Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +13 -0
- all_results.json +7 -0
- checkpoint-50/README.md +202 -0
- checkpoint-50/adapter_config.json +34 -0
- checkpoint-50/adapter_model.safetensors +3 -0
- checkpoint-50/added_tokens.json +13 -0
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/special_tokens_map.json +24 -0
- checkpoint-50/tokenizer.json +0 -0
- checkpoint-50/tokenizer.model +3 -0
- checkpoint-50/tokenizer_config.json +130 -0
- checkpoint-50/trainer_state.json +783 -0
- checkpoint-50/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +130 -0
- train_results.json +7 -0
- trainer_state.json +927 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": "unsloth",
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": true
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d29a5fa7ec06df6a7ca72300e931eca019a45d3922d8b9e3b5d799c4bc7989f4
|
| 3 |
+
size 239135488
|
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.3115796759977179,
|
| 4 |
+
"train_runtime": 2023.6846,
|
| 5 |
+
"train_samples_per_second": 0.918,
|
| 6 |
+
"train_steps_per_second": 0.029
|
| 7 |
+
}
|
checkpoint-50/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-50/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
|
| 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": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": "unsloth",
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": true
|
| 34 |
+
}
|
checkpoint-50/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93b9a964163327b23110bba3a75230ef484698f4f17f04f73b73ac1b05de24c7
|
| 3 |
+
size 239135488
|
checkpoint-50/added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
checkpoint-50/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da613aad0a24b740dbdbe365b30b5174653295859dba4e3b32c1d73a74d421fc
|
| 3 |
+
size 478419450
|
checkpoint-50/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d2ee366fddbdbf93b963fd76d685132dda784901c1e676aa0ba89a3a8d73d13
|
| 3 |
+
size 14244
|
checkpoint-50/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17b3ca82f560484e0770233c85055d284818a22302a9a2e8c525a518582c723e
|
| 3 |
+
size 1064
|
checkpoint-50/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-50/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-50/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-50/tokenizer_config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|assistant|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<|placeholder1|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<|placeholder2|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<|placeholder3|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|placeholder4|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|system|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": true,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": true,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<|placeholder5|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<|placeholder6|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<|user|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": true,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"bos_token": "<s>",
|
| 119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
| 120 |
+
"clean_up_tokenization_spaces": false,
|
| 121 |
+
"eos_token": "<|endoftext|>",
|
| 122 |
+
"legacy": false,
|
| 123 |
+
"model_max_length": 4096,
|
| 124 |
+
"pad_token": "<unk>",
|
| 125 |
+
"padding_side": "right",
|
| 126 |
+
"sp_model_kwargs": {},
|
| 127 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 128 |
+
"unk_token": "<unk>",
|
| 129 |
+
"use_default_system_prompt": false
|
| 130 |
+
}
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2132208347320557,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoints/2024-06-10_15-37-32/checkpoint-50",
|
| 4 |
+
"epoch": 0.847457627118644,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01694915254237288,
|
| 13 |
+
"grad_norm": 8.13034439086914,
|
| 14 |
+
"learning_rate": 6.666666666666667e-05,
|
| 15 |
+
"loss": 2.9658,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01694915254237288,
|
| 20 |
+
"eval_loss": 2.9201831817626953,
|
| 21 |
+
"eval_runtime": 20.1288,
|
| 22 |
+
"eval_samples_per_second": 7.75,
|
| 23 |
+
"eval_steps_per_second": 0.497,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03389830508474576,
|
| 28 |
+
"grad_norm": 7.588105201721191,
|
| 29 |
+
"learning_rate": 0.00013333333333333334,
|
| 30 |
+
"loss": 2.8251,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03389830508474576,
|
| 35 |
+
"eval_loss": 2.1139814853668213,
|
| 36 |
+
"eval_runtime": 20.166,
|
| 37 |
+
"eval_samples_per_second": 7.736,
|
| 38 |
+
"eval_steps_per_second": 0.496,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05084745762711865,
|
| 43 |
+
"grad_norm": 4.060599327087402,
|
| 44 |
+
"learning_rate": 0.0002,
|
| 45 |
+
"loss": 2.1092,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.05084745762711865,
|
| 50 |
+
"eval_loss": 1.677042841911316,
|
| 51 |
+
"eval_runtime": 20.2239,
|
| 52 |
+
"eval_samples_per_second": 7.714,
|
| 53 |
+
"eval_steps_per_second": 0.494,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.06779661016949153,
|
| 58 |
+
"grad_norm": 1.6822344064712524,
|
| 59 |
+
"learning_rate": 0.0002666666666666667,
|
| 60 |
+
"loss": 1.6407,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.06779661016949153,
|
| 65 |
+
"eval_loss": 1.512647271156311,
|
| 66 |
+
"eval_runtime": 20.2526,
|
| 67 |
+
"eval_samples_per_second": 7.703,
|
| 68 |
+
"eval_steps_per_second": 0.494,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.0847457627118644,
|
| 73 |
+
"grad_norm": 0.8077585697174072,
|
| 74 |
+
"learning_rate": 0.0003333333333333334,
|
| 75 |
+
"loss": 1.48,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.0847457627118644,
|
| 80 |
+
"eval_loss": 1.4189282655715942,
|
| 81 |
+
"eval_runtime": 20.3082,
|
| 82 |
+
"eval_samples_per_second": 7.682,
|
| 83 |
+
"eval_steps_per_second": 0.492,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.1016949152542373,
|
| 88 |
+
"grad_norm": 0.7878511548042297,
|
| 89 |
+
"learning_rate": 0.0004,
|
| 90 |
+
"loss": 1.4139,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.1016949152542373,
|
| 95 |
+
"eval_loss": 1.3850855827331543,
|
| 96 |
+
"eval_runtime": 20.3109,
|
| 97 |
+
"eval_samples_per_second": 7.681,
|
| 98 |
+
"eval_steps_per_second": 0.492,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.11864406779661017,
|
| 103 |
+
"grad_norm": 0.49660709500312805,
|
| 104 |
+
"learning_rate": 0.00039245283018867925,
|
| 105 |
+
"loss": 1.392,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.11864406779661017,
|
| 110 |
+
"eval_loss": 1.425636887550354,
|
| 111 |
+
"eval_runtime": 20.1672,
|
| 112 |
+
"eval_samples_per_second": 7.735,
|
| 113 |
+
"eval_steps_per_second": 0.496,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.13559322033898305,
|
| 118 |
+
"grad_norm": 1.5075709819793701,
|
| 119 |
+
"learning_rate": 0.00038490566037735854,
|
| 120 |
+
"loss": 1.3954,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13559322033898305,
|
| 125 |
+
"eval_loss": 1.347417950630188,
|
| 126 |
+
"eval_runtime": 20.2898,
|
| 127 |
+
"eval_samples_per_second": 7.689,
|
| 128 |
+
"eval_steps_per_second": 0.493,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.15254237288135594,
|
| 133 |
+
"grad_norm": 0.517346203327179,
|
| 134 |
+
"learning_rate": 0.00037735849056603777,
|
| 135 |
+
"loss": 1.3231,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.15254237288135594,
|
| 140 |
+
"eval_loss": 1.314124345779419,
|
| 141 |
+
"eval_runtime": 20.2626,
|
| 142 |
+
"eval_samples_per_second": 7.699,
|
| 143 |
+
"eval_steps_per_second": 0.494,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1694915254237288,
|
| 148 |
+
"grad_norm": 0.2546059191226959,
|
| 149 |
+
"learning_rate": 0.000369811320754717,
|
| 150 |
+
"loss": 1.2504,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.1694915254237288,
|
| 155 |
+
"eval_loss": 1.2959833145141602,
|
| 156 |
+
"eval_runtime": 20.2614,
|
| 157 |
+
"eval_samples_per_second": 7.699,
|
| 158 |
+
"eval_steps_per_second": 0.494,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1864406779661017,
|
| 163 |
+
"grad_norm": 0.1385415643453598,
|
| 164 |
+
"learning_rate": 0.00036226415094339624,
|
| 165 |
+
"loss": 1.274,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1864406779661017,
|
| 170 |
+
"eval_loss": 1.2856695652008057,
|
| 171 |
+
"eval_runtime": 20.2637,
|
| 172 |
+
"eval_samples_per_second": 7.698,
|
| 173 |
+
"eval_steps_per_second": 0.493,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.2033898305084746,
|
| 178 |
+
"grad_norm": 0.13630884885787964,
|
| 179 |
+
"learning_rate": 0.0003547169811320755,
|
| 180 |
+
"loss": 1.2657,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.2033898305084746,
|
| 185 |
+
"eval_loss": 1.2764700651168823,
|
| 186 |
+
"eval_runtime": 20.2991,
|
| 187 |
+
"eval_samples_per_second": 7.685,
|
| 188 |
+
"eval_steps_per_second": 0.493,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.22033898305084745,
|
| 193 |
+
"grad_norm": 0.12581680715084076,
|
| 194 |
+
"learning_rate": 0.00034716981132075476,
|
| 195 |
+
"loss": 1.2436,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.22033898305084745,
|
| 200 |
+
"eval_loss": 1.269006609916687,
|
| 201 |
+
"eval_runtime": 20.2819,
|
| 202 |
+
"eval_samples_per_second": 7.692,
|
| 203 |
+
"eval_steps_per_second": 0.493,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.23728813559322035,
|
| 208 |
+
"grad_norm": 0.12691529095172882,
|
| 209 |
+
"learning_rate": 0.000339622641509434,
|
| 210 |
+
"loss": 1.2478,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.23728813559322035,
|
| 215 |
+
"eval_loss": 1.2635128498077393,
|
| 216 |
+
"eval_runtime": 20.2714,
|
| 217 |
+
"eval_samples_per_second": 7.696,
|
| 218 |
+
"eval_steps_per_second": 0.493,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2542372881355932,
|
| 223 |
+
"grad_norm": 0.12215649336576462,
|
| 224 |
+
"learning_rate": 0.0003320754716981132,
|
| 225 |
+
"loss": 1.2741,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2542372881355932,
|
| 230 |
+
"eval_loss": 1.2581740617752075,
|
| 231 |
+
"eval_runtime": 20.2259,
|
| 232 |
+
"eval_samples_per_second": 7.713,
|
| 233 |
+
"eval_steps_per_second": 0.494,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2711864406779661,
|
| 238 |
+
"grad_norm": 0.11825581640005112,
|
| 239 |
+
"learning_rate": 0.0003245283018867925,
|
| 240 |
+
"loss": 1.2508,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2711864406779661,
|
| 245 |
+
"eval_loss": 1.253954529762268,
|
| 246 |
+
"eval_runtime": 20.3786,
|
| 247 |
+
"eval_samples_per_second": 7.655,
|
| 248 |
+
"eval_steps_per_second": 0.491,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.288135593220339,
|
| 253 |
+
"grad_norm": 0.11941225081682205,
|
| 254 |
+
"learning_rate": 0.00031698113207547174,
|
| 255 |
+
"loss": 1.2587,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.288135593220339,
|
| 260 |
+
"eval_loss": 1.2502553462982178,
|
| 261 |
+
"eval_runtime": 20.2903,
|
| 262 |
+
"eval_samples_per_second": 7.688,
|
| 263 |
+
"eval_steps_per_second": 0.493,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.3050847457627119,
|
| 268 |
+
"grad_norm": 0.11191528290510178,
|
| 269 |
+
"learning_rate": 0.000309433962264151,
|
| 270 |
+
"loss": 1.2692,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3050847457627119,
|
| 275 |
+
"eval_loss": 1.2474076747894287,
|
| 276 |
+
"eval_runtime": 20.3196,
|
| 277 |
+
"eval_samples_per_second": 7.677,
|
| 278 |
+
"eval_steps_per_second": 0.492,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.3220338983050847,
|
| 283 |
+
"grad_norm": 0.11136776953935623,
|
| 284 |
+
"learning_rate": 0.0003018867924528302,
|
| 285 |
+
"loss": 1.2347,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.3220338983050847,
|
| 290 |
+
"eval_loss": 1.2446962594985962,
|
| 291 |
+
"eval_runtime": 20.1872,
|
| 292 |
+
"eval_samples_per_second": 7.728,
|
| 293 |
+
"eval_steps_per_second": 0.495,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.3389830508474576,
|
| 298 |
+
"grad_norm": 0.1218048483133316,
|
| 299 |
+
"learning_rate": 0.00029433962264150944,
|
| 300 |
+
"loss": 1.2619,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.3389830508474576,
|
| 305 |
+
"eval_loss": 1.2424840927124023,
|
| 306 |
+
"eval_runtime": 20.354,
|
| 307 |
+
"eval_samples_per_second": 7.664,
|
| 308 |
+
"eval_steps_per_second": 0.491,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.3559322033898305,
|
| 313 |
+
"grad_norm": 0.11501109600067139,
|
| 314 |
+
"learning_rate": 0.00028679245283018867,
|
| 315 |
+
"loss": 1.2759,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.3559322033898305,
|
| 320 |
+
"eval_loss": 1.2401403188705444,
|
| 321 |
+
"eval_runtime": 20.2503,
|
| 322 |
+
"eval_samples_per_second": 7.704,
|
| 323 |
+
"eval_steps_per_second": 0.494,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3728813559322034,
|
| 328 |
+
"grad_norm": 0.11031804978847504,
|
| 329 |
+
"learning_rate": 0.0002792452830188679,
|
| 330 |
+
"loss": 1.2141,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3728813559322034,
|
| 335 |
+
"eval_loss": 1.2376986742019653,
|
| 336 |
+
"eval_runtime": 20.2534,
|
| 337 |
+
"eval_samples_per_second": 7.702,
|
| 338 |
+
"eval_steps_per_second": 0.494,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3898305084745763,
|
| 343 |
+
"grad_norm": 0.10441834479570389,
|
| 344 |
+
"learning_rate": 0.0002716981132075472,
|
| 345 |
+
"loss": 1.2333,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3898305084745763,
|
| 350 |
+
"eval_loss": 1.2357385158538818,
|
| 351 |
+
"eval_runtime": 20.2681,
|
| 352 |
+
"eval_samples_per_second": 7.697,
|
| 353 |
+
"eval_steps_per_second": 0.493,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.4067796610169492,
|
| 358 |
+
"grad_norm": 0.10192928463220596,
|
| 359 |
+
"learning_rate": 0.0002641509433962264,
|
| 360 |
+
"loss": 1.2022,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.4067796610169492,
|
| 365 |
+
"eval_loss": 1.23451828956604,
|
| 366 |
+
"eval_runtime": 20.2473,
|
| 367 |
+
"eval_samples_per_second": 7.705,
|
| 368 |
+
"eval_steps_per_second": 0.494,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.423728813559322,
|
| 373 |
+
"grad_norm": 0.11488105356693268,
|
| 374 |
+
"learning_rate": 0.00025660377358490566,
|
| 375 |
+
"loss": 1.2704,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.423728813559322,
|
| 380 |
+
"eval_loss": 1.2329152822494507,
|
| 381 |
+
"eval_runtime": 20.2073,
|
| 382 |
+
"eval_samples_per_second": 7.72,
|
| 383 |
+
"eval_steps_per_second": 0.495,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.4406779661016949,
|
| 388 |
+
"grad_norm": 0.10615106672048569,
|
| 389 |
+
"learning_rate": 0.0002490566037735849,
|
| 390 |
+
"loss": 1.2121,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.4406779661016949,
|
| 395 |
+
"eval_loss": 1.2312597036361694,
|
| 396 |
+
"eval_runtime": 20.2584,
|
| 397 |
+
"eval_samples_per_second": 7.701,
|
| 398 |
+
"eval_steps_per_second": 0.494,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.4576271186440678,
|
| 403 |
+
"grad_norm": 0.10923189669847488,
|
| 404 |
+
"learning_rate": 0.00024150943396226415,
|
| 405 |
+
"loss": 1.217,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.4576271186440678,
|
| 410 |
+
"eval_loss": 1.2297359704971313,
|
| 411 |
+
"eval_runtime": 20.3031,
|
| 412 |
+
"eval_samples_per_second": 7.684,
|
| 413 |
+
"eval_steps_per_second": 0.493,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.4745762711864407,
|
| 418 |
+
"grad_norm": 0.0974133163690567,
|
| 419 |
+
"learning_rate": 0.0002339622641509434,
|
| 420 |
+
"loss": 1.1978,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.4745762711864407,
|
| 425 |
+
"eval_loss": 1.2286475896835327,
|
| 426 |
+
"eval_runtime": 20.3065,
|
| 427 |
+
"eval_samples_per_second": 7.682,
|
| 428 |
+
"eval_steps_per_second": 0.492,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4915254237288136,
|
| 433 |
+
"grad_norm": 0.10017339885234833,
|
| 434 |
+
"learning_rate": 0.00022641509433962264,
|
| 435 |
+
"loss": 1.1895,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.4915254237288136,
|
| 440 |
+
"eval_loss": 1.2275595664978027,
|
| 441 |
+
"eval_runtime": 20.2412,
|
| 442 |
+
"eval_samples_per_second": 7.707,
|
| 443 |
+
"eval_steps_per_second": 0.494,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5084745762711864,
|
| 448 |
+
"grad_norm": 0.09858958423137665,
|
| 449 |
+
"learning_rate": 0.0002188679245283019,
|
| 450 |
+
"loss": 1.1669,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5084745762711864,
|
| 455 |
+
"eval_loss": 1.2265597581863403,
|
| 456 |
+
"eval_runtime": 20.3183,
|
| 457 |
+
"eval_samples_per_second": 7.678,
|
| 458 |
+
"eval_steps_per_second": 0.492,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.5254237288135594,
|
| 463 |
+
"grad_norm": 0.10503731667995453,
|
| 464 |
+
"learning_rate": 0.00021132075471698113,
|
| 465 |
+
"loss": 1.2623,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.5254237288135594,
|
| 470 |
+
"eval_loss": 1.2255297899246216,
|
| 471 |
+
"eval_runtime": 20.2895,
|
| 472 |
+
"eval_samples_per_second": 7.689,
|
| 473 |
+
"eval_steps_per_second": 0.493,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.5423728813559322,
|
| 478 |
+
"grad_norm": 0.09913704544305801,
|
| 479 |
+
"learning_rate": 0.0002037735849056604,
|
| 480 |
+
"loss": 1.1958,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.5423728813559322,
|
| 485 |
+
"eval_loss": 1.2245802879333496,
|
| 486 |
+
"eval_runtime": 20.2724,
|
| 487 |
+
"eval_samples_per_second": 7.695,
|
| 488 |
+
"eval_steps_per_second": 0.493,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.559322033898305,
|
| 493 |
+
"grad_norm": 0.10186842828989029,
|
| 494 |
+
"learning_rate": 0.00019622641509433963,
|
| 495 |
+
"loss": 1.214,
|
| 496 |
+
"step": 33
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.559322033898305,
|
| 500 |
+
"eval_loss": 1.2234857082366943,
|
| 501 |
+
"eval_runtime": 20.2474,
|
| 502 |
+
"eval_samples_per_second": 7.705,
|
| 503 |
+
"eval_steps_per_second": 0.494,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.576271186440678,
|
| 508 |
+
"grad_norm": 0.10213778913021088,
|
| 509 |
+
"learning_rate": 0.00018867924528301889,
|
| 510 |
+
"loss": 1.221,
|
| 511 |
+
"step": 34
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.576271186440678,
|
| 515 |
+
"eval_loss": 1.222362995147705,
|
| 516 |
+
"eval_runtime": 20.335,
|
| 517 |
+
"eval_samples_per_second": 7.672,
|
| 518 |
+
"eval_steps_per_second": 0.492,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.5932203389830508,
|
| 523 |
+
"grad_norm": 0.10020826011896133,
|
| 524 |
+
"learning_rate": 0.00018113207547169812,
|
| 525 |
+
"loss": 1.2528,
|
| 526 |
+
"step": 35
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.5932203389830508,
|
| 530 |
+
"eval_loss": 1.2214902639389038,
|
| 531 |
+
"eval_runtime": 20.286,
|
| 532 |
+
"eval_samples_per_second": 7.69,
|
| 533 |
+
"eval_steps_per_second": 0.493,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6101694915254238,
|
| 538 |
+
"grad_norm": 0.10454258322715759,
|
| 539 |
+
"learning_rate": 0.00017358490566037738,
|
| 540 |
+
"loss": 1.2263,
|
| 541 |
+
"step": 36
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6101694915254238,
|
| 545 |
+
"eval_loss": 1.2206357717514038,
|
| 546 |
+
"eval_runtime": 20.2459,
|
| 547 |
+
"eval_samples_per_second": 7.705,
|
| 548 |
+
"eval_steps_per_second": 0.494,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6271186440677966,
|
| 553 |
+
"grad_norm": 0.09862061589956284,
|
| 554 |
+
"learning_rate": 0.0001660377358490566,
|
| 555 |
+
"loss": 1.1575,
|
| 556 |
+
"step": 37
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6271186440677966,
|
| 560 |
+
"eval_loss": 1.2198610305786133,
|
| 561 |
+
"eval_runtime": 20.2576,
|
| 562 |
+
"eval_samples_per_second": 7.701,
|
| 563 |
+
"eval_steps_per_second": 0.494,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.6440677966101694,
|
| 568 |
+
"grad_norm": 0.09934031218290329,
|
| 569 |
+
"learning_rate": 0.00015849056603773587,
|
| 570 |
+
"loss": 1.226,
|
| 571 |
+
"step": 38
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.6440677966101694,
|
| 575 |
+
"eval_loss": 1.2193130254745483,
|
| 576 |
+
"eval_runtime": 20.2923,
|
| 577 |
+
"eval_samples_per_second": 7.688,
|
| 578 |
+
"eval_steps_per_second": 0.493,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.6610169491525424,
|
| 583 |
+
"grad_norm": 0.09604943543672562,
|
| 584 |
+
"learning_rate": 0.0001509433962264151,
|
| 585 |
+
"loss": 1.1985,
|
| 586 |
+
"step": 39
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.6610169491525424,
|
| 590 |
+
"eval_loss": 1.2188695669174194,
|
| 591 |
+
"eval_runtime": 20.2462,
|
| 592 |
+
"eval_samples_per_second": 7.705,
|
| 593 |
+
"eval_steps_per_second": 0.494,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.6779661016949152,
|
| 598 |
+
"grad_norm": 0.10007863491773605,
|
| 599 |
+
"learning_rate": 0.00014339622641509434,
|
| 600 |
+
"loss": 1.2235,
|
| 601 |
+
"step": 40
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.6779661016949152,
|
| 605 |
+
"eval_loss": 1.2182458639144897,
|
| 606 |
+
"eval_runtime": 20.3015,
|
| 607 |
+
"eval_samples_per_second": 7.684,
|
| 608 |
+
"eval_steps_per_second": 0.493,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.6949152542372882,
|
| 613 |
+
"grad_norm": 0.10070552676916122,
|
| 614 |
+
"learning_rate": 0.0001358490566037736,
|
| 615 |
+
"loss": 1.1838,
|
| 616 |
+
"step": 41
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.6949152542372882,
|
| 620 |
+
"eval_loss": 1.217565655708313,
|
| 621 |
+
"eval_runtime": 20.3449,
|
| 622 |
+
"eval_samples_per_second": 7.668,
|
| 623 |
+
"eval_steps_per_second": 0.492,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.711864406779661,
|
| 628 |
+
"grad_norm": 0.10276733338832855,
|
| 629 |
+
"learning_rate": 0.00012830188679245283,
|
| 630 |
+
"loss": 1.2086,
|
| 631 |
+
"step": 42
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.711864406779661,
|
| 635 |
+
"eval_loss": 1.2170318365097046,
|
| 636 |
+
"eval_runtime": 20.2482,
|
| 637 |
+
"eval_samples_per_second": 7.704,
|
| 638 |
+
"eval_steps_per_second": 0.494,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7288135593220338,
|
| 643 |
+
"grad_norm": 0.09609915316104889,
|
| 644 |
+
"learning_rate": 0.00012075471698113207,
|
| 645 |
+
"loss": 1.1769,
|
| 646 |
+
"step": 43
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7288135593220338,
|
| 650 |
+
"eval_loss": 1.2166293859481812,
|
| 651 |
+
"eval_runtime": 20.2547,
|
| 652 |
+
"eval_samples_per_second": 7.702,
|
| 653 |
+
"eval_steps_per_second": 0.494,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7457627118644068,
|
| 658 |
+
"grad_norm": 0.09979274868965149,
|
| 659 |
+
"learning_rate": 0.00011320754716981132,
|
| 660 |
+
"loss": 1.205,
|
| 661 |
+
"step": 44
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7457627118644068,
|
| 665 |
+
"eval_loss": 1.2162456512451172,
|
| 666 |
+
"eval_runtime": 20.2557,
|
| 667 |
+
"eval_samples_per_second": 7.702,
|
| 668 |
+
"eval_steps_per_second": 0.494,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.7627118644067796,
|
| 673 |
+
"grad_norm": 0.10145589709281921,
|
| 674 |
+
"learning_rate": 0.00010566037735849057,
|
| 675 |
+
"loss": 1.2559,
|
| 676 |
+
"step": 45
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.7627118644067796,
|
| 680 |
+
"eval_loss": 1.2157071828842163,
|
| 681 |
+
"eval_runtime": 20.2591,
|
| 682 |
+
"eval_samples_per_second": 7.7,
|
| 683 |
+
"eval_steps_per_second": 0.494,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.7796610169491526,
|
| 688 |
+
"grad_norm": 0.10324625670909882,
|
| 689 |
+
"learning_rate": 9.811320754716981e-05,
|
| 690 |
+
"loss": 1.1895,
|
| 691 |
+
"step": 46
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.7796610169491526,
|
| 695 |
+
"eval_loss": 1.2151949405670166,
|
| 696 |
+
"eval_runtime": 20.2914,
|
| 697 |
+
"eval_samples_per_second": 7.688,
|
| 698 |
+
"eval_steps_per_second": 0.493,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.7966101694915254,
|
| 703 |
+
"grad_norm": 0.09847307205200195,
|
| 704 |
+
"learning_rate": 9.056603773584906e-05,
|
| 705 |
+
"loss": 1.1881,
|
| 706 |
+
"step": 47
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.7966101694915254,
|
| 710 |
+
"eval_loss": 1.2146611213684082,
|
| 711 |
+
"eval_runtime": 20.2529,
|
| 712 |
+
"eval_samples_per_second": 7.703,
|
| 713 |
+
"eval_steps_per_second": 0.494,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.8135593220338984,
|
| 718 |
+
"grad_norm": 0.09867937117815018,
|
| 719 |
+
"learning_rate": 8.30188679245283e-05,
|
| 720 |
+
"loss": 1.209,
|
| 721 |
+
"step": 48
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.8135593220338984,
|
| 725 |
+
"eval_loss": 1.214185118675232,
|
| 726 |
+
"eval_runtime": 20.359,
|
| 727 |
+
"eval_samples_per_second": 7.662,
|
| 728 |
+
"eval_steps_per_second": 0.491,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.8305084745762712,
|
| 733 |
+
"grad_norm": 0.09706506878137589,
|
| 734 |
+
"learning_rate": 7.547169811320755e-05,
|
| 735 |
+
"loss": 1.2062,
|
| 736 |
+
"step": 49
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.8305084745762712,
|
| 740 |
+
"eval_loss": 1.2136766910552979,
|
| 741 |
+
"eval_runtime": 20.276,
|
| 742 |
+
"eval_samples_per_second": 7.694,
|
| 743 |
+
"eval_steps_per_second": 0.493,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.847457627118644,
|
| 748 |
+
"grad_norm": 0.09803847968578339,
|
| 749 |
+
"learning_rate": 6.79245283018868e-05,
|
| 750 |
+
"loss": 1.2089,
|
| 751 |
+
"step": 50
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.847457627118644,
|
| 755 |
+
"eval_loss": 1.2132208347320557,
|
| 756 |
+
"eval_runtime": 20.1963,
|
| 757 |
+
"eval_samples_per_second": 7.724,
|
| 758 |
+
"eval_steps_per_second": 0.495,
|
| 759 |
+
"step": 50
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 1,
|
| 763 |
+
"max_steps": 59,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 1,
|
| 766 |
+
"save_steps": 10,
|
| 767 |
+
"stateful_callbacks": {
|
| 768 |
+
"TrainerControl": {
|
| 769 |
+
"args": {
|
| 770 |
+
"should_epoch_stop": false,
|
| 771 |
+
"should_evaluate": false,
|
| 772 |
+
"should_log": false,
|
| 773 |
+
"should_save": true,
|
| 774 |
+
"should_training_stop": false
|
| 775 |
+
},
|
| 776 |
+
"attributes": {}
|
| 777 |
+
}
|
| 778 |
+
},
|
| 779 |
+
"total_flos": 3.71819915771904e+16,
|
| 780 |
+
"train_batch_size": 32,
|
| 781 |
+
"trial_name": null,
|
| 782 |
+
"trial_params": null
|
| 783 |
+
}
|
checkpoint-50/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587a975ca5d52e7de4ed67c53c113d801a25590e7ec8458e33153b0def14267d
|
| 3 |
+
size 5688
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|assistant|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<|placeholder1|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<|placeholder2|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<|placeholder3|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|placeholder4|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|system|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": true,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": true,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<|placeholder5|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<|placeholder6|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<|user|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": true,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"bos_token": "<s>",
|
| 119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
| 120 |
+
"clean_up_tokenization_spaces": false,
|
| 121 |
+
"eos_token": "<|endoftext|>",
|
| 122 |
+
"legacy": false,
|
| 123 |
+
"model_max_length": 4096,
|
| 124 |
+
"pad_token": "<unk>",
|
| 125 |
+
"padding_side": "right",
|
| 126 |
+
"sp_model_kwargs": {},
|
| 127 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 128 |
+
"unk_token": "<unk>",
|
| 129 |
+
"use_default_system_prompt": false
|
| 130 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.3115796759977179,
|
| 4 |
+
"train_runtime": 2023.6846,
|
| 5 |
+
"train_samples_per_second": 0.918,
|
| 6 |
+
"train_steps_per_second": 0.029
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,927 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2132208347320557,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoints/2024-06-10_15-37-32/checkpoint-50",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 59,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01694915254237288,
|
| 13 |
+
"grad_norm": 8.13034439086914,
|
| 14 |
+
"learning_rate": 6.666666666666667e-05,
|
| 15 |
+
"loss": 2.9658,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01694915254237288,
|
| 20 |
+
"eval_loss": 2.9201831817626953,
|
| 21 |
+
"eval_runtime": 20.1288,
|
| 22 |
+
"eval_samples_per_second": 7.75,
|
| 23 |
+
"eval_steps_per_second": 0.497,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03389830508474576,
|
| 28 |
+
"grad_norm": 7.588105201721191,
|
| 29 |
+
"learning_rate": 0.00013333333333333334,
|
| 30 |
+
"loss": 2.8251,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03389830508474576,
|
| 35 |
+
"eval_loss": 2.1139814853668213,
|
| 36 |
+
"eval_runtime": 20.166,
|
| 37 |
+
"eval_samples_per_second": 7.736,
|
| 38 |
+
"eval_steps_per_second": 0.496,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05084745762711865,
|
| 43 |
+
"grad_norm": 4.060599327087402,
|
| 44 |
+
"learning_rate": 0.0002,
|
| 45 |
+
"loss": 2.1092,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.05084745762711865,
|
| 50 |
+
"eval_loss": 1.677042841911316,
|
| 51 |
+
"eval_runtime": 20.2239,
|
| 52 |
+
"eval_samples_per_second": 7.714,
|
| 53 |
+
"eval_steps_per_second": 0.494,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.06779661016949153,
|
| 58 |
+
"grad_norm": 1.6822344064712524,
|
| 59 |
+
"learning_rate": 0.0002666666666666667,
|
| 60 |
+
"loss": 1.6407,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.06779661016949153,
|
| 65 |
+
"eval_loss": 1.512647271156311,
|
| 66 |
+
"eval_runtime": 20.2526,
|
| 67 |
+
"eval_samples_per_second": 7.703,
|
| 68 |
+
"eval_steps_per_second": 0.494,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.0847457627118644,
|
| 73 |
+
"grad_norm": 0.8077585697174072,
|
| 74 |
+
"learning_rate": 0.0003333333333333334,
|
| 75 |
+
"loss": 1.48,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.0847457627118644,
|
| 80 |
+
"eval_loss": 1.4189282655715942,
|
| 81 |
+
"eval_runtime": 20.3082,
|
| 82 |
+
"eval_samples_per_second": 7.682,
|
| 83 |
+
"eval_steps_per_second": 0.492,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.1016949152542373,
|
| 88 |
+
"grad_norm": 0.7878511548042297,
|
| 89 |
+
"learning_rate": 0.0004,
|
| 90 |
+
"loss": 1.4139,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.1016949152542373,
|
| 95 |
+
"eval_loss": 1.3850855827331543,
|
| 96 |
+
"eval_runtime": 20.3109,
|
| 97 |
+
"eval_samples_per_second": 7.681,
|
| 98 |
+
"eval_steps_per_second": 0.492,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.11864406779661017,
|
| 103 |
+
"grad_norm": 0.49660709500312805,
|
| 104 |
+
"learning_rate": 0.00039245283018867925,
|
| 105 |
+
"loss": 1.392,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.11864406779661017,
|
| 110 |
+
"eval_loss": 1.425636887550354,
|
| 111 |
+
"eval_runtime": 20.1672,
|
| 112 |
+
"eval_samples_per_second": 7.735,
|
| 113 |
+
"eval_steps_per_second": 0.496,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.13559322033898305,
|
| 118 |
+
"grad_norm": 1.5075709819793701,
|
| 119 |
+
"learning_rate": 0.00038490566037735854,
|
| 120 |
+
"loss": 1.3954,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13559322033898305,
|
| 125 |
+
"eval_loss": 1.347417950630188,
|
| 126 |
+
"eval_runtime": 20.2898,
|
| 127 |
+
"eval_samples_per_second": 7.689,
|
| 128 |
+
"eval_steps_per_second": 0.493,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.15254237288135594,
|
| 133 |
+
"grad_norm": 0.517346203327179,
|
| 134 |
+
"learning_rate": 0.00037735849056603777,
|
| 135 |
+
"loss": 1.3231,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.15254237288135594,
|
| 140 |
+
"eval_loss": 1.314124345779419,
|
| 141 |
+
"eval_runtime": 20.2626,
|
| 142 |
+
"eval_samples_per_second": 7.699,
|
| 143 |
+
"eval_steps_per_second": 0.494,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1694915254237288,
|
| 148 |
+
"grad_norm": 0.2546059191226959,
|
| 149 |
+
"learning_rate": 0.000369811320754717,
|
| 150 |
+
"loss": 1.2504,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.1694915254237288,
|
| 155 |
+
"eval_loss": 1.2959833145141602,
|
| 156 |
+
"eval_runtime": 20.2614,
|
| 157 |
+
"eval_samples_per_second": 7.699,
|
| 158 |
+
"eval_steps_per_second": 0.494,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1864406779661017,
|
| 163 |
+
"grad_norm": 0.1385415643453598,
|
| 164 |
+
"learning_rate": 0.00036226415094339624,
|
| 165 |
+
"loss": 1.274,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1864406779661017,
|
| 170 |
+
"eval_loss": 1.2856695652008057,
|
| 171 |
+
"eval_runtime": 20.2637,
|
| 172 |
+
"eval_samples_per_second": 7.698,
|
| 173 |
+
"eval_steps_per_second": 0.493,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.2033898305084746,
|
| 178 |
+
"grad_norm": 0.13630884885787964,
|
| 179 |
+
"learning_rate": 0.0003547169811320755,
|
| 180 |
+
"loss": 1.2657,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.2033898305084746,
|
| 185 |
+
"eval_loss": 1.2764700651168823,
|
| 186 |
+
"eval_runtime": 20.2991,
|
| 187 |
+
"eval_samples_per_second": 7.685,
|
| 188 |
+
"eval_steps_per_second": 0.493,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.22033898305084745,
|
| 193 |
+
"grad_norm": 0.12581680715084076,
|
| 194 |
+
"learning_rate": 0.00034716981132075476,
|
| 195 |
+
"loss": 1.2436,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.22033898305084745,
|
| 200 |
+
"eval_loss": 1.269006609916687,
|
| 201 |
+
"eval_runtime": 20.2819,
|
| 202 |
+
"eval_samples_per_second": 7.692,
|
| 203 |
+
"eval_steps_per_second": 0.493,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.23728813559322035,
|
| 208 |
+
"grad_norm": 0.12691529095172882,
|
| 209 |
+
"learning_rate": 0.000339622641509434,
|
| 210 |
+
"loss": 1.2478,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.23728813559322035,
|
| 215 |
+
"eval_loss": 1.2635128498077393,
|
| 216 |
+
"eval_runtime": 20.2714,
|
| 217 |
+
"eval_samples_per_second": 7.696,
|
| 218 |
+
"eval_steps_per_second": 0.493,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2542372881355932,
|
| 223 |
+
"grad_norm": 0.12215649336576462,
|
| 224 |
+
"learning_rate": 0.0003320754716981132,
|
| 225 |
+
"loss": 1.2741,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2542372881355932,
|
| 230 |
+
"eval_loss": 1.2581740617752075,
|
| 231 |
+
"eval_runtime": 20.2259,
|
| 232 |
+
"eval_samples_per_second": 7.713,
|
| 233 |
+
"eval_steps_per_second": 0.494,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2711864406779661,
|
| 238 |
+
"grad_norm": 0.11825581640005112,
|
| 239 |
+
"learning_rate": 0.0003245283018867925,
|
| 240 |
+
"loss": 1.2508,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2711864406779661,
|
| 245 |
+
"eval_loss": 1.253954529762268,
|
| 246 |
+
"eval_runtime": 20.3786,
|
| 247 |
+
"eval_samples_per_second": 7.655,
|
| 248 |
+
"eval_steps_per_second": 0.491,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.288135593220339,
|
| 253 |
+
"grad_norm": 0.11941225081682205,
|
| 254 |
+
"learning_rate": 0.00031698113207547174,
|
| 255 |
+
"loss": 1.2587,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.288135593220339,
|
| 260 |
+
"eval_loss": 1.2502553462982178,
|
| 261 |
+
"eval_runtime": 20.2903,
|
| 262 |
+
"eval_samples_per_second": 7.688,
|
| 263 |
+
"eval_steps_per_second": 0.493,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.3050847457627119,
|
| 268 |
+
"grad_norm": 0.11191528290510178,
|
| 269 |
+
"learning_rate": 0.000309433962264151,
|
| 270 |
+
"loss": 1.2692,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3050847457627119,
|
| 275 |
+
"eval_loss": 1.2474076747894287,
|
| 276 |
+
"eval_runtime": 20.3196,
|
| 277 |
+
"eval_samples_per_second": 7.677,
|
| 278 |
+
"eval_steps_per_second": 0.492,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.3220338983050847,
|
| 283 |
+
"grad_norm": 0.11136776953935623,
|
| 284 |
+
"learning_rate": 0.0003018867924528302,
|
| 285 |
+
"loss": 1.2347,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.3220338983050847,
|
| 290 |
+
"eval_loss": 1.2446962594985962,
|
| 291 |
+
"eval_runtime": 20.1872,
|
| 292 |
+
"eval_samples_per_second": 7.728,
|
| 293 |
+
"eval_steps_per_second": 0.495,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.3389830508474576,
|
| 298 |
+
"grad_norm": 0.1218048483133316,
|
| 299 |
+
"learning_rate": 0.00029433962264150944,
|
| 300 |
+
"loss": 1.2619,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.3389830508474576,
|
| 305 |
+
"eval_loss": 1.2424840927124023,
|
| 306 |
+
"eval_runtime": 20.354,
|
| 307 |
+
"eval_samples_per_second": 7.664,
|
| 308 |
+
"eval_steps_per_second": 0.491,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.3559322033898305,
|
| 313 |
+
"grad_norm": 0.11501109600067139,
|
| 314 |
+
"learning_rate": 0.00028679245283018867,
|
| 315 |
+
"loss": 1.2759,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.3559322033898305,
|
| 320 |
+
"eval_loss": 1.2401403188705444,
|
| 321 |
+
"eval_runtime": 20.2503,
|
| 322 |
+
"eval_samples_per_second": 7.704,
|
| 323 |
+
"eval_steps_per_second": 0.494,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3728813559322034,
|
| 328 |
+
"grad_norm": 0.11031804978847504,
|
| 329 |
+
"learning_rate": 0.0002792452830188679,
|
| 330 |
+
"loss": 1.2141,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3728813559322034,
|
| 335 |
+
"eval_loss": 1.2376986742019653,
|
| 336 |
+
"eval_runtime": 20.2534,
|
| 337 |
+
"eval_samples_per_second": 7.702,
|
| 338 |
+
"eval_steps_per_second": 0.494,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3898305084745763,
|
| 343 |
+
"grad_norm": 0.10441834479570389,
|
| 344 |
+
"learning_rate": 0.0002716981132075472,
|
| 345 |
+
"loss": 1.2333,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3898305084745763,
|
| 350 |
+
"eval_loss": 1.2357385158538818,
|
| 351 |
+
"eval_runtime": 20.2681,
|
| 352 |
+
"eval_samples_per_second": 7.697,
|
| 353 |
+
"eval_steps_per_second": 0.493,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.4067796610169492,
|
| 358 |
+
"grad_norm": 0.10192928463220596,
|
| 359 |
+
"learning_rate": 0.0002641509433962264,
|
| 360 |
+
"loss": 1.2022,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.4067796610169492,
|
| 365 |
+
"eval_loss": 1.23451828956604,
|
| 366 |
+
"eval_runtime": 20.2473,
|
| 367 |
+
"eval_samples_per_second": 7.705,
|
| 368 |
+
"eval_steps_per_second": 0.494,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.423728813559322,
|
| 373 |
+
"grad_norm": 0.11488105356693268,
|
| 374 |
+
"learning_rate": 0.00025660377358490566,
|
| 375 |
+
"loss": 1.2704,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.423728813559322,
|
| 380 |
+
"eval_loss": 1.2329152822494507,
|
| 381 |
+
"eval_runtime": 20.2073,
|
| 382 |
+
"eval_samples_per_second": 7.72,
|
| 383 |
+
"eval_steps_per_second": 0.495,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.4406779661016949,
|
| 388 |
+
"grad_norm": 0.10615106672048569,
|
| 389 |
+
"learning_rate": 0.0002490566037735849,
|
| 390 |
+
"loss": 1.2121,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.4406779661016949,
|
| 395 |
+
"eval_loss": 1.2312597036361694,
|
| 396 |
+
"eval_runtime": 20.2584,
|
| 397 |
+
"eval_samples_per_second": 7.701,
|
| 398 |
+
"eval_steps_per_second": 0.494,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.4576271186440678,
|
| 403 |
+
"grad_norm": 0.10923189669847488,
|
| 404 |
+
"learning_rate": 0.00024150943396226415,
|
| 405 |
+
"loss": 1.217,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.4576271186440678,
|
| 410 |
+
"eval_loss": 1.2297359704971313,
|
| 411 |
+
"eval_runtime": 20.3031,
|
| 412 |
+
"eval_samples_per_second": 7.684,
|
| 413 |
+
"eval_steps_per_second": 0.493,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.4745762711864407,
|
| 418 |
+
"grad_norm": 0.0974133163690567,
|
| 419 |
+
"learning_rate": 0.0002339622641509434,
|
| 420 |
+
"loss": 1.1978,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.4745762711864407,
|
| 425 |
+
"eval_loss": 1.2286475896835327,
|
| 426 |
+
"eval_runtime": 20.3065,
|
| 427 |
+
"eval_samples_per_second": 7.682,
|
| 428 |
+
"eval_steps_per_second": 0.492,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4915254237288136,
|
| 433 |
+
"grad_norm": 0.10017339885234833,
|
| 434 |
+
"learning_rate": 0.00022641509433962264,
|
| 435 |
+
"loss": 1.1895,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.4915254237288136,
|
| 440 |
+
"eval_loss": 1.2275595664978027,
|
| 441 |
+
"eval_runtime": 20.2412,
|
| 442 |
+
"eval_samples_per_second": 7.707,
|
| 443 |
+
"eval_steps_per_second": 0.494,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5084745762711864,
|
| 448 |
+
"grad_norm": 0.09858958423137665,
|
| 449 |
+
"learning_rate": 0.0002188679245283019,
|
| 450 |
+
"loss": 1.1669,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5084745762711864,
|
| 455 |
+
"eval_loss": 1.2265597581863403,
|
| 456 |
+
"eval_runtime": 20.3183,
|
| 457 |
+
"eval_samples_per_second": 7.678,
|
| 458 |
+
"eval_steps_per_second": 0.492,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.5254237288135594,
|
| 463 |
+
"grad_norm": 0.10503731667995453,
|
| 464 |
+
"learning_rate": 0.00021132075471698113,
|
| 465 |
+
"loss": 1.2623,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.5254237288135594,
|
| 470 |
+
"eval_loss": 1.2255297899246216,
|
| 471 |
+
"eval_runtime": 20.2895,
|
| 472 |
+
"eval_samples_per_second": 7.689,
|
| 473 |
+
"eval_steps_per_second": 0.493,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.5423728813559322,
|
| 478 |
+
"grad_norm": 0.09913704544305801,
|
| 479 |
+
"learning_rate": 0.0002037735849056604,
|
| 480 |
+
"loss": 1.1958,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.5423728813559322,
|
| 485 |
+
"eval_loss": 1.2245802879333496,
|
| 486 |
+
"eval_runtime": 20.2724,
|
| 487 |
+
"eval_samples_per_second": 7.695,
|
| 488 |
+
"eval_steps_per_second": 0.493,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.559322033898305,
|
| 493 |
+
"grad_norm": 0.10186842828989029,
|
| 494 |
+
"learning_rate": 0.00019622641509433963,
|
| 495 |
+
"loss": 1.214,
|
| 496 |
+
"step": 33
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.559322033898305,
|
| 500 |
+
"eval_loss": 1.2234857082366943,
|
| 501 |
+
"eval_runtime": 20.2474,
|
| 502 |
+
"eval_samples_per_second": 7.705,
|
| 503 |
+
"eval_steps_per_second": 0.494,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.576271186440678,
|
| 508 |
+
"grad_norm": 0.10213778913021088,
|
| 509 |
+
"learning_rate": 0.00018867924528301889,
|
| 510 |
+
"loss": 1.221,
|
| 511 |
+
"step": 34
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.576271186440678,
|
| 515 |
+
"eval_loss": 1.222362995147705,
|
| 516 |
+
"eval_runtime": 20.335,
|
| 517 |
+
"eval_samples_per_second": 7.672,
|
| 518 |
+
"eval_steps_per_second": 0.492,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.5932203389830508,
|
| 523 |
+
"grad_norm": 0.10020826011896133,
|
| 524 |
+
"learning_rate": 0.00018113207547169812,
|
| 525 |
+
"loss": 1.2528,
|
| 526 |
+
"step": 35
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.5932203389830508,
|
| 530 |
+
"eval_loss": 1.2214902639389038,
|
| 531 |
+
"eval_runtime": 20.286,
|
| 532 |
+
"eval_samples_per_second": 7.69,
|
| 533 |
+
"eval_steps_per_second": 0.493,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6101694915254238,
|
| 538 |
+
"grad_norm": 0.10454258322715759,
|
| 539 |
+
"learning_rate": 0.00017358490566037738,
|
| 540 |
+
"loss": 1.2263,
|
| 541 |
+
"step": 36
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6101694915254238,
|
| 545 |
+
"eval_loss": 1.2206357717514038,
|
| 546 |
+
"eval_runtime": 20.2459,
|
| 547 |
+
"eval_samples_per_second": 7.705,
|
| 548 |
+
"eval_steps_per_second": 0.494,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6271186440677966,
|
| 553 |
+
"grad_norm": 0.09862061589956284,
|
| 554 |
+
"learning_rate": 0.0001660377358490566,
|
| 555 |
+
"loss": 1.1575,
|
| 556 |
+
"step": 37
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6271186440677966,
|
| 560 |
+
"eval_loss": 1.2198610305786133,
|
| 561 |
+
"eval_runtime": 20.2576,
|
| 562 |
+
"eval_samples_per_second": 7.701,
|
| 563 |
+
"eval_steps_per_second": 0.494,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.6440677966101694,
|
| 568 |
+
"grad_norm": 0.09934031218290329,
|
| 569 |
+
"learning_rate": 0.00015849056603773587,
|
| 570 |
+
"loss": 1.226,
|
| 571 |
+
"step": 38
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.6440677966101694,
|
| 575 |
+
"eval_loss": 1.2193130254745483,
|
| 576 |
+
"eval_runtime": 20.2923,
|
| 577 |
+
"eval_samples_per_second": 7.688,
|
| 578 |
+
"eval_steps_per_second": 0.493,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.6610169491525424,
|
| 583 |
+
"grad_norm": 0.09604943543672562,
|
| 584 |
+
"learning_rate": 0.0001509433962264151,
|
| 585 |
+
"loss": 1.1985,
|
| 586 |
+
"step": 39
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.6610169491525424,
|
| 590 |
+
"eval_loss": 1.2188695669174194,
|
| 591 |
+
"eval_runtime": 20.2462,
|
| 592 |
+
"eval_samples_per_second": 7.705,
|
| 593 |
+
"eval_steps_per_second": 0.494,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.6779661016949152,
|
| 598 |
+
"grad_norm": 0.10007863491773605,
|
| 599 |
+
"learning_rate": 0.00014339622641509434,
|
| 600 |
+
"loss": 1.2235,
|
| 601 |
+
"step": 40
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.6779661016949152,
|
| 605 |
+
"eval_loss": 1.2182458639144897,
|
| 606 |
+
"eval_runtime": 20.3015,
|
| 607 |
+
"eval_samples_per_second": 7.684,
|
| 608 |
+
"eval_steps_per_second": 0.493,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.6949152542372882,
|
| 613 |
+
"grad_norm": 0.10070552676916122,
|
| 614 |
+
"learning_rate": 0.0001358490566037736,
|
| 615 |
+
"loss": 1.1838,
|
| 616 |
+
"step": 41
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.6949152542372882,
|
| 620 |
+
"eval_loss": 1.217565655708313,
|
| 621 |
+
"eval_runtime": 20.3449,
|
| 622 |
+
"eval_samples_per_second": 7.668,
|
| 623 |
+
"eval_steps_per_second": 0.492,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.711864406779661,
|
| 628 |
+
"grad_norm": 0.10276733338832855,
|
| 629 |
+
"learning_rate": 0.00012830188679245283,
|
| 630 |
+
"loss": 1.2086,
|
| 631 |
+
"step": 42
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.711864406779661,
|
| 635 |
+
"eval_loss": 1.2170318365097046,
|
| 636 |
+
"eval_runtime": 20.2482,
|
| 637 |
+
"eval_samples_per_second": 7.704,
|
| 638 |
+
"eval_steps_per_second": 0.494,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7288135593220338,
|
| 643 |
+
"grad_norm": 0.09609915316104889,
|
| 644 |
+
"learning_rate": 0.00012075471698113207,
|
| 645 |
+
"loss": 1.1769,
|
| 646 |
+
"step": 43
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7288135593220338,
|
| 650 |
+
"eval_loss": 1.2166293859481812,
|
| 651 |
+
"eval_runtime": 20.2547,
|
| 652 |
+
"eval_samples_per_second": 7.702,
|
| 653 |
+
"eval_steps_per_second": 0.494,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7457627118644068,
|
| 658 |
+
"grad_norm": 0.09979274868965149,
|
| 659 |
+
"learning_rate": 0.00011320754716981132,
|
| 660 |
+
"loss": 1.205,
|
| 661 |
+
"step": 44
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7457627118644068,
|
| 665 |
+
"eval_loss": 1.2162456512451172,
|
| 666 |
+
"eval_runtime": 20.2557,
|
| 667 |
+
"eval_samples_per_second": 7.702,
|
| 668 |
+
"eval_steps_per_second": 0.494,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.7627118644067796,
|
| 673 |
+
"grad_norm": 0.10145589709281921,
|
| 674 |
+
"learning_rate": 0.00010566037735849057,
|
| 675 |
+
"loss": 1.2559,
|
| 676 |
+
"step": 45
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.7627118644067796,
|
| 680 |
+
"eval_loss": 1.2157071828842163,
|
| 681 |
+
"eval_runtime": 20.2591,
|
| 682 |
+
"eval_samples_per_second": 7.7,
|
| 683 |
+
"eval_steps_per_second": 0.494,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.7796610169491526,
|
| 688 |
+
"grad_norm": 0.10324625670909882,
|
| 689 |
+
"learning_rate": 9.811320754716981e-05,
|
| 690 |
+
"loss": 1.1895,
|
| 691 |
+
"step": 46
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.7796610169491526,
|
| 695 |
+
"eval_loss": 1.2151949405670166,
|
| 696 |
+
"eval_runtime": 20.2914,
|
| 697 |
+
"eval_samples_per_second": 7.688,
|
| 698 |
+
"eval_steps_per_second": 0.493,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.7966101694915254,
|
| 703 |
+
"grad_norm": 0.09847307205200195,
|
| 704 |
+
"learning_rate": 9.056603773584906e-05,
|
| 705 |
+
"loss": 1.1881,
|
| 706 |
+
"step": 47
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.7966101694915254,
|
| 710 |
+
"eval_loss": 1.2146611213684082,
|
| 711 |
+
"eval_runtime": 20.2529,
|
| 712 |
+
"eval_samples_per_second": 7.703,
|
| 713 |
+
"eval_steps_per_second": 0.494,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.8135593220338984,
|
| 718 |
+
"grad_norm": 0.09867937117815018,
|
| 719 |
+
"learning_rate": 8.30188679245283e-05,
|
| 720 |
+
"loss": 1.209,
|
| 721 |
+
"step": 48
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.8135593220338984,
|
| 725 |
+
"eval_loss": 1.214185118675232,
|
| 726 |
+
"eval_runtime": 20.359,
|
| 727 |
+
"eval_samples_per_second": 7.662,
|
| 728 |
+
"eval_steps_per_second": 0.491,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.8305084745762712,
|
| 733 |
+
"grad_norm": 0.09706506878137589,
|
| 734 |
+
"learning_rate": 7.547169811320755e-05,
|
| 735 |
+
"loss": 1.2062,
|
| 736 |
+
"step": 49
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.8305084745762712,
|
| 740 |
+
"eval_loss": 1.2136766910552979,
|
| 741 |
+
"eval_runtime": 20.276,
|
| 742 |
+
"eval_samples_per_second": 7.694,
|
| 743 |
+
"eval_steps_per_second": 0.493,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.847457627118644,
|
| 748 |
+
"grad_norm": 0.09803847968578339,
|
| 749 |
+
"learning_rate": 6.79245283018868e-05,
|
| 750 |
+
"loss": 1.2089,
|
| 751 |
+
"step": 50
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.847457627118644,
|
| 755 |
+
"eval_loss": 1.2132208347320557,
|
| 756 |
+
"eval_runtime": 20.1963,
|
| 757 |
+
"eval_samples_per_second": 7.724,
|
| 758 |
+
"eval_steps_per_second": 0.495,
|
| 759 |
+
"step": 50
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.864406779661017,
|
| 763 |
+
"grad_norm": 0.09517968446016312,
|
| 764 |
+
"learning_rate": 6.037735849056604e-05,
|
| 765 |
+
"loss": 1.2095,
|
| 766 |
+
"step": 51
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.864406779661017,
|
| 770 |
+
"eval_loss": 1.2128576040267944,
|
| 771 |
+
"eval_runtime": 20.2645,
|
| 772 |
+
"eval_samples_per_second": 7.698,
|
| 773 |
+
"eval_steps_per_second": 0.493,
|
| 774 |
+
"step": 51
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.8813559322033898,
|
| 778 |
+
"grad_norm": 0.09574303776025772,
|
| 779 |
+
"learning_rate": 5.283018867924528e-05,
|
| 780 |
+
"loss": 1.1798,
|
| 781 |
+
"step": 52
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.8813559322033898,
|
| 785 |
+
"eval_loss": 1.212473750114441,
|
| 786 |
+
"eval_runtime": 20.2258,
|
| 787 |
+
"eval_samples_per_second": 7.713,
|
| 788 |
+
"eval_steps_per_second": 0.494,
|
| 789 |
+
"step": 52
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.8983050847457628,
|
| 793 |
+
"grad_norm": 0.09871205687522888,
|
| 794 |
+
"learning_rate": 4.528301886792453e-05,
|
| 795 |
+
"loss": 1.1746,
|
| 796 |
+
"step": 53
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.8983050847457628,
|
| 800 |
+
"eval_loss": 1.2121562957763672,
|
| 801 |
+
"eval_runtime": 20.2541,
|
| 802 |
+
"eval_samples_per_second": 7.702,
|
| 803 |
+
"eval_steps_per_second": 0.494,
|
| 804 |
+
"step": 53
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9152542372881356,
|
| 808 |
+
"grad_norm": 0.09647679328918457,
|
| 809 |
+
"learning_rate": 3.7735849056603776e-05,
|
| 810 |
+
"loss": 1.2166,
|
| 811 |
+
"step": 54
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.9152542372881356,
|
| 815 |
+
"eval_loss": 1.2118746042251587,
|
| 816 |
+
"eval_runtime": 20.2835,
|
| 817 |
+
"eval_samples_per_second": 7.691,
|
| 818 |
+
"eval_steps_per_second": 0.493,
|
| 819 |
+
"step": 54
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.9322033898305084,
|
| 823 |
+
"grad_norm": 0.09742645174264908,
|
| 824 |
+
"learning_rate": 3.018867924528302e-05,
|
| 825 |
+
"loss": 1.169,
|
| 826 |
+
"step": 55
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.9322033898305084,
|
| 830 |
+
"eval_loss": 1.2116155624389648,
|
| 831 |
+
"eval_runtime": 20.3096,
|
| 832 |
+
"eval_samples_per_second": 7.681,
|
| 833 |
+
"eval_steps_per_second": 0.492,
|
| 834 |
+
"step": 55
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.9491525423728814,
|
| 838 |
+
"grad_norm": 0.09928184747695923,
|
| 839 |
+
"learning_rate": 2.2641509433962265e-05,
|
| 840 |
+
"loss": 1.1945,
|
| 841 |
+
"step": 56
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.9491525423728814,
|
| 845 |
+
"eval_loss": 1.2114187479019165,
|
| 846 |
+
"eval_runtime": 20.2297,
|
| 847 |
+
"eval_samples_per_second": 7.711,
|
| 848 |
+
"eval_steps_per_second": 0.494,
|
| 849 |
+
"step": 56
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.9661016949152542,
|
| 853 |
+
"grad_norm": 0.10244324803352356,
|
| 854 |
+
"learning_rate": 1.509433962264151e-05,
|
| 855 |
+
"loss": 1.1877,
|
| 856 |
+
"step": 57
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.9661016949152542,
|
| 860 |
+
"eval_loss": 1.2112743854522705,
|
| 861 |
+
"eval_runtime": 20.345,
|
| 862 |
+
"eval_samples_per_second": 7.668,
|
| 863 |
+
"eval_steps_per_second": 0.492,
|
| 864 |
+
"step": 57
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9830508474576272,
|
| 868 |
+
"grad_norm": 0.10198235511779785,
|
| 869 |
+
"learning_rate": 7.547169811320755e-06,
|
| 870 |
+
"loss": 1.2429,
|
| 871 |
+
"step": 58
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.9830508474576272,
|
| 875 |
+
"eval_loss": 1.211168885231018,
|
| 876 |
+
"eval_runtime": 20.2851,
|
| 877 |
+
"eval_samples_per_second": 7.69,
|
| 878 |
+
"eval_steps_per_second": 0.493,
|
| 879 |
+
"step": 58
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.0,
|
| 883 |
+
"grad_norm": 0.6312069296836853,
|
| 884 |
+
"learning_rate": 0.0,
|
| 885 |
+
"loss": 1.0437,
|
| 886 |
+
"step": 59
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.0,
|
| 890 |
+
"eval_loss": 1.2111324071884155,
|
| 891 |
+
"eval_runtime": 20.2646,
|
| 892 |
+
"eval_samples_per_second": 7.698,
|
| 893 |
+
"eval_steps_per_second": 0.493,
|
| 894 |
+
"step": 59
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.0,
|
| 898 |
+
"step": 59,
|
| 899 |
+
"total_flos": 4.315434897427661e+16,
|
| 900 |
+
"train_loss": 1.3115796759977179,
|
| 901 |
+
"train_runtime": 2023.6846,
|
| 902 |
+
"train_samples_per_second": 0.918,
|
| 903 |
+
"train_steps_per_second": 0.029
|
| 904 |
+
}
|
| 905 |
+
],
|
| 906 |
+
"logging_steps": 1,
|
| 907 |
+
"max_steps": 59,
|
| 908 |
+
"num_input_tokens_seen": 0,
|
| 909 |
+
"num_train_epochs": 1,
|
| 910 |
+
"save_steps": 10,
|
| 911 |
+
"stateful_callbacks": {
|
| 912 |
+
"TrainerControl": {
|
| 913 |
+
"args": {
|
| 914 |
+
"should_epoch_stop": false,
|
| 915 |
+
"should_evaluate": false,
|
| 916 |
+
"should_log": false,
|
| 917 |
+
"should_save": true,
|
| 918 |
+
"should_training_stop": false
|
| 919 |
+
},
|
| 920 |
+
"attributes": {}
|
| 921 |
+
}
|
| 922 |
+
},
|
| 923 |
+
"total_flos": 4.315434897427661e+16,
|
| 924 |
+
"train_batch_size": 32,
|
| 925 |
+
"trial_name": null,
|
| 926 |
+
"trial_params": null
|
| 927 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587a975ca5d52e7de4ed67c53c113d801a25590e7ec8458e33153b0def14267d
|
| 3 |
+
size 5688
|