Upload 12 files
Browse files- README.md +202 -0
- adapter_model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1048 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: google/gemma-7b-it
|
| 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_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7247616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e472256015ab3321b2936015f9f6fac1b9dc926b5b62cd1d3db3f018e74485ff
|
| 3 |
size 7247616
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08c44ad6d94f3fcc548d1c4b773b746f029a85e94cfc59471da43568cef5b2b8
|
| 3 |
+
size 14591866
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ad55119de1e13a9887ebdb75b834f80d5ec038b410405f875ebf02be93c9cbf
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ff26b2c82187b78643f5b30ed10abde142c89e0ea7822c395397e0b3a13cdae
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1048 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.83203125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01953125,
|
| 13 |
+
"grad_norm": 6.625,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 12.2067,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0390625,
|
| 20 |
+
"grad_norm": 6.4375,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 12.0134,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05859375,
|
| 27 |
+
"grad_norm": 7.6875,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 11.4098,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.078125,
|
| 34 |
+
"grad_norm": 7.40625,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 10.0389,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09765625,
|
| 41 |
+
"grad_norm": 7.40625,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 8.5586,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1171875,
|
| 48 |
+
"grad_norm": 8.375,
|
| 49 |
+
"learning_rate": 6e-05,
|
| 50 |
+
"loss": 7.2376,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13671875,
|
| 55 |
+
"grad_norm": 10.8125,
|
| 56 |
+
"learning_rate": 7e-05,
|
| 57 |
+
"loss": 6.2848,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.15625,
|
| 62 |
+
"grad_norm": 13.6875,
|
| 63 |
+
"learning_rate": 8e-05,
|
| 64 |
+
"loss": 5.0552,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17578125,
|
| 69 |
+
"grad_norm": 14.875,
|
| 70 |
+
"learning_rate": 9e-05,
|
| 71 |
+
"loss": 3.7062,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1953125,
|
| 76 |
+
"grad_norm": 14.875,
|
| 77 |
+
"learning_rate": 0.0001,
|
| 78 |
+
"loss": 2.22,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.21484375,
|
| 83 |
+
"grad_norm": 4.15625,
|
| 84 |
+
"learning_rate": 9.930362116991644e-05,
|
| 85 |
+
"loss": 0.7615,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.234375,
|
| 90 |
+
"grad_norm": 2.265625,
|
| 91 |
+
"learning_rate": 9.860724233983287e-05,
|
| 92 |
+
"loss": 0.3524,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25390625,
|
| 97 |
+
"grad_norm": 1.203125,
|
| 98 |
+
"learning_rate": 9.79108635097493e-05,
|
| 99 |
+
"loss": 0.29,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2734375,
|
| 104 |
+
"grad_norm": 2.765625,
|
| 105 |
+
"learning_rate": 9.721448467966574e-05,
|
| 106 |
+
"loss": 0.3019,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.29296875,
|
| 111 |
+
"grad_norm": 1.8125,
|
| 112 |
+
"learning_rate": 9.651810584958218e-05,
|
| 113 |
+
"loss": 0.2656,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3125,
|
| 118 |
+
"grad_norm": 1.0,
|
| 119 |
+
"learning_rate": 9.58217270194986e-05,
|
| 120 |
+
"loss": 0.2589,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.33203125,
|
| 125 |
+
"grad_norm": 2.0625,
|
| 126 |
+
"learning_rate": 9.512534818941504e-05,
|
| 127 |
+
"loss": 0.2599,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3515625,
|
| 132 |
+
"grad_norm": 1.1328125,
|
| 133 |
+
"learning_rate": 9.442896935933148e-05,
|
| 134 |
+
"loss": 0.2475,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.37109375,
|
| 139 |
+
"grad_norm": 1.359375,
|
| 140 |
+
"learning_rate": 9.373259052924791e-05,
|
| 141 |
+
"loss": 0.2394,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.390625,
|
| 146 |
+
"grad_norm": 2.03125,
|
| 147 |
+
"learning_rate": 9.303621169916435e-05,
|
| 148 |
+
"loss": 0.2196,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.41015625,
|
| 153 |
+
"grad_norm": 1.21875,
|
| 154 |
+
"learning_rate": 9.233983286908079e-05,
|
| 155 |
+
"loss": 0.2454,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4296875,
|
| 160 |
+
"grad_norm": 0.734375,
|
| 161 |
+
"learning_rate": 9.164345403899723e-05,
|
| 162 |
+
"loss": 0.2208,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.44921875,
|
| 167 |
+
"grad_norm": 1.015625,
|
| 168 |
+
"learning_rate": 9.094707520891366e-05,
|
| 169 |
+
"loss": 0.2191,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.46875,
|
| 174 |
+
"grad_norm": 0.8359375,
|
| 175 |
+
"learning_rate": 9.025069637883009e-05,
|
| 176 |
+
"loss": 0.2117,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.48828125,
|
| 181 |
+
"grad_norm": 1.0703125,
|
| 182 |
+
"learning_rate": 8.955431754874652e-05,
|
| 183 |
+
"loss": 0.2274,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5078125,
|
| 188 |
+
"grad_norm": 1.25,
|
| 189 |
+
"learning_rate": 8.885793871866296e-05,
|
| 190 |
+
"loss": 0.1993,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.52734375,
|
| 195 |
+
"grad_norm": 1.1328125,
|
| 196 |
+
"learning_rate": 8.81615598885794e-05,
|
| 197 |
+
"loss": 0.2185,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.546875,
|
| 202 |
+
"grad_norm": 0.7578125,
|
| 203 |
+
"learning_rate": 8.746518105849582e-05,
|
| 204 |
+
"loss": 0.2048,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.56640625,
|
| 209 |
+
"grad_norm": 0.7734375,
|
| 210 |
+
"learning_rate": 8.676880222841226e-05,
|
| 211 |
+
"loss": 0.2008,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5859375,
|
| 216 |
+
"grad_norm": 0.92578125,
|
| 217 |
+
"learning_rate": 8.60724233983287e-05,
|
| 218 |
+
"loss": 0.1946,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.60546875,
|
| 223 |
+
"grad_norm": 0.83984375,
|
| 224 |
+
"learning_rate": 8.537604456824512e-05,
|
| 225 |
+
"loss": 0.1977,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.625,
|
| 230 |
+
"grad_norm": 0.62890625,
|
| 231 |
+
"learning_rate": 8.467966573816156e-05,
|
| 232 |
+
"loss": 0.1928,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.64453125,
|
| 237 |
+
"grad_norm": 1.0625,
|
| 238 |
+
"learning_rate": 8.3983286908078e-05,
|
| 239 |
+
"loss": 0.2045,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6640625,
|
| 244 |
+
"grad_norm": 0.546875,
|
| 245 |
+
"learning_rate": 8.328690807799443e-05,
|
| 246 |
+
"loss": 0.189,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.68359375,
|
| 251 |
+
"grad_norm": 1.3203125,
|
| 252 |
+
"learning_rate": 8.259052924791086e-05,
|
| 253 |
+
"loss": 0.1849,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.703125,
|
| 258 |
+
"grad_norm": 0.71484375,
|
| 259 |
+
"learning_rate": 8.18941504178273e-05,
|
| 260 |
+
"loss": 0.1868,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.72265625,
|
| 265 |
+
"grad_norm": 0.73828125,
|
| 266 |
+
"learning_rate": 8.119777158774373e-05,
|
| 267 |
+
"loss": 0.1968,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7421875,
|
| 272 |
+
"grad_norm": 0.94140625,
|
| 273 |
+
"learning_rate": 8.050139275766017e-05,
|
| 274 |
+
"loss": 0.1875,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.76171875,
|
| 279 |
+
"grad_norm": 1.2421875,
|
| 280 |
+
"learning_rate": 7.980501392757661e-05,
|
| 281 |
+
"loss": 0.1849,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.78125,
|
| 286 |
+
"grad_norm": 0.6875,
|
| 287 |
+
"learning_rate": 7.910863509749304e-05,
|
| 288 |
+
"loss": 0.184,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.80078125,
|
| 293 |
+
"grad_norm": 0.59765625,
|
| 294 |
+
"learning_rate": 7.841225626740948e-05,
|
| 295 |
+
"loss": 0.1742,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8203125,
|
| 300 |
+
"grad_norm": 0.66015625,
|
| 301 |
+
"learning_rate": 7.771587743732592e-05,
|
| 302 |
+
"loss": 0.173,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.83984375,
|
| 307 |
+
"grad_norm": 0.5703125,
|
| 308 |
+
"learning_rate": 7.701949860724234e-05,
|
| 309 |
+
"loss": 0.1583,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.859375,
|
| 314 |
+
"grad_norm": 0.625,
|
| 315 |
+
"learning_rate": 7.632311977715878e-05,
|
| 316 |
+
"loss": 0.1507,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.87890625,
|
| 321 |
+
"grad_norm": 0.9375,
|
| 322 |
+
"learning_rate": 7.562674094707522e-05,
|
| 323 |
+
"loss": 0.1667,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8984375,
|
| 328 |
+
"grad_norm": 0.6484375,
|
| 329 |
+
"learning_rate": 7.493036211699165e-05,
|
| 330 |
+
"loss": 0.1445,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.91796875,
|
| 335 |
+
"grad_norm": 0.66796875,
|
| 336 |
+
"learning_rate": 7.423398328690808e-05,
|
| 337 |
+
"loss": 0.1268,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9375,
|
| 342 |
+
"grad_norm": 0.734375,
|
| 343 |
+
"learning_rate": 7.353760445682452e-05,
|
| 344 |
+
"loss": 0.1437,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.95703125,
|
| 349 |
+
"grad_norm": 0.77734375,
|
| 350 |
+
"learning_rate": 7.284122562674095e-05,
|
| 351 |
+
"loss": 0.1439,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9765625,
|
| 356 |
+
"grad_norm": 1.0,
|
| 357 |
+
"learning_rate": 7.214484679665738e-05,
|
| 358 |
+
"loss": 0.1341,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.99609375,
|
| 363 |
+
"grad_norm": 0.74609375,
|
| 364 |
+
"learning_rate": 7.144846796657381e-05,
|
| 365 |
+
"loss": 0.1202,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.015625,
|
| 370 |
+
"grad_norm": 0.66015625,
|
| 371 |
+
"learning_rate": 7.075208913649025e-05,
|
| 372 |
+
"loss": 0.1236,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.03515625,
|
| 377 |
+
"grad_norm": 0.72265625,
|
| 378 |
+
"learning_rate": 7.005571030640669e-05,
|
| 379 |
+
"loss": 0.1184,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.0546875,
|
| 384 |
+
"grad_norm": 1.203125,
|
| 385 |
+
"learning_rate": 6.935933147632311e-05,
|
| 386 |
+
"loss": 0.124,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.07421875,
|
| 391 |
+
"grad_norm": 0.83984375,
|
| 392 |
+
"learning_rate": 6.866295264623955e-05,
|
| 393 |
+
"loss": 0.1223,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.09375,
|
| 398 |
+
"grad_norm": 0.66015625,
|
| 399 |
+
"learning_rate": 6.796657381615599e-05,
|
| 400 |
+
"loss": 0.1136,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.11328125,
|
| 405 |
+
"grad_norm": 0.7578125,
|
| 406 |
+
"learning_rate": 6.727019498607243e-05,
|
| 407 |
+
"loss": 0.1113,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.1328125,
|
| 412 |
+
"grad_norm": 1.1015625,
|
| 413 |
+
"learning_rate": 6.657381615598886e-05,
|
| 414 |
+
"loss": 0.1055,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.15234375,
|
| 419 |
+
"grad_norm": 0.54296875,
|
| 420 |
+
"learning_rate": 6.58774373259053e-05,
|
| 421 |
+
"loss": 0.1148,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.171875,
|
| 426 |
+
"grad_norm": 0.91015625,
|
| 427 |
+
"learning_rate": 6.518105849582174e-05,
|
| 428 |
+
"loss": 0.1082,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.19140625,
|
| 433 |
+
"grad_norm": 0.9140625,
|
| 434 |
+
"learning_rate": 6.448467966573817e-05,
|
| 435 |
+
"loss": 0.0998,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.2109375,
|
| 440 |
+
"grad_norm": 0.84375,
|
| 441 |
+
"learning_rate": 6.37883008356546e-05,
|
| 442 |
+
"loss": 0.1083,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.23046875,
|
| 447 |
+
"grad_norm": 0.65625,
|
| 448 |
+
"learning_rate": 6.309192200557104e-05,
|
| 449 |
+
"loss": 0.1035,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.25,
|
| 454 |
+
"grad_norm": 0.9921875,
|
| 455 |
+
"learning_rate": 6.239554317548747e-05,
|
| 456 |
+
"loss": 0.1097,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.26953125,
|
| 461 |
+
"grad_norm": 0.458984375,
|
| 462 |
+
"learning_rate": 6.169916434540391e-05,
|
| 463 |
+
"loss": 0.1096,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.2890625,
|
| 468 |
+
"grad_norm": 0.51953125,
|
| 469 |
+
"learning_rate": 6.100278551532034e-05,
|
| 470 |
+
"loss": 0.1072,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.30859375,
|
| 475 |
+
"grad_norm": 0.59765625,
|
| 476 |
+
"learning_rate": 6.030640668523677e-05,
|
| 477 |
+
"loss": 0.1094,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.328125,
|
| 482 |
+
"grad_norm": 0.59375,
|
| 483 |
+
"learning_rate": 5.96100278551532e-05,
|
| 484 |
+
"loss": 0.1106,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.34765625,
|
| 489 |
+
"grad_norm": 0.388671875,
|
| 490 |
+
"learning_rate": 5.891364902506964e-05,
|
| 491 |
+
"loss": 0.1014,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.3671875,
|
| 496 |
+
"grad_norm": 0.478515625,
|
| 497 |
+
"learning_rate": 5.821727019498607e-05,
|
| 498 |
+
"loss": 0.1151,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.38671875,
|
| 503 |
+
"grad_norm": 0.71484375,
|
| 504 |
+
"learning_rate": 5.752089136490251e-05,
|
| 505 |
+
"loss": 0.1117,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.40625,
|
| 510 |
+
"grad_norm": 0.61328125,
|
| 511 |
+
"learning_rate": 5.682451253481894e-05,
|
| 512 |
+
"loss": 0.1102,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.42578125,
|
| 517 |
+
"grad_norm": 0.80078125,
|
| 518 |
+
"learning_rate": 5.6128133704735375e-05,
|
| 519 |
+
"loss": 0.1093,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.4453125,
|
| 524 |
+
"grad_norm": 0.55078125,
|
| 525 |
+
"learning_rate": 5.5431754874651806e-05,
|
| 526 |
+
"loss": 0.1046,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.46484375,
|
| 531 |
+
"grad_norm": 0.4765625,
|
| 532 |
+
"learning_rate": 5.473537604456824e-05,
|
| 533 |
+
"loss": 0.1013,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.484375,
|
| 538 |
+
"grad_norm": 0.99609375,
|
| 539 |
+
"learning_rate": 5.4038997214484674e-05,
|
| 540 |
+
"loss": 0.1108,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.50390625,
|
| 545 |
+
"grad_norm": 0.71875,
|
| 546 |
+
"learning_rate": 5.3342618384401125e-05,
|
| 547 |
+
"loss": 0.1068,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.5234375,
|
| 552 |
+
"grad_norm": 0.671875,
|
| 553 |
+
"learning_rate": 5.2646239554317555e-05,
|
| 554 |
+
"loss": 0.1037,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.54296875,
|
| 559 |
+
"grad_norm": 0.7265625,
|
| 560 |
+
"learning_rate": 5.194986072423399e-05,
|
| 561 |
+
"loss": 0.1091,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.5625,
|
| 566 |
+
"grad_norm": 0.58203125,
|
| 567 |
+
"learning_rate": 5.125348189415042e-05,
|
| 568 |
+
"loss": 0.0982,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.58203125,
|
| 573 |
+
"grad_norm": 1.015625,
|
| 574 |
+
"learning_rate": 5.055710306406686e-05,
|
| 575 |
+
"loss": 0.1121,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.6015625,
|
| 580 |
+
"grad_norm": 0.4140625,
|
| 581 |
+
"learning_rate": 4.986072423398329e-05,
|
| 582 |
+
"loss": 0.1028,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.62109375,
|
| 587 |
+
"grad_norm": 1.09375,
|
| 588 |
+
"learning_rate": 4.916434540389973e-05,
|
| 589 |
+
"loss": 0.1057,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.640625,
|
| 594 |
+
"grad_norm": 0.73046875,
|
| 595 |
+
"learning_rate": 4.846796657381616e-05,
|
| 596 |
+
"loss": 0.1048,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.66015625,
|
| 601 |
+
"grad_norm": 1.265625,
|
| 602 |
+
"learning_rate": 4.7771587743732597e-05,
|
| 603 |
+
"loss": 0.1053,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.6796875,
|
| 608 |
+
"grad_norm": 0.72265625,
|
| 609 |
+
"learning_rate": 4.707520891364903e-05,
|
| 610 |
+
"loss": 0.0982,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.69921875,
|
| 615 |
+
"grad_norm": 0.42578125,
|
| 616 |
+
"learning_rate": 4.637883008356546e-05,
|
| 617 |
+
"loss": 0.0999,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.71875,
|
| 622 |
+
"grad_norm": 0.55859375,
|
| 623 |
+
"learning_rate": 4.5682451253481895e-05,
|
| 624 |
+
"loss": 0.1044,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.73828125,
|
| 629 |
+
"grad_norm": 0.57421875,
|
| 630 |
+
"learning_rate": 4.4986072423398326e-05,
|
| 631 |
+
"loss": 0.106,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.7578125,
|
| 636 |
+
"grad_norm": 0.546875,
|
| 637 |
+
"learning_rate": 4.428969359331476e-05,
|
| 638 |
+
"loss": 0.0987,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.77734375,
|
| 643 |
+
"grad_norm": 0.5546875,
|
| 644 |
+
"learning_rate": 4.35933147632312e-05,
|
| 645 |
+
"loss": 0.0935,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.796875,
|
| 650 |
+
"grad_norm": 0.6171875,
|
| 651 |
+
"learning_rate": 4.289693593314764e-05,
|
| 652 |
+
"loss": 0.0984,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.81640625,
|
| 657 |
+
"grad_norm": 0.431640625,
|
| 658 |
+
"learning_rate": 4.220055710306407e-05,
|
| 659 |
+
"loss": 0.1019,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.8359375,
|
| 664 |
+
"grad_norm": 0.79296875,
|
| 665 |
+
"learning_rate": 4.1504178272980506e-05,
|
| 666 |
+
"loss": 0.1046,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.85546875,
|
| 671 |
+
"grad_norm": 0.51171875,
|
| 672 |
+
"learning_rate": 4.0807799442896936e-05,
|
| 673 |
+
"loss": 0.1057,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.875,
|
| 678 |
+
"grad_norm": 0.79296875,
|
| 679 |
+
"learning_rate": 4.0111420612813374e-05,
|
| 680 |
+
"loss": 0.102,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.89453125,
|
| 685 |
+
"grad_norm": 0.57421875,
|
| 686 |
+
"learning_rate": 3.9415041782729804e-05,
|
| 687 |
+
"loss": 0.0955,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.9140625,
|
| 692 |
+
"grad_norm": 0.68359375,
|
| 693 |
+
"learning_rate": 3.871866295264624e-05,
|
| 694 |
+
"loss": 0.1012,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.93359375,
|
| 699 |
+
"grad_norm": 0.51171875,
|
| 700 |
+
"learning_rate": 3.802228412256267e-05,
|
| 701 |
+
"loss": 0.1026,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.953125,
|
| 706 |
+
"grad_norm": 0.494140625,
|
| 707 |
+
"learning_rate": 3.7325905292479116e-05,
|
| 708 |
+
"loss": 0.1015,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.97265625,
|
| 713 |
+
"grad_norm": 0.5078125,
|
| 714 |
+
"learning_rate": 3.662952646239555e-05,
|
| 715 |
+
"loss": 0.1069,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.9921875,
|
| 720 |
+
"grad_norm": 0.69921875,
|
| 721 |
+
"learning_rate": 3.5933147632311984e-05,
|
| 722 |
+
"loss": 0.0937,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.01171875,
|
| 727 |
+
"grad_norm": 0.58984375,
|
| 728 |
+
"learning_rate": 3.5236768802228415e-05,
|
| 729 |
+
"loss": 0.0985,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.03125,
|
| 734 |
+
"grad_norm": 0.466796875,
|
| 735 |
+
"learning_rate": 3.454038997214485e-05,
|
| 736 |
+
"loss": 0.1058,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.05078125,
|
| 741 |
+
"grad_norm": 0.7578125,
|
| 742 |
+
"learning_rate": 3.384401114206128e-05,
|
| 743 |
+
"loss": 0.0993,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.0703125,
|
| 748 |
+
"grad_norm": 0.8671875,
|
| 749 |
+
"learning_rate": 3.314763231197771e-05,
|
| 750 |
+
"loss": 0.1004,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.08984375,
|
| 755 |
+
"grad_norm": 0.71875,
|
| 756 |
+
"learning_rate": 3.245125348189415e-05,
|
| 757 |
+
"loss": 0.0988,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.109375,
|
| 762 |
+
"grad_norm": 0.50390625,
|
| 763 |
+
"learning_rate": 3.175487465181058e-05,
|
| 764 |
+
"loss": 0.1189,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.12890625,
|
| 769 |
+
"grad_norm": 0.703125,
|
| 770 |
+
"learning_rate": 3.105849582172702e-05,
|
| 771 |
+
"loss": 0.1001,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.1484375,
|
| 776 |
+
"grad_norm": 0.7734375,
|
| 777 |
+
"learning_rate": 3.036211699164346e-05,
|
| 778 |
+
"loss": 0.1079,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.16796875,
|
| 783 |
+
"grad_norm": 0.703125,
|
| 784 |
+
"learning_rate": 2.9665738161559893e-05,
|
| 785 |
+
"loss": 0.1067,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.1875,
|
| 790 |
+
"grad_norm": 0.470703125,
|
| 791 |
+
"learning_rate": 2.8969359331476327e-05,
|
| 792 |
+
"loss": 0.0987,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.20703125,
|
| 797 |
+
"grad_norm": 0.53125,
|
| 798 |
+
"learning_rate": 2.827298050139276e-05,
|
| 799 |
+
"loss": 0.0969,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.2265625,
|
| 804 |
+
"grad_norm": 0.55859375,
|
| 805 |
+
"learning_rate": 2.7576601671309192e-05,
|
| 806 |
+
"loss": 0.0976,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.24609375,
|
| 811 |
+
"grad_norm": 0.515625,
|
| 812 |
+
"learning_rate": 2.6880222841225626e-05,
|
| 813 |
+
"loss": 0.1017,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.265625,
|
| 818 |
+
"grad_norm": 0.95703125,
|
| 819 |
+
"learning_rate": 2.618384401114206e-05,
|
| 820 |
+
"loss": 0.0963,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.28515625,
|
| 825 |
+
"grad_norm": 0.71484375,
|
| 826 |
+
"learning_rate": 2.5487465181058494e-05,
|
| 827 |
+
"loss": 0.1029,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.3046875,
|
| 832 |
+
"grad_norm": 0.9296875,
|
| 833 |
+
"learning_rate": 2.479108635097493e-05,
|
| 834 |
+
"loss": 0.099,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.32421875,
|
| 839 |
+
"grad_norm": 0.482421875,
|
| 840 |
+
"learning_rate": 2.4094707520891365e-05,
|
| 841 |
+
"loss": 0.1005,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.34375,
|
| 846 |
+
"grad_norm": 0.6171875,
|
| 847 |
+
"learning_rate": 2.33983286908078e-05,
|
| 848 |
+
"loss": 0.0955,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.36328125,
|
| 853 |
+
"grad_norm": 0.515625,
|
| 854 |
+
"learning_rate": 2.2701949860724233e-05,
|
| 855 |
+
"loss": 0.0982,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.3828125,
|
| 860 |
+
"grad_norm": 0.7265625,
|
| 861 |
+
"learning_rate": 2.200557103064067e-05,
|
| 862 |
+
"loss": 0.1055,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.40234375,
|
| 867 |
+
"grad_norm": 0.6484375,
|
| 868 |
+
"learning_rate": 2.1309192200557104e-05,
|
| 869 |
+
"loss": 0.1029,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.421875,
|
| 874 |
+
"grad_norm": 0.59765625,
|
| 875 |
+
"learning_rate": 2.0612813370473538e-05,
|
| 876 |
+
"loss": 0.0998,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.44140625,
|
| 881 |
+
"grad_norm": 0.6796875,
|
| 882 |
+
"learning_rate": 1.9916434540389972e-05,
|
| 883 |
+
"loss": 0.0963,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.4609375,
|
| 888 |
+
"grad_norm": 0.478515625,
|
| 889 |
+
"learning_rate": 1.922005571030641e-05,
|
| 890 |
+
"loss": 0.1001,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.48046875,
|
| 895 |
+
"grad_norm": 0.48828125,
|
| 896 |
+
"learning_rate": 1.8523676880222844e-05,
|
| 897 |
+
"loss": 0.1031,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.5,
|
| 902 |
+
"grad_norm": 0.52734375,
|
| 903 |
+
"learning_rate": 1.7827298050139278e-05,
|
| 904 |
+
"loss": 0.0981,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.51953125,
|
| 909 |
+
"grad_norm": 0.578125,
|
| 910 |
+
"learning_rate": 1.713091922005571e-05,
|
| 911 |
+
"loss": 0.1022,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.5390625,
|
| 916 |
+
"grad_norm": 0.875,
|
| 917 |
+
"learning_rate": 1.6434540389972145e-05,
|
| 918 |
+
"loss": 0.0981,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.55859375,
|
| 923 |
+
"grad_norm": 0.59375,
|
| 924 |
+
"learning_rate": 1.5738161559888583e-05,
|
| 925 |
+
"loss": 0.0974,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.578125,
|
| 930 |
+
"grad_norm": 0.7578125,
|
| 931 |
+
"learning_rate": 1.5041782729805015e-05,
|
| 932 |
+
"loss": 0.0961,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.59765625,
|
| 937 |
+
"grad_norm": 0.7265625,
|
| 938 |
+
"learning_rate": 1.4345403899721449e-05,
|
| 939 |
+
"loss": 0.0927,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.6171875,
|
| 944 |
+
"grad_norm": 0.51953125,
|
| 945 |
+
"learning_rate": 1.3649025069637883e-05,
|
| 946 |
+
"loss": 0.102,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.63671875,
|
| 951 |
+
"grad_norm": 0.6171875,
|
| 952 |
+
"learning_rate": 1.2952646239554317e-05,
|
| 953 |
+
"loss": 0.0991,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.65625,
|
| 958 |
+
"grad_norm": 0.5078125,
|
| 959 |
+
"learning_rate": 1.2256267409470753e-05,
|
| 960 |
+
"loss": 0.0951,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.67578125,
|
| 965 |
+
"grad_norm": 0.515625,
|
| 966 |
+
"learning_rate": 1.1559888579387188e-05,
|
| 967 |
+
"loss": 0.0944,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.6953125,
|
| 972 |
+
"grad_norm": 0.703125,
|
| 973 |
+
"learning_rate": 1.086350974930362e-05,
|
| 974 |
+
"loss": 0.1067,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.71484375,
|
| 979 |
+
"grad_norm": 0.7265625,
|
| 980 |
+
"learning_rate": 1.0167130919220056e-05,
|
| 981 |
+
"loss": 0.0935,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.734375,
|
| 986 |
+
"grad_norm": 0.66015625,
|
| 987 |
+
"learning_rate": 9.47075208913649e-06,
|
| 988 |
+
"loss": 0.0963,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.75390625,
|
| 993 |
+
"grad_norm": 0.84375,
|
| 994 |
+
"learning_rate": 8.774373259052924e-06,
|
| 995 |
+
"loss": 0.1012,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.7734375,
|
| 1000 |
+
"grad_norm": 0.7265625,
|
| 1001 |
+
"learning_rate": 8.07799442896936e-06,
|
| 1002 |
+
"loss": 0.0954,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.79296875,
|
| 1007 |
+
"grad_norm": 0.462890625,
|
| 1008 |
+
"learning_rate": 7.381615598885794e-06,
|
| 1009 |
+
"loss": 0.0997,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.8125,
|
| 1014 |
+
"grad_norm": 0.5703125,
|
| 1015 |
+
"learning_rate": 6.6852367688022295e-06,
|
| 1016 |
+
"loss": 0.0999,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.83203125,
|
| 1021 |
+
"grad_norm": 0.5859375,
|
| 1022 |
+
"learning_rate": 5.988857938718663e-06,
|
| 1023 |
+
"loss": 0.0898,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
}
|
| 1026 |
+
],
|
| 1027 |
+
"logging_steps": 10,
|
| 1028 |
+
"max_steps": 1536,
|
| 1029 |
+
"num_input_tokens_seen": 0,
|
| 1030 |
+
"num_train_epochs": 3,
|
| 1031 |
+
"save_steps": 10,
|
| 1032 |
+
"stateful_callbacks": {
|
| 1033 |
+
"TrainerControl": {
|
| 1034 |
+
"args": {
|
| 1035 |
+
"should_epoch_stop": false,
|
| 1036 |
+
"should_evaluate": false,
|
| 1037 |
+
"should_log": false,
|
| 1038 |
+
"should_save": true,
|
| 1039 |
+
"should_training_stop": false
|
| 1040 |
+
},
|
| 1041 |
+
"attributes": {}
|
| 1042 |
+
}
|
| 1043 |
+
},
|
| 1044 |
+
"total_flos": 5763521685399552.0,
|
| 1045 |
+
"train_batch_size": 1,
|
| 1046 |
+
"trial_name": null,
|
| 1047 |
+
"trial_params": null
|
| 1048 |
+
}
|