Upload folder using huggingface_hub
Browse files- checkpoint-11500/README.md +202 -0
- checkpoint-11500/adapter_config.json +29 -0
- checkpoint-11500/adapter_model.safetensors +3 -0
- checkpoint-11500/optimizer.pt +3 -0
- checkpoint-11500/rng_state.pth +3 -0
- checkpoint-11500/scheduler.pt +3 -0
- checkpoint-11500/trainer_state.json +854 -0
- checkpoint-11500/training_args.bin +3 -0
- checkpoint-12000/README.md +202 -0
- checkpoint-12000/adapter_config.json +29 -0
- checkpoint-12000/adapter_model.safetensors +3 -0
- checkpoint-12000/optimizer.pt +3 -0
- checkpoint-12000/rng_state.pth +3 -0
- checkpoint-12000/scheduler.pt +3 -0
- checkpoint-12000/trainer_state.json +889 -0
- checkpoint-12000/training_args.bin +3 -0
checkpoint-11500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: HuggingFaceTB/SmolLM2-135M
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
checkpoint-11500/adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
checkpoint-11500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3485375d79f5262e1be98bf7f7535292ae8ca59e2030c48512365d1c6ef0321
|
| 3 |
+
size 3702168
|
checkpoint-11500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef4a19811929d27023acaf3740856fd3556c392c8f16563332be230d78b36747
|
| 3 |
+
size 7473658
|
checkpoint-11500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63abaa6a9a4d63fe25da5196438ef04054105daf8d37994164c777f9cf9cd6eb
|
| 3 |
+
size 14244
|
checkpoint-11500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b92ff34f57c8bd696c4446e5b8e3000ded93ede6917f5ca7dca792504cbe262c
|
| 3 |
+
size 1064
|
checkpoint-11500/trainer_state.json
ADDED
|
@@ -0,0 +1,854 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.875,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.025,
|
| 13 |
+
"grad_norm": 0.2082100212574005,
|
| 14 |
+
"learning_rate": 0.0004958333333333334,
|
| 15 |
+
"loss": 1.3502,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 0.1778642237186432,
|
| 21 |
+
"learning_rate": 0.0004916666666666666,
|
| 22 |
+
"loss": 1.1649,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.075,
|
| 27 |
+
"grad_norm": 0.2463778257369995,
|
| 28 |
+
"learning_rate": 0.0004875,
|
| 29 |
+
"loss": 1.1395,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1,
|
| 34 |
+
"grad_norm": 0.20819446444511414,
|
| 35 |
+
"learning_rate": 0.00048333333333333334,
|
| 36 |
+
"loss": 1.1056,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.125,
|
| 41 |
+
"grad_norm": 0.23243966698646545,
|
| 42 |
+
"learning_rate": 0.0004791666666666667,
|
| 43 |
+
"loss": 1.1329,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"grad_norm": 0.19812804460525513,
|
| 49 |
+
"learning_rate": 0.000475,
|
| 50 |
+
"loss": 1.1169,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.175,
|
| 55 |
+
"grad_norm": 0.2258671671152115,
|
| 56 |
+
"learning_rate": 0.00047083333333333336,
|
| 57 |
+
"loss": 1.1318,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"grad_norm": 0.20714746415615082,
|
| 63 |
+
"learning_rate": 0.00046666666666666666,
|
| 64 |
+
"loss": 1.114,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.225,
|
| 69 |
+
"grad_norm": 0.22002336382865906,
|
| 70 |
+
"learning_rate": 0.0004625,
|
| 71 |
+
"loss": 1.1269,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.25,
|
| 76 |
+
"grad_norm": 0.2159491330385208,
|
| 77 |
+
"learning_rate": 0.0004583333333333333,
|
| 78 |
+
"loss": 1.0694,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.275,
|
| 83 |
+
"grad_norm": 0.20638039708137512,
|
| 84 |
+
"learning_rate": 0.0004541666666666667,
|
| 85 |
+
"loss": 1.0929,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"grad_norm": 0.2234920710325241,
|
| 91 |
+
"learning_rate": 0.00045000000000000004,
|
| 92 |
+
"loss": 1.0903,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.325,
|
| 97 |
+
"grad_norm": 0.23063984513282776,
|
| 98 |
+
"learning_rate": 0.00044583333333333335,
|
| 99 |
+
"loss": 1.095,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.35,
|
| 104 |
+
"grad_norm": 0.221044659614563,
|
| 105 |
+
"learning_rate": 0.00044166666666666665,
|
| 106 |
+
"loss": 1.0859,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.375,
|
| 111 |
+
"grad_norm": 0.19685755670070648,
|
| 112 |
+
"learning_rate": 0.0004375,
|
| 113 |
+
"loss": 1.0643,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4,
|
| 118 |
+
"grad_norm": 0.2428029328584671,
|
| 119 |
+
"learning_rate": 0.00043333333333333337,
|
| 120 |
+
"loss": 1.0715,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.425,
|
| 125 |
+
"grad_norm": 0.21401169896125793,
|
| 126 |
+
"learning_rate": 0.00042916666666666667,
|
| 127 |
+
"loss": 1.0821,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45,
|
| 132 |
+
"grad_norm": 0.23752962052822113,
|
| 133 |
+
"learning_rate": 0.000425,
|
| 134 |
+
"loss": 1.0936,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.475,
|
| 139 |
+
"grad_norm": 0.23333564400672913,
|
| 140 |
+
"learning_rate": 0.00042083333333333333,
|
| 141 |
+
"loss": 1.0842,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5,
|
| 146 |
+
"grad_norm": 0.2038385421037674,
|
| 147 |
+
"learning_rate": 0.0004166666666666667,
|
| 148 |
+
"loss": 1.0831,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.525,
|
| 153 |
+
"grad_norm": 0.24392388761043549,
|
| 154 |
+
"learning_rate": 0.0004125,
|
| 155 |
+
"loss": 1.069,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.55,
|
| 160 |
+
"grad_norm": 0.2810049057006836,
|
| 161 |
+
"learning_rate": 0.00040833333333333336,
|
| 162 |
+
"loss": 1.0649,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.575,
|
| 167 |
+
"grad_norm": 0.24431484937667847,
|
| 168 |
+
"learning_rate": 0.00040416666666666666,
|
| 169 |
+
"loss": 1.0955,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6,
|
| 174 |
+
"grad_norm": 0.2268693745136261,
|
| 175 |
+
"learning_rate": 0.0004,
|
| 176 |
+
"loss": 1.0639,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.625,
|
| 181 |
+
"grad_norm": 0.22379685938358307,
|
| 182 |
+
"learning_rate": 0.0003958333333333333,
|
| 183 |
+
"loss": 1.0864,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.65,
|
| 188 |
+
"grad_norm": 0.22857442498207092,
|
| 189 |
+
"learning_rate": 0.0003916666666666667,
|
| 190 |
+
"loss": 1.0895,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.675,
|
| 195 |
+
"grad_norm": 0.22649641335010529,
|
| 196 |
+
"learning_rate": 0.00038750000000000004,
|
| 197 |
+
"loss": 1.0656,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7,
|
| 202 |
+
"grad_norm": 0.2611943185329437,
|
| 203 |
+
"learning_rate": 0.00038333333333333334,
|
| 204 |
+
"loss": 1.0492,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.725,
|
| 209 |
+
"grad_norm": 0.2599722743034363,
|
| 210 |
+
"learning_rate": 0.00037916666666666665,
|
| 211 |
+
"loss": 1.0639,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.75,
|
| 216 |
+
"grad_norm": 0.2554958462715149,
|
| 217 |
+
"learning_rate": 0.000375,
|
| 218 |
+
"loss": 1.0592,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.775,
|
| 223 |
+
"grad_norm": 0.262107789516449,
|
| 224 |
+
"learning_rate": 0.00037083333333333337,
|
| 225 |
+
"loss": 1.0458,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8,
|
| 230 |
+
"grad_norm": 0.23872502148151398,
|
| 231 |
+
"learning_rate": 0.00036666666666666667,
|
| 232 |
+
"loss": 1.0479,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.825,
|
| 237 |
+
"grad_norm": 0.2865801155567169,
|
| 238 |
+
"learning_rate": 0.0003625,
|
| 239 |
+
"loss": 1.0421,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.85,
|
| 244 |
+
"grad_norm": 0.2661890685558319,
|
| 245 |
+
"learning_rate": 0.00035833333333333333,
|
| 246 |
+
"loss": 1.0653,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.875,
|
| 251 |
+
"grad_norm": 0.25706493854522705,
|
| 252 |
+
"learning_rate": 0.0003541666666666667,
|
| 253 |
+
"loss": 1.057,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9,
|
| 258 |
+
"grad_norm": 0.25889962911605835,
|
| 259 |
+
"learning_rate": 0.00035,
|
| 260 |
+
"loss": 1.0435,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.925,
|
| 265 |
+
"grad_norm": 0.28601542115211487,
|
| 266 |
+
"learning_rate": 0.00034583333333333335,
|
| 267 |
+
"loss": 1.0564,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.95,
|
| 272 |
+
"grad_norm": 0.2556051015853882,
|
| 273 |
+
"learning_rate": 0.00034166666666666666,
|
| 274 |
+
"loss": 1.0354,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.975,
|
| 279 |
+
"grad_norm": 0.259920597076416,
|
| 280 |
+
"learning_rate": 0.0003375,
|
| 281 |
+
"loss": 1.0617,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.0,
|
| 286 |
+
"grad_norm": 0.26773035526275635,
|
| 287 |
+
"learning_rate": 0.0003333333333333333,
|
| 288 |
+
"loss": 1.0162,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.0,
|
| 293 |
+
"eval_loss": 1.041967749595642,
|
| 294 |
+
"eval_runtime": 70.7784,
|
| 295 |
+
"eval_samples_per_second": 56.514,
|
| 296 |
+
"eval_steps_per_second": 14.129,
|
| 297 |
+
"step": 4000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.025,
|
| 301 |
+
"grad_norm": 0.27995696663856506,
|
| 302 |
+
"learning_rate": 0.0003291666666666667,
|
| 303 |
+
"loss": 1.0294,
|
| 304 |
+
"step": 4100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.05,
|
| 308 |
+
"grad_norm": 0.26720207929611206,
|
| 309 |
+
"learning_rate": 0.00032500000000000004,
|
| 310 |
+
"loss": 1.0201,
|
| 311 |
+
"step": 4200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.075,
|
| 315 |
+
"grad_norm": 0.26933032274246216,
|
| 316 |
+
"learning_rate": 0.00032083333333333334,
|
| 317 |
+
"loss": 1.0337,
|
| 318 |
+
"step": 4300
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1,
|
| 322 |
+
"grad_norm": 0.2675634026527405,
|
| 323 |
+
"learning_rate": 0.00031666666666666665,
|
| 324 |
+
"loss": 1.0204,
|
| 325 |
+
"step": 4400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.125,
|
| 329 |
+
"grad_norm": 0.29779279232025146,
|
| 330 |
+
"learning_rate": 0.0003125,
|
| 331 |
+
"loss": 1.0116,
|
| 332 |
+
"step": 4500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.15,
|
| 336 |
+
"grad_norm": 0.2576355040073395,
|
| 337 |
+
"learning_rate": 0.00030833333333333337,
|
| 338 |
+
"loss": 1.0422,
|
| 339 |
+
"step": 4600
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.175,
|
| 343 |
+
"grad_norm": 0.26360246539115906,
|
| 344 |
+
"learning_rate": 0.00030416666666666667,
|
| 345 |
+
"loss": 1.0304,
|
| 346 |
+
"step": 4700
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2,
|
| 350 |
+
"grad_norm": 0.2623592019081116,
|
| 351 |
+
"learning_rate": 0.0003,
|
| 352 |
+
"loss": 1.0344,
|
| 353 |
+
"step": 4800
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.225,
|
| 357 |
+
"grad_norm": 0.2560625970363617,
|
| 358 |
+
"learning_rate": 0.00029583333333333333,
|
| 359 |
+
"loss": 1.0323,
|
| 360 |
+
"step": 4900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.25,
|
| 364 |
+
"grad_norm": 0.27826786041259766,
|
| 365 |
+
"learning_rate": 0.0002916666666666667,
|
| 366 |
+
"loss": 1.0147,
|
| 367 |
+
"step": 5000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.275,
|
| 371 |
+
"grad_norm": 0.26778700947761536,
|
| 372 |
+
"learning_rate": 0.0002875,
|
| 373 |
+
"loss": 1.0212,
|
| 374 |
+
"step": 5100
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3,
|
| 378 |
+
"grad_norm": 0.2655790150165558,
|
| 379 |
+
"learning_rate": 0.00028333333333333335,
|
| 380 |
+
"loss": 1.0429,
|
| 381 |
+
"step": 5200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.325,
|
| 385 |
+
"grad_norm": 0.23913314938545227,
|
| 386 |
+
"learning_rate": 0.00027916666666666666,
|
| 387 |
+
"loss": 1.0093,
|
| 388 |
+
"step": 5300
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.35,
|
| 392 |
+
"grad_norm": 0.25580066442489624,
|
| 393 |
+
"learning_rate": 0.000275,
|
| 394 |
+
"loss": 1.0157,
|
| 395 |
+
"step": 5400
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.375,
|
| 399 |
+
"grad_norm": 0.3255338966846466,
|
| 400 |
+
"learning_rate": 0.0002708333333333333,
|
| 401 |
+
"loss": 1.0291,
|
| 402 |
+
"step": 5500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4,
|
| 406 |
+
"grad_norm": 0.2690030634403229,
|
| 407 |
+
"learning_rate": 0.0002666666666666667,
|
| 408 |
+
"loss": 1.0428,
|
| 409 |
+
"step": 5600
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.425,
|
| 413 |
+
"grad_norm": 0.2967054843902588,
|
| 414 |
+
"learning_rate": 0.00026250000000000004,
|
| 415 |
+
"loss": 1.0077,
|
| 416 |
+
"step": 5700
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.45,
|
| 420 |
+
"grad_norm": 0.26981931924819946,
|
| 421 |
+
"learning_rate": 0.00025833333333333334,
|
| 422 |
+
"loss": 1.022,
|
| 423 |
+
"step": 5800
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.475,
|
| 427 |
+
"grad_norm": 0.29188498854637146,
|
| 428 |
+
"learning_rate": 0.00025416666666666665,
|
| 429 |
+
"loss": 1.0317,
|
| 430 |
+
"step": 5900
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.5,
|
| 434 |
+
"grad_norm": 0.26391416788101196,
|
| 435 |
+
"learning_rate": 0.00025,
|
| 436 |
+
"loss": 1.0311,
|
| 437 |
+
"step": 6000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.525,
|
| 441 |
+
"grad_norm": 0.2949013113975525,
|
| 442 |
+
"learning_rate": 0.0002458333333333333,
|
| 443 |
+
"loss": 0.998,
|
| 444 |
+
"step": 6100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.55,
|
| 448 |
+
"grad_norm": 0.25229978561401367,
|
| 449 |
+
"learning_rate": 0.00024166666666666667,
|
| 450 |
+
"loss": 1.0241,
|
| 451 |
+
"step": 6200
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.575,
|
| 455 |
+
"grad_norm": 0.2736811637878418,
|
| 456 |
+
"learning_rate": 0.0002375,
|
| 457 |
+
"loss": 1.0214,
|
| 458 |
+
"step": 6300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.6,
|
| 462 |
+
"grad_norm": 0.31093525886535645,
|
| 463 |
+
"learning_rate": 0.00023333333333333333,
|
| 464 |
+
"loss": 0.9709,
|
| 465 |
+
"step": 6400
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.625,
|
| 469 |
+
"grad_norm": 0.32644134759902954,
|
| 470 |
+
"learning_rate": 0.00022916666666666666,
|
| 471 |
+
"loss": 1.003,
|
| 472 |
+
"step": 6500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.65,
|
| 476 |
+
"grad_norm": 0.29749053716659546,
|
| 477 |
+
"learning_rate": 0.00022500000000000002,
|
| 478 |
+
"loss": 0.9985,
|
| 479 |
+
"step": 6600
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.675,
|
| 483 |
+
"grad_norm": 0.27901262044906616,
|
| 484 |
+
"learning_rate": 0.00022083333333333333,
|
| 485 |
+
"loss": 1.0096,
|
| 486 |
+
"step": 6700
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7,
|
| 490 |
+
"grad_norm": 0.32841789722442627,
|
| 491 |
+
"learning_rate": 0.00021666666666666668,
|
| 492 |
+
"loss": 1.0007,
|
| 493 |
+
"step": 6800
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.725,
|
| 497 |
+
"grad_norm": 0.30320826172828674,
|
| 498 |
+
"learning_rate": 0.0002125,
|
| 499 |
+
"loss": 1.0326,
|
| 500 |
+
"step": 6900
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.75,
|
| 504 |
+
"grad_norm": 0.2965095639228821,
|
| 505 |
+
"learning_rate": 0.00020833333333333335,
|
| 506 |
+
"loss": 1.0028,
|
| 507 |
+
"step": 7000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.775,
|
| 511 |
+
"grad_norm": 0.31121572852134705,
|
| 512 |
+
"learning_rate": 0.00020416666666666668,
|
| 513 |
+
"loss": 0.9839,
|
| 514 |
+
"step": 7100
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.8,
|
| 518 |
+
"grad_norm": 0.2947477698326111,
|
| 519 |
+
"learning_rate": 0.0002,
|
| 520 |
+
"loss": 0.9841,
|
| 521 |
+
"step": 7200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.825,
|
| 525 |
+
"grad_norm": 0.2830908000469208,
|
| 526 |
+
"learning_rate": 0.00019583333333333334,
|
| 527 |
+
"loss": 1.0089,
|
| 528 |
+
"step": 7300
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.85,
|
| 532 |
+
"grad_norm": 0.29144686460494995,
|
| 533 |
+
"learning_rate": 0.00019166666666666667,
|
| 534 |
+
"loss": 1.0038,
|
| 535 |
+
"step": 7400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.875,
|
| 539 |
+
"grad_norm": 0.2925328016281128,
|
| 540 |
+
"learning_rate": 0.0001875,
|
| 541 |
+
"loss": 1.003,
|
| 542 |
+
"step": 7500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.9,
|
| 546 |
+
"grad_norm": 0.3474633991718292,
|
| 547 |
+
"learning_rate": 0.00018333333333333334,
|
| 548 |
+
"loss": 1.0265,
|
| 549 |
+
"step": 7600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.925,
|
| 553 |
+
"grad_norm": 0.2939680814743042,
|
| 554 |
+
"learning_rate": 0.00017916666666666667,
|
| 555 |
+
"loss": 1.0145,
|
| 556 |
+
"step": 7700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.95,
|
| 560 |
+
"grad_norm": 0.2775793969631195,
|
| 561 |
+
"learning_rate": 0.000175,
|
| 562 |
+
"loss": 0.9977,
|
| 563 |
+
"step": 7800
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.975,
|
| 567 |
+
"grad_norm": 0.3091006577014923,
|
| 568 |
+
"learning_rate": 0.00017083333333333333,
|
| 569 |
+
"loss": 1.0255,
|
| 570 |
+
"step": 7900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0,
|
| 574 |
+
"grad_norm": 0.32153698801994324,
|
| 575 |
+
"learning_rate": 0.00016666666666666666,
|
| 576 |
+
"loss": 1.0262,
|
| 577 |
+
"step": 8000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.0,
|
| 581 |
+
"eval_loss": 1.0134142637252808,
|
| 582 |
+
"eval_runtime": 71.1474,
|
| 583 |
+
"eval_samples_per_second": 56.221,
|
| 584 |
+
"eval_steps_per_second": 14.055,
|
| 585 |
+
"step": 8000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.025,
|
| 589 |
+
"grad_norm": 0.31311318278312683,
|
| 590 |
+
"learning_rate": 0.00016250000000000002,
|
| 591 |
+
"loss": 1.0097,
|
| 592 |
+
"step": 8100
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.05,
|
| 596 |
+
"grad_norm": 0.308938205242157,
|
| 597 |
+
"learning_rate": 0.00015833333333333332,
|
| 598 |
+
"loss": 0.9912,
|
| 599 |
+
"step": 8200
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.075,
|
| 603 |
+
"grad_norm": 0.29837608337402344,
|
| 604 |
+
"learning_rate": 0.00015416666666666668,
|
| 605 |
+
"loss": 0.9945,
|
| 606 |
+
"step": 8300
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.1,
|
| 610 |
+
"grad_norm": 0.29206210374832153,
|
| 611 |
+
"learning_rate": 0.00015,
|
| 612 |
+
"loss": 0.9608,
|
| 613 |
+
"step": 8400
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.125,
|
| 617 |
+
"grad_norm": 0.29734155535697937,
|
| 618 |
+
"learning_rate": 0.00014583333333333335,
|
| 619 |
+
"loss": 1.0005,
|
| 620 |
+
"step": 8500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.15,
|
| 624 |
+
"grad_norm": 0.31197240948677063,
|
| 625 |
+
"learning_rate": 0.00014166666666666668,
|
| 626 |
+
"loss": 0.9936,
|
| 627 |
+
"step": 8600
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.175,
|
| 631 |
+
"grad_norm": 0.3193836808204651,
|
| 632 |
+
"learning_rate": 0.0001375,
|
| 633 |
+
"loss": 1.0125,
|
| 634 |
+
"step": 8700
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.2,
|
| 638 |
+
"grad_norm": 0.29876908659935,
|
| 639 |
+
"learning_rate": 0.00013333333333333334,
|
| 640 |
+
"loss": 1.0084,
|
| 641 |
+
"step": 8800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.225,
|
| 645 |
+
"grad_norm": 0.32974332571029663,
|
| 646 |
+
"learning_rate": 0.00012916666666666667,
|
| 647 |
+
"loss": 0.9983,
|
| 648 |
+
"step": 8900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.25,
|
| 652 |
+
"grad_norm": 0.2792109549045563,
|
| 653 |
+
"learning_rate": 0.000125,
|
| 654 |
+
"loss": 0.9892,
|
| 655 |
+
"step": 9000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.275,
|
| 659 |
+
"grad_norm": 0.30666106939315796,
|
| 660 |
+
"learning_rate": 0.00012083333333333333,
|
| 661 |
+
"loss": 0.9899,
|
| 662 |
+
"step": 9100
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.3,
|
| 666 |
+
"grad_norm": 0.32148030400276184,
|
| 667 |
+
"learning_rate": 0.00011666666666666667,
|
| 668 |
+
"loss": 0.9903,
|
| 669 |
+
"step": 9200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.325,
|
| 673 |
+
"grad_norm": 0.3192428648471832,
|
| 674 |
+
"learning_rate": 0.00011250000000000001,
|
| 675 |
+
"loss": 0.9844,
|
| 676 |
+
"step": 9300
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.35,
|
| 680 |
+
"grad_norm": 0.31449925899505615,
|
| 681 |
+
"learning_rate": 0.00010833333333333334,
|
| 682 |
+
"loss": 0.9968,
|
| 683 |
+
"step": 9400
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.375,
|
| 687 |
+
"grad_norm": 0.2781430780887604,
|
| 688 |
+
"learning_rate": 0.00010416666666666667,
|
| 689 |
+
"loss": 0.971,
|
| 690 |
+
"step": 9500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.4,
|
| 694 |
+
"grad_norm": 0.352714866399765,
|
| 695 |
+
"learning_rate": 0.0001,
|
| 696 |
+
"loss": 0.9805,
|
| 697 |
+
"step": 9600
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.425,
|
| 701 |
+
"grad_norm": 0.29257628321647644,
|
| 702 |
+
"learning_rate": 9.583333333333334e-05,
|
| 703 |
+
"loss": 0.9829,
|
| 704 |
+
"step": 9700
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.45,
|
| 708 |
+
"grad_norm": 0.31601646542549133,
|
| 709 |
+
"learning_rate": 9.166666666666667e-05,
|
| 710 |
+
"loss": 1.029,
|
| 711 |
+
"step": 9800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.475,
|
| 715 |
+
"grad_norm": 0.3273641765117645,
|
| 716 |
+
"learning_rate": 8.75e-05,
|
| 717 |
+
"loss": 1.0122,
|
| 718 |
+
"step": 9900
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.5,
|
| 722 |
+
"grad_norm": 0.3294784128665924,
|
| 723 |
+
"learning_rate": 8.333333333333333e-05,
|
| 724 |
+
"loss": 0.9829,
|
| 725 |
+
"step": 10000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.525,
|
| 729 |
+
"grad_norm": 0.33815255761146545,
|
| 730 |
+
"learning_rate": 7.916666666666666e-05,
|
| 731 |
+
"loss": 0.9808,
|
| 732 |
+
"step": 10100
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.55,
|
| 736 |
+
"grad_norm": 0.33642280101776123,
|
| 737 |
+
"learning_rate": 7.5e-05,
|
| 738 |
+
"loss": 0.9817,
|
| 739 |
+
"step": 10200
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.575,
|
| 743 |
+
"grad_norm": 0.30594727396965027,
|
| 744 |
+
"learning_rate": 7.083333333333334e-05,
|
| 745 |
+
"loss": 0.9935,
|
| 746 |
+
"step": 10300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.6,
|
| 750 |
+
"grad_norm": 0.2828643023967743,
|
| 751 |
+
"learning_rate": 6.666666666666667e-05,
|
| 752 |
+
"loss": 0.9801,
|
| 753 |
+
"step": 10400
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.625,
|
| 757 |
+
"grad_norm": 0.30603161454200745,
|
| 758 |
+
"learning_rate": 6.25e-05,
|
| 759 |
+
"loss": 0.956,
|
| 760 |
+
"step": 10500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.65,
|
| 764 |
+
"grad_norm": 0.33404436707496643,
|
| 765 |
+
"learning_rate": 5.833333333333333e-05,
|
| 766 |
+
"loss": 0.9764,
|
| 767 |
+
"step": 10600
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.675,
|
| 771 |
+
"grad_norm": 0.31933677196502686,
|
| 772 |
+
"learning_rate": 5.416666666666667e-05,
|
| 773 |
+
"loss": 0.9925,
|
| 774 |
+
"step": 10700
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.7,
|
| 778 |
+
"grad_norm": 0.3033044934272766,
|
| 779 |
+
"learning_rate": 5e-05,
|
| 780 |
+
"loss": 1.0186,
|
| 781 |
+
"step": 10800
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.725,
|
| 785 |
+
"grad_norm": 0.3226676881313324,
|
| 786 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 787 |
+
"loss": 0.9668,
|
| 788 |
+
"step": 10900
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.75,
|
| 792 |
+
"grad_norm": 0.3162941336631775,
|
| 793 |
+
"learning_rate": 4.1666666666666665e-05,
|
| 794 |
+
"loss": 0.9896,
|
| 795 |
+
"step": 11000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.775,
|
| 799 |
+
"grad_norm": 0.26616427302360535,
|
| 800 |
+
"learning_rate": 3.75e-05,
|
| 801 |
+
"loss": 0.9534,
|
| 802 |
+
"step": 11100
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.8,
|
| 806 |
+
"grad_norm": 0.3296871781349182,
|
| 807 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 808 |
+
"loss": 0.9515,
|
| 809 |
+
"step": 11200
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.825,
|
| 813 |
+
"grad_norm": 0.33690381050109863,
|
| 814 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 815 |
+
"loss": 0.9941,
|
| 816 |
+
"step": 11300
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.85,
|
| 820 |
+
"grad_norm": 0.3230708837509155,
|
| 821 |
+
"learning_rate": 2.5e-05,
|
| 822 |
+
"loss": 1.0061,
|
| 823 |
+
"step": 11400
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.875,
|
| 827 |
+
"grad_norm": 0.30407923460006714,
|
| 828 |
+
"learning_rate": 2.0833333333333333e-05,
|
| 829 |
+
"loss": 1.0121,
|
| 830 |
+
"step": 11500
|
| 831 |
+
}
|
| 832 |
+
],
|
| 833 |
+
"logging_steps": 100,
|
| 834 |
+
"max_steps": 12000,
|
| 835 |
+
"num_input_tokens_seen": 0,
|
| 836 |
+
"num_train_epochs": 3,
|
| 837 |
+
"save_steps": 500,
|
| 838 |
+
"stateful_callbacks": {
|
| 839 |
+
"TrainerControl": {
|
| 840 |
+
"args": {
|
| 841 |
+
"should_epoch_stop": false,
|
| 842 |
+
"should_evaluate": false,
|
| 843 |
+
"should_log": false,
|
| 844 |
+
"should_save": true,
|
| 845 |
+
"should_training_stop": false
|
| 846 |
+
},
|
| 847 |
+
"attributes": {}
|
| 848 |
+
}
|
| 849 |
+
},
|
| 850 |
+
"total_flos": 1.5138055913472e+16,
|
| 851 |
+
"train_batch_size": 4,
|
| 852 |
+
"trial_name": null,
|
| 853 |
+
"trial_params": null
|
| 854 |
+
}
|
checkpoint-11500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a15d761e2a319ab5a1242d68e02509d0416bef1b2e9f394a75f923744fe76a
|
| 3 |
+
size 5240
|
checkpoint-12000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: HuggingFaceTB/SmolLM2-135M
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
checkpoint-12000/adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
checkpoint-12000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05385138e4a73fe2f6d0e135631ba499d2670c47ad54d702182a1b7aa07a74e1
|
| 3 |
+
size 3702168
|
checkpoint-12000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50ae5e98dce254af0ddf6f067d850d3d1023f24adeb1ce72ad987ee5513ed860
|
| 3 |
+
size 7473658
|
checkpoint-12000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f060db117449f0f7b1a99b6bbbaa38ccaf51382c5b2ede831249f6e57ab9947
|
| 3 |
+
size 14244
|
checkpoint-12000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:951bb8d7d83c437589808181dd6a52fab98f8e3d2d14bd05d5bc15ebdc783270
|
| 3 |
+
size 1064
|
checkpoint-12000/trainer_state.json
ADDED
|
@@ -0,0 +1,889 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.025,
|
| 13 |
+
"grad_norm": 0.2082100212574005,
|
| 14 |
+
"learning_rate": 0.0004958333333333334,
|
| 15 |
+
"loss": 1.3502,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 0.1778642237186432,
|
| 21 |
+
"learning_rate": 0.0004916666666666666,
|
| 22 |
+
"loss": 1.1649,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.075,
|
| 27 |
+
"grad_norm": 0.2463778257369995,
|
| 28 |
+
"learning_rate": 0.0004875,
|
| 29 |
+
"loss": 1.1395,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1,
|
| 34 |
+
"grad_norm": 0.20819446444511414,
|
| 35 |
+
"learning_rate": 0.00048333333333333334,
|
| 36 |
+
"loss": 1.1056,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.125,
|
| 41 |
+
"grad_norm": 0.23243966698646545,
|
| 42 |
+
"learning_rate": 0.0004791666666666667,
|
| 43 |
+
"loss": 1.1329,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"grad_norm": 0.19812804460525513,
|
| 49 |
+
"learning_rate": 0.000475,
|
| 50 |
+
"loss": 1.1169,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.175,
|
| 55 |
+
"grad_norm": 0.2258671671152115,
|
| 56 |
+
"learning_rate": 0.00047083333333333336,
|
| 57 |
+
"loss": 1.1318,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"grad_norm": 0.20714746415615082,
|
| 63 |
+
"learning_rate": 0.00046666666666666666,
|
| 64 |
+
"loss": 1.114,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.225,
|
| 69 |
+
"grad_norm": 0.22002336382865906,
|
| 70 |
+
"learning_rate": 0.0004625,
|
| 71 |
+
"loss": 1.1269,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.25,
|
| 76 |
+
"grad_norm": 0.2159491330385208,
|
| 77 |
+
"learning_rate": 0.0004583333333333333,
|
| 78 |
+
"loss": 1.0694,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.275,
|
| 83 |
+
"grad_norm": 0.20638039708137512,
|
| 84 |
+
"learning_rate": 0.0004541666666666667,
|
| 85 |
+
"loss": 1.0929,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"grad_norm": 0.2234920710325241,
|
| 91 |
+
"learning_rate": 0.00045000000000000004,
|
| 92 |
+
"loss": 1.0903,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.325,
|
| 97 |
+
"grad_norm": 0.23063984513282776,
|
| 98 |
+
"learning_rate": 0.00044583333333333335,
|
| 99 |
+
"loss": 1.095,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.35,
|
| 104 |
+
"grad_norm": 0.221044659614563,
|
| 105 |
+
"learning_rate": 0.00044166666666666665,
|
| 106 |
+
"loss": 1.0859,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.375,
|
| 111 |
+
"grad_norm": 0.19685755670070648,
|
| 112 |
+
"learning_rate": 0.0004375,
|
| 113 |
+
"loss": 1.0643,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4,
|
| 118 |
+
"grad_norm": 0.2428029328584671,
|
| 119 |
+
"learning_rate": 0.00043333333333333337,
|
| 120 |
+
"loss": 1.0715,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.425,
|
| 125 |
+
"grad_norm": 0.21401169896125793,
|
| 126 |
+
"learning_rate": 0.00042916666666666667,
|
| 127 |
+
"loss": 1.0821,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45,
|
| 132 |
+
"grad_norm": 0.23752962052822113,
|
| 133 |
+
"learning_rate": 0.000425,
|
| 134 |
+
"loss": 1.0936,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.475,
|
| 139 |
+
"grad_norm": 0.23333564400672913,
|
| 140 |
+
"learning_rate": 0.00042083333333333333,
|
| 141 |
+
"loss": 1.0842,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5,
|
| 146 |
+
"grad_norm": 0.2038385421037674,
|
| 147 |
+
"learning_rate": 0.0004166666666666667,
|
| 148 |
+
"loss": 1.0831,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.525,
|
| 153 |
+
"grad_norm": 0.24392388761043549,
|
| 154 |
+
"learning_rate": 0.0004125,
|
| 155 |
+
"loss": 1.069,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.55,
|
| 160 |
+
"grad_norm": 0.2810049057006836,
|
| 161 |
+
"learning_rate": 0.00040833333333333336,
|
| 162 |
+
"loss": 1.0649,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.575,
|
| 167 |
+
"grad_norm": 0.24431484937667847,
|
| 168 |
+
"learning_rate": 0.00040416666666666666,
|
| 169 |
+
"loss": 1.0955,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6,
|
| 174 |
+
"grad_norm": 0.2268693745136261,
|
| 175 |
+
"learning_rate": 0.0004,
|
| 176 |
+
"loss": 1.0639,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.625,
|
| 181 |
+
"grad_norm": 0.22379685938358307,
|
| 182 |
+
"learning_rate": 0.0003958333333333333,
|
| 183 |
+
"loss": 1.0864,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.65,
|
| 188 |
+
"grad_norm": 0.22857442498207092,
|
| 189 |
+
"learning_rate": 0.0003916666666666667,
|
| 190 |
+
"loss": 1.0895,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.675,
|
| 195 |
+
"grad_norm": 0.22649641335010529,
|
| 196 |
+
"learning_rate": 0.00038750000000000004,
|
| 197 |
+
"loss": 1.0656,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7,
|
| 202 |
+
"grad_norm": 0.2611943185329437,
|
| 203 |
+
"learning_rate": 0.00038333333333333334,
|
| 204 |
+
"loss": 1.0492,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.725,
|
| 209 |
+
"grad_norm": 0.2599722743034363,
|
| 210 |
+
"learning_rate": 0.00037916666666666665,
|
| 211 |
+
"loss": 1.0639,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.75,
|
| 216 |
+
"grad_norm": 0.2554958462715149,
|
| 217 |
+
"learning_rate": 0.000375,
|
| 218 |
+
"loss": 1.0592,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.775,
|
| 223 |
+
"grad_norm": 0.262107789516449,
|
| 224 |
+
"learning_rate": 0.00037083333333333337,
|
| 225 |
+
"loss": 1.0458,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8,
|
| 230 |
+
"grad_norm": 0.23872502148151398,
|
| 231 |
+
"learning_rate": 0.00036666666666666667,
|
| 232 |
+
"loss": 1.0479,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.825,
|
| 237 |
+
"grad_norm": 0.2865801155567169,
|
| 238 |
+
"learning_rate": 0.0003625,
|
| 239 |
+
"loss": 1.0421,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.85,
|
| 244 |
+
"grad_norm": 0.2661890685558319,
|
| 245 |
+
"learning_rate": 0.00035833333333333333,
|
| 246 |
+
"loss": 1.0653,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.875,
|
| 251 |
+
"grad_norm": 0.25706493854522705,
|
| 252 |
+
"learning_rate": 0.0003541666666666667,
|
| 253 |
+
"loss": 1.057,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9,
|
| 258 |
+
"grad_norm": 0.25889962911605835,
|
| 259 |
+
"learning_rate": 0.00035,
|
| 260 |
+
"loss": 1.0435,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.925,
|
| 265 |
+
"grad_norm": 0.28601542115211487,
|
| 266 |
+
"learning_rate": 0.00034583333333333335,
|
| 267 |
+
"loss": 1.0564,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.95,
|
| 272 |
+
"grad_norm": 0.2556051015853882,
|
| 273 |
+
"learning_rate": 0.00034166666666666666,
|
| 274 |
+
"loss": 1.0354,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.975,
|
| 279 |
+
"grad_norm": 0.259920597076416,
|
| 280 |
+
"learning_rate": 0.0003375,
|
| 281 |
+
"loss": 1.0617,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.0,
|
| 286 |
+
"grad_norm": 0.26773035526275635,
|
| 287 |
+
"learning_rate": 0.0003333333333333333,
|
| 288 |
+
"loss": 1.0162,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.0,
|
| 293 |
+
"eval_loss": 1.041967749595642,
|
| 294 |
+
"eval_runtime": 70.7784,
|
| 295 |
+
"eval_samples_per_second": 56.514,
|
| 296 |
+
"eval_steps_per_second": 14.129,
|
| 297 |
+
"step": 4000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.025,
|
| 301 |
+
"grad_norm": 0.27995696663856506,
|
| 302 |
+
"learning_rate": 0.0003291666666666667,
|
| 303 |
+
"loss": 1.0294,
|
| 304 |
+
"step": 4100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.05,
|
| 308 |
+
"grad_norm": 0.26720207929611206,
|
| 309 |
+
"learning_rate": 0.00032500000000000004,
|
| 310 |
+
"loss": 1.0201,
|
| 311 |
+
"step": 4200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.075,
|
| 315 |
+
"grad_norm": 0.26933032274246216,
|
| 316 |
+
"learning_rate": 0.00032083333333333334,
|
| 317 |
+
"loss": 1.0337,
|
| 318 |
+
"step": 4300
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1,
|
| 322 |
+
"grad_norm": 0.2675634026527405,
|
| 323 |
+
"learning_rate": 0.00031666666666666665,
|
| 324 |
+
"loss": 1.0204,
|
| 325 |
+
"step": 4400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.125,
|
| 329 |
+
"grad_norm": 0.29779279232025146,
|
| 330 |
+
"learning_rate": 0.0003125,
|
| 331 |
+
"loss": 1.0116,
|
| 332 |
+
"step": 4500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.15,
|
| 336 |
+
"grad_norm": 0.2576355040073395,
|
| 337 |
+
"learning_rate": 0.00030833333333333337,
|
| 338 |
+
"loss": 1.0422,
|
| 339 |
+
"step": 4600
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.175,
|
| 343 |
+
"grad_norm": 0.26360246539115906,
|
| 344 |
+
"learning_rate": 0.00030416666666666667,
|
| 345 |
+
"loss": 1.0304,
|
| 346 |
+
"step": 4700
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2,
|
| 350 |
+
"grad_norm": 0.2623592019081116,
|
| 351 |
+
"learning_rate": 0.0003,
|
| 352 |
+
"loss": 1.0344,
|
| 353 |
+
"step": 4800
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.225,
|
| 357 |
+
"grad_norm": 0.2560625970363617,
|
| 358 |
+
"learning_rate": 0.00029583333333333333,
|
| 359 |
+
"loss": 1.0323,
|
| 360 |
+
"step": 4900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.25,
|
| 364 |
+
"grad_norm": 0.27826786041259766,
|
| 365 |
+
"learning_rate": 0.0002916666666666667,
|
| 366 |
+
"loss": 1.0147,
|
| 367 |
+
"step": 5000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.275,
|
| 371 |
+
"grad_norm": 0.26778700947761536,
|
| 372 |
+
"learning_rate": 0.0002875,
|
| 373 |
+
"loss": 1.0212,
|
| 374 |
+
"step": 5100
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3,
|
| 378 |
+
"grad_norm": 0.2655790150165558,
|
| 379 |
+
"learning_rate": 0.00028333333333333335,
|
| 380 |
+
"loss": 1.0429,
|
| 381 |
+
"step": 5200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.325,
|
| 385 |
+
"grad_norm": 0.23913314938545227,
|
| 386 |
+
"learning_rate": 0.00027916666666666666,
|
| 387 |
+
"loss": 1.0093,
|
| 388 |
+
"step": 5300
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.35,
|
| 392 |
+
"grad_norm": 0.25580066442489624,
|
| 393 |
+
"learning_rate": 0.000275,
|
| 394 |
+
"loss": 1.0157,
|
| 395 |
+
"step": 5400
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.375,
|
| 399 |
+
"grad_norm": 0.3255338966846466,
|
| 400 |
+
"learning_rate": 0.0002708333333333333,
|
| 401 |
+
"loss": 1.0291,
|
| 402 |
+
"step": 5500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4,
|
| 406 |
+
"grad_norm": 0.2690030634403229,
|
| 407 |
+
"learning_rate": 0.0002666666666666667,
|
| 408 |
+
"loss": 1.0428,
|
| 409 |
+
"step": 5600
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.425,
|
| 413 |
+
"grad_norm": 0.2967054843902588,
|
| 414 |
+
"learning_rate": 0.00026250000000000004,
|
| 415 |
+
"loss": 1.0077,
|
| 416 |
+
"step": 5700
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.45,
|
| 420 |
+
"grad_norm": 0.26981931924819946,
|
| 421 |
+
"learning_rate": 0.00025833333333333334,
|
| 422 |
+
"loss": 1.022,
|
| 423 |
+
"step": 5800
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.475,
|
| 427 |
+
"grad_norm": 0.29188498854637146,
|
| 428 |
+
"learning_rate": 0.00025416666666666665,
|
| 429 |
+
"loss": 1.0317,
|
| 430 |
+
"step": 5900
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.5,
|
| 434 |
+
"grad_norm": 0.26391416788101196,
|
| 435 |
+
"learning_rate": 0.00025,
|
| 436 |
+
"loss": 1.0311,
|
| 437 |
+
"step": 6000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.525,
|
| 441 |
+
"grad_norm": 0.2949013113975525,
|
| 442 |
+
"learning_rate": 0.0002458333333333333,
|
| 443 |
+
"loss": 0.998,
|
| 444 |
+
"step": 6100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.55,
|
| 448 |
+
"grad_norm": 0.25229978561401367,
|
| 449 |
+
"learning_rate": 0.00024166666666666667,
|
| 450 |
+
"loss": 1.0241,
|
| 451 |
+
"step": 6200
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.575,
|
| 455 |
+
"grad_norm": 0.2736811637878418,
|
| 456 |
+
"learning_rate": 0.0002375,
|
| 457 |
+
"loss": 1.0214,
|
| 458 |
+
"step": 6300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.6,
|
| 462 |
+
"grad_norm": 0.31093525886535645,
|
| 463 |
+
"learning_rate": 0.00023333333333333333,
|
| 464 |
+
"loss": 0.9709,
|
| 465 |
+
"step": 6400
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.625,
|
| 469 |
+
"grad_norm": 0.32644134759902954,
|
| 470 |
+
"learning_rate": 0.00022916666666666666,
|
| 471 |
+
"loss": 1.003,
|
| 472 |
+
"step": 6500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.65,
|
| 476 |
+
"grad_norm": 0.29749053716659546,
|
| 477 |
+
"learning_rate": 0.00022500000000000002,
|
| 478 |
+
"loss": 0.9985,
|
| 479 |
+
"step": 6600
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.675,
|
| 483 |
+
"grad_norm": 0.27901262044906616,
|
| 484 |
+
"learning_rate": 0.00022083333333333333,
|
| 485 |
+
"loss": 1.0096,
|
| 486 |
+
"step": 6700
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7,
|
| 490 |
+
"grad_norm": 0.32841789722442627,
|
| 491 |
+
"learning_rate": 0.00021666666666666668,
|
| 492 |
+
"loss": 1.0007,
|
| 493 |
+
"step": 6800
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.725,
|
| 497 |
+
"grad_norm": 0.30320826172828674,
|
| 498 |
+
"learning_rate": 0.0002125,
|
| 499 |
+
"loss": 1.0326,
|
| 500 |
+
"step": 6900
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.75,
|
| 504 |
+
"grad_norm": 0.2965095639228821,
|
| 505 |
+
"learning_rate": 0.00020833333333333335,
|
| 506 |
+
"loss": 1.0028,
|
| 507 |
+
"step": 7000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.775,
|
| 511 |
+
"grad_norm": 0.31121572852134705,
|
| 512 |
+
"learning_rate": 0.00020416666666666668,
|
| 513 |
+
"loss": 0.9839,
|
| 514 |
+
"step": 7100
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.8,
|
| 518 |
+
"grad_norm": 0.2947477698326111,
|
| 519 |
+
"learning_rate": 0.0002,
|
| 520 |
+
"loss": 0.9841,
|
| 521 |
+
"step": 7200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.825,
|
| 525 |
+
"grad_norm": 0.2830908000469208,
|
| 526 |
+
"learning_rate": 0.00019583333333333334,
|
| 527 |
+
"loss": 1.0089,
|
| 528 |
+
"step": 7300
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.85,
|
| 532 |
+
"grad_norm": 0.29144686460494995,
|
| 533 |
+
"learning_rate": 0.00019166666666666667,
|
| 534 |
+
"loss": 1.0038,
|
| 535 |
+
"step": 7400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.875,
|
| 539 |
+
"grad_norm": 0.2925328016281128,
|
| 540 |
+
"learning_rate": 0.0001875,
|
| 541 |
+
"loss": 1.003,
|
| 542 |
+
"step": 7500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.9,
|
| 546 |
+
"grad_norm": 0.3474633991718292,
|
| 547 |
+
"learning_rate": 0.00018333333333333334,
|
| 548 |
+
"loss": 1.0265,
|
| 549 |
+
"step": 7600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.925,
|
| 553 |
+
"grad_norm": 0.2939680814743042,
|
| 554 |
+
"learning_rate": 0.00017916666666666667,
|
| 555 |
+
"loss": 1.0145,
|
| 556 |
+
"step": 7700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.95,
|
| 560 |
+
"grad_norm": 0.2775793969631195,
|
| 561 |
+
"learning_rate": 0.000175,
|
| 562 |
+
"loss": 0.9977,
|
| 563 |
+
"step": 7800
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.975,
|
| 567 |
+
"grad_norm": 0.3091006577014923,
|
| 568 |
+
"learning_rate": 0.00017083333333333333,
|
| 569 |
+
"loss": 1.0255,
|
| 570 |
+
"step": 7900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0,
|
| 574 |
+
"grad_norm": 0.32153698801994324,
|
| 575 |
+
"learning_rate": 0.00016666666666666666,
|
| 576 |
+
"loss": 1.0262,
|
| 577 |
+
"step": 8000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.0,
|
| 581 |
+
"eval_loss": 1.0134142637252808,
|
| 582 |
+
"eval_runtime": 71.1474,
|
| 583 |
+
"eval_samples_per_second": 56.221,
|
| 584 |
+
"eval_steps_per_second": 14.055,
|
| 585 |
+
"step": 8000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.025,
|
| 589 |
+
"grad_norm": 0.31311318278312683,
|
| 590 |
+
"learning_rate": 0.00016250000000000002,
|
| 591 |
+
"loss": 1.0097,
|
| 592 |
+
"step": 8100
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.05,
|
| 596 |
+
"grad_norm": 0.308938205242157,
|
| 597 |
+
"learning_rate": 0.00015833333333333332,
|
| 598 |
+
"loss": 0.9912,
|
| 599 |
+
"step": 8200
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.075,
|
| 603 |
+
"grad_norm": 0.29837608337402344,
|
| 604 |
+
"learning_rate": 0.00015416666666666668,
|
| 605 |
+
"loss": 0.9945,
|
| 606 |
+
"step": 8300
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.1,
|
| 610 |
+
"grad_norm": 0.29206210374832153,
|
| 611 |
+
"learning_rate": 0.00015,
|
| 612 |
+
"loss": 0.9608,
|
| 613 |
+
"step": 8400
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.125,
|
| 617 |
+
"grad_norm": 0.29734155535697937,
|
| 618 |
+
"learning_rate": 0.00014583333333333335,
|
| 619 |
+
"loss": 1.0005,
|
| 620 |
+
"step": 8500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.15,
|
| 624 |
+
"grad_norm": 0.31197240948677063,
|
| 625 |
+
"learning_rate": 0.00014166666666666668,
|
| 626 |
+
"loss": 0.9936,
|
| 627 |
+
"step": 8600
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.175,
|
| 631 |
+
"grad_norm": 0.3193836808204651,
|
| 632 |
+
"learning_rate": 0.0001375,
|
| 633 |
+
"loss": 1.0125,
|
| 634 |
+
"step": 8700
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.2,
|
| 638 |
+
"grad_norm": 0.29876908659935,
|
| 639 |
+
"learning_rate": 0.00013333333333333334,
|
| 640 |
+
"loss": 1.0084,
|
| 641 |
+
"step": 8800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.225,
|
| 645 |
+
"grad_norm": 0.32974332571029663,
|
| 646 |
+
"learning_rate": 0.00012916666666666667,
|
| 647 |
+
"loss": 0.9983,
|
| 648 |
+
"step": 8900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.25,
|
| 652 |
+
"grad_norm": 0.2792109549045563,
|
| 653 |
+
"learning_rate": 0.000125,
|
| 654 |
+
"loss": 0.9892,
|
| 655 |
+
"step": 9000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.275,
|
| 659 |
+
"grad_norm": 0.30666106939315796,
|
| 660 |
+
"learning_rate": 0.00012083333333333333,
|
| 661 |
+
"loss": 0.9899,
|
| 662 |
+
"step": 9100
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.3,
|
| 666 |
+
"grad_norm": 0.32148030400276184,
|
| 667 |
+
"learning_rate": 0.00011666666666666667,
|
| 668 |
+
"loss": 0.9903,
|
| 669 |
+
"step": 9200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.325,
|
| 673 |
+
"grad_norm": 0.3192428648471832,
|
| 674 |
+
"learning_rate": 0.00011250000000000001,
|
| 675 |
+
"loss": 0.9844,
|
| 676 |
+
"step": 9300
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.35,
|
| 680 |
+
"grad_norm": 0.31449925899505615,
|
| 681 |
+
"learning_rate": 0.00010833333333333334,
|
| 682 |
+
"loss": 0.9968,
|
| 683 |
+
"step": 9400
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.375,
|
| 687 |
+
"grad_norm": 0.2781430780887604,
|
| 688 |
+
"learning_rate": 0.00010416666666666667,
|
| 689 |
+
"loss": 0.971,
|
| 690 |
+
"step": 9500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.4,
|
| 694 |
+
"grad_norm": 0.352714866399765,
|
| 695 |
+
"learning_rate": 0.0001,
|
| 696 |
+
"loss": 0.9805,
|
| 697 |
+
"step": 9600
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.425,
|
| 701 |
+
"grad_norm": 0.29257628321647644,
|
| 702 |
+
"learning_rate": 9.583333333333334e-05,
|
| 703 |
+
"loss": 0.9829,
|
| 704 |
+
"step": 9700
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.45,
|
| 708 |
+
"grad_norm": 0.31601646542549133,
|
| 709 |
+
"learning_rate": 9.166666666666667e-05,
|
| 710 |
+
"loss": 1.029,
|
| 711 |
+
"step": 9800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.475,
|
| 715 |
+
"grad_norm": 0.3273641765117645,
|
| 716 |
+
"learning_rate": 8.75e-05,
|
| 717 |
+
"loss": 1.0122,
|
| 718 |
+
"step": 9900
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.5,
|
| 722 |
+
"grad_norm": 0.3294784128665924,
|
| 723 |
+
"learning_rate": 8.333333333333333e-05,
|
| 724 |
+
"loss": 0.9829,
|
| 725 |
+
"step": 10000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.525,
|
| 729 |
+
"grad_norm": 0.33815255761146545,
|
| 730 |
+
"learning_rate": 7.916666666666666e-05,
|
| 731 |
+
"loss": 0.9808,
|
| 732 |
+
"step": 10100
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.55,
|
| 736 |
+
"grad_norm": 0.33642280101776123,
|
| 737 |
+
"learning_rate": 7.5e-05,
|
| 738 |
+
"loss": 0.9817,
|
| 739 |
+
"step": 10200
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.575,
|
| 743 |
+
"grad_norm": 0.30594727396965027,
|
| 744 |
+
"learning_rate": 7.083333333333334e-05,
|
| 745 |
+
"loss": 0.9935,
|
| 746 |
+
"step": 10300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.6,
|
| 750 |
+
"grad_norm": 0.2828643023967743,
|
| 751 |
+
"learning_rate": 6.666666666666667e-05,
|
| 752 |
+
"loss": 0.9801,
|
| 753 |
+
"step": 10400
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.625,
|
| 757 |
+
"grad_norm": 0.30603161454200745,
|
| 758 |
+
"learning_rate": 6.25e-05,
|
| 759 |
+
"loss": 0.956,
|
| 760 |
+
"step": 10500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.65,
|
| 764 |
+
"grad_norm": 0.33404436707496643,
|
| 765 |
+
"learning_rate": 5.833333333333333e-05,
|
| 766 |
+
"loss": 0.9764,
|
| 767 |
+
"step": 10600
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.675,
|
| 771 |
+
"grad_norm": 0.31933677196502686,
|
| 772 |
+
"learning_rate": 5.416666666666667e-05,
|
| 773 |
+
"loss": 0.9925,
|
| 774 |
+
"step": 10700
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.7,
|
| 778 |
+
"grad_norm": 0.3033044934272766,
|
| 779 |
+
"learning_rate": 5e-05,
|
| 780 |
+
"loss": 1.0186,
|
| 781 |
+
"step": 10800
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.725,
|
| 785 |
+
"grad_norm": 0.3226676881313324,
|
| 786 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 787 |
+
"loss": 0.9668,
|
| 788 |
+
"step": 10900
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.75,
|
| 792 |
+
"grad_norm": 0.3162941336631775,
|
| 793 |
+
"learning_rate": 4.1666666666666665e-05,
|
| 794 |
+
"loss": 0.9896,
|
| 795 |
+
"step": 11000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.775,
|
| 799 |
+
"grad_norm": 0.26616427302360535,
|
| 800 |
+
"learning_rate": 3.75e-05,
|
| 801 |
+
"loss": 0.9534,
|
| 802 |
+
"step": 11100
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.8,
|
| 806 |
+
"grad_norm": 0.3296871781349182,
|
| 807 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 808 |
+
"loss": 0.9515,
|
| 809 |
+
"step": 11200
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.825,
|
| 813 |
+
"grad_norm": 0.33690381050109863,
|
| 814 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 815 |
+
"loss": 0.9941,
|
| 816 |
+
"step": 11300
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.85,
|
| 820 |
+
"grad_norm": 0.3230708837509155,
|
| 821 |
+
"learning_rate": 2.5e-05,
|
| 822 |
+
"loss": 1.0061,
|
| 823 |
+
"step": 11400
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.875,
|
| 827 |
+
"grad_norm": 0.30407923460006714,
|
| 828 |
+
"learning_rate": 2.0833333333333333e-05,
|
| 829 |
+
"loss": 1.0121,
|
| 830 |
+
"step": 11500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.9,
|
| 834 |
+
"grad_norm": 0.2791903018951416,
|
| 835 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 836 |
+
"loss": 0.9744,
|
| 837 |
+
"step": 11600
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.925,
|
| 841 |
+
"grad_norm": 0.35448238253593445,
|
| 842 |
+
"learning_rate": 1.25e-05,
|
| 843 |
+
"loss": 1.0008,
|
| 844 |
+
"step": 11700
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.95,
|
| 848 |
+
"grad_norm": 0.31761014461517334,
|
| 849 |
+
"learning_rate": 8.333333333333334e-06,
|
| 850 |
+
"loss": 0.9842,
|
| 851 |
+
"step": 11800
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.975,
|
| 855 |
+
"grad_norm": 0.3444092273712158,
|
| 856 |
+
"learning_rate": 4.166666666666667e-06,
|
| 857 |
+
"loss": 0.9806,
|
| 858 |
+
"step": 11900
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 3.0,
|
| 862 |
+
"grad_norm": 0.30812370777130127,
|
| 863 |
+
"learning_rate": 0.0,
|
| 864 |
+
"loss": 1.0067,
|
| 865 |
+
"step": 12000
|
| 866 |
+
}
|
| 867 |
+
],
|
| 868 |
+
"logging_steps": 100,
|
| 869 |
+
"max_steps": 12000,
|
| 870 |
+
"num_input_tokens_seen": 0,
|
| 871 |
+
"num_train_epochs": 3,
|
| 872 |
+
"save_steps": 500,
|
| 873 |
+
"stateful_callbacks": {
|
| 874 |
+
"TrainerControl": {
|
| 875 |
+
"args": {
|
| 876 |
+
"should_epoch_stop": false,
|
| 877 |
+
"should_evaluate": false,
|
| 878 |
+
"should_log": false,
|
| 879 |
+
"should_save": true,
|
| 880 |
+
"should_training_stop": true
|
| 881 |
+
},
|
| 882 |
+
"attributes": {}
|
| 883 |
+
}
|
| 884 |
+
},
|
| 885 |
+
"total_flos": 1.5796232257536e+16,
|
| 886 |
+
"train_batch_size": 4,
|
| 887 |
+
"trial_name": null,
|
| 888 |
+
"trial_params": null
|
| 889 |
+
}
|
checkpoint-12000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a15d761e2a319ab5a1242d68e02509d0416bef1b2e9f394a75f923744fe76a
|
| 3 |
+
size 5240
|