Upload folder using huggingface_hub
Browse files- checkpoint-4800/README.md +206 -0
- checkpoint-4800/adapter_config.json +48 -0
- checkpoint-4800/adapter_model.safetensors +3 -0
- checkpoint-4800/optimizer.pt +3 -0
- checkpoint-4800/preprocessor_config.json +10 -0
- checkpoint-4800/rng_state.pth +3 -0
- checkpoint-4800/scaler.pt +3 -0
- checkpoint-4800/scheduler.pt +3 -0
- checkpoint-4800/trainer_state.json +706 -0
- checkpoint-4800/training_args.bin +3 -0
- checkpoint-5000/README.md +206 -0
- checkpoint-5000/adapter_config.json +48 -0
- checkpoint-5000/adapter_model.safetensors +3 -0
- checkpoint-5000/optimizer.pt +3 -0
- checkpoint-5000/preprocessor_config.json +10 -0
- checkpoint-5000/rng_state.pth +3 -0
- checkpoint-5000/scaler.pt +3 -0
- checkpoint-5000/scheduler.pt +3 -0
- checkpoint-5000/trainer_state.json +734 -0
- checkpoint-5000/training_args.bin +3 -0
- checkpoint-5001/README.md +206 -0
- checkpoint-5001/adapter_config.json +48 -0
- checkpoint-5001/adapter_model.safetensors +3 -0
- checkpoint-5001/optimizer.pt +3 -0
- checkpoint-5001/preprocessor_config.json +10 -0
- checkpoint-5001/rng_state.pth +3 -0
- checkpoint-5001/scaler.pt +3 -0
- checkpoint-5001/scheduler.pt +3 -0
- checkpoint-5001/trainer_state.json +734 -0
- checkpoint-5001/training_args.bin +3 -0
checkpoint-4800/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: tinkvu/wav2vec2-large-xlsr-amharic-healthcare
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:tinkvu/wav2vec2-large-xlsr-amharic-healthcare
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.18.0
|
checkpoint-4800/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "Wav2Vec2ForCTC",
|
| 7 |
+
"parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
|
| 8 |
+
},
|
| 9 |
+
"base_model_name_or_path": "tinkvu/wav2vec2-large-xlsr-amharic-healthcare",
|
| 10 |
+
"bias": "none",
|
| 11 |
+
"corda_config": null,
|
| 12 |
+
"ensure_weight_tying": false,
|
| 13 |
+
"eva_config": null,
|
| 14 |
+
"exclude_modules": null,
|
| 15 |
+
"fan_in_fan_out": false,
|
| 16 |
+
"inference_mode": true,
|
| 17 |
+
"init_lora_weights": true,
|
| 18 |
+
"layer_replication": null,
|
| 19 |
+
"layers_pattern": null,
|
| 20 |
+
"layers_to_transform": null,
|
| 21 |
+
"loftq_config": {},
|
| 22 |
+
"lora_alpha": 32,
|
| 23 |
+
"lora_bias": false,
|
| 24 |
+
"lora_dropout": 0.05,
|
| 25 |
+
"megatron_config": null,
|
| 26 |
+
"megatron_core": "megatron.core",
|
| 27 |
+
"modules_to_save": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.18.0",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"fc2",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"fc1",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"out_proj",
|
| 40 |
+
"v_proj"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": null,
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-4800/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b94833f7953f32ef49bc33486828f0294e6f1d4c8e21970687c840f2c832b1e0
|
| 3 |
+
size 12610664
|
checkpoint-4800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56b6ec12866348d3bf718c52dd3cf239a75990f52ab7aa86d1aa9e4805ec6b53
|
| 3 |
+
size 25327034
|
checkpoint-4800/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-4800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3525b75218401e73865cc0270e8bd606b853f31756a6d9e8b511c58565e06000
|
| 3 |
+
size 14308
|
checkpoint-4800/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b2448f0914773f32921479c4246fc3dea33103c48c01f24891857705a0882d
|
| 3 |
+
size 988
|
checkpoint-4800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e52d9fa1cfb486c7935854e059b6f28c5f346e2723a9a65bddf87ba2351f0607
|
| 3 |
+
size 1064
|
checkpoint-4800/trainer_state.json
ADDED
|
@@ -0,0 +1,706 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.96,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01,
|
| 14 |
+
"grad_norm": 2.4969277381896973,
|
| 15 |
+
"learning_rate": 1.76e-05,
|
| 16 |
+
"loss": 19.5898,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 8.099705696105957,
|
| 22 |
+
"learning_rate": 3.76e-05,
|
| 23 |
+
"loss": 17.8223,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 11.919422149658203,
|
| 29 |
+
"learning_rate": 5.72e-05,
|
| 30 |
+
"loss": 10.8995,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 6.321387767791748,
|
| 36 |
+
"learning_rate": 7.64e-05,
|
| 37 |
+
"loss": 3.1441,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 1.5579607486724854,
|
| 43 |
+
"learning_rate": 9.64e-05,
|
| 44 |
+
"loss": 1.0788,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 2.1052896976470947,
|
| 50 |
+
"learning_rate": 0.0001164,
|
| 51 |
+
"loss": 0.3291,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07,
|
| 56 |
+
"grad_norm": 1.402535319328308,
|
| 57 |
+
"learning_rate": 0.0001364,
|
| 58 |
+
"loss": 0.3073,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08,
|
| 63 |
+
"grad_norm": 1.533136248588562,
|
| 64 |
+
"learning_rate": 0.00015600000000000002,
|
| 65 |
+
"loss": 0.4065,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09,
|
| 70 |
+
"grad_norm": 2.3747737407684326,
|
| 71 |
+
"learning_rate": 0.00017600000000000002,
|
| 72 |
+
"loss": 0.294,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1,
|
| 77 |
+
"grad_norm": 6.622051239013672,
|
| 78 |
+
"learning_rate": 0.000196,
|
| 79 |
+
"loss": 0.2311,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"grad_norm": 1.6454269886016846,
|
| 85 |
+
"learning_rate": 0.00019822222222222225,
|
| 86 |
+
"loss": 0.3515,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"grad_norm": 10.714489936828613,
|
| 92 |
+
"learning_rate": 0.000196,
|
| 93 |
+
"loss": 0.1957,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13,
|
| 98 |
+
"grad_norm": 1.3993964195251465,
|
| 99 |
+
"learning_rate": 0.0001937777777777778,
|
| 100 |
+
"loss": 0.2028,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14,
|
| 105 |
+
"grad_norm": 0.7649514675140381,
|
| 106 |
+
"learning_rate": 0.0001916,
|
| 107 |
+
"loss": 0.2995,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15,
|
| 112 |
+
"grad_norm": 0.5896079540252686,
|
| 113 |
+
"learning_rate": 0.0001893777777777778,
|
| 114 |
+
"loss": 0.1876,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16,
|
| 119 |
+
"grad_norm": 0.6604533791542053,
|
| 120 |
+
"learning_rate": 0.00018715555555555557,
|
| 121 |
+
"loss": 0.19,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"grad_norm": 2.047614097595215,
|
| 127 |
+
"learning_rate": 0.00018493333333333335,
|
| 128 |
+
"loss": 0.0988,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"grad_norm": 1.374024748802185,
|
| 134 |
+
"learning_rate": 0.00018271111111111112,
|
| 135 |
+
"loss": 0.1355,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.19,
|
| 140 |
+
"grad_norm": 1.4950742721557617,
|
| 141 |
+
"learning_rate": 0.0001804888888888889,
|
| 142 |
+
"loss": 0.1303,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2,
|
| 147 |
+
"grad_norm": 2.006479024887085,
|
| 148 |
+
"learning_rate": 0.00017826666666666667,
|
| 149 |
+
"loss": 0.1999,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.21,
|
| 154 |
+
"grad_norm": 1.1253306865692139,
|
| 155 |
+
"learning_rate": 0.00017604444444444445,
|
| 156 |
+
"loss": 0.152,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.22,
|
| 161 |
+
"grad_norm": 0.8224861025810242,
|
| 162 |
+
"learning_rate": 0.00017382222222222222,
|
| 163 |
+
"loss": 0.1444,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23,
|
| 168 |
+
"grad_norm": 0.523875892162323,
|
| 169 |
+
"learning_rate": 0.0001716,
|
| 170 |
+
"loss": 0.155,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"grad_norm": 1.7560786008834839,
|
| 176 |
+
"learning_rate": 0.0001693777777777778,
|
| 177 |
+
"loss": 0.1934,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 0.6891859173774719,
|
| 183 |
+
"learning_rate": 0.00016715555555555555,
|
| 184 |
+
"loss": 0.1062,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.26,
|
| 189 |
+
"grad_norm": 3.0257561206817627,
|
| 190 |
+
"learning_rate": 0.00016493333333333335,
|
| 191 |
+
"loss": 0.1132,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.27,
|
| 196 |
+
"grad_norm": 0.0,
|
| 197 |
+
"learning_rate": 0.00016351111111111112,
|
| 198 |
+
"loss": 0.3971,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.28,
|
| 203 |
+
"grad_norm": 0.0,
|
| 204 |
+
"learning_rate": 0.0001612888888888889,
|
| 205 |
+
"loss": 0.2656,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29,
|
| 210 |
+
"grad_norm": 0.0,
|
| 211 |
+
"learning_rate": 0.00015924444444444447,
|
| 212 |
+
"loss": 0.4477,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"grad_norm": 0.0,
|
| 218 |
+
"learning_rate": 0.00015706666666666667,
|
| 219 |
+
"loss": 0.3441,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.31,
|
| 224 |
+
"grad_norm": 0.0,
|
| 225 |
+
"learning_rate": 0.00015484444444444445,
|
| 226 |
+
"loss": 0.1985,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.32,
|
| 231 |
+
"grad_norm": 0.0,
|
| 232 |
+
"learning_rate": 0.00015262222222222222,
|
| 233 |
+
"loss": 0.2074,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.33,
|
| 238 |
+
"grad_norm": 0.0,
|
| 239 |
+
"learning_rate": 0.00015066666666666668,
|
| 240 |
+
"loss": 0.481,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.34,
|
| 245 |
+
"grad_norm": 0.0,
|
| 246 |
+
"learning_rate": 0.00014857777777777778,
|
| 247 |
+
"loss": 0.2268,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.35,
|
| 252 |
+
"grad_norm": 0.0,
|
| 253 |
+
"learning_rate": 0.00014635555555555556,
|
| 254 |
+
"loss": 0.1873,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"grad_norm": 0.0,
|
| 260 |
+
"learning_rate": 0.00014413333333333333,
|
| 261 |
+
"loss": 0.2051,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.37,
|
| 266 |
+
"grad_norm": 0.0,
|
| 267 |
+
"learning_rate": 0.00014191111111111113,
|
| 268 |
+
"loss": 0.2184,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.38,
|
| 273 |
+
"grad_norm": 0.0,
|
| 274 |
+
"learning_rate": 0.00013968888888888888,
|
| 275 |
+
"loss": 0.112,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.39,
|
| 280 |
+
"grad_norm": 0.0,
|
| 281 |
+
"learning_rate": 0.00013751111111111113,
|
| 282 |
+
"loss": 0.2867,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4,
|
| 287 |
+
"grad_norm": 0.0,
|
| 288 |
+
"learning_rate": 0.00013528888888888888,
|
| 289 |
+
"loss": 0.1132,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.41,
|
| 294 |
+
"grad_norm": 0.0,
|
| 295 |
+
"learning_rate": 0.00013306666666666668,
|
| 296 |
+
"loss": 0.2804,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"grad_norm": 0.0,
|
| 302 |
+
"learning_rate": 0.00013084444444444446,
|
| 303 |
+
"loss": 0.1317,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.43,
|
| 308 |
+
"grad_norm": 0.0,
|
| 309 |
+
"learning_rate": 0.00012862222222222223,
|
| 310 |
+
"loss": 0.1032,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.44,
|
| 315 |
+
"grad_norm": 0.0,
|
| 316 |
+
"learning_rate": 0.0001264,
|
| 317 |
+
"loss": 0.1184,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.45,
|
| 322 |
+
"grad_norm": 0.0,
|
| 323 |
+
"learning_rate": 0.00012417777777777778,
|
| 324 |
+
"loss": 0.1207,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.46,
|
| 329 |
+
"grad_norm": 0.0,
|
| 330 |
+
"learning_rate": 0.00012195555555555556,
|
| 331 |
+
"loss": 0.1269,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.47,
|
| 336 |
+
"grad_norm": 0.0,
|
| 337 |
+
"learning_rate": 0.00011973333333333335,
|
| 338 |
+
"loss": 0.1391,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"grad_norm": 0.0,
|
| 344 |
+
"learning_rate": 0.00011773333333333334,
|
| 345 |
+
"loss": 0.2337,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49,
|
| 350 |
+
"grad_norm": 0.0,
|
| 351 |
+
"learning_rate": 0.00011586666666666667,
|
| 352 |
+
"loss": 0.3983,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5,
|
| 357 |
+
"grad_norm": 0.0,
|
| 358 |
+
"learning_rate": 0.00011373333333333334,
|
| 359 |
+
"loss": 0.1904,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.51,
|
| 364 |
+
"grad_norm": 0.0,
|
| 365 |
+
"learning_rate": 0.00011160000000000002,
|
| 366 |
+
"loss": 0.2106,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.52,
|
| 371 |
+
"grad_norm": 0.0,
|
| 372 |
+
"learning_rate": 0.00010942222222222223,
|
| 373 |
+
"loss": 0.1193,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.53,
|
| 378 |
+
"grad_norm": 0.0,
|
| 379 |
+
"learning_rate": 0.00010720000000000002,
|
| 380 |
+
"loss": 0.1406,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.54,
|
| 385 |
+
"grad_norm": 0.0,
|
| 386 |
+
"learning_rate": 0.00010497777777777778,
|
| 387 |
+
"loss": 0.1312,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.55,
|
| 392 |
+
"grad_norm": 0.0,
|
| 393 |
+
"learning_rate": 0.00010275555555555557,
|
| 394 |
+
"loss": 0.1193,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.56,
|
| 399 |
+
"grad_norm": 0.0,
|
| 400 |
+
"learning_rate": 0.00010053333333333334,
|
| 401 |
+
"loss": 0.1838,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.57,
|
| 406 |
+
"grad_norm": 0.0,
|
| 407 |
+
"learning_rate": 9.831111111111112e-05,
|
| 408 |
+
"loss": 0.1306,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.58,
|
| 413 |
+
"grad_norm": 0.0,
|
| 414 |
+
"learning_rate": 9.608888888888889e-05,
|
| 415 |
+
"loss": 0.1127,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.59,
|
| 420 |
+
"grad_norm": 0.0,
|
| 421 |
+
"learning_rate": 9.386666666666667e-05,
|
| 422 |
+
"loss": 0.1963,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6,
|
| 427 |
+
"grad_norm": 0.0,
|
| 428 |
+
"learning_rate": 9.164444444444444e-05,
|
| 429 |
+
"loss": 0.1813,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.61,
|
| 434 |
+
"grad_norm": 0.0,
|
| 435 |
+
"learning_rate": 8.942222222222223e-05,
|
| 436 |
+
"loss": 0.2901,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.62,
|
| 441 |
+
"grad_norm": 0.0,
|
| 442 |
+
"learning_rate": 8.72e-05,
|
| 443 |
+
"loss": 0.0905,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.63,
|
| 448 |
+
"grad_norm": 0.0,
|
| 449 |
+
"learning_rate": 8.497777777777778e-05,
|
| 450 |
+
"loss": 0.1058,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.64,
|
| 455 |
+
"grad_norm": 0.0,
|
| 456 |
+
"learning_rate": 8.275555555555557e-05,
|
| 457 |
+
"loss": 0.0965,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.65,
|
| 462 |
+
"grad_norm": 0.0,
|
| 463 |
+
"learning_rate": 8.053333333333334e-05,
|
| 464 |
+
"loss": 0.0936,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.66,
|
| 469 |
+
"grad_norm": 0.0,
|
| 470 |
+
"learning_rate": 7.831111111111112e-05,
|
| 471 |
+
"loss": 0.1093,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.67,
|
| 476 |
+
"grad_norm": 0.0,
|
| 477 |
+
"learning_rate": 7.613333333333333e-05,
|
| 478 |
+
"loss": 0.1311,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.68,
|
| 483 |
+
"grad_norm": 0.0,
|
| 484 |
+
"learning_rate": 7.391111111111112e-05,
|
| 485 |
+
"loss": 0.1027,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.69,
|
| 490 |
+
"grad_norm": 0.0,
|
| 491 |
+
"learning_rate": 7.16888888888889e-05,
|
| 492 |
+
"loss": 0.0657,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7,
|
| 497 |
+
"grad_norm": 0.0,
|
| 498 |
+
"learning_rate": 6.946666666666667e-05,
|
| 499 |
+
"loss": 0.0836,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.71,
|
| 504 |
+
"grad_norm": 0.0,
|
| 505 |
+
"learning_rate": 6.724444444444445e-05,
|
| 506 |
+
"loss": 0.0843,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.72,
|
| 511 |
+
"grad_norm": 0.0,
|
| 512 |
+
"learning_rate": 6.502222222222223e-05,
|
| 513 |
+
"loss": 0.0796,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.73,
|
| 518 |
+
"grad_norm": 0.0,
|
| 519 |
+
"learning_rate": 6.280000000000001e-05,
|
| 520 |
+
"loss": 0.0975,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.74,
|
| 525 |
+
"grad_norm": 0.0,
|
| 526 |
+
"learning_rate": 6.057777777777778e-05,
|
| 527 |
+
"loss": 0.0945,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.75,
|
| 532 |
+
"grad_norm": 0.0,
|
| 533 |
+
"learning_rate": 5.8355555555555565e-05,
|
| 534 |
+
"loss": 0.128,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.76,
|
| 539 |
+
"grad_norm": 0.0,
|
| 540 |
+
"learning_rate": 5.613333333333334e-05,
|
| 541 |
+
"loss": 0.0835,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.77,
|
| 546 |
+
"grad_norm": 0.0,
|
| 547 |
+
"learning_rate": 5.3911111111111115e-05,
|
| 548 |
+
"loss": 0.0689,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.78,
|
| 553 |
+
"grad_norm": 0.0,
|
| 554 |
+
"learning_rate": 5.1688888888888883e-05,
|
| 555 |
+
"loss": 0.0727,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.79,
|
| 560 |
+
"grad_norm": 0.0,
|
| 561 |
+
"learning_rate": 4.9466666666666665e-05,
|
| 562 |
+
"loss": 0.0858,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8,
|
| 567 |
+
"grad_norm": 0.0,
|
| 568 |
+
"learning_rate": 4.724444444444445e-05,
|
| 569 |
+
"loss": 0.133,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.81,
|
| 574 |
+
"grad_norm": 0.0,
|
| 575 |
+
"learning_rate": 4.502222222222223e-05,
|
| 576 |
+
"loss": 0.1415,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.82,
|
| 581 |
+
"grad_norm": 0.0,
|
| 582 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 583 |
+
"loss": 0.084,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.83,
|
| 588 |
+
"grad_norm": 0.0,
|
| 589 |
+
"learning_rate": 4.057777777777778e-05,
|
| 590 |
+
"loss": 0.0646,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.84,
|
| 595 |
+
"grad_norm": 0.0,
|
| 596 |
+
"learning_rate": 3.8355555555555553e-05,
|
| 597 |
+
"loss": 0.0846,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.85,
|
| 602 |
+
"grad_norm": 0.0,
|
| 603 |
+
"learning_rate": 3.6133333333333335e-05,
|
| 604 |
+
"loss": 0.0827,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.86,
|
| 609 |
+
"grad_norm": 0.0,
|
| 610 |
+
"learning_rate": 3.391111111111111e-05,
|
| 611 |
+
"loss": 0.0659,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.87,
|
| 616 |
+
"grad_norm": 0.0,
|
| 617 |
+
"learning_rate": 3.168888888888889e-05,
|
| 618 |
+
"loss": 0.0723,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.88,
|
| 623 |
+
"grad_norm": 0.0,
|
| 624 |
+
"learning_rate": 2.946666666666667e-05,
|
| 625 |
+
"loss": 0.0909,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.89,
|
| 630 |
+
"grad_norm": 0.0,
|
| 631 |
+
"learning_rate": 2.7244444444444445e-05,
|
| 632 |
+
"loss": 0.0962,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9,
|
| 637 |
+
"grad_norm": 0.0,
|
| 638 |
+
"learning_rate": 2.5022222222222224e-05,
|
| 639 |
+
"loss": 0.0838,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.91,
|
| 644 |
+
"grad_norm": 0.0,
|
| 645 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 646 |
+
"loss": 0.137,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.92,
|
| 651 |
+
"grad_norm": 0.0,
|
| 652 |
+
"learning_rate": 2.062222222222222e-05,
|
| 653 |
+
"loss": 0.151,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.93,
|
| 658 |
+
"grad_norm": 0.0,
|
| 659 |
+
"learning_rate": 1.84e-05,
|
| 660 |
+
"loss": 0.1,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.94,
|
| 665 |
+
"grad_norm": 0.0,
|
| 666 |
+
"learning_rate": 1.617777777777778e-05,
|
| 667 |
+
"loss": 0.0763,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.95,
|
| 672 |
+
"grad_norm": 0.0,
|
| 673 |
+
"learning_rate": 1.3955555555555555e-05,
|
| 674 |
+
"loss": 0.2048,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.96,
|
| 679 |
+
"grad_norm": 0.0,
|
| 680 |
+
"learning_rate": 1.1733333333333333e-05,
|
| 681 |
+
"loss": 0.1829,
|
| 682 |
+
"step": 4800
|
| 683 |
+
}
|
| 684 |
+
],
|
| 685 |
+
"logging_steps": 50,
|
| 686 |
+
"max_steps": 5000,
|
| 687 |
+
"num_input_tokens_seen": 0,
|
| 688 |
+
"num_train_epochs": 9223372036854775807,
|
| 689 |
+
"save_steps": 200,
|
| 690 |
+
"stateful_callbacks": {
|
| 691 |
+
"TrainerControl": {
|
| 692 |
+
"args": {
|
| 693 |
+
"should_epoch_stop": false,
|
| 694 |
+
"should_evaluate": false,
|
| 695 |
+
"should_log": false,
|
| 696 |
+
"should_save": true,
|
| 697 |
+
"should_training_stop": false
|
| 698 |
+
},
|
| 699 |
+
"attributes": {}
|
| 700 |
+
}
|
| 701 |
+
},
|
| 702 |
+
"total_flos": 5.622660590999084e+18,
|
| 703 |
+
"train_batch_size": 1,
|
| 704 |
+
"trial_name": null,
|
| 705 |
+
"trial_params": null
|
| 706 |
+
}
|
checkpoint-4800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c914d1162d969be07a28866d27b70136a6145fb226e21fdb5ca172fa8cc238d
|
| 3 |
+
size 5368
|
checkpoint-5000/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: tinkvu/wav2vec2-large-xlsr-amharic-healthcare
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:tinkvu/wav2vec2-large-xlsr-amharic-healthcare
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.18.0
|
checkpoint-5000/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "Wav2Vec2ForCTC",
|
| 7 |
+
"parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
|
| 8 |
+
},
|
| 9 |
+
"base_model_name_or_path": "tinkvu/wav2vec2-large-xlsr-amharic-healthcare",
|
| 10 |
+
"bias": "none",
|
| 11 |
+
"corda_config": null,
|
| 12 |
+
"ensure_weight_tying": false,
|
| 13 |
+
"eva_config": null,
|
| 14 |
+
"exclude_modules": null,
|
| 15 |
+
"fan_in_fan_out": false,
|
| 16 |
+
"inference_mode": true,
|
| 17 |
+
"init_lora_weights": true,
|
| 18 |
+
"layer_replication": null,
|
| 19 |
+
"layers_pattern": null,
|
| 20 |
+
"layers_to_transform": null,
|
| 21 |
+
"loftq_config": {},
|
| 22 |
+
"lora_alpha": 32,
|
| 23 |
+
"lora_bias": false,
|
| 24 |
+
"lora_dropout": 0.05,
|
| 25 |
+
"megatron_config": null,
|
| 26 |
+
"megatron_core": "megatron.core",
|
| 27 |
+
"modules_to_save": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.18.0",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"fc2",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"fc1",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"out_proj",
|
| 40 |
+
"v_proj"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": null,
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-5000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b94833f7953f32ef49bc33486828f0294e6f1d4c8e21970687c840f2c832b1e0
|
| 3 |
+
size 12610664
|
checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc09ebe8d77cac1a1e53048182f106ea6de38cedd5f5771a5a98de74edd67e36
|
| 3 |
+
size 25327034
|
checkpoint-5000/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-5000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2659cb4e60e37a9bb37150e55e3cd20a5f33a9d703b53ff7cbfe2e0807285e52
|
| 3 |
+
size 14308
|
checkpoint-5000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bd303ddfd62eb46548aabbf09bda78c123534cdd76aeec496e88f6edf6a6d84
|
| 3 |
+
size 988
|
checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81296d7a42b175767c4064a500d9c3b456ca12efa1938516551ad5dfc47353cb
|
| 3 |
+
size 1064
|
checkpoint-5000/trainer_state.json
ADDED
|
@@ -0,0 +1,734 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 5000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01,
|
| 14 |
+
"grad_norm": 2.4969277381896973,
|
| 15 |
+
"learning_rate": 1.76e-05,
|
| 16 |
+
"loss": 19.5898,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 8.099705696105957,
|
| 22 |
+
"learning_rate": 3.76e-05,
|
| 23 |
+
"loss": 17.8223,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 11.919422149658203,
|
| 29 |
+
"learning_rate": 5.72e-05,
|
| 30 |
+
"loss": 10.8995,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 6.321387767791748,
|
| 36 |
+
"learning_rate": 7.64e-05,
|
| 37 |
+
"loss": 3.1441,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 1.5579607486724854,
|
| 43 |
+
"learning_rate": 9.64e-05,
|
| 44 |
+
"loss": 1.0788,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 2.1052896976470947,
|
| 50 |
+
"learning_rate": 0.0001164,
|
| 51 |
+
"loss": 0.3291,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07,
|
| 56 |
+
"grad_norm": 1.402535319328308,
|
| 57 |
+
"learning_rate": 0.0001364,
|
| 58 |
+
"loss": 0.3073,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08,
|
| 63 |
+
"grad_norm": 1.533136248588562,
|
| 64 |
+
"learning_rate": 0.00015600000000000002,
|
| 65 |
+
"loss": 0.4065,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09,
|
| 70 |
+
"grad_norm": 2.3747737407684326,
|
| 71 |
+
"learning_rate": 0.00017600000000000002,
|
| 72 |
+
"loss": 0.294,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1,
|
| 77 |
+
"grad_norm": 6.622051239013672,
|
| 78 |
+
"learning_rate": 0.000196,
|
| 79 |
+
"loss": 0.2311,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"grad_norm": 1.6454269886016846,
|
| 85 |
+
"learning_rate": 0.00019822222222222225,
|
| 86 |
+
"loss": 0.3515,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"grad_norm": 10.714489936828613,
|
| 92 |
+
"learning_rate": 0.000196,
|
| 93 |
+
"loss": 0.1957,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13,
|
| 98 |
+
"grad_norm": 1.3993964195251465,
|
| 99 |
+
"learning_rate": 0.0001937777777777778,
|
| 100 |
+
"loss": 0.2028,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14,
|
| 105 |
+
"grad_norm": 0.7649514675140381,
|
| 106 |
+
"learning_rate": 0.0001916,
|
| 107 |
+
"loss": 0.2995,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15,
|
| 112 |
+
"grad_norm": 0.5896079540252686,
|
| 113 |
+
"learning_rate": 0.0001893777777777778,
|
| 114 |
+
"loss": 0.1876,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16,
|
| 119 |
+
"grad_norm": 0.6604533791542053,
|
| 120 |
+
"learning_rate": 0.00018715555555555557,
|
| 121 |
+
"loss": 0.19,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"grad_norm": 2.047614097595215,
|
| 127 |
+
"learning_rate": 0.00018493333333333335,
|
| 128 |
+
"loss": 0.0988,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"grad_norm": 1.374024748802185,
|
| 134 |
+
"learning_rate": 0.00018271111111111112,
|
| 135 |
+
"loss": 0.1355,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.19,
|
| 140 |
+
"grad_norm": 1.4950742721557617,
|
| 141 |
+
"learning_rate": 0.0001804888888888889,
|
| 142 |
+
"loss": 0.1303,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2,
|
| 147 |
+
"grad_norm": 2.006479024887085,
|
| 148 |
+
"learning_rate": 0.00017826666666666667,
|
| 149 |
+
"loss": 0.1999,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.21,
|
| 154 |
+
"grad_norm": 1.1253306865692139,
|
| 155 |
+
"learning_rate": 0.00017604444444444445,
|
| 156 |
+
"loss": 0.152,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.22,
|
| 161 |
+
"grad_norm": 0.8224861025810242,
|
| 162 |
+
"learning_rate": 0.00017382222222222222,
|
| 163 |
+
"loss": 0.1444,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23,
|
| 168 |
+
"grad_norm": 0.523875892162323,
|
| 169 |
+
"learning_rate": 0.0001716,
|
| 170 |
+
"loss": 0.155,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"grad_norm": 1.7560786008834839,
|
| 176 |
+
"learning_rate": 0.0001693777777777778,
|
| 177 |
+
"loss": 0.1934,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 0.6891859173774719,
|
| 183 |
+
"learning_rate": 0.00016715555555555555,
|
| 184 |
+
"loss": 0.1062,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.26,
|
| 189 |
+
"grad_norm": 3.0257561206817627,
|
| 190 |
+
"learning_rate": 0.00016493333333333335,
|
| 191 |
+
"loss": 0.1132,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.27,
|
| 196 |
+
"grad_norm": 0.0,
|
| 197 |
+
"learning_rate": 0.00016351111111111112,
|
| 198 |
+
"loss": 0.3971,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.28,
|
| 203 |
+
"grad_norm": 0.0,
|
| 204 |
+
"learning_rate": 0.0001612888888888889,
|
| 205 |
+
"loss": 0.2656,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29,
|
| 210 |
+
"grad_norm": 0.0,
|
| 211 |
+
"learning_rate": 0.00015924444444444447,
|
| 212 |
+
"loss": 0.4477,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"grad_norm": 0.0,
|
| 218 |
+
"learning_rate": 0.00015706666666666667,
|
| 219 |
+
"loss": 0.3441,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.31,
|
| 224 |
+
"grad_norm": 0.0,
|
| 225 |
+
"learning_rate": 0.00015484444444444445,
|
| 226 |
+
"loss": 0.1985,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.32,
|
| 231 |
+
"grad_norm": 0.0,
|
| 232 |
+
"learning_rate": 0.00015262222222222222,
|
| 233 |
+
"loss": 0.2074,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.33,
|
| 238 |
+
"grad_norm": 0.0,
|
| 239 |
+
"learning_rate": 0.00015066666666666668,
|
| 240 |
+
"loss": 0.481,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.34,
|
| 245 |
+
"grad_norm": 0.0,
|
| 246 |
+
"learning_rate": 0.00014857777777777778,
|
| 247 |
+
"loss": 0.2268,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.35,
|
| 252 |
+
"grad_norm": 0.0,
|
| 253 |
+
"learning_rate": 0.00014635555555555556,
|
| 254 |
+
"loss": 0.1873,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"grad_norm": 0.0,
|
| 260 |
+
"learning_rate": 0.00014413333333333333,
|
| 261 |
+
"loss": 0.2051,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.37,
|
| 266 |
+
"grad_norm": 0.0,
|
| 267 |
+
"learning_rate": 0.00014191111111111113,
|
| 268 |
+
"loss": 0.2184,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.38,
|
| 273 |
+
"grad_norm": 0.0,
|
| 274 |
+
"learning_rate": 0.00013968888888888888,
|
| 275 |
+
"loss": 0.112,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.39,
|
| 280 |
+
"grad_norm": 0.0,
|
| 281 |
+
"learning_rate": 0.00013751111111111113,
|
| 282 |
+
"loss": 0.2867,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4,
|
| 287 |
+
"grad_norm": 0.0,
|
| 288 |
+
"learning_rate": 0.00013528888888888888,
|
| 289 |
+
"loss": 0.1132,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.41,
|
| 294 |
+
"grad_norm": 0.0,
|
| 295 |
+
"learning_rate": 0.00013306666666666668,
|
| 296 |
+
"loss": 0.2804,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"grad_norm": 0.0,
|
| 302 |
+
"learning_rate": 0.00013084444444444446,
|
| 303 |
+
"loss": 0.1317,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.43,
|
| 308 |
+
"grad_norm": 0.0,
|
| 309 |
+
"learning_rate": 0.00012862222222222223,
|
| 310 |
+
"loss": 0.1032,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.44,
|
| 315 |
+
"grad_norm": 0.0,
|
| 316 |
+
"learning_rate": 0.0001264,
|
| 317 |
+
"loss": 0.1184,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.45,
|
| 322 |
+
"grad_norm": 0.0,
|
| 323 |
+
"learning_rate": 0.00012417777777777778,
|
| 324 |
+
"loss": 0.1207,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.46,
|
| 329 |
+
"grad_norm": 0.0,
|
| 330 |
+
"learning_rate": 0.00012195555555555556,
|
| 331 |
+
"loss": 0.1269,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.47,
|
| 336 |
+
"grad_norm": 0.0,
|
| 337 |
+
"learning_rate": 0.00011973333333333335,
|
| 338 |
+
"loss": 0.1391,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"grad_norm": 0.0,
|
| 344 |
+
"learning_rate": 0.00011773333333333334,
|
| 345 |
+
"loss": 0.2337,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49,
|
| 350 |
+
"grad_norm": 0.0,
|
| 351 |
+
"learning_rate": 0.00011586666666666667,
|
| 352 |
+
"loss": 0.3983,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5,
|
| 357 |
+
"grad_norm": 0.0,
|
| 358 |
+
"learning_rate": 0.00011373333333333334,
|
| 359 |
+
"loss": 0.1904,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.51,
|
| 364 |
+
"grad_norm": 0.0,
|
| 365 |
+
"learning_rate": 0.00011160000000000002,
|
| 366 |
+
"loss": 0.2106,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.52,
|
| 371 |
+
"grad_norm": 0.0,
|
| 372 |
+
"learning_rate": 0.00010942222222222223,
|
| 373 |
+
"loss": 0.1193,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.53,
|
| 378 |
+
"grad_norm": 0.0,
|
| 379 |
+
"learning_rate": 0.00010720000000000002,
|
| 380 |
+
"loss": 0.1406,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.54,
|
| 385 |
+
"grad_norm": 0.0,
|
| 386 |
+
"learning_rate": 0.00010497777777777778,
|
| 387 |
+
"loss": 0.1312,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.55,
|
| 392 |
+
"grad_norm": 0.0,
|
| 393 |
+
"learning_rate": 0.00010275555555555557,
|
| 394 |
+
"loss": 0.1193,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.56,
|
| 399 |
+
"grad_norm": 0.0,
|
| 400 |
+
"learning_rate": 0.00010053333333333334,
|
| 401 |
+
"loss": 0.1838,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.57,
|
| 406 |
+
"grad_norm": 0.0,
|
| 407 |
+
"learning_rate": 9.831111111111112e-05,
|
| 408 |
+
"loss": 0.1306,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.58,
|
| 413 |
+
"grad_norm": 0.0,
|
| 414 |
+
"learning_rate": 9.608888888888889e-05,
|
| 415 |
+
"loss": 0.1127,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.59,
|
| 420 |
+
"grad_norm": 0.0,
|
| 421 |
+
"learning_rate": 9.386666666666667e-05,
|
| 422 |
+
"loss": 0.1963,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6,
|
| 427 |
+
"grad_norm": 0.0,
|
| 428 |
+
"learning_rate": 9.164444444444444e-05,
|
| 429 |
+
"loss": 0.1813,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.61,
|
| 434 |
+
"grad_norm": 0.0,
|
| 435 |
+
"learning_rate": 8.942222222222223e-05,
|
| 436 |
+
"loss": 0.2901,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.62,
|
| 441 |
+
"grad_norm": 0.0,
|
| 442 |
+
"learning_rate": 8.72e-05,
|
| 443 |
+
"loss": 0.0905,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.63,
|
| 448 |
+
"grad_norm": 0.0,
|
| 449 |
+
"learning_rate": 8.497777777777778e-05,
|
| 450 |
+
"loss": 0.1058,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.64,
|
| 455 |
+
"grad_norm": 0.0,
|
| 456 |
+
"learning_rate": 8.275555555555557e-05,
|
| 457 |
+
"loss": 0.0965,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.65,
|
| 462 |
+
"grad_norm": 0.0,
|
| 463 |
+
"learning_rate": 8.053333333333334e-05,
|
| 464 |
+
"loss": 0.0936,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.66,
|
| 469 |
+
"grad_norm": 0.0,
|
| 470 |
+
"learning_rate": 7.831111111111112e-05,
|
| 471 |
+
"loss": 0.1093,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.67,
|
| 476 |
+
"grad_norm": 0.0,
|
| 477 |
+
"learning_rate": 7.613333333333333e-05,
|
| 478 |
+
"loss": 0.1311,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.68,
|
| 483 |
+
"grad_norm": 0.0,
|
| 484 |
+
"learning_rate": 7.391111111111112e-05,
|
| 485 |
+
"loss": 0.1027,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.69,
|
| 490 |
+
"grad_norm": 0.0,
|
| 491 |
+
"learning_rate": 7.16888888888889e-05,
|
| 492 |
+
"loss": 0.0657,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7,
|
| 497 |
+
"grad_norm": 0.0,
|
| 498 |
+
"learning_rate": 6.946666666666667e-05,
|
| 499 |
+
"loss": 0.0836,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.71,
|
| 504 |
+
"grad_norm": 0.0,
|
| 505 |
+
"learning_rate": 6.724444444444445e-05,
|
| 506 |
+
"loss": 0.0843,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.72,
|
| 511 |
+
"grad_norm": 0.0,
|
| 512 |
+
"learning_rate": 6.502222222222223e-05,
|
| 513 |
+
"loss": 0.0796,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.73,
|
| 518 |
+
"grad_norm": 0.0,
|
| 519 |
+
"learning_rate": 6.280000000000001e-05,
|
| 520 |
+
"loss": 0.0975,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.74,
|
| 525 |
+
"grad_norm": 0.0,
|
| 526 |
+
"learning_rate": 6.057777777777778e-05,
|
| 527 |
+
"loss": 0.0945,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.75,
|
| 532 |
+
"grad_norm": 0.0,
|
| 533 |
+
"learning_rate": 5.8355555555555565e-05,
|
| 534 |
+
"loss": 0.128,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.76,
|
| 539 |
+
"grad_norm": 0.0,
|
| 540 |
+
"learning_rate": 5.613333333333334e-05,
|
| 541 |
+
"loss": 0.0835,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.77,
|
| 546 |
+
"grad_norm": 0.0,
|
| 547 |
+
"learning_rate": 5.3911111111111115e-05,
|
| 548 |
+
"loss": 0.0689,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.78,
|
| 553 |
+
"grad_norm": 0.0,
|
| 554 |
+
"learning_rate": 5.1688888888888883e-05,
|
| 555 |
+
"loss": 0.0727,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.79,
|
| 560 |
+
"grad_norm": 0.0,
|
| 561 |
+
"learning_rate": 4.9466666666666665e-05,
|
| 562 |
+
"loss": 0.0858,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8,
|
| 567 |
+
"grad_norm": 0.0,
|
| 568 |
+
"learning_rate": 4.724444444444445e-05,
|
| 569 |
+
"loss": 0.133,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.81,
|
| 574 |
+
"grad_norm": 0.0,
|
| 575 |
+
"learning_rate": 4.502222222222223e-05,
|
| 576 |
+
"loss": 0.1415,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.82,
|
| 581 |
+
"grad_norm": 0.0,
|
| 582 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 583 |
+
"loss": 0.084,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.83,
|
| 588 |
+
"grad_norm": 0.0,
|
| 589 |
+
"learning_rate": 4.057777777777778e-05,
|
| 590 |
+
"loss": 0.0646,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.84,
|
| 595 |
+
"grad_norm": 0.0,
|
| 596 |
+
"learning_rate": 3.8355555555555553e-05,
|
| 597 |
+
"loss": 0.0846,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.85,
|
| 602 |
+
"grad_norm": 0.0,
|
| 603 |
+
"learning_rate": 3.6133333333333335e-05,
|
| 604 |
+
"loss": 0.0827,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.86,
|
| 609 |
+
"grad_norm": 0.0,
|
| 610 |
+
"learning_rate": 3.391111111111111e-05,
|
| 611 |
+
"loss": 0.0659,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.87,
|
| 616 |
+
"grad_norm": 0.0,
|
| 617 |
+
"learning_rate": 3.168888888888889e-05,
|
| 618 |
+
"loss": 0.0723,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.88,
|
| 623 |
+
"grad_norm": 0.0,
|
| 624 |
+
"learning_rate": 2.946666666666667e-05,
|
| 625 |
+
"loss": 0.0909,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.89,
|
| 630 |
+
"grad_norm": 0.0,
|
| 631 |
+
"learning_rate": 2.7244444444444445e-05,
|
| 632 |
+
"loss": 0.0962,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9,
|
| 637 |
+
"grad_norm": 0.0,
|
| 638 |
+
"learning_rate": 2.5022222222222224e-05,
|
| 639 |
+
"loss": 0.0838,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.91,
|
| 644 |
+
"grad_norm": 0.0,
|
| 645 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 646 |
+
"loss": 0.137,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.92,
|
| 651 |
+
"grad_norm": 0.0,
|
| 652 |
+
"learning_rate": 2.062222222222222e-05,
|
| 653 |
+
"loss": 0.151,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.93,
|
| 658 |
+
"grad_norm": 0.0,
|
| 659 |
+
"learning_rate": 1.84e-05,
|
| 660 |
+
"loss": 0.1,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.94,
|
| 665 |
+
"grad_norm": 0.0,
|
| 666 |
+
"learning_rate": 1.617777777777778e-05,
|
| 667 |
+
"loss": 0.0763,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.95,
|
| 672 |
+
"grad_norm": 0.0,
|
| 673 |
+
"learning_rate": 1.3955555555555555e-05,
|
| 674 |
+
"loss": 0.2048,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.96,
|
| 679 |
+
"grad_norm": 0.0,
|
| 680 |
+
"learning_rate": 1.1733333333333333e-05,
|
| 681 |
+
"loss": 0.1829,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.97,
|
| 686 |
+
"grad_norm": 0.0,
|
| 687 |
+
"learning_rate": 9.511111111111112e-06,
|
| 688 |
+
"loss": 0.1028,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.98,
|
| 693 |
+
"grad_norm": 0.0,
|
| 694 |
+
"learning_rate": 7.288888888888889e-06,
|
| 695 |
+
"loss": 0.1039,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.99,
|
| 700 |
+
"grad_norm": 0.0,
|
| 701 |
+
"learning_rate": 5.066666666666667e-06,
|
| 702 |
+
"loss": 0.0719,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0,
|
| 707 |
+
"grad_norm": 0.0,
|
| 708 |
+
"learning_rate": 2.8444444444444446e-06,
|
| 709 |
+
"loss": 0.0712,
|
| 710 |
+
"step": 5000
|
| 711 |
+
}
|
| 712 |
+
],
|
| 713 |
+
"logging_steps": 50,
|
| 714 |
+
"max_steps": 5000,
|
| 715 |
+
"num_input_tokens_seen": 0,
|
| 716 |
+
"num_train_epochs": 9223372036854775807,
|
| 717 |
+
"save_steps": 200,
|
| 718 |
+
"stateful_callbacks": {
|
| 719 |
+
"TrainerControl": {
|
| 720 |
+
"args": {
|
| 721 |
+
"should_epoch_stop": false,
|
| 722 |
+
"should_evaluate": false,
|
| 723 |
+
"should_log": false,
|
| 724 |
+
"should_save": true,
|
| 725 |
+
"should_training_stop": true
|
| 726 |
+
},
|
| 727 |
+
"attributes": {}
|
| 728 |
+
}
|
| 729 |
+
},
|
| 730 |
+
"total_flos": 5.965059712153151e+18,
|
| 731 |
+
"train_batch_size": 1,
|
| 732 |
+
"trial_name": null,
|
| 733 |
+
"trial_params": null
|
| 734 |
+
}
|
checkpoint-5000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c914d1162d969be07a28866d27b70136a6145fb226e21fdb5ca172fa8cc238d
|
| 3 |
+
size 5368
|
checkpoint-5001/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: tinkvu/wav2vec2-large-xlsr-amharic-healthcare
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:tinkvu/wav2vec2-large-xlsr-amharic-healthcare
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.18.0
|
checkpoint-5001/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "Wav2Vec2ForCTC",
|
| 7 |
+
"parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
|
| 8 |
+
},
|
| 9 |
+
"base_model_name_or_path": "tinkvu/wav2vec2-large-xlsr-amharic-healthcare",
|
| 10 |
+
"bias": "none",
|
| 11 |
+
"corda_config": null,
|
| 12 |
+
"ensure_weight_tying": false,
|
| 13 |
+
"eva_config": null,
|
| 14 |
+
"exclude_modules": null,
|
| 15 |
+
"fan_in_fan_out": false,
|
| 16 |
+
"inference_mode": true,
|
| 17 |
+
"init_lora_weights": true,
|
| 18 |
+
"layer_replication": null,
|
| 19 |
+
"layers_pattern": null,
|
| 20 |
+
"layers_to_transform": null,
|
| 21 |
+
"loftq_config": {},
|
| 22 |
+
"lora_alpha": 32,
|
| 23 |
+
"lora_bias": false,
|
| 24 |
+
"lora_dropout": 0.05,
|
| 25 |
+
"megatron_config": null,
|
| 26 |
+
"megatron_core": "megatron.core",
|
| 27 |
+
"modules_to_save": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.18.0",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"fc2",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"fc1",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"out_proj",
|
| 40 |
+
"v_proj"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": null,
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
checkpoint-5001/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b94833f7953f32ef49bc33486828f0294e6f1d4c8e21970687c840f2c832b1e0
|
| 3 |
+
size 12610664
|
checkpoint-5001/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4d8e12a90994f2184ba088e8090c659526e3b75cfe02ccca2dceac264300c7c
|
| 3 |
+
size 25327034
|
checkpoint-5001/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-5001/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e756890108a8f741a185bce7f0602c3aa17eba79f6f5512073164be496d80b2
|
| 3 |
+
size 14308
|
checkpoint-5001/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a91d19f4eff6d661e3ac8e6d859a592e95afaa30622db0085dba164eafa44de2
|
| 3 |
+
size 988
|
checkpoint-5001/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e33af232a099127febd9ad133ed35db3a358842052c8ba5d0301120dc3429f3c
|
| 3 |
+
size 1064
|
checkpoint-5001/trainer_state.json
ADDED
|
@@ -0,0 +1,734 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0002,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 5001,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01,
|
| 14 |
+
"grad_norm": 2.4969277381896973,
|
| 15 |
+
"learning_rate": 1.76e-05,
|
| 16 |
+
"loss": 19.5898,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 8.099705696105957,
|
| 22 |
+
"learning_rate": 3.76e-05,
|
| 23 |
+
"loss": 17.8223,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 11.919422149658203,
|
| 29 |
+
"learning_rate": 5.72e-05,
|
| 30 |
+
"loss": 10.8995,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 6.321387767791748,
|
| 36 |
+
"learning_rate": 7.64e-05,
|
| 37 |
+
"loss": 3.1441,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 1.5579607486724854,
|
| 43 |
+
"learning_rate": 9.64e-05,
|
| 44 |
+
"loss": 1.0788,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 2.1052896976470947,
|
| 50 |
+
"learning_rate": 0.0001164,
|
| 51 |
+
"loss": 0.3291,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07,
|
| 56 |
+
"grad_norm": 1.402535319328308,
|
| 57 |
+
"learning_rate": 0.0001364,
|
| 58 |
+
"loss": 0.3073,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08,
|
| 63 |
+
"grad_norm": 1.533136248588562,
|
| 64 |
+
"learning_rate": 0.00015600000000000002,
|
| 65 |
+
"loss": 0.4065,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09,
|
| 70 |
+
"grad_norm": 2.3747737407684326,
|
| 71 |
+
"learning_rate": 0.00017600000000000002,
|
| 72 |
+
"loss": 0.294,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1,
|
| 77 |
+
"grad_norm": 6.622051239013672,
|
| 78 |
+
"learning_rate": 0.000196,
|
| 79 |
+
"loss": 0.2311,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"grad_norm": 1.6454269886016846,
|
| 85 |
+
"learning_rate": 0.00019822222222222225,
|
| 86 |
+
"loss": 0.3515,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"grad_norm": 10.714489936828613,
|
| 92 |
+
"learning_rate": 0.000196,
|
| 93 |
+
"loss": 0.1957,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13,
|
| 98 |
+
"grad_norm": 1.3993964195251465,
|
| 99 |
+
"learning_rate": 0.0001937777777777778,
|
| 100 |
+
"loss": 0.2028,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14,
|
| 105 |
+
"grad_norm": 0.7649514675140381,
|
| 106 |
+
"learning_rate": 0.0001916,
|
| 107 |
+
"loss": 0.2995,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15,
|
| 112 |
+
"grad_norm": 0.5896079540252686,
|
| 113 |
+
"learning_rate": 0.0001893777777777778,
|
| 114 |
+
"loss": 0.1876,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16,
|
| 119 |
+
"grad_norm": 0.6604533791542053,
|
| 120 |
+
"learning_rate": 0.00018715555555555557,
|
| 121 |
+
"loss": 0.19,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"grad_norm": 2.047614097595215,
|
| 127 |
+
"learning_rate": 0.00018493333333333335,
|
| 128 |
+
"loss": 0.0988,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"grad_norm": 1.374024748802185,
|
| 134 |
+
"learning_rate": 0.00018271111111111112,
|
| 135 |
+
"loss": 0.1355,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.19,
|
| 140 |
+
"grad_norm": 1.4950742721557617,
|
| 141 |
+
"learning_rate": 0.0001804888888888889,
|
| 142 |
+
"loss": 0.1303,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2,
|
| 147 |
+
"grad_norm": 2.006479024887085,
|
| 148 |
+
"learning_rate": 0.00017826666666666667,
|
| 149 |
+
"loss": 0.1999,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.21,
|
| 154 |
+
"grad_norm": 1.1253306865692139,
|
| 155 |
+
"learning_rate": 0.00017604444444444445,
|
| 156 |
+
"loss": 0.152,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.22,
|
| 161 |
+
"grad_norm": 0.8224861025810242,
|
| 162 |
+
"learning_rate": 0.00017382222222222222,
|
| 163 |
+
"loss": 0.1444,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23,
|
| 168 |
+
"grad_norm": 0.523875892162323,
|
| 169 |
+
"learning_rate": 0.0001716,
|
| 170 |
+
"loss": 0.155,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"grad_norm": 1.7560786008834839,
|
| 176 |
+
"learning_rate": 0.0001693777777777778,
|
| 177 |
+
"loss": 0.1934,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 0.6891859173774719,
|
| 183 |
+
"learning_rate": 0.00016715555555555555,
|
| 184 |
+
"loss": 0.1062,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.26,
|
| 189 |
+
"grad_norm": 3.0257561206817627,
|
| 190 |
+
"learning_rate": 0.00016493333333333335,
|
| 191 |
+
"loss": 0.1132,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.27,
|
| 196 |
+
"grad_norm": 0.0,
|
| 197 |
+
"learning_rate": 0.00016351111111111112,
|
| 198 |
+
"loss": 0.3971,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.28,
|
| 203 |
+
"grad_norm": 0.0,
|
| 204 |
+
"learning_rate": 0.0001612888888888889,
|
| 205 |
+
"loss": 0.2656,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29,
|
| 210 |
+
"grad_norm": 0.0,
|
| 211 |
+
"learning_rate": 0.00015924444444444447,
|
| 212 |
+
"loss": 0.4477,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"grad_norm": 0.0,
|
| 218 |
+
"learning_rate": 0.00015706666666666667,
|
| 219 |
+
"loss": 0.3441,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.31,
|
| 224 |
+
"grad_norm": 0.0,
|
| 225 |
+
"learning_rate": 0.00015484444444444445,
|
| 226 |
+
"loss": 0.1985,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.32,
|
| 231 |
+
"grad_norm": 0.0,
|
| 232 |
+
"learning_rate": 0.00015262222222222222,
|
| 233 |
+
"loss": 0.2074,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.33,
|
| 238 |
+
"grad_norm": 0.0,
|
| 239 |
+
"learning_rate": 0.00015066666666666668,
|
| 240 |
+
"loss": 0.481,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.34,
|
| 245 |
+
"grad_norm": 0.0,
|
| 246 |
+
"learning_rate": 0.00014857777777777778,
|
| 247 |
+
"loss": 0.2268,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.35,
|
| 252 |
+
"grad_norm": 0.0,
|
| 253 |
+
"learning_rate": 0.00014635555555555556,
|
| 254 |
+
"loss": 0.1873,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"grad_norm": 0.0,
|
| 260 |
+
"learning_rate": 0.00014413333333333333,
|
| 261 |
+
"loss": 0.2051,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.37,
|
| 266 |
+
"grad_norm": 0.0,
|
| 267 |
+
"learning_rate": 0.00014191111111111113,
|
| 268 |
+
"loss": 0.2184,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.38,
|
| 273 |
+
"grad_norm": 0.0,
|
| 274 |
+
"learning_rate": 0.00013968888888888888,
|
| 275 |
+
"loss": 0.112,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.39,
|
| 280 |
+
"grad_norm": 0.0,
|
| 281 |
+
"learning_rate": 0.00013751111111111113,
|
| 282 |
+
"loss": 0.2867,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4,
|
| 287 |
+
"grad_norm": 0.0,
|
| 288 |
+
"learning_rate": 0.00013528888888888888,
|
| 289 |
+
"loss": 0.1132,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.41,
|
| 294 |
+
"grad_norm": 0.0,
|
| 295 |
+
"learning_rate": 0.00013306666666666668,
|
| 296 |
+
"loss": 0.2804,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"grad_norm": 0.0,
|
| 302 |
+
"learning_rate": 0.00013084444444444446,
|
| 303 |
+
"loss": 0.1317,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.43,
|
| 308 |
+
"grad_norm": 0.0,
|
| 309 |
+
"learning_rate": 0.00012862222222222223,
|
| 310 |
+
"loss": 0.1032,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.44,
|
| 315 |
+
"grad_norm": 0.0,
|
| 316 |
+
"learning_rate": 0.0001264,
|
| 317 |
+
"loss": 0.1184,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.45,
|
| 322 |
+
"grad_norm": 0.0,
|
| 323 |
+
"learning_rate": 0.00012417777777777778,
|
| 324 |
+
"loss": 0.1207,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.46,
|
| 329 |
+
"grad_norm": 0.0,
|
| 330 |
+
"learning_rate": 0.00012195555555555556,
|
| 331 |
+
"loss": 0.1269,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.47,
|
| 336 |
+
"grad_norm": 0.0,
|
| 337 |
+
"learning_rate": 0.00011973333333333335,
|
| 338 |
+
"loss": 0.1391,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"grad_norm": 0.0,
|
| 344 |
+
"learning_rate": 0.00011773333333333334,
|
| 345 |
+
"loss": 0.2337,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49,
|
| 350 |
+
"grad_norm": 0.0,
|
| 351 |
+
"learning_rate": 0.00011586666666666667,
|
| 352 |
+
"loss": 0.3983,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5,
|
| 357 |
+
"grad_norm": 0.0,
|
| 358 |
+
"learning_rate": 0.00011373333333333334,
|
| 359 |
+
"loss": 0.1904,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.51,
|
| 364 |
+
"grad_norm": 0.0,
|
| 365 |
+
"learning_rate": 0.00011160000000000002,
|
| 366 |
+
"loss": 0.2106,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.52,
|
| 371 |
+
"grad_norm": 0.0,
|
| 372 |
+
"learning_rate": 0.00010942222222222223,
|
| 373 |
+
"loss": 0.1193,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.53,
|
| 378 |
+
"grad_norm": 0.0,
|
| 379 |
+
"learning_rate": 0.00010720000000000002,
|
| 380 |
+
"loss": 0.1406,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.54,
|
| 385 |
+
"grad_norm": 0.0,
|
| 386 |
+
"learning_rate": 0.00010497777777777778,
|
| 387 |
+
"loss": 0.1312,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.55,
|
| 392 |
+
"grad_norm": 0.0,
|
| 393 |
+
"learning_rate": 0.00010275555555555557,
|
| 394 |
+
"loss": 0.1193,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.56,
|
| 399 |
+
"grad_norm": 0.0,
|
| 400 |
+
"learning_rate": 0.00010053333333333334,
|
| 401 |
+
"loss": 0.1838,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.57,
|
| 406 |
+
"grad_norm": 0.0,
|
| 407 |
+
"learning_rate": 9.831111111111112e-05,
|
| 408 |
+
"loss": 0.1306,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.58,
|
| 413 |
+
"grad_norm": 0.0,
|
| 414 |
+
"learning_rate": 9.608888888888889e-05,
|
| 415 |
+
"loss": 0.1127,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.59,
|
| 420 |
+
"grad_norm": 0.0,
|
| 421 |
+
"learning_rate": 9.386666666666667e-05,
|
| 422 |
+
"loss": 0.1963,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6,
|
| 427 |
+
"grad_norm": 0.0,
|
| 428 |
+
"learning_rate": 9.164444444444444e-05,
|
| 429 |
+
"loss": 0.1813,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.61,
|
| 434 |
+
"grad_norm": 0.0,
|
| 435 |
+
"learning_rate": 8.942222222222223e-05,
|
| 436 |
+
"loss": 0.2901,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.62,
|
| 441 |
+
"grad_norm": 0.0,
|
| 442 |
+
"learning_rate": 8.72e-05,
|
| 443 |
+
"loss": 0.0905,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.63,
|
| 448 |
+
"grad_norm": 0.0,
|
| 449 |
+
"learning_rate": 8.497777777777778e-05,
|
| 450 |
+
"loss": 0.1058,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.64,
|
| 455 |
+
"grad_norm": 0.0,
|
| 456 |
+
"learning_rate": 8.275555555555557e-05,
|
| 457 |
+
"loss": 0.0965,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.65,
|
| 462 |
+
"grad_norm": 0.0,
|
| 463 |
+
"learning_rate": 8.053333333333334e-05,
|
| 464 |
+
"loss": 0.0936,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.66,
|
| 469 |
+
"grad_norm": 0.0,
|
| 470 |
+
"learning_rate": 7.831111111111112e-05,
|
| 471 |
+
"loss": 0.1093,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.67,
|
| 476 |
+
"grad_norm": 0.0,
|
| 477 |
+
"learning_rate": 7.613333333333333e-05,
|
| 478 |
+
"loss": 0.1311,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.68,
|
| 483 |
+
"grad_norm": 0.0,
|
| 484 |
+
"learning_rate": 7.391111111111112e-05,
|
| 485 |
+
"loss": 0.1027,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.69,
|
| 490 |
+
"grad_norm": 0.0,
|
| 491 |
+
"learning_rate": 7.16888888888889e-05,
|
| 492 |
+
"loss": 0.0657,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7,
|
| 497 |
+
"grad_norm": 0.0,
|
| 498 |
+
"learning_rate": 6.946666666666667e-05,
|
| 499 |
+
"loss": 0.0836,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.71,
|
| 504 |
+
"grad_norm": 0.0,
|
| 505 |
+
"learning_rate": 6.724444444444445e-05,
|
| 506 |
+
"loss": 0.0843,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.72,
|
| 511 |
+
"grad_norm": 0.0,
|
| 512 |
+
"learning_rate": 6.502222222222223e-05,
|
| 513 |
+
"loss": 0.0796,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.73,
|
| 518 |
+
"grad_norm": 0.0,
|
| 519 |
+
"learning_rate": 6.280000000000001e-05,
|
| 520 |
+
"loss": 0.0975,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.74,
|
| 525 |
+
"grad_norm": 0.0,
|
| 526 |
+
"learning_rate": 6.057777777777778e-05,
|
| 527 |
+
"loss": 0.0945,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.75,
|
| 532 |
+
"grad_norm": 0.0,
|
| 533 |
+
"learning_rate": 5.8355555555555565e-05,
|
| 534 |
+
"loss": 0.128,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.76,
|
| 539 |
+
"grad_norm": 0.0,
|
| 540 |
+
"learning_rate": 5.613333333333334e-05,
|
| 541 |
+
"loss": 0.0835,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.77,
|
| 546 |
+
"grad_norm": 0.0,
|
| 547 |
+
"learning_rate": 5.3911111111111115e-05,
|
| 548 |
+
"loss": 0.0689,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.78,
|
| 553 |
+
"grad_norm": 0.0,
|
| 554 |
+
"learning_rate": 5.1688888888888883e-05,
|
| 555 |
+
"loss": 0.0727,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.79,
|
| 560 |
+
"grad_norm": 0.0,
|
| 561 |
+
"learning_rate": 4.9466666666666665e-05,
|
| 562 |
+
"loss": 0.0858,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8,
|
| 567 |
+
"grad_norm": 0.0,
|
| 568 |
+
"learning_rate": 4.724444444444445e-05,
|
| 569 |
+
"loss": 0.133,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.81,
|
| 574 |
+
"grad_norm": 0.0,
|
| 575 |
+
"learning_rate": 4.502222222222223e-05,
|
| 576 |
+
"loss": 0.1415,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.82,
|
| 581 |
+
"grad_norm": 0.0,
|
| 582 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 583 |
+
"loss": 0.084,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.83,
|
| 588 |
+
"grad_norm": 0.0,
|
| 589 |
+
"learning_rate": 4.057777777777778e-05,
|
| 590 |
+
"loss": 0.0646,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.84,
|
| 595 |
+
"grad_norm": 0.0,
|
| 596 |
+
"learning_rate": 3.8355555555555553e-05,
|
| 597 |
+
"loss": 0.0846,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.85,
|
| 602 |
+
"grad_norm": 0.0,
|
| 603 |
+
"learning_rate": 3.6133333333333335e-05,
|
| 604 |
+
"loss": 0.0827,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.86,
|
| 609 |
+
"grad_norm": 0.0,
|
| 610 |
+
"learning_rate": 3.391111111111111e-05,
|
| 611 |
+
"loss": 0.0659,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.87,
|
| 616 |
+
"grad_norm": 0.0,
|
| 617 |
+
"learning_rate": 3.168888888888889e-05,
|
| 618 |
+
"loss": 0.0723,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.88,
|
| 623 |
+
"grad_norm": 0.0,
|
| 624 |
+
"learning_rate": 2.946666666666667e-05,
|
| 625 |
+
"loss": 0.0909,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.89,
|
| 630 |
+
"grad_norm": 0.0,
|
| 631 |
+
"learning_rate": 2.7244444444444445e-05,
|
| 632 |
+
"loss": 0.0962,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9,
|
| 637 |
+
"grad_norm": 0.0,
|
| 638 |
+
"learning_rate": 2.5022222222222224e-05,
|
| 639 |
+
"loss": 0.0838,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.91,
|
| 644 |
+
"grad_norm": 0.0,
|
| 645 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 646 |
+
"loss": 0.137,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.92,
|
| 651 |
+
"grad_norm": 0.0,
|
| 652 |
+
"learning_rate": 2.062222222222222e-05,
|
| 653 |
+
"loss": 0.151,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.93,
|
| 658 |
+
"grad_norm": 0.0,
|
| 659 |
+
"learning_rate": 1.84e-05,
|
| 660 |
+
"loss": 0.1,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.94,
|
| 665 |
+
"grad_norm": 0.0,
|
| 666 |
+
"learning_rate": 1.617777777777778e-05,
|
| 667 |
+
"loss": 0.0763,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.95,
|
| 672 |
+
"grad_norm": 0.0,
|
| 673 |
+
"learning_rate": 1.3955555555555555e-05,
|
| 674 |
+
"loss": 0.2048,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.96,
|
| 679 |
+
"grad_norm": 0.0,
|
| 680 |
+
"learning_rate": 1.1733333333333333e-05,
|
| 681 |
+
"loss": 0.1829,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.97,
|
| 686 |
+
"grad_norm": 0.0,
|
| 687 |
+
"learning_rate": 9.511111111111112e-06,
|
| 688 |
+
"loss": 0.1028,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.98,
|
| 693 |
+
"grad_norm": 0.0,
|
| 694 |
+
"learning_rate": 7.288888888888889e-06,
|
| 695 |
+
"loss": 0.1039,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.99,
|
| 700 |
+
"grad_norm": 0.0,
|
| 701 |
+
"learning_rate": 5.066666666666667e-06,
|
| 702 |
+
"loss": 0.0719,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0,
|
| 707 |
+
"grad_norm": 0.0,
|
| 708 |
+
"learning_rate": 2.8444444444444446e-06,
|
| 709 |
+
"loss": 0.0712,
|
| 710 |
+
"step": 5000
|
| 711 |
+
}
|
| 712 |
+
],
|
| 713 |
+
"logging_steps": 50,
|
| 714 |
+
"max_steps": 5000,
|
| 715 |
+
"num_input_tokens_seen": 0,
|
| 716 |
+
"num_train_epochs": 9223372036854775807,
|
| 717 |
+
"save_steps": 200,
|
| 718 |
+
"stateful_callbacks": {
|
| 719 |
+
"TrainerControl": {
|
| 720 |
+
"args": {
|
| 721 |
+
"should_epoch_stop": false,
|
| 722 |
+
"should_evaluate": false,
|
| 723 |
+
"should_log": false,
|
| 724 |
+
"should_save": true,
|
| 725 |
+
"should_training_stop": true
|
| 726 |
+
},
|
| 727 |
+
"attributes": {}
|
| 728 |
+
}
|
| 729 |
+
},
|
| 730 |
+
"total_flos": 5.966293791739906e+18,
|
| 731 |
+
"train_batch_size": 1,
|
| 732 |
+
"trial_name": null,
|
| 733 |
+
"trial_params": null
|
| 734 |
+
}
|
checkpoint-5001/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6750694c4eac2ee8f68ff96dd2d091aa195827faf50bac6fb6d68217a85c7a5e
|
| 3 |
+
size 5368
|