Upload folder using huggingface_hub
Browse files- checkpoint-1950/README.md +202 -0
- checkpoint-1950/adapter_config.json +34 -0
- checkpoint-1950/adapter_model.safetensors +3 -0
- checkpoint-1950/optimizer.pt +3 -0
- checkpoint-1950/rng_state.pth +3 -0
- checkpoint-1950/scheduler.pt +3 -0
- checkpoint-1950/trainer_state.json +712 -0
- checkpoint-1950/training_args.bin +3 -0
- checkpoint-1953/README.md +202 -0
- checkpoint-1953/adapter_config.json +34 -0
- checkpoint-1953/adapter_model.safetensors +3 -0
- checkpoint-1953/optimizer.pt +3 -0
- checkpoint-1953/rng_state.pth +3 -0
- checkpoint-1953/scheduler.pt +3 -0
- checkpoint-1953/trainer_state.json +712 -0
- checkpoint-1953/training_args.bin +3 -0
- tokenizer_config.json +0 -0
checkpoint-1950/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.14.0
|
checkpoint-1950/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 64,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"o_proj",
|
| 27 |
+
"qkv_proj",
|
| 28 |
+
"gate_up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-1950/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2db8573795b769d9c0fd223f635c52a93dc1728a471eb1b50ba87b20a9ff4442
|
| 3 |
+
size 184584072
|
checkpoint-1950/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aa67ab6b941679217f74978eee8227d0292b7d8939124fff5d409901784fb89
|
| 3 |
+
size 369314554
|
checkpoint-1950/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9dac9d3fda7d0bf2aae97dec5c19a6d8593551513065f958c12cd435c36bd93
|
| 3 |
+
size 14244
|
checkpoint-1950/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62a804885b6e63e4121abba74aaa0135a84845303880f4e48a30f0f65f812a0f
|
| 3 |
+
size 1064
|
checkpoint-1950/trainer_state.json
ADDED
|
@@ -0,0 +1,712 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9953917050691246,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1950,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.030721966205837174,
|
| 13 |
+
"grad_norm": 0.1512155830860138,
|
| 14 |
+
"learning_rate": 9.897593445980543e-05,
|
| 15 |
+
"loss": 1.4355,
|
| 16 |
+
"step": 20
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06144393241167435,
|
| 20 |
+
"grad_norm": 0.07312213629484177,
|
| 21 |
+
"learning_rate": 9.795186891961086e-05,
|
| 22 |
+
"loss": 0.0851,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09216589861751152,
|
| 27 |
+
"grad_norm": 0.08094536513090134,
|
| 28 |
+
"learning_rate": 9.692780337941628e-05,
|
| 29 |
+
"loss": 0.056,
|
| 30 |
+
"step": 60
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1228878648233487,
|
| 34 |
+
"grad_norm": 0.05470961704850197,
|
| 35 |
+
"learning_rate": 9.590373783922172e-05,
|
| 36 |
+
"loss": 0.0474,
|
| 37 |
+
"step": 80
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15360983102918588,
|
| 41 |
+
"grad_norm": 0.05098584294319153,
|
| 42 |
+
"learning_rate": 9.487967229902714e-05,
|
| 43 |
+
"loss": 0.0454,
|
| 44 |
+
"step": 100
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18433179723502305,
|
| 48 |
+
"grad_norm": 0.058107804507017136,
|
| 49 |
+
"learning_rate": 9.385560675883256e-05,
|
| 50 |
+
"loss": 0.0438,
|
| 51 |
+
"step": 120
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21505376344086022,
|
| 55 |
+
"grad_norm": 0.05871523171663284,
|
| 56 |
+
"learning_rate": 9.2831541218638e-05,
|
| 57 |
+
"loss": 0.0412,
|
| 58 |
+
"step": 140
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2457757296466974,
|
| 62 |
+
"grad_norm": 0.053748778998851776,
|
| 63 |
+
"learning_rate": 9.180747567844342e-05,
|
| 64 |
+
"loss": 0.041,
|
| 65 |
+
"step": 160
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2764976958525346,
|
| 69 |
+
"grad_norm": 0.04749336093664169,
|
| 70 |
+
"learning_rate": 9.078341013824884e-05,
|
| 71 |
+
"loss": 0.0394,
|
| 72 |
+
"step": 180
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.30721966205837176,
|
| 76 |
+
"grad_norm": 0.051831599324941635,
|
| 77 |
+
"learning_rate": 8.975934459805428e-05,
|
| 78 |
+
"loss": 0.0382,
|
| 79 |
+
"step": 200
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3379416282642089,
|
| 83 |
+
"grad_norm": 0.05264313519001007,
|
| 84 |
+
"learning_rate": 8.873527905785972e-05,
|
| 85 |
+
"loss": 0.038,
|
| 86 |
+
"step": 220
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3686635944700461,
|
| 90 |
+
"grad_norm": 0.048551175743341446,
|
| 91 |
+
"learning_rate": 8.771121351766514e-05,
|
| 92 |
+
"loss": 0.0371,
|
| 93 |
+
"step": 240
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39938556067588327,
|
| 97 |
+
"grad_norm": 0.05650593340396881,
|
| 98 |
+
"learning_rate": 8.668714797747056e-05,
|
| 99 |
+
"loss": 0.0361,
|
| 100 |
+
"step": 260
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.43010752688172044,
|
| 104 |
+
"grad_norm": 0.053584594279527664,
|
| 105 |
+
"learning_rate": 8.566308243727598e-05,
|
| 106 |
+
"loss": 0.0373,
|
| 107 |
+
"step": 280
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4608294930875576,
|
| 111 |
+
"grad_norm": 0.052629247307777405,
|
| 112 |
+
"learning_rate": 8.463901689708142e-05,
|
| 113 |
+
"loss": 0.0369,
|
| 114 |
+
"step": 300
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4915514592933948,
|
| 118 |
+
"grad_norm": 0.048385780304670334,
|
| 119 |
+
"learning_rate": 8.361495135688684e-05,
|
| 120 |
+
"loss": 0.0365,
|
| 121 |
+
"step": 320
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.522273425499232,
|
| 125 |
+
"grad_norm": 0.05694854259490967,
|
| 126 |
+
"learning_rate": 8.259088581669228e-05,
|
| 127 |
+
"loss": 0.0356,
|
| 128 |
+
"step": 340
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5529953917050692,
|
| 132 |
+
"grad_norm": 0.045489437878131866,
|
| 133 |
+
"learning_rate": 8.15668202764977e-05,
|
| 134 |
+
"loss": 0.0352,
|
| 135 |
+
"step": 360
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5837173579109063,
|
| 139 |
+
"grad_norm": 0.04657004028558731,
|
| 140 |
+
"learning_rate": 8.054275473630313e-05,
|
| 141 |
+
"loss": 0.034,
|
| 142 |
+
"step": 380
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6144393241167435,
|
| 146 |
+
"grad_norm": 0.04624749720096588,
|
| 147 |
+
"learning_rate": 7.951868919610856e-05,
|
| 148 |
+
"loss": 0.0339,
|
| 149 |
+
"step": 400
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6451612903225806,
|
| 153 |
+
"grad_norm": 0.05539771914482117,
|
| 154 |
+
"learning_rate": 7.849462365591398e-05,
|
| 155 |
+
"loss": 0.0349,
|
| 156 |
+
"step": 420
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6758832565284179,
|
| 160 |
+
"grad_norm": 0.05361827835440636,
|
| 161 |
+
"learning_rate": 7.74705581157194e-05,
|
| 162 |
+
"loss": 0.0342,
|
| 163 |
+
"step": 440
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.706605222734255,
|
| 167 |
+
"grad_norm": 0.04784597083926201,
|
| 168 |
+
"learning_rate": 7.644649257552484e-05,
|
| 169 |
+
"loss": 0.0338,
|
| 170 |
+
"step": 460
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7373271889400922,
|
| 174 |
+
"grad_norm": 0.04615575075149536,
|
| 175 |
+
"learning_rate": 7.542242703533027e-05,
|
| 176 |
+
"loss": 0.0332,
|
| 177 |
+
"step": 480
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7680491551459293,
|
| 181 |
+
"grad_norm": 0.0510617159307003,
|
| 182 |
+
"learning_rate": 7.43983614951357e-05,
|
| 183 |
+
"loss": 0.0334,
|
| 184 |
+
"step": 500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7987711213517665,
|
| 188 |
+
"grad_norm": 0.05362660437822342,
|
| 189 |
+
"learning_rate": 7.337429595494112e-05,
|
| 190 |
+
"loss": 0.0334,
|
| 191 |
+
"step": 520
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8294930875576036,
|
| 195 |
+
"grad_norm": 0.057389482855796814,
|
| 196 |
+
"learning_rate": 7.235023041474655e-05,
|
| 197 |
+
"loss": 0.032,
|
| 198 |
+
"step": 540
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8602150537634409,
|
| 202 |
+
"grad_norm": 0.04695713147521019,
|
| 203 |
+
"learning_rate": 7.132616487455197e-05,
|
| 204 |
+
"loss": 0.033,
|
| 205 |
+
"step": 560
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.890937019969278,
|
| 209 |
+
"grad_norm": 0.04749588668346405,
|
| 210 |
+
"learning_rate": 7.030209933435741e-05,
|
| 211 |
+
"loss": 0.0329,
|
| 212 |
+
"step": 580
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9216589861751152,
|
| 216 |
+
"grad_norm": 0.04851127415895462,
|
| 217 |
+
"learning_rate": 6.927803379416283e-05,
|
| 218 |
+
"loss": 0.0325,
|
| 219 |
+
"step": 600
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9523809523809523,
|
| 223 |
+
"grad_norm": 0.04438120499253273,
|
| 224 |
+
"learning_rate": 6.825396825396825e-05,
|
| 225 |
+
"loss": 0.033,
|
| 226 |
+
"step": 620
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9831029185867896,
|
| 230 |
+
"grad_norm": 0.040635980665683746,
|
| 231 |
+
"learning_rate": 6.722990271377369e-05,
|
| 232 |
+
"loss": 0.0321,
|
| 233 |
+
"step": 640
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0138248847926268,
|
| 237 |
+
"grad_norm": 0.06111369654536247,
|
| 238 |
+
"learning_rate": 6.620583717357911e-05,
|
| 239 |
+
"loss": 0.0316,
|
| 240 |
+
"step": 660
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.044546850998464,
|
| 244 |
+
"grad_norm": 0.04458026960492134,
|
| 245 |
+
"learning_rate": 6.518177163338453e-05,
|
| 246 |
+
"loss": 0.0294,
|
| 247 |
+
"step": 680
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.075268817204301,
|
| 251 |
+
"grad_norm": 0.049614399671554565,
|
| 252 |
+
"learning_rate": 6.415770609318996e-05,
|
| 253 |
+
"loss": 0.0292,
|
| 254 |
+
"step": 700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.1059907834101383,
|
| 258 |
+
"grad_norm": 0.0497017428278923,
|
| 259 |
+
"learning_rate": 6.31336405529954e-05,
|
| 260 |
+
"loss": 0.0296,
|
| 261 |
+
"step": 720
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.1367127496159755,
|
| 265 |
+
"grad_norm": 0.07175371795892715,
|
| 266 |
+
"learning_rate": 6.210957501280083e-05,
|
| 267 |
+
"loss": 0.03,
|
| 268 |
+
"step": 740
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.1674347158218126,
|
| 272 |
+
"grad_norm": 0.051305390894412994,
|
| 273 |
+
"learning_rate": 6.108550947260625e-05,
|
| 274 |
+
"loss": 0.0299,
|
| 275 |
+
"step": 760
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.1981566820276497,
|
| 279 |
+
"grad_norm": 0.04788351058959961,
|
| 280 |
+
"learning_rate": 6.006144393241168e-05,
|
| 281 |
+
"loss": 0.0288,
|
| 282 |
+
"step": 780
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.228878648233487,
|
| 286 |
+
"grad_norm": 0.042062848806381226,
|
| 287 |
+
"learning_rate": 5.90373783922171e-05,
|
| 288 |
+
"loss": 0.0294,
|
| 289 |
+
"step": 800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.2596006144393241,
|
| 293 |
+
"grad_norm": 0.04787632077932358,
|
| 294 |
+
"learning_rate": 5.801331285202253e-05,
|
| 295 |
+
"loss": 0.0289,
|
| 296 |
+
"step": 820
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.2903225806451613,
|
| 300 |
+
"grad_norm": 0.04673902690410614,
|
| 301 |
+
"learning_rate": 5.6989247311827965e-05,
|
| 302 |
+
"loss": 0.0295,
|
| 303 |
+
"step": 840
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.3210445468509984,
|
| 307 |
+
"grad_norm": 0.049946922808885574,
|
| 308 |
+
"learning_rate": 5.5965181771633393e-05,
|
| 309 |
+
"loss": 0.0288,
|
| 310 |
+
"step": 860
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.3517665130568357,
|
| 314 |
+
"grad_norm": 0.04578813165426254,
|
| 315 |
+
"learning_rate": 5.4941116231438816e-05,
|
| 316 |
+
"loss": 0.0288,
|
| 317 |
+
"step": 880
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.3824884792626728,
|
| 321 |
+
"grad_norm": 0.04998716711997986,
|
| 322 |
+
"learning_rate": 5.3917050691244244e-05,
|
| 323 |
+
"loss": 0.0287,
|
| 324 |
+
"step": 900
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.41321044546851,
|
| 328 |
+
"grad_norm": 0.043574895709753036,
|
| 329 |
+
"learning_rate": 5.2892985151049667e-05,
|
| 330 |
+
"loss": 0.0291,
|
| 331 |
+
"step": 920
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4439324116743473,
|
| 335 |
+
"grad_norm": 0.04888541251420975,
|
| 336 |
+
"learning_rate": 5.1868919610855095e-05,
|
| 337 |
+
"loss": 0.0286,
|
| 338 |
+
"step": 940
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.4746543778801844,
|
| 342 |
+
"grad_norm": 0.04586420953273773,
|
| 343 |
+
"learning_rate": 5.084485407066052e-05,
|
| 344 |
+
"loss": 0.0287,
|
| 345 |
+
"step": 960
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.5053763440860215,
|
| 349 |
+
"grad_norm": 0.054376959800720215,
|
| 350 |
+
"learning_rate": 4.982078853046595e-05,
|
| 351 |
+
"loss": 0.0282,
|
| 352 |
+
"step": 980
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.5360983102918588,
|
| 356 |
+
"grad_norm": 0.04396720603108406,
|
| 357 |
+
"learning_rate": 4.879672299027138e-05,
|
| 358 |
+
"loss": 0.0287,
|
| 359 |
+
"step": 1000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.5668202764976957,
|
| 363 |
+
"grad_norm": 0.045876361429691315,
|
| 364 |
+
"learning_rate": 4.7772657450076804e-05,
|
| 365 |
+
"loss": 0.0287,
|
| 366 |
+
"step": 1020
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.597542242703533,
|
| 370 |
+
"grad_norm": 0.054340336471796036,
|
| 371 |
+
"learning_rate": 4.674859190988223e-05,
|
| 372 |
+
"loss": 0.0297,
|
| 373 |
+
"step": 1040
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.6282642089093702,
|
| 377 |
+
"grad_norm": 0.046706799417734146,
|
| 378 |
+
"learning_rate": 4.572452636968766e-05,
|
| 379 |
+
"loss": 0.0287,
|
| 380 |
+
"step": 1060
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.6589861751152073,
|
| 384 |
+
"grad_norm": 0.05444665625691414,
|
| 385 |
+
"learning_rate": 4.470046082949309e-05,
|
| 386 |
+
"loss": 0.0284,
|
| 387 |
+
"step": 1080
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.6897081413210446,
|
| 391 |
+
"grad_norm": 0.04873611778020859,
|
| 392 |
+
"learning_rate": 4.367639528929851e-05,
|
| 393 |
+
"loss": 0.0285,
|
| 394 |
+
"step": 1100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.7204301075268817,
|
| 398 |
+
"grad_norm": 0.049390435218811035,
|
| 399 |
+
"learning_rate": 4.265232974910394e-05,
|
| 400 |
+
"loss": 0.0282,
|
| 401 |
+
"step": 1120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.7511520737327189,
|
| 405 |
+
"grad_norm": 0.04932021722197533,
|
| 406 |
+
"learning_rate": 4.162826420890937e-05,
|
| 407 |
+
"loss": 0.0283,
|
| 408 |
+
"step": 1140
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.7818740399385562,
|
| 412 |
+
"grad_norm": 0.0462203249335289,
|
| 413 |
+
"learning_rate": 4.06041986687148e-05,
|
| 414 |
+
"loss": 0.0291,
|
| 415 |
+
"step": 1160
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.812596006144393,
|
| 419 |
+
"grad_norm": 0.045431822538375854,
|
| 420 |
+
"learning_rate": 3.958013312852022e-05,
|
| 421 |
+
"loss": 0.0285,
|
| 422 |
+
"step": 1180
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.8433179723502304,
|
| 426 |
+
"grad_norm": 0.04209066182374954,
|
| 427 |
+
"learning_rate": 3.855606758832566e-05,
|
| 428 |
+
"loss": 0.0281,
|
| 429 |
+
"step": 1200
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.8740399385560675,
|
| 433 |
+
"grad_norm": 0.04643911495804787,
|
| 434 |
+
"learning_rate": 3.753200204813108e-05,
|
| 435 |
+
"loss": 0.0282,
|
| 436 |
+
"step": 1220
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.9047619047619047,
|
| 440 |
+
"grad_norm": 0.05297870934009552,
|
| 441 |
+
"learning_rate": 3.650793650793651e-05,
|
| 442 |
+
"loss": 0.0283,
|
| 443 |
+
"step": 1240
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.935483870967742,
|
| 447 |
+
"grad_norm": 0.045079439878463745,
|
| 448 |
+
"learning_rate": 3.548387096774194e-05,
|
| 449 |
+
"loss": 0.0286,
|
| 450 |
+
"step": 1260
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.966205837173579,
|
| 454 |
+
"grad_norm": 0.04396852105855942,
|
| 455 |
+
"learning_rate": 3.4459805427547367e-05,
|
| 456 |
+
"loss": 0.028,
|
| 457 |
+
"step": 1280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.9969278033794162,
|
| 461 |
+
"grad_norm": 0.04810136556625366,
|
| 462 |
+
"learning_rate": 3.343573988735279e-05,
|
| 463 |
+
"loss": 0.0278,
|
| 464 |
+
"step": 1300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.0276497695852536,
|
| 468 |
+
"grad_norm": 0.04735556244850159,
|
| 469 |
+
"learning_rate": 3.2411674347158224e-05,
|
| 470 |
+
"loss": 0.0252,
|
| 471 |
+
"step": 1320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.0583717357910905,
|
| 475 |
+
"grad_norm": 0.047580786049366,
|
| 476 |
+
"learning_rate": 3.1387608806963646e-05,
|
| 477 |
+
"loss": 0.0252,
|
| 478 |
+
"step": 1340
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.089093701996928,
|
| 482 |
+
"grad_norm": 0.05648692324757576,
|
| 483 |
+
"learning_rate": 3.0363543266769072e-05,
|
| 484 |
+
"loss": 0.0259,
|
| 485 |
+
"step": 1360
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.119815668202765,
|
| 489 |
+
"grad_norm": 0.05537613108754158,
|
| 490 |
+
"learning_rate": 2.9339477726574504e-05,
|
| 491 |
+
"loss": 0.0249,
|
| 492 |
+
"step": 1380
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.150537634408602,
|
| 496 |
+
"grad_norm": 0.05248798429965973,
|
| 497 |
+
"learning_rate": 2.831541218637993e-05,
|
| 498 |
+
"loss": 0.0247,
|
| 499 |
+
"step": 1400
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.1812596006144394,
|
| 503 |
+
"grad_norm": 0.05146801844239235,
|
| 504 |
+
"learning_rate": 2.7291346646185355e-05,
|
| 505 |
+
"loss": 0.0253,
|
| 506 |
+
"step": 1420
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.2119815668202767,
|
| 510 |
+
"grad_norm": 0.05279408395290375,
|
| 511 |
+
"learning_rate": 2.626728110599078e-05,
|
| 512 |
+
"loss": 0.0252,
|
| 513 |
+
"step": 1440
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.2427035330261136,
|
| 517 |
+
"grad_norm": 0.050060730427503586,
|
| 518 |
+
"learning_rate": 2.5243215565796213e-05,
|
| 519 |
+
"loss": 0.0252,
|
| 520 |
+
"step": 1460
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.273425499231951,
|
| 524 |
+
"grad_norm": 0.05538507178425789,
|
| 525 |
+
"learning_rate": 2.421915002560164e-05,
|
| 526 |
+
"loss": 0.0248,
|
| 527 |
+
"step": 1480
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.3041474654377883,
|
| 531 |
+
"grad_norm": 0.0514647401869297,
|
| 532 |
+
"learning_rate": 2.3195084485407068e-05,
|
| 533 |
+
"loss": 0.0254,
|
| 534 |
+
"step": 1500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.334869431643625,
|
| 538 |
+
"grad_norm": 0.05420660972595215,
|
| 539 |
+
"learning_rate": 2.2171018945212493e-05,
|
| 540 |
+
"loss": 0.0252,
|
| 541 |
+
"step": 1520
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.3655913978494625,
|
| 545 |
+
"grad_norm": 0.05415211245417595,
|
| 546 |
+
"learning_rate": 2.1146953405017922e-05,
|
| 547 |
+
"loss": 0.0248,
|
| 548 |
+
"step": 1540
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.3963133640552994,
|
| 552 |
+
"grad_norm": 0.054315581917762756,
|
| 553 |
+
"learning_rate": 2.012288786482335e-05,
|
| 554 |
+
"loss": 0.0247,
|
| 555 |
+
"step": 1560
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.4270353302611367,
|
| 559 |
+
"grad_norm": 0.052055474370718,
|
| 560 |
+
"learning_rate": 1.9098822324628776e-05,
|
| 561 |
+
"loss": 0.0248,
|
| 562 |
+
"step": 1580
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.457757296466974,
|
| 566 |
+
"grad_norm": 0.04970501363277435,
|
| 567 |
+
"learning_rate": 1.8074756784434205e-05,
|
| 568 |
+
"loss": 0.0249,
|
| 569 |
+
"step": 1600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.488479262672811,
|
| 573 |
+
"grad_norm": 0.05602123215794563,
|
| 574 |
+
"learning_rate": 1.7050691244239634e-05,
|
| 575 |
+
"loss": 0.0247,
|
| 576 |
+
"step": 1620
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.5192012288786483,
|
| 580 |
+
"grad_norm": 0.05873609706759453,
|
| 581 |
+
"learning_rate": 1.602662570404506e-05,
|
| 582 |
+
"loss": 0.0242,
|
| 583 |
+
"step": 1640
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.549923195084485,
|
| 587 |
+
"grad_norm": 0.06298800557851791,
|
| 588 |
+
"learning_rate": 1.5002560163850487e-05,
|
| 589 |
+
"loss": 0.025,
|
| 590 |
+
"step": 1660
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.5806451612903225,
|
| 594 |
+
"grad_norm": 0.051834046840667725,
|
| 595 |
+
"learning_rate": 1.3978494623655914e-05,
|
| 596 |
+
"loss": 0.0246,
|
| 597 |
+
"step": 1680
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.61136712749616,
|
| 601 |
+
"grad_norm": 0.05892595276236534,
|
| 602 |
+
"learning_rate": 1.2954429083461341e-05,
|
| 603 |
+
"loss": 0.0243,
|
| 604 |
+
"step": 1700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.6420890937019967,
|
| 608 |
+
"grad_norm": 0.05549076944589615,
|
| 609 |
+
"learning_rate": 1.1930363543266769e-05,
|
| 610 |
+
"loss": 0.0252,
|
| 611 |
+
"step": 1720
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.672811059907834,
|
| 615 |
+
"grad_norm": 0.05536745488643646,
|
| 616 |
+
"learning_rate": 1.0906298003072197e-05,
|
| 617 |
+
"loss": 0.0253,
|
| 618 |
+
"step": 1740
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.7035330261136714,
|
| 622 |
+
"grad_norm": 0.05979848653078079,
|
| 623 |
+
"learning_rate": 9.882232462877625e-06,
|
| 624 |
+
"loss": 0.0252,
|
| 625 |
+
"step": 1760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.7342549923195083,
|
| 629 |
+
"grad_norm": 0.04978615790605545,
|
| 630 |
+
"learning_rate": 8.858166922683052e-06,
|
| 631 |
+
"loss": 0.0247,
|
| 632 |
+
"step": 1780
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.7649769585253456,
|
| 636 |
+
"grad_norm": 0.05952267348766327,
|
| 637 |
+
"learning_rate": 7.834101382488479e-06,
|
| 638 |
+
"loss": 0.0242,
|
| 639 |
+
"step": 1800
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.795698924731183,
|
| 643 |
+
"grad_norm": 0.05571313947439194,
|
| 644 |
+
"learning_rate": 6.810035842293908e-06,
|
| 645 |
+
"loss": 0.0242,
|
| 646 |
+
"step": 1820
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.82642089093702,
|
| 650 |
+
"grad_norm": 0.060350194573402405,
|
| 651 |
+
"learning_rate": 5.785970302099334e-06,
|
| 652 |
+
"loss": 0.0247,
|
| 653 |
+
"step": 1840
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.857142857142857,
|
| 657 |
+
"grad_norm": 0.053442951291799545,
|
| 658 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 659 |
+
"loss": 0.0241,
|
| 660 |
+
"step": 1860
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.8878648233486945,
|
| 664 |
+
"grad_norm": 0.06173479184508324,
|
| 665 |
+
"learning_rate": 3.7378392217101896e-06,
|
| 666 |
+
"loss": 0.0244,
|
| 667 |
+
"step": 1880
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.9185867895545314,
|
| 671 |
+
"grad_norm": 0.05805809050798416,
|
| 672 |
+
"learning_rate": 2.7137736815156172e-06,
|
| 673 |
+
"loss": 0.0245,
|
| 674 |
+
"step": 1900
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.9493087557603688,
|
| 678 |
+
"grad_norm": 0.05551229417324066,
|
| 679 |
+
"learning_rate": 1.6897081413210446e-06,
|
| 680 |
+
"loss": 0.0244,
|
| 681 |
+
"step": 1920
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.980030721966206,
|
| 685 |
+
"grad_norm": 0.05892977863550186,
|
| 686 |
+
"learning_rate": 6.656426011264722e-07,
|
| 687 |
+
"loss": 0.0236,
|
| 688 |
+
"step": 1940
|
| 689 |
+
}
|
| 690 |
+
],
|
| 691 |
+
"logging_steps": 20,
|
| 692 |
+
"max_steps": 1953,
|
| 693 |
+
"num_input_tokens_seen": 0,
|
| 694 |
+
"num_train_epochs": 3,
|
| 695 |
+
"save_steps": 50,
|
| 696 |
+
"stateful_callbacks": {
|
| 697 |
+
"TrainerControl": {
|
| 698 |
+
"args": {
|
| 699 |
+
"should_epoch_stop": false,
|
| 700 |
+
"should_evaluate": false,
|
| 701 |
+
"should_log": false,
|
| 702 |
+
"should_save": true,
|
| 703 |
+
"should_training_stop": false
|
| 704 |
+
},
|
| 705 |
+
"attributes": {}
|
| 706 |
+
}
|
| 707 |
+
},
|
| 708 |
+
"total_flos": 6.262477486093763e+17,
|
| 709 |
+
"train_batch_size": 4,
|
| 710 |
+
"trial_name": null,
|
| 711 |
+
"trial_params": null
|
| 712 |
+
}
|
checkpoint-1950/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1479fdd1dbc57e34459b11b8b5a6fa52e44010c7da49005807d4ee5d68528000
|
| 3 |
+
size 5304
|
checkpoint-1953/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.14.0
|
checkpoint-1953/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 64,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"o_proj",
|
| 27 |
+
"qkv_proj",
|
| 28 |
+
"gate_up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-1953/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:984947e531e78f25b7af0feffcf3013c3cf503d78e8ed985d6ea513917c1acfc
|
| 3 |
+
size 184584072
|
checkpoint-1953/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd8e6d32238ab07ef09788b9d9949d22b88ea096b2574e75c6478a89a7a21967
|
| 3 |
+
size 369314554
|
checkpoint-1953/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dbfd788c0f7ad756cf3d5087d0190bba88664c044facd42f9459a8818166257
|
| 3 |
+
size 14244
|
checkpoint-1953/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c67a60a733bd92f57d37e7ce9af23cdfceaa0d212e1769ffe3373aaa7eecaa84
|
| 3 |
+
size 1064
|
checkpoint-1953/trainer_state.json
ADDED
|
@@ -0,0 +1,712 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1953,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.030721966205837174,
|
| 13 |
+
"grad_norm": 0.1512155830860138,
|
| 14 |
+
"learning_rate": 9.897593445980543e-05,
|
| 15 |
+
"loss": 1.4355,
|
| 16 |
+
"step": 20
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06144393241167435,
|
| 20 |
+
"grad_norm": 0.07312213629484177,
|
| 21 |
+
"learning_rate": 9.795186891961086e-05,
|
| 22 |
+
"loss": 0.0851,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09216589861751152,
|
| 27 |
+
"grad_norm": 0.08094536513090134,
|
| 28 |
+
"learning_rate": 9.692780337941628e-05,
|
| 29 |
+
"loss": 0.056,
|
| 30 |
+
"step": 60
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1228878648233487,
|
| 34 |
+
"grad_norm": 0.05470961704850197,
|
| 35 |
+
"learning_rate": 9.590373783922172e-05,
|
| 36 |
+
"loss": 0.0474,
|
| 37 |
+
"step": 80
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15360983102918588,
|
| 41 |
+
"grad_norm": 0.05098584294319153,
|
| 42 |
+
"learning_rate": 9.487967229902714e-05,
|
| 43 |
+
"loss": 0.0454,
|
| 44 |
+
"step": 100
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18433179723502305,
|
| 48 |
+
"grad_norm": 0.058107804507017136,
|
| 49 |
+
"learning_rate": 9.385560675883256e-05,
|
| 50 |
+
"loss": 0.0438,
|
| 51 |
+
"step": 120
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21505376344086022,
|
| 55 |
+
"grad_norm": 0.05871523171663284,
|
| 56 |
+
"learning_rate": 9.2831541218638e-05,
|
| 57 |
+
"loss": 0.0412,
|
| 58 |
+
"step": 140
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2457757296466974,
|
| 62 |
+
"grad_norm": 0.053748778998851776,
|
| 63 |
+
"learning_rate": 9.180747567844342e-05,
|
| 64 |
+
"loss": 0.041,
|
| 65 |
+
"step": 160
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2764976958525346,
|
| 69 |
+
"grad_norm": 0.04749336093664169,
|
| 70 |
+
"learning_rate": 9.078341013824884e-05,
|
| 71 |
+
"loss": 0.0394,
|
| 72 |
+
"step": 180
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.30721966205837176,
|
| 76 |
+
"grad_norm": 0.051831599324941635,
|
| 77 |
+
"learning_rate": 8.975934459805428e-05,
|
| 78 |
+
"loss": 0.0382,
|
| 79 |
+
"step": 200
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3379416282642089,
|
| 83 |
+
"grad_norm": 0.05264313519001007,
|
| 84 |
+
"learning_rate": 8.873527905785972e-05,
|
| 85 |
+
"loss": 0.038,
|
| 86 |
+
"step": 220
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3686635944700461,
|
| 90 |
+
"grad_norm": 0.048551175743341446,
|
| 91 |
+
"learning_rate": 8.771121351766514e-05,
|
| 92 |
+
"loss": 0.0371,
|
| 93 |
+
"step": 240
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39938556067588327,
|
| 97 |
+
"grad_norm": 0.05650593340396881,
|
| 98 |
+
"learning_rate": 8.668714797747056e-05,
|
| 99 |
+
"loss": 0.0361,
|
| 100 |
+
"step": 260
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.43010752688172044,
|
| 104 |
+
"grad_norm": 0.053584594279527664,
|
| 105 |
+
"learning_rate": 8.566308243727598e-05,
|
| 106 |
+
"loss": 0.0373,
|
| 107 |
+
"step": 280
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4608294930875576,
|
| 111 |
+
"grad_norm": 0.052629247307777405,
|
| 112 |
+
"learning_rate": 8.463901689708142e-05,
|
| 113 |
+
"loss": 0.0369,
|
| 114 |
+
"step": 300
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4915514592933948,
|
| 118 |
+
"grad_norm": 0.048385780304670334,
|
| 119 |
+
"learning_rate": 8.361495135688684e-05,
|
| 120 |
+
"loss": 0.0365,
|
| 121 |
+
"step": 320
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.522273425499232,
|
| 125 |
+
"grad_norm": 0.05694854259490967,
|
| 126 |
+
"learning_rate": 8.259088581669228e-05,
|
| 127 |
+
"loss": 0.0356,
|
| 128 |
+
"step": 340
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5529953917050692,
|
| 132 |
+
"grad_norm": 0.045489437878131866,
|
| 133 |
+
"learning_rate": 8.15668202764977e-05,
|
| 134 |
+
"loss": 0.0352,
|
| 135 |
+
"step": 360
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5837173579109063,
|
| 139 |
+
"grad_norm": 0.04657004028558731,
|
| 140 |
+
"learning_rate": 8.054275473630313e-05,
|
| 141 |
+
"loss": 0.034,
|
| 142 |
+
"step": 380
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6144393241167435,
|
| 146 |
+
"grad_norm": 0.04624749720096588,
|
| 147 |
+
"learning_rate": 7.951868919610856e-05,
|
| 148 |
+
"loss": 0.0339,
|
| 149 |
+
"step": 400
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6451612903225806,
|
| 153 |
+
"grad_norm": 0.05539771914482117,
|
| 154 |
+
"learning_rate": 7.849462365591398e-05,
|
| 155 |
+
"loss": 0.0349,
|
| 156 |
+
"step": 420
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6758832565284179,
|
| 160 |
+
"grad_norm": 0.05361827835440636,
|
| 161 |
+
"learning_rate": 7.74705581157194e-05,
|
| 162 |
+
"loss": 0.0342,
|
| 163 |
+
"step": 440
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.706605222734255,
|
| 167 |
+
"grad_norm": 0.04784597083926201,
|
| 168 |
+
"learning_rate": 7.644649257552484e-05,
|
| 169 |
+
"loss": 0.0338,
|
| 170 |
+
"step": 460
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7373271889400922,
|
| 174 |
+
"grad_norm": 0.04615575075149536,
|
| 175 |
+
"learning_rate": 7.542242703533027e-05,
|
| 176 |
+
"loss": 0.0332,
|
| 177 |
+
"step": 480
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7680491551459293,
|
| 181 |
+
"grad_norm": 0.0510617159307003,
|
| 182 |
+
"learning_rate": 7.43983614951357e-05,
|
| 183 |
+
"loss": 0.0334,
|
| 184 |
+
"step": 500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7987711213517665,
|
| 188 |
+
"grad_norm": 0.05362660437822342,
|
| 189 |
+
"learning_rate": 7.337429595494112e-05,
|
| 190 |
+
"loss": 0.0334,
|
| 191 |
+
"step": 520
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8294930875576036,
|
| 195 |
+
"grad_norm": 0.057389482855796814,
|
| 196 |
+
"learning_rate": 7.235023041474655e-05,
|
| 197 |
+
"loss": 0.032,
|
| 198 |
+
"step": 540
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8602150537634409,
|
| 202 |
+
"grad_norm": 0.04695713147521019,
|
| 203 |
+
"learning_rate": 7.132616487455197e-05,
|
| 204 |
+
"loss": 0.033,
|
| 205 |
+
"step": 560
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.890937019969278,
|
| 209 |
+
"grad_norm": 0.04749588668346405,
|
| 210 |
+
"learning_rate": 7.030209933435741e-05,
|
| 211 |
+
"loss": 0.0329,
|
| 212 |
+
"step": 580
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9216589861751152,
|
| 216 |
+
"grad_norm": 0.04851127415895462,
|
| 217 |
+
"learning_rate": 6.927803379416283e-05,
|
| 218 |
+
"loss": 0.0325,
|
| 219 |
+
"step": 600
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9523809523809523,
|
| 223 |
+
"grad_norm": 0.04438120499253273,
|
| 224 |
+
"learning_rate": 6.825396825396825e-05,
|
| 225 |
+
"loss": 0.033,
|
| 226 |
+
"step": 620
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9831029185867896,
|
| 230 |
+
"grad_norm": 0.040635980665683746,
|
| 231 |
+
"learning_rate": 6.722990271377369e-05,
|
| 232 |
+
"loss": 0.0321,
|
| 233 |
+
"step": 640
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0138248847926268,
|
| 237 |
+
"grad_norm": 0.06111369654536247,
|
| 238 |
+
"learning_rate": 6.620583717357911e-05,
|
| 239 |
+
"loss": 0.0316,
|
| 240 |
+
"step": 660
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.044546850998464,
|
| 244 |
+
"grad_norm": 0.04458026960492134,
|
| 245 |
+
"learning_rate": 6.518177163338453e-05,
|
| 246 |
+
"loss": 0.0294,
|
| 247 |
+
"step": 680
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.075268817204301,
|
| 251 |
+
"grad_norm": 0.049614399671554565,
|
| 252 |
+
"learning_rate": 6.415770609318996e-05,
|
| 253 |
+
"loss": 0.0292,
|
| 254 |
+
"step": 700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.1059907834101383,
|
| 258 |
+
"grad_norm": 0.0497017428278923,
|
| 259 |
+
"learning_rate": 6.31336405529954e-05,
|
| 260 |
+
"loss": 0.0296,
|
| 261 |
+
"step": 720
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.1367127496159755,
|
| 265 |
+
"grad_norm": 0.07175371795892715,
|
| 266 |
+
"learning_rate": 6.210957501280083e-05,
|
| 267 |
+
"loss": 0.03,
|
| 268 |
+
"step": 740
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.1674347158218126,
|
| 272 |
+
"grad_norm": 0.051305390894412994,
|
| 273 |
+
"learning_rate": 6.108550947260625e-05,
|
| 274 |
+
"loss": 0.0299,
|
| 275 |
+
"step": 760
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.1981566820276497,
|
| 279 |
+
"grad_norm": 0.04788351058959961,
|
| 280 |
+
"learning_rate": 6.006144393241168e-05,
|
| 281 |
+
"loss": 0.0288,
|
| 282 |
+
"step": 780
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.228878648233487,
|
| 286 |
+
"grad_norm": 0.042062848806381226,
|
| 287 |
+
"learning_rate": 5.90373783922171e-05,
|
| 288 |
+
"loss": 0.0294,
|
| 289 |
+
"step": 800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.2596006144393241,
|
| 293 |
+
"grad_norm": 0.04787632077932358,
|
| 294 |
+
"learning_rate": 5.801331285202253e-05,
|
| 295 |
+
"loss": 0.0289,
|
| 296 |
+
"step": 820
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.2903225806451613,
|
| 300 |
+
"grad_norm": 0.04673902690410614,
|
| 301 |
+
"learning_rate": 5.6989247311827965e-05,
|
| 302 |
+
"loss": 0.0295,
|
| 303 |
+
"step": 840
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.3210445468509984,
|
| 307 |
+
"grad_norm": 0.049946922808885574,
|
| 308 |
+
"learning_rate": 5.5965181771633393e-05,
|
| 309 |
+
"loss": 0.0288,
|
| 310 |
+
"step": 860
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.3517665130568357,
|
| 314 |
+
"grad_norm": 0.04578813165426254,
|
| 315 |
+
"learning_rate": 5.4941116231438816e-05,
|
| 316 |
+
"loss": 0.0288,
|
| 317 |
+
"step": 880
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.3824884792626728,
|
| 321 |
+
"grad_norm": 0.04998716711997986,
|
| 322 |
+
"learning_rate": 5.3917050691244244e-05,
|
| 323 |
+
"loss": 0.0287,
|
| 324 |
+
"step": 900
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.41321044546851,
|
| 328 |
+
"grad_norm": 0.043574895709753036,
|
| 329 |
+
"learning_rate": 5.2892985151049667e-05,
|
| 330 |
+
"loss": 0.0291,
|
| 331 |
+
"step": 920
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4439324116743473,
|
| 335 |
+
"grad_norm": 0.04888541251420975,
|
| 336 |
+
"learning_rate": 5.1868919610855095e-05,
|
| 337 |
+
"loss": 0.0286,
|
| 338 |
+
"step": 940
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.4746543778801844,
|
| 342 |
+
"grad_norm": 0.04586420953273773,
|
| 343 |
+
"learning_rate": 5.084485407066052e-05,
|
| 344 |
+
"loss": 0.0287,
|
| 345 |
+
"step": 960
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.5053763440860215,
|
| 349 |
+
"grad_norm": 0.054376959800720215,
|
| 350 |
+
"learning_rate": 4.982078853046595e-05,
|
| 351 |
+
"loss": 0.0282,
|
| 352 |
+
"step": 980
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.5360983102918588,
|
| 356 |
+
"grad_norm": 0.04396720603108406,
|
| 357 |
+
"learning_rate": 4.879672299027138e-05,
|
| 358 |
+
"loss": 0.0287,
|
| 359 |
+
"step": 1000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.5668202764976957,
|
| 363 |
+
"grad_norm": 0.045876361429691315,
|
| 364 |
+
"learning_rate": 4.7772657450076804e-05,
|
| 365 |
+
"loss": 0.0287,
|
| 366 |
+
"step": 1020
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.597542242703533,
|
| 370 |
+
"grad_norm": 0.054340336471796036,
|
| 371 |
+
"learning_rate": 4.674859190988223e-05,
|
| 372 |
+
"loss": 0.0297,
|
| 373 |
+
"step": 1040
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.6282642089093702,
|
| 377 |
+
"grad_norm": 0.046706799417734146,
|
| 378 |
+
"learning_rate": 4.572452636968766e-05,
|
| 379 |
+
"loss": 0.0287,
|
| 380 |
+
"step": 1060
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.6589861751152073,
|
| 384 |
+
"grad_norm": 0.05444665625691414,
|
| 385 |
+
"learning_rate": 4.470046082949309e-05,
|
| 386 |
+
"loss": 0.0284,
|
| 387 |
+
"step": 1080
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.6897081413210446,
|
| 391 |
+
"grad_norm": 0.04873611778020859,
|
| 392 |
+
"learning_rate": 4.367639528929851e-05,
|
| 393 |
+
"loss": 0.0285,
|
| 394 |
+
"step": 1100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.7204301075268817,
|
| 398 |
+
"grad_norm": 0.049390435218811035,
|
| 399 |
+
"learning_rate": 4.265232974910394e-05,
|
| 400 |
+
"loss": 0.0282,
|
| 401 |
+
"step": 1120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.7511520737327189,
|
| 405 |
+
"grad_norm": 0.04932021722197533,
|
| 406 |
+
"learning_rate": 4.162826420890937e-05,
|
| 407 |
+
"loss": 0.0283,
|
| 408 |
+
"step": 1140
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.7818740399385562,
|
| 412 |
+
"grad_norm": 0.0462203249335289,
|
| 413 |
+
"learning_rate": 4.06041986687148e-05,
|
| 414 |
+
"loss": 0.0291,
|
| 415 |
+
"step": 1160
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.812596006144393,
|
| 419 |
+
"grad_norm": 0.045431822538375854,
|
| 420 |
+
"learning_rate": 3.958013312852022e-05,
|
| 421 |
+
"loss": 0.0285,
|
| 422 |
+
"step": 1180
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.8433179723502304,
|
| 426 |
+
"grad_norm": 0.04209066182374954,
|
| 427 |
+
"learning_rate": 3.855606758832566e-05,
|
| 428 |
+
"loss": 0.0281,
|
| 429 |
+
"step": 1200
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.8740399385560675,
|
| 433 |
+
"grad_norm": 0.04643911495804787,
|
| 434 |
+
"learning_rate": 3.753200204813108e-05,
|
| 435 |
+
"loss": 0.0282,
|
| 436 |
+
"step": 1220
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.9047619047619047,
|
| 440 |
+
"grad_norm": 0.05297870934009552,
|
| 441 |
+
"learning_rate": 3.650793650793651e-05,
|
| 442 |
+
"loss": 0.0283,
|
| 443 |
+
"step": 1240
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.935483870967742,
|
| 447 |
+
"grad_norm": 0.045079439878463745,
|
| 448 |
+
"learning_rate": 3.548387096774194e-05,
|
| 449 |
+
"loss": 0.0286,
|
| 450 |
+
"step": 1260
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.966205837173579,
|
| 454 |
+
"grad_norm": 0.04396852105855942,
|
| 455 |
+
"learning_rate": 3.4459805427547367e-05,
|
| 456 |
+
"loss": 0.028,
|
| 457 |
+
"step": 1280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.9969278033794162,
|
| 461 |
+
"grad_norm": 0.04810136556625366,
|
| 462 |
+
"learning_rate": 3.343573988735279e-05,
|
| 463 |
+
"loss": 0.0278,
|
| 464 |
+
"step": 1300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.0276497695852536,
|
| 468 |
+
"grad_norm": 0.04735556244850159,
|
| 469 |
+
"learning_rate": 3.2411674347158224e-05,
|
| 470 |
+
"loss": 0.0252,
|
| 471 |
+
"step": 1320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.0583717357910905,
|
| 475 |
+
"grad_norm": 0.047580786049366,
|
| 476 |
+
"learning_rate": 3.1387608806963646e-05,
|
| 477 |
+
"loss": 0.0252,
|
| 478 |
+
"step": 1340
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.089093701996928,
|
| 482 |
+
"grad_norm": 0.05648692324757576,
|
| 483 |
+
"learning_rate": 3.0363543266769072e-05,
|
| 484 |
+
"loss": 0.0259,
|
| 485 |
+
"step": 1360
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.119815668202765,
|
| 489 |
+
"grad_norm": 0.05537613108754158,
|
| 490 |
+
"learning_rate": 2.9339477726574504e-05,
|
| 491 |
+
"loss": 0.0249,
|
| 492 |
+
"step": 1380
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.150537634408602,
|
| 496 |
+
"grad_norm": 0.05248798429965973,
|
| 497 |
+
"learning_rate": 2.831541218637993e-05,
|
| 498 |
+
"loss": 0.0247,
|
| 499 |
+
"step": 1400
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.1812596006144394,
|
| 503 |
+
"grad_norm": 0.05146801844239235,
|
| 504 |
+
"learning_rate": 2.7291346646185355e-05,
|
| 505 |
+
"loss": 0.0253,
|
| 506 |
+
"step": 1420
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.2119815668202767,
|
| 510 |
+
"grad_norm": 0.05279408395290375,
|
| 511 |
+
"learning_rate": 2.626728110599078e-05,
|
| 512 |
+
"loss": 0.0252,
|
| 513 |
+
"step": 1440
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.2427035330261136,
|
| 517 |
+
"grad_norm": 0.050060730427503586,
|
| 518 |
+
"learning_rate": 2.5243215565796213e-05,
|
| 519 |
+
"loss": 0.0252,
|
| 520 |
+
"step": 1460
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.273425499231951,
|
| 524 |
+
"grad_norm": 0.05538507178425789,
|
| 525 |
+
"learning_rate": 2.421915002560164e-05,
|
| 526 |
+
"loss": 0.0248,
|
| 527 |
+
"step": 1480
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.3041474654377883,
|
| 531 |
+
"grad_norm": 0.0514647401869297,
|
| 532 |
+
"learning_rate": 2.3195084485407068e-05,
|
| 533 |
+
"loss": 0.0254,
|
| 534 |
+
"step": 1500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.334869431643625,
|
| 538 |
+
"grad_norm": 0.05420660972595215,
|
| 539 |
+
"learning_rate": 2.2171018945212493e-05,
|
| 540 |
+
"loss": 0.0252,
|
| 541 |
+
"step": 1520
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.3655913978494625,
|
| 545 |
+
"grad_norm": 0.05415211245417595,
|
| 546 |
+
"learning_rate": 2.1146953405017922e-05,
|
| 547 |
+
"loss": 0.0248,
|
| 548 |
+
"step": 1540
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.3963133640552994,
|
| 552 |
+
"grad_norm": 0.054315581917762756,
|
| 553 |
+
"learning_rate": 2.012288786482335e-05,
|
| 554 |
+
"loss": 0.0247,
|
| 555 |
+
"step": 1560
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.4270353302611367,
|
| 559 |
+
"grad_norm": 0.052055474370718,
|
| 560 |
+
"learning_rate": 1.9098822324628776e-05,
|
| 561 |
+
"loss": 0.0248,
|
| 562 |
+
"step": 1580
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.457757296466974,
|
| 566 |
+
"grad_norm": 0.04970501363277435,
|
| 567 |
+
"learning_rate": 1.8074756784434205e-05,
|
| 568 |
+
"loss": 0.0249,
|
| 569 |
+
"step": 1600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.488479262672811,
|
| 573 |
+
"grad_norm": 0.05602123215794563,
|
| 574 |
+
"learning_rate": 1.7050691244239634e-05,
|
| 575 |
+
"loss": 0.0247,
|
| 576 |
+
"step": 1620
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.5192012288786483,
|
| 580 |
+
"grad_norm": 0.05873609706759453,
|
| 581 |
+
"learning_rate": 1.602662570404506e-05,
|
| 582 |
+
"loss": 0.0242,
|
| 583 |
+
"step": 1640
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.549923195084485,
|
| 587 |
+
"grad_norm": 0.06298800557851791,
|
| 588 |
+
"learning_rate": 1.5002560163850487e-05,
|
| 589 |
+
"loss": 0.025,
|
| 590 |
+
"step": 1660
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.5806451612903225,
|
| 594 |
+
"grad_norm": 0.051834046840667725,
|
| 595 |
+
"learning_rate": 1.3978494623655914e-05,
|
| 596 |
+
"loss": 0.0246,
|
| 597 |
+
"step": 1680
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.61136712749616,
|
| 601 |
+
"grad_norm": 0.05892595276236534,
|
| 602 |
+
"learning_rate": 1.2954429083461341e-05,
|
| 603 |
+
"loss": 0.0243,
|
| 604 |
+
"step": 1700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.6420890937019967,
|
| 608 |
+
"grad_norm": 0.05549076944589615,
|
| 609 |
+
"learning_rate": 1.1930363543266769e-05,
|
| 610 |
+
"loss": 0.0252,
|
| 611 |
+
"step": 1720
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.672811059907834,
|
| 615 |
+
"grad_norm": 0.05536745488643646,
|
| 616 |
+
"learning_rate": 1.0906298003072197e-05,
|
| 617 |
+
"loss": 0.0253,
|
| 618 |
+
"step": 1740
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.7035330261136714,
|
| 622 |
+
"grad_norm": 0.05979848653078079,
|
| 623 |
+
"learning_rate": 9.882232462877625e-06,
|
| 624 |
+
"loss": 0.0252,
|
| 625 |
+
"step": 1760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.7342549923195083,
|
| 629 |
+
"grad_norm": 0.04978615790605545,
|
| 630 |
+
"learning_rate": 8.858166922683052e-06,
|
| 631 |
+
"loss": 0.0247,
|
| 632 |
+
"step": 1780
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.7649769585253456,
|
| 636 |
+
"grad_norm": 0.05952267348766327,
|
| 637 |
+
"learning_rate": 7.834101382488479e-06,
|
| 638 |
+
"loss": 0.0242,
|
| 639 |
+
"step": 1800
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.795698924731183,
|
| 643 |
+
"grad_norm": 0.05571313947439194,
|
| 644 |
+
"learning_rate": 6.810035842293908e-06,
|
| 645 |
+
"loss": 0.0242,
|
| 646 |
+
"step": 1820
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.82642089093702,
|
| 650 |
+
"grad_norm": 0.060350194573402405,
|
| 651 |
+
"learning_rate": 5.785970302099334e-06,
|
| 652 |
+
"loss": 0.0247,
|
| 653 |
+
"step": 1840
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.857142857142857,
|
| 657 |
+
"grad_norm": 0.053442951291799545,
|
| 658 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 659 |
+
"loss": 0.0241,
|
| 660 |
+
"step": 1860
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.8878648233486945,
|
| 664 |
+
"grad_norm": 0.06173479184508324,
|
| 665 |
+
"learning_rate": 3.7378392217101896e-06,
|
| 666 |
+
"loss": 0.0244,
|
| 667 |
+
"step": 1880
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.9185867895545314,
|
| 671 |
+
"grad_norm": 0.05805809050798416,
|
| 672 |
+
"learning_rate": 2.7137736815156172e-06,
|
| 673 |
+
"loss": 0.0245,
|
| 674 |
+
"step": 1900
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.9493087557603688,
|
| 678 |
+
"grad_norm": 0.05551229417324066,
|
| 679 |
+
"learning_rate": 1.6897081413210446e-06,
|
| 680 |
+
"loss": 0.0244,
|
| 681 |
+
"step": 1920
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.980030721966206,
|
| 685 |
+
"grad_norm": 0.05892977863550186,
|
| 686 |
+
"learning_rate": 6.656426011264722e-07,
|
| 687 |
+
"loss": 0.0236,
|
| 688 |
+
"step": 1940
|
| 689 |
+
}
|
| 690 |
+
],
|
| 691 |
+
"logging_steps": 20,
|
| 692 |
+
"max_steps": 1953,
|
| 693 |
+
"num_input_tokens_seen": 0,
|
| 694 |
+
"num_train_epochs": 3,
|
| 695 |
+
"save_steps": 50,
|
| 696 |
+
"stateful_callbacks": {
|
| 697 |
+
"TrainerControl": {
|
| 698 |
+
"args": {
|
| 699 |
+
"should_epoch_stop": false,
|
| 700 |
+
"should_evaluate": false,
|
| 701 |
+
"should_log": false,
|
| 702 |
+
"should_save": true,
|
| 703 |
+
"should_training_stop": true
|
| 704 |
+
},
|
| 705 |
+
"attributes": {}
|
| 706 |
+
}
|
| 707 |
+
},
|
| 708 |
+
"total_flos": 6.271511642882703e+17,
|
| 709 |
+
"train_batch_size": 4,
|
| 710 |
+
"trial_name": null,
|
| 711 |
+
"trial_params": null
|
| 712 |
+
}
|
checkpoint-1953/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1479fdd1dbc57e34459b11b8b5a6fa52e44010c7da49005807d4ee5d68528000
|
| 3 |
+
size 5304
|
tokenizer_config.json
ADDED
|
File without changes
|