Uploaded checkpoint-2500
Browse files- README.md +202 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1811 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: deepseek-ai/deepseek-coder-1.3b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.8.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 64,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 32,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
+
"down_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"q_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_rslora": false
|
| 32 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c75e352e85a2a0244d0c5b96b8d89eb93a63954476fe3e68d7e0f0f7741b411
|
| 3 |
+
size 119975656
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde7b955a7d88f53db302662547d205aa8225e08b9c6651a9e3a8868bbb2ec40
|
| 3 |
+
size 240145026
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:763d4f397fbd8e2128612f32f5c273b211bf68ec4372f02c7c91ca944e405a2f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:498562333c8d92eb0c350d42d2b96f8962ee063ac9a040f6cdd010c509c5d855
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1811 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.019110437482595444,
|
| 3 |
+
"best_model_checkpoint": "runs/deepseek_lora_20240422-151242/checkpoint-2500",
|
| 4 |
+
"epoch": 0.7832693663350826,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 1.4764970541000366,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.5176,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 2.0680618286132812,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.5115,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 2.892202138900757,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.4821,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 1.8446696996688843,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.4669,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 1.351251244544983,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.5485,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 1.4435632228851318,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.3646,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"grad_norm": 2.500685691833496,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.5509,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 4.027316093444824,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.4173,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03,
|
| 69 |
+
"grad_norm": 1.5012431144714355,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.4232,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03,
|
| 76 |
+
"grad_norm": 4.025063991546631,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.3952,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03,
|
| 83 |
+
"grad_norm": 1.2457600831985474,
|
| 84 |
+
"learning_rate": 4.4e-06,
|
| 85 |
+
"loss": 1.1888,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"grad_norm": 1.2635124921798706,
|
| 91 |
+
"learning_rate": 4.800000000000001e-06,
|
| 92 |
+
"loss": 1.2259,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"grad_norm": 1.6183345317840576,
|
| 98 |
+
"learning_rate": 5.2e-06,
|
| 99 |
+
"loss": 1.0052,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.04,
|
| 104 |
+
"grad_norm": 2.38128924369812,
|
| 105 |
+
"learning_rate": 5.600000000000001e-06,
|
| 106 |
+
"loss": 0.9928,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05,
|
| 111 |
+
"grad_norm": 1.641148328781128,
|
| 112 |
+
"learning_rate": 6e-06,
|
| 113 |
+
"loss": 0.9287,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05,
|
| 118 |
+
"grad_norm": 1.0428839921951294,
|
| 119 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 120 |
+
"loss": 0.7218,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.05,
|
| 125 |
+
"grad_norm": 1.0025560855865479,
|
| 126 |
+
"learning_rate": 6.800000000000001e-06,
|
| 127 |
+
"loss": 0.6115,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06,
|
| 132 |
+
"grad_norm": 0.962586522102356,
|
| 133 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 134 |
+
"loss": 0.5337,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"grad_norm": 0.46322694420814514,
|
| 140 |
+
"learning_rate": 7.600000000000001e-06,
|
| 141 |
+
"loss": 0.3379,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06,
|
| 146 |
+
"grad_norm": 3.5135998725891113,
|
| 147 |
+
"learning_rate": 8.000000000000001e-06,
|
| 148 |
+
"loss": 0.3204,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07,
|
| 153 |
+
"grad_norm": 0.4679415225982666,
|
| 154 |
+
"learning_rate": 8.400000000000001e-06,
|
| 155 |
+
"loss": 0.2534,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.07,
|
| 160 |
+
"grad_norm": 0.6532612442970276,
|
| 161 |
+
"learning_rate": 8.8e-06,
|
| 162 |
+
"loss": 0.1868,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07,
|
| 167 |
+
"grad_norm": 0.841340184211731,
|
| 168 |
+
"learning_rate": 9.200000000000002e-06,
|
| 169 |
+
"loss": 0.2609,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08,
|
| 174 |
+
"grad_norm": 0.7561472058296204,
|
| 175 |
+
"learning_rate": 9.600000000000001e-06,
|
| 176 |
+
"loss": 0.3831,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"grad_norm": 0.38061589002609253,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 0.3377,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08,
|
| 188 |
+
"grad_norm": 0.24261775612831116,
|
| 189 |
+
"learning_rate": 1.04e-05,
|
| 190 |
+
"loss": 0.1452,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.08,
|
| 195 |
+
"grad_norm": 2.345815896987915,
|
| 196 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 197 |
+
"loss": 0.0759,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.09,
|
| 202 |
+
"grad_norm": 0.30060628056526184,
|
| 203 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 204 |
+
"loss": 0.233,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.09,
|
| 209 |
+
"grad_norm": 0.45316824316978455,
|
| 210 |
+
"learning_rate": 1.16e-05,
|
| 211 |
+
"loss": 0.1512,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.09,
|
| 216 |
+
"grad_norm": 0.31342798471450806,
|
| 217 |
+
"learning_rate": 1.2e-05,
|
| 218 |
+
"loss": 0.1612,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"grad_norm": 3.0591862201690674,
|
| 224 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 225 |
+
"loss": 0.1128,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1,
|
| 230 |
+
"grad_norm": 0.04360930994153023,
|
| 231 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 232 |
+
"loss": 0.1209,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1,
|
| 237 |
+
"grad_norm": 0.2543979585170746,
|
| 238 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 239 |
+
"loss": 0.139,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11,
|
| 244 |
+
"grad_norm": 5.55256462097168,
|
| 245 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 246 |
+
"loss": 0.1386,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11,
|
| 251 |
+
"grad_norm": 0.032540880143642426,
|
| 252 |
+
"learning_rate": 1.4e-05,
|
| 253 |
+
"loss": 0.0659,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.11,
|
| 258 |
+
"grad_norm": 0.020825587213039398,
|
| 259 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 260 |
+
"loss": 0.0491,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"grad_norm": 5.304826736450195,
|
| 266 |
+
"learning_rate": 1.48e-05,
|
| 267 |
+
"loss": 0.1335,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12,
|
| 272 |
+
"grad_norm": 0.03812132403254509,
|
| 273 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 274 |
+
"loss": 0.0341,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.12,
|
| 279 |
+
"grad_norm": 0.0986132025718689,
|
| 280 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 281 |
+
"loss": 0.1627,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.13,
|
| 286 |
+
"grad_norm": 0.4882945716381073,
|
| 287 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 288 |
+
"loss": 0.0757,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.13,
|
| 293 |
+
"grad_norm": 0.015025519765913486,
|
| 294 |
+
"learning_rate": 1.64e-05,
|
| 295 |
+
"loss": 0.0658,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.13,
|
| 300 |
+
"grad_norm": 0.16647090017795563,
|
| 301 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 302 |
+
"loss": 0.0375,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.13,
|
| 307 |
+
"grad_norm": 0.016350600868463516,
|
| 308 |
+
"learning_rate": 1.72e-05,
|
| 309 |
+
"loss": 0.1766,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.14,
|
| 314 |
+
"grad_norm": 0.011344443075358868,
|
| 315 |
+
"learning_rate": 1.76e-05,
|
| 316 |
+
"loss": 0.0802,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.14,
|
| 321 |
+
"grad_norm": 0.05872802808880806,
|
| 322 |
+
"learning_rate": 1.8e-05,
|
| 323 |
+
"loss": 0.0866,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.14,
|
| 328 |
+
"grad_norm": 2.6746442317962646,
|
| 329 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 330 |
+
"loss": 0.0869,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15,
|
| 335 |
+
"grad_norm": 0.01068535540252924,
|
| 336 |
+
"learning_rate": 1.88e-05,
|
| 337 |
+
"loss": 0.2154,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.15,
|
| 342 |
+
"grad_norm": 0.020563703030347824,
|
| 343 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 344 |
+
"loss": 0.101,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.15,
|
| 349 |
+
"grad_norm": 0.17447501420974731,
|
| 350 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 351 |
+
"loss": 0.1116,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16,
|
| 356 |
+
"grad_norm": 3.7621819972991943,
|
| 357 |
+
"learning_rate": 2e-05,
|
| 358 |
+
"loss": 0.1465,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.16,
|
| 363 |
+
"eval_loss": 0.05017045885324478,
|
| 364 |
+
"eval_runtime": 61.9228,
|
| 365 |
+
"eval_samples_per_second": 16.149,
|
| 366 |
+
"eval_steps_per_second": 16.149,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.16,
|
| 371 |
+
"grad_norm": 0.015244358219206333,
|
| 372 |
+
"learning_rate": 1.9955555555555557e-05,
|
| 373 |
+
"loss": 0.0218,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.16,
|
| 378 |
+
"grad_norm": 0.20013077557086945,
|
| 379 |
+
"learning_rate": 1.9911111111111112e-05,
|
| 380 |
+
"loss": 0.0845,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.17,
|
| 385 |
+
"grad_norm": 0.007578707300126553,
|
| 386 |
+
"learning_rate": 1.9866666666666667e-05,
|
| 387 |
+
"loss": 0.1364,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.17,
|
| 392 |
+
"grad_norm": 1.6152952909469604,
|
| 393 |
+
"learning_rate": 1.9822222222222226e-05,
|
| 394 |
+
"loss": 0.1135,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.17,
|
| 399 |
+
"grad_norm": 2.0188419818878174,
|
| 400 |
+
"learning_rate": 1.977777777777778e-05,
|
| 401 |
+
"loss": 0.1452,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.18,
|
| 406 |
+
"grad_norm": 0.007765072397887707,
|
| 407 |
+
"learning_rate": 1.9733333333333336e-05,
|
| 408 |
+
"loss": 0.1082,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.18,
|
| 413 |
+
"grad_norm": 0.11964543163776398,
|
| 414 |
+
"learning_rate": 1.968888888888889e-05,
|
| 415 |
+
"loss": 0.0912,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.18,
|
| 420 |
+
"grad_norm": 4.242813587188721,
|
| 421 |
+
"learning_rate": 1.9644444444444447e-05,
|
| 422 |
+
"loss": 0.1243,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.18,
|
| 427 |
+
"grad_norm": 0.00892120786011219,
|
| 428 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 429 |
+
"loss": 0.1229,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.19,
|
| 434 |
+
"grad_norm": 0.008041107095777988,
|
| 435 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 436 |
+
"loss": 0.1782,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.19,
|
| 441 |
+
"grad_norm": 0.013454565778374672,
|
| 442 |
+
"learning_rate": 1.9511111111111113e-05,
|
| 443 |
+
"loss": 0.0647,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.19,
|
| 448 |
+
"grad_norm": 0.15643712878227234,
|
| 449 |
+
"learning_rate": 1.9466666666666668e-05,
|
| 450 |
+
"loss": 0.0449,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2,
|
| 455 |
+
"grad_norm": 0.01665414497256279,
|
| 456 |
+
"learning_rate": 1.9422222222222223e-05,
|
| 457 |
+
"loss": 0.0636,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2,
|
| 462 |
+
"grad_norm": 0.01023570355027914,
|
| 463 |
+
"learning_rate": 1.9377777777777778e-05,
|
| 464 |
+
"loss": 0.0566,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.2,
|
| 469 |
+
"grad_norm": 0.00858321599662304,
|
| 470 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 471 |
+
"loss": 0.2039,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.21,
|
| 476 |
+
"grad_norm": 4.273760795593262,
|
| 477 |
+
"learning_rate": 1.928888888888889e-05,
|
| 478 |
+
"loss": 0.0662,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.21,
|
| 483 |
+
"grad_norm": 0.022378291934728622,
|
| 484 |
+
"learning_rate": 1.9244444444444444e-05,
|
| 485 |
+
"loss": 0.1163,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.21,
|
| 490 |
+
"grad_norm": 0.08007720112800598,
|
| 491 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 492 |
+
"loss": 0.0781,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.22,
|
| 497 |
+
"grad_norm": 0.018208255991339684,
|
| 498 |
+
"learning_rate": 1.9155555555555558e-05,
|
| 499 |
+
"loss": 0.099,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.22,
|
| 504 |
+
"grad_norm": 0.07240291684865952,
|
| 505 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 506 |
+
"loss": 0.0522,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.22,
|
| 511 |
+
"grad_norm": 1.5902518033981323,
|
| 512 |
+
"learning_rate": 1.9066666666666668e-05,
|
| 513 |
+
"loss": 0.0421,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.23,
|
| 518 |
+
"grad_norm": 0.01304863765835762,
|
| 519 |
+
"learning_rate": 1.9022222222222223e-05,
|
| 520 |
+
"loss": 0.0968,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.23,
|
| 525 |
+
"grad_norm": 0.013874703086912632,
|
| 526 |
+
"learning_rate": 1.897777777777778e-05,
|
| 527 |
+
"loss": 0.016,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.23,
|
| 532 |
+
"grad_norm": 0.01731191948056221,
|
| 533 |
+
"learning_rate": 1.8933333333333334e-05,
|
| 534 |
+
"loss": 0.0936,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.23,
|
| 539 |
+
"grad_norm": 3.513253688812256,
|
| 540 |
+
"learning_rate": 1.888888888888889e-05,
|
| 541 |
+
"loss": 0.1283,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.24,
|
| 546 |
+
"grad_norm": 0.9819907546043396,
|
| 547 |
+
"learning_rate": 1.8844444444444444e-05,
|
| 548 |
+
"loss": 0.1182,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.24,
|
| 553 |
+
"grad_norm": 4.303761005401611,
|
| 554 |
+
"learning_rate": 1.88e-05,
|
| 555 |
+
"loss": 0.0491,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.24,
|
| 560 |
+
"grad_norm": 5.017575740814209,
|
| 561 |
+
"learning_rate": 1.8755555555555558e-05,
|
| 562 |
+
"loss": 0.115,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.25,
|
| 567 |
+
"grad_norm": 0.07593460381031036,
|
| 568 |
+
"learning_rate": 1.8711111111111113e-05,
|
| 569 |
+
"loss": 0.0237,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.25,
|
| 574 |
+
"grad_norm": 3.1718034744262695,
|
| 575 |
+
"learning_rate": 1.866666666666667e-05,
|
| 576 |
+
"loss": 0.1243,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.25,
|
| 581 |
+
"grad_norm": 0.009034764021635056,
|
| 582 |
+
"learning_rate": 1.8622222222222224e-05,
|
| 583 |
+
"loss": 0.0435,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.26,
|
| 588 |
+
"grad_norm": 0.008039540611207485,
|
| 589 |
+
"learning_rate": 1.857777777777778e-05,
|
| 590 |
+
"loss": 0.0797,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.26,
|
| 595 |
+
"grad_norm": 0.030577246099710464,
|
| 596 |
+
"learning_rate": 1.8533333333333334e-05,
|
| 597 |
+
"loss": 0.0902,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.26,
|
| 602 |
+
"grad_norm": 0.01614721678197384,
|
| 603 |
+
"learning_rate": 1.848888888888889e-05,
|
| 604 |
+
"loss": 0.0443,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.27,
|
| 609 |
+
"grad_norm": 0.00745397200807929,
|
| 610 |
+
"learning_rate": 1.8444444444444448e-05,
|
| 611 |
+
"loss": 0.013,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.27,
|
| 616 |
+
"grad_norm": 0.0033397756051272154,
|
| 617 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 618 |
+
"loss": 0.0177,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.27,
|
| 623 |
+
"grad_norm": 0.005004946142435074,
|
| 624 |
+
"learning_rate": 1.835555555555556e-05,
|
| 625 |
+
"loss": 0.0414,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.28,
|
| 630 |
+
"grad_norm": 0.005703146569430828,
|
| 631 |
+
"learning_rate": 1.8311111111111114e-05,
|
| 632 |
+
"loss": 0.1875,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.28,
|
| 637 |
+
"grad_norm": 0.011084661819040775,
|
| 638 |
+
"learning_rate": 1.826666666666667e-05,
|
| 639 |
+
"loss": 0.0093,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.28,
|
| 644 |
+
"grad_norm": 2.5405566692352295,
|
| 645 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 646 |
+
"loss": 0.074,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.29,
|
| 651 |
+
"grad_norm": 0.003973611164838076,
|
| 652 |
+
"learning_rate": 1.817777777777778e-05,
|
| 653 |
+
"loss": 0.0506,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.29,
|
| 658 |
+
"grad_norm": 0.04966599866747856,
|
| 659 |
+
"learning_rate": 1.8133333333333335e-05,
|
| 660 |
+
"loss": 0.0544,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.29,
|
| 665 |
+
"grad_norm": 0.01420037355273962,
|
| 666 |
+
"learning_rate": 1.808888888888889e-05,
|
| 667 |
+
"loss": 0.0153,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.29,
|
| 672 |
+
"grad_norm": 3.305298328399658,
|
| 673 |
+
"learning_rate": 1.8044444444444445e-05,
|
| 674 |
+
"loss": 0.0359,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3,
|
| 679 |
+
"grad_norm": 2.4599621295928955,
|
| 680 |
+
"learning_rate": 1.8e-05,
|
| 681 |
+
"loss": 0.0808,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.3,
|
| 686 |
+
"grad_norm": 2.250840187072754,
|
| 687 |
+
"learning_rate": 1.7955555555555556e-05,
|
| 688 |
+
"loss": 0.1756,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3,
|
| 693 |
+
"grad_norm": 2.541337251663208,
|
| 694 |
+
"learning_rate": 1.791111111111111e-05,
|
| 695 |
+
"loss": 0.0827,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.31,
|
| 700 |
+
"grad_norm": 0.04627770185470581,
|
| 701 |
+
"learning_rate": 1.7866666666666666e-05,
|
| 702 |
+
"loss": 0.0777,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.31,
|
| 707 |
+
"grad_norm": 0.06008163094520569,
|
| 708 |
+
"learning_rate": 1.782222222222222e-05,
|
| 709 |
+
"loss": 0.0921,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.31,
|
| 714 |
+
"grad_norm": 0.03849005699157715,
|
| 715 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 716 |
+
"loss": 0.0555,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.31,
|
| 721 |
+
"eval_loss": 0.028874782845377922,
|
| 722 |
+
"eval_runtime": 61.928,
|
| 723 |
+
"eval_samples_per_second": 16.148,
|
| 724 |
+
"eval_steps_per_second": 16.148,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.32,
|
| 729 |
+
"grad_norm": 0.006071585696190596,
|
| 730 |
+
"learning_rate": 1.7733333333333335e-05,
|
| 731 |
+
"loss": 0.0399,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.32,
|
| 736 |
+
"grad_norm": 0.012464660219848156,
|
| 737 |
+
"learning_rate": 1.768888888888889e-05,
|
| 738 |
+
"loss": 0.075,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.32,
|
| 743 |
+
"grad_norm": 0.0500749833881855,
|
| 744 |
+
"learning_rate": 1.7644444444444446e-05,
|
| 745 |
+
"loss": 0.1375,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.33,
|
| 750 |
+
"grad_norm": 1.1470282077789307,
|
| 751 |
+
"learning_rate": 1.76e-05,
|
| 752 |
+
"loss": 0.0725,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.33,
|
| 757 |
+
"grad_norm": 4.040950775146484,
|
| 758 |
+
"learning_rate": 1.7555555555555556e-05,
|
| 759 |
+
"loss": 0.0757,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.33,
|
| 764 |
+
"grad_norm": 0.010639629326760769,
|
| 765 |
+
"learning_rate": 1.751111111111111e-05,
|
| 766 |
+
"loss": 0.0495,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.34,
|
| 771 |
+
"grad_norm": 0.009533255361020565,
|
| 772 |
+
"learning_rate": 1.7466666666666667e-05,
|
| 773 |
+
"loss": 0.0125,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.34,
|
| 778 |
+
"grad_norm": 2.4316189289093018,
|
| 779 |
+
"learning_rate": 1.7422222222222222e-05,
|
| 780 |
+
"loss": 0.089,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.34,
|
| 785 |
+
"grad_norm": 0.18850259482860565,
|
| 786 |
+
"learning_rate": 1.737777777777778e-05,
|
| 787 |
+
"loss": 0.0359,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.34,
|
| 792 |
+
"grad_norm": 0.012972812168300152,
|
| 793 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 794 |
+
"loss": 0.0618,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.35,
|
| 799 |
+
"grad_norm": 1.8784104585647583,
|
| 800 |
+
"learning_rate": 1.728888888888889e-05,
|
| 801 |
+
"loss": 0.106,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.35,
|
| 806 |
+
"grad_norm": 0.02918626181781292,
|
| 807 |
+
"learning_rate": 1.7244444444444446e-05,
|
| 808 |
+
"loss": 0.0367,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.35,
|
| 813 |
+
"grad_norm": 5.1463236808776855,
|
| 814 |
+
"learning_rate": 1.72e-05,
|
| 815 |
+
"loss": 0.0784,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.36,
|
| 820 |
+
"grad_norm": 2.754035234451294,
|
| 821 |
+
"learning_rate": 1.7155555555555557e-05,
|
| 822 |
+
"loss": 0.08,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.36,
|
| 827 |
+
"grad_norm": 0.014391366392374039,
|
| 828 |
+
"learning_rate": 1.7111111111111112e-05,
|
| 829 |
+
"loss": 0.1047,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.36,
|
| 834 |
+
"grad_norm": 0.016152633354067802,
|
| 835 |
+
"learning_rate": 1.706666666666667e-05,
|
| 836 |
+
"loss": 0.0453,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.37,
|
| 841 |
+
"grad_norm": 0.020005827769637108,
|
| 842 |
+
"learning_rate": 1.7022222222222226e-05,
|
| 843 |
+
"loss": 0.0388,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.37,
|
| 848 |
+
"grad_norm": 0.004559040535241365,
|
| 849 |
+
"learning_rate": 1.697777777777778e-05,
|
| 850 |
+
"loss": 0.0306,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.37,
|
| 855 |
+
"grad_norm": 0.5455616116523743,
|
| 856 |
+
"learning_rate": 1.6933333333333336e-05,
|
| 857 |
+
"loss": 0.0595,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.38,
|
| 862 |
+
"grad_norm": 0.00697706313803792,
|
| 863 |
+
"learning_rate": 1.688888888888889e-05,
|
| 864 |
+
"loss": 0.1236,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.38,
|
| 869 |
+
"grad_norm": 1.926461935043335,
|
| 870 |
+
"learning_rate": 1.6844444444444447e-05,
|
| 871 |
+
"loss": 0.0155,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.38,
|
| 876 |
+
"grad_norm": 2.4559099674224854,
|
| 877 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 878 |
+
"loss": 0.0083,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.39,
|
| 883 |
+
"grad_norm": 0.033357810229063034,
|
| 884 |
+
"learning_rate": 1.6755555555555557e-05,
|
| 885 |
+
"loss": 0.0337,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.39,
|
| 890 |
+
"grad_norm": 0.008271641097962856,
|
| 891 |
+
"learning_rate": 1.6711111111111112e-05,
|
| 892 |
+
"loss": 0.0618,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.39,
|
| 897 |
+
"grad_norm": 0.003830987960100174,
|
| 898 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 899 |
+
"loss": 0.0097,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.39,
|
| 904 |
+
"grad_norm": 0.021310480311512947,
|
| 905 |
+
"learning_rate": 1.6622222222222223e-05,
|
| 906 |
+
"loss": 0.0717,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.4,
|
| 911 |
+
"grad_norm": 2.166944980621338,
|
| 912 |
+
"learning_rate": 1.6577777777777778e-05,
|
| 913 |
+
"loss": 0.0135,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.4,
|
| 918 |
+
"grad_norm": 0.0050102900713682175,
|
| 919 |
+
"learning_rate": 1.6533333333333333e-05,
|
| 920 |
+
"loss": 0.02,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.4,
|
| 925 |
+
"grad_norm": 0.044907063245773315,
|
| 926 |
+
"learning_rate": 1.648888888888889e-05,
|
| 927 |
+
"loss": 0.0688,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.41,
|
| 932 |
+
"grad_norm": 0.06957779079675674,
|
| 933 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 934 |
+
"loss": 0.0887,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.41,
|
| 939 |
+
"grad_norm": 1.025342583656311,
|
| 940 |
+
"learning_rate": 1.64e-05,
|
| 941 |
+
"loss": 0.0536,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.41,
|
| 946 |
+
"grad_norm": 0.011287701316177845,
|
| 947 |
+
"learning_rate": 1.6355555555555557e-05,
|
| 948 |
+
"loss": 0.0663,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.42,
|
| 953 |
+
"grad_norm": 3.220019578933716,
|
| 954 |
+
"learning_rate": 1.6311111111111113e-05,
|
| 955 |
+
"loss": 0.0495,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.42,
|
| 960 |
+
"grad_norm": 1.6111379861831665,
|
| 961 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 962 |
+
"loss": 0.0658,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.42,
|
| 967 |
+
"grad_norm": 0.004258489701896906,
|
| 968 |
+
"learning_rate": 1.6222222222222223e-05,
|
| 969 |
+
"loss": 0.0022,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.43,
|
| 974 |
+
"grad_norm": 1.0197640657424927,
|
| 975 |
+
"learning_rate": 1.617777777777778e-05,
|
| 976 |
+
"loss": 0.0969,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.43,
|
| 981 |
+
"grad_norm": 0.003954906482249498,
|
| 982 |
+
"learning_rate": 1.6133333333333334e-05,
|
| 983 |
+
"loss": 0.0474,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.43,
|
| 988 |
+
"grad_norm": 5.326837539672852,
|
| 989 |
+
"learning_rate": 1.608888888888889e-05,
|
| 990 |
+
"loss": 0.0683,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.44,
|
| 995 |
+
"grad_norm": 0.008893176913261414,
|
| 996 |
+
"learning_rate": 1.6044444444444444e-05,
|
| 997 |
+
"loss": 0.0577,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.44,
|
| 1002 |
+
"grad_norm": 0.007870793342590332,
|
| 1003 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1004 |
+
"loss": 0.0658,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.44,
|
| 1009 |
+
"grad_norm": 0.003645359305664897,
|
| 1010 |
+
"learning_rate": 1.5955555555555558e-05,
|
| 1011 |
+
"loss": 0.004,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.44,
|
| 1016 |
+
"grad_norm": 0.6187639236450195,
|
| 1017 |
+
"learning_rate": 1.5911111111111113e-05,
|
| 1018 |
+
"loss": 0.0814,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.45,
|
| 1023 |
+
"grad_norm": 1.7969435453414917,
|
| 1024 |
+
"learning_rate": 1.586666666666667e-05,
|
| 1025 |
+
"loss": 0.0154,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.45,
|
| 1030 |
+
"grad_norm": 2.8159172534942627,
|
| 1031 |
+
"learning_rate": 1.5822222222222224e-05,
|
| 1032 |
+
"loss": 0.1169,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.45,
|
| 1037 |
+
"grad_norm": 1.7929564714431763,
|
| 1038 |
+
"learning_rate": 1.577777777777778e-05,
|
| 1039 |
+
"loss": 0.1261,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.46,
|
| 1044 |
+
"grad_norm": 0.2537187337875366,
|
| 1045 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 1046 |
+
"loss": 0.0193,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.46,
|
| 1051 |
+
"grad_norm": 0.004017004277557135,
|
| 1052 |
+
"learning_rate": 1.5688888888888893e-05,
|
| 1053 |
+
"loss": 0.0246,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.46,
|
| 1058 |
+
"grad_norm": 3.6317222118377686,
|
| 1059 |
+
"learning_rate": 1.5644444444444448e-05,
|
| 1060 |
+
"loss": 0.0987,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.47,
|
| 1065 |
+
"grad_norm": 0.007867836393415928,
|
| 1066 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 1067 |
+
"loss": 0.0535,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.47,
|
| 1072 |
+
"grad_norm": 1.21237313747406,
|
| 1073 |
+
"learning_rate": 1.555555555555556e-05,
|
| 1074 |
+
"loss": 0.0514,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.47,
|
| 1079 |
+
"eval_loss": 0.021845491603016853,
|
| 1080 |
+
"eval_runtime": 61.8947,
|
| 1081 |
+
"eval_samples_per_second": 16.156,
|
| 1082 |
+
"eval_steps_per_second": 16.156,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.47,
|
| 1087 |
+
"grad_norm": 0.022142503410577774,
|
| 1088 |
+
"learning_rate": 1.5511111111111114e-05,
|
| 1089 |
+
"loss": 0.0561,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.48,
|
| 1094 |
+
"grad_norm": 1.5647516250610352,
|
| 1095 |
+
"learning_rate": 1.546666666666667e-05,
|
| 1096 |
+
"loss": 0.0338,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.48,
|
| 1101 |
+
"grad_norm": 0.00992211140692234,
|
| 1102 |
+
"learning_rate": 1.5422222222222224e-05,
|
| 1103 |
+
"loss": 0.0595,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.48,
|
| 1108 |
+
"grad_norm": 0.0023656291887164116,
|
| 1109 |
+
"learning_rate": 1.537777777777778e-05,
|
| 1110 |
+
"loss": 0.0406,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.49,
|
| 1115 |
+
"grad_norm": 0.043642736971378326,
|
| 1116 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 1117 |
+
"loss": 0.1006,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.49,
|
| 1122 |
+
"grad_norm": 0.14472796022891998,
|
| 1123 |
+
"learning_rate": 1.528888888888889e-05,
|
| 1124 |
+
"loss": 0.0087,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.49,
|
| 1129 |
+
"grad_norm": 0.002529141725972295,
|
| 1130 |
+
"learning_rate": 1.5244444444444447e-05,
|
| 1131 |
+
"loss": 0.0283,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.5,
|
| 1136 |
+
"grad_norm": 0.0024450107011944056,
|
| 1137 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 1138 |
+
"loss": 0.0695,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.5,
|
| 1143 |
+
"grad_norm": 0.016819190233945847,
|
| 1144 |
+
"learning_rate": 1.5155555555555557e-05,
|
| 1145 |
+
"loss": 0.0606,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.5,
|
| 1150 |
+
"grad_norm": 1.9701637029647827,
|
| 1151 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 1152 |
+
"loss": 0.0807,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.5,
|
| 1157 |
+
"grad_norm": 0.029984062537550926,
|
| 1158 |
+
"learning_rate": 1.5066666666666668e-05,
|
| 1159 |
+
"loss": 0.0693,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.51,
|
| 1164 |
+
"grad_norm": 0.3928338587284088,
|
| 1165 |
+
"learning_rate": 1.5022222222222223e-05,
|
| 1166 |
+
"loss": 0.0741,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.51,
|
| 1171 |
+
"grad_norm": 0.005559510085731745,
|
| 1172 |
+
"learning_rate": 1.497777777777778e-05,
|
| 1173 |
+
"loss": 0.0725,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.51,
|
| 1178 |
+
"grad_norm": 0.0025930607225745916,
|
| 1179 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 1180 |
+
"loss": 0.1192,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.52,
|
| 1185 |
+
"grad_norm": 2.3535702228546143,
|
| 1186 |
+
"learning_rate": 1.488888888888889e-05,
|
| 1187 |
+
"loss": 0.0606,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.52,
|
| 1192 |
+
"grad_norm": 3.1475963592529297,
|
| 1193 |
+
"learning_rate": 1.4844444444444445e-05,
|
| 1194 |
+
"loss": 0.0956,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.52,
|
| 1199 |
+
"grad_norm": 0.003930664621293545,
|
| 1200 |
+
"learning_rate": 1.48e-05,
|
| 1201 |
+
"loss": 0.0246,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.53,
|
| 1206 |
+
"grad_norm": 3.315476655960083,
|
| 1207 |
+
"learning_rate": 1.4755555555555556e-05,
|
| 1208 |
+
"loss": 0.0953,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.53,
|
| 1213 |
+
"grad_norm": 0.8841826319694519,
|
| 1214 |
+
"learning_rate": 1.4711111111111111e-05,
|
| 1215 |
+
"loss": 0.035,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.53,
|
| 1220 |
+
"grad_norm": 0.01530434563755989,
|
| 1221 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 1222 |
+
"loss": 0.0383,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.54,
|
| 1227 |
+
"grad_norm": 7.836932182312012,
|
| 1228 |
+
"learning_rate": 1.4622222222222225e-05,
|
| 1229 |
+
"loss": 0.0981,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.54,
|
| 1234 |
+
"grad_norm": 0.0168469101190567,
|
| 1235 |
+
"learning_rate": 1.457777777777778e-05,
|
| 1236 |
+
"loss": 0.1095,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.54,
|
| 1241 |
+
"grad_norm": 0.15857402980327606,
|
| 1242 |
+
"learning_rate": 1.4533333333333335e-05,
|
| 1243 |
+
"loss": 0.0574,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.55,
|
| 1248 |
+
"grad_norm": 1.5915563106536865,
|
| 1249 |
+
"learning_rate": 1.448888888888889e-05,
|
| 1250 |
+
"loss": 0.0305,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.55,
|
| 1255 |
+
"grad_norm": 0.039337050169706345,
|
| 1256 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 1257 |
+
"loss": 0.0177,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.55,
|
| 1262 |
+
"grad_norm": 0.0033416992519050837,
|
| 1263 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 1264 |
+
"loss": 0.0009,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.55,
|
| 1269 |
+
"grad_norm": 0.00678109098225832,
|
| 1270 |
+
"learning_rate": 1.4355555555555556e-05,
|
| 1271 |
+
"loss": 0.07,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.56,
|
| 1276 |
+
"grad_norm": 2.4513912200927734,
|
| 1277 |
+
"learning_rate": 1.4311111111111111e-05,
|
| 1278 |
+
"loss": 0.0865,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.56,
|
| 1283 |
+
"grad_norm": 0.966366708278656,
|
| 1284 |
+
"learning_rate": 1.4266666666666668e-05,
|
| 1285 |
+
"loss": 0.0032,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.56,
|
| 1290 |
+
"grad_norm": 2.9548590183258057,
|
| 1291 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 1292 |
+
"loss": 0.0721,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.57,
|
| 1297 |
+
"grad_norm": 3.815798044204712,
|
| 1298 |
+
"learning_rate": 1.4177777777777779e-05,
|
| 1299 |
+
"loss": 0.032,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.57,
|
| 1304 |
+
"grad_norm": 2.7791800498962402,
|
| 1305 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 1306 |
+
"loss": 0.0763,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.57,
|
| 1311 |
+
"grad_norm": 0.004075185861438513,
|
| 1312 |
+
"learning_rate": 1.408888888888889e-05,
|
| 1313 |
+
"loss": 0.0085,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.58,
|
| 1318 |
+
"grad_norm": 0.0038460579235106707,
|
| 1319 |
+
"learning_rate": 1.4044444444444445e-05,
|
| 1320 |
+
"loss": 0.0696,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.58,
|
| 1325 |
+
"grad_norm": 0.005857239011675119,
|
| 1326 |
+
"learning_rate": 1.4e-05,
|
| 1327 |
+
"loss": 0.0559,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.58,
|
| 1332 |
+
"grad_norm": 0.1006237044930458,
|
| 1333 |
+
"learning_rate": 1.3955555555555558e-05,
|
| 1334 |
+
"loss": 0.059,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.59,
|
| 1339 |
+
"grad_norm": 0.004246099852025509,
|
| 1340 |
+
"learning_rate": 1.3911111111111114e-05,
|
| 1341 |
+
"loss": 0.0866,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.59,
|
| 1346 |
+
"grad_norm": 0.00666034035384655,
|
| 1347 |
+
"learning_rate": 1.3866666666666669e-05,
|
| 1348 |
+
"loss": 0.0452,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.59,
|
| 1353 |
+
"grad_norm": 0.0027115230914205313,
|
| 1354 |
+
"learning_rate": 1.3822222222222224e-05,
|
| 1355 |
+
"loss": 0.033,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.6,
|
| 1360 |
+
"grad_norm": 3.016477108001709,
|
| 1361 |
+
"learning_rate": 1.377777777777778e-05,
|
| 1362 |
+
"loss": 0.0437,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.6,
|
| 1367 |
+
"grad_norm": 1.4079822301864624,
|
| 1368 |
+
"learning_rate": 1.3733333333333335e-05,
|
| 1369 |
+
"loss": 0.0474,
|
| 1370 |
+
"step": 1910
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.6,
|
| 1374 |
+
"grad_norm": 0.0025102542713284492,
|
| 1375 |
+
"learning_rate": 1.368888888888889e-05,
|
| 1376 |
+
"loss": 0.0631,
|
| 1377 |
+
"step": 1920
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.6,
|
| 1381 |
+
"grad_norm": 1.394373893737793,
|
| 1382 |
+
"learning_rate": 1.3644444444444445e-05,
|
| 1383 |
+
"loss": 0.0446,
|
| 1384 |
+
"step": 1930
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.61,
|
| 1388 |
+
"grad_norm": 1.0866854190826416,
|
| 1389 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 1390 |
+
"loss": 0.0073,
|
| 1391 |
+
"step": 1940
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.61,
|
| 1395 |
+
"grad_norm": 0.007402149029076099,
|
| 1396 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 1397 |
+
"loss": 0.0311,
|
| 1398 |
+
"step": 1950
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.61,
|
| 1402 |
+
"grad_norm": 0.004811545833945274,
|
| 1403 |
+
"learning_rate": 1.3511111111111112e-05,
|
| 1404 |
+
"loss": 0.0861,
|
| 1405 |
+
"step": 1960
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.62,
|
| 1409 |
+
"grad_norm": 0.004000263754278421,
|
| 1410 |
+
"learning_rate": 1.3466666666666668e-05,
|
| 1411 |
+
"loss": 0.0342,
|
| 1412 |
+
"step": 1970
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.62,
|
| 1416 |
+
"grad_norm": 0.003166991053149104,
|
| 1417 |
+
"learning_rate": 1.3422222222222223e-05,
|
| 1418 |
+
"loss": 0.0897,
|
| 1419 |
+
"step": 1980
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.62,
|
| 1423 |
+
"grad_norm": 0.006424722261726856,
|
| 1424 |
+
"learning_rate": 1.3377777777777778e-05,
|
| 1425 |
+
"loss": 0.0161,
|
| 1426 |
+
"step": 1990
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.63,
|
| 1430 |
+
"grad_norm": 0.0020944385323673487,
|
| 1431 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 1432 |
+
"loss": 0.0358,
|
| 1433 |
+
"step": 2000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.63,
|
| 1437 |
+
"eval_loss": 0.017703723162412643,
|
| 1438 |
+
"eval_runtime": 61.8922,
|
| 1439 |
+
"eval_samples_per_second": 16.157,
|
| 1440 |
+
"eval_steps_per_second": 16.157,
|
| 1441 |
+
"step": 2000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.63,
|
| 1445 |
+
"grad_norm": 0.003021718468517065,
|
| 1446 |
+
"learning_rate": 1.3288888888888889e-05,
|
| 1447 |
+
"loss": 0.0445,
|
| 1448 |
+
"step": 2010
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.63,
|
| 1452 |
+
"grad_norm": 0.010362805798649788,
|
| 1453 |
+
"learning_rate": 1.3244444444444447e-05,
|
| 1454 |
+
"loss": 0.0308,
|
| 1455 |
+
"step": 2020
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.64,
|
| 1459 |
+
"grad_norm": 0.32867729663848877,
|
| 1460 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 1461 |
+
"loss": 0.0514,
|
| 1462 |
+
"step": 2030
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 0.64,
|
| 1466 |
+
"grad_norm": 0.0034784479066729546,
|
| 1467 |
+
"learning_rate": 1.3155555555555558e-05,
|
| 1468 |
+
"loss": 0.0002,
|
| 1469 |
+
"step": 2040
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 0.64,
|
| 1473 |
+
"grad_norm": 0.08931613713502884,
|
| 1474 |
+
"learning_rate": 1.3111111111111113e-05,
|
| 1475 |
+
"loss": 0.0351,
|
| 1476 |
+
"step": 2050
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 0.65,
|
| 1480 |
+
"grad_norm": 0.0024316832423210144,
|
| 1481 |
+
"learning_rate": 1.3066666666666668e-05,
|
| 1482 |
+
"loss": 0.0822,
|
| 1483 |
+
"step": 2060
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 0.65,
|
| 1487 |
+
"grad_norm": 0.6956457495689392,
|
| 1488 |
+
"learning_rate": 1.3022222222222223e-05,
|
| 1489 |
+
"loss": 0.0656,
|
| 1490 |
+
"step": 2070
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.65,
|
| 1494 |
+
"grad_norm": 0.006866452284157276,
|
| 1495 |
+
"learning_rate": 1.2977777777777779e-05,
|
| 1496 |
+
"loss": 0.0709,
|
| 1497 |
+
"step": 2080
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.65,
|
| 1501 |
+
"grad_norm": 0.6907499432563782,
|
| 1502 |
+
"learning_rate": 1.2933333333333334e-05,
|
| 1503 |
+
"loss": 0.0474,
|
| 1504 |
+
"step": 2090
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.66,
|
| 1508 |
+
"grad_norm": 1.3049083948135376,
|
| 1509 |
+
"learning_rate": 1.288888888888889e-05,
|
| 1510 |
+
"loss": 0.096,
|
| 1511 |
+
"step": 2100
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 0.66,
|
| 1515 |
+
"grad_norm": 0.015370524488389492,
|
| 1516 |
+
"learning_rate": 1.2844444444444446e-05,
|
| 1517 |
+
"loss": 0.0433,
|
| 1518 |
+
"step": 2110
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 0.66,
|
| 1522 |
+
"grad_norm": 0.02007671445608139,
|
| 1523 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 1524 |
+
"loss": 0.0422,
|
| 1525 |
+
"step": 2120
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 0.67,
|
| 1529 |
+
"grad_norm": 0.00284277624450624,
|
| 1530 |
+
"learning_rate": 1.2755555555555556e-05,
|
| 1531 |
+
"loss": 0.0432,
|
| 1532 |
+
"step": 2130
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.67,
|
| 1536 |
+
"grad_norm": 0.0024309258442372084,
|
| 1537 |
+
"learning_rate": 1.2711111111111112e-05,
|
| 1538 |
+
"loss": 0.0462,
|
| 1539 |
+
"step": 2140
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.67,
|
| 1543 |
+
"grad_norm": 0.016368340700864792,
|
| 1544 |
+
"learning_rate": 1.2666666666666667e-05,
|
| 1545 |
+
"loss": 0.0804,
|
| 1546 |
+
"step": 2150
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.68,
|
| 1550 |
+
"grad_norm": 0.005066912155598402,
|
| 1551 |
+
"learning_rate": 1.2622222222222222e-05,
|
| 1552 |
+
"loss": 0.0807,
|
| 1553 |
+
"step": 2160
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 0.68,
|
| 1557 |
+
"grad_norm": 0.002282659988850355,
|
| 1558 |
+
"learning_rate": 1.257777777777778e-05,
|
| 1559 |
+
"loss": 0.0395,
|
| 1560 |
+
"step": 2170
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 0.68,
|
| 1564 |
+
"grad_norm": 0.8781790137290955,
|
| 1565 |
+
"learning_rate": 1.2533333333333336e-05,
|
| 1566 |
+
"loss": 0.0168,
|
| 1567 |
+
"step": 2180
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.69,
|
| 1571 |
+
"grad_norm": 0.0021755376365035772,
|
| 1572 |
+
"learning_rate": 1.2488888888888891e-05,
|
| 1573 |
+
"loss": 0.1348,
|
| 1574 |
+
"step": 2190
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 0.69,
|
| 1578 |
+
"grad_norm": 0.0018356326036155224,
|
| 1579 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 1580 |
+
"loss": 0.0419,
|
| 1581 |
+
"step": 2200
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.69,
|
| 1585 |
+
"grad_norm": 0.0016609402373433113,
|
| 1586 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 1587 |
+
"loss": 0.0738,
|
| 1588 |
+
"step": 2210
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 0.7,
|
| 1592 |
+
"grad_norm": 1.0487405061721802,
|
| 1593 |
+
"learning_rate": 1.2355555555555557e-05,
|
| 1594 |
+
"loss": 0.0209,
|
| 1595 |
+
"step": 2220
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 0.7,
|
| 1599 |
+
"grad_norm": 0.0034472872503101826,
|
| 1600 |
+
"learning_rate": 1.2311111111111112e-05,
|
| 1601 |
+
"loss": 0.0322,
|
| 1602 |
+
"step": 2230
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.7,
|
| 1606 |
+
"grad_norm": 2.6054458618164062,
|
| 1607 |
+
"learning_rate": 1.2266666666666667e-05,
|
| 1608 |
+
"loss": 0.1416,
|
| 1609 |
+
"step": 2240
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.7,
|
| 1613 |
+
"grad_norm": 2.022294044494629,
|
| 1614 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 1615 |
+
"loss": 0.0846,
|
| 1616 |
+
"step": 2250
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.71,
|
| 1620 |
+
"grad_norm": 0.010752925649285316,
|
| 1621 |
+
"learning_rate": 1.217777777777778e-05,
|
| 1622 |
+
"loss": 0.0093,
|
| 1623 |
+
"step": 2260
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.71,
|
| 1627 |
+
"grad_norm": 1.9160808324813843,
|
| 1628 |
+
"learning_rate": 1.2133333333333335e-05,
|
| 1629 |
+
"loss": 0.0751,
|
| 1630 |
+
"step": 2270
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 0.71,
|
| 1634 |
+
"grad_norm": 0.002021084539592266,
|
| 1635 |
+
"learning_rate": 1.208888888888889e-05,
|
| 1636 |
+
"loss": 0.0271,
|
| 1637 |
+
"step": 2280
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 0.72,
|
| 1641 |
+
"grad_norm": 0.0034389556385576725,
|
| 1642 |
+
"learning_rate": 1.2044444444444445e-05,
|
| 1643 |
+
"loss": 0.0233,
|
| 1644 |
+
"step": 2290
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.72,
|
| 1648 |
+
"grad_norm": 0.0031041186302900314,
|
| 1649 |
+
"learning_rate": 1.2e-05,
|
| 1650 |
+
"loss": 0.068,
|
| 1651 |
+
"step": 2300
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.72,
|
| 1655 |
+
"grad_norm": 0.0017185291508212686,
|
| 1656 |
+
"learning_rate": 1.1955555555555556e-05,
|
| 1657 |
+
"loss": 0.0369,
|
| 1658 |
+
"step": 2310
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.73,
|
| 1662 |
+
"grad_norm": 0.008447349071502686,
|
| 1663 |
+
"learning_rate": 1.191111111111111e-05,
|
| 1664 |
+
"loss": 0.0549,
|
| 1665 |
+
"step": 2320
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.73,
|
| 1669 |
+
"grad_norm": 0.0062310476787388325,
|
| 1670 |
+
"learning_rate": 1.186666666666667e-05,
|
| 1671 |
+
"loss": 0.0575,
|
| 1672 |
+
"step": 2330
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 0.73,
|
| 1676 |
+
"grad_norm": 0.7583394646644592,
|
| 1677 |
+
"learning_rate": 1.1822222222222225e-05,
|
| 1678 |
+
"loss": 0.0256,
|
| 1679 |
+
"step": 2340
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.74,
|
| 1683 |
+
"grad_norm": 0.4174383878707886,
|
| 1684 |
+
"learning_rate": 1.177777777777778e-05,
|
| 1685 |
+
"loss": 0.0805,
|
| 1686 |
+
"step": 2350
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.74,
|
| 1690 |
+
"grad_norm": 0.003498498583212495,
|
| 1691 |
+
"learning_rate": 1.1733333333333335e-05,
|
| 1692 |
+
"loss": 0.0472,
|
| 1693 |
+
"step": 2360
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.74,
|
| 1697 |
+
"grad_norm": 4.035282135009766,
|
| 1698 |
+
"learning_rate": 1.168888888888889e-05,
|
| 1699 |
+
"loss": 0.0662,
|
| 1700 |
+
"step": 2370
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.75,
|
| 1704 |
+
"grad_norm": 0.0031760677229613066,
|
| 1705 |
+
"learning_rate": 1.1644444444444446e-05,
|
| 1706 |
+
"loss": 0.0367,
|
| 1707 |
+
"step": 2380
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.75,
|
| 1711 |
+
"grad_norm": 0.006041550077497959,
|
| 1712 |
+
"learning_rate": 1.16e-05,
|
| 1713 |
+
"loss": 0.0408,
|
| 1714 |
+
"step": 2390
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.75,
|
| 1718 |
+
"grad_norm": 0.004563288297504187,
|
| 1719 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 1720 |
+
"loss": 0.0133,
|
| 1721 |
+
"step": 2400
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.76,
|
| 1725 |
+
"grad_norm": 2.7603859901428223,
|
| 1726 |
+
"learning_rate": 1.1511111111111113e-05,
|
| 1727 |
+
"loss": 0.0268,
|
| 1728 |
+
"step": 2410
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.76,
|
| 1732 |
+
"grad_norm": 0.0016988619463518262,
|
| 1733 |
+
"learning_rate": 1.1466666666666668e-05,
|
| 1734 |
+
"loss": 0.0542,
|
| 1735 |
+
"step": 2420
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.76,
|
| 1739 |
+
"grad_norm": 0.005680690053850412,
|
| 1740 |
+
"learning_rate": 1.1422222222222223e-05,
|
| 1741 |
+
"loss": 0.0311,
|
| 1742 |
+
"step": 2430
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.76,
|
| 1746 |
+
"grad_norm": 3.9060475826263428,
|
| 1747 |
+
"learning_rate": 1.1377777777777779e-05,
|
| 1748 |
+
"loss": 0.1159,
|
| 1749 |
+
"step": 2440
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.77,
|
| 1753 |
+
"grad_norm": 2.005553722381592,
|
| 1754 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 1755 |
+
"loss": 0.0648,
|
| 1756 |
+
"step": 2450
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.77,
|
| 1760 |
+
"grad_norm": 4.020055294036865,
|
| 1761 |
+
"learning_rate": 1.1288888888888889e-05,
|
| 1762 |
+
"loss": 0.0312,
|
| 1763 |
+
"step": 2460
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.77,
|
| 1767 |
+
"grad_norm": 0.021578742191195488,
|
| 1768 |
+
"learning_rate": 1.1244444444444444e-05,
|
| 1769 |
+
"loss": 0.0285,
|
| 1770 |
+
"step": 2470
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.78,
|
| 1774 |
+
"grad_norm": 0.00151452433783561,
|
| 1775 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 1776 |
+
"loss": 0.0666,
|
| 1777 |
+
"step": 2480
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.78,
|
| 1781 |
+
"grad_norm": 1.127124309539795,
|
| 1782 |
+
"learning_rate": 1.1155555555555556e-05,
|
| 1783 |
+
"loss": 0.0362,
|
| 1784 |
+
"step": 2490
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 0.78,
|
| 1788 |
+
"grad_norm": 0.0015013846568763256,
|
| 1789 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 1790 |
+
"loss": 0.0575,
|
| 1791 |
+
"step": 2500
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.78,
|
| 1795 |
+
"eval_loss": 0.019110437482595444,
|
| 1796 |
+
"eval_runtime": 61.8844,
|
| 1797 |
+
"eval_samples_per_second": 16.159,
|
| 1798 |
+
"eval_steps_per_second": 16.159,
|
| 1799 |
+
"step": 2500
|
| 1800 |
+
}
|
| 1801 |
+
],
|
| 1802 |
+
"logging_steps": 10,
|
| 1803 |
+
"max_steps": 5000,
|
| 1804 |
+
"num_input_tokens_seen": 0,
|
| 1805 |
+
"num_train_epochs": 2,
|
| 1806 |
+
"save_steps": 2500,
|
| 1807 |
+
"total_flos": 4.025531498496e+16,
|
| 1808 |
+
"train_batch_size": 1,
|
| 1809 |
+
"trial_name": null,
|
| 1810 |
+
"trial_params": null
|
| 1811 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:147523bb2896dc07fdc080f98264dcb6897fe57fb71a631833d6632dd6b2130a
|
| 3 |
+
size 4920
|