Upload 8 files
Browse files- checkpoint-16000/README.md +207 -0
- checkpoint-16000/adapter_config.json +29 -0
- checkpoint-16000/adapter_model.safetensors +3 -0
- checkpoint-16000/optimizer.pt +3 -0
- checkpoint-16000/rng_state.pth +3 -0
- checkpoint-16000/scheduler.pt +3 -0
- checkpoint-16000/trainer_state.json +1139 -0
- checkpoint-16000/training_args.bin +3 -0
checkpoint-16000/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: nickypro/tinyllama-15M
|
| 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 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 22 |
+
- **Model type:** [More Information Needed]
|
| 23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 24 |
+
- **License:** [More Information Needed]
|
| 25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 26 |
+
|
| 27 |
+
### Model Sources [optional]
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** [More Information Needed]
|
| 32 |
+
- **Paper [optional]:** [More Information Needed]
|
| 33 |
+
- **Demo [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
## Uses
|
| 36 |
+
|
| 37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 38 |
+
|
| 39 |
+
### Direct Use
|
| 40 |
+
|
| 41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 42 |
+
|
| 43 |
+
[More Information Needed]
|
| 44 |
+
|
| 45 |
+
### Downstream Use [optional]
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Out-of-Scope Use
|
| 52 |
+
|
| 53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
## Bias, Risks, and Limitations
|
| 58 |
+
|
| 59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
### Recommendations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 66 |
+
|
| 67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 68 |
+
|
| 69 |
+
## How to Get Started with the Model
|
| 70 |
+
|
| 71 |
+
Use the code below to get started with the model.
|
| 72 |
+
|
| 73 |
+
[More Information Needed]
|
| 74 |
+
|
| 75 |
+
## Training Details
|
| 76 |
+
|
| 77 |
+
### Training Data
|
| 78 |
+
|
| 79 |
+
<!-- This should link to a Data 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. -->
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
### Training Procedure
|
| 84 |
+
|
| 85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 86 |
+
|
| 87 |
+
#### Preprocessing [optional]
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
#### Training Hyperparameters
|
| 93 |
+
|
| 94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 95 |
+
|
| 96 |
+
#### Speeds, Sizes, Times [optional]
|
| 97 |
+
|
| 98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 99 |
+
|
| 100 |
+
[More Information Needed]
|
| 101 |
+
|
| 102 |
+
## Evaluation
|
| 103 |
+
|
| 104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 105 |
+
|
| 106 |
+
### Testing Data, Factors & Metrics
|
| 107 |
+
|
| 108 |
+
#### Testing Data
|
| 109 |
+
|
| 110 |
+
<!-- This should link to a Data Card if possible. -->
|
| 111 |
+
|
| 112 |
+
[More Information Needed]
|
| 113 |
+
|
| 114 |
+
#### Factors
|
| 115 |
+
|
| 116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Metrics
|
| 121 |
+
|
| 122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
### Results
|
| 127 |
+
|
| 128 |
+
[More Information Needed]
|
| 129 |
+
|
| 130 |
+
#### Summary
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
## Model Examination [optional]
|
| 135 |
+
|
| 136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
## Environmental Impact
|
| 141 |
+
|
| 142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 143 |
+
|
| 144 |
+
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).
|
| 145 |
+
|
| 146 |
+
- **Hardware Type:** [More Information Needed]
|
| 147 |
+
- **Hours used:** [More Information Needed]
|
| 148 |
+
- **Cloud Provider:** [More Information Needed]
|
| 149 |
+
- **Compute Region:** [More Information Needed]
|
| 150 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 151 |
+
|
| 152 |
+
## Technical Specifications [optional]
|
| 153 |
+
|
| 154 |
+
### Model Architecture and Objective
|
| 155 |
+
|
| 156 |
+
[More Information Needed]
|
| 157 |
+
|
| 158 |
+
### Compute Infrastructure
|
| 159 |
+
|
| 160 |
+
[More Information Needed]
|
| 161 |
+
|
| 162 |
+
#### Hardware
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
#### Software
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
## Citation [optional]
|
| 171 |
+
|
| 172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 173 |
+
|
| 174 |
+
**BibTeX:**
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
**APA:**
|
| 179 |
+
|
| 180 |
+
[More Information Needed]
|
| 181 |
+
|
| 182 |
+
## Glossary [optional]
|
| 183 |
+
|
| 184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## More Information [optional]
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
## Model Card Authors [optional]
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Model Card Contact
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
## Training procedure
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
- PEFT 0.6.1
|
checkpoint-16000/adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "nickypro/tinyllama-15M",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 64,
|
| 12 |
+
"lora_dropout": 0.05,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 64,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"down_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"lm_head",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"k_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM"
|
| 29 |
+
}
|
checkpoint-16000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d65f4025196714c4d0bdcad283d356d7780d8b3ec7b2de3aaa2b99339c49d526
|
| 3 |
+
size 16681976
|
checkpoint-16000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:169c6da3508fa7bdb7cb8e8fd7f72b9c75be531b70cc4f9bd24367d782ef4b73
|
| 3 |
+
size 33413946
|
checkpoint-16000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39dbf1d844a9992c04156e8f26097b66c86d4a136ff4e8dd95a0d61fddf67447
|
| 3 |
+
size 14244
|
checkpoint-16000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c433a611a29d5b077ab91ae6da062fd3c434ada04dfee5ef27669bde33d28e6e
|
| 3 |
+
size 1064
|
checkpoint-16000/trainer_state.json
ADDED
|
@@ -0,0 +1,1139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.893337455557273,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 16000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 0.0002981331673926571,
|
| 14 |
+
"loss": 2.3038,
|
| 15 |
+
"step": 200
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"eval_loss": 1.589147925376892,
|
| 20 |
+
"eval_runtime": 2.1684,
|
| 21 |
+
"eval_samples_per_second": 461.163,
|
| 22 |
+
"eval_steps_per_second": 57.645,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.25,
|
| 27 |
+
"learning_rate": 0.00029439950217797134,
|
| 28 |
+
"loss": 1.5398,
|
| 29 |
+
"step": 400
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.25,
|
| 33 |
+
"eval_loss": 1.4633430242538452,
|
| 34 |
+
"eval_runtime": 2.1071,
|
| 35 |
+
"eval_samples_per_second": 474.58,
|
| 36 |
+
"eval_steps_per_second": 59.323,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.37,
|
| 41 |
+
"learning_rate": 0.00029066583696328563,
|
| 42 |
+
"loss": 1.4615,
|
| 43 |
+
"step": 600
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.37,
|
| 47 |
+
"eval_loss": 1.4296711683273315,
|
| 48 |
+
"eval_runtime": 2.4812,
|
| 49 |
+
"eval_samples_per_second": 403.032,
|
| 50 |
+
"eval_steps_per_second": 50.379,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.49,
|
| 55 |
+
"learning_rate": 0.0002869321717485998,
|
| 56 |
+
"loss": 1.4244,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.49,
|
| 61 |
+
"eval_loss": 1.3793567419052124,
|
| 62 |
+
"eval_runtime": 2.9698,
|
| 63 |
+
"eval_samples_per_second": 336.72,
|
| 64 |
+
"eval_steps_per_second": 42.09,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.62,
|
| 69 |
+
"learning_rate": 0.0002831985065339141,
|
| 70 |
+
"loss": 1.3921,
|
| 71 |
+
"step": 1000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.62,
|
| 75 |
+
"eval_loss": 1.3315461874008179,
|
| 76 |
+
"eval_runtime": 2.7793,
|
| 77 |
+
"eval_samples_per_second": 359.806,
|
| 78 |
+
"eval_steps_per_second": 44.976,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.74,
|
| 83 |
+
"learning_rate": 0.00027946484131922836,
|
| 84 |
+
"loss": 1.0958,
|
| 85 |
+
"step": 1200
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.74,
|
| 89 |
+
"eval_loss": 0.7548955082893372,
|
| 90 |
+
"eval_runtime": 2.7656,
|
| 91 |
+
"eval_samples_per_second": 361.592,
|
| 92 |
+
"eval_steps_per_second": 45.199,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.87,
|
| 97 |
+
"learning_rate": 0.0002757311761045426,
|
| 98 |
+
"loss": 0.6312,
|
| 99 |
+
"step": 1400
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.87,
|
| 103 |
+
"eval_loss": 0.3990221917629242,
|
| 104 |
+
"eval_runtime": 2.1502,
|
| 105 |
+
"eval_samples_per_second": 465.071,
|
| 106 |
+
"eval_steps_per_second": 58.134,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.99,
|
| 111 |
+
"learning_rate": 0.00027199751088985685,
|
| 112 |
+
"loss": 0.4093,
|
| 113 |
+
"step": 1600
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.99,
|
| 117 |
+
"eval_loss": 0.26113563776016235,
|
| 118 |
+
"eval_runtime": 3.5103,
|
| 119 |
+
"eval_samples_per_second": 284.875,
|
| 120 |
+
"eval_steps_per_second": 35.609,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.11,
|
| 125 |
+
"learning_rate": 0.00026826384567517114,
|
| 126 |
+
"loss": 0.2959,
|
| 127 |
+
"step": 1800
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.11,
|
| 131 |
+
"eval_loss": 0.2783801257610321,
|
| 132 |
+
"eval_runtime": 2.8441,
|
| 133 |
+
"eval_samples_per_second": 351.603,
|
| 134 |
+
"eval_steps_per_second": 43.95,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.24,
|
| 139 |
+
"learning_rate": 0.00026453018046048533,
|
| 140 |
+
"loss": 0.2589,
|
| 141 |
+
"step": 2000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.24,
|
| 145 |
+
"eval_loss": 0.20705343782901764,
|
| 146 |
+
"eval_runtime": 2.7524,
|
| 147 |
+
"eval_samples_per_second": 363.322,
|
| 148 |
+
"eval_steps_per_second": 45.415,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.36,
|
| 153 |
+
"learning_rate": 0.0002607965152457996,
|
| 154 |
+
"loss": 0.2246,
|
| 155 |
+
"step": 2200
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.36,
|
| 159 |
+
"eval_loss": 0.15551678836345673,
|
| 160 |
+
"eval_runtime": 2.15,
|
| 161 |
+
"eval_samples_per_second": 465.117,
|
| 162 |
+
"eval_steps_per_second": 58.14,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.48,
|
| 167 |
+
"learning_rate": 0.00025706285003111387,
|
| 168 |
+
"loss": 0.1991,
|
| 169 |
+
"step": 2400
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.48,
|
| 173 |
+
"eval_loss": 0.15825262665748596,
|
| 174 |
+
"eval_runtime": 2.1344,
|
| 175 |
+
"eval_samples_per_second": 468.515,
|
| 176 |
+
"eval_steps_per_second": 58.564,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.61,
|
| 181 |
+
"learning_rate": 0.0002533291848164281,
|
| 182 |
+
"loss": 0.1784,
|
| 183 |
+
"step": 2600
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.61,
|
| 187 |
+
"eval_loss": 0.12008943408727646,
|
| 188 |
+
"eval_runtime": 2.1414,
|
| 189 |
+
"eval_samples_per_second": 466.985,
|
| 190 |
+
"eval_steps_per_second": 58.373,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.73,
|
| 195 |
+
"learning_rate": 0.00024959551960174235,
|
| 196 |
+
"loss": 0.1598,
|
| 197 |
+
"step": 2800
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.73,
|
| 201 |
+
"eval_loss": 0.12511701881885529,
|
| 202 |
+
"eval_runtime": 2.55,
|
| 203 |
+
"eval_samples_per_second": 392.155,
|
| 204 |
+
"eval_steps_per_second": 49.019,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.86,
|
| 209 |
+
"learning_rate": 0.0002458618543870566,
|
| 210 |
+
"loss": 0.164,
|
| 211 |
+
"step": 3000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.86,
|
| 215 |
+
"eval_loss": 0.11049681156873703,
|
| 216 |
+
"eval_runtime": 2.9765,
|
| 217 |
+
"eval_samples_per_second": 335.97,
|
| 218 |
+
"eval_steps_per_second": 41.996,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.98,
|
| 223 |
+
"learning_rate": 0.00024212818917237084,
|
| 224 |
+
"loss": 0.1475,
|
| 225 |
+
"step": 3200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.98,
|
| 229 |
+
"eval_loss": 0.0954003781080246,
|
| 230 |
+
"eval_runtime": 2.8437,
|
| 231 |
+
"eval_samples_per_second": 351.659,
|
| 232 |
+
"eval_steps_per_second": 43.957,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.1,
|
| 237 |
+
"learning_rate": 0.0002383945239576851,
|
| 238 |
+
"loss": 0.1388,
|
| 239 |
+
"step": 3400
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.1,
|
| 243 |
+
"eval_loss": 0.10116879642009735,
|
| 244 |
+
"eval_runtime": 2.7628,
|
| 245 |
+
"eval_samples_per_second": 361.954,
|
| 246 |
+
"eval_steps_per_second": 45.244,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.23,
|
| 251 |
+
"learning_rate": 0.00023466085874299935,
|
| 252 |
+
"loss": 0.1346,
|
| 253 |
+
"step": 3600
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.23,
|
| 257 |
+
"eval_loss": 0.10693109035491943,
|
| 258 |
+
"eval_runtime": 3.1697,
|
| 259 |
+
"eval_samples_per_second": 315.491,
|
| 260 |
+
"eval_steps_per_second": 39.436,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.35,
|
| 265 |
+
"learning_rate": 0.00023092719352831362,
|
| 266 |
+
"loss": 0.1232,
|
| 267 |
+
"step": 3800
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.35,
|
| 271 |
+
"eval_loss": 0.09901304543018341,
|
| 272 |
+
"eval_runtime": 2.1178,
|
| 273 |
+
"eval_samples_per_second": 472.183,
|
| 274 |
+
"eval_steps_per_second": 59.023,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.47,
|
| 279 |
+
"learning_rate": 0.00022719352831362786,
|
| 280 |
+
"loss": 0.1187,
|
| 281 |
+
"step": 4000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.47,
|
| 285 |
+
"eval_loss": 0.11418598890304565,
|
| 286 |
+
"eval_runtime": 2.1348,
|
| 287 |
+
"eval_samples_per_second": 468.423,
|
| 288 |
+
"eval_steps_per_second": 58.553,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.6,
|
| 293 |
+
"learning_rate": 0.0002234598630989421,
|
| 294 |
+
"loss": 0.1133,
|
| 295 |
+
"step": 4200
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.6,
|
| 299 |
+
"eval_loss": 0.0984039306640625,
|
| 300 |
+
"eval_runtime": 2.1382,
|
| 301 |
+
"eval_samples_per_second": 467.676,
|
| 302 |
+
"eval_steps_per_second": 58.459,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.72,
|
| 307 |
+
"learning_rate": 0.00021972619788425635,
|
| 308 |
+
"loss": 0.1088,
|
| 309 |
+
"step": 4400
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.72,
|
| 313 |
+
"eval_loss": 0.07466612011194229,
|
| 314 |
+
"eval_runtime": 2.8862,
|
| 315 |
+
"eval_samples_per_second": 346.477,
|
| 316 |
+
"eval_steps_per_second": 43.31,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.84,
|
| 321 |
+
"learning_rate": 0.00021599253266957062,
|
| 322 |
+
"loss": 0.1025,
|
| 323 |
+
"step": 4600
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.84,
|
| 327 |
+
"eval_loss": 0.1227998435497284,
|
| 328 |
+
"eval_runtime": 2.8738,
|
| 329 |
+
"eval_samples_per_second": 347.966,
|
| 330 |
+
"eval_steps_per_second": 43.496,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.97,
|
| 335 |
+
"learning_rate": 0.00021225886745488486,
|
| 336 |
+
"loss": 0.0971,
|
| 337 |
+
"step": 4800
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.97,
|
| 341 |
+
"eval_loss": 0.07324225455522537,
|
| 342 |
+
"eval_runtime": 2.2831,
|
| 343 |
+
"eval_samples_per_second": 437.994,
|
| 344 |
+
"eval_steps_per_second": 54.749,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.09,
|
| 349 |
+
"learning_rate": 0.00020852520224019913,
|
| 350 |
+
"loss": 0.0853,
|
| 351 |
+
"step": 5000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.09,
|
| 355 |
+
"eval_loss": 0.07788190990686417,
|
| 356 |
+
"eval_runtime": 2.1358,
|
| 357 |
+
"eval_samples_per_second": 468.199,
|
| 358 |
+
"eval_steps_per_second": 58.525,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.22,
|
| 363 |
+
"learning_rate": 0.00020479153702551337,
|
| 364 |
+
"loss": 0.0865,
|
| 365 |
+
"step": 5200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.22,
|
| 369 |
+
"eval_loss": 0.06575259566307068,
|
| 370 |
+
"eval_runtime": 2.1474,
|
| 371 |
+
"eval_samples_per_second": 465.679,
|
| 372 |
+
"eval_steps_per_second": 58.21,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.34,
|
| 377 |
+
"learning_rate": 0.0002010578718108276,
|
| 378 |
+
"loss": 0.0768,
|
| 379 |
+
"step": 5400
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.34,
|
| 383 |
+
"eval_loss": 0.08183684200048447,
|
| 384 |
+
"eval_runtime": 2.1211,
|
| 385 |
+
"eval_samples_per_second": 471.453,
|
| 386 |
+
"eval_steps_per_second": 58.932,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.46,
|
| 391 |
+
"learning_rate": 0.00019732420659614186,
|
| 392 |
+
"loss": 0.0738,
|
| 393 |
+
"step": 5600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.46,
|
| 397 |
+
"eval_loss": 0.04662672430276871,
|
| 398 |
+
"eval_runtime": 2.7913,
|
| 399 |
+
"eval_samples_per_second": 358.253,
|
| 400 |
+
"eval_steps_per_second": 44.782,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.59,
|
| 405 |
+
"learning_rate": 0.0001935905413814561,
|
| 406 |
+
"loss": 0.0622,
|
| 407 |
+
"step": 5800
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.59,
|
| 411 |
+
"eval_loss": 0.0433196946978569,
|
| 412 |
+
"eval_runtime": 3.1597,
|
| 413 |
+
"eval_samples_per_second": 316.49,
|
| 414 |
+
"eval_steps_per_second": 39.561,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 3.71,
|
| 419 |
+
"learning_rate": 0.00018985687616677037,
|
| 420 |
+
"loss": 0.0671,
|
| 421 |
+
"step": 6000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.71,
|
| 425 |
+
"eval_loss": 0.038382936269044876,
|
| 426 |
+
"eval_runtime": 2.1009,
|
| 427 |
+
"eval_samples_per_second": 475.976,
|
| 428 |
+
"eval_steps_per_second": 59.497,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.83,
|
| 433 |
+
"learning_rate": 0.0001861232109520846,
|
| 434 |
+
"loss": 0.0545,
|
| 435 |
+
"step": 6200
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.83,
|
| 439 |
+
"eval_loss": 0.04082392156124115,
|
| 440 |
+
"eval_runtime": 2.1346,
|
| 441 |
+
"eval_samples_per_second": 468.481,
|
| 442 |
+
"eval_steps_per_second": 58.56,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.96,
|
| 447 |
+
"learning_rate": 0.00018238954573739888,
|
| 448 |
+
"loss": 0.0564,
|
| 449 |
+
"step": 6400
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.96,
|
| 453 |
+
"eval_loss": 0.043197453022003174,
|
| 454 |
+
"eval_runtime": 2.1169,
|
| 455 |
+
"eval_samples_per_second": 472.389,
|
| 456 |
+
"eval_steps_per_second": 59.049,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 4.08,
|
| 461 |
+
"learning_rate": 0.0001786558805227131,
|
| 462 |
+
"loss": 0.0523,
|
| 463 |
+
"step": 6600
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 4.08,
|
| 467 |
+
"eval_loss": 0.03342806547880173,
|
| 468 |
+
"eval_runtime": 2.4926,
|
| 469 |
+
"eval_samples_per_second": 401.182,
|
| 470 |
+
"eval_steps_per_second": 50.148,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.2,
|
| 475 |
+
"learning_rate": 0.00017492221530802736,
|
| 476 |
+
"loss": 0.0456,
|
| 477 |
+
"step": 6800
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.2,
|
| 481 |
+
"eval_loss": 0.02744474820792675,
|
| 482 |
+
"eval_runtime": 3.0,
|
| 483 |
+
"eval_samples_per_second": 333.335,
|
| 484 |
+
"eval_steps_per_second": 41.667,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.33,
|
| 489 |
+
"learning_rate": 0.0001711885500933416,
|
| 490 |
+
"loss": 0.0442,
|
| 491 |
+
"step": 7000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.33,
|
| 495 |
+
"eval_loss": 0.024560416117310524,
|
| 496 |
+
"eval_runtime": 2.6752,
|
| 497 |
+
"eval_samples_per_second": 373.806,
|
| 498 |
+
"eval_steps_per_second": 46.726,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 4.45,
|
| 503 |
+
"learning_rate": 0.00016745488487865588,
|
| 504 |
+
"loss": 0.0383,
|
| 505 |
+
"step": 7200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.45,
|
| 509 |
+
"eval_loss": 0.018605533987283707,
|
| 510 |
+
"eval_runtime": 2.1117,
|
| 511 |
+
"eval_samples_per_second": 473.559,
|
| 512 |
+
"eval_steps_per_second": 59.195,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.58,
|
| 517 |
+
"learning_rate": 0.00016372121966397012,
|
| 518 |
+
"loss": 0.0348,
|
| 519 |
+
"step": 7400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.58,
|
| 523 |
+
"eval_loss": 0.01473915483802557,
|
| 524 |
+
"eval_runtime": 2.1223,
|
| 525 |
+
"eval_samples_per_second": 471.193,
|
| 526 |
+
"eval_steps_per_second": 58.899,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 4.7,
|
| 531 |
+
"learning_rate": 0.0001599875544492844,
|
| 532 |
+
"loss": 0.0299,
|
| 533 |
+
"step": 7600
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.7,
|
| 537 |
+
"eval_loss": 0.025838036090135574,
|
| 538 |
+
"eval_runtime": 2.1138,
|
| 539 |
+
"eval_samples_per_second": 473.088,
|
| 540 |
+
"eval_steps_per_second": 59.136,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 4.82,
|
| 545 |
+
"learning_rate": 0.0001562538892345986,
|
| 546 |
+
"loss": 0.0268,
|
| 547 |
+
"step": 7800
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 4.82,
|
| 551 |
+
"eval_loss": 0.01688736118376255,
|
| 552 |
+
"eval_runtime": 2.1658,
|
| 553 |
+
"eval_samples_per_second": 461.718,
|
| 554 |
+
"eval_steps_per_second": 57.715,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.95,
|
| 559 |
+
"learning_rate": 0.00015252022401991287,
|
| 560 |
+
"loss": 0.0272,
|
| 561 |
+
"step": 8000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.95,
|
| 565 |
+
"eval_loss": 0.020514091476798058,
|
| 566 |
+
"eval_runtime": 2.1415,
|
| 567 |
+
"eval_samples_per_second": 466.966,
|
| 568 |
+
"eval_steps_per_second": 58.371,
|
| 569 |
+
"step": 8000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.07,
|
| 573 |
+
"learning_rate": 0.00014878655880522712,
|
| 574 |
+
"loss": 0.0277,
|
| 575 |
+
"step": 8200
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.07,
|
| 579 |
+
"eval_loss": 0.018993763253092766,
|
| 580 |
+
"eval_runtime": 2.3074,
|
| 581 |
+
"eval_samples_per_second": 433.383,
|
| 582 |
+
"eval_steps_per_second": 54.173,
|
| 583 |
+
"step": 8200
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 5.19,
|
| 587 |
+
"learning_rate": 0.00014505289359054139,
|
| 588 |
+
"loss": 0.0253,
|
| 589 |
+
"step": 8400
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.19,
|
| 593 |
+
"eval_loss": 0.0132982786744833,
|
| 594 |
+
"eval_runtime": 2.7723,
|
| 595 |
+
"eval_samples_per_second": 360.706,
|
| 596 |
+
"eval_steps_per_second": 45.088,
|
| 597 |
+
"step": 8400
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 5.32,
|
| 601 |
+
"learning_rate": 0.00014131922837585563,
|
| 602 |
+
"loss": 0.0208,
|
| 603 |
+
"step": 8600
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.32,
|
| 607 |
+
"eval_loss": 0.011603164486587048,
|
| 608 |
+
"eval_runtime": 2.2147,
|
| 609 |
+
"eval_samples_per_second": 451.518,
|
| 610 |
+
"eval_steps_per_second": 56.44,
|
| 611 |
+
"step": 8600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.44,
|
| 615 |
+
"learning_rate": 0.00013758556316116987,
|
| 616 |
+
"loss": 0.019,
|
| 617 |
+
"step": 8800
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.44,
|
| 621 |
+
"eval_loss": 0.007933158427476883,
|
| 622 |
+
"eval_runtime": 2.565,
|
| 623 |
+
"eval_samples_per_second": 389.858,
|
| 624 |
+
"eval_steps_per_second": 48.732,
|
| 625 |
+
"step": 8800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 5.57,
|
| 629 |
+
"learning_rate": 0.00013385189794648414,
|
| 630 |
+
"loss": 0.0179,
|
| 631 |
+
"step": 9000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 5.57,
|
| 635 |
+
"eval_loss": 0.00808796752244234,
|
| 636 |
+
"eval_runtime": 2.157,
|
| 637 |
+
"eval_samples_per_second": 463.605,
|
| 638 |
+
"eval_steps_per_second": 57.951,
|
| 639 |
+
"step": 9000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.69,
|
| 643 |
+
"learning_rate": 0.00013011823273179835,
|
| 644 |
+
"loss": 0.0136,
|
| 645 |
+
"step": 9200
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.69,
|
| 649 |
+
"eval_loss": 0.02137412503361702,
|
| 650 |
+
"eval_runtime": 2.1642,
|
| 651 |
+
"eval_samples_per_second": 462.06,
|
| 652 |
+
"eval_steps_per_second": 57.758,
|
| 653 |
+
"step": 9200
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 5.81,
|
| 657 |
+
"learning_rate": 0.00012638456751711262,
|
| 658 |
+
"loss": 0.0196,
|
| 659 |
+
"step": 9400
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.81,
|
| 663 |
+
"eval_loss": 0.009271830320358276,
|
| 664 |
+
"eval_runtime": 2.7483,
|
| 665 |
+
"eval_samples_per_second": 363.865,
|
| 666 |
+
"eval_steps_per_second": 45.483,
|
| 667 |
+
"step": 9400
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 5.94,
|
| 671 |
+
"learning_rate": 0.00012265090230242687,
|
| 672 |
+
"loss": 0.015,
|
| 673 |
+
"step": 9600
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 5.94,
|
| 677 |
+
"eval_loss": 0.011388062499463558,
|
| 678 |
+
"eval_runtime": 3.1063,
|
| 679 |
+
"eval_samples_per_second": 321.931,
|
| 680 |
+
"eval_steps_per_second": 40.241,
|
| 681 |
+
"step": 9600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.06,
|
| 685 |
+
"learning_rate": 0.00011891723708774112,
|
| 686 |
+
"loss": 0.0196,
|
| 687 |
+
"step": 9800
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 6.06,
|
| 691 |
+
"eval_loss": 0.009324445389211178,
|
| 692 |
+
"eval_runtime": 2.9695,
|
| 693 |
+
"eval_samples_per_second": 336.759,
|
| 694 |
+
"eval_steps_per_second": 42.095,
|
| 695 |
+
"step": 9800
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 6.18,
|
| 699 |
+
"learning_rate": 0.00011518357187305538,
|
| 700 |
+
"loss": 0.0192,
|
| 701 |
+
"step": 10000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 6.18,
|
| 705 |
+
"eval_loss": 0.008494062349200249,
|
| 706 |
+
"eval_runtime": 2.1785,
|
| 707 |
+
"eval_samples_per_second": 459.035,
|
| 708 |
+
"eval_steps_per_second": 57.379,
|
| 709 |
+
"step": 10000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 6.31,
|
| 713 |
+
"learning_rate": 0.00011144990665836963,
|
| 714 |
+
"loss": 0.0155,
|
| 715 |
+
"step": 10200
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 6.31,
|
| 719 |
+
"eval_loss": 0.005131287965923548,
|
| 720 |
+
"eval_runtime": 2.2151,
|
| 721 |
+
"eval_samples_per_second": 451.441,
|
| 722 |
+
"eval_steps_per_second": 56.43,
|
| 723 |
+
"step": 10200
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 6.43,
|
| 727 |
+
"learning_rate": 0.00010771624144368388,
|
| 728 |
+
"loss": 0.0182,
|
| 729 |
+
"step": 10400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 6.43,
|
| 733 |
+
"eval_loss": 0.01033452432602644,
|
| 734 |
+
"eval_runtime": 2.204,
|
| 735 |
+
"eval_samples_per_second": 453.729,
|
| 736 |
+
"eval_steps_per_second": 56.716,
|
| 737 |
+
"step": 10400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 6.55,
|
| 741 |
+
"learning_rate": 0.00010398257622899813,
|
| 742 |
+
"loss": 0.0149,
|
| 743 |
+
"step": 10600
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 6.55,
|
| 747 |
+
"eval_loss": 0.006081216037273407,
|
| 748 |
+
"eval_runtime": 2.6138,
|
| 749 |
+
"eval_samples_per_second": 382.582,
|
| 750 |
+
"eval_steps_per_second": 47.823,
|
| 751 |
+
"step": 10600
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 6.68,
|
| 755 |
+
"learning_rate": 0.00010024891101431236,
|
| 756 |
+
"loss": 0.0155,
|
| 757 |
+
"step": 10800
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 6.68,
|
| 761 |
+
"eval_loss": 0.008235114626586437,
|
| 762 |
+
"eval_runtime": 2.9799,
|
| 763 |
+
"eval_samples_per_second": 335.587,
|
| 764 |
+
"eval_steps_per_second": 41.948,
|
| 765 |
+
"step": 10800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.8,
|
| 769 |
+
"learning_rate": 9.651524579962662e-05,
|
| 770 |
+
"loss": 0.0125,
|
| 771 |
+
"step": 11000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 6.8,
|
| 775 |
+
"eval_loss": 0.0061024767346680164,
|
| 776 |
+
"eval_runtime": 3.1763,
|
| 777 |
+
"eval_samples_per_second": 314.832,
|
| 778 |
+
"eval_steps_per_second": 39.354,
|
| 779 |
+
"step": 11000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 6.93,
|
| 783 |
+
"learning_rate": 9.278158058494087e-05,
|
| 784 |
+
"loss": 0.0126,
|
| 785 |
+
"step": 11200
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 6.93,
|
| 789 |
+
"eval_loss": 0.0077368393540382385,
|
| 790 |
+
"eval_runtime": 2.1677,
|
| 791 |
+
"eval_samples_per_second": 461.31,
|
| 792 |
+
"eval_steps_per_second": 57.664,
|
| 793 |
+
"step": 11200
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 7.05,
|
| 797 |
+
"learning_rate": 8.904791537025512e-05,
|
| 798 |
+
"loss": 0.016,
|
| 799 |
+
"step": 11400
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 7.05,
|
| 803 |
+
"eval_loss": 0.01462015975266695,
|
| 804 |
+
"eval_runtime": 2.163,
|
| 805 |
+
"eval_samples_per_second": 462.313,
|
| 806 |
+
"eval_steps_per_second": 57.789,
|
| 807 |
+
"step": 11400
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 7.17,
|
| 811 |
+
"learning_rate": 8.531425015556937e-05,
|
| 812 |
+
"loss": 0.0168,
|
| 813 |
+
"step": 11600
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 7.17,
|
| 817 |
+
"eval_loss": 0.013114248402416706,
|
| 818 |
+
"eval_runtime": 2.177,
|
| 819 |
+
"eval_samples_per_second": 459.355,
|
| 820 |
+
"eval_steps_per_second": 57.419,
|
| 821 |
+
"step": 11600
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 7.3,
|
| 825 |
+
"learning_rate": 8.158058494088363e-05,
|
| 826 |
+
"loss": 0.0115,
|
| 827 |
+
"step": 11800
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 7.3,
|
| 831 |
+
"eval_loss": 0.0058467877097427845,
|
| 832 |
+
"eval_runtime": 2.8432,
|
| 833 |
+
"eval_samples_per_second": 351.72,
|
| 834 |
+
"eval_steps_per_second": 43.965,
|
| 835 |
+
"step": 11800
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 7.42,
|
| 839 |
+
"learning_rate": 7.784691972619787e-05,
|
| 840 |
+
"loss": 0.0109,
|
| 841 |
+
"step": 12000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 7.42,
|
| 845 |
+
"eval_loss": 0.007328983396291733,
|
| 846 |
+
"eval_runtime": 2.9781,
|
| 847 |
+
"eval_samples_per_second": 335.785,
|
| 848 |
+
"eval_steps_per_second": 41.973,
|
| 849 |
+
"step": 12000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 7.54,
|
| 853 |
+
"learning_rate": 7.411325451151213e-05,
|
| 854 |
+
"loss": 0.01,
|
| 855 |
+
"step": 12200
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 7.54,
|
| 859 |
+
"eval_loss": 0.00543447770178318,
|
| 860 |
+
"eval_runtime": 2.13,
|
| 861 |
+
"eval_samples_per_second": 469.492,
|
| 862 |
+
"eval_steps_per_second": 58.686,
|
| 863 |
+
"step": 12200
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 7.67,
|
| 867 |
+
"learning_rate": 7.037958929682637e-05,
|
| 868 |
+
"loss": 0.0085,
|
| 869 |
+
"step": 12400
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 7.67,
|
| 873 |
+
"eval_loss": 0.005294375587254763,
|
| 874 |
+
"eval_runtime": 2.1484,
|
| 875 |
+
"eval_samples_per_second": 465.459,
|
| 876 |
+
"eval_steps_per_second": 58.182,
|
| 877 |
+
"step": 12400
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 7.79,
|
| 881 |
+
"learning_rate": 6.664592408214062e-05,
|
| 882 |
+
"loss": 0.0105,
|
| 883 |
+
"step": 12600
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 7.79,
|
| 887 |
+
"eval_loss": 0.0051603252068161964,
|
| 888 |
+
"eval_runtime": 2.1621,
|
| 889 |
+
"eval_samples_per_second": 462.523,
|
| 890 |
+
"eval_steps_per_second": 57.815,
|
| 891 |
+
"step": 12600
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 7.91,
|
| 895 |
+
"learning_rate": 6.291225886745488e-05,
|
| 896 |
+
"loss": 0.01,
|
| 897 |
+
"step": 12800
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 7.91,
|
| 901 |
+
"eval_loss": 0.005722519941627979,
|
| 902 |
+
"eval_runtime": 2.7684,
|
| 903 |
+
"eval_samples_per_second": 361.216,
|
| 904 |
+
"eval_steps_per_second": 45.152,
|
| 905 |
+
"step": 12800
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 8.04,
|
| 909 |
+
"learning_rate": 5.917859365276913e-05,
|
| 910 |
+
"loss": 0.0071,
|
| 911 |
+
"step": 13000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 8.04,
|
| 915 |
+
"eval_loss": 0.004564732778817415,
|
| 916 |
+
"eval_runtime": 2.7551,
|
| 917 |
+
"eval_samples_per_second": 362.961,
|
| 918 |
+
"eval_steps_per_second": 45.37,
|
| 919 |
+
"step": 13000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 8.16,
|
| 923 |
+
"learning_rate": 5.5444928438083385e-05,
|
| 924 |
+
"loss": 0.0065,
|
| 925 |
+
"step": 13200
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 8.16,
|
| 929 |
+
"eval_loss": 0.004461783915758133,
|
| 930 |
+
"eval_runtime": 3.1705,
|
| 931 |
+
"eval_samples_per_second": 315.412,
|
| 932 |
+
"eval_steps_per_second": 39.426,
|
| 933 |
+
"step": 13200
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 8.29,
|
| 937 |
+
"learning_rate": 5.171126322339763e-05,
|
| 938 |
+
"loss": 0.0075,
|
| 939 |
+
"step": 13400
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 8.29,
|
| 943 |
+
"eval_loss": 0.004132562782615423,
|
| 944 |
+
"eval_runtime": 3.5027,
|
| 945 |
+
"eval_samples_per_second": 285.498,
|
| 946 |
+
"eval_steps_per_second": 35.687,
|
| 947 |
+
"step": 13400
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 8.41,
|
| 951 |
+
"learning_rate": 4.797759800871188e-05,
|
| 952 |
+
"loss": 0.0072,
|
| 953 |
+
"step": 13600
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 8.41,
|
| 957 |
+
"eval_loss": 0.004298557061702013,
|
| 958 |
+
"eval_runtime": 2.1516,
|
| 959 |
+
"eval_samples_per_second": 464.775,
|
| 960 |
+
"eval_steps_per_second": 58.097,
|
| 961 |
+
"step": 13600
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 8.53,
|
| 965 |
+
"learning_rate": 4.424393279402613e-05,
|
| 966 |
+
"loss": 0.0077,
|
| 967 |
+
"step": 13800
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 8.53,
|
| 971 |
+
"eval_loss": 0.005747557617723942,
|
| 972 |
+
"eval_runtime": 2.1174,
|
| 973 |
+
"eval_samples_per_second": 472.272,
|
| 974 |
+
"eval_steps_per_second": 59.034,
|
| 975 |
+
"step": 13800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 8.66,
|
| 979 |
+
"learning_rate": 4.051026757934038e-05,
|
| 980 |
+
"loss": 0.009,
|
| 981 |
+
"step": 14000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 8.66,
|
| 985 |
+
"eval_loss": 0.005076244939118624,
|
| 986 |
+
"eval_runtime": 2.1715,
|
| 987 |
+
"eval_samples_per_second": 460.514,
|
| 988 |
+
"eval_steps_per_second": 57.564,
|
| 989 |
+
"step": 14000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 8.78,
|
| 993 |
+
"learning_rate": 3.677660236465463e-05,
|
| 994 |
+
"loss": 0.0066,
|
| 995 |
+
"step": 14200
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 8.78,
|
| 999 |
+
"eval_loss": 0.004328867886215448,
|
| 1000 |
+
"eval_runtime": 2.1457,
|
| 1001 |
+
"eval_samples_per_second": 466.038,
|
| 1002 |
+
"eval_steps_per_second": 58.255,
|
| 1003 |
+
"step": 14200
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 8.9,
|
| 1007 |
+
"learning_rate": 3.304293714996888e-05,
|
| 1008 |
+
"loss": 0.0065,
|
| 1009 |
+
"step": 14400
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 8.9,
|
| 1013 |
+
"eval_loss": 0.004579309374094009,
|
| 1014 |
+
"eval_runtime": 2.5023,
|
| 1015 |
+
"eval_samples_per_second": 399.626,
|
| 1016 |
+
"eval_steps_per_second": 49.953,
|
| 1017 |
+
"step": 14400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 9.03,
|
| 1021 |
+
"learning_rate": 2.9309271935283136e-05,
|
| 1022 |
+
"loss": 0.0047,
|
| 1023 |
+
"step": 14600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 9.03,
|
| 1027 |
+
"eval_loss": 0.00406376738101244,
|
| 1028 |
+
"eval_runtime": 3.0193,
|
| 1029 |
+
"eval_samples_per_second": 331.204,
|
| 1030 |
+
"eval_steps_per_second": 41.401,
|
| 1031 |
+
"step": 14600
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 9.15,
|
| 1035 |
+
"learning_rate": 2.5575606720597382e-05,
|
| 1036 |
+
"loss": 0.0049,
|
| 1037 |
+
"step": 14800
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 9.15,
|
| 1041 |
+
"eval_loss": 0.0037133253645151854,
|
| 1042 |
+
"eval_runtime": 2.5419,
|
| 1043 |
+
"eval_samples_per_second": 393.406,
|
| 1044 |
+
"eval_steps_per_second": 49.176,
|
| 1045 |
+
"step": 14800
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 9.28,
|
| 1049 |
+
"learning_rate": 2.1841941505911635e-05,
|
| 1050 |
+
"loss": 0.0048,
|
| 1051 |
+
"step": 15000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 9.28,
|
| 1055 |
+
"eval_loss": 0.0035180081613361835,
|
| 1056 |
+
"eval_runtime": 2.1535,
|
| 1057 |
+
"eval_samples_per_second": 464.362,
|
| 1058 |
+
"eval_steps_per_second": 58.045,
|
| 1059 |
+
"step": 15000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 9.4,
|
| 1063 |
+
"learning_rate": 1.8108276291225884e-05,
|
| 1064 |
+
"loss": 0.0045,
|
| 1065 |
+
"step": 15200
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 9.4,
|
| 1069 |
+
"eval_loss": 0.0041992985643446445,
|
| 1070 |
+
"eval_runtime": 2.1652,
|
| 1071 |
+
"eval_samples_per_second": 461.858,
|
| 1072 |
+
"eval_steps_per_second": 57.732,
|
| 1073 |
+
"step": 15200
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 9.52,
|
| 1077 |
+
"learning_rate": 1.4374611076540135e-05,
|
| 1078 |
+
"loss": 0.0041,
|
| 1079 |
+
"step": 15400
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 9.52,
|
| 1083 |
+
"eval_loss": 0.003915323410183191,
|
| 1084 |
+
"eval_runtime": 2.7057,
|
| 1085 |
+
"eval_samples_per_second": 369.59,
|
| 1086 |
+
"eval_steps_per_second": 46.199,
|
| 1087 |
+
"step": 15400
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 9.65,
|
| 1091 |
+
"learning_rate": 1.0640945861854385e-05,
|
| 1092 |
+
"loss": 0.0042,
|
| 1093 |
+
"step": 15600
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 9.65,
|
| 1097 |
+
"eval_loss": 0.0032798268366605043,
|
| 1098 |
+
"eval_runtime": 3.0263,
|
| 1099 |
+
"eval_samples_per_second": 330.438,
|
| 1100 |
+
"eval_steps_per_second": 41.305,
|
| 1101 |
+
"step": 15600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 9.77,
|
| 1105 |
+
"learning_rate": 6.907280647168636e-06,
|
| 1106 |
+
"loss": 0.0041,
|
| 1107 |
+
"step": 15800
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 9.77,
|
| 1111 |
+
"eval_loss": 0.003197046695277095,
|
| 1112 |
+
"eval_runtime": 2.2279,
|
| 1113 |
+
"eval_samples_per_second": 448.855,
|
| 1114 |
+
"eval_steps_per_second": 56.107,
|
| 1115 |
+
"step": 15800
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 9.89,
|
| 1119 |
+
"learning_rate": 3.173615432482887e-06,
|
| 1120 |
+
"loss": 0.0039,
|
| 1121 |
+
"step": 16000
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 9.89,
|
| 1125 |
+
"eval_loss": 0.003054018598049879,
|
| 1126 |
+
"eval_runtime": 2.2116,
|
| 1127 |
+
"eval_samples_per_second": 452.155,
|
| 1128 |
+
"eval_steps_per_second": 56.519,
|
| 1129 |
+
"step": 16000
|
| 1130 |
+
}
|
| 1131 |
+
],
|
| 1132 |
+
"logging_steps": 200,
|
| 1133 |
+
"max_steps": 16170,
|
| 1134 |
+
"num_train_epochs": 10,
|
| 1135 |
+
"save_steps": 200,
|
| 1136 |
+
"total_flos": 6146864391499776.0,
|
| 1137 |
+
"trial_name": null,
|
| 1138 |
+
"trial_params": null
|
| 1139 |
+
}
|
checkpoint-16000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:151f7c03b13beb37d6cb3eb5afcbb06b6c8d33160a6f55a4964868b2d7d024bb
|
| 3 |
+
size 4600
|