Training in progress, epoch 4, checkpoint
Browse files- checkpoint-253/README.md +219 -0
- checkpoint-253/adapter_config.json +28 -0
- checkpoint-253/adapter_model.safetensors +3 -0
- checkpoint-253/optimizer.pt +3 -0
- checkpoint-253/rng_state.pth +3 -0
- checkpoint-253/scheduler.pt +3 -0
- checkpoint-253/trainer_state.json +1625 -0
- checkpoint-253/training_args.bin +3 -0
checkpoint-253/README.md
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: yentinglin/Taiwan-LLM-7B-v2.0-chat
|
| 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 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 22 |
+
- **Model type:** [More Information Needed]
|
| 23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 24 |
+
- **License:** [More Information Needed]
|
| 25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 26 |
+
|
| 27 |
+
### Model Sources [optional]
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** [More Information Needed]
|
| 32 |
+
- **Paper [optional]:** [More Information Needed]
|
| 33 |
+
- **Demo [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
## Uses
|
| 36 |
+
|
| 37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 38 |
+
|
| 39 |
+
### Direct Use
|
| 40 |
+
|
| 41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 42 |
+
|
| 43 |
+
[More Information Needed]
|
| 44 |
+
|
| 45 |
+
### Downstream Use [optional]
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Out-of-Scope Use
|
| 52 |
+
|
| 53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
## Bias, Risks, and Limitations
|
| 58 |
+
|
| 59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
### Recommendations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 66 |
+
|
| 67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 68 |
+
|
| 69 |
+
## How to Get Started with the Model
|
| 70 |
+
|
| 71 |
+
Use the code below to get started with the model.
|
| 72 |
+
|
| 73 |
+
[More Information Needed]
|
| 74 |
+
|
| 75 |
+
## Training Details
|
| 76 |
+
|
| 77 |
+
### Training Data
|
| 78 |
+
|
| 79 |
+
<!-- This should link to a Data 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. -->
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
### Training Procedure
|
| 84 |
+
|
| 85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 86 |
+
|
| 87 |
+
#### Preprocessing [optional]
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
#### Training Hyperparameters
|
| 93 |
+
|
| 94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 95 |
+
|
| 96 |
+
#### Speeds, Sizes, Times [optional]
|
| 97 |
+
|
| 98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 99 |
+
|
| 100 |
+
[More Information Needed]
|
| 101 |
+
|
| 102 |
+
## Evaluation
|
| 103 |
+
|
| 104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 105 |
+
|
| 106 |
+
### Testing Data, Factors & Metrics
|
| 107 |
+
|
| 108 |
+
#### Testing Data
|
| 109 |
+
|
| 110 |
+
<!-- This should link to a Data Card if possible. -->
|
| 111 |
+
|
| 112 |
+
[More Information Needed]
|
| 113 |
+
|
| 114 |
+
#### Factors
|
| 115 |
+
|
| 116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Metrics
|
| 121 |
+
|
| 122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
### Results
|
| 127 |
+
|
| 128 |
+
[More Information Needed]
|
| 129 |
+
|
| 130 |
+
#### Summary
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
## Model Examination [optional]
|
| 135 |
+
|
| 136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
## Environmental Impact
|
| 141 |
+
|
| 142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 143 |
+
|
| 144 |
+
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).
|
| 145 |
+
|
| 146 |
+
- **Hardware Type:** [More Information Needed]
|
| 147 |
+
- **Hours used:** [More Information Needed]
|
| 148 |
+
- **Cloud Provider:** [More Information Needed]
|
| 149 |
+
- **Compute Region:** [More Information Needed]
|
| 150 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 151 |
+
|
| 152 |
+
## Technical Specifications [optional]
|
| 153 |
+
|
| 154 |
+
### Model Architecture and Objective
|
| 155 |
+
|
| 156 |
+
[More Information Needed]
|
| 157 |
+
|
| 158 |
+
### Compute Infrastructure
|
| 159 |
+
|
| 160 |
+
[More Information Needed]
|
| 161 |
+
|
| 162 |
+
#### Hardware
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
#### Software
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
## Citation [optional]
|
| 171 |
+
|
| 172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 173 |
+
|
| 174 |
+
**BibTeX:**
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
**APA:**
|
| 179 |
+
|
| 180 |
+
[More Information Needed]
|
| 181 |
+
|
| 182 |
+
## Glossary [optional]
|
| 183 |
+
|
| 184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## More Information [optional]
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
## Model Card Authors [optional]
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Model Card Contact
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
## Training procedure
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
+
- quant_method: bitsandbytes
|
| 206 |
+
- load_in_8bit: False
|
| 207 |
+
- load_in_4bit: True
|
| 208 |
+
- llm_int8_threshold: 6.0
|
| 209 |
+
- llm_int8_skip_modules: None
|
| 210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
+
- llm_int8_has_fp16_weight: False
|
| 212 |
+
- bnb_4bit_quant_type: nf4
|
| 213 |
+
- bnb_4bit_use_double_quant: True
|
| 214 |
+
- bnb_4bit_compute_dtype: float16
|
| 215 |
+
|
| 216 |
+
### Framework versions
|
| 217 |
+
|
| 218 |
+
|
| 219 |
+
- PEFT 0.6.0
|
checkpoint-253/adapter_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.05,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 4,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"gate_proj",
|
| 20 |
+
"q_proj",
|
| 21 |
+
"up_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM"
|
| 28 |
+
}
|
checkpoint-253/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d49db9926e9a4d0487128e75a82cb720844613e4624f8cd6813ebb73b5eed76
|
| 3 |
+
size 40036040
|
checkpoint-253/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:274b96e7f084fa2062568bf7d0600877ff014952a4787725a3cd5ddc7e92567f
|
| 3 |
+
size 80218053
|
checkpoint-253/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f6433f342fc64fff71ce16bde55b2406f407616f919df6b0079eafd85cadf8c
|
| 3 |
+
size 14575
|
checkpoint-253/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e7401feafb8007b675aedfcdf60e6ca3fdef600d02190676ec65c25cbbb9404
|
| 3 |
+
size 627
|
checkpoint-253/trainer_state.json
ADDED
|
@@ -0,0 +1,1625 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.018145161290322,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 253,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 4.2125,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_loss": 4.052073955535889,
|
| 20 |
+
"eval_runtime": 61.8325,
|
| 21 |
+
"eval_samples_per_second": 4.043,
|
| 22 |
+
"eval_steps_per_second": 4.043,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 4e-05,
|
| 28 |
+
"loss": 4.2885,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.05,
|
| 33 |
+
"learning_rate": 6e-05,
|
| 34 |
+
"loss": 4.2535,
|
| 35 |
+
"step": 3
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.06,
|
| 39 |
+
"learning_rate": 8e-05,
|
| 40 |
+
"loss": 4.0238,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.08,
|
| 45 |
+
"learning_rate": 0.0001,
|
| 46 |
+
"loss": 3.8658,
|
| 47 |
+
"step": 5
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.1,
|
| 51 |
+
"learning_rate": 0.00012,
|
| 52 |
+
"loss": 3.991,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.11,
|
| 57 |
+
"learning_rate": 0.00014,
|
| 58 |
+
"loss": 3.8686,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13,
|
| 63 |
+
"learning_rate": 0.00016,
|
| 64 |
+
"loss": 3.8117,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15,
|
| 69 |
+
"learning_rate": 0.00018,
|
| 70 |
+
"loss": 4.0165,
|
| 71 |
+
"step": 9
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.16,
|
| 75 |
+
"learning_rate": 0.0002,
|
| 76 |
+
"loss": 3.7689,
|
| 77 |
+
"step": 10
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.18,
|
| 81 |
+
"learning_rate": 0.0001999979107245606,
|
| 82 |
+
"loss": 3.6961,
|
| 83 |
+
"step": 11
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.19,
|
| 87 |
+
"learning_rate": 0.00019999164298554375,
|
| 88 |
+
"loss": 3.5999,
|
| 89 |
+
"step": 12
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21,
|
| 93 |
+
"learning_rate": 0.00019998119704485014,
|
| 94 |
+
"loss": 3.5358,
|
| 95 |
+
"step": 13
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.23,
|
| 99 |
+
"learning_rate": 0.00019996657333896877,
|
| 100 |
+
"loss": 3.51,
|
| 101 |
+
"step": 14
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.24,
|
| 105 |
+
"learning_rate": 0.00019994777247895855,
|
| 106 |
+
"loss": 3.3729,
|
| 107 |
+
"step": 15
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26,
|
| 111 |
+
"learning_rate": 0.00019992479525042303,
|
| 112 |
+
"loss": 3.3557,
|
| 113 |
+
"step": 16
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.27,
|
| 117 |
+
"learning_rate": 0.00019989764261347736,
|
| 118 |
+
"loss": 3.3868,
|
| 119 |
+
"step": 17
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.29,
|
| 123 |
+
"learning_rate": 0.00019986631570270832,
|
| 124 |
+
"loss": 3.4494,
|
| 125 |
+
"step": 18
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.31,
|
| 129 |
+
"learning_rate": 0.00019983081582712685,
|
| 130 |
+
"loss": 3.4571,
|
| 131 |
+
"step": 19
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.32,
|
| 135 |
+
"learning_rate": 0.00019979114447011323,
|
| 136 |
+
"loss": 3.254,
|
| 137 |
+
"step": 20
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.34,
|
| 141 |
+
"learning_rate": 0.00019974730328935534,
|
| 142 |
+
"loss": 3.2094,
|
| 143 |
+
"step": 21
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.35,
|
| 147 |
+
"learning_rate": 0.0001996992941167792,
|
| 148 |
+
"loss": 3.2843,
|
| 149 |
+
"step": 22
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.37,
|
| 153 |
+
"learning_rate": 0.00019964711895847258,
|
| 154 |
+
"loss": 3.2776,
|
| 155 |
+
"step": 23
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.39,
|
| 159 |
+
"learning_rate": 0.00019959077999460095,
|
| 160 |
+
"loss": 2.9951,
|
| 161 |
+
"step": 24
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.4,
|
| 165 |
+
"learning_rate": 0.00019953027957931658,
|
| 166 |
+
"loss": 3.1523,
|
| 167 |
+
"step": 25
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.4,
|
| 171 |
+
"eval_loss": 2.9463467597961426,
|
| 172 |
+
"eval_runtime": 62.0633,
|
| 173 |
+
"eval_samples_per_second": 4.028,
|
| 174 |
+
"eval_steps_per_second": 4.028,
|
| 175 |
+
"step": 25
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.42,
|
| 179 |
+
"learning_rate": 0.00019946562024066014,
|
| 180 |
+
"loss": 3.0537,
|
| 181 |
+
"step": 26
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.44,
|
| 185 |
+
"learning_rate": 0.00019939680468045499,
|
| 186 |
+
"loss": 2.8775,
|
| 187 |
+
"step": 27
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.45,
|
| 191 |
+
"learning_rate": 0.00019932383577419432,
|
| 192 |
+
"loss": 3.0155,
|
| 193 |
+
"step": 28
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.47,
|
| 197 |
+
"learning_rate": 0.00019924671657092096,
|
| 198 |
+
"loss": 2.8512,
|
| 199 |
+
"step": 29
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.48,
|
| 203 |
+
"learning_rate": 0.00019916545029310012,
|
| 204 |
+
"loss": 2.7208,
|
| 205 |
+
"step": 30
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5,
|
| 209 |
+
"learning_rate": 0.00019908004033648453,
|
| 210 |
+
"loss": 2.7177,
|
| 211 |
+
"step": 31
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.52,
|
| 215 |
+
"learning_rate": 0.00019899049026997272,
|
| 216 |
+
"loss": 2.536,
|
| 217 |
+
"step": 32
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.53,
|
| 221 |
+
"learning_rate": 0.00019889680383545973,
|
| 222 |
+
"loss": 2.6654,
|
| 223 |
+
"step": 33
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.55,
|
| 227 |
+
"learning_rate": 0.00019879898494768093,
|
| 228 |
+
"loss": 2.5692,
|
| 229 |
+
"step": 34
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.56,
|
| 233 |
+
"learning_rate": 0.00019869703769404828,
|
| 234 |
+
"loss": 2.4448,
|
| 235 |
+
"step": 35
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.58,
|
| 239 |
+
"learning_rate": 0.00019859096633447965,
|
| 240 |
+
"loss": 2.4296,
|
| 241 |
+
"step": 36
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.6,
|
| 245 |
+
"learning_rate": 0.00019848077530122083,
|
| 246 |
+
"loss": 2.3887,
|
| 247 |
+
"step": 37
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.61,
|
| 251 |
+
"learning_rate": 0.0001983664691986601,
|
| 252 |
+
"loss": 2.3225,
|
| 253 |
+
"step": 38
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.63,
|
| 257 |
+
"learning_rate": 0.00019824805280313623,
|
| 258 |
+
"loss": 2.1755,
|
| 259 |
+
"step": 39
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.65,
|
| 263 |
+
"learning_rate": 0.00019812553106273847,
|
| 264 |
+
"loss": 2.1252,
|
| 265 |
+
"step": 40
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.66,
|
| 269 |
+
"learning_rate": 0.00019799890909710013,
|
| 270 |
+
"loss": 2.1585,
|
| 271 |
+
"step": 41
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.68,
|
| 275 |
+
"learning_rate": 0.00019786819219718443,
|
| 276 |
+
"loss": 2.2467,
|
| 277 |
+
"step": 42
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.69,
|
| 281 |
+
"learning_rate": 0.0001977333858250636,
|
| 282 |
+
"loss": 2.0564,
|
| 283 |
+
"step": 43
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.71,
|
| 287 |
+
"learning_rate": 0.00019759449561369038,
|
| 288 |
+
"loss": 2.0713,
|
| 289 |
+
"step": 44
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.73,
|
| 293 |
+
"learning_rate": 0.00019745152736666302,
|
| 294 |
+
"loss": 1.9998,
|
| 295 |
+
"step": 45
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.74,
|
| 299 |
+
"learning_rate": 0.00019730448705798239,
|
| 300 |
+
"loss": 2.1497,
|
| 301 |
+
"step": 46
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.76,
|
| 305 |
+
"learning_rate": 0.00019715338083180269,
|
| 306 |
+
"loss": 1.9467,
|
| 307 |
+
"step": 47
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.77,
|
| 311 |
+
"learning_rate": 0.00019699821500217434,
|
| 312 |
+
"loss": 1.9195,
|
| 313 |
+
"step": 48
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.79,
|
| 317 |
+
"learning_rate": 0.0001968389960527806,
|
| 318 |
+
"loss": 1.7969,
|
| 319 |
+
"step": 49
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.81,
|
| 323 |
+
"learning_rate": 0.0001966757306366662,
|
| 324 |
+
"loss": 1.9685,
|
| 325 |
+
"step": 50
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.81,
|
| 329 |
+
"eval_loss": 1.8644403219223022,
|
| 330 |
+
"eval_runtime": 62.0885,
|
| 331 |
+
"eval_samples_per_second": 4.027,
|
| 332 |
+
"eval_steps_per_second": 4.027,
|
| 333 |
+
"step": 50
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.82,
|
| 337 |
+
"learning_rate": 0.00019650842557595967,
|
| 338 |
+
"loss": 1.8609,
|
| 339 |
+
"step": 51
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.84,
|
| 343 |
+
"learning_rate": 0.00019633708786158806,
|
| 344 |
+
"loss": 1.8528,
|
| 345 |
+
"step": 52
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.85,
|
| 349 |
+
"learning_rate": 0.00019616172465298492,
|
| 350 |
+
"loss": 1.7482,
|
| 351 |
+
"step": 53
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.87,
|
| 355 |
+
"learning_rate": 0.00019598234327779118,
|
| 356 |
+
"loss": 1.5841,
|
| 357 |
+
"step": 54
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.89,
|
| 361 |
+
"learning_rate": 0.0001957989512315489,
|
| 362 |
+
"loss": 1.8643,
|
| 363 |
+
"step": 55
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9,
|
| 367 |
+
"learning_rate": 0.00019561155617738797,
|
| 368 |
+
"loss": 1.7103,
|
| 369 |
+
"step": 56
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.92,
|
| 373 |
+
"learning_rate": 0.00019542016594570615,
|
| 374 |
+
"loss": 1.886,
|
| 375 |
+
"step": 57
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.94,
|
| 379 |
+
"learning_rate": 0.00019522478853384155,
|
| 380 |
+
"loss": 1.7265,
|
| 381 |
+
"step": 58
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.95,
|
| 385 |
+
"learning_rate": 0.00019502543210573881,
|
| 386 |
+
"loss": 1.7261,
|
| 387 |
+
"step": 59
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.97,
|
| 391 |
+
"learning_rate": 0.00019482210499160765,
|
| 392 |
+
"loss": 1.6018,
|
| 393 |
+
"step": 60
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.98,
|
| 397 |
+
"learning_rate": 0.00019461481568757506,
|
| 398 |
+
"loss": 1.7412,
|
| 399 |
+
"step": 61
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.0,
|
| 403 |
+
"learning_rate": 0.00019440357285533,
|
| 404 |
+
"loss": 1.5618,
|
| 405 |
+
"step": 62
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.02,
|
| 409 |
+
"learning_rate": 0.00019418838532176173,
|
| 410 |
+
"loss": 1.6051,
|
| 411 |
+
"step": 63
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.01,
|
| 415 |
+
"learning_rate": 0.00019396926207859084,
|
| 416 |
+
"loss": 1.5225,
|
| 417 |
+
"step": 64
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.03,
|
| 421 |
+
"learning_rate": 0.0001937462122819935,
|
| 422 |
+
"loss": 1.6547,
|
| 423 |
+
"step": 65
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.04,
|
| 427 |
+
"learning_rate": 0.000193519245252219,
|
| 428 |
+
"loss": 1.6184,
|
| 429 |
+
"step": 66
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.06,
|
| 433 |
+
"learning_rate": 0.0001932883704732001,
|
| 434 |
+
"loss": 1.4581,
|
| 435 |
+
"step": 67
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.07,
|
| 439 |
+
"learning_rate": 0.00019305359759215685,
|
| 440 |
+
"loss": 1.567,
|
| 441 |
+
"step": 68
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.09,
|
| 445 |
+
"learning_rate": 0.00019281493641919368,
|
| 446 |
+
"loss": 1.645,
|
| 447 |
+
"step": 69
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.11,
|
| 451 |
+
"learning_rate": 0.00019257239692688907,
|
| 452 |
+
"loss": 1.5237,
|
| 453 |
+
"step": 70
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.12,
|
| 457 |
+
"learning_rate": 0.00019232598924987903,
|
| 458 |
+
"loss": 1.4956,
|
| 459 |
+
"step": 71
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.14,
|
| 463 |
+
"learning_rate": 0.00019207572368443385,
|
| 464 |
+
"loss": 1.5493,
|
| 465 |
+
"step": 72
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.16,
|
| 469 |
+
"learning_rate": 0.00019182161068802741,
|
| 470 |
+
"loss": 1.495,
|
| 471 |
+
"step": 73
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.17,
|
| 475 |
+
"learning_rate": 0.0001915636608789006,
|
| 476 |
+
"loss": 1.3961,
|
| 477 |
+
"step": 74
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.19,
|
| 481 |
+
"learning_rate": 0.00019130188503561741,
|
| 482 |
+
"loss": 1.5639,
|
| 483 |
+
"step": 75
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.19,
|
| 487 |
+
"eval_loss": 1.5244245529174805,
|
| 488 |
+
"eval_runtime": 62.0668,
|
| 489 |
+
"eval_samples_per_second": 4.028,
|
| 490 |
+
"eval_steps_per_second": 4.028,
|
| 491 |
+
"step": 75
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.2,
|
| 495 |
+
"learning_rate": 0.0001910362940966147,
|
| 496 |
+
"loss": 1.4871,
|
| 497 |
+
"step": 76
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.22,
|
| 501 |
+
"learning_rate": 0.00019076689915974488,
|
| 502 |
+
"loss": 1.6211,
|
| 503 |
+
"step": 77
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.24,
|
| 507 |
+
"learning_rate": 0.00019049371148181253,
|
| 508 |
+
"loss": 1.4287,
|
| 509 |
+
"step": 78
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.25,
|
| 513 |
+
"learning_rate": 0.0001902167424781038,
|
| 514 |
+
"loss": 1.4661,
|
| 515 |
+
"step": 79
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.27,
|
| 519 |
+
"learning_rate": 0.00018993600372190932,
|
| 520 |
+
"loss": 1.5775,
|
| 521 |
+
"step": 80
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.28,
|
| 525 |
+
"learning_rate": 0.00018965150694404094,
|
| 526 |
+
"loss": 1.4292,
|
| 527 |
+
"step": 81
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.3,
|
| 531 |
+
"learning_rate": 0.00018936326403234125,
|
| 532 |
+
"loss": 1.4739,
|
| 533 |
+
"step": 82
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.32,
|
| 537 |
+
"learning_rate": 0.00018907128703118695,
|
| 538 |
+
"loss": 1.5025,
|
| 539 |
+
"step": 83
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.33,
|
| 543 |
+
"learning_rate": 0.00018877558814098561,
|
| 544 |
+
"loss": 1.423,
|
| 545 |
+
"step": 84
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.35,
|
| 549 |
+
"learning_rate": 0.00018847617971766577,
|
| 550 |
+
"loss": 1.4102,
|
| 551 |
+
"step": 85
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.36,
|
| 555 |
+
"learning_rate": 0.0001881730742721608,
|
| 556 |
+
"loss": 1.4348,
|
| 557 |
+
"step": 86
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.38,
|
| 561 |
+
"learning_rate": 0.00018786628446988593,
|
| 562 |
+
"loss": 1.3953,
|
| 563 |
+
"step": 87
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.4,
|
| 567 |
+
"learning_rate": 0.0001875558231302091,
|
| 568 |
+
"loss": 1.3912,
|
| 569 |
+
"step": 88
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.41,
|
| 573 |
+
"learning_rate": 0.00018724170322591537,
|
| 574 |
+
"loss": 1.4086,
|
| 575 |
+
"step": 89
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.43,
|
| 579 |
+
"learning_rate": 0.00018692393788266479,
|
| 580 |
+
"loss": 1.3259,
|
| 581 |
+
"step": 90
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.45,
|
| 585 |
+
"learning_rate": 0.00018660254037844388,
|
| 586 |
+
"loss": 1.5038,
|
| 587 |
+
"step": 91
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.46,
|
| 591 |
+
"learning_rate": 0.00018627752414301086,
|
| 592 |
+
"loss": 1.3597,
|
| 593 |
+
"step": 92
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.48,
|
| 597 |
+
"learning_rate": 0.00018594890275733453,
|
| 598 |
+
"loss": 1.466,
|
| 599 |
+
"step": 93
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.49,
|
| 603 |
+
"learning_rate": 0.00018561668995302667,
|
| 604 |
+
"loss": 1.3287,
|
| 605 |
+
"step": 94
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.51,
|
| 609 |
+
"learning_rate": 0.0001852808996117683,
|
| 610 |
+
"loss": 1.3319,
|
| 611 |
+
"step": 95
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.53,
|
| 615 |
+
"learning_rate": 0.00018494154576472976,
|
| 616 |
+
"loss": 1.4434,
|
| 617 |
+
"step": 96
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.54,
|
| 621 |
+
"learning_rate": 0.0001845986425919841,
|
| 622 |
+
"loss": 1.4025,
|
| 623 |
+
"step": 97
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.56,
|
| 627 |
+
"learning_rate": 0.00018425220442191495,
|
| 628 |
+
"loss": 1.3213,
|
| 629 |
+
"step": 98
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.57,
|
| 633 |
+
"learning_rate": 0.00018390224573061747,
|
| 634 |
+
"loss": 1.2632,
|
| 635 |
+
"step": 99
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.59,
|
| 639 |
+
"learning_rate": 0.00018354878114129367,
|
| 640 |
+
"loss": 1.2843,
|
| 641 |
+
"step": 100
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.59,
|
| 645 |
+
"eval_loss": 1.4124521017074585,
|
| 646 |
+
"eval_runtime": 62.1529,
|
| 647 |
+
"eval_samples_per_second": 4.022,
|
| 648 |
+
"eval_steps_per_second": 4.022,
|
| 649 |
+
"step": 100
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.61,
|
| 653 |
+
"learning_rate": 0.00018319182542364117,
|
| 654 |
+
"loss": 1.4325,
|
| 655 |
+
"step": 101
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.62,
|
| 659 |
+
"learning_rate": 0.00018283139349323634,
|
| 660 |
+
"loss": 1.3073,
|
| 661 |
+
"step": 102
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.64,
|
| 665 |
+
"learning_rate": 0.0001824675004109107,
|
| 666 |
+
"loss": 1.4306,
|
| 667 |
+
"step": 103
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.66,
|
| 671 |
+
"learning_rate": 0.00018210016138212187,
|
| 672 |
+
"loss": 1.4146,
|
| 673 |
+
"step": 104
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.67,
|
| 677 |
+
"learning_rate": 0.00018172939175631808,
|
| 678 |
+
"loss": 1.4248,
|
| 679 |
+
"step": 105
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.69,
|
| 683 |
+
"learning_rate": 0.00018135520702629675,
|
| 684 |
+
"loss": 1.1905,
|
| 685 |
+
"step": 106
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.7,
|
| 689 |
+
"learning_rate": 0.00018097762282755727,
|
| 690 |
+
"loss": 1.2818,
|
| 691 |
+
"step": 107
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.72,
|
| 695 |
+
"learning_rate": 0.00018059665493764743,
|
| 696 |
+
"loss": 1.3104,
|
| 697 |
+
"step": 108
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.74,
|
| 701 |
+
"learning_rate": 0.0001802123192755044,
|
| 702 |
+
"loss": 1.3141,
|
| 703 |
+
"step": 109
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.75,
|
| 707 |
+
"learning_rate": 0.0001798246319007893,
|
| 708 |
+
"loss": 1.2494,
|
| 709 |
+
"step": 110
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.77,
|
| 713 |
+
"learning_rate": 0.0001794336090132164,
|
| 714 |
+
"loss": 1.2817,
|
| 715 |
+
"step": 111
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.78,
|
| 719 |
+
"learning_rate": 0.00017903926695187595,
|
| 720 |
+
"loss": 1.2675,
|
| 721 |
+
"step": 112
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.8,
|
| 725 |
+
"learning_rate": 0.00017864162219455163,
|
| 726 |
+
"loss": 1.3368,
|
| 727 |
+
"step": 113
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.82,
|
| 731 |
+
"learning_rate": 0.00017824069135703198,
|
| 732 |
+
"loss": 1.3054,
|
| 733 |
+
"step": 114
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.83,
|
| 737 |
+
"learning_rate": 0.00017783649119241602,
|
| 738 |
+
"loss": 1.4334,
|
| 739 |
+
"step": 115
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.85,
|
| 743 |
+
"learning_rate": 0.00017742903859041325,
|
| 744 |
+
"loss": 1.3058,
|
| 745 |
+
"step": 116
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.86,
|
| 749 |
+
"learning_rate": 0.00017701835057663798,
|
| 750 |
+
"loss": 1.2882,
|
| 751 |
+
"step": 117
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.88,
|
| 755 |
+
"learning_rate": 0.0001766044443118978,
|
| 756 |
+
"loss": 1.1971,
|
| 757 |
+
"step": 118
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.9,
|
| 761 |
+
"learning_rate": 0.00017618733709147662,
|
| 762 |
+
"loss": 1.2832,
|
| 763 |
+
"step": 119
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.91,
|
| 767 |
+
"learning_rate": 0.0001757670463444118,
|
| 768 |
+
"loss": 1.2372,
|
| 769 |
+
"step": 120
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.93,
|
| 773 |
+
"learning_rate": 0.00017534358963276607,
|
| 774 |
+
"loss": 1.182,
|
| 775 |
+
"step": 121
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.95,
|
| 779 |
+
"learning_rate": 0.00017491698465089362,
|
| 780 |
+
"loss": 1.2228,
|
| 781 |
+
"step": 122
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.96,
|
| 785 |
+
"learning_rate": 0.00017448724922470058,
|
| 786 |
+
"loss": 1.3541,
|
| 787 |
+
"step": 123
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.98,
|
| 791 |
+
"learning_rate": 0.00017405440131090048,
|
| 792 |
+
"loss": 1.2751,
|
| 793 |
+
"step": 124
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.99,
|
| 797 |
+
"learning_rate": 0.00017361845899626355,
|
| 798 |
+
"loss": 1.1626,
|
| 799 |
+
"step": 125
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 1.99,
|
| 803 |
+
"eval_loss": 1.351290225982666,
|
| 804 |
+
"eval_runtime": 62.1247,
|
| 805 |
+
"eval_samples_per_second": 4.024,
|
| 806 |
+
"eval_steps_per_second": 4.024,
|
| 807 |
+
"step": 125
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.01,
|
| 811 |
+
"learning_rate": 0.00017317944049686124,
|
| 812 |
+
"loss": 1.2837,
|
| 813 |
+
"step": 126
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.01,
|
| 817 |
+
"learning_rate": 0.00017273736415730488,
|
| 818 |
+
"loss": 1.1712,
|
| 819 |
+
"step": 127
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.02,
|
| 823 |
+
"learning_rate": 0.00017229224844997928,
|
| 824 |
+
"loss": 1.1996,
|
| 825 |
+
"step": 128
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.04,
|
| 829 |
+
"learning_rate": 0.00017184411197427077,
|
| 830 |
+
"loss": 1.1007,
|
| 831 |
+
"step": 129
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.05,
|
| 835 |
+
"learning_rate": 0.00017139297345578994,
|
| 836 |
+
"loss": 1.1426,
|
| 837 |
+
"step": 130
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.07,
|
| 841 |
+
"learning_rate": 0.0001709388517455893,
|
| 842 |
+
"loss": 1.2041,
|
| 843 |
+
"step": 131
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.09,
|
| 847 |
+
"learning_rate": 0.00017048176581937563,
|
| 848 |
+
"loss": 1.1214,
|
| 849 |
+
"step": 132
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.1,
|
| 853 |
+
"learning_rate": 0.00017048176581937563,
|
| 854 |
+
"loss": 1.1013,
|
| 855 |
+
"step": 133
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.12,
|
| 859 |
+
"learning_rate": 0.00017002173477671686,
|
| 860 |
+
"loss": 1.0937,
|
| 861 |
+
"step": 134
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.14,
|
| 865 |
+
"learning_rate": 0.0001695587778402442,
|
| 866 |
+
"loss": 1.132,
|
| 867 |
+
"step": 135
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.15,
|
| 871 |
+
"learning_rate": 0.0001690929143548488,
|
| 872 |
+
"loss": 1.1336,
|
| 873 |
+
"step": 136
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.17,
|
| 877 |
+
"learning_rate": 0.0001686241637868734,
|
| 878 |
+
"loss": 1.0649,
|
| 879 |
+
"step": 137
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.18,
|
| 883 |
+
"learning_rate": 0.00016815254572329896,
|
| 884 |
+
"loss": 1.126,
|
| 885 |
+
"step": 138
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.2,
|
| 889 |
+
"learning_rate": 0.00016767807987092621,
|
| 890 |
+
"loss": 1.1903,
|
| 891 |
+
"step": 139
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.22,
|
| 895 |
+
"learning_rate": 0.00016720078605555224,
|
| 896 |
+
"loss": 1.2231,
|
| 897 |
+
"step": 140
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.23,
|
| 901 |
+
"learning_rate": 0.00016672068422114196,
|
| 902 |
+
"loss": 1.2027,
|
| 903 |
+
"step": 141
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.25,
|
| 907 |
+
"learning_rate": 0.0001662377944289948,
|
| 908 |
+
"loss": 1.1121,
|
| 909 |
+
"step": 142
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.26,
|
| 913 |
+
"learning_rate": 0.0001657521368569064,
|
| 914 |
+
"loss": 1.1226,
|
| 915 |
+
"step": 143
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.28,
|
| 919 |
+
"learning_rate": 0.00016526373179832546,
|
| 920 |
+
"loss": 1.2607,
|
| 921 |
+
"step": 144
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.3,
|
| 925 |
+
"learning_rate": 0.00016477259966150588,
|
| 926 |
+
"loss": 1.0129,
|
| 927 |
+
"step": 145
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.31,
|
| 931 |
+
"learning_rate": 0.00016427876096865394,
|
| 932 |
+
"loss": 1.1083,
|
| 933 |
+
"step": 146
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.33,
|
| 937 |
+
"learning_rate": 0.0001637822363550706,
|
| 938 |
+
"loss": 1.1899,
|
| 939 |
+
"step": 147
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.34,
|
| 943 |
+
"learning_rate": 0.00016328304656828952,
|
| 944 |
+
"loss": 1.1603,
|
| 945 |
+
"step": 148
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.36,
|
| 949 |
+
"learning_rate": 0.00016278121246720987,
|
| 950 |
+
"loss": 1.1224,
|
| 951 |
+
"step": 149
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.38,
|
| 955 |
+
"learning_rate": 0.00016227675502122492,
|
| 956 |
+
"loss": 1.2645,
|
| 957 |
+
"step": 150
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.38,
|
| 961 |
+
"eval_loss": 1.3386605978012085,
|
| 962 |
+
"eval_runtime": 62.2057,
|
| 963 |
+
"eval_samples_per_second": 4.019,
|
| 964 |
+
"eval_steps_per_second": 4.019,
|
| 965 |
+
"step": 150
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 2.39,
|
| 969 |
+
"learning_rate": 0.00016176969530934572,
|
| 970 |
+
"loss": 1.1165,
|
| 971 |
+
"step": 151
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.41,
|
| 975 |
+
"learning_rate": 0.0001612600545193203,
|
| 976 |
+
"loss": 1.1705,
|
| 977 |
+
"step": 152
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.43,
|
| 981 |
+
"learning_rate": 0.00016074785394674837,
|
| 982 |
+
"loss": 1.1285,
|
| 983 |
+
"step": 153
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.44,
|
| 987 |
+
"learning_rate": 0.0001602331149941915,
|
| 988 |
+
"loss": 1.2047,
|
| 989 |
+
"step": 154
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.46,
|
| 993 |
+
"learning_rate": 0.00015971585917027862,
|
| 994 |
+
"loss": 1.0933,
|
| 995 |
+
"step": 155
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 2.47,
|
| 999 |
+
"learning_rate": 0.0001591961080888076,
|
| 1000 |
+
"loss": 1.1415,
|
| 1001 |
+
"step": 156
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 2.49,
|
| 1005 |
+
"learning_rate": 0.0001586738834678418,
|
| 1006 |
+
"loss": 1.1956,
|
| 1007 |
+
"step": 157
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.51,
|
| 1011 |
+
"learning_rate": 0.00015814920712880267,
|
| 1012 |
+
"loss": 1.264,
|
| 1013 |
+
"step": 158
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.52,
|
| 1017 |
+
"learning_rate": 0.00015762210099555803,
|
| 1018 |
+
"loss": 1.1909,
|
| 1019 |
+
"step": 159
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.54,
|
| 1023 |
+
"learning_rate": 0.00015709258709350582,
|
| 1024 |
+
"loss": 1.0594,
|
| 1025 |
+
"step": 160
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.55,
|
| 1029 |
+
"learning_rate": 0.00015656068754865387,
|
| 1030 |
+
"loss": 1.1423,
|
| 1031 |
+
"step": 161
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.57,
|
| 1035 |
+
"learning_rate": 0.00015602642458669528,
|
| 1036 |
+
"loss": 1.1687,
|
| 1037 |
+
"step": 162
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.59,
|
| 1041 |
+
"learning_rate": 0.0001554898205320797,
|
| 1042 |
+
"loss": 1.0989,
|
| 1043 |
+
"step": 163
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.6,
|
| 1047 |
+
"learning_rate": 0.0001549508978070806,
|
| 1048 |
+
"loss": 1.2288,
|
| 1049 |
+
"step": 164
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.62,
|
| 1053 |
+
"learning_rate": 0.00015440967893085828,
|
| 1054 |
+
"loss": 1.2075,
|
| 1055 |
+
"step": 165
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.64,
|
| 1059 |
+
"learning_rate": 0.0001538661865185188,
|
| 1060 |
+
"loss": 1.256,
|
| 1061 |
+
"step": 166
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.65,
|
| 1065 |
+
"learning_rate": 0.00015332044328016914,
|
| 1066 |
+
"loss": 1.1595,
|
| 1067 |
+
"step": 167
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.67,
|
| 1071 |
+
"learning_rate": 0.0001527724720199682,
|
| 1072 |
+
"loss": 1.1199,
|
| 1073 |
+
"step": 168
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.68,
|
| 1077 |
+
"learning_rate": 0.00015222229563517385,
|
| 1078 |
+
"loss": 1.1336,
|
| 1079 |
+
"step": 169
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.7,
|
| 1083 |
+
"learning_rate": 0.00015166993711518631,
|
| 1084 |
+
"loss": 1.1568,
|
| 1085 |
+
"step": 170
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 2.72,
|
| 1089 |
+
"learning_rate": 0.00015111541954058734,
|
| 1090 |
+
"loss": 1.0688,
|
| 1091 |
+
"step": 171
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.73,
|
| 1095 |
+
"learning_rate": 0.0001505587660821759,
|
| 1096 |
+
"loss": 1.1648,
|
| 1097 |
+
"step": 172
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.75,
|
| 1101 |
+
"learning_rate": 0.00015000000000000001,
|
| 1102 |
+
"loss": 1.0783,
|
| 1103 |
+
"step": 173
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.76,
|
| 1107 |
+
"learning_rate": 0.00014943914464238468,
|
| 1108 |
+
"loss": 1.1639,
|
| 1109 |
+
"step": 174
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.78,
|
| 1113 |
+
"learning_rate": 0.00014887622344495643,
|
| 1114 |
+
"loss": 1.3175,
|
| 1115 |
+
"step": 175
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.78,
|
| 1119 |
+
"eval_loss": 1.3120231628417969,
|
| 1120 |
+
"eval_runtime": 62.1097,
|
| 1121 |
+
"eval_samples_per_second": 4.025,
|
| 1122 |
+
"eval_steps_per_second": 4.025,
|
| 1123 |
+
"step": 175
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.8,
|
| 1127 |
+
"learning_rate": 0.00014831125992966385,
|
| 1128 |
+
"loss": 1.059,
|
| 1129 |
+
"step": 176
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.81,
|
| 1133 |
+
"learning_rate": 0.0001477442777037949,
|
| 1134 |
+
"loss": 1.0881,
|
| 1135 |
+
"step": 177
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.83,
|
| 1139 |
+
"learning_rate": 0.00014717530045899038,
|
| 1140 |
+
"loss": 1.1179,
|
| 1141 |
+
"step": 178
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.84,
|
| 1145 |
+
"learning_rate": 0.0001466043519702539,
|
| 1146 |
+
"loss": 1.1869,
|
| 1147 |
+
"step": 179
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.86,
|
| 1151 |
+
"learning_rate": 0.0001460314560949586,
|
| 1152 |
+
"loss": 1.142,
|
| 1153 |
+
"step": 180
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.88,
|
| 1157 |
+
"learning_rate": 0.00014545663677185006,
|
| 1158 |
+
"loss": 1.0172,
|
| 1159 |
+
"step": 181
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.89,
|
| 1163 |
+
"learning_rate": 0.00014487991802004623,
|
| 1164 |
+
"loss": 1.0003,
|
| 1165 |
+
"step": 182
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.91,
|
| 1169 |
+
"learning_rate": 0.00014430132393803352,
|
| 1170 |
+
"loss": 1.2018,
|
| 1171 |
+
"step": 183
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.93,
|
| 1175 |
+
"learning_rate": 0.0001437208787026601,
|
| 1176 |
+
"loss": 1.0541,
|
| 1177 |
+
"step": 184
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.94,
|
| 1181 |
+
"learning_rate": 0.00014313860656812536,
|
| 1182 |
+
"loss": 1.1134,
|
| 1183 |
+
"step": 185
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 2.96,
|
| 1187 |
+
"learning_rate": 0.00014255453186496673,
|
| 1188 |
+
"loss": 1.2113,
|
| 1189 |
+
"step": 186
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.97,
|
| 1193 |
+
"learning_rate": 0.0001419686789990429,
|
| 1194 |
+
"loss": 1.1616,
|
| 1195 |
+
"step": 187
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.99,
|
| 1199 |
+
"learning_rate": 0.00014138107245051392,
|
| 1200 |
+
"loss": 1.1475,
|
| 1201 |
+
"step": 188
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 3.01,
|
| 1205 |
+
"learning_rate": 0.00014079173677281837,
|
| 1206 |
+
"loss": 1.1168,
|
| 1207 |
+
"step": 189
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 3.0,
|
| 1211 |
+
"learning_rate": 0.0001402006965916474,
|
| 1212 |
+
"loss": 0.9838,
|
| 1213 |
+
"step": 190
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.02,
|
| 1217 |
+
"learning_rate": 0.0001396079766039157,
|
| 1218 |
+
"loss": 0.8454,
|
| 1219 |
+
"step": 191
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 3.03,
|
| 1223 |
+
"learning_rate": 0.0001390136015767295,
|
| 1224 |
+
"loss": 1.1056,
|
| 1225 |
+
"step": 192
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 3.05,
|
| 1229 |
+
"learning_rate": 0.00013841759634635178,
|
| 1230 |
+
"loss": 1.0452,
|
| 1231 |
+
"step": 193
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.07,
|
| 1235 |
+
"learning_rate": 0.00013781998581716427,
|
| 1236 |
+
"loss": 0.9212,
|
| 1237 |
+
"step": 194
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 3.08,
|
| 1241 |
+
"learning_rate": 0.00013722079496062702,
|
| 1242 |
+
"loss": 1.0476,
|
| 1243 |
+
"step": 195
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 3.1,
|
| 1247 |
+
"learning_rate": 0.0001366200488142348,
|
| 1248 |
+
"loss": 0.9267,
|
| 1249 |
+
"step": 196
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 3.11,
|
| 1253 |
+
"learning_rate": 0.00013601777248047105,
|
| 1254 |
+
"loss": 1.1301,
|
| 1255 |
+
"step": 197
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.13,
|
| 1259 |
+
"learning_rate": 0.00013541399112575878,
|
| 1260 |
+
"loss": 0.9814,
|
| 1261 |
+
"step": 198
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 3.15,
|
| 1265 |
+
"learning_rate": 0.00013480872997940905,
|
| 1266 |
+
"loss": 1.022,
|
| 1267 |
+
"step": 199
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 3.16,
|
| 1271 |
+
"learning_rate": 0.00013420201433256689,
|
| 1272 |
+
"loss": 0.979,
|
| 1273 |
+
"step": 200
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 3.16,
|
| 1277 |
+
"eval_loss": 1.3181864023208618,
|
| 1278 |
+
"eval_runtime": 62.2184,
|
| 1279 |
+
"eval_samples_per_second": 4.018,
|
| 1280 |
+
"eval_steps_per_second": 4.018,
|
| 1281 |
+
"step": 200
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 3.18,
|
| 1285 |
+
"learning_rate": 0.00013359386953715421,
|
| 1286 |
+
"loss": 0.908,
|
| 1287 |
+
"step": 201
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.2,
|
| 1291 |
+
"learning_rate": 0.00013298432100481079,
|
| 1292 |
+
"loss": 0.9209,
|
| 1293 |
+
"step": 202
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.21,
|
| 1297 |
+
"learning_rate": 0.00013237339420583212,
|
| 1298 |
+
"loss": 1.0095,
|
| 1299 |
+
"step": 203
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.23,
|
| 1303 |
+
"learning_rate": 0.00013176111466810532,
|
| 1304 |
+
"loss": 1.0415,
|
| 1305 |
+
"step": 204
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.24,
|
| 1309 |
+
"learning_rate": 0.00013114750797604247,
|
| 1310 |
+
"loss": 1.0286,
|
| 1311 |
+
"step": 205
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 3.26,
|
| 1315 |
+
"learning_rate": 0.00013053259976951133,
|
| 1316 |
+
"loss": 0.9969,
|
| 1317 |
+
"step": 206
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 3.28,
|
| 1321 |
+
"learning_rate": 0.00012991641574276418,
|
| 1322 |
+
"loss": 1.0106,
|
| 1323 |
+
"step": 207
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 3.29,
|
| 1327 |
+
"learning_rate": 0.00012929898164336408,
|
| 1328 |
+
"loss": 1.0094,
|
| 1329 |
+
"step": 208
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.31,
|
| 1333 |
+
"learning_rate": 0.00012868032327110904,
|
| 1334 |
+
"loss": 1.0417,
|
| 1335 |
+
"step": 209
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.32,
|
| 1339 |
+
"learning_rate": 0.0001280604664769539,
|
| 1340 |
+
"loss": 0.9764,
|
| 1341 |
+
"step": 210
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 3.34,
|
| 1345 |
+
"learning_rate": 0.00012743943716193016,
|
| 1346 |
+
"loss": 1.0592,
|
| 1347 |
+
"step": 211
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.36,
|
| 1351 |
+
"learning_rate": 0.00012681726127606376,
|
| 1352 |
+
"loss": 1.0541,
|
| 1353 |
+
"step": 212
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 3.37,
|
| 1357 |
+
"learning_rate": 0.0001261939648172906,
|
| 1358 |
+
"loss": 0.9032,
|
| 1359 |
+
"step": 213
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.39,
|
| 1363 |
+
"learning_rate": 0.0001255695738303704,
|
| 1364 |
+
"loss": 1.0044,
|
| 1365 |
+
"step": 214
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 3.41,
|
| 1369 |
+
"learning_rate": 0.00012494411440579814,
|
| 1370 |
+
"loss": 1.0148,
|
| 1371 |
+
"step": 215
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 3.42,
|
| 1375 |
+
"learning_rate": 0.00012431761267871417,
|
| 1376 |
+
"loss": 0.881,
|
| 1377 |
+
"step": 216
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 3.44,
|
| 1381 |
+
"learning_rate": 0.00012369009482781192,
|
| 1382 |
+
"loss": 0.926,
|
| 1383 |
+
"step": 217
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 3.45,
|
| 1387 |
+
"learning_rate": 0.00012306158707424403,
|
| 1388 |
+
"loss": 0.9837,
|
| 1389 |
+
"step": 218
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.47,
|
| 1393 |
+
"learning_rate": 0.00012243211568052677,
|
| 1394 |
+
"loss": 1.0499,
|
| 1395 |
+
"step": 219
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.49,
|
| 1399 |
+
"learning_rate": 0.0001218017069494426,
|
| 1400 |
+
"loss": 0.9517,
|
| 1401 |
+
"step": 220
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 3.5,
|
| 1405 |
+
"learning_rate": 0.0001211703872229411,
|
| 1406 |
+
"loss": 0.9389,
|
| 1407 |
+
"step": 221
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.52,
|
| 1411 |
+
"learning_rate": 0.0001205381828810382,
|
| 1412 |
+
"loss": 1.0278,
|
| 1413 |
+
"step": 222
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 3.53,
|
| 1417 |
+
"learning_rate": 0.00011990512034071406,
|
| 1418 |
+
"loss": 0.9211,
|
| 1419 |
+
"step": 223
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.55,
|
| 1423 |
+
"learning_rate": 0.00011927122605480898,
|
| 1424 |
+
"loss": 1.0141,
|
| 1425 |
+
"step": 224
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 3.57,
|
| 1429 |
+
"learning_rate": 0.00011863652651091823,
|
| 1430 |
+
"loss": 1.0649,
|
| 1431 |
+
"step": 225
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.57,
|
| 1435 |
+
"eval_loss": 1.314542531967163,
|
| 1436 |
+
"eval_runtime": 62.1983,
|
| 1437 |
+
"eval_samples_per_second": 4.019,
|
| 1438 |
+
"eval_steps_per_second": 4.019,
|
| 1439 |
+
"step": 225
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 3.58,
|
| 1443 |
+
"learning_rate": 0.00011800104823028515,
|
| 1444 |
+
"loss": 0.9642,
|
| 1445 |
+
"step": 226
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.6,
|
| 1449 |
+
"learning_rate": 0.00011736481776669306,
|
| 1450 |
+
"loss": 1.0534,
|
| 1451 |
+
"step": 227
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 3.61,
|
| 1455 |
+
"learning_rate": 0.00011672786170535552,
|
| 1456 |
+
"loss": 1.0212,
|
| 1457 |
+
"step": 228
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 3.63,
|
| 1461 |
+
"learning_rate": 0.00011609020666180575,
|
| 1462 |
+
"loss": 0.9801,
|
| 1463 |
+
"step": 229
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 3.65,
|
| 1467 |
+
"learning_rate": 0.00011545187928078406,
|
| 1468 |
+
"loss": 0.9185,
|
| 1469 |
+
"step": 230
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 3.66,
|
| 1473 |
+
"learning_rate": 0.0001148129062351249,
|
| 1474 |
+
"loss": 0.9292,
|
| 1475 |
+
"step": 231
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 3.68,
|
| 1479 |
+
"learning_rate": 0.00011417331422464205,
|
| 1480 |
+
"loss": 0.9453,
|
| 1481 |
+
"step": 232
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 3.7,
|
| 1485 |
+
"learning_rate": 0.00011353312997501313,
|
| 1486 |
+
"loss": 0.9784,
|
| 1487 |
+
"step": 233
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.71,
|
| 1491 |
+
"learning_rate": 0.00011289238023666266,
|
| 1492 |
+
"loss": 1.0346,
|
| 1493 |
+
"step": 234
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 3.73,
|
| 1497 |
+
"learning_rate": 0.00011225109178364455,
|
| 1498 |
+
"loss": 0.9485,
|
| 1499 |
+
"step": 235
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 3.74,
|
| 1503 |
+
"learning_rate": 0.00011160929141252303,
|
| 1504 |
+
"loss": 0.9783,
|
| 1505 |
+
"step": 236
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.76,
|
| 1509 |
+
"learning_rate": 0.00011096700594125318,
|
| 1510 |
+
"loss": 0.8651,
|
| 1511 |
+
"step": 237
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 3.78,
|
| 1515 |
+
"learning_rate": 0.00011032426220806018,
|
| 1516 |
+
"loss": 0.982,
|
| 1517 |
+
"step": 238
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.79,
|
| 1521 |
+
"learning_rate": 0.00010968108707031792,
|
| 1522 |
+
"loss": 1.0657,
|
| 1523 |
+
"step": 239
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 3.81,
|
| 1527 |
+
"learning_rate": 0.00010903750740342682,
|
| 1528 |
+
"loss": 1.0281,
|
| 1529 |
+
"step": 240
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.82,
|
| 1533 |
+
"learning_rate": 0.00010839355009969068,
|
| 1534 |
+
"loss": 0.9484,
|
| 1535 |
+
"step": 241
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.84,
|
| 1539 |
+
"learning_rate": 0.0001077492420671931,
|
| 1540 |
+
"loss": 0.9936,
|
| 1541 |
+
"step": 242
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 3.86,
|
| 1545 |
+
"learning_rate": 0.00010710461022867302,
|
| 1546 |
+
"loss": 0.9556,
|
| 1547 |
+
"step": 243
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 3.87,
|
| 1551 |
+
"learning_rate": 0.0001064596815203998,
|
| 1552 |
+
"loss": 0.92,
|
| 1553 |
+
"step": 244
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 3.89,
|
| 1557 |
+
"learning_rate": 0.00010581448289104758,
|
| 1558 |
+
"loss": 0.954,
|
| 1559 |
+
"step": 245
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 3.91,
|
| 1563 |
+
"learning_rate": 0.00010516904130056946,
|
| 1564 |
+
"loss": 0.9427,
|
| 1565 |
+
"step": 246
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 3.92,
|
| 1569 |
+
"learning_rate": 0.00010452338371907064,
|
| 1570 |
+
"loss": 0.9644,
|
| 1571 |
+
"step": 247
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.94,
|
| 1575 |
+
"learning_rate": 0.0001038775371256817,
|
| 1576 |
+
"loss": 0.9458,
|
| 1577 |
+
"step": 248
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 3.95,
|
| 1581 |
+
"learning_rate": 0.00010323152850743107,
|
| 1582 |
+
"loss": 1.003,
|
| 1583 |
+
"step": 249
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 3.97,
|
| 1587 |
+
"learning_rate": 0.00010258538485811765,
|
| 1588 |
+
"loss": 1.0749,
|
| 1589 |
+
"step": 250
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 3.97,
|
| 1593 |
+
"eval_loss": 1.3046478033065796,
|
| 1594 |
+
"eval_runtime": 62.1024,
|
| 1595 |
+
"eval_samples_per_second": 4.026,
|
| 1596 |
+
"eval_steps_per_second": 4.026,
|
| 1597 |
+
"step": 250
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 3.99,
|
| 1601 |
+
"learning_rate": 0.00010193913317718244,
|
| 1602 |
+
"loss": 0.961,
|
| 1603 |
+
"step": 251
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 4.0,
|
| 1607 |
+
"learning_rate": 0.00010129280046858086,
|
| 1608 |
+
"loss": 0.9708,
|
| 1609 |
+
"step": 252
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 4.02,
|
| 1613 |
+
"learning_rate": 0.00010064641373965393,
|
| 1614 |
+
"loss": 0.8755,
|
| 1615 |
+
"step": 253
|
| 1616 |
+
}
|
| 1617 |
+
],
|
| 1618 |
+
"logging_steps": 1,
|
| 1619 |
+
"max_steps": 496,
|
| 1620 |
+
"num_train_epochs": 8,
|
| 1621 |
+
"save_steps": 500,
|
| 1622 |
+
"total_flos": 1.6474185518599373e+17,
|
| 1623 |
+
"trial_name": null,
|
| 1624 |
+
"trial_params": null
|
| 1625 |
+
}
|
checkpoint-253/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd619dab9182cb5c3d41449df0f56b3c988747f0ca62d01d956c1090a75990f
|
| 3 |
+
size 4603
|