Upload folder using huggingface_hub
Browse files- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +37 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +733 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-50/README.md +202 -0
- checkpoint-50/adapter_config.json +37 -0
- checkpoint-50/adapter_model.safetensors +3 -0
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/trainer_state.json +383 -0
- checkpoint-50/training_args.bin +3 -0
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: rinna/llama-3-youko-8b
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"embed_tokens",
|
| 19 |
+
"lm_head"
|
| 20 |
+
],
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 128,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": "unsloth",
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
+
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": true
|
| 37 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92d0d05e06bc25d8773d0aa7bbc424759b00d64f07846de5f4ee86d30789bb2b
|
| 3 |
+
size 11849545016
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1de29957f8d3d72eed4eb3644acf58321a0f5415f54ccf366858e348d55d880c
|
| 3 |
+
size 2778493596
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af34d41a387513fe16d2f526704002f5f5013be898bf20077d67118a76362740
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da542b8958b1a0b8a043729d035cfc7e974b103881eaa9132c25d65d52bd503
|
| 3 |
+
size 1064
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.20128824476650564,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.002012882447665056,
|
| 13 |
+
"grad_norm": 22.921390533447266,
|
| 14 |
+
"learning_rate": 6.5e-06,
|
| 15 |
+
"loss": 1.3427,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004025764895330112,
|
| 20 |
+
"grad_norm": 14.772722244262695,
|
| 21 |
+
"learning_rate": 1.3e-05,
|
| 22 |
+
"loss": 1.3647,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.006038647342995169,
|
| 27 |
+
"grad_norm": 11.458742141723633,
|
| 28 |
+
"learning_rate": 1.9499999999999996e-05,
|
| 29 |
+
"loss": 1.2841,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008051529790660225,
|
| 34 |
+
"grad_norm": 4.747677326202393,
|
| 35 |
+
"learning_rate": 2.6e-05,
|
| 36 |
+
"loss": 1.1644,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.010064412238325281,
|
| 41 |
+
"grad_norm": 3.687121629714966,
|
| 42 |
+
"learning_rate": 3.25e-05,
|
| 43 |
+
"loss": 1.1084,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.012077294685990338,
|
| 48 |
+
"grad_norm": 3.178232431411743,
|
| 49 |
+
"learning_rate": 3.899999999999999e-05,
|
| 50 |
+
"loss": 1.0753,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.014090177133655395,
|
| 55 |
+
"grad_norm": 2.476033926010132,
|
| 56 |
+
"learning_rate": 4.5499999999999995e-05,
|
| 57 |
+
"loss": 1.075,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.01610305958132045,
|
| 62 |
+
"grad_norm": 1.9162139892578125,
|
| 63 |
+
"learning_rate": 5.2e-05,
|
| 64 |
+
"loss": 1.0195,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.018115942028985508,
|
| 69 |
+
"grad_norm": 1.797377109527588,
|
| 70 |
+
"learning_rate": 5.85e-05,
|
| 71 |
+
"loss": 0.9884,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.020128824476650563,
|
| 76 |
+
"grad_norm": 1.816100835800171,
|
| 77 |
+
"learning_rate": 6.5e-05,
|
| 78 |
+
"loss": 0.9945,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02214170692431562,
|
| 83 |
+
"grad_norm": 1.843664526939392,
|
| 84 |
+
"learning_rate": 6.499932098548219e-05,
|
| 85 |
+
"loss": 0.8802,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.024154589371980676,
|
| 90 |
+
"grad_norm": 1.7202250957489014,
|
| 91 |
+
"learning_rate": 6.49972839703017e-05,
|
| 92 |
+
"loss": 0.9833,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.026167471819645734,
|
| 97 |
+
"grad_norm": 1.4981484413146973,
|
| 98 |
+
"learning_rate": 6.499388903957628e-05,
|
| 99 |
+
"loss": 0.9481,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.02818035426731079,
|
| 104 |
+
"grad_norm": 1.4716213941574097,
|
| 105 |
+
"learning_rate": 6.498913633516483e-05,
|
| 106 |
+
"loss": 0.8809,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.030193236714975844,
|
| 111 |
+
"grad_norm": 1.3817026615142822,
|
| 112 |
+
"learning_rate": 6.498302605566152e-05,
|
| 113 |
+
"loss": 0.9264,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0322061191626409,
|
| 118 |
+
"grad_norm": 1.509097695350647,
|
| 119 |
+
"learning_rate": 6.497555845638748e-05,
|
| 120 |
+
"loss": 0.8829,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03421900161030596,
|
| 125 |
+
"grad_norm": 1.5498337745666504,
|
| 126 |
+
"learning_rate": 6.496673384938014e-05,
|
| 127 |
+
"loss": 0.9227,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.036231884057971016,
|
| 132 |
+
"grad_norm": 1.527828574180603,
|
| 133 |
+
"learning_rate": 6.49565526033802e-05,
|
| 134 |
+
"loss": 0.9488,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.038244766505636074,
|
| 139 |
+
"grad_norm": 1.4578592777252197,
|
| 140 |
+
"learning_rate": 6.494501514381621e-05,
|
| 141 |
+
"loss": 0.8845,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.040257648953301126,
|
| 146 |
+
"grad_norm": 1.4198046922683716,
|
| 147 |
+
"learning_rate": 6.493212195278678e-05,
|
| 148 |
+
"loss": 0.8809,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.042270531400966184,
|
| 153 |
+
"grad_norm": 1.4455400705337524,
|
| 154 |
+
"learning_rate": 6.491787356904047e-05,
|
| 155 |
+
"loss": 0.8686,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04428341384863124,
|
| 160 |
+
"grad_norm": 1.5711616277694702,
|
| 161 |
+
"learning_rate": 6.490227058795323e-05,
|
| 162 |
+
"loss": 0.96,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.046296296296296294,
|
| 167 |
+
"grad_norm": 1.4603729248046875,
|
| 168 |
+
"learning_rate": 6.488531366150359e-05,
|
| 169 |
+
"loss": 0.9026,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04830917874396135,
|
| 174 |
+
"grad_norm": 1.4184608459472656,
|
| 175 |
+
"learning_rate": 6.48670034982453e-05,
|
| 176 |
+
"loss": 0.9426,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05032206119162641,
|
| 181 |
+
"grad_norm": 1.4080291986465454,
|
| 182 |
+
"learning_rate": 6.484734086327788e-05,
|
| 183 |
+
"loss": 0.8857,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.05233494363929147,
|
| 188 |
+
"grad_norm": 1.4739091396331787,
|
| 189 |
+
"learning_rate": 6.482632657821454e-05,
|
| 190 |
+
"loss": 0.8897,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.05434782608695652,
|
| 195 |
+
"grad_norm": 1.320746898651123,
|
| 196 |
+
"learning_rate": 6.480396152114787e-05,
|
| 197 |
+
"loss": 0.8512,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.05636070853462158,
|
| 202 |
+
"grad_norm": 1.4142905473709106,
|
| 203 |
+
"learning_rate": 6.478024662661315e-05,
|
| 204 |
+
"loss": 0.9459,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.05837359098228664,
|
| 209 |
+
"grad_norm": 1.3830432891845703,
|
| 210 |
+
"learning_rate": 6.47551828855493e-05,
|
| 211 |
+
"loss": 0.8605,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06038647342995169,
|
| 216 |
+
"grad_norm": 1.3653528690338135,
|
| 217 |
+
"learning_rate": 6.472877134525753e-05,
|
| 218 |
+
"loss": 0.8446,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06239935587761675,
|
| 223 |
+
"grad_norm": 1.3041807413101196,
|
| 224 |
+
"learning_rate": 6.470101310935746e-05,
|
| 225 |
+
"loss": 0.8407,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.0644122383252818,
|
| 230 |
+
"grad_norm": 1.3803820610046387,
|
| 231 |
+
"learning_rate": 6.467190933774112e-05,
|
| 232 |
+
"loss": 0.8505,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06642512077294686,
|
| 237 |
+
"grad_norm": 1.3407087326049805,
|
| 238 |
+
"learning_rate": 6.464146124652441e-05,
|
| 239 |
+
"loss": 0.794,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06843800322061191,
|
| 244 |
+
"grad_norm": 1.4283268451690674,
|
| 245 |
+
"learning_rate": 6.460967010799629e-05,
|
| 246 |
+
"loss": 0.9139,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07045088566827697,
|
| 251 |
+
"grad_norm": 1.3512784242630005,
|
| 252 |
+
"learning_rate": 6.457653725056568e-05,
|
| 253 |
+
"loss": 0.807,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.07246376811594203,
|
| 258 |
+
"grad_norm": 1.3088512420654297,
|
| 259 |
+
"learning_rate": 6.454206405870587e-05,
|
| 260 |
+
"loss": 0.8968,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07447665056360708,
|
| 265 |
+
"grad_norm": 1.2908034324645996,
|
| 266 |
+
"learning_rate": 6.450625197289675e-05,
|
| 267 |
+
"loss": 0.8447,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.07648953301127215,
|
| 272 |
+
"grad_norm": 1.3444992303848267,
|
| 273 |
+
"learning_rate": 6.446910248956453e-05,
|
| 274 |
+
"loss": 0.8891,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.0785024154589372,
|
| 279 |
+
"grad_norm": 1.2567275762557983,
|
| 280 |
+
"learning_rate": 6.443061716101926e-05,
|
| 281 |
+
"loss": 0.8134,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.08051529790660225,
|
| 286 |
+
"grad_norm": 1.3401930332183838,
|
| 287 |
+
"learning_rate": 6.439079759539e-05,
|
| 288 |
+
"loss": 0.8751,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08252818035426732,
|
| 293 |
+
"grad_norm": 1.3348793983459473,
|
| 294 |
+
"learning_rate": 6.434964545655754e-05,
|
| 295 |
+
"loss": 0.7942,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.08454106280193237,
|
| 300 |
+
"grad_norm": 1.311357021331787,
|
| 301 |
+
"learning_rate": 6.430716246408493e-05,
|
| 302 |
+
"loss": 0.8461,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08655394524959742,
|
| 307 |
+
"grad_norm": 1.3319345712661743,
|
| 308 |
+
"learning_rate": 6.426335039314566e-05,
|
| 309 |
+
"loss": 0.8821,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.08856682769726248,
|
| 314 |
+
"grad_norm": 1.304795742034912,
|
| 315 |
+
"learning_rate": 6.421821107444936e-05,
|
| 316 |
+
"loss": 0.8655,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.09057971014492754,
|
| 321 |
+
"grad_norm": 1.422869086265564,
|
| 322 |
+
"learning_rate": 6.417174639416547e-05,
|
| 323 |
+
"loss": 0.9261,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09259259259259259,
|
| 328 |
+
"grad_norm": 1.2931973934173584,
|
| 329 |
+
"learning_rate": 6.412395829384427e-05,
|
| 330 |
+
"loss": 0.8157,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09460547504025765,
|
| 335 |
+
"grad_norm": 1.2984646558761597,
|
| 336 |
+
"learning_rate": 6.407484877033586e-05,
|
| 337 |
+
"loss": 0.7919,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.0966183574879227,
|
| 342 |
+
"grad_norm": 1.2596486806869507,
|
| 343 |
+
"learning_rate": 6.402441987570665e-05,
|
| 344 |
+
"loss": 0.7682,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09863123993558776,
|
| 349 |
+
"grad_norm": 1.3544796705245972,
|
| 350 |
+
"learning_rate": 6.397267371715368e-05,
|
| 351 |
+
"loss": 0.9084,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.10064412238325282,
|
| 356 |
+
"grad_norm": 1.2623202800750732,
|
| 357 |
+
"learning_rate": 6.391961245691652e-05,
|
| 358 |
+
"loss": 0.8482,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.10265700483091787,
|
| 363 |
+
"grad_norm": 1.320026159286499,
|
| 364 |
+
"learning_rate": 6.386523831218689e-05,
|
| 365 |
+
"loss": 0.8436,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.10466988727858294,
|
| 370 |
+
"grad_norm": 1.4064967632293701,
|
| 371 |
+
"learning_rate": 6.38095535550161e-05,
|
| 372 |
+
"loss": 0.8962,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.10668276972624799,
|
| 377 |
+
"grad_norm": 1.3178116083145142,
|
| 378 |
+
"learning_rate": 6.375256051222009e-05,
|
| 379 |
+
"loss": 0.8064,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.10869565217391304,
|
| 384 |
+
"grad_norm": 1.2729371786117554,
|
| 385 |
+
"learning_rate": 6.369426156528213e-05,
|
| 386 |
+
"loss": 0.8338,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1107085346215781,
|
| 391 |
+
"grad_norm": 1.2167425155639648,
|
| 392 |
+
"learning_rate": 6.363465915025339e-05,
|
| 393 |
+
"loss": 0.8078,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.11272141706924316,
|
| 398 |
+
"grad_norm": 1.3006845712661743,
|
| 399 |
+
"learning_rate": 6.357375575765108e-05,
|
| 400 |
+
"loss": 0.8462,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.11473429951690821,
|
| 405 |
+
"grad_norm": 1.245822787284851,
|
| 406 |
+
"learning_rate": 6.351155393235449e-05,
|
| 407 |
+
"loss": 0.8394,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.11674718196457327,
|
| 412 |
+
"grad_norm": 1.2608625888824463,
|
| 413 |
+
"learning_rate": 6.34480562734985e-05,
|
| 414 |
+
"loss": 0.8606,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.11876006441223833,
|
| 419 |
+
"grad_norm": 1.2614774703979492,
|
| 420 |
+
"learning_rate": 6.33832654343651e-05,
|
| 421 |
+
"loss": 0.7633,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.12077294685990338,
|
| 426 |
+
"grad_norm": 1.3382893800735474,
|
| 427 |
+
"learning_rate": 6.331718412227247e-05,
|
| 428 |
+
"loss": 0.8514,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.12278582930756844,
|
| 433 |
+
"grad_norm": 1.2239303588867188,
|
| 434 |
+
"learning_rate": 6.324981509846189e-05,
|
| 435 |
+
"loss": 0.8319,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1247987117552335,
|
| 440 |
+
"grad_norm": 1.3828685283660889,
|
| 441 |
+
"learning_rate": 6.318116117798225e-05,
|
| 442 |
+
"loss": 0.8683,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.12681159420289856,
|
| 447 |
+
"grad_norm": 1.304027795791626,
|
| 448 |
+
"learning_rate": 6.311122522957255e-05,
|
| 449 |
+
"loss": 0.887,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1288244766505636,
|
| 454 |
+
"grad_norm": 1.3097902536392212,
|
| 455 |
+
"learning_rate": 6.304001017554202e-05,
|
| 456 |
+
"loss": 0.8636,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.13083735909822866,
|
| 461 |
+
"grad_norm": 1.281269907951355,
|
| 462 |
+
"learning_rate": 6.296751899164788e-05,
|
| 463 |
+
"loss": 0.7537,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.13285024154589373,
|
| 468 |
+
"grad_norm": 1.2349010705947876,
|
| 469 |
+
"learning_rate": 6.289375470697116e-05,
|
| 470 |
+
"loss": 0.8451,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13486312399355876,
|
| 475 |
+
"grad_norm": 1.2939257621765137,
|
| 476 |
+
"learning_rate": 6.281872040379001e-05,
|
| 477 |
+
"loss": 0.8249,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.13687600644122383,
|
| 482 |
+
"grad_norm": 1.308341145515442,
|
| 483 |
+
"learning_rate": 6.274241921745097e-05,
|
| 484 |
+
"loss": 0.8764,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.1388888888888889,
|
| 489 |
+
"grad_norm": 1.311805009841919,
|
| 490 |
+
"learning_rate": 6.266485433623794e-05,
|
| 491 |
+
"loss": 0.8308,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.14090177133655393,
|
| 496 |
+
"grad_norm": 1.6127303838729858,
|
| 497 |
+
"learning_rate": 6.258602900123894e-05,
|
| 498 |
+
"loss": 0.8069,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.142914653784219,
|
| 503 |
+
"grad_norm": 1.292090654373169,
|
| 504 |
+
"learning_rate": 6.250594650621067e-05,
|
| 505 |
+
"loss": 0.8174,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.14492753623188406,
|
| 510 |
+
"grad_norm": 1.256778359413147,
|
| 511 |
+
"learning_rate": 6.2424610197441e-05,
|
| 512 |
+
"loss": 0.7956,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1469404186795491,
|
| 517 |
+
"grad_norm": 1.2579149007797241,
|
| 518 |
+
"learning_rate": 6.23420234736089e-05,
|
| 519 |
+
"loss": 0.8267,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.14895330112721417,
|
| 524 |
+
"grad_norm": 1.3226171731948853,
|
| 525 |
+
"learning_rate": 6.225818978564269e-05,
|
| 526 |
+
"loss": 0.9322,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.15096618357487923,
|
| 531 |
+
"grad_norm": 1.1891167163848877,
|
| 532 |
+
"learning_rate": 6.217311263657565e-05,
|
| 533 |
+
"loss": 0.7886,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.1529790660225443,
|
| 538 |
+
"grad_norm": 1.2481876611709595,
|
| 539 |
+
"learning_rate": 6.208679558139977e-05,
|
| 540 |
+
"loss": 0.7832,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.15499194847020933,
|
| 545 |
+
"grad_norm": 1.2592449188232422,
|
| 546 |
+
"learning_rate": 6.199924222691707e-05,
|
| 547 |
+
"loss": 0.8061,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.1570048309178744,
|
| 552 |
+
"grad_norm": 1.250359058380127,
|
| 553 |
+
"learning_rate": 6.191045623158907e-05,
|
| 554 |
+
"loss": 0.7942,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.15901771336553946,
|
| 559 |
+
"grad_norm": 1.2406524419784546,
|
| 560 |
+
"learning_rate": 6.182044130538373e-05,
|
| 561 |
+
"loss": 0.7766,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.1610305958132045,
|
| 566 |
+
"grad_norm": 1.2620049715042114,
|
| 567 |
+
"learning_rate": 6.172920120962052e-05,
|
| 568 |
+
"loss": 0.8445,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.16304347826086957,
|
| 573 |
+
"grad_norm": 1.2618622779846191,
|
| 574 |
+
"learning_rate": 6.16367397568133e-05,
|
| 575 |
+
"loss": 0.812,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.16505636070853463,
|
| 580 |
+
"grad_norm": 1.2560168504714966,
|
| 581 |
+
"learning_rate": 6.15430608105109e-05,
|
| 582 |
+
"loss": 0.8331,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.16706924315619967,
|
| 587 |
+
"grad_norm": 1.2386751174926758,
|
| 588 |
+
"learning_rate": 6.144816828513576e-05,
|
| 589 |
+
"loss": 0.7318,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.16908212560386474,
|
| 594 |
+
"grad_norm": 1.3558485507965088,
|
| 595 |
+
"learning_rate": 6.135206614582031e-05,
|
| 596 |
+
"loss": 0.8476,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.1710950080515298,
|
| 601 |
+
"grad_norm": 1.2461968660354614,
|
| 602 |
+
"learning_rate": 6.125475840824137e-05,
|
| 603 |
+
"loss": 0.8012,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.17310789049919484,
|
| 608 |
+
"grad_norm": 1.2398920059204102,
|
| 609 |
+
"learning_rate": 6.115624913845225e-05,
|
| 610 |
+
"loss": 0.8033,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.1751207729468599,
|
| 615 |
+
"grad_norm": 1.3263791799545288,
|
| 616 |
+
"learning_rate": 6.105654245271292e-05,
|
| 617 |
+
"loss": 0.8511,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.17713365539452497,
|
| 622 |
+
"grad_norm": 1.2072999477386475,
|
| 623 |
+
"learning_rate": 6.095564251731795e-05,
|
| 624 |
+
"loss": 0.7478,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.17914653784219,
|
| 629 |
+
"grad_norm": 1.287801742553711,
|
| 630 |
+
"learning_rate": 6.085355354842249e-05,
|
| 631 |
+
"loss": 0.8152,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.18115942028985507,
|
| 636 |
+
"grad_norm": 1.2826151847839355,
|
| 637 |
+
"learning_rate": 6.0750279811866046e-05,
|
| 638 |
+
"loss": 0.7918,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.18317230273752014,
|
| 643 |
+
"grad_norm": 1.276780605316162,
|
| 644 |
+
"learning_rate": 6.0645825622994254e-05,
|
| 645 |
+
"loss": 0.8774,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.18518518518518517,
|
| 650 |
+
"grad_norm": 1.2205020189285278,
|
| 651 |
+
"learning_rate": 6.0540195346478515e-05,
|
| 652 |
+
"loss": 0.8398,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.18719806763285024,
|
| 657 |
+
"grad_norm": 1.2247477769851685,
|
| 658 |
+
"learning_rate": 6.043339339613371e-05,
|
| 659 |
+
"loss": 0.8322,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.1892109500805153,
|
| 664 |
+
"grad_norm": 1.3282443284988403,
|
| 665 |
+
"learning_rate": 6.0325424234733656e-05,
|
| 666 |
+
"loss": 0.8003,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.19122383252818034,
|
| 671 |
+
"grad_norm": 1.3472024202346802,
|
| 672 |
+
"learning_rate": 6.0216292373824696e-05,
|
| 673 |
+
"loss": 0.8305,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.1932367149758454,
|
| 678 |
+
"grad_norm": 1.2812607288360596,
|
| 679 |
+
"learning_rate": 6.010600237353716e-05,
|
| 680 |
+
"loss": 0.7657,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.19524959742351047,
|
| 685 |
+
"grad_norm": 1.2958053350448608,
|
| 686 |
+
"learning_rate": 5.999455884239483e-05,
|
| 687 |
+
"loss": 0.869,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.1972624798711755,
|
| 692 |
+
"grad_norm": 1.2021034955978394,
|
| 693 |
+
"learning_rate": 5.988196643712235e-05,
|
| 694 |
+
"loss": 0.7798,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.19927536231884058,
|
| 699 |
+
"grad_norm": 1.2430065870285034,
|
| 700 |
+
"learning_rate": 5.976822986245067e-05,
|
| 701 |
+
"loss": 0.7496,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.20128824476650564,
|
| 706 |
+
"grad_norm": 1.2749730348587036,
|
| 707 |
+
"learning_rate": 5.9653353870920434e-05,
|
| 708 |
+
"loss": 0.831,
|
| 709 |
+
"step": 100
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 1,
|
| 713 |
+
"max_steps": 496,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 1,
|
| 716 |
+
"save_steps": 50,
|
| 717 |
+
"stateful_callbacks": {
|
| 718 |
+
"TrainerControl": {
|
| 719 |
+
"args": {
|
| 720 |
+
"should_epoch_stop": false,
|
| 721 |
+
"should_evaluate": false,
|
| 722 |
+
"should_log": false,
|
| 723 |
+
"should_save": true,
|
| 724 |
+
"should_training_stop": false
|
| 725 |
+
},
|
| 726 |
+
"attributes": {}
|
| 727 |
+
}
|
| 728 |
+
},
|
| 729 |
+
"total_flos": 1.189794361882706e+17,
|
| 730 |
+
"train_batch_size": 6,
|
| 731 |
+
"trial_name": null,
|
| 732 |
+
"trial_params": null
|
| 733 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d099daa3926570d9e2501eaac78896812191b5c803506c6b4dc9b531482a17b
|
| 3 |
+
size 5112
|
checkpoint-50/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: rinna/llama-3-youko-8b
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-50/adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "rinna/llama-3-youko-8b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"embed_tokens",
|
| 19 |
+
"lm_head"
|
| 20 |
+
],
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 128,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": "unsloth",
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
+
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": true
|
| 37 |
+
}
|
checkpoint-50/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60cdf01103d0d16c917672595466985b1595d46a048d7285282fc6db18f7a654
|
| 3 |
+
size 11849545016
|
checkpoint-50/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ac1126e459c9c1a3155ebf3054c1cff1aa2f0f61312b9fa19080cfec65d7a13
|
| 3 |
+
size 2778493596
|
checkpoint-50/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af34d41a387513fe16d2f526704002f5f5013be898bf20077d67118a76362740
|
| 3 |
+
size 14244
|
checkpoint-50/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68a604eccd63938d2fa022c2aa991d7744dde2c7bb6dc324fa4f0fac6a7be08e
|
| 3 |
+
size 1064
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.10064412238325282,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.002012882447665056,
|
| 13 |
+
"grad_norm": 22.921390533447266,
|
| 14 |
+
"learning_rate": 6.5e-06,
|
| 15 |
+
"loss": 1.3427,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004025764895330112,
|
| 20 |
+
"grad_norm": 14.772722244262695,
|
| 21 |
+
"learning_rate": 1.3e-05,
|
| 22 |
+
"loss": 1.3647,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.006038647342995169,
|
| 27 |
+
"grad_norm": 11.458742141723633,
|
| 28 |
+
"learning_rate": 1.9499999999999996e-05,
|
| 29 |
+
"loss": 1.2841,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008051529790660225,
|
| 34 |
+
"grad_norm": 4.747677326202393,
|
| 35 |
+
"learning_rate": 2.6e-05,
|
| 36 |
+
"loss": 1.1644,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.010064412238325281,
|
| 41 |
+
"grad_norm": 3.687121629714966,
|
| 42 |
+
"learning_rate": 3.25e-05,
|
| 43 |
+
"loss": 1.1084,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.012077294685990338,
|
| 48 |
+
"grad_norm": 3.178232431411743,
|
| 49 |
+
"learning_rate": 3.899999999999999e-05,
|
| 50 |
+
"loss": 1.0753,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.014090177133655395,
|
| 55 |
+
"grad_norm": 2.476033926010132,
|
| 56 |
+
"learning_rate": 4.5499999999999995e-05,
|
| 57 |
+
"loss": 1.075,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.01610305958132045,
|
| 62 |
+
"grad_norm": 1.9162139892578125,
|
| 63 |
+
"learning_rate": 5.2e-05,
|
| 64 |
+
"loss": 1.0195,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.018115942028985508,
|
| 69 |
+
"grad_norm": 1.797377109527588,
|
| 70 |
+
"learning_rate": 5.85e-05,
|
| 71 |
+
"loss": 0.9884,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.020128824476650563,
|
| 76 |
+
"grad_norm": 1.816100835800171,
|
| 77 |
+
"learning_rate": 6.5e-05,
|
| 78 |
+
"loss": 0.9945,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02214170692431562,
|
| 83 |
+
"grad_norm": 1.843664526939392,
|
| 84 |
+
"learning_rate": 6.499932098548219e-05,
|
| 85 |
+
"loss": 0.8802,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.024154589371980676,
|
| 90 |
+
"grad_norm": 1.7202250957489014,
|
| 91 |
+
"learning_rate": 6.49972839703017e-05,
|
| 92 |
+
"loss": 0.9833,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.026167471819645734,
|
| 97 |
+
"grad_norm": 1.4981484413146973,
|
| 98 |
+
"learning_rate": 6.499388903957628e-05,
|
| 99 |
+
"loss": 0.9481,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.02818035426731079,
|
| 104 |
+
"grad_norm": 1.4716213941574097,
|
| 105 |
+
"learning_rate": 6.498913633516483e-05,
|
| 106 |
+
"loss": 0.8809,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.030193236714975844,
|
| 111 |
+
"grad_norm": 1.3817026615142822,
|
| 112 |
+
"learning_rate": 6.498302605566152e-05,
|
| 113 |
+
"loss": 0.9264,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0322061191626409,
|
| 118 |
+
"grad_norm": 1.509097695350647,
|
| 119 |
+
"learning_rate": 6.497555845638748e-05,
|
| 120 |
+
"loss": 0.8829,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03421900161030596,
|
| 125 |
+
"grad_norm": 1.5498337745666504,
|
| 126 |
+
"learning_rate": 6.496673384938014e-05,
|
| 127 |
+
"loss": 0.9227,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.036231884057971016,
|
| 132 |
+
"grad_norm": 1.527828574180603,
|
| 133 |
+
"learning_rate": 6.49565526033802e-05,
|
| 134 |
+
"loss": 0.9488,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.038244766505636074,
|
| 139 |
+
"grad_norm": 1.4578592777252197,
|
| 140 |
+
"learning_rate": 6.494501514381621e-05,
|
| 141 |
+
"loss": 0.8845,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.040257648953301126,
|
| 146 |
+
"grad_norm": 1.4198046922683716,
|
| 147 |
+
"learning_rate": 6.493212195278678e-05,
|
| 148 |
+
"loss": 0.8809,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.042270531400966184,
|
| 153 |
+
"grad_norm": 1.4455400705337524,
|
| 154 |
+
"learning_rate": 6.491787356904047e-05,
|
| 155 |
+
"loss": 0.8686,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04428341384863124,
|
| 160 |
+
"grad_norm": 1.5711616277694702,
|
| 161 |
+
"learning_rate": 6.490227058795323e-05,
|
| 162 |
+
"loss": 0.96,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.046296296296296294,
|
| 167 |
+
"grad_norm": 1.4603729248046875,
|
| 168 |
+
"learning_rate": 6.488531366150359e-05,
|
| 169 |
+
"loss": 0.9026,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.04830917874396135,
|
| 174 |
+
"grad_norm": 1.4184608459472656,
|
| 175 |
+
"learning_rate": 6.48670034982453e-05,
|
| 176 |
+
"loss": 0.9426,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05032206119162641,
|
| 181 |
+
"grad_norm": 1.4080291986465454,
|
| 182 |
+
"learning_rate": 6.484734086327788e-05,
|
| 183 |
+
"loss": 0.8857,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.05233494363929147,
|
| 188 |
+
"grad_norm": 1.4739091396331787,
|
| 189 |
+
"learning_rate": 6.482632657821454e-05,
|
| 190 |
+
"loss": 0.8897,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.05434782608695652,
|
| 195 |
+
"grad_norm": 1.320746898651123,
|
| 196 |
+
"learning_rate": 6.480396152114787e-05,
|
| 197 |
+
"loss": 0.8512,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.05636070853462158,
|
| 202 |
+
"grad_norm": 1.4142905473709106,
|
| 203 |
+
"learning_rate": 6.478024662661315e-05,
|
| 204 |
+
"loss": 0.9459,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.05837359098228664,
|
| 209 |
+
"grad_norm": 1.3830432891845703,
|
| 210 |
+
"learning_rate": 6.47551828855493e-05,
|
| 211 |
+
"loss": 0.8605,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06038647342995169,
|
| 216 |
+
"grad_norm": 1.3653528690338135,
|
| 217 |
+
"learning_rate": 6.472877134525753e-05,
|
| 218 |
+
"loss": 0.8446,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06239935587761675,
|
| 223 |
+
"grad_norm": 1.3041807413101196,
|
| 224 |
+
"learning_rate": 6.470101310935746e-05,
|
| 225 |
+
"loss": 0.8407,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.0644122383252818,
|
| 230 |
+
"grad_norm": 1.3803820610046387,
|
| 231 |
+
"learning_rate": 6.467190933774112e-05,
|
| 232 |
+
"loss": 0.8505,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06642512077294686,
|
| 237 |
+
"grad_norm": 1.3407087326049805,
|
| 238 |
+
"learning_rate": 6.464146124652441e-05,
|
| 239 |
+
"loss": 0.794,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06843800322061191,
|
| 244 |
+
"grad_norm": 1.4283268451690674,
|
| 245 |
+
"learning_rate": 6.460967010799629e-05,
|
| 246 |
+
"loss": 0.9139,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.07045088566827697,
|
| 251 |
+
"grad_norm": 1.3512784242630005,
|
| 252 |
+
"learning_rate": 6.457653725056568e-05,
|
| 253 |
+
"loss": 0.807,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.07246376811594203,
|
| 258 |
+
"grad_norm": 1.3088512420654297,
|
| 259 |
+
"learning_rate": 6.454206405870587e-05,
|
| 260 |
+
"loss": 0.8968,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07447665056360708,
|
| 265 |
+
"grad_norm": 1.2908034324645996,
|
| 266 |
+
"learning_rate": 6.450625197289675e-05,
|
| 267 |
+
"loss": 0.8447,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.07648953301127215,
|
| 272 |
+
"grad_norm": 1.3444992303848267,
|
| 273 |
+
"learning_rate": 6.446910248956453e-05,
|
| 274 |
+
"loss": 0.8891,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.0785024154589372,
|
| 279 |
+
"grad_norm": 1.2567275762557983,
|
| 280 |
+
"learning_rate": 6.443061716101926e-05,
|
| 281 |
+
"loss": 0.8134,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.08051529790660225,
|
| 286 |
+
"grad_norm": 1.3401930332183838,
|
| 287 |
+
"learning_rate": 6.439079759539e-05,
|
| 288 |
+
"loss": 0.8751,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08252818035426732,
|
| 293 |
+
"grad_norm": 1.3348793983459473,
|
| 294 |
+
"learning_rate": 6.434964545655754e-05,
|
| 295 |
+
"loss": 0.7942,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.08454106280193237,
|
| 300 |
+
"grad_norm": 1.311357021331787,
|
| 301 |
+
"learning_rate": 6.430716246408493e-05,
|
| 302 |
+
"loss": 0.8461,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08655394524959742,
|
| 307 |
+
"grad_norm": 1.3319345712661743,
|
| 308 |
+
"learning_rate": 6.426335039314566e-05,
|
| 309 |
+
"loss": 0.8821,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.08856682769726248,
|
| 314 |
+
"grad_norm": 1.304795742034912,
|
| 315 |
+
"learning_rate": 6.421821107444936e-05,
|
| 316 |
+
"loss": 0.8655,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.09057971014492754,
|
| 321 |
+
"grad_norm": 1.422869086265564,
|
| 322 |
+
"learning_rate": 6.417174639416547e-05,
|
| 323 |
+
"loss": 0.9261,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09259259259259259,
|
| 328 |
+
"grad_norm": 1.2931973934173584,
|
| 329 |
+
"learning_rate": 6.412395829384427e-05,
|
| 330 |
+
"loss": 0.8157,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09460547504025765,
|
| 335 |
+
"grad_norm": 1.2984646558761597,
|
| 336 |
+
"learning_rate": 6.407484877033586e-05,
|
| 337 |
+
"loss": 0.7919,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.0966183574879227,
|
| 342 |
+
"grad_norm": 1.2596486806869507,
|
| 343 |
+
"learning_rate": 6.402441987570665e-05,
|
| 344 |
+
"loss": 0.7682,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09863123993558776,
|
| 349 |
+
"grad_norm": 1.3544796705245972,
|
| 350 |
+
"learning_rate": 6.397267371715368e-05,
|
| 351 |
+
"loss": 0.9084,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.10064412238325282,
|
| 356 |
+
"grad_norm": 1.2623202800750732,
|
| 357 |
+
"learning_rate": 6.391961245691652e-05,
|
| 358 |
+
"loss": 0.8482,
|
| 359 |
+
"step": 50
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 1,
|
| 363 |
+
"max_steps": 496,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 1,
|
| 366 |
+
"save_steps": 50,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 5.877172627557581e+16,
|
| 380 |
+
"train_batch_size": 6,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|
checkpoint-50/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d099daa3926570d9e2501eaac78896812191b5c803506c6b4dc9b531482a17b
|
| 3 |
+
size 5112
|