|
| 2508 |
+
"loss": 3.56,
|
| 2509 |
+
"step": 356
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.028554289142171566,
|
| 2513 |
+
"grad_norm": 4.781105995178223,
|
| 2514 |
+
"learning_rate": 0.00017567266543932014,
|
| 2515 |
+
"loss": 4.1717,
|
| 2516 |
+
"step": 357
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.028634273145370925,
|
| 2520 |
+
"grad_norm": 6.14730167388916,
|
| 2521 |
+
"learning_rate": 0.00017553827347189938,
|
| 2522 |
+
"loss": 3.501,
|
| 2523 |
+
"step": 358
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.028714257148570285,
|
| 2527 |
+
"grad_norm": 4.144578456878662,
|
| 2528 |
+
"learning_rate": 0.00017540356302329007,
|
| 2529 |
+
"loss": 3.6008,
|
| 2530 |
+
"step": 359
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.028794241151769647,
|
| 2534 |
+
"grad_norm": 4.807369709014893,
|
| 2535 |
+
"learning_rate": 0.00017526853466145244,
|
| 2536 |
+
"loss": 4.4085,
|
| 2537 |
+
"step": 360
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.028874225154969006,
|
| 2541 |
+
"grad_norm": 3.8738791942596436,
|
| 2542 |
+
"learning_rate": 0.00017513318895568737,
|
| 2543 |
+
"loss": 2.7231,
|
| 2544 |
+
"step": 361
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.028954209158168365,
|
| 2548 |
+
"grad_norm": 4.871976852416992,
|
| 2549 |
+
"learning_rate": 0.0001749975264766334,
|
| 2550 |
+
"loss": 4.6136,
|
| 2551 |
+
"step": 362
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.029034193161367728,
|
| 2555 |
+
"grad_norm": 3.6613216400146484,
|
| 2556 |
+
"learning_rate": 0.00017486154779626482,
|
| 2557 |
+
"loss": 3.2433,
|
| 2558 |
+
"step": 363
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.029114177164567087,
|
| 2562 |
+
"grad_norm": 6.628910064697266,
|
| 2563 |
+
"learning_rate": 0.0001747252534878891,
|
| 2564 |
+
"loss": 4.12,
|
| 2565 |
+
"step": 364
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.029194161167766446,
|
| 2569 |
+
"grad_norm": 3.9633758068084717,
|
| 2570 |
+
"learning_rate": 0.00017458864412614434,
|
| 2571 |
+
"loss": 3.3254,
|
| 2572 |
+
"step": 365
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.029274145170965805,
|
| 2576 |
+
"grad_norm": 5.479128837585449,
|
| 2577 |
+
"learning_rate": 0.000174451720286997,
|
| 2578 |
+
"loss": 4.8234,
|
| 2579 |
+
"step": 366
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.029354129174165168,
|
| 2583 |
+
"grad_norm": 5.950286388397217,
|
| 2584 |
+
"learning_rate": 0.00017431448254773944,
|
| 2585 |
+
"loss": 5.4012,
|
| 2586 |
+
"step": 367
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.029434113177364527,
|
| 2590 |
+
"grad_norm": 3.8191025257110596,
|
| 2591 |
+
"learning_rate": 0.00017417693148698743,
|
| 2592 |
+
"loss": 3.1482,
|
| 2593 |
+
"step": 368
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.029514097180563886,
|
| 2597 |
+
"grad_norm": 3.818920135498047,
|
| 2598 |
+
"learning_rate": 0.0001740390676846778,
|
| 2599 |
+
"loss": 4.2181,
|
| 2600 |
+
"step": 369
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.02959408118376325,
|
| 2604 |
+
"grad_norm": 4.036929607391357,
|
| 2605 |
+
"learning_rate": 0.00017390089172206592,
|
| 2606 |
+
"loss": 3.2691,
|
| 2607 |
+
"step": 370
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.029674065186962608,
|
| 2611 |
+
"grad_norm": 3.912344217300415,
|
| 2612 |
+
"learning_rate": 0.0001737624041817233,
|
| 2613 |
+
"loss": 3.7853,
|
| 2614 |
+
"step": 371
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.029754049190161967,
|
| 2618 |
+
"grad_norm": 4.815845012664795,
|
| 2619 |
+
"learning_rate": 0.00017362360564753505,
|
| 2620 |
+
"loss": 4.7852,
|
| 2621 |
+
"step": 372
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.029834033193361326,
|
| 2625 |
+
"grad_norm": 4.733504772186279,
|
| 2626 |
+
"learning_rate": 0.00017348449670469756,
|
| 2627 |
+
"loss": 5.0045,
|
| 2628 |
+
"step": 373
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.02991401719656069,
|
| 2632 |
+
"grad_norm": 3.8281900882720947,
|
| 2633 |
+
"learning_rate": 0.00017334507793971592,
|
| 2634 |
+
"loss": 3.4749,
|
| 2635 |
+
"step": 374
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.029994001199760048,
|
| 2639 |
+
"grad_norm": 4.226433277130127,
|
| 2640 |
+
"learning_rate": 0.00017320534994040148,
|
| 2641 |
+
"loss": 3.6603,
|
| 2642 |
+
"step": 375
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.030073985202959407,
|
| 2646 |
+
"grad_norm": 3.6558430194854736,
|
| 2647 |
+
"learning_rate": 0.00017306531329586933,
|
| 2648 |
+
"loss": 3.5563,
|
| 2649 |
+
"step": 376
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.03015396920615877,
|
| 2653 |
+
"grad_norm": 3.7194387912750244,
|
| 2654 |
+
"learning_rate": 0.00017292496859653588,
|
| 2655 |
+
"loss": 3.1529,
|
| 2656 |
+
"step": 377
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.03023395320935813,
|
| 2660 |
+
"grad_norm": 4.224362373352051,
|
| 2661 |
+
"learning_rate": 0.00017278431643411642,
|
| 2662 |
+
"loss": 3.0775,
|
| 2663 |
+
"step": 378
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.030313937212557488,
|
| 2667 |
+
"grad_norm": 4.306207656860352,
|
| 2668 |
+
"learning_rate": 0.00017264335740162242,
|
| 2669 |
+
"loss": 3.2271,
|
| 2670 |
+
"step": 379
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.030393921215756847,
|
| 2674 |
+
"grad_norm": 6.243900775909424,
|
| 2675 |
+
"learning_rate": 0.00017250209209335927,
|
| 2676 |
+
"loss": 4.905,
|
| 2677 |
+
"step": 380
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.03047390521895621,
|
| 2681 |
+
"grad_norm": 4.626831531524658,
|
| 2682 |
+
"learning_rate": 0.00017236052110492365,
|
| 2683 |
+
"loss": 3.9372,
|
| 2684 |
+
"step": 381
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.03055388922215557,
|
| 2688 |
+
"grad_norm": 3.9243571758270264,
|
| 2689 |
+
"learning_rate": 0.00017221864503320092,
|
| 2690 |
+
"loss": 3.6657,
|
| 2691 |
+
"step": 382
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.030633873225354928,
|
| 2695 |
+
"grad_norm": 4.48898983001709,
|
| 2696 |
+
"learning_rate": 0.00017207646447636295,
|
| 2697 |
+
"loss": 3.0103,
|
| 2698 |
+
"step": 383
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.03071385722855429,
|
| 2702 |
+
"grad_norm": 4.642123699188232,
|
| 2703 |
+
"learning_rate": 0.0001719339800338651,
|
| 2704 |
+
"loss": 3.9077,
|
| 2705 |
+
"step": 384
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.03079384123175365,
|
| 2709 |
+
"grad_norm": 4.266906261444092,
|
| 2710 |
+
"learning_rate": 0.0001717911923064442,
|
| 2711 |
+
"loss": 3.7819,
|
| 2712 |
+
"step": 385
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.03079384123175365,
|
| 2716 |
+
"eval_loss": 0.9522297978401184,
|
| 2717 |
+
"eval_runtime": 288.1682,
|
| 2718 |
+
"eval_samples_per_second": 18.271,
|
| 2719 |
+
"eval_steps_per_second": 9.137,
|
| 2720 |
+
"step": 385
|
| 2721 |
+
}
|
| 2722 |
+
],
|
| 2723 |
+
"logging_steps": 1,
|
| 2724 |
+
"max_steps": 1540,
|
| 2725 |
+
"num_input_tokens_seen": 0,
|
| 2726 |
+
"num_train_epochs": 1,
|
| 2727 |
+
"save_steps": 385,
|
| 2728 |
+
"stateful_callbacks": {
|
| 2729 |
+
"TrainerControl": {
|
| 2730 |
+
"args": {
|
| 2731 |
+
"should_epoch_stop": false,
|
| 2732 |
+
"should_evaluate": false,
|
| 2733 |
+
"should_log": false,
|
| 2734 |
+
"should_save": true,
|
| 2735 |
+
"should_training_stop": false
|
| 2736 |
+
},
|
| 2737 |
+
"attributes": {}
|
| 2738 |
+
}
|
| 2739 |
+
},
|
| 2740 |
+
"total_flos": 1.7600393986965504e+17,
|
| 2741 |
+
"train_batch_size": 2,
|
| 2742 |
+
"trial_name": null,
|
| 2743 |
+
"trial_params": null
|
| 2744 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e9fb63fb901227a78d49b512821152d1ec895187d3fc4c3e2d6807ba942e72b
|
| 3 |
+
size 6776
|