Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +14 -0
- all_results.json +7 -0
- checkpoint-50/README.md +202 -0
- checkpoint-50/adapter_config.json +31 -0
- checkpoint-50/adapter_model.safetensors +3 -0
- checkpoint-50/added_tokens.json +14 -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 +139 -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 +139 -0
- train_results.json +7 -0
- trainer_state.json +1497 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
| 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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
| 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": 0.05,
|
| 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": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"qkv_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_up_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ead9259011ccf374f558cb174144206848fde8b55339b6d4edb42837650a6b6
|
| 3 |
+
size 201361312
|
added_tokens.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"eos_token": 32011
|
| 14 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.1783372968742527,
|
| 4 |
+
"train_runtime": 2093.8635,
|
| 5 |
+
"train_samples_per_second": 1.472,
|
| 6 |
+
"train_steps_per_second": 0.046
|
| 7 |
+
}
|
checkpoint-50/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
| 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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
| 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": 0.05,
|
| 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": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"qkv_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_up_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
checkpoint-50/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaf4206c90db31f14634235c3b0b0e6d85bf985d5d100583fd19d7144ca5ef81
|
| 3 |
+
size 201361312
|
checkpoint-50/added_tokens.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"eos_token": 32011
|
| 14 |
+
}
|
checkpoint-50/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d703f3965eec18d8d6080751c935b26f3f245e51e102f0e4ba45c2afcb87921
|
| 3 |
+
size 402807738
|
checkpoint-50/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8cb185c4a0ed853bd64bac22493da61093f938a291afe82c270ce410f878bd8
|
| 3 |
+
size 14180
|
checkpoint-50/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f68ebb363d73879d29955f061f18dabc8ebc5237455a081d88c0443bcfb371ce
|
| 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 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32011": {
|
| 118 |
+
"content": "eos_token",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"bos_token": "<s>",
|
| 127 |
+
"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 %}",
|
| 128 |
+
"clean_up_tokenization_spaces": false,
|
| 129 |
+
"eos_token": "<|endoftext|>",
|
| 130 |
+
"legacy": false,
|
| 131 |
+
"model_max_length": 4096,
|
| 132 |
+
"pad_token": "<unk>",
|
| 133 |
+
"padding_side": "right",
|
| 134 |
+
"sp_model_kwargs": {},
|
| 135 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 136 |
+
"truncation_side": "left",
|
| 137 |
+
"unk_token": "<unk>",
|
| 138 |
+
"use_default_system_prompt": false
|
| 139 |
+
}
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3649392127990723,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoints/2024-06-11_11-02-23/checkpoint-50",
|
| 4 |
+
"epoch": 0.5154639175257731,
|
| 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": 0.010309278350515464,
|
| 13 |
+
"grad_norm": 2.784351348876953,
|
| 14 |
+
"learning_rate": 4e-05,
|
| 15 |
+
"loss": 5.0719,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010309278350515464,
|
| 20 |
+
"eval_loss": 4.890735149383545,
|
| 21 |
+
"eval_runtime": 11.998,
|
| 22 |
+
"eval_samples_per_second": 11.252,
|
| 23 |
+
"eval_steps_per_second": 0.75,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.020618556701030927,
|
| 28 |
+
"grad_norm": 2.8573310375213623,
|
| 29 |
+
"learning_rate": 8e-05,
|
| 30 |
+
"loss": 4.9508,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.020618556701030927,
|
| 35 |
+
"eval_loss": 4.775210857391357,
|
| 36 |
+
"eval_runtime": 12.0698,
|
| 37 |
+
"eval_samples_per_second": 11.185,
|
| 38 |
+
"eval_steps_per_second": 0.746,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.030927835051546393,
|
| 43 |
+
"grad_norm": 2.920828104019165,
|
| 44 |
+
"learning_rate": 0.00012,
|
| 45 |
+
"loss": 4.973,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.030927835051546393,
|
| 50 |
+
"eval_loss": 4.2439093589782715,
|
| 51 |
+
"eval_runtime": 12.1674,
|
| 52 |
+
"eval_samples_per_second": 11.095,
|
| 53 |
+
"eval_steps_per_second": 0.74,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.041237113402061855,
|
| 58 |
+
"grad_norm": 3.0682826042175293,
|
| 59 |
+
"learning_rate": 0.00016,
|
| 60 |
+
"loss": 4.3398,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.041237113402061855,
|
| 65 |
+
"eval_loss": 3.316483497619629,
|
| 66 |
+
"eval_runtime": 12.1421,
|
| 67 |
+
"eval_samples_per_second": 11.118,
|
| 68 |
+
"eval_steps_per_second": 0.741,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05154639175257732,
|
| 73 |
+
"grad_norm": 3.1937592029571533,
|
| 74 |
+
"learning_rate": 0.0002,
|
| 75 |
+
"loss": 3.253,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.05154639175257732,
|
| 80 |
+
"eval_loss": 2.4086239337921143,
|
| 81 |
+
"eval_runtime": 12.0796,
|
| 82 |
+
"eval_samples_per_second": 11.176,
|
| 83 |
+
"eval_steps_per_second": 0.745,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.061855670103092786,
|
| 88 |
+
"grad_norm": 2.0619874000549316,
|
| 89 |
+
"learning_rate": 0.00024,
|
| 90 |
+
"loss": 2.3725,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.061855670103092786,
|
| 95 |
+
"eval_loss": 1.9427752494812012,
|
| 96 |
+
"eval_runtime": 12.1816,
|
| 97 |
+
"eval_samples_per_second": 11.082,
|
| 98 |
+
"eval_steps_per_second": 0.739,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07216494845360824,
|
| 103 |
+
"grad_norm": 1.4178358316421509,
|
| 104 |
+
"learning_rate": 0.00028,
|
| 105 |
+
"loss": 1.7391,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.07216494845360824,
|
| 110 |
+
"eval_loss": 1.6751385927200317,
|
| 111 |
+
"eval_runtime": 12.2395,
|
| 112 |
+
"eval_samples_per_second": 11.03,
|
| 113 |
+
"eval_steps_per_second": 0.735,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08247422680412371,
|
| 118 |
+
"grad_norm": 0.9345605373382568,
|
| 119 |
+
"learning_rate": 0.00032,
|
| 120 |
+
"loss": 1.4029,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08247422680412371,
|
| 125 |
+
"eval_loss": 1.551221489906311,
|
| 126 |
+
"eval_runtime": 12.2329,
|
| 127 |
+
"eval_samples_per_second": 11.036,
|
| 128 |
+
"eval_steps_per_second": 0.736,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09278350515463918,
|
| 133 |
+
"grad_norm": 1.1335052251815796,
|
| 134 |
+
"learning_rate": 0.00036,
|
| 135 |
+
"loss": 1.4404,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09278350515463918,
|
| 140 |
+
"eval_loss": 1.447738528251648,
|
| 141 |
+
"eval_runtime": 12.2069,
|
| 142 |
+
"eval_samples_per_second": 11.059,
|
| 143 |
+
"eval_steps_per_second": 0.737,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.10309278350515463,
|
| 148 |
+
"grad_norm": 0.23779241740703583,
|
| 149 |
+
"learning_rate": 0.0004,
|
| 150 |
+
"loss": 1.3197,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10309278350515463,
|
| 155 |
+
"eval_loss": 1.4138007164001465,
|
| 156 |
+
"eval_runtime": 12.2609,
|
| 157 |
+
"eval_samples_per_second": 11.011,
|
| 158 |
+
"eval_steps_per_second": 0.734,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1134020618556701,
|
| 163 |
+
"grad_norm": 0.19672752916812897,
|
| 164 |
+
"learning_rate": 0.00039540229885057476,
|
| 165 |
+
"loss": 1.2882,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1134020618556701,
|
| 170 |
+
"eval_loss": 1.393249750137329,
|
| 171 |
+
"eval_runtime": 12.1836,
|
| 172 |
+
"eval_samples_per_second": 11.08,
|
| 173 |
+
"eval_steps_per_second": 0.739,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.12371134020618557,
|
| 178 |
+
"grad_norm": 0.2525981366634369,
|
| 179 |
+
"learning_rate": 0.00039080459770114945,
|
| 180 |
+
"loss": 1.2831,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.12371134020618557,
|
| 185 |
+
"eval_loss": 1.4042422771453857,
|
| 186 |
+
"eval_runtime": 12.232,
|
| 187 |
+
"eval_samples_per_second": 11.037,
|
| 188 |
+
"eval_steps_per_second": 0.736,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13402061855670103,
|
| 193 |
+
"grad_norm": 0.23460708558559418,
|
| 194 |
+
"learning_rate": 0.0003862068965517242,
|
| 195 |
+
"loss": 1.1615,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.13402061855670103,
|
| 200 |
+
"eval_loss": 1.4705734252929688,
|
| 201 |
+
"eval_runtime": 12.2648,
|
| 202 |
+
"eval_samples_per_second": 11.007,
|
| 203 |
+
"eval_steps_per_second": 0.734,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.14432989690721648,
|
| 208 |
+
"grad_norm": 0.21198733150959015,
|
| 209 |
+
"learning_rate": 0.00038160919540229887,
|
| 210 |
+
"loss": 1.0625,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.14432989690721648,
|
| 215 |
+
"eval_loss": 1.5055038928985596,
|
| 216 |
+
"eval_runtime": 12.2044,
|
| 217 |
+
"eval_samples_per_second": 11.062,
|
| 218 |
+
"eval_steps_per_second": 0.737,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15463917525773196,
|
| 223 |
+
"grad_norm": 0.3658374845981598,
|
| 224 |
+
"learning_rate": 0.00037701149425287356,
|
| 225 |
+
"loss": 1.1191,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15463917525773196,
|
| 230 |
+
"eval_loss": 1.4498964548110962,
|
| 231 |
+
"eval_runtime": 12.2004,
|
| 232 |
+
"eval_samples_per_second": 11.065,
|
| 233 |
+
"eval_steps_per_second": 0.738,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.16494845360824742,
|
| 238 |
+
"grad_norm": 0.222326397895813,
|
| 239 |
+
"learning_rate": 0.0003724137931034483,
|
| 240 |
+
"loss": 1.0887,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.16494845360824742,
|
| 245 |
+
"eval_loss": 1.3819501399993896,
|
| 246 |
+
"eval_runtime": 12.1444,
|
| 247 |
+
"eval_samples_per_second": 11.116,
|
| 248 |
+
"eval_steps_per_second": 0.741,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17525773195876287,
|
| 253 |
+
"grad_norm": 0.1682404726743698,
|
| 254 |
+
"learning_rate": 0.000367816091954023,
|
| 255 |
+
"loss": 1.0915,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.17525773195876287,
|
| 260 |
+
"eval_loss": 1.3552738428115845,
|
| 261 |
+
"eval_runtime": 12.2121,
|
| 262 |
+
"eval_samples_per_second": 11.055,
|
| 263 |
+
"eval_steps_per_second": 0.737,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.18556701030927836,
|
| 268 |
+
"grad_norm": 0.15567483007907867,
|
| 269 |
+
"learning_rate": 0.0003632183908045977,
|
| 270 |
+
"loss": 1.0509,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.18556701030927836,
|
| 275 |
+
"eval_loss": 1.3488575220108032,
|
| 276 |
+
"eval_runtime": 12.2988,
|
| 277 |
+
"eval_samples_per_second": 10.977,
|
| 278 |
+
"eval_steps_per_second": 0.732,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.1958762886597938,
|
| 283 |
+
"grad_norm": 0.1600300371646881,
|
| 284 |
+
"learning_rate": 0.0003586206896551724,
|
| 285 |
+
"loss": 0.9982,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.1958762886597938,
|
| 290 |
+
"eval_loss": 1.3651177883148193,
|
| 291 |
+
"eval_runtime": 12.1263,
|
| 292 |
+
"eval_samples_per_second": 11.133,
|
| 293 |
+
"eval_steps_per_second": 0.742,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.20618556701030927,
|
| 298 |
+
"grad_norm": 0.1044178307056427,
|
| 299 |
+
"learning_rate": 0.00035402298850574715,
|
| 300 |
+
"loss": 0.9809,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.20618556701030927,
|
| 305 |
+
"eval_loss": 1.401971697807312,
|
| 306 |
+
"eval_runtime": 12.2092,
|
| 307 |
+
"eval_samples_per_second": 11.057,
|
| 308 |
+
"eval_steps_per_second": 0.737,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.21649484536082475,
|
| 313 |
+
"grad_norm": 0.12360141426324844,
|
| 314 |
+
"learning_rate": 0.0003494252873563219,
|
| 315 |
+
"loss": 1.0549,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.21649484536082475,
|
| 320 |
+
"eval_loss": 1.426545262336731,
|
| 321 |
+
"eval_runtime": 12.1581,
|
| 322 |
+
"eval_samples_per_second": 11.104,
|
| 323 |
+
"eval_steps_per_second": 0.74,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2268041237113402,
|
| 328 |
+
"grad_norm": 0.12509943544864655,
|
| 329 |
+
"learning_rate": 0.0003448275862068965,
|
| 330 |
+
"loss": 1.0323,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2268041237113402,
|
| 335 |
+
"eval_loss": 1.4258630275726318,
|
| 336 |
+
"eval_runtime": 12.201,
|
| 337 |
+
"eval_samples_per_second": 11.065,
|
| 338 |
+
"eval_steps_per_second": 0.738,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.23711340206185566,
|
| 343 |
+
"grad_norm": 0.13586747646331787,
|
| 344 |
+
"learning_rate": 0.00034022988505747127,
|
| 345 |
+
"loss": 1.0746,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.23711340206185566,
|
| 350 |
+
"eval_loss": 1.3952091932296753,
|
| 351 |
+
"eval_runtime": 12.1932,
|
| 352 |
+
"eval_samples_per_second": 11.072,
|
| 353 |
+
"eval_steps_per_second": 0.738,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.24742268041237114,
|
| 358 |
+
"grad_norm": 0.08069202303886414,
|
| 359 |
+
"learning_rate": 0.000335632183908046,
|
| 360 |
+
"loss": 0.9645,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.24742268041237114,
|
| 365 |
+
"eval_loss": 1.376875638961792,
|
| 366 |
+
"eval_runtime": 12.2172,
|
| 367 |
+
"eval_samples_per_second": 11.05,
|
| 368 |
+
"eval_steps_per_second": 0.737,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.25773195876288657,
|
| 373 |
+
"grad_norm": 0.09109444171190262,
|
| 374 |
+
"learning_rate": 0.0003310344827586207,
|
| 375 |
+
"loss": 0.9345,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.25773195876288657,
|
| 380 |
+
"eval_loss": 1.373625636100769,
|
| 381 |
+
"eval_runtime": 12.2642,
|
| 382 |
+
"eval_samples_per_second": 11.008,
|
| 383 |
+
"eval_steps_per_second": 0.734,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.26804123711340205,
|
| 388 |
+
"grad_norm": 0.0649966150522232,
|
| 389 |
+
"learning_rate": 0.00032643678160919543,
|
| 390 |
+
"loss": 1.0266,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.26804123711340205,
|
| 395 |
+
"eval_loss": 1.3720897436141968,
|
| 396 |
+
"eval_runtime": 12.1576,
|
| 397 |
+
"eval_samples_per_second": 11.104,
|
| 398 |
+
"eval_steps_per_second": 0.74,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.27835051546391754,
|
| 403 |
+
"grad_norm": 0.09308775514364243,
|
| 404 |
+
"learning_rate": 0.0003218390804597701,
|
| 405 |
+
"loss": 0.9797,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.27835051546391754,
|
| 410 |
+
"eval_loss": 1.3858685493469238,
|
| 411 |
+
"eval_runtime": 12.1546,
|
| 412 |
+
"eval_samples_per_second": 11.107,
|
| 413 |
+
"eval_steps_per_second": 0.74,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.28865979381443296,
|
| 418 |
+
"grad_norm": 0.06654678285121918,
|
| 419 |
+
"learning_rate": 0.00031724137931034486,
|
| 420 |
+
"loss": 1.0072,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.28865979381443296,
|
| 425 |
+
"eval_loss": 1.4031970500946045,
|
| 426 |
+
"eval_runtime": 12.1666,
|
| 427 |
+
"eval_samples_per_second": 11.096,
|
| 428 |
+
"eval_steps_per_second": 0.74,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.29896907216494845,
|
| 433 |
+
"grad_norm": 0.07720344513654709,
|
| 434 |
+
"learning_rate": 0.0003126436781609196,
|
| 435 |
+
"loss": 0.923,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.29896907216494845,
|
| 440 |
+
"eval_loss": 1.4118249416351318,
|
| 441 |
+
"eval_runtime": 12.1572,
|
| 442 |
+
"eval_samples_per_second": 11.105,
|
| 443 |
+
"eval_steps_per_second": 0.74,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.30927835051546393,
|
| 448 |
+
"grad_norm": 0.10230278223752975,
|
| 449 |
+
"learning_rate": 0.00030804597701149423,
|
| 450 |
+
"loss": 0.9821,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.30927835051546393,
|
| 455 |
+
"eval_loss": 1.4045817852020264,
|
| 456 |
+
"eval_runtime": 12.1974,
|
| 457 |
+
"eval_samples_per_second": 11.068,
|
| 458 |
+
"eval_steps_per_second": 0.738,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.31958762886597936,
|
| 463 |
+
"grad_norm": 0.07451125234365463,
|
| 464 |
+
"learning_rate": 0.00030344827586206897,
|
| 465 |
+
"loss": 1.0021,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.31958762886597936,
|
| 470 |
+
"eval_loss": 1.391209363937378,
|
| 471 |
+
"eval_runtime": 12.2389,
|
| 472 |
+
"eval_samples_per_second": 11.03,
|
| 473 |
+
"eval_steps_per_second": 0.735,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.32989690721649484,
|
| 478 |
+
"grad_norm": 0.0714351087808609,
|
| 479 |
+
"learning_rate": 0.00029885057471264366,
|
| 480 |
+
"loss": 1.0071,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.32989690721649484,
|
| 485 |
+
"eval_loss": 1.3730576038360596,
|
| 486 |
+
"eval_runtime": 12.2102,
|
| 487 |
+
"eval_samples_per_second": 11.056,
|
| 488 |
+
"eval_steps_per_second": 0.737,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3402061855670103,
|
| 493 |
+
"grad_norm": 0.06839103996753693,
|
| 494 |
+
"learning_rate": 0.0002942528735632184,
|
| 495 |
+
"loss": 0.973,
|
| 496 |
+
"step": 33
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.3402061855670103,
|
| 500 |
+
"eval_loss": 1.3659778833389282,
|
| 501 |
+
"eval_runtime": 12.2323,
|
| 502 |
+
"eval_samples_per_second": 11.036,
|
| 503 |
+
"eval_steps_per_second": 0.736,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.35051546391752575,
|
| 508 |
+
"grad_norm": 0.08078178018331528,
|
| 509 |
+
"learning_rate": 0.00028965517241379314,
|
| 510 |
+
"loss": 0.964,
|
| 511 |
+
"step": 34
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.35051546391752575,
|
| 515 |
+
"eval_loss": 1.3762452602386475,
|
| 516 |
+
"eval_runtime": 12.2027,
|
| 517 |
+
"eval_samples_per_second": 11.063,
|
| 518 |
+
"eval_steps_per_second": 0.738,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.36082474226804123,
|
| 523 |
+
"grad_norm": 0.06870069354772568,
|
| 524 |
+
"learning_rate": 0.0002850574712643678,
|
| 525 |
+
"loss": 0.9148,
|
| 526 |
+
"step": 35
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.36082474226804123,
|
| 530 |
+
"eval_loss": 1.3925738334655762,
|
| 531 |
+
"eval_runtime": 12.2644,
|
| 532 |
+
"eval_samples_per_second": 11.007,
|
| 533 |
+
"eval_steps_per_second": 0.734,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3711340206185567,
|
| 538 |
+
"grad_norm": 0.06974003463983536,
|
| 539 |
+
"learning_rate": 0.00028045977011494257,
|
| 540 |
+
"loss": 1.0128,
|
| 541 |
+
"step": 36
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3711340206185567,
|
| 545 |
+
"eval_loss": 1.4087179899215698,
|
| 546 |
+
"eval_runtime": 12.2407,
|
| 547 |
+
"eval_samples_per_second": 11.029,
|
| 548 |
+
"eval_steps_per_second": 0.735,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.38144329896907214,
|
| 553 |
+
"grad_norm": 0.08603405207395554,
|
| 554 |
+
"learning_rate": 0.00027586206896551725,
|
| 555 |
+
"loss": 0.9776,
|
| 556 |
+
"step": 37
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.38144329896907214,
|
| 560 |
+
"eval_loss": 1.4067703485488892,
|
| 561 |
+
"eval_runtime": 12.173,
|
| 562 |
+
"eval_samples_per_second": 11.09,
|
| 563 |
+
"eval_steps_per_second": 0.739,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.3917525773195876,
|
| 568 |
+
"grad_norm": 0.07761300355195999,
|
| 569 |
+
"learning_rate": 0.00027126436781609194,
|
| 570 |
+
"loss": 0.9655,
|
| 571 |
+
"step": 38
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3917525773195876,
|
| 575 |
+
"eval_loss": 1.3932013511657715,
|
| 576 |
+
"eval_runtime": 12.1941,
|
| 577 |
+
"eval_samples_per_second": 11.071,
|
| 578 |
+
"eval_steps_per_second": 0.738,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.4020618556701031,
|
| 583 |
+
"grad_norm": 0.06392566114664078,
|
| 584 |
+
"learning_rate": 0.0002666666666666667,
|
| 585 |
+
"loss": 0.974,
|
| 586 |
+
"step": 39
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.4020618556701031,
|
| 590 |
+
"eval_loss": 1.3819767236709595,
|
| 591 |
+
"eval_runtime": 12.1765,
|
| 592 |
+
"eval_samples_per_second": 11.087,
|
| 593 |
+
"eval_steps_per_second": 0.739,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.41237113402061853,
|
| 598 |
+
"grad_norm": 0.05517549812793732,
|
| 599 |
+
"learning_rate": 0.00026206896551724137,
|
| 600 |
+
"loss": 0.9793,
|
| 601 |
+
"step": 40
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.41237113402061853,
|
| 605 |
+
"eval_loss": 1.3717000484466553,
|
| 606 |
+
"eval_runtime": 12.2217,
|
| 607 |
+
"eval_samples_per_second": 11.046,
|
| 608 |
+
"eval_steps_per_second": 0.736,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.422680412371134,
|
| 613 |
+
"grad_norm": 0.0804053246974945,
|
| 614 |
+
"learning_rate": 0.0002574712643678161,
|
| 615 |
+
"loss": 0.9585,
|
| 616 |
+
"step": 41
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.422680412371134,
|
| 620 |
+
"eval_loss": 1.3579998016357422,
|
| 621 |
+
"eval_runtime": 12.182,
|
| 622 |
+
"eval_samples_per_second": 11.082,
|
| 623 |
+
"eval_steps_per_second": 0.739,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.4329896907216495,
|
| 628 |
+
"grad_norm": 0.07214821875095367,
|
| 629 |
+
"learning_rate": 0.0002528735632183908,
|
| 630 |
+
"loss": 0.9332,
|
| 631 |
+
"step": 42
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.4329896907216495,
|
| 635 |
+
"eval_loss": 1.3583327531814575,
|
| 636 |
+
"eval_runtime": 12.1257,
|
| 637 |
+
"eval_samples_per_second": 11.133,
|
| 638 |
+
"eval_steps_per_second": 0.742,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.44329896907216493,
|
| 643 |
+
"grad_norm": 0.07595060020685196,
|
| 644 |
+
"learning_rate": 0.00024827586206896553,
|
| 645 |
+
"loss": 0.8998,
|
| 646 |
+
"step": 43
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.44329896907216493,
|
| 650 |
+
"eval_loss": 1.3721704483032227,
|
| 651 |
+
"eval_runtime": 12.2745,
|
| 652 |
+
"eval_samples_per_second": 10.998,
|
| 653 |
+
"eval_steps_per_second": 0.733,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4536082474226804,
|
| 658 |
+
"grad_norm": 0.07757716625928879,
|
| 659 |
+
"learning_rate": 0.00024367816091954025,
|
| 660 |
+
"loss": 0.9661,
|
| 661 |
+
"step": 44
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4536082474226804,
|
| 665 |
+
"eval_loss": 1.3984168767929077,
|
| 666 |
+
"eval_runtime": 12.1398,
|
| 667 |
+
"eval_samples_per_second": 11.12,
|
| 668 |
+
"eval_steps_per_second": 0.741,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.4639175257731959,
|
| 673 |
+
"grad_norm": 0.053873661905527115,
|
| 674 |
+
"learning_rate": 0.00023908045977011496,
|
| 675 |
+
"loss": 0.9418,
|
| 676 |
+
"step": 45
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4639175257731959,
|
| 680 |
+
"eval_loss": 1.4266961812973022,
|
| 681 |
+
"eval_runtime": 12.1955,
|
| 682 |
+
"eval_samples_per_second": 11.07,
|
| 683 |
+
"eval_steps_per_second": 0.738,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.4742268041237113,
|
| 688 |
+
"grad_norm": 0.08943776786327362,
|
| 689 |
+
"learning_rate": 0.00023448275862068965,
|
| 690 |
+
"loss": 0.9309,
|
| 691 |
+
"step": 46
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.4742268041237113,
|
| 695 |
+
"eval_loss": 1.4349451065063477,
|
| 696 |
+
"eval_runtime": 12.1983,
|
| 697 |
+
"eval_samples_per_second": 11.067,
|
| 698 |
+
"eval_steps_per_second": 0.738,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.4845360824742268,
|
| 703 |
+
"grad_norm": 0.0885058343410492,
|
| 704 |
+
"learning_rate": 0.00022988505747126436,
|
| 705 |
+
"loss": 1.0245,
|
| 706 |
+
"step": 47
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.4845360824742268,
|
| 710 |
+
"eval_loss": 1.4226434230804443,
|
| 711 |
+
"eval_runtime": 12.1753,
|
| 712 |
+
"eval_samples_per_second": 11.088,
|
| 713 |
+
"eval_steps_per_second": 0.739,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4948453608247423,
|
| 718 |
+
"grad_norm": 0.058818139135837555,
|
| 719 |
+
"learning_rate": 0.00022528735632183907,
|
| 720 |
+
"loss": 0.9007,
|
| 721 |
+
"step": 48
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.4948453608247423,
|
| 725 |
+
"eval_loss": 1.4033018350601196,
|
| 726 |
+
"eval_runtime": 12.267,
|
| 727 |
+
"eval_samples_per_second": 11.005,
|
| 728 |
+
"eval_steps_per_second": 0.734,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.5051546391752577,
|
| 733 |
+
"grad_norm": 0.07104739546775818,
|
| 734 |
+
"learning_rate": 0.0002206896551724138,
|
| 735 |
+
"loss": 0.9469,
|
| 736 |
+
"step": 49
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.5051546391752577,
|
| 740 |
+
"eval_loss": 1.3786002397537231,
|
| 741 |
+
"eval_runtime": 12.2731,
|
| 742 |
+
"eval_samples_per_second": 11.0,
|
| 743 |
+
"eval_steps_per_second": 0.733,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5154639175257731,
|
| 748 |
+
"grad_norm": 0.05872216075658798,
|
| 749 |
+
"learning_rate": 0.00021609195402298853,
|
| 750 |
+
"loss": 0.9671,
|
| 751 |
+
"step": 50
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5154639175257731,
|
| 755 |
+
"eval_loss": 1.3649392127990723,
|
| 756 |
+
"eval_runtime": 12.1662,
|
| 757 |
+
"eval_samples_per_second": 11.096,
|
| 758 |
+
"eval_steps_per_second": 0.74,
|
| 759 |
+
"step": 50
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 1,
|
| 763 |
+
"max_steps": 97,
|
| 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": 1.85446101417984e+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 sha256:9e2496b844a585edb80814b321f3eb6391f1e777dbd2b00fdafd91d647f31951
|
| 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 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32011": {
|
| 118 |
+
"content": "eos_token",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"bos_token": "<s>",
|
| 127 |
+
"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 %}",
|
| 128 |
+
"clean_up_tokenization_spaces": false,
|
| 129 |
+
"eos_token": "<|endoftext|>",
|
| 130 |
+
"legacy": false,
|
| 131 |
+
"model_max_length": 4096,
|
| 132 |
+
"pad_token": "<unk>",
|
| 133 |
+
"padding_side": "right",
|
| 134 |
+
"sp_model_kwargs": {},
|
| 135 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 136 |
+
"truncation_side": "left",
|
| 137 |
+
"unk_token": "<unk>",
|
| 138 |
+
"use_default_system_prompt": false
|
| 139 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.1783372968742527,
|
| 4 |
+
"train_runtime": 2093.8635,
|
| 5 |
+
"train_samples_per_second": 1.472,
|
| 6 |
+
"train_steps_per_second": 0.046
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1497 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3649392127990723,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoints/2024-06-11_11-02-23/checkpoint-50",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 97,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010309278350515464,
|
| 13 |
+
"grad_norm": 2.784351348876953,
|
| 14 |
+
"learning_rate": 4e-05,
|
| 15 |
+
"loss": 5.0719,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010309278350515464,
|
| 20 |
+
"eval_loss": 4.890735149383545,
|
| 21 |
+
"eval_runtime": 11.998,
|
| 22 |
+
"eval_samples_per_second": 11.252,
|
| 23 |
+
"eval_steps_per_second": 0.75,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.020618556701030927,
|
| 28 |
+
"grad_norm": 2.8573310375213623,
|
| 29 |
+
"learning_rate": 8e-05,
|
| 30 |
+
"loss": 4.9508,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.020618556701030927,
|
| 35 |
+
"eval_loss": 4.775210857391357,
|
| 36 |
+
"eval_runtime": 12.0698,
|
| 37 |
+
"eval_samples_per_second": 11.185,
|
| 38 |
+
"eval_steps_per_second": 0.746,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.030927835051546393,
|
| 43 |
+
"grad_norm": 2.920828104019165,
|
| 44 |
+
"learning_rate": 0.00012,
|
| 45 |
+
"loss": 4.973,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.030927835051546393,
|
| 50 |
+
"eval_loss": 4.2439093589782715,
|
| 51 |
+
"eval_runtime": 12.1674,
|
| 52 |
+
"eval_samples_per_second": 11.095,
|
| 53 |
+
"eval_steps_per_second": 0.74,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.041237113402061855,
|
| 58 |
+
"grad_norm": 3.0682826042175293,
|
| 59 |
+
"learning_rate": 0.00016,
|
| 60 |
+
"loss": 4.3398,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.041237113402061855,
|
| 65 |
+
"eval_loss": 3.316483497619629,
|
| 66 |
+
"eval_runtime": 12.1421,
|
| 67 |
+
"eval_samples_per_second": 11.118,
|
| 68 |
+
"eval_steps_per_second": 0.741,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05154639175257732,
|
| 73 |
+
"grad_norm": 3.1937592029571533,
|
| 74 |
+
"learning_rate": 0.0002,
|
| 75 |
+
"loss": 3.253,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.05154639175257732,
|
| 80 |
+
"eval_loss": 2.4086239337921143,
|
| 81 |
+
"eval_runtime": 12.0796,
|
| 82 |
+
"eval_samples_per_second": 11.176,
|
| 83 |
+
"eval_steps_per_second": 0.745,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.061855670103092786,
|
| 88 |
+
"grad_norm": 2.0619874000549316,
|
| 89 |
+
"learning_rate": 0.00024,
|
| 90 |
+
"loss": 2.3725,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.061855670103092786,
|
| 95 |
+
"eval_loss": 1.9427752494812012,
|
| 96 |
+
"eval_runtime": 12.1816,
|
| 97 |
+
"eval_samples_per_second": 11.082,
|
| 98 |
+
"eval_steps_per_second": 0.739,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07216494845360824,
|
| 103 |
+
"grad_norm": 1.4178358316421509,
|
| 104 |
+
"learning_rate": 0.00028,
|
| 105 |
+
"loss": 1.7391,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.07216494845360824,
|
| 110 |
+
"eval_loss": 1.6751385927200317,
|
| 111 |
+
"eval_runtime": 12.2395,
|
| 112 |
+
"eval_samples_per_second": 11.03,
|
| 113 |
+
"eval_steps_per_second": 0.735,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08247422680412371,
|
| 118 |
+
"grad_norm": 0.9345605373382568,
|
| 119 |
+
"learning_rate": 0.00032,
|
| 120 |
+
"loss": 1.4029,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08247422680412371,
|
| 125 |
+
"eval_loss": 1.551221489906311,
|
| 126 |
+
"eval_runtime": 12.2329,
|
| 127 |
+
"eval_samples_per_second": 11.036,
|
| 128 |
+
"eval_steps_per_second": 0.736,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09278350515463918,
|
| 133 |
+
"grad_norm": 1.1335052251815796,
|
| 134 |
+
"learning_rate": 0.00036,
|
| 135 |
+
"loss": 1.4404,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09278350515463918,
|
| 140 |
+
"eval_loss": 1.447738528251648,
|
| 141 |
+
"eval_runtime": 12.2069,
|
| 142 |
+
"eval_samples_per_second": 11.059,
|
| 143 |
+
"eval_steps_per_second": 0.737,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.10309278350515463,
|
| 148 |
+
"grad_norm": 0.23779241740703583,
|
| 149 |
+
"learning_rate": 0.0004,
|
| 150 |
+
"loss": 1.3197,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10309278350515463,
|
| 155 |
+
"eval_loss": 1.4138007164001465,
|
| 156 |
+
"eval_runtime": 12.2609,
|
| 157 |
+
"eval_samples_per_second": 11.011,
|
| 158 |
+
"eval_steps_per_second": 0.734,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1134020618556701,
|
| 163 |
+
"grad_norm": 0.19672752916812897,
|
| 164 |
+
"learning_rate": 0.00039540229885057476,
|
| 165 |
+
"loss": 1.2882,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1134020618556701,
|
| 170 |
+
"eval_loss": 1.393249750137329,
|
| 171 |
+
"eval_runtime": 12.1836,
|
| 172 |
+
"eval_samples_per_second": 11.08,
|
| 173 |
+
"eval_steps_per_second": 0.739,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.12371134020618557,
|
| 178 |
+
"grad_norm": 0.2525981366634369,
|
| 179 |
+
"learning_rate": 0.00039080459770114945,
|
| 180 |
+
"loss": 1.2831,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.12371134020618557,
|
| 185 |
+
"eval_loss": 1.4042422771453857,
|
| 186 |
+
"eval_runtime": 12.232,
|
| 187 |
+
"eval_samples_per_second": 11.037,
|
| 188 |
+
"eval_steps_per_second": 0.736,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13402061855670103,
|
| 193 |
+
"grad_norm": 0.23460708558559418,
|
| 194 |
+
"learning_rate": 0.0003862068965517242,
|
| 195 |
+
"loss": 1.1615,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.13402061855670103,
|
| 200 |
+
"eval_loss": 1.4705734252929688,
|
| 201 |
+
"eval_runtime": 12.2648,
|
| 202 |
+
"eval_samples_per_second": 11.007,
|
| 203 |
+
"eval_steps_per_second": 0.734,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.14432989690721648,
|
| 208 |
+
"grad_norm": 0.21198733150959015,
|
| 209 |
+
"learning_rate": 0.00038160919540229887,
|
| 210 |
+
"loss": 1.0625,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.14432989690721648,
|
| 215 |
+
"eval_loss": 1.5055038928985596,
|
| 216 |
+
"eval_runtime": 12.2044,
|
| 217 |
+
"eval_samples_per_second": 11.062,
|
| 218 |
+
"eval_steps_per_second": 0.737,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15463917525773196,
|
| 223 |
+
"grad_norm": 0.3658374845981598,
|
| 224 |
+
"learning_rate": 0.00037701149425287356,
|
| 225 |
+
"loss": 1.1191,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15463917525773196,
|
| 230 |
+
"eval_loss": 1.4498964548110962,
|
| 231 |
+
"eval_runtime": 12.2004,
|
| 232 |
+
"eval_samples_per_second": 11.065,
|
| 233 |
+
"eval_steps_per_second": 0.738,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.16494845360824742,
|
| 238 |
+
"grad_norm": 0.222326397895813,
|
| 239 |
+
"learning_rate": 0.0003724137931034483,
|
| 240 |
+
"loss": 1.0887,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.16494845360824742,
|
| 245 |
+
"eval_loss": 1.3819501399993896,
|
| 246 |
+
"eval_runtime": 12.1444,
|
| 247 |
+
"eval_samples_per_second": 11.116,
|
| 248 |
+
"eval_steps_per_second": 0.741,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17525773195876287,
|
| 253 |
+
"grad_norm": 0.1682404726743698,
|
| 254 |
+
"learning_rate": 0.000367816091954023,
|
| 255 |
+
"loss": 1.0915,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.17525773195876287,
|
| 260 |
+
"eval_loss": 1.3552738428115845,
|
| 261 |
+
"eval_runtime": 12.2121,
|
| 262 |
+
"eval_samples_per_second": 11.055,
|
| 263 |
+
"eval_steps_per_second": 0.737,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.18556701030927836,
|
| 268 |
+
"grad_norm": 0.15567483007907867,
|
| 269 |
+
"learning_rate": 0.0003632183908045977,
|
| 270 |
+
"loss": 1.0509,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.18556701030927836,
|
| 275 |
+
"eval_loss": 1.3488575220108032,
|
| 276 |
+
"eval_runtime": 12.2988,
|
| 277 |
+
"eval_samples_per_second": 10.977,
|
| 278 |
+
"eval_steps_per_second": 0.732,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.1958762886597938,
|
| 283 |
+
"grad_norm": 0.1600300371646881,
|
| 284 |
+
"learning_rate": 0.0003586206896551724,
|
| 285 |
+
"loss": 0.9982,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.1958762886597938,
|
| 290 |
+
"eval_loss": 1.3651177883148193,
|
| 291 |
+
"eval_runtime": 12.1263,
|
| 292 |
+
"eval_samples_per_second": 11.133,
|
| 293 |
+
"eval_steps_per_second": 0.742,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.20618556701030927,
|
| 298 |
+
"grad_norm": 0.1044178307056427,
|
| 299 |
+
"learning_rate": 0.00035402298850574715,
|
| 300 |
+
"loss": 0.9809,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.20618556701030927,
|
| 305 |
+
"eval_loss": 1.401971697807312,
|
| 306 |
+
"eval_runtime": 12.2092,
|
| 307 |
+
"eval_samples_per_second": 11.057,
|
| 308 |
+
"eval_steps_per_second": 0.737,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.21649484536082475,
|
| 313 |
+
"grad_norm": 0.12360141426324844,
|
| 314 |
+
"learning_rate": 0.0003494252873563219,
|
| 315 |
+
"loss": 1.0549,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.21649484536082475,
|
| 320 |
+
"eval_loss": 1.426545262336731,
|
| 321 |
+
"eval_runtime": 12.1581,
|
| 322 |
+
"eval_samples_per_second": 11.104,
|
| 323 |
+
"eval_steps_per_second": 0.74,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2268041237113402,
|
| 328 |
+
"grad_norm": 0.12509943544864655,
|
| 329 |
+
"learning_rate": 0.0003448275862068965,
|
| 330 |
+
"loss": 1.0323,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2268041237113402,
|
| 335 |
+
"eval_loss": 1.4258630275726318,
|
| 336 |
+
"eval_runtime": 12.201,
|
| 337 |
+
"eval_samples_per_second": 11.065,
|
| 338 |
+
"eval_steps_per_second": 0.738,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.23711340206185566,
|
| 343 |
+
"grad_norm": 0.13586747646331787,
|
| 344 |
+
"learning_rate": 0.00034022988505747127,
|
| 345 |
+
"loss": 1.0746,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.23711340206185566,
|
| 350 |
+
"eval_loss": 1.3952091932296753,
|
| 351 |
+
"eval_runtime": 12.1932,
|
| 352 |
+
"eval_samples_per_second": 11.072,
|
| 353 |
+
"eval_steps_per_second": 0.738,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.24742268041237114,
|
| 358 |
+
"grad_norm": 0.08069202303886414,
|
| 359 |
+
"learning_rate": 0.000335632183908046,
|
| 360 |
+
"loss": 0.9645,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.24742268041237114,
|
| 365 |
+
"eval_loss": 1.376875638961792,
|
| 366 |
+
"eval_runtime": 12.2172,
|
| 367 |
+
"eval_samples_per_second": 11.05,
|
| 368 |
+
"eval_steps_per_second": 0.737,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.25773195876288657,
|
| 373 |
+
"grad_norm": 0.09109444171190262,
|
| 374 |
+
"learning_rate": 0.0003310344827586207,
|
| 375 |
+
"loss": 0.9345,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.25773195876288657,
|
| 380 |
+
"eval_loss": 1.373625636100769,
|
| 381 |
+
"eval_runtime": 12.2642,
|
| 382 |
+
"eval_samples_per_second": 11.008,
|
| 383 |
+
"eval_steps_per_second": 0.734,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.26804123711340205,
|
| 388 |
+
"grad_norm": 0.0649966150522232,
|
| 389 |
+
"learning_rate": 0.00032643678160919543,
|
| 390 |
+
"loss": 1.0266,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.26804123711340205,
|
| 395 |
+
"eval_loss": 1.3720897436141968,
|
| 396 |
+
"eval_runtime": 12.1576,
|
| 397 |
+
"eval_samples_per_second": 11.104,
|
| 398 |
+
"eval_steps_per_second": 0.74,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.27835051546391754,
|
| 403 |
+
"grad_norm": 0.09308775514364243,
|
| 404 |
+
"learning_rate": 0.0003218390804597701,
|
| 405 |
+
"loss": 0.9797,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.27835051546391754,
|
| 410 |
+
"eval_loss": 1.3858685493469238,
|
| 411 |
+
"eval_runtime": 12.1546,
|
| 412 |
+
"eval_samples_per_second": 11.107,
|
| 413 |
+
"eval_steps_per_second": 0.74,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.28865979381443296,
|
| 418 |
+
"grad_norm": 0.06654678285121918,
|
| 419 |
+
"learning_rate": 0.00031724137931034486,
|
| 420 |
+
"loss": 1.0072,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.28865979381443296,
|
| 425 |
+
"eval_loss": 1.4031970500946045,
|
| 426 |
+
"eval_runtime": 12.1666,
|
| 427 |
+
"eval_samples_per_second": 11.096,
|
| 428 |
+
"eval_steps_per_second": 0.74,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.29896907216494845,
|
| 433 |
+
"grad_norm": 0.07720344513654709,
|
| 434 |
+
"learning_rate": 0.0003126436781609196,
|
| 435 |
+
"loss": 0.923,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.29896907216494845,
|
| 440 |
+
"eval_loss": 1.4118249416351318,
|
| 441 |
+
"eval_runtime": 12.1572,
|
| 442 |
+
"eval_samples_per_second": 11.105,
|
| 443 |
+
"eval_steps_per_second": 0.74,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.30927835051546393,
|
| 448 |
+
"grad_norm": 0.10230278223752975,
|
| 449 |
+
"learning_rate": 0.00030804597701149423,
|
| 450 |
+
"loss": 0.9821,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.30927835051546393,
|
| 455 |
+
"eval_loss": 1.4045817852020264,
|
| 456 |
+
"eval_runtime": 12.1974,
|
| 457 |
+
"eval_samples_per_second": 11.068,
|
| 458 |
+
"eval_steps_per_second": 0.738,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.31958762886597936,
|
| 463 |
+
"grad_norm": 0.07451125234365463,
|
| 464 |
+
"learning_rate": 0.00030344827586206897,
|
| 465 |
+
"loss": 1.0021,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.31958762886597936,
|
| 470 |
+
"eval_loss": 1.391209363937378,
|
| 471 |
+
"eval_runtime": 12.2389,
|
| 472 |
+
"eval_samples_per_second": 11.03,
|
| 473 |
+
"eval_steps_per_second": 0.735,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.32989690721649484,
|
| 478 |
+
"grad_norm": 0.0714351087808609,
|
| 479 |
+
"learning_rate": 0.00029885057471264366,
|
| 480 |
+
"loss": 1.0071,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.32989690721649484,
|
| 485 |
+
"eval_loss": 1.3730576038360596,
|
| 486 |
+
"eval_runtime": 12.2102,
|
| 487 |
+
"eval_samples_per_second": 11.056,
|
| 488 |
+
"eval_steps_per_second": 0.737,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3402061855670103,
|
| 493 |
+
"grad_norm": 0.06839103996753693,
|
| 494 |
+
"learning_rate": 0.0002942528735632184,
|
| 495 |
+
"loss": 0.973,
|
| 496 |
+
"step": 33
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.3402061855670103,
|
| 500 |
+
"eval_loss": 1.3659778833389282,
|
| 501 |
+
"eval_runtime": 12.2323,
|
| 502 |
+
"eval_samples_per_second": 11.036,
|
| 503 |
+
"eval_steps_per_second": 0.736,
|
| 504 |
+
"step": 33
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.35051546391752575,
|
| 508 |
+
"grad_norm": 0.08078178018331528,
|
| 509 |
+
"learning_rate": 0.00028965517241379314,
|
| 510 |
+
"loss": 0.964,
|
| 511 |
+
"step": 34
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.35051546391752575,
|
| 515 |
+
"eval_loss": 1.3762452602386475,
|
| 516 |
+
"eval_runtime": 12.2027,
|
| 517 |
+
"eval_samples_per_second": 11.063,
|
| 518 |
+
"eval_steps_per_second": 0.738,
|
| 519 |
+
"step": 34
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.36082474226804123,
|
| 523 |
+
"grad_norm": 0.06870069354772568,
|
| 524 |
+
"learning_rate": 0.0002850574712643678,
|
| 525 |
+
"loss": 0.9148,
|
| 526 |
+
"step": 35
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.36082474226804123,
|
| 530 |
+
"eval_loss": 1.3925738334655762,
|
| 531 |
+
"eval_runtime": 12.2644,
|
| 532 |
+
"eval_samples_per_second": 11.007,
|
| 533 |
+
"eval_steps_per_second": 0.734,
|
| 534 |
+
"step": 35
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3711340206185567,
|
| 538 |
+
"grad_norm": 0.06974003463983536,
|
| 539 |
+
"learning_rate": 0.00028045977011494257,
|
| 540 |
+
"loss": 1.0128,
|
| 541 |
+
"step": 36
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3711340206185567,
|
| 545 |
+
"eval_loss": 1.4087179899215698,
|
| 546 |
+
"eval_runtime": 12.2407,
|
| 547 |
+
"eval_samples_per_second": 11.029,
|
| 548 |
+
"eval_steps_per_second": 0.735,
|
| 549 |
+
"step": 36
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.38144329896907214,
|
| 553 |
+
"grad_norm": 0.08603405207395554,
|
| 554 |
+
"learning_rate": 0.00027586206896551725,
|
| 555 |
+
"loss": 0.9776,
|
| 556 |
+
"step": 37
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.38144329896907214,
|
| 560 |
+
"eval_loss": 1.4067703485488892,
|
| 561 |
+
"eval_runtime": 12.173,
|
| 562 |
+
"eval_samples_per_second": 11.09,
|
| 563 |
+
"eval_steps_per_second": 0.739,
|
| 564 |
+
"step": 37
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.3917525773195876,
|
| 568 |
+
"grad_norm": 0.07761300355195999,
|
| 569 |
+
"learning_rate": 0.00027126436781609194,
|
| 570 |
+
"loss": 0.9655,
|
| 571 |
+
"step": 38
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3917525773195876,
|
| 575 |
+
"eval_loss": 1.3932013511657715,
|
| 576 |
+
"eval_runtime": 12.1941,
|
| 577 |
+
"eval_samples_per_second": 11.071,
|
| 578 |
+
"eval_steps_per_second": 0.738,
|
| 579 |
+
"step": 38
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.4020618556701031,
|
| 583 |
+
"grad_norm": 0.06392566114664078,
|
| 584 |
+
"learning_rate": 0.0002666666666666667,
|
| 585 |
+
"loss": 0.974,
|
| 586 |
+
"step": 39
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.4020618556701031,
|
| 590 |
+
"eval_loss": 1.3819767236709595,
|
| 591 |
+
"eval_runtime": 12.1765,
|
| 592 |
+
"eval_samples_per_second": 11.087,
|
| 593 |
+
"eval_steps_per_second": 0.739,
|
| 594 |
+
"step": 39
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.41237113402061853,
|
| 598 |
+
"grad_norm": 0.05517549812793732,
|
| 599 |
+
"learning_rate": 0.00026206896551724137,
|
| 600 |
+
"loss": 0.9793,
|
| 601 |
+
"step": 40
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.41237113402061853,
|
| 605 |
+
"eval_loss": 1.3717000484466553,
|
| 606 |
+
"eval_runtime": 12.2217,
|
| 607 |
+
"eval_samples_per_second": 11.046,
|
| 608 |
+
"eval_steps_per_second": 0.736,
|
| 609 |
+
"step": 40
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.422680412371134,
|
| 613 |
+
"grad_norm": 0.0804053246974945,
|
| 614 |
+
"learning_rate": 0.0002574712643678161,
|
| 615 |
+
"loss": 0.9585,
|
| 616 |
+
"step": 41
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.422680412371134,
|
| 620 |
+
"eval_loss": 1.3579998016357422,
|
| 621 |
+
"eval_runtime": 12.182,
|
| 622 |
+
"eval_samples_per_second": 11.082,
|
| 623 |
+
"eval_steps_per_second": 0.739,
|
| 624 |
+
"step": 41
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.4329896907216495,
|
| 628 |
+
"grad_norm": 0.07214821875095367,
|
| 629 |
+
"learning_rate": 0.0002528735632183908,
|
| 630 |
+
"loss": 0.9332,
|
| 631 |
+
"step": 42
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.4329896907216495,
|
| 635 |
+
"eval_loss": 1.3583327531814575,
|
| 636 |
+
"eval_runtime": 12.1257,
|
| 637 |
+
"eval_samples_per_second": 11.133,
|
| 638 |
+
"eval_steps_per_second": 0.742,
|
| 639 |
+
"step": 42
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.44329896907216493,
|
| 643 |
+
"grad_norm": 0.07595060020685196,
|
| 644 |
+
"learning_rate": 0.00024827586206896553,
|
| 645 |
+
"loss": 0.8998,
|
| 646 |
+
"step": 43
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.44329896907216493,
|
| 650 |
+
"eval_loss": 1.3721704483032227,
|
| 651 |
+
"eval_runtime": 12.2745,
|
| 652 |
+
"eval_samples_per_second": 10.998,
|
| 653 |
+
"eval_steps_per_second": 0.733,
|
| 654 |
+
"step": 43
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4536082474226804,
|
| 658 |
+
"grad_norm": 0.07757716625928879,
|
| 659 |
+
"learning_rate": 0.00024367816091954025,
|
| 660 |
+
"loss": 0.9661,
|
| 661 |
+
"step": 44
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4536082474226804,
|
| 665 |
+
"eval_loss": 1.3984168767929077,
|
| 666 |
+
"eval_runtime": 12.1398,
|
| 667 |
+
"eval_samples_per_second": 11.12,
|
| 668 |
+
"eval_steps_per_second": 0.741,
|
| 669 |
+
"step": 44
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.4639175257731959,
|
| 673 |
+
"grad_norm": 0.053873661905527115,
|
| 674 |
+
"learning_rate": 0.00023908045977011496,
|
| 675 |
+
"loss": 0.9418,
|
| 676 |
+
"step": 45
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4639175257731959,
|
| 680 |
+
"eval_loss": 1.4266961812973022,
|
| 681 |
+
"eval_runtime": 12.1955,
|
| 682 |
+
"eval_samples_per_second": 11.07,
|
| 683 |
+
"eval_steps_per_second": 0.738,
|
| 684 |
+
"step": 45
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.4742268041237113,
|
| 688 |
+
"grad_norm": 0.08943776786327362,
|
| 689 |
+
"learning_rate": 0.00023448275862068965,
|
| 690 |
+
"loss": 0.9309,
|
| 691 |
+
"step": 46
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.4742268041237113,
|
| 695 |
+
"eval_loss": 1.4349451065063477,
|
| 696 |
+
"eval_runtime": 12.1983,
|
| 697 |
+
"eval_samples_per_second": 11.067,
|
| 698 |
+
"eval_steps_per_second": 0.738,
|
| 699 |
+
"step": 46
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.4845360824742268,
|
| 703 |
+
"grad_norm": 0.0885058343410492,
|
| 704 |
+
"learning_rate": 0.00022988505747126436,
|
| 705 |
+
"loss": 1.0245,
|
| 706 |
+
"step": 47
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.4845360824742268,
|
| 710 |
+
"eval_loss": 1.4226434230804443,
|
| 711 |
+
"eval_runtime": 12.1753,
|
| 712 |
+
"eval_samples_per_second": 11.088,
|
| 713 |
+
"eval_steps_per_second": 0.739,
|
| 714 |
+
"step": 47
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4948453608247423,
|
| 718 |
+
"grad_norm": 0.058818139135837555,
|
| 719 |
+
"learning_rate": 0.00022528735632183907,
|
| 720 |
+
"loss": 0.9007,
|
| 721 |
+
"step": 48
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.4948453608247423,
|
| 725 |
+
"eval_loss": 1.4033018350601196,
|
| 726 |
+
"eval_runtime": 12.267,
|
| 727 |
+
"eval_samples_per_second": 11.005,
|
| 728 |
+
"eval_steps_per_second": 0.734,
|
| 729 |
+
"step": 48
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.5051546391752577,
|
| 733 |
+
"grad_norm": 0.07104739546775818,
|
| 734 |
+
"learning_rate": 0.0002206896551724138,
|
| 735 |
+
"loss": 0.9469,
|
| 736 |
+
"step": 49
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.5051546391752577,
|
| 740 |
+
"eval_loss": 1.3786002397537231,
|
| 741 |
+
"eval_runtime": 12.2731,
|
| 742 |
+
"eval_samples_per_second": 11.0,
|
| 743 |
+
"eval_steps_per_second": 0.733,
|
| 744 |
+
"step": 49
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5154639175257731,
|
| 748 |
+
"grad_norm": 0.05872216075658798,
|
| 749 |
+
"learning_rate": 0.00021609195402298853,
|
| 750 |
+
"loss": 0.9671,
|
| 751 |
+
"step": 50
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5154639175257731,
|
| 755 |
+
"eval_loss": 1.3649392127990723,
|
| 756 |
+
"eval_runtime": 12.1662,
|
| 757 |
+
"eval_samples_per_second": 11.096,
|
| 758 |
+
"eval_steps_per_second": 0.74,
|
| 759 |
+
"step": 50
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5257731958762887,
|
| 763 |
+
"grad_norm": 0.07843936234712601,
|
| 764 |
+
"learning_rate": 0.00021149425287356324,
|
| 765 |
+
"loss": 0.9052,
|
| 766 |
+
"step": 51
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5257731958762887,
|
| 770 |
+
"eval_loss": 1.3671882152557373,
|
| 771 |
+
"eval_runtime": 12.1527,
|
| 772 |
+
"eval_samples_per_second": 11.109,
|
| 773 |
+
"eval_steps_per_second": 0.741,
|
| 774 |
+
"step": 51
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5360824742268041,
|
| 778 |
+
"grad_norm": 0.07407287508249283,
|
| 779 |
+
"learning_rate": 0.00020689655172413795,
|
| 780 |
+
"loss": 0.9221,
|
| 781 |
+
"step": 52
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.5360824742268041,
|
| 785 |
+
"eval_loss": 1.3811315298080444,
|
| 786 |
+
"eval_runtime": 12.1661,
|
| 787 |
+
"eval_samples_per_second": 11.096,
|
| 788 |
+
"eval_steps_per_second": 0.74,
|
| 789 |
+
"step": 52
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.5463917525773195,
|
| 793 |
+
"grad_norm": 0.06168922409415245,
|
| 794 |
+
"learning_rate": 0.00020229885057471267,
|
| 795 |
+
"loss": 0.9809,
|
| 796 |
+
"step": 53
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.5463917525773195,
|
| 800 |
+
"eval_loss": 1.3900806903839111,
|
| 801 |
+
"eval_runtime": 12.1958,
|
| 802 |
+
"eval_samples_per_second": 11.069,
|
| 803 |
+
"eval_steps_per_second": 0.738,
|
| 804 |
+
"step": 53
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.5567010309278351,
|
| 808 |
+
"grad_norm": 0.05980532988905907,
|
| 809 |
+
"learning_rate": 0.00019770114942528738,
|
| 810 |
+
"loss": 0.9492,
|
| 811 |
+
"step": 54
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.5567010309278351,
|
| 815 |
+
"eval_loss": 1.4011154174804688,
|
| 816 |
+
"eval_runtime": 12.1559,
|
| 817 |
+
"eval_samples_per_second": 11.106,
|
| 818 |
+
"eval_steps_per_second": 0.74,
|
| 819 |
+
"step": 54
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.5670103092783505,
|
| 823 |
+
"grad_norm": 0.05770307034254074,
|
| 824 |
+
"learning_rate": 0.0001931034482758621,
|
| 825 |
+
"loss": 0.9377,
|
| 826 |
+
"step": 55
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.5670103092783505,
|
| 830 |
+
"eval_loss": 1.4104657173156738,
|
| 831 |
+
"eval_runtime": 12.2103,
|
| 832 |
+
"eval_samples_per_second": 11.056,
|
| 833 |
+
"eval_steps_per_second": 0.737,
|
| 834 |
+
"step": 55
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5773195876288659,
|
| 838 |
+
"grad_norm": 0.05812888965010643,
|
| 839 |
+
"learning_rate": 0.00018850574712643678,
|
| 840 |
+
"loss": 0.9139,
|
| 841 |
+
"step": 56
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.5773195876288659,
|
| 845 |
+
"eval_loss": 1.4152581691741943,
|
| 846 |
+
"eval_runtime": 12.1515,
|
| 847 |
+
"eval_samples_per_second": 11.11,
|
| 848 |
+
"eval_steps_per_second": 0.741,
|
| 849 |
+
"step": 56
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5876288659793815,
|
| 853 |
+
"grad_norm": 0.0625990554690361,
|
| 854 |
+
"learning_rate": 0.0001839080459770115,
|
| 855 |
+
"loss": 0.9111,
|
| 856 |
+
"step": 57
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5876288659793815,
|
| 860 |
+
"eval_loss": 1.4142401218414307,
|
| 861 |
+
"eval_runtime": 12.208,
|
| 862 |
+
"eval_samples_per_second": 11.058,
|
| 863 |
+
"eval_steps_per_second": 0.737,
|
| 864 |
+
"step": 57
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5979381443298969,
|
| 868 |
+
"grad_norm": 0.06904823333024979,
|
| 869 |
+
"learning_rate": 0.0001793103448275862,
|
| 870 |
+
"loss": 0.9019,
|
| 871 |
+
"step": 58
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5979381443298969,
|
| 875 |
+
"eval_loss": 1.4036115407943726,
|
| 876 |
+
"eval_runtime": 12.1626,
|
| 877 |
+
"eval_samples_per_second": 11.1,
|
| 878 |
+
"eval_steps_per_second": 0.74,
|
| 879 |
+
"step": 58
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.6082474226804123,
|
| 883 |
+
"grad_norm": 0.06511174887418747,
|
| 884 |
+
"learning_rate": 0.00017471264367816095,
|
| 885 |
+
"loss": 0.9409,
|
| 886 |
+
"step": 59
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.6082474226804123,
|
| 890 |
+
"eval_loss": 1.3875020742416382,
|
| 891 |
+
"eval_runtime": 12.1594,
|
| 892 |
+
"eval_samples_per_second": 11.103,
|
| 893 |
+
"eval_steps_per_second": 0.74,
|
| 894 |
+
"step": 59
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.6185567010309279,
|
| 898 |
+
"grad_norm": 0.06755220890045166,
|
| 899 |
+
"learning_rate": 0.00017011494252873563,
|
| 900 |
+
"loss": 0.8928,
|
| 901 |
+
"step": 60
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.6185567010309279,
|
| 905 |
+
"eval_loss": 1.3814879655838013,
|
| 906 |
+
"eval_runtime": 12.1832,
|
| 907 |
+
"eval_samples_per_second": 11.081,
|
| 908 |
+
"eval_steps_per_second": 0.739,
|
| 909 |
+
"step": 60
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.6288659793814433,
|
| 913 |
+
"grad_norm": 0.057419709861278534,
|
| 914 |
+
"learning_rate": 0.00016551724137931035,
|
| 915 |
+
"loss": 0.8698,
|
| 916 |
+
"step": 61
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.6288659793814433,
|
| 920 |
+
"eval_loss": 1.376993179321289,
|
| 921 |
+
"eval_runtime": 12.1649,
|
| 922 |
+
"eval_samples_per_second": 11.097,
|
| 923 |
+
"eval_steps_per_second": 0.74,
|
| 924 |
+
"step": 61
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.6391752577319587,
|
| 928 |
+
"grad_norm": 0.09423535317182541,
|
| 929 |
+
"learning_rate": 0.00016091954022988506,
|
| 930 |
+
"loss": 0.9605,
|
| 931 |
+
"step": 62
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.6391752577319587,
|
| 935 |
+
"eval_loss": 1.3864612579345703,
|
| 936 |
+
"eval_runtime": 12.1886,
|
| 937 |
+
"eval_samples_per_second": 11.076,
|
| 938 |
+
"eval_steps_per_second": 0.738,
|
| 939 |
+
"step": 62
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.6494845360824743,
|
| 943 |
+
"grad_norm": 0.05667712539434433,
|
| 944 |
+
"learning_rate": 0.0001563218390804598,
|
| 945 |
+
"loss": 0.9863,
|
| 946 |
+
"step": 63
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.6494845360824743,
|
| 950 |
+
"eval_loss": 1.3983639478683472,
|
| 951 |
+
"eval_runtime": 12.1418,
|
| 952 |
+
"eval_samples_per_second": 11.119,
|
| 953 |
+
"eval_steps_per_second": 0.741,
|
| 954 |
+
"step": 63
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6597938144329897,
|
| 958 |
+
"grad_norm": 0.061302803456783295,
|
| 959 |
+
"learning_rate": 0.00015172413793103449,
|
| 960 |
+
"loss": 0.9454,
|
| 961 |
+
"step": 64
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6597938144329897,
|
| 965 |
+
"eval_loss": 1.406610369682312,
|
| 966 |
+
"eval_runtime": 12.2718,
|
| 967 |
+
"eval_samples_per_second": 11.001,
|
| 968 |
+
"eval_steps_per_second": 0.733,
|
| 969 |
+
"step": 64
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6701030927835051,
|
| 973 |
+
"grad_norm": 0.06619007140398026,
|
| 974 |
+
"learning_rate": 0.0001471264367816092,
|
| 975 |
+
"loss": 0.9302,
|
| 976 |
+
"step": 65
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.6701030927835051,
|
| 980 |
+
"eval_loss": 1.408695936203003,
|
| 981 |
+
"eval_runtime": 12.1873,
|
| 982 |
+
"eval_samples_per_second": 11.077,
|
| 983 |
+
"eval_steps_per_second": 0.738,
|
| 984 |
+
"step": 65
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.6804123711340206,
|
| 988 |
+
"grad_norm": 0.059212010353803635,
|
| 989 |
+
"learning_rate": 0.0001425287356321839,
|
| 990 |
+
"loss": 0.9409,
|
| 991 |
+
"step": 66
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.6804123711340206,
|
| 995 |
+
"eval_loss": 1.4100947380065918,
|
| 996 |
+
"eval_runtime": 12.2058,
|
| 997 |
+
"eval_samples_per_second": 11.06,
|
| 998 |
+
"eval_steps_per_second": 0.737,
|
| 999 |
+
"step": 66
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6907216494845361,
|
| 1003 |
+
"grad_norm": 0.06854245811700821,
|
| 1004 |
+
"learning_rate": 0.00013793103448275863,
|
| 1005 |
+
"loss": 0.9408,
|
| 1006 |
+
"step": 67
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6907216494845361,
|
| 1010 |
+
"eval_loss": 1.4050439596176147,
|
| 1011 |
+
"eval_runtime": 12.1478,
|
| 1012 |
+
"eval_samples_per_second": 11.113,
|
| 1013 |
+
"eval_steps_per_second": 0.741,
|
| 1014 |
+
"step": 67
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.7010309278350515,
|
| 1018 |
+
"grad_norm": 0.05722883343696594,
|
| 1019 |
+
"learning_rate": 0.00013333333333333334,
|
| 1020 |
+
"loss": 0.91,
|
| 1021 |
+
"step": 68
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.7010309278350515,
|
| 1025 |
+
"eval_loss": 1.397505283355713,
|
| 1026 |
+
"eval_runtime": 12.1678,
|
| 1027 |
+
"eval_samples_per_second": 11.095,
|
| 1028 |
+
"eval_steps_per_second": 0.74,
|
| 1029 |
+
"step": 68
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.711340206185567,
|
| 1033 |
+
"grad_norm": 0.07448893785476685,
|
| 1034 |
+
"learning_rate": 0.00012873563218390805,
|
| 1035 |
+
"loss": 0.9451,
|
| 1036 |
+
"step": 69
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.711340206185567,
|
| 1040 |
+
"eval_loss": 1.3847121000289917,
|
| 1041 |
+
"eval_runtime": 12.1444,
|
| 1042 |
+
"eval_samples_per_second": 11.116,
|
| 1043 |
+
"eval_steps_per_second": 0.741,
|
| 1044 |
+
"step": 69
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.7216494845360825,
|
| 1048 |
+
"grad_norm": 0.055692195892333984,
|
| 1049 |
+
"learning_rate": 0.00012413793103448277,
|
| 1050 |
+
"loss": 0.8967,
|
| 1051 |
+
"step": 70
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.7216494845360825,
|
| 1055 |
+
"eval_loss": 1.376731038093567,
|
| 1056 |
+
"eval_runtime": 12.1911,
|
| 1057 |
+
"eval_samples_per_second": 11.074,
|
| 1058 |
+
"eval_steps_per_second": 0.738,
|
| 1059 |
+
"step": 70
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7319587628865979,
|
| 1063 |
+
"grad_norm": 0.06589022278785706,
|
| 1064 |
+
"learning_rate": 0.00011954022988505748,
|
| 1065 |
+
"loss": 0.8795,
|
| 1066 |
+
"step": 71
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7319587628865979,
|
| 1070 |
+
"eval_loss": 1.3753036260604858,
|
| 1071 |
+
"eval_runtime": 12.1728,
|
| 1072 |
+
"eval_samples_per_second": 11.09,
|
| 1073 |
+
"eval_steps_per_second": 0.739,
|
| 1074 |
+
"step": 71
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7422680412371134,
|
| 1078 |
+
"grad_norm": 0.12176728248596191,
|
| 1079 |
+
"learning_rate": 0.00011494252873563218,
|
| 1080 |
+
"loss": 0.9092,
|
| 1081 |
+
"step": 72
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.7422680412371134,
|
| 1085 |
+
"eval_loss": 1.3911007642745972,
|
| 1086 |
+
"eval_runtime": 12.1946,
|
| 1087 |
+
"eval_samples_per_second": 11.07,
|
| 1088 |
+
"eval_steps_per_second": 0.738,
|
| 1089 |
+
"step": 72
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.7525773195876289,
|
| 1093 |
+
"grad_norm": 0.05275936424732208,
|
| 1094 |
+
"learning_rate": 0.0001103448275862069,
|
| 1095 |
+
"loss": 0.9621,
|
| 1096 |
+
"step": 73
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.7525773195876289,
|
| 1100 |
+
"eval_loss": 1.407221794128418,
|
| 1101 |
+
"eval_runtime": 12.2388,
|
| 1102 |
+
"eval_samples_per_second": 11.031,
|
| 1103 |
+
"eval_steps_per_second": 0.735,
|
| 1104 |
+
"step": 73
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.7628865979381443,
|
| 1108 |
+
"grad_norm": 0.06748662143945694,
|
| 1109 |
+
"learning_rate": 0.00010574712643678162,
|
| 1110 |
+
"loss": 0.9154,
|
| 1111 |
+
"step": 74
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.7628865979381443,
|
| 1115 |
+
"eval_loss": 1.4170591831207275,
|
| 1116 |
+
"eval_runtime": 12.1869,
|
| 1117 |
+
"eval_samples_per_second": 11.078,
|
| 1118 |
+
"eval_steps_per_second": 0.739,
|
| 1119 |
+
"step": 74
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.7731958762886598,
|
| 1123 |
+
"grad_norm": 0.0736880972981453,
|
| 1124 |
+
"learning_rate": 0.00010114942528735633,
|
| 1125 |
+
"loss": 0.911,
|
| 1126 |
+
"step": 75
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.7731958762886598,
|
| 1130 |
+
"eval_loss": 1.4201780557632446,
|
| 1131 |
+
"eval_runtime": 12.2248,
|
| 1132 |
+
"eval_samples_per_second": 11.043,
|
| 1133 |
+
"eval_steps_per_second": 0.736,
|
| 1134 |
+
"step": 75
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.7835051546391752,
|
| 1138 |
+
"grad_norm": 0.05896177887916565,
|
| 1139 |
+
"learning_rate": 9.655172413793105e-05,
|
| 1140 |
+
"loss": 0.9412,
|
| 1141 |
+
"step": 76
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.7835051546391752,
|
| 1145 |
+
"eval_loss": 1.4200078248977661,
|
| 1146 |
+
"eval_runtime": 12.1599,
|
| 1147 |
+
"eval_samples_per_second": 11.102,
|
| 1148 |
+
"eval_steps_per_second": 0.74,
|
| 1149 |
+
"step": 76
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.7938144329896907,
|
| 1153 |
+
"grad_norm": 0.06385839730501175,
|
| 1154 |
+
"learning_rate": 9.195402298850575e-05,
|
| 1155 |
+
"loss": 0.8999,
|
| 1156 |
+
"step": 77
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.7938144329896907,
|
| 1160 |
+
"eval_loss": 1.4164679050445557,
|
| 1161 |
+
"eval_runtime": 12.1435,
|
| 1162 |
+
"eval_samples_per_second": 11.117,
|
| 1163 |
+
"eval_steps_per_second": 0.741,
|
| 1164 |
+
"step": 77
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8041237113402062,
|
| 1168 |
+
"grad_norm": 0.0656963661313057,
|
| 1169 |
+
"learning_rate": 8.735632183908047e-05,
|
| 1170 |
+
"loss": 0.8924,
|
| 1171 |
+
"step": 78
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8041237113402062,
|
| 1175 |
+
"eval_loss": 1.4131464958190918,
|
| 1176 |
+
"eval_runtime": 12.147,
|
| 1177 |
+
"eval_samples_per_second": 11.114,
|
| 1178 |
+
"eval_steps_per_second": 0.741,
|
| 1179 |
+
"step": 78
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8144329896907216,
|
| 1183 |
+
"grad_norm": 0.07376889884471893,
|
| 1184 |
+
"learning_rate": 8.275862068965517e-05,
|
| 1185 |
+
"loss": 0.9304,
|
| 1186 |
+
"step": 79
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8144329896907216,
|
| 1190 |
+
"eval_loss": 1.4098708629608154,
|
| 1191 |
+
"eval_runtime": 12.1509,
|
| 1192 |
+
"eval_samples_per_second": 11.11,
|
| 1193 |
+
"eval_steps_per_second": 0.741,
|
| 1194 |
+
"step": 79
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.8247422680412371,
|
| 1198 |
+
"grad_norm": 0.06411939859390259,
|
| 1199 |
+
"learning_rate": 7.81609195402299e-05,
|
| 1200 |
+
"loss": 0.9216,
|
| 1201 |
+
"step": 80
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.8247422680412371,
|
| 1205 |
+
"eval_loss": 1.4088366031646729,
|
| 1206 |
+
"eval_runtime": 12.1696,
|
| 1207 |
+
"eval_samples_per_second": 11.093,
|
| 1208 |
+
"eval_steps_per_second": 0.74,
|
| 1209 |
+
"step": 80
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.8350515463917526,
|
| 1213 |
+
"grad_norm": 0.06034550443291664,
|
| 1214 |
+
"learning_rate": 7.35632183908046e-05,
|
| 1215 |
+
"loss": 0.8914,
|
| 1216 |
+
"step": 81
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.8350515463917526,
|
| 1220 |
+
"eval_loss": 1.4062119722366333,
|
| 1221 |
+
"eval_runtime": 12.1085,
|
| 1222 |
+
"eval_samples_per_second": 11.149,
|
| 1223 |
+
"eval_steps_per_second": 0.743,
|
| 1224 |
+
"step": 81
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.845360824742268,
|
| 1228 |
+
"grad_norm": 0.06504890322685242,
|
| 1229 |
+
"learning_rate": 6.896551724137931e-05,
|
| 1230 |
+
"loss": 0.9608,
|
| 1231 |
+
"step": 82
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.845360824742268,
|
| 1235 |
+
"eval_loss": 1.4031813144683838,
|
| 1236 |
+
"eval_runtime": 12.1849,
|
| 1237 |
+
"eval_samples_per_second": 11.079,
|
| 1238 |
+
"eval_steps_per_second": 0.739,
|
| 1239 |
+
"step": 82
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.8556701030927835,
|
| 1243 |
+
"grad_norm": 0.05961364135146141,
|
| 1244 |
+
"learning_rate": 6.436781609195403e-05,
|
| 1245 |
+
"loss": 0.8992,
|
| 1246 |
+
"step": 83
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.8556701030927835,
|
| 1250 |
+
"eval_loss": 1.4021321535110474,
|
| 1251 |
+
"eval_runtime": 12.2033,
|
| 1252 |
+
"eval_samples_per_second": 11.063,
|
| 1253 |
+
"eval_steps_per_second": 0.738,
|
| 1254 |
+
"step": 83
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.865979381443299,
|
| 1258 |
+
"grad_norm": 0.06472059339284897,
|
| 1259 |
+
"learning_rate": 5.977011494252874e-05,
|
| 1260 |
+
"loss": 0.9458,
|
| 1261 |
+
"step": 84
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.865979381443299,
|
| 1265 |
+
"eval_loss": 1.3988347053527832,
|
| 1266 |
+
"eval_runtime": 12.169,
|
| 1267 |
+
"eval_samples_per_second": 11.094,
|
| 1268 |
+
"eval_steps_per_second": 0.74,
|
| 1269 |
+
"step": 84
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8762886597938144,
|
| 1273 |
+
"grad_norm": 0.05986656993627548,
|
| 1274 |
+
"learning_rate": 5.517241379310345e-05,
|
| 1275 |
+
"loss": 0.8628,
|
| 1276 |
+
"step": 85
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8762886597938144,
|
| 1280 |
+
"eval_loss": 1.3969188928604126,
|
| 1281 |
+
"eval_runtime": 12.2292,
|
| 1282 |
+
"eval_samples_per_second": 11.039,
|
| 1283 |
+
"eval_steps_per_second": 0.736,
|
| 1284 |
+
"step": 85
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8865979381443299,
|
| 1288 |
+
"grad_norm": 0.062148451805114746,
|
| 1289 |
+
"learning_rate": 5.057471264367817e-05,
|
| 1290 |
+
"loss": 0.8841,
|
| 1291 |
+
"step": 86
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8865979381443299,
|
| 1295 |
+
"eval_loss": 1.3965938091278076,
|
| 1296 |
+
"eval_runtime": 12.1883,
|
| 1297 |
+
"eval_samples_per_second": 11.076,
|
| 1298 |
+
"eval_steps_per_second": 0.738,
|
| 1299 |
+
"step": 86
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.8969072164948454,
|
| 1303 |
+
"grad_norm": 0.05559258908033371,
|
| 1304 |
+
"learning_rate": 4.597701149425287e-05,
|
| 1305 |
+
"loss": 0.8883,
|
| 1306 |
+
"step": 87
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.8969072164948454,
|
| 1310 |
+
"eval_loss": 1.3965078592300415,
|
| 1311 |
+
"eval_runtime": 12.1185,
|
| 1312 |
+
"eval_samples_per_second": 11.14,
|
| 1313 |
+
"eval_steps_per_second": 0.743,
|
| 1314 |
+
"step": 87
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.9072164948453608,
|
| 1318 |
+
"grad_norm": 0.05684094876050949,
|
| 1319 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 1320 |
+
"loss": 0.8765,
|
| 1321 |
+
"step": 88
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.9072164948453608,
|
| 1325 |
+
"eval_loss": 1.3967227935791016,
|
| 1326 |
+
"eval_runtime": 12.1899,
|
| 1327 |
+
"eval_samples_per_second": 11.075,
|
| 1328 |
+
"eval_steps_per_second": 0.738,
|
| 1329 |
+
"step": 88
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.9175257731958762,
|
| 1333 |
+
"grad_norm": 0.05952519550919533,
|
| 1334 |
+
"learning_rate": 3.67816091954023e-05,
|
| 1335 |
+
"loss": 0.8598,
|
| 1336 |
+
"step": 89
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.9175257731958762,
|
| 1340 |
+
"eval_loss": 1.3951915502548218,
|
| 1341 |
+
"eval_runtime": 12.1745,
|
| 1342 |
+
"eval_samples_per_second": 11.089,
|
| 1343 |
+
"eval_steps_per_second": 0.739,
|
| 1344 |
+
"step": 89
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.9278350515463918,
|
| 1348 |
+
"grad_norm": 0.06364478170871735,
|
| 1349 |
+
"learning_rate": 3.218390804597701e-05,
|
| 1350 |
+
"loss": 0.9653,
|
| 1351 |
+
"step": 90
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.9278350515463918,
|
| 1355 |
+
"eval_loss": 1.394257664680481,
|
| 1356 |
+
"eval_runtime": 12.2896,
|
| 1357 |
+
"eval_samples_per_second": 10.985,
|
| 1358 |
+
"eval_steps_per_second": 0.732,
|
| 1359 |
+
"step": 90
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.9381443298969072,
|
| 1363 |
+
"grad_norm": 0.06441052258014679,
|
| 1364 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 1365 |
+
"loss": 0.9397,
|
| 1366 |
+
"step": 91
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.9381443298969072,
|
| 1370 |
+
"eval_loss": 1.392314076423645,
|
| 1371 |
+
"eval_runtime": 12.2278,
|
| 1372 |
+
"eval_samples_per_second": 11.04,
|
| 1373 |
+
"eval_steps_per_second": 0.736,
|
| 1374 |
+
"step": 91
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9484536082474226,
|
| 1378 |
+
"grad_norm": 0.06320352107286453,
|
| 1379 |
+
"learning_rate": 2.2988505747126437e-05,
|
| 1380 |
+
"loss": 0.8635,
|
| 1381 |
+
"step": 92
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9484536082474226,
|
| 1385 |
+
"eval_loss": 1.3919230699539185,
|
| 1386 |
+
"eval_runtime": 12.1765,
|
| 1387 |
+
"eval_samples_per_second": 11.087,
|
| 1388 |
+
"eval_steps_per_second": 0.739,
|
| 1389 |
+
"step": 92
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9587628865979382,
|
| 1393 |
+
"grad_norm": 0.062386397272348404,
|
| 1394 |
+
"learning_rate": 1.839080459770115e-05,
|
| 1395 |
+
"loss": 0.9257,
|
| 1396 |
+
"step": 93
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9587628865979382,
|
| 1400 |
+
"eval_loss": 1.3923670053482056,
|
| 1401 |
+
"eval_runtime": 12.2566,
|
| 1402 |
+
"eval_samples_per_second": 11.014,
|
| 1403 |
+
"eval_steps_per_second": 0.734,
|
| 1404 |
+
"step": 93
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.9690721649484536,
|
| 1408 |
+
"grad_norm": 0.05672856792807579,
|
| 1409 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 1410 |
+
"loss": 0.8754,
|
| 1411 |
+
"step": 94
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.9690721649484536,
|
| 1415 |
+
"eval_loss": 1.393159031867981,
|
| 1416 |
+
"eval_runtime": 12.1859,
|
| 1417 |
+
"eval_samples_per_second": 11.078,
|
| 1418 |
+
"eval_steps_per_second": 0.739,
|
| 1419 |
+
"step": 94
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.979381443298969,
|
| 1423 |
+
"grad_norm": 0.06344141811132431,
|
| 1424 |
+
"learning_rate": 9.195402298850575e-06,
|
| 1425 |
+
"loss": 0.9454,
|
| 1426 |
+
"step": 95
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.979381443298969,
|
| 1430 |
+
"eval_loss": 1.3938028812408447,
|
| 1431 |
+
"eval_runtime": 12.1382,
|
| 1432 |
+
"eval_samples_per_second": 11.122,
|
| 1433 |
+
"eval_steps_per_second": 0.741,
|
| 1434 |
+
"step": 95
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.9896907216494846,
|
| 1438 |
+
"grad_norm": 0.06258992105722427,
|
| 1439 |
+
"learning_rate": 4.5977011494252875e-06,
|
| 1440 |
+
"loss": 0.9112,
|
| 1441 |
+
"step": 96
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.9896907216494846,
|
| 1445 |
+
"eval_loss": 1.394579529762268,
|
| 1446 |
+
"eval_runtime": 12.1768,
|
| 1447 |
+
"eval_samples_per_second": 11.087,
|
| 1448 |
+
"eval_steps_per_second": 0.739,
|
| 1449 |
+
"step": 96
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.0,
|
| 1453 |
+
"grad_norm": 0.08749664574861526,
|
| 1454 |
+
"learning_rate": 0.0,
|
| 1455 |
+
"loss": 0.8526,
|
| 1456 |
+
"step": 97
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.0,
|
| 1460 |
+
"eval_loss": 1.3950037956237793,
|
| 1461 |
+
"eval_runtime": 12.1878,
|
| 1462 |
+
"eval_samples_per_second": 11.077,
|
| 1463 |
+
"eval_steps_per_second": 0.738,
|
| 1464 |
+
"step": 97
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 1.0,
|
| 1468 |
+
"step": 97,
|
| 1469 |
+
"total_flos": 3.573314566697779e+16,
|
| 1470 |
+
"train_loss": 1.1783372968742527,
|
| 1471 |
+
"train_runtime": 2093.8635,
|
| 1472 |
+
"train_samples_per_second": 1.472,
|
| 1473 |
+
"train_steps_per_second": 0.046
|
| 1474 |
+
}
|
| 1475 |
+
],
|
| 1476 |
+
"logging_steps": 1,
|
| 1477 |
+
"max_steps": 97,
|
| 1478 |
+
"num_input_tokens_seen": 0,
|
| 1479 |
+
"num_train_epochs": 1,
|
| 1480 |
+
"save_steps": 10,
|
| 1481 |
+
"stateful_callbacks": {
|
| 1482 |
+
"TrainerControl": {
|
| 1483 |
+
"args": {
|
| 1484 |
+
"should_epoch_stop": false,
|
| 1485 |
+
"should_evaluate": false,
|
| 1486 |
+
"should_log": false,
|
| 1487 |
+
"should_save": true,
|
| 1488 |
+
"should_training_stop": false
|
| 1489 |
+
},
|
| 1490 |
+
"attributes": {}
|
| 1491 |
+
}
|
| 1492 |
+
},
|
| 1493 |
+
"total_flos": 3.573314566697779e+16,
|
| 1494 |
+
"train_batch_size": 32,
|
| 1495 |
+
"trial_name": null,
|
| 1496 |
+
"trial_params": null
|
| 1497 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e2496b844a585edb80814b321f3eb6391f1e777dbd2b00fdafd91d647f31951
|
| 3 |
+
size 5688
|