Upload 8 files
Browse files- README.md +200 -1
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1365 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: unsloth/llama-3-8b
|
| 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 0.11.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/llama-3-8b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"out_proj",
|
| 25 |
+
"up_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3807584c29359449e0e43f01225588c64c314f597f783509bb53914009922c77
|
| 3 |
+
size 75514264
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5aebf9d35ce79314e0918724462e94a45ffec39322df20455e1f695824451dc
|
| 3 |
+
size 151103098
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a977537baf79b08794f5b5d5eb700635c0534aff659cb33f857ba03c3c7bc89
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff3df154d503558a7bf306c75c56049db853b80cdc6fa22e95bde8189c670a68
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1365 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2809600234031677,
|
| 3 |
+
"best_model_checkpoint": "./lora_bn_resume/checkpoint-1800",
|
| 4 |
+
"epoch": 1.157556270096463,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006430868167202572,
|
| 13 |
+
"grad_norm": 0.3332834541797638,
|
| 14 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 15 |
+
"loss": 0.643,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012861736334405145,
|
| 20 |
+
"grad_norm": 0.3670434355735779,
|
| 21 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 22 |
+
"loss": 0.5391,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01929260450160772,
|
| 27 |
+
"grad_norm": 0.2655458152294159,
|
| 28 |
+
"learning_rate": 8.999999999999999e-05,
|
| 29 |
+
"loss": 0.4222,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02572347266881029,
|
| 34 |
+
"grad_norm": 0.18765214085578918,
|
| 35 |
+
"learning_rate": 0.00011999999999999999,
|
| 36 |
+
"loss": 0.38,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03215434083601286,
|
| 41 |
+
"grad_norm": 0.17279677093029022,
|
| 42 |
+
"learning_rate": 0.00015,
|
| 43 |
+
"loss": 0.3474,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03858520900321544,
|
| 48 |
+
"grad_norm": 0.19536016881465912,
|
| 49 |
+
"learning_rate": 0.00017999999999999998,
|
| 50 |
+
"loss": 0.3482,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04501607717041801,
|
| 55 |
+
"grad_norm": 0.24155691266059875,
|
| 56 |
+
"learning_rate": 0.00020999999999999998,
|
| 57 |
+
"loss": 0.3519,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05144694533762058,
|
| 62 |
+
"grad_norm": 0.15769515931606293,
|
| 63 |
+
"learning_rate": 0.00023999999999999998,
|
| 64 |
+
"loss": 0.3442,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05787781350482315,
|
| 69 |
+
"grad_norm": 0.15895752608776093,
|
| 70 |
+
"learning_rate": 0.00027,
|
| 71 |
+
"loss": 0.3419,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06430868167202572,
|
| 76 |
+
"grad_norm": 0.1517348736524582,
|
| 77 |
+
"learning_rate": 0.0003,
|
| 78 |
+
"loss": 0.3325,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0707395498392283,
|
| 83 |
+
"grad_norm": 0.1374281644821167,
|
| 84 |
+
"learning_rate": 0.00029934282584884994,
|
| 85 |
+
"loss": 0.3364,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07717041800643087,
|
| 90 |
+
"grad_norm": 0.14599083364009857,
|
| 91 |
+
"learning_rate": 0.00029868565169769985,
|
| 92 |
+
"loss": 0.3296,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08360128617363344,
|
| 97 |
+
"grad_norm": 0.1735353320837021,
|
| 98 |
+
"learning_rate": 0.0002980284775465498,
|
| 99 |
+
"loss": 0.3296,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09003215434083602,
|
| 104 |
+
"grad_norm": 0.16351208090782166,
|
| 105 |
+
"learning_rate": 0.00029737130339539973,
|
| 106 |
+
"loss": 0.3359,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.09646302250803858,
|
| 111 |
+
"grad_norm": 0.15383951365947723,
|
| 112 |
+
"learning_rate": 0.0002967141292442497,
|
| 113 |
+
"loss": 0.3401,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10289389067524116,
|
| 118 |
+
"grad_norm": 0.16704361140727997,
|
| 119 |
+
"learning_rate": 0.00029605695509309966,
|
| 120 |
+
"loss": 0.3378,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10932475884244373,
|
| 125 |
+
"grad_norm": 0.14677385985851288,
|
| 126 |
+
"learning_rate": 0.00029539978094194957,
|
| 127 |
+
"loss": 0.3404,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1157556270096463,
|
| 132 |
+
"grad_norm": 0.2054668664932251,
|
| 133 |
+
"learning_rate": 0.00029474260679079954,
|
| 134 |
+
"loss": 0.3379,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12218649517684887,
|
| 139 |
+
"grad_norm": 0.15476278960704803,
|
| 140 |
+
"learning_rate": 0.00029408543263964945,
|
| 141 |
+
"loss": 0.3395,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12861736334405144,
|
| 146 |
+
"grad_norm": 0.1571033000946045,
|
| 147 |
+
"learning_rate": 0.0002934282584884994,
|
| 148 |
+
"loss": 0.3318,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.12861736334405144,
|
| 153 |
+
"eval_loss": 0.32538482546806335,
|
| 154 |
+
"eval_runtime": 830.7418,
|
| 155 |
+
"eval_samples_per_second": 2.407,
|
| 156 |
+
"eval_steps_per_second": 2.407,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.13504823151125403,
|
| 161 |
+
"grad_norm": 0.13506701588630676,
|
| 162 |
+
"learning_rate": 0.0002927710843373494,
|
| 163 |
+
"loss": 0.3316,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.1414790996784566,
|
| 168 |
+
"grad_norm": 0.16322733461856842,
|
| 169 |
+
"learning_rate": 0.0002921139101861993,
|
| 170 |
+
"loss": 0.3415,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14790996784565916,
|
| 175 |
+
"grad_norm": 0.16979773342609406,
|
| 176 |
+
"learning_rate": 0.00029145673603504926,
|
| 177 |
+
"loss": 0.3272,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.15434083601286175,
|
| 182 |
+
"grad_norm": 0.1605272740125656,
|
| 183 |
+
"learning_rate": 0.0002907995618838992,
|
| 184 |
+
"loss": 0.3292,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1607717041800643,
|
| 189 |
+
"grad_norm": 0.16240820288658142,
|
| 190 |
+
"learning_rate": 0.00029014238773274913,
|
| 191 |
+
"loss": 0.3256,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.16720257234726688,
|
| 196 |
+
"grad_norm": 0.14710214734077454,
|
| 197 |
+
"learning_rate": 0.0002894852135815991,
|
| 198 |
+
"loss": 0.3234,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.17363344051446947,
|
| 203 |
+
"grad_norm": 0.14770746231079102,
|
| 204 |
+
"learning_rate": 0.000288828039430449,
|
| 205 |
+
"loss": 0.3264,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.18006430868167203,
|
| 210 |
+
"grad_norm": 0.14894965291023254,
|
| 211 |
+
"learning_rate": 0.000288170865279299,
|
| 212 |
+
"loss": 0.3211,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1864951768488746,
|
| 217 |
+
"grad_norm": 0.1738394796848297,
|
| 218 |
+
"learning_rate": 0.00028751369112814894,
|
| 219 |
+
"loss": 0.3107,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.19292604501607716,
|
| 224 |
+
"grad_norm": 0.15344616770744324,
|
| 225 |
+
"learning_rate": 0.00028685651697699885,
|
| 226 |
+
"loss": 0.3126,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.19935691318327975,
|
| 231 |
+
"grad_norm": 0.180983766913414,
|
| 232 |
+
"learning_rate": 0.0002861993428258488,
|
| 233 |
+
"loss": 0.3142,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2057877813504823,
|
| 238 |
+
"grad_norm": 0.17168308794498444,
|
| 239 |
+
"learning_rate": 0.00028554216867469873,
|
| 240 |
+
"loss": 0.3207,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.21221864951768488,
|
| 245 |
+
"grad_norm": 0.17984597384929657,
|
| 246 |
+
"learning_rate": 0.0002848849945235487,
|
| 247 |
+
"loss": 0.3158,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.21864951768488747,
|
| 252 |
+
"grad_norm": 0.15579424798488617,
|
| 253 |
+
"learning_rate": 0.00028422782037239866,
|
| 254 |
+
"loss": 0.3133,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.22508038585209003,
|
| 259 |
+
"grad_norm": 0.15541236102581024,
|
| 260 |
+
"learning_rate": 0.0002835706462212486,
|
| 261 |
+
"loss": 0.3203,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2315112540192926,
|
| 266 |
+
"grad_norm": 0.14372068643569946,
|
| 267 |
+
"learning_rate": 0.00028291347207009854,
|
| 268 |
+
"loss": 0.3284,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2379421221864952,
|
| 273 |
+
"grad_norm": 0.16621021926403046,
|
| 274 |
+
"learning_rate": 0.0002822562979189485,
|
| 275 |
+
"loss": 0.3218,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.24437299035369775,
|
| 280 |
+
"grad_norm": 0.1540420651435852,
|
| 281 |
+
"learning_rate": 0.0002815991237677984,
|
| 282 |
+
"loss": 0.3117,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.2508038585209003,
|
| 287 |
+
"grad_norm": 0.1495533287525177,
|
| 288 |
+
"learning_rate": 0.0002809419496166484,
|
| 289 |
+
"loss": 0.318,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.2572347266881029,
|
| 294 |
+
"grad_norm": 0.3620932400226593,
|
| 295 |
+
"learning_rate": 0.00028028477546549835,
|
| 296 |
+
"loss": 0.3241,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.2572347266881029,
|
| 301 |
+
"eval_loss": 0.3119981288909912,
|
| 302 |
+
"eval_runtime": 842.192,
|
| 303 |
+
"eval_samples_per_second": 2.375,
|
| 304 |
+
"eval_steps_per_second": 2.375,
|
| 305 |
+
"step": 400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.26366559485530544,
|
| 309 |
+
"grad_norm": 0.14988340437412262,
|
| 310 |
+
"learning_rate": 0.00027962760131434826,
|
| 311 |
+
"loss": 0.3132,
|
| 312 |
+
"step": 410
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.27009646302250806,
|
| 316 |
+
"grad_norm": 0.14897547662258148,
|
| 317 |
+
"learning_rate": 0.0002789704271631982,
|
| 318 |
+
"loss": 0.3159,
|
| 319 |
+
"step": 420
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.2765273311897106,
|
| 323 |
+
"grad_norm": 0.1518355906009674,
|
| 324 |
+
"learning_rate": 0.0002783132530120482,
|
| 325 |
+
"loss": 0.3131,
|
| 326 |
+
"step": 430
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.2829581993569132,
|
| 330 |
+
"grad_norm": 0.1667843610048294,
|
| 331 |
+
"learning_rate": 0.0002776560788608981,
|
| 332 |
+
"loss": 0.3176,
|
| 333 |
+
"step": 440
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.28938906752411575,
|
| 337 |
+
"grad_norm": 0.1573045551776886,
|
| 338 |
+
"learning_rate": 0.00027699890470974807,
|
| 339 |
+
"loss": 0.3063,
|
| 340 |
+
"step": 450
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.2958199356913183,
|
| 344 |
+
"grad_norm": 0.2083781659603119,
|
| 345 |
+
"learning_rate": 0.000276341730558598,
|
| 346 |
+
"loss": 0.3121,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.3022508038585209,
|
| 351 |
+
"grad_norm": 0.15114179253578186,
|
| 352 |
+
"learning_rate": 0.00027568455640744795,
|
| 353 |
+
"loss": 0.3115,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.3086816720257235,
|
| 358 |
+
"grad_norm": 0.1676609367132187,
|
| 359 |
+
"learning_rate": 0.0002750273822562979,
|
| 360 |
+
"loss": 0.3102,
|
| 361 |
+
"step": 480
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.31511254019292606,
|
| 365 |
+
"grad_norm": 0.1511840969324112,
|
| 366 |
+
"learning_rate": 0.0002743702081051478,
|
| 367 |
+
"loss": 0.2958,
|
| 368 |
+
"step": 490
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.3215434083601286,
|
| 372 |
+
"grad_norm": 0.14467953145503998,
|
| 373 |
+
"learning_rate": 0.0002737130339539978,
|
| 374 |
+
"loss": 0.3141,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.3279742765273312,
|
| 379 |
+
"grad_norm": 0.14991098642349243,
|
| 380 |
+
"learning_rate": 0.00027305585980284776,
|
| 381 |
+
"loss": 0.2971,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.33440514469453375,
|
| 386 |
+
"grad_norm": 0.15232595801353455,
|
| 387 |
+
"learning_rate": 0.00027239868565169767,
|
| 388 |
+
"loss": 0.309,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.3408360128617363,
|
| 393 |
+
"grad_norm": 0.14672474563121796,
|
| 394 |
+
"learning_rate": 0.00027174151150054763,
|
| 395 |
+
"loss": 0.303,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.34726688102893893,
|
| 400 |
+
"grad_norm": 0.1486695259809494,
|
| 401 |
+
"learning_rate": 0.0002710843373493976,
|
| 402 |
+
"loss": 0.3049,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.3536977491961415,
|
| 407 |
+
"grad_norm": 0.14715538918972015,
|
| 408 |
+
"learning_rate": 0.0002704271631982475,
|
| 409 |
+
"loss": 0.2989,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.36012861736334406,
|
| 414 |
+
"grad_norm": 0.16407349705696106,
|
| 415 |
+
"learning_rate": 0.0002697699890470975,
|
| 416 |
+
"loss": 0.3096,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.3665594855305466,
|
| 421 |
+
"grad_norm": 0.17212547361850739,
|
| 422 |
+
"learning_rate": 0.00026911281489594744,
|
| 423 |
+
"loss": 0.3071,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.3729903536977492,
|
| 428 |
+
"grad_norm": 0.17516419291496277,
|
| 429 |
+
"learning_rate": 0.00026845564074479735,
|
| 430 |
+
"loss": 0.3012,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.37942122186495175,
|
| 435 |
+
"grad_norm": 0.16375690698623657,
|
| 436 |
+
"learning_rate": 0.0002677984665936473,
|
| 437 |
+
"loss": 0.3001,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.3858520900321543,
|
| 442 |
+
"grad_norm": 0.16078205406665802,
|
| 443 |
+
"learning_rate": 0.00026714129244249723,
|
| 444 |
+
"loss": 0.3033,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.3858520900321543,
|
| 449 |
+
"eval_loss": 0.30340561270713806,
|
| 450 |
+
"eval_runtime": 843.3627,
|
| 451 |
+
"eval_samples_per_second": 2.371,
|
| 452 |
+
"eval_steps_per_second": 2.371,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.39228295819935693,
|
| 457 |
+
"grad_norm": 0.16159534454345703,
|
| 458 |
+
"learning_rate": 0.0002664841182913472,
|
| 459 |
+
"loss": 0.3094,
|
| 460 |
+
"step": 610
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.3987138263665595,
|
| 464 |
+
"grad_norm": 0.16596971452236176,
|
| 465 |
+
"learning_rate": 0.00026582694414019716,
|
| 466 |
+
"loss": 0.3006,
|
| 467 |
+
"step": 620
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.40514469453376206,
|
| 471 |
+
"grad_norm": 0.1850331723690033,
|
| 472 |
+
"learning_rate": 0.00026516976998904707,
|
| 473 |
+
"loss": 0.3071,
|
| 474 |
+
"step": 630
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.4115755627009646,
|
| 478 |
+
"grad_norm": 0.16145645081996918,
|
| 479 |
+
"learning_rate": 0.00026451259583789704,
|
| 480 |
+
"loss": 0.3045,
|
| 481 |
+
"step": 640
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.4180064308681672,
|
| 485 |
+
"grad_norm": 0.1462334543466568,
|
| 486 |
+
"learning_rate": 0.00026385542168674695,
|
| 487 |
+
"loss": 0.3127,
|
| 488 |
+
"step": 650
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.42443729903536975,
|
| 492 |
+
"grad_norm": 0.1508970707654953,
|
| 493 |
+
"learning_rate": 0.0002631982475355969,
|
| 494 |
+
"loss": 0.3047,
|
| 495 |
+
"step": 660
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.43086816720257237,
|
| 499 |
+
"grad_norm": 0.17199252545833588,
|
| 500 |
+
"learning_rate": 0.0002625410733844469,
|
| 501 |
+
"loss": 0.304,
|
| 502 |
+
"step": 670
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.43729903536977494,
|
| 506 |
+
"grad_norm": 0.15578508377075195,
|
| 507 |
+
"learning_rate": 0.0002618838992332968,
|
| 508 |
+
"loss": 0.3049,
|
| 509 |
+
"step": 680
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.4437299035369775,
|
| 513 |
+
"grad_norm": 0.17518927156925201,
|
| 514 |
+
"learning_rate": 0.00026122672508214676,
|
| 515 |
+
"loss": 0.2975,
|
| 516 |
+
"step": 690
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.45016077170418006,
|
| 520 |
+
"grad_norm": 0.16074487566947937,
|
| 521 |
+
"learning_rate": 0.0002605695509309967,
|
| 522 |
+
"loss": 0.2911,
|
| 523 |
+
"step": 700
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.4565916398713826,
|
| 527 |
+
"grad_norm": 0.13804423809051514,
|
| 528 |
+
"learning_rate": 0.00025991237677984664,
|
| 529 |
+
"loss": 0.3013,
|
| 530 |
+
"step": 710
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.4630225080385852,
|
| 534 |
+
"grad_norm": 0.15148524940013885,
|
| 535 |
+
"learning_rate": 0.0002592552026286966,
|
| 536 |
+
"loss": 0.302,
|
| 537 |
+
"step": 720
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.4694533762057878,
|
| 541 |
+
"grad_norm": 0.18637600541114807,
|
| 542 |
+
"learning_rate": 0.0002585980284775465,
|
| 543 |
+
"loss": 0.2945,
|
| 544 |
+
"step": 730
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.4758842443729904,
|
| 548 |
+
"grad_norm": 0.16151027381420135,
|
| 549 |
+
"learning_rate": 0.0002579408543263965,
|
| 550 |
+
"loss": 0.2991,
|
| 551 |
+
"step": 740
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.48231511254019294,
|
| 555 |
+
"grad_norm": 0.14255981147289276,
|
| 556 |
+
"learning_rate": 0.00025728368017524644,
|
| 557 |
+
"loss": 0.3166,
|
| 558 |
+
"step": 750
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.4887459807073955,
|
| 562 |
+
"grad_norm": 0.14939677715301514,
|
| 563 |
+
"learning_rate": 0.00025662650602409636,
|
| 564 |
+
"loss": 0.296,
|
| 565 |
+
"step": 760
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.49517684887459806,
|
| 569 |
+
"grad_norm": 0.15057405829429626,
|
| 570 |
+
"learning_rate": 0.0002559693318729463,
|
| 571 |
+
"loss": 0.2827,
|
| 572 |
+
"step": 770
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.5016077170418006,
|
| 576 |
+
"grad_norm": 0.162841796875,
|
| 577 |
+
"learning_rate": 0.00025531215772179623,
|
| 578 |
+
"loss": 0.301,
|
| 579 |
+
"step": 780
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.5080385852090032,
|
| 583 |
+
"grad_norm": 0.13532967865467072,
|
| 584 |
+
"learning_rate": 0.0002546549835706462,
|
| 585 |
+
"loss": 0.2915,
|
| 586 |
+
"step": 790
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.5144694533762058,
|
| 590 |
+
"grad_norm": 0.14414694905281067,
|
| 591 |
+
"learning_rate": 0.00025399780941949616,
|
| 592 |
+
"loss": 0.2963,
|
| 593 |
+
"step": 800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.5144694533762058,
|
| 597 |
+
"eval_loss": 0.2967182695865631,
|
| 598 |
+
"eval_runtime": 836.6673,
|
| 599 |
+
"eval_samples_per_second": 2.39,
|
| 600 |
+
"eval_steps_per_second": 2.39,
|
| 601 |
+
"step": 800
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.5209003215434084,
|
| 605 |
+
"grad_norm": 0.1773417443037033,
|
| 606 |
+
"learning_rate": 0.0002533406352683461,
|
| 607 |
+
"loss": 0.2983,
|
| 608 |
+
"step": 810
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.5273311897106109,
|
| 612 |
+
"grad_norm": 0.15203996002674103,
|
| 613 |
+
"learning_rate": 0.00025268346111719604,
|
| 614 |
+
"loss": 0.3116,
|
| 615 |
+
"step": 820
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.5337620578778135,
|
| 619 |
+
"grad_norm": 0.14001955091953278,
|
| 620 |
+
"learning_rate": 0.00025202628696604595,
|
| 621 |
+
"loss": 0.2895,
|
| 622 |
+
"step": 830
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.5401929260450161,
|
| 626 |
+
"grad_norm": 0.14643649756908417,
|
| 627 |
+
"learning_rate": 0.0002513691128148959,
|
| 628 |
+
"loss": 0.2923,
|
| 629 |
+
"step": 840
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.5466237942122186,
|
| 633 |
+
"grad_norm": 0.1428484320640564,
|
| 634 |
+
"learning_rate": 0.0002507119386637459,
|
| 635 |
+
"loss": 0.3001,
|
| 636 |
+
"step": 850
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.5530546623794212,
|
| 640 |
+
"grad_norm": 0.1566481739282608,
|
| 641 |
+
"learning_rate": 0.0002500547645125958,
|
| 642 |
+
"loss": 0.3019,
|
| 643 |
+
"step": 860
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.5594855305466238,
|
| 647 |
+
"grad_norm": 0.15484847128391266,
|
| 648 |
+
"learning_rate": 0.00024939759036144576,
|
| 649 |
+
"loss": 0.2952,
|
| 650 |
+
"step": 870
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.5659163987138264,
|
| 654 |
+
"grad_norm": 0.16524390876293182,
|
| 655 |
+
"learning_rate": 0.00024874041621029573,
|
| 656 |
+
"loss": 0.2956,
|
| 657 |
+
"step": 880
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.572347266881029,
|
| 661 |
+
"grad_norm": 0.16674397885799408,
|
| 662 |
+
"learning_rate": 0.00024808324205914564,
|
| 663 |
+
"loss": 0.2917,
|
| 664 |
+
"step": 890
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.5787781350482315,
|
| 668 |
+
"grad_norm": 0.15178845822811127,
|
| 669 |
+
"learning_rate": 0.0002474260679079956,
|
| 670 |
+
"loss": 0.2999,
|
| 671 |
+
"step": 900
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.5852090032154341,
|
| 675 |
+
"grad_norm": 0.15306776762008667,
|
| 676 |
+
"learning_rate": 0.0002467688937568455,
|
| 677 |
+
"loss": 0.2909,
|
| 678 |
+
"step": 910
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.5916398713826366,
|
| 682 |
+
"grad_norm": 0.16369566321372986,
|
| 683 |
+
"learning_rate": 0.0002461117196056955,
|
| 684 |
+
"loss": 0.3041,
|
| 685 |
+
"step": 920
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.5980707395498392,
|
| 689 |
+
"grad_norm": 0.15131248533725739,
|
| 690 |
+
"learning_rate": 0.00024545454545454545,
|
| 691 |
+
"loss": 0.2948,
|
| 692 |
+
"step": 930
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.6045016077170418,
|
| 696 |
+
"grad_norm": 0.1472727656364441,
|
| 697 |
+
"learning_rate": 0.00024479737130339536,
|
| 698 |
+
"loss": 0.2926,
|
| 699 |
+
"step": 940
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.6109324758842444,
|
| 703 |
+
"grad_norm": 0.17377722263336182,
|
| 704 |
+
"learning_rate": 0.00024414019715224533,
|
| 705 |
+
"loss": 0.298,
|
| 706 |
+
"step": 950
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.617363344051447,
|
| 710 |
+
"grad_norm": 0.1630556285381317,
|
| 711 |
+
"learning_rate": 0.00024348302300109526,
|
| 712 |
+
"loss": 0.2921,
|
| 713 |
+
"step": 960
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.6237942122186495,
|
| 717 |
+
"grad_norm": 0.1495707631111145,
|
| 718 |
+
"learning_rate": 0.0002428258488499452,
|
| 719 |
+
"loss": 0.3057,
|
| 720 |
+
"step": 970
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.6302250803858521,
|
| 724 |
+
"grad_norm": 0.14349451661109924,
|
| 725 |
+
"learning_rate": 0.00024216867469879517,
|
| 726 |
+
"loss": 0.2978,
|
| 727 |
+
"step": 980
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.6366559485530546,
|
| 731 |
+
"grad_norm": 0.15608881413936615,
|
| 732 |
+
"learning_rate": 0.0002415115005476451,
|
| 733 |
+
"loss": 0.2888,
|
| 734 |
+
"step": 990
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.6430868167202572,
|
| 738 |
+
"grad_norm": 0.15335732698440552,
|
| 739 |
+
"learning_rate": 0.00024085432639649505,
|
| 740 |
+
"loss": 0.2968,
|
| 741 |
+
"step": 1000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.6430868167202572,
|
| 745 |
+
"eval_loss": 0.2915716767311096,
|
| 746 |
+
"eval_runtime": 833.5453,
|
| 747 |
+
"eval_samples_per_second": 2.399,
|
| 748 |
+
"eval_steps_per_second": 2.399,
|
| 749 |
+
"step": 1000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.6495176848874598,
|
| 753 |
+
"grad_norm": 0.17396800220012665,
|
| 754 |
+
"learning_rate": 0.00024019715224534498,
|
| 755 |
+
"loss": 0.285,
|
| 756 |
+
"step": 1010
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.6559485530546624,
|
| 760 |
+
"grad_norm": 0.15287892520427704,
|
| 761 |
+
"learning_rate": 0.00023953997809419495,
|
| 762 |
+
"loss": 0.2992,
|
| 763 |
+
"step": 1020
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.662379421221865,
|
| 767 |
+
"grad_norm": 0.15309476852416992,
|
| 768 |
+
"learning_rate": 0.0002388828039430449,
|
| 769 |
+
"loss": 0.2927,
|
| 770 |
+
"step": 1030
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.6688102893890675,
|
| 774 |
+
"grad_norm": 0.17866992950439453,
|
| 775 |
+
"learning_rate": 0.00023822562979189483,
|
| 776 |
+
"loss": 0.291,
|
| 777 |
+
"step": 1040
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6752411575562701,
|
| 781 |
+
"grad_norm": 0.1827457696199417,
|
| 782 |
+
"learning_rate": 0.0002375684556407448,
|
| 783 |
+
"loss": 0.289,
|
| 784 |
+
"step": 1050
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.6816720257234726,
|
| 788 |
+
"grad_norm": 0.15376009047031403,
|
| 789 |
+
"learning_rate": 0.0002369112814895947,
|
| 790 |
+
"loss": 0.2916,
|
| 791 |
+
"step": 1060
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.6881028938906752,
|
| 795 |
+
"grad_norm": 0.16380611062049866,
|
| 796 |
+
"learning_rate": 0.00023625410733844467,
|
| 797 |
+
"loss": 0.2894,
|
| 798 |
+
"step": 1070
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.6945337620578779,
|
| 802 |
+
"grad_norm": 0.1561112254858017,
|
| 803 |
+
"learning_rate": 0.00023559693318729464,
|
| 804 |
+
"loss": 0.2895,
|
| 805 |
+
"step": 1080
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.7009646302250804,
|
| 809 |
+
"grad_norm": 0.14859697222709656,
|
| 810 |
+
"learning_rate": 0.00023493975903614455,
|
| 811 |
+
"loss": 0.2889,
|
| 812 |
+
"step": 1090
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.707395498392283,
|
| 816 |
+
"grad_norm": 0.15627552568912506,
|
| 817 |
+
"learning_rate": 0.0002342825848849945,
|
| 818 |
+
"loss": 0.2889,
|
| 819 |
+
"step": 1100
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.7138263665594855,
|
| 823 |
+
"grad_norm": 0.16106264293193817,
|
| 824 |
+
"learning_rate": 0.00023362541073384445,
|
| 825 |
+
"loss": 0.2858,
|
| 826 |
+
"step": 1110
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.7202572347266881,
|
| 830 |
+
"grad_norm": 0.1667865663766861,
|
| 831 |
+
"learning_rate": 0.0002329682365826944,
|
| 832 |
+
"loss": 0.289,
|
| 833 |
+
"step": 1120
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.7266881028938906,
|
| 837 |
+
"grad_norm": 0.17265114188194275,
|
| 838 |
+
"learning_rate": 0.00023231106243154436,
|
| 839 |
+
"loss": 0.2888,
|
| 840 |
+
"step": 1130
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.7331189710610932,
|
| 844 |
+
"grad_norm": 0.16795796155929565,
|
| 845 |
+
"learning_rate": 0.00023165388828039427,
|
| 846 |
+
"loss": 0.2824,
|
| 847 |
+
"step": 1140
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.7395498392282959,
|
| 851 |
+
"grad_norm": 0.144576758146286,
|
| 852 |
+
"learning_rate": 0.00023099671412924423,
|
| 853 |
+
"loss": 0.2896,
|
| 854 |
+
"step": 1150
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.7459807073954984,
|
| 858 |
+
"grad_norm": 0.15994594991207123,
|
| 859 |
+
"learning_rate": 0.0002303395399780942,
|
| 860 |
+
"loss": 0.2969,
|
| 861 |
+
"step": 1160
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.752411575562701,
|
| 865 |
+
"grad_norm": 0.1481965035200119,
|
| 866 |
+
"learning_rate": 0.0002296823658269441,
|
| 867 |
+
"loss": 0.2832,
|
| 868 |
+
"step": 1170
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.7588424437299035,
|
| 872 |
+
"grad_norm": 0.143247589468956,
|
| 873 |
+
"learning_rate": 0.00022902519167579408,
|
| 874 |
+
"loss": 0.293,
|
| 875 |
+
"step": 1180
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.7652733118971061,
|
| 879 |
+
"grad_norm": 0.17525409162044525,
|
| 880 |
+
"learning_rate": 0.000228368017524644,
|
| 881 |
+
"loss": 0.282,
|
| 882 |
+
"step": 1190
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.7717041800643086,
|
| 886 |
+
"grad_norm": 0.16322872042655945,
|
| 887 |
+
"learning_rate": 0.00022771084337349395,
|
| 888 |
+
"loss": 0.2888,
|
| 889 |
+
"step": 1200
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.7717041800643086,
|
| 893 |
+
"eval_loss": 0.2870965301990509,
|
| 894 |
+
"eval_runtime": 837.2115,
|
| 895 |
+
"eval_samples_per_second": 2.389,
|
| 896 |
+
"eval_steps_per_second": 2.389,
|
| 897 |
+
"step": 1200
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.7781350482315113,
|
| 901 |
+
"grad_norm": 0.1486148089170456,
|
| 902 |
+
"learning_rate": 0.00022705366922234392,
|
| 903 |
+
"loss": 0.2648,
|
| 904 |
+
"step": 1210
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.7845659163987139,
|
| 908 |
+
"grad_norm": 0.1699255108833313,
|
| 909 |
+
"learning_rate": 0.00022639649507119383,
|
| 910 |
+
"loss": 0.2781,
|
| 911 |
+
"step": 1220
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.7909967845659164,
|
| 915 |
+
"grad_norm": 0.17535263299942017,
|
| 916 |
+
"learning_rate": 0.0002257393209200438,
|
| 917 |
+
"loss": 0.258,
|
| 918 |
+
"step": 1230
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.797427652733119,
|
| 922 |
+
"grad_norm": 0.1789318472146988,
|
| 923 |
+
"learning_rate": 0.00022508214676889373,
|
| 924 |
+
"loss": 0.2704,
|
| 925 |
+
"step": 1240
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.8038585209003215,
|
| 929 |
+
"grad_norm": 0.1452336609363556,
|
| 930 |
+
"learning_rate": 0.00022442497261774367,
|
| 931 |
+
"loss": 0.2644,
|
| 932 |
+
"step": 1250
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.8102893890675241,
|
| 936 |
+
"grad_norm": 0.14961348474025726,
|
| 937 |
+
"learning_rate": 0.00022376779846659364,
|
| 938 |
+
"loss": 0.2761,
|
| 939 |
+
"step": 1260
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.8167202572347267,
|
| 943 |
+
"grad_norm": 0.14857113361358643,
|
| 944 |
+
"learning_rate": 0.00022311062431544358,
|
| 945 |
+
"loss": 0.2693,
|
| 946 |
+
"step": 1270
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.8231511254019293,
|
| 950 |
+
"grad_norm": 0.172617107629776,
|
| 951 |
+
"learning_rate": 0.00022245345016429352,
|
| 952 |
+
"loss": 0.2668,
|
| 953 |
+
"step": 1280
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.8295819935691319,
|
| 957 |
+
"grad_norm": 0.15187814831733704,
|
| 958 |
+
"learning_rate": 0.00022179627601314345,
|
| 959 |
+
"loss": 0.2612,
|
| 960 |
+
"step": 1290
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.8360128617363344,
|
| 964 |
+
"grad_norm": 0.15238122642040253,
|
| 965 |
+
"learning_rate": 0.0002211391018619934,
|
| 966 |
+
"loss": 0.281,
|
| 967 |
+
"step": 1300
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.842443729903537,
|
| 971 |
+
"grad_norm": 0.15372508764266968,
|
| 972 |
+
"learning_rate": 0.00022048192771084336,
|
| 973 |
+
"loss": 0.268,
|
| 974 |
+
"step": 1310
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.8488745980707395,
|
| 978 |
+
"grad_norm": 0.17595216631889343,
|
| 979 |
+
"learning_rate": 0.0002198247535596933,
|
| 980 |
+
"loss": 0.2708,
|
| 981 |
+
"step": 1320
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.8553054662379421,
|
| 985 |
+
"grad_norm": 0.17156840860843658,
|
| 986 |
+
"learning_rate": 0.00021916757940854324,
|
| 987 |
+
"loss": 0.2781,
|
| 988 |
+
"step": 1330
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.8617363344051447,
|
| 992 |
+
"grad_norm": 0.15553158521652222,
|
| 993 |
+
"learning_rate": 0.0002185104052573932,
|
| 994 |
+
"loss": 0.2691,
|
| 995 |
+
"step": 1340
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.8681672025723473,
|
| 999 |
+
"grad_norm": 0.15347564220428467,
|
| 1000 |
+
"learning_rate": 0.00021785323110624314,
|
| 1001 |
+
"loss": 0.2677,
|
| 1002 |
+
"step": 1350
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.8745980707395499,
|
| 1006 |
+
"grad_norm": 0.15675435960292816,
|
| 1007 |
+
"learning_rate": 0.00021719605695509308,
|
| 1008 |
+
"loss": 0.2745,
|
| 1009 |
+
"step": 1360
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.8810289389067524,
|
| 1013 |
+
"grad_norm": 0.17261667549610138,
|
| 1014 |
+
"learning_rate": 0.00021653888280394302,
|
| 1015 |
+
"loss": 0.2738,
|
| 1016 |
+
"step": 1370
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.887459807073955,
|
| 1020 |
+
"grad_norm": 0.17966938018798828,
|
| 1021 |
+
"learning_rate": 0.00021588170865279298,
|
| 1022 |
+
"loss": 0.2626,
|
| 1023 |
+
"step": 1380
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.8938906752411575,
|
| 1027 |
+
"grad_norm": 0.1592021882534027,
|
| 1028 |
+
"learning_rate": 0.00021522453450164292,
|
| 1029 |
+
"loss": 0.2714,
|
| 1030 |
+
"step": 1390
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.9003215434083601,
|
| 1034 |
+
"grad_norm": 0.203449547290802,
|
| 1035 |
+
"learning_rate": 0.00021456736035049286,
|
| 1036 |
+
"loss": 0.2677,
|
| 1037 |
+
"step": 1400
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.9003215434083601,
|
| 1041 |
+
"eval_loss": 0.28547272086143494,
|
| 1042 |
+
"eval_runtime": 841.1547,
|
| 1043 |
+
"eval_samples_per_second": 2.378,
|
| 1044 |
+
"eval_steps_per_second": 2.378,
|
| 1045 |
+
"step": 1400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.9067524115755627,
|
| 1049 |
+
"grad_norm": 0.15531207621097565,
|
| 1050 |
+
"learning_rate": 0.00021391018619934283,
|
| 1051 |
+
"loss": 0.27,
|
| 1052 |
+
"step": 1410
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.9131832797427653,
|
| 1056 |
+
"grad_norm": 0.33703845739364624,
|
| 1057 |
+
"learning_rate": 0.00021325301204819274,
|
| 1058 |
+
"loss": 0.2748,
|
| 1059 |
+
"step": 1420
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.9196141479099679,
|
| 1063 |
+
"grad_norm": 0.20089037716388702,
|
| 1064 |
+
"learning_rate": 0.0002125958378970427,
|
| 1065 |
+
"loss": 0.2685,
|
| 1066 |
+
"step": 1430
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.9260450160771704,
|
| 1070 |
+
"grad_norm": 0.1531943380832672,
|
| 1071 |
+
"learning_rate": 0.00021193866374589267,
|
| 1072 |
+
"loss": 0.2729,
|
| 1073 |
+
"step": 1440
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.932475884244373,
|
| 1077 |
+
"grad_norm": 0.15565109252929688,
|
| 1078 |
+
"learning_rate": 0.00021128148959474258,
|
| 1079 |
+
"loss": 0.2681,
|
| 1080 |
+
"step": 1450
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.9389067524115756,
|
| 1084 |
+
"grad_norm": 0.18514017760753632,
|
| 1085 |
+
"learning_rate": 0.00021062431544359255,
|
| 1086 |
+
"loss": 0.2761,
|
| 1087 |
+
"step": 1460
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.9453376205787781,
|
| 1091 |
+
"grad_norm": 0.16498805582523346,
|
| 1092 |
+
"learning_rate": 0.00020996714129244246,
|
| 1093 |
+
"loss": 0.2723,
|
| 1094 |
+
"step": 1470
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.9517684887459807,
|
| 1098 |
+
"grad_norm": 0.16682648658752441,
|
| 1099 |
+
"learning_rate": 0.00020930996714129242,
|
| 1100 |
+
"loss": 0.2679,
|
| 1101 |
+
"step": 1480
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.9581993569131833,
|
| 1105 |
+
"grad_norm": 0.16485853493213654,
|
| 1106 |
+
"learning_rate": 0.0002086527929901424,
|
| 1107 |
+
"loss": 0.2649,
|
| 1108 |
+
"step": 1490
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.9646302250803859,
|
| 1112 |
+
"grad_norm": 0.28759464621543884,
|
| 1113 |
+
"learning_rate": 0.0002079956188389923,
|
| 1114 |
+
"loss": 0.2761,
|
| 1115 |
+
"step": 1500
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.9710610932475884,
|
| 1119 |
+
"grad_norm": 0.16720062494277954,
|
| 1120 |
+
"learning_rate": 0.00020733844468784227,
|
| 1121 |
+
"loss": 0.2622,
|
| 1122 |
+
"step": 1510
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.977491961414791,
|
| 1126 |
+
"grad_norm": 0.15708176791667938,
|
| 1127 |
+
"learning_rate": 0.00020668127053669218,
|
| 1128 |
+
"loss": 0.2785,
|
| 1129 |
+
"step": 1520
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.9839228295819936,
|
| 1133 |
+
"grad_norm": 0.14977172017097473,
|
| 1134 |
+
"learning_rate": 0.00020602409638554214,
|
| 1135 |
+
"loss": 0.2647,
|
| 1136 |
+
"step": 1530
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.9903536977491961,
|
| 1140 |
+
"grad_norm": 0.15259595215320587,
|
| 1141 |
+
"learning_rate": 0.0002053669222343921,
|
| 1142 |
+
"loss": 0.2612,
|
| 1143 |
+
"step": 1540
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.9967845659163987,
|
| 1147 |
+
"grad_norm": 0.16366101801395416,
|
| 1148 |
+
"learning_rate": 0.00020470974808324202,
|
| 1149 |
+
"loss": 0.2717,
|
| 1150 |
+
"step": 1550
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.0032154340836013,
|
| 1154 |
+
"grad_norm": 0.1795603334903717,
|
| 1155 |
+
"learning_rate": 0.000204052573932092,
|
| 1156 |
+
"loss": 0.267,
|
| 1157 |
+
"step": 1560
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.0096463022508038,
|
| 1161 |
+
"grad_norm": 0.17623689770698547,
|
| 1162 |
+
"learning_rate": 0.00020339539978094195,
|
| 1163 |
+
"loss": 0.252,
|
| 1164 |
+
"step": 1570
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.0160771704180065,
|
| 1168 |
+
"grad_norm": 0.15394379198551178,
|
| 1169 |
+
"learning_rate": 0.00020273822562979186,
|
| 1170 |
+
"loss": 0.2685,
|
| 1171 |
+
"step": 1580
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.022508038585209,
|
| 1175 |
+
"grad_norm": 0.16083110868930817,
|
| 1176 |
+
"learning_rate": 0.00020208105147864183,
|
| 1177 |
+
"loss": 0.2573,
|
| 1178 |
+
"step": 1590
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.0289389067524115,
|
| 1182 |
+
"grad_norm": 0.1885363757610321,
|
| 1183 |
+
"learning_rate": 0.00020142387732749177,
|
| 1184 |
+
"loss": 0.2592,
|
| 1185 |
+
"step": 1600
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.0289389067524115,
|
| 1189 |
+
"eval_loss": 0.2842000424861908,
|
| 1190 |
+
"eval_runtime": 845.1823,
|
| 1191 |
+
"eval_samples_per_second": 2.366,
|
| 1192 |
+
"eval_steps_per_second": 2.366,
|
| 1193 |
+
"step": 1600
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.0353697749196142,
|
| 1197 |
+
"grad_norm": 0.1810334175825119,
|
| 1198 |
+
"learning_rate": 0.0002007667031763417,
|
| 1199 |
+
"loss": 0.272,
|
| 1200 |
+
"step": 1610
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.0418006430868167,
|
| 1204 |
+
"grad_norm": 0.17008474469184875,
|
| 1205 |
+
"learning_rate": 0.00020010952902519167,
|
| 1206 |
+
"loss": 0.2516,
|
| 1207 |
+
"step": 1620
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.0482315112540193,
|
| 1211 |
+
"grad_norm": 0.1848730593919754,
|
| 1212 |
+
"learning_rate": 0.00019945235487404158,
|
| 1213 |
+
"loss": 0.2627,
|
| 1214 |
+
"step": 1630
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.0546623794212218,
|
| 1218 |
+
"grad_norm": 0.16504080593585968,
|
| 1219 |
+
"learning_rate": 0.00019879518072289155,
|
| 1220 |
+
"loss": 0.256,
|
| 1221 |
+
"step": 1640
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.0610932475884245,
|
| 1225 |
+
"grad_norm": 0.166968435049057,
|
| 1226 |
+
"learning_rate": 0.0001981380065717415,
|
| 1227 |
+
"loss": 0.269,
|
| 1228 |
+
"step": 1650
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.067524115755627,
|
| 1232 |
+
"grad_norm": 0.20997032523155212,
|
| 1233 |
+
"learning_rate": 0.00019748083242059143,
|
| 1234 |
+
"loss": 0.2641,
|
| 1235 |
+
"step": 1660
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.0739549839228295,
|
| 1239 |
+
"grad_norm": 0.18889103829860687,
|
| 1240 |
+
"learning_rate": 0.0001968236582694414,
|
| 1241 |
+
"loss": 0.2499,
|
| 1242 |
+
"step": 1670
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.0803858520900322,
|
| 1246 |
+
"grad_norm": 0.15986306965351105,
|
| 1247 |
+
"learning_rate": 0.00019616648411829133,
|
| 1248 |
+
"loss": 0.2659,
|
| 1249 |
+
"step": 1680
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.0868167202572347,
|
| 1253 |
+
"grad_norm": 0.15300147235393524,
|
| 1254 |
+
"learning_rate": 0.00019550930996714127,
|
| 1255 |
+
"loss": 0.2649,
|
| 1256 |
+
"step": 1690
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.0932475884244373,
|
| 1260 |
+
"grad_norm": 0.16770875453948975,
|
| 1261 |
+
"learning_rate": 0.0001948521358159912,
|
| 1262 |
+
"loss": 0.265,
|
| 1263 |
+
"step": 1700
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.09967845659164,
|
| 1267 |
+
"grad_norm": 0.15347127616405487,
|
| 1268 |
+
"learning_rate": 0.00019419496166484117,
|
| 1269 |
+
"loss": 0.2629,
|
| 1270 |
+
"step": 1710
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.1061093247588425,
|
| 1274 |
+
"grad_norm": 0.1624882072210312,
|
| 1275 |
+
"learning_rate": 0.0001935377875136911,
|
| 1276 |
+
"loss": 0.2651,
|
| 1277 |
+
"step": 1720
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.112540192926045,
|
| 1281 |
+
"grad_norm": 0.17137973010540009,
|
| 1282 |
+
"learning_rate": 0.00019288061336254105,
|
| 1283 |
+
"loss": 0.2564,
|
| 1284 |
+
"step": 1730
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.1189710610932475,
|
| 1288 |
+
"grad_norm": 0.16637948155403137,
|
| 1289 |
+
"learning_rate": 0.00019222343921139102,
|
| 1290 |
+
"loss": 0.2642,
|
| 1291 |
+
"step": 1740
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.1254019292604502,
|
| 1295 |
+
"grad_norm": 0.1559745818376541,
|
| 1296 |
+
"learning_rate": 0.00019156626506024093,
|
| 1297 |
+
"loss": 0.2679,
|
| 1298 |
+
"step": 1750
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.1318327974276527,
|
| 1302 |
+
"grad_norm": 0.1712270975112915,
|
| 1303 |
+
"learning_rate": 0.0001909090909090909,
|
| 1304 |
+
"loss": 0.2611,
|
| 1305 |
+
"step": 1760
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.1382636655948553,
|
| 1309 |
+
"grad_norm": 0.18316815793514252,
|
| 1310 |
+
"learning_rate": 0.00019025191675794086,
|
| 1311 |
+
"loss": 0.2661,
|
| 1312 |
+
"step": 1770
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.144694533762058,
|
| 1316 |
+
"grad_norm": 0.16947688162326813,
|
| 1317 |
+
"learning_rate": 0.00018959474260679077,
|
| 1318 |
+
"loss": 0.2635,
|
| 1319 |
+
"step": 1780
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.1511254019292605,
|
| 1323 |
+
"grad_norm": 0.16996344923973083,
|
| 1324 |
+
"learning_rate": 0.00018893756845564074,
|
| 1325 |
+
"loss": 0.2612,
|
| 1326 |
+
"step": 1790
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.157556270096463,
|
| 1330 |
+
"grad_norm": 0.16218321025371552,
|
| 1331 |
+
"learning_rate": 0.00018828039430449068,
|
| 1332 |
+
"loss": 0.2614,
|
| 1333 |
+
"step": 1800
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.157556270096463,
|
| 1337 |
+
"eval_loss": 0.2809600234031677,
|
| 1338 |
+
"eval_runtime": 829.6019,
|
| 1339 |
+
"eval_samples_per_second": 2.411,
|
| 1340 |
+
"eval_steps_per_second": 2.411,
|
| 1341 |
+
"step": 1800
|
| 1342 |
+
}
|
| 1343 |
+
],
|
| 1344 |
+
"logging_steps": 10,
|
| 1345 |
+
"max_steps": 4665,
|
| 1346 |
+
"num_input_tokens_seen": 0,
|
| 1347 |
+
"num_train_epochs": 3,
|
| 1348 |
+
"save_steps": 200,
|
| 1349 |
+
"stateful_callbacks": {
|
| 1350 |
+
"TrainerControl": {
|
| 1351 |
+
"args": {
|
| 1352 |
+
"should_epoch_stop": false,
|
| 1353 |
+
"should_evaluate": false,
|
| 1354 |
+
"should_log": false,
|
| 1355 |
+
"should_save": true,
|
| 1356 |
+
"should_training_stop": false
|
| 1357 |
+
},
|
| 1358 |
+
"attributes": {}
|
| 1359 |
+
}
|
| 1360 |
+
},
|
| 1361 |
+
"total_flos": 2.64707486237098e+18,
|
| 1362 |
+
"train_batch_size": 1,
|
| 1363 |
+
"trial_name": null,
|
| 1364 |
+
"trial_params": null
|
| 1365 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29b7e03fe0a8c61c30c12490f2820039fd437f04fc4a9e0f5deb6ad1472e680f
|
| 3 |
+
size 5048
|