Instructions to use heitorrosa/logun-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use heitorrosa/logun-base with PEFT:
Task type is invalid.
- Transformers
How to use heitorrosa/logun-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="heitorrosa/logun-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("heitorrosa/logun-base") model = AutoModelForMaskedLM.from_pretrained("heitorrosa/logun-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- sft/checkpoint-1050/README.md +206 -0
- sft/checkpoint-1050/optimizer.pt +3 -0
- sft/checkpoint-1050/rng_state_0.pth +3 -0
- sft/checkpoint-1050/scaler.pt +3 -0
- sft/checkpoint-1050/scheduler.pt +3 -0
- sft/checkpoint-1050/sft/adapter_config.json +50 -0
- sft/checkpoint-1050/sft/adapter_model.safetensors +3 -0
- sft/checkpoint-1050/tokenizer.json +0 -0
- sft/checkpoint-1050/tokenizer_config.json +19 -0
- sft/checkpoint-1050/trainer_state.json +594 -0
- sft/checkpoint-1050/training_args.bin +3 -0
sft/checkpoint-1050/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: heitorrosa/logun-base
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:heitorrosa/logun-base
|
| 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 0.20.0
|
sft/checkpoint-1050/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab60c18a0539aad547515fef55b55e662ebefe09d28fe464059694a32cbdc31d
|
| 3 |
+
size 27204427
|
sft/checkpoint-1050/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c0f266599d1ff4e56a669c662e61d60ed351eb9daf91865ffe5e026d6c72813
|
| 3 |
+
size 14917
|
sft/checkpoint-1050/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ede54ef3c0d242aa73e3ca3612df8d74ea0831a30ff2fa10026a7fcc4d7ae25d
|
| 3 |
+
size 1383
|
sft/checkpoint-1050/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20c301afb0e5f30885bd7a85d692f5bb9cc1bab3fd792e876eae16fc7f72ce5b
|
| 3 |
+
size 1465
|
sft/checkpoint-1050/sft/adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "heitorrosa/logun-base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": [
|
| 26 |
+
"classifier",
|
| 27 |
+
"classifier",
|
| 28 |
+
"score"
|
| 29 |
+
],
|
| 30 |
+
"monteclora_config": null,
|
| 31 |
+
"peft_type": "LORA",
|
| 32 |
+
"peft_version": "0.20.0",
|
| 33 |
+
"qalora_group_size": 16,
|
| 34 |
+
"r": 16,
|
| 35 |
+
"rank_pattern": {},
|
| 36 |
+
"revision": null,
|
| 37 |
+
"target_modules": [
|
| 38 |
+
"Wqkv",
|
| 39 |
+
"Wo",
|
| 40 |
+
"Wi"
|
| 41 |
+
],
|
| 42 |
+
"target_parameters": null,
|
| 43 |
+
"task_type": "SEQ_CLS",
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_bdlora": null,
|
| 46 |
+
"use_dora": false,
|
| 47 |
+
"use_qalora": false,
|
| 48 |
+
"use_rslora": false,
|
| 49 |
+
"velora_config": null
|
| 50 |
+
}
|
sft/checkpoint-1050/sft/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6238fca7cfec3f3878a28f9181d087ad7ace390a9fac76b5c04797761ba21d79
|
| 3 |
+
size 13547940
|
sft/checkpoint-1050/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft/checkpoint-1050/tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "[CLS]",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 8192,
|
| 14 |
+
"pad_token": "[PAD]",
|
| 15 |
+
"padding_side": "right",
|
| 16 |
+
"tokenizer_class": "TokenizersBackend",
|
| 17 |
+
"truncation_side": "right",
|
| 18 |
+
"unk_token": "[UNK]"
|
| 19 |
+
}
|
sft/checkpoint-1050/trainer_state.json
ADDED
|
@@ -0,0 +1,594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9675377944450956,
|
| 6 |
+
"eval_steps": 150,
|
| 7 |
+
"global_step": 1050,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02812609867572952,
|
| 14 |
+
"grad_norm": NaN,
|
| 15 |
+
"learning_rate": 4.666666666666667e-06,
|
| 16 |
+
"loss": 40.91645100911458,
|
| 17 |
+
"step": 15
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05625219735145904,
|
| 21 |
+
"grad_norm": 108.49263000488281,
|
| 22 |
+
"learning_rate": 9.666666666666667e-06,
|
| 23 |
+
"loss": 38.68733317057292,
|
| 24 |
+
"step": 30
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08437829602718856,
|
| 28 |
+
"grad_norm": 87.13339233398438,
|
| 29 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 30 |
+
"loss": 37.54708658854167,
|
| 31 |
+
"step": 45
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11250439470291808,
|
| 35 |
+
"grad_norm": 82.61961364746094,
|
| 36 |
+
"learning_rate": 1.9666666666666666e-05,
|
| 37 |
+
"loss": 35.59373372395833,
|
| 38 |
+
"step": 60
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1406304933786476,
|
| 42 |
+
"grad_norm": 94.90762329101562,
|
| 43 |
+
"learning_rate": 2.466666666666667e-05,
|
| 44 |
+
"loss": 34.33445638020833,
|
| 45 |
+
"step": 75
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16875659205437712,
|
| 49 |
+
"grad_norm": 64.12799072265625,
|
| 50 |
+
"learning_rate": 2.9666666666666672e-05,
|
| 51 |
+
"loss": 33.768391927083336,
|
| 52 |
+
"step": 90
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19688269073010664,
|
| 56 |
+
"grad_norm": 61.35285568237305,
|
| 57 |
+
"learning_rate": 3.466666666666667e-05,
|
| 58 |
+
"loss": 33.065120442708334,
|
| 59 |
+
"step": 105
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22500878940583616,
|
| 63 |
+
"grad_norm": 56.75034713745117,
|
| 64 |
+
"learning_rate": 3.966666666666667e-05,
|
| 65 |
+
"loss": 32.87635091145833,
|
| 66 |
+
"step": 120
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2531348880815657,
|
| 70 |
+
"grad_norm": 88.83663177490234,
|
| 71 |
+
"learning_rate": 4.466666666666667e-05,
|
| 72 |
+
"loss": 31.945328776041666,
|
| 73 |
+
"step": 135
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2812609867572952,
|
| 77 |
+
"grad_norm": 53.496788024902344,
|
| 78 |
+
"learning_rate": 4.966666666666667e-05,
|
| 79 |
+
"loss": 32.28165283203125,
|
| 80 |
+
"step": 150
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2812609867572952,
|
| 84 |
+
"eval_accuracy": 0.4985507246376812,
|
| 85 |
+
"eval_loss": 1.9326186180114746,
|
| 86 |
+
"eval_macro_f1": 0.4513996326113265,
|
| 87 |
+
"eval_runtime": 7.0971,
|
| 88 |
+
"eval_samples_per_second": 48.611,
|
| 89 |
+
"eval_steps_per_second": 6.2,
|
| 90 |
+
"step": 150
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.30938708543302473,
|
| 94 |
+
"grad_norm": 54.809783935546875,
|
| 95 |
+
"learning_rate": 4.9830179524502674e-05,
|
| 96 |
+
"loss": 30.544930013020835,
|
| 97 |
+
"step": 165
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.33751318410875425,
|
| 101 |
+
"grad_norm": 68.34676361083984,
|
| 102 |
+
"learning_rate": 4.964822901504124e-05,
|
| 103 |
+
"loss": 29.883894856770834,
|
| 104 |
+
"step": 180
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.36563928278448377,
|
| 108 |
+
"grad_norm": 70.30874633789062,
|
| 109 |
+
"learning_rate": 4.9466278505579815e-05,
|
| 110 |
+
"loss": 29.711442057291666,
|
| 111 |
+
"step": 195
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.3937653814602133,
|
| 115 |
+
"grad_norm": 105.4150161743164,
|
| 116 |
+
"learning_rate": 4.928432799611839e-05,
|
| 117 |
+
"loss": 29.863224283854166,
|
| 118 |
+
"step": 210
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.4218914801359428,
|
| 122 |
+
"grad_norm": 81.67976379394531,
|
| 123 |
+
"learning_rate": 4.910237748665696e-05,
|
| 124 |
+
"loss": 29.67599080403646,
|
| 125 |
+
"step": 225
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.4500175788116723,
|
| 129 |
+
"grad_norm": 78.1202621459961,
|
| 130 |
+
"learning_rate": 4.8920426977195536e-05,
|
| 131 |
+
"loss": 28.802783203125,
|
| 132 |
+
"step": 240
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.47814367748740183,
|
| 136 |
+
"grad_norm": 73.63782501220703,
|
| 137 |
+
"learning_rate": 4.873847646773411e-05,
|
| 138 |
+
"loss": 27.798103841145835,
|
| 139 |
+
"step": 255
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.5062697761631314,
|
| 143 |
+
"grad_norm": 77.5123519897461,
|
| 144 |
+
"learning_rate": 4.855652595827268e-05,
|
| 145 |
+
"loss": 26.746952311197916,
|
| 146 |
+
"step": 270
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.5343958748388609,
|
| 150 |
+
"grad_norm": 70.0318603515625,
|
| 151 |
+
"learning_rate": 4.837457544881126e-05,
|
| 152 |
+
"loss": 26.3315673828125,
|
| 153 |
+
"step": 285
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.5625219735145904,
|
| 157 |
+
"grad_norm": 66.42996215820312,
|
| 158 |
+
"learning_rate": 4.819262493934984e-05,
|
| 159 |
+
"loss": 26.488555908203125,
|
| 160 |
+
"step": 300
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.5625219735145904,
|
| 164 |
+
"eval_accuracy": 0.6318840579710145,
|
| 165 |
+
"eval_loss": 1.615958333015442,
|
| 166 |
+
"eval_macro_f1": 0.6129856465867943,
|
| 167 |
+
"eval_runtime": 2.3114,
|
| 168 |
+
"eval_samples_per_second": 149.263,
|
| 169 |
+
"eval_steps_per_second": 19.036,
|
| 170 |
+
"step": 300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5906480721903199,
|
| 174 |
+
"grad_norm": 68.63166046142578,
|
| 175 |
+
"learning_rate": 4.801067442988841e-05,
|
| 176 |
+
"loss": 26.851969401041668,
|
| 177 |
+
"step": 315
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6187741708660495,
|
| 181 |
+
"grad_norm": 94.37174224853516,
|
| 182 |
+
"learning_rate": 4.7828723920426985e-05,
|
| 183 |
+
"loss": 26.854146321614582,
|
| 184 |
+
"step": 330
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6469002695417789,
|
| 188 |
+
"grad_norm": 85.5411605834961,
|
| 189 |
+
"learning_rate": 4.764677341096555e-05,
|
| 190 |
+
"loss": 24.6757080078125,
|
| 191 |
+
"step": 345
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6750263682175085,
|
| 195 |
+
"grad_norm": 64.81537628173828,
|
| 196 |
+
"learning_rate": 4.7464822901504125e-05,
|
| 197 |
+
"loss": 27.398944091796874,
|
| 198 |
+
"step": 360
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7031524668932381,
|
| 202 |
+
"grad_norm": 98.3795394897461,
|
| 203 |
+
"learning_rate": 4.72828723920427e-05,
|
| 204 |
+
"loss": 25.361378987630207,
|
| 205 |
+
"step": 375
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7312785655689675,
|
| 209 |
+
"grad_norm": 60.86552810668945,
|
| 210 |
+
"learning_rate": 4.710092188258127e-05,
|
| 211 |
+
"loss": 23.455232747395833,
|
| 212 |
+
"step": 390
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7594046642446971,
|
| 216 |
+
"grad_norm": 65.06398010253906,
|
| 217 |
+
"learning_rate": 4.6918971373119846e-05,
|
| 218 |
+
"loss": 25.147119140625,
|
| 219 |
+
"step": 405
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7875307629204266,
|
| 223 |
+
"grad_norm": 64.24246978759766,
|
| 224 |
+
"learning_rate": 4.673702086365842e-05,
|
| 225 |
+
"loss": 26.254545084635417,
|
| 226 |
+
"step": 420
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8156568615961561,
|
| 230 |
+
"grad_norm": 85.69407653808594,
|
| 231 |
+
"learning_rate": 4.6555070354196993e-05,
|
| 232 |
+
"loss": 25.228023274739584,
|
| 233 |
+
"step": 435
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8437829602718856,
|
| 237 |
+
"grad_norm": 91.77117919921875,
|
| 238 |
+
"learning_rate": 4.637311984473557e-05,
|
| 239 |
+
"loss": 24.674845377604168,
|
| 240 |
+
"step": 450
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8437829602718856,
|
| 244 |
+
"eval_accuracy": 0.6579710144927536,
|
| 245 |
+
"eval_loss": 1.529452919960022,
|
| 246 |
+
"eval_macro_f1": 0.6434151685975086,
|
| 247 |
+
"eval_runtime": 2.2932,
|
| 248 |
+
"eval_samples_per_second": 150.442,
|
| 249 |
+
"eval_steps_per_second": 19.187,
|
| 250 |
+
"step": 450
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.8719090589476152,
|
| 254 |
+
"grad_norm": 59.32505798339844,
|
| 255 |
+
"learning_rate": 4.619116933527414e-05,
|
| 256 |
+
"loss": 25.152834065755208,
|
| 257 |
+
"step": 465
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.9000351576233446,
|
| 261 |
+
"grad_norm": 68.90987396240234,
|
| 262 |
+
"learning_rate": 4.6009218825812714e-05,
|
| 263 |
+
"loss": 23.644384765625,
|
| 264 |
+
"step": 480
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.9281612562990742,
|
| 268 |
+
"grad_norm": 78.69176483154297,
|
| 269 |
+
"learning_rate": 4.582726831635129e-05,
|
| 270 |
+
"loss": 24.69483642578125,
|
| 271 |
+
"step": 495
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.9562873549748037,
|
| 275 |
+
"grad_norm": 71.7799072265625,
|
| 276 |
+
"learning_rate": 4.564531780688986e-05,
|
| 277 |
+
"loss": 23.468556722005207,
|
| 278 |
+
"step": 510
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.9844134536505332,
|
| 282 |
+
"grad_norm": 99.54678344726562,
|
| 283 |
+
"learning_rate": 4.5463367297428435e-05,
|
| 284 |
+
"loss": 24.51992390950521,
|
| 285 |
+
"step": 525
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.011250439470292,
|
| 289 |
+
"grad_norm": 81.2381362915039,
|
| 290 |
+
"learning_rate": 4.528141678796701e-05,
|
| 291 |
+
"loss": 22.73736572265625,
|
| 292 |
+
"step": 540
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.0393765381460214,
|
| 296 |
+
"grad_norm": 72.6605224609375,
|
| 297 |
+
"learning_rate": 4.509946627850558e-05,
|
| 298 |
+
"loss": 24.33416748046875,
|
| 299 |
+
"step": 555
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0675026368217508,
|
| 303 |
+
"grad_norm": 80.05354309082031,
|
| 304 |
+
"learning_rate": 4.4917515769044156e-05,
|
| 305 |
+
"loss": 22.052213541666667,
|
| 306 |
+
"step": 570
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.0956287354974803,
|
| 310 |
+
"grad_norm": 90.22277069091797,
|
| 311 |
+
"learning_rate": 4.473556525958273e-05,
|
| 312 |
+
"loss": 22.770609537760418,
|
| 313 |
+
"step": 585
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.12375483417321,
|
| 317 |
+
"grad_norm": 69.45885467529297,
|
| 318 |
+
"learning_rate": 4.4553614750121304e-05,
|
| 319 |
+
"loss": 24.028635660807293,
|
| 320 |
+
"step": 600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.12375483417321,
|
| 324 |
+
"eval_accuracy": 0.6608695652173913,
|
| 325 |
+
"eval_loss": 1.49661386013031,
|
| 326 |
+
"eval_macro_f1": 0.6466193853427896,
|
| 327 |
+
"eval_runtime": 2.2405,
|
| 328 |
+
"eval_samples_per_second": 153.984,
|
| 329 |
+
"eval_steps_per_second": 19.639,
|
| 330 |
+
"step": 600
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.1518809328489394,
|
| 334 |
+
"grad_norm": 109.61043548583984,
|
| 335 |
+
"learning_rate": 4.437166424065988e-05,
|
| 336 |
+
"loss": 23.77248331705729,
|
| 337 |
+
"step": 615
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.180007031524669,
|
| 341 |
+
"grad_norm": 71.86944580078125,
|
| 342 |
+
"learning_rate": 4.418971373119845e-05,
|
| 343 |
+
"loss": 22.4523193359375,
|
| 344 |
+
"step": 630
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.2081331302003984,
|
| 348 |
+
"grad_norm": 79.43173217773438,
|
| 349 |
+
"learning_rate": 4.4007763221737025e-05,
|
| 350 |
+
"loss": 23.30051472981771,
|
| 351 |
+
"step": 645
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.236259228876128,
|
| 355 |
+
"grad_norm": 73.39543914794922,
|
| 356 |
+
"learning_rate": 4.38258127122756e-05,
|
| 357 |
+
"loss": 23.162101236979165,
|
| 358 |
+
"step": 660
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.2643853275518575,
|
| 362 |
+
"grad_norm": 92.3052978515625,
|
| 363 |
+
"learning_rate": 4.3643862202814165e-05,
|
| 364 |
+
"loss": 22.967840576171874,
|
| 365 |
+
"step": 675
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.292511426227587,
|
| 369 |
+
"grad_norm": 79.57266998291016,
|
| 370 |
+
"learning_rate": 4.346191169335274e-05,
|
| 371 |
+
"loss": 24.993180338541666,
|
| 372 |
+
"step": 690
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.3206375249033164,
|
| 376 |
+
"grad_norm": 81.71668243408203,
|
| 377 |
+
"learning_rate": 4.327996118389131e-05,
|
| 378 |
+
"loss": 23.013671875,
|
| 379 |
+
"step": 705
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.3487636235790461,
|
| 383 |
+
"grad_norm": 64.0071029663086,
|
| 384 |
+
"learning_rate": 4.3098010674429886e-05,
|
| 385 |
+
"loss": 23.570048014322918,
|
| 386 |
+
"step": 720
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.3768897222547756,
|
| 390 |
+
"grad_norm": 98.42646789550781,
|
| 391 |
+
"learning_rate": 4.291606016496847e-05,
|
| 392 |
+
"loss": 22.822066243489584,
|
| 393 |
+
"step": 735
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.405015820930505,
|
| 397 |
+
"grad_norm": 77.34905242919922,
|
| 398 |
+
"learning_rate": 4.273410965550704e-05,
|
| 399 |
+
"loss": 24.35296630859375,
|
| 400 |
+
"step": 750
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.405015820930505,
|
| 404 |
+
"eval_accuracy": 0.6608695652173913,
|
| 405 |
+
"eval_loss": 1.4775240421295166,
|
| 406 |
+
"eval_macro_f1": 0.6485427050773,
|
| 407 |
+
"eval_runtime": 2.2991,
|
| 408 |
+
"eval_samples_per_second": 150.061,
|
| 409 |
+
"eval_steps_per_second": 19.138,
|
| 410 |
+
"step": 750
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.4331419196062347,
|
| 414 |
+
"grad_norm": 74.36935424804688,
|
| 415 |
+
"learning_rate": 4.2552159146045614e-05,
|
| 416 |
+
"loss": 24.365966796875,
|
| 417 |
+
"step": 765
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.4612680182819642,
|
| 421 |
+
"grad_norm": 72.57489013671875,
|
| 422 |
+
"learning_rate": 4.237020863658419e-05,
|
| 423 |
+
"loss": 22.283140055338542,
|
| 424 |
+
"step": 780
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.4893941169576936,
|
| 428 |
+
"grad_norm": 66.50872039794922,
|
| 429 |
+
"learning_rate": 4.218825812712276e-05,
|
| 430 |
+
"loss": 22.849454752604167,
|
| 431 |
+
"step": 795
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.5175202156334233,
|
| 435 |
+
"grad_norm": 73.18653869628906,
|
| 436 |
+
"learning_rate": 4.2006307617661335e-05,
|
| 437 |
+
"loss": 23.213165283203125,
|
| 438 |
+
"step": 810
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.5456463143091526,
|
| 442 |
+
"grad_norm": 100.36980438232422,
|
| 443 |
+
"learning_rate": 4.182435710819991e-05,
|
| 444 |
+
"loss": 22.919950358072917,
|
| 445 |
+
"step": 825
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.5737724129848822,
|
| 449 |
+
"grad_norm": 92.35721588134766,
|
| 450 |
+
"learning_rate": 4.1642406598738476e-05,
|
| 451 |
+
"loss": 23.443257649739582,
|
| 452 |
+
"step": 840
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.6018985116606117,
|
| 456 |
+
"grad_norm": 79.11441802978516,
|
| 457 |
+
"learning_rate": 4.146045608927705e-05,
|
| 458 |
+
"loss": 23.26278076171875,
|
| 459 |
+
"step": 855
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.6300246103363412,
|
| 463 |
+
"grad_norm": 92.07249450683594,
|
| 464 |
+
"learning_rate": 4.127850557981562e-05,
|
| 465 |
+
"loss": 21.62847900390625,
|
| 466 |
+
"step": 870
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.6581507090120708,
|
| 470 |
+
"grad_norm": 62.01802444458008,
|
| 471 |
+
"learning_rate": 4.1096555070354197e-05,
|
| 472 |
+
"loss": 22.551171875,
|
| 473 |
+
"step": 885
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.6862768076878003,
|
| 477 |
+
"grad_norm": 87.6247787475586,
|
| 478 |
+
"learning_rate": 4.091460456089277e-05,
|
| 479 |
+
"loss": 23.632059733072918,
|
| 480 |
+
"step": 900
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.6862768076878003,
|
| 484 |
+
"eval_accuracy": 0.6898550724637681,
|
| 485 |
+
"eval_loss": 1.4343311786651611,
|
| 486 |
+
"eval_macro_f1": 0.6784067065231657,
|
| 487 |
+
"eval_runtime": 2.2935,
|
| 488 |
+
"eval_samples_per_second": 150.428,
|
| 489 |
+
"eval_steps_per_second": 19.185,
|
| 490 |
+
"step": 900
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.7144029063635298,
|
| 494 |
+
"grad_norm": 77.10883331298828,
|
| 495 |
+
"learning_rate": 4.0732654051431344e-05,
|
| 496 |
+
"loss": 23.429276529947916,
|
| 497 |
+
"step": 915
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.7425290050392594,
|
| 501 |
+
"grad_norm": 88.47496795654297,
|
| 502 |
+
"learning_rate": 4.055070354196992e-05,
|
| 503 |
+
"loss": 23.187703450520832,
|
| 504 |
+
"step": 930
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.770655103714989,
|
| 508 |
+
"grad_norm": 104.27533721923828,
|
| 509 |
+
"learning_rate": 4.036875303250849e-05,
|
| 510 |
+
"loss": 24.269075520833333,
|
| 511 |
+
"step": 945
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.7987812023907184,
|
| 515 |
+
"grad_norm": 67.3711166381836,
|
| 516 |
+
"learning_rate": 4.0186802523047065e-05,
|
| 517 |
+
"loss": 22.98969930013021,
|
| 518 |
+
"step": 960
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.826907301066448,
|
| 522 |
+
"grad_norm": 67.43853759765625,
|
| 523 |
+
"learning_rate": 4.0004852013585645e-05,
|
| 524 |
+
"loss": 23.56575724283854,
|
| 525 |
+
"step": 975
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.8550333997421773,
|
| 529 |
+
"grad_norm": 77.04778289794922,
|
| 530 |
+
"learning_rate": 3.982290150412422e-05,
|
| 531 |
+
"loss": 22.3833251953125,
|
| 532 |
+
"step": 990
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.883159498417907,
|
| 536 |
+
"grad_norm": 83.1104507446289,
|
| 537 |
+
"learning_rate": 3.9640950994662786e-05,
|
| 538 |
+
"loss": 22.058768717447915,
|
| 539 |
+
"step": 1005
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.9112855970936364,
|
| 543 |
+
"grad_norm": 67.31427001953125,
|
| 544 |
+
"learning_rate": 3.945900048520136e-05,
|
| 545 |
+
"loss": 23.626953125,
|
| 546 |
+
"step": 1020
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.939411695769366,
|
| 550 |
+
"grad_norm": 78.14697265625,
|
| 551 |
+
"learning_rate": 3.927704997573993e-05,
|
| 552 |
+
"loss": 23.199896240234374,
|
| 553 |
+
"step": 1035
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.9675377944450956,
|
| 557 |
+
"grad_norm": 86.21821594238281,
|
| 558 |
+
"learning_rate": 3.909509946627851e-05,
|
| 559 |
+
"loss": 22.229060872395834,
|
| 560 |
+
"step": 1050
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.9675377944450956,
|
| 564 |
+
"eval_accuracy": 0.6840579710144927,
|
| 565 |
+
"eval_loss": 1.3762412071228027,
|
| 566 |
+
"eval_macro_f1": 0.6729193842335214,
|
| 567 |
+
"eval_runtime": 2.2854,
|
| 568 |
+
"eval_samples_per_second": 150.959,
|
| 569 |
+
"eval_steps_per_second": 19.253,
|
| 570 |
+
"step": 1050
|
| 571 |
+
}
|
| 572 |
+
],
|
| 573 |
+
"logging_steps": 15,
|
| 574 |
+
"max_steps": 4272,
|
| 575 |
+
"num_input_tokens_seen": 0,
|
| 576 |
+
"num_train_epochs": 8,
|
| 577 |
+
"save_steps": 150,
|
| 578 |
+
"stateful_callbacks": {
|
| 579 |
+
"TrainerControl": {
|
| 580 |
+
"args": {
|
| 581 |
+
"should_epoch_stop": false,
|
| 582 |
+
"should_evaluate": false,
|
| 583 |
+
"should_log": false,
|
| 584 |
+
"should_save": true,
|
| 585 |
+
"should_training_stop": false
|
| 586 |
+
},
|
| 587 |
+
"attributes": {}
|
| 588 |
+
}
|
| 589 |
+
},
|
| 590 |
+
"total_flos": 2474585240895488.0,
|
| 591 |
+
"train_batch_size": 2,
|
| 592 |
+
"trial_name": null,
|
| 593 |
+
"trial_params": null
|
| 594 |
+
}
|
sft/checkpoint-1050/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37d5b6b59a9b3ebbb703393ea1b80963b65b36ea5e43b5614682c24b6cd469ff
|
| 3 |
+
size 5201
|