Commit
•
43fd9e4
1
Parent(s):
6d96a2f
Upload 8 files
Browse files- README.md +202 -3
- adapter_config.json +29 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1533 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 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 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7dc07c8711811876a2574ceae0d54648a12092e78e64ed0f9226f93cb636c48
|
| 3 |
+
size 16823434
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e1cec9fdd5f532a9143affb50feb85d62759daa8df3de39a86cd9179e202085
|
| 3 |
+
size 33662074
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34f745fa6dfaaddd7baec3093d9b799d21ce1fc1d5ec7905895d613f9f8836d5
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:802aea6a94596a1508efd2609357c7d03b7afc6793c019662dc8c4716ec3f4be
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2660675048828125,
|
| 3 |
+
"best_model_checkpoint": "/scratch/czm5kz/llama2-7b_8_50_0.0003_sg_finetuned_combined/checkpoint-840",
|
| 4 |
+
"epoch": 49.411764705882355,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 840,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.29,
|
| 13 |
+
"grad_norm": NaN,
|
| 14 |
+
"learning_rate": 0.0002989411764705882,
|
| 15 |
+
"loss": 5.4103,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.59,
|
| 20 |
+
"grad_norm": 1.4938805103302002,
|
| 21 |
+
"learning_rate": 0.0002971764705882353,
|
| 22 |
+
"loss": 5.1285,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.88,
|
| 27 |
+
"grad_norm": 2.592315673828125,
|
| 28 |
+
"learning_rate": 0.0002954117647058823,
|
| 29 |
+
"loss": 4.2667,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.18,
|
| 34 |
+
"grad_norm": 2.206411123275757,
|
| 35 |
+
"learning_rate": 0.0002936470588235294,
|
| 36 |
+
"loss": 3.4402,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.18,
|
| 41 |
+
"eval_loss": 3.1646199226379395,
|
| 42 |
+
"eval_runtime": 1.9198,
|
| 43 |
+
"eval_samples_per_second": 69.797,
|
| 44 |
+
"eval_steps_per_second": 8.855,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.47,
|
| 49 |
+
"grad_norm": 1.824563980102539,
|
| 50 |
+
"learning_rate": 0.00029188235294117643,
|
| 51 |
+
"loss": 3.1312,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.76,
|
| 56 |
+
"grad_norm": 2.1594173908233643,
|
| 57 |
+
"learning_rate": 0.0002901176470588235,
|
| 58 |
+
"loss": 2.675,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.06,
|
| 63 |
+
"grad_norm": 2.2764227390289307,
|
| 64 |
+
"learning_rate": 0.00028835294117647055,
|
| 65 |
+
"loss": 2.491,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.35,
|
| 70 |
+
"grad_norm": 2.14278507232666,
|
| 71 |
+
"learning_rate": 0.00028658823529411763,
|
| 72 |
+
"loss": 2.2694,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.35,
|
| 77 |
+
"eval_loss": 2.0995066165924072,
|
| 78 |
+
"eval_runtime": 1.9224,
|
| 79 |
+
"eval_samples_per_second": 69.704,
|
| 80 |
+
"eval_steps_per_second": 8.843,
|
| 81 |
+
"step": 40
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.65,
|
| 85 |
+
"grad_norm": 2.457611560821533,
|
| 86 |
+
"learning_rate": 0.0002848235294117647,
|
| 87 |
+
"loss": 2.115,
|
| 88 |
+
"step": 45
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.94,
|
| 92 |
+
"grad_norm": 3.5367114543914795,
|
| 93 |
+
"learning_rate": 0.00028305882352941175,
|
| 94 |
+
"loss": 1.9109,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.24,
|
| 99 |
+
"grad_norm": 5.9490227699279785,
|
| 100 |
+
"learning_rate": 0.0002812941176470588,
|
| 101 |
+
"loss": 1.6125,
|
| 102 |
+
"step": 55
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.53,
|
| 106 |
+
"grad_norm": 4.218448638916016,
|
| 107 |
+
"learning_rate": 0.00027952941176470587,
|
| 108 |
+
"loss": 1.6965,
|
| 109 |
+
"step": 60
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.53,
|
| 113 |
+
"eval_loss": 1.309256672859192,
|
| 114 |
+
"eval_runtime": 1.9221,
|
| 115 |
+
"eval_samples_per_second": 69.714,
|
| 116 |
+
"eval_steps_per_second": 8.844,
|
| 117 |
+
"step": 60
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.82,
|
| 121 |
+
"grad_norm": 4.950811862945557,
|
| 122 |
+
"learning_rate": 0.0002777647058823529,
|
| 123 |
+
"loss": 1.2561,
|
| 124 |
+
"step": 65
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.12,
|
| 128 |
+
"grad_norm": 3.5115580558776855,
|
| 129 |
+
"learning_rate": 0.000276,
|
| 130 |
+
"loss": 1.2923,
|
| 131 |
+
"step": 70
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.41,
|
| 135 |
+
"grad_norm": 4.053131103515625,
|
| 136 |
+
"learning_rate": 0.000274235294117647,
|
| 137 |
+
"loss": 0.8754,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.71,
|
| 142 |
+
"grad_norm": 8.593412399291992,
|
| 143 |
+
"learning_rate": 0.0002724705882352941,
|
| 144 |
+
"loss": 0.9971,
|
| 145 |
+
"step": 80
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.71,
|
| 149 |
+
"eval_loss": 0.7918062210083008,
|
| 150 |
+
"eval_runtime": 1.923,
|
| 151 |
+
"eval_samples_per_second": 69.684,
|
| 152 |
+
"eval_steps_per_second": 8.841,
|
| 153 |
+
"step": 80
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.0,
|
| 157 |
+
"grad_norm": 5.546477794647217,
|
| 158 |
+
"learning_rate": 0.00027070588235294114,
|
| 159 |
+
"loss": 1.0066,
|
| 160 |
+
"step": 85
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 5.29,
|
| 164 |
+
"grad_norm": 4.750329971313477,
|
| 165 |
+
"learning_rate": 0.0002689411764705882,
|
| 166 |
+
"loss": 0.6666,
|
| 167 |
+
"step": 90
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.59,
|
| 171 |
+
"grad_norm": 6.40559720993042,
|
| 172 |
+
"learning_rate": 0.00026717647058823525,
|
| 173 |
+
"loss": 0.7559,
|
| 174 |
+
"step": 95
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.88,
|
| 178 |
+
"grad_norm": 4.358940124511719,
|
| 179 |
+
"learning_rate": 0.00026541176470588234,
|
| 180 |
+
"loss": 0.6462,
|
| 181 |
+
"step": 100
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.88,
|
| 185 |
+
"eval_loss": 0.5163397789001465,
|
| 186 |
+
"eval_runtime": 1.9282,
|
| 187 |
+
"eval_samples_per_second": 69.496,
|
| 188 |
+
"eval_steps_per_second": 8.817,
|
| 189 |
+
"step": 100
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.18,
|
| 193 |
+
"grad_norm": 2.795166015625,
|
| 194 |
+
"learning_rate": 0.00026364705882352937,
|
| 195 |
+
"loss": 0.5542,
|
| 196 |
+
"step": 105
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.47,
|
| 200 |
+
"grad_norm": 5.22014856338501,
|
| 201 |
+
"learning_rate": 0.00026188235294117646,
|
| 202 |
+
"loss": 0.4833,
|
| 203 |
+
"step": 110
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 6.76,
|
| 207 |
+
"grad_norm": 3.8278372287750244,
|
| 208 |
+
"learning_rate": 0.0002601176470588235,
|
| 209 |
+
"loss": 0.5228,
|
| 210 |
+
"step": 115
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 7.06,
|
| 214 |
+
"grad_norm": 3.607290029525757,
|
| 215 |
+
"learning_rate": 0.0002583529411764706,
|
| 216 |
+
"loss": 0.5413,
|
| 217 |
+
"step": 120
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 7.06,
|
| 221 |
+
"eval_loss": 0.43107467889785767,
|
| 222 |
+
"eval_runtime": 1.9336,
|
| 223 |
+
"eval_samples_per_second": 69.302,
|
| 224 |
+
"eval_steps_per_second": 8.792,
|
| 225 |
+
"step": 120
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.35,
|
| 229 |
+
"grad_norm": 2.634229898452759,
|
| 230 |
+
"learning_rate": 0.00025658823529411766,
|
| 231 |
+
"loss": 0.4545,
|
| 232 |
+
"step": 125
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 7.65,
|
| 236 |
+
"grad_norm": 5.728726863861084,
|
| 237 |
+
"learning_rate": 0.0002548235294117647,
|
| 238 |
+
"loss": 0.4578,
|
| 239 |
+
"step": 130
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 7.94,
|
| 243 |
+
"grad_norm": 3.3267197608947754,
|
| 244 |
+
"learning_rate": 0.0002530588235294117,
|
| 245 |
+
"loss": 0.4934,
|
| 246 |
+
"step": 135
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 8.24,
|
| 250 |
+
"grad_norm": 2.8072242736816406,
|
| 251 |
+
"learning_rate": 0.0002512941176470588,
|
| 252 |
+
"loss": 0.4146,
|
| 253 |
+
"step": 140
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 8.24,
|
| 257 |
+
"eval_loss": 0.37879472970962524,
|
| 258 |
+
"eval_runtime": 1.9304,
|
| 259 |
+
"eval_samples_per_second": 69.415,
|
| 260 |
+
"eval_steps_per_second": 8.806,
|
| 261 |
+
"step": 140
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.53,
|
| 265 |
+
"grad_norm": 4.419933319091797,
|
| 266 |
+
"learning_rate": 0.00024952941176470584,
|
| 267 |
+
"loss": 0.436,
|
| 268 |
+
"step": 145
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.82,
|
| 272 |
+
"grad_norm": 2.759542465209961,
|
| 273 |
+
"learning_rate": 0.00024776470588235293,
|
| 274 |
+
"loss": 0.4245,
|
| 275 |
+
"step": 150
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.12,
|
| 279 |
+
"grad_norm": 2.82211971282959,
|
| 280 |
+
"learning_rate": 0.00024599999999999996,
|
| 281 |
+
"loss": 0.4608,
|
| 282 |
+
"step": 155
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.41,
|
| 286 |
+
"grad_norm": 3.7776830196380615,
|
| 287 |
+
"learning_rate": 0.00024423529411764705,
|
| 288 |
+
"loss": 0.3992,
|
| 289 |
+
"step": 160
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 9.41,
|
| 293 |
+
"eval_loss": 0.35705941915512085,
|
| 294 |
+
"eval_runtime": 1.9328,
|
| 295 |
+
"eval_samples_per_second": 69.328,
|
| 296 |
+
"eval_steps_per_second": 8.795,
|
| 297 |
+
"step": 160
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.71,
|
| 301 |
+
"grad_norm": 3.110931873321533,
|
| 302 |
+
"learning_rate": 0.0002424705882352941,
|
| 303 |
+
"loss": 0.4201,
|
| 304 |
+
"step": 165
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 10.0,
|
| 308 |
+
"grad_norm": 2.9114022254943848,
|
| 309 |
+
"learning_rate": 0.00024070588235294117,
|
| 310 |
+
"loss": 0.4171,
|
| 311 |
+
"step": 170
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 10.29,
|
| 315 |
+
"grad_norm": 2.747077703475952,
|
| 316 |
+
"learning_rate": 0.00023894117647058823,
|
| 317 |
+
"loss": 0.3664,
|
| 318 |
+
"step": 175
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 10.59,
|
| 322 |
+
"grad_norm": 3.499821424484253,
|
| 323 |
+
"learning_rate": 0.00023717647058823526,
|
| 324 |
+
"loss": 0.3934,
|
| 325 |
+
"step": 180
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 10.59,
|
| 329 |
+
"eval_loss": 0.3550761640071869,
|
| 330 |
+
"eval_runtime": 1.9331,
|
| 331 |
+
"eval_samples_per_second": 69.318,
|
| 332 |
+
"eval_steps_per_second": 8.794,
|
| 333 |
+
"step": 180
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 10.88,
|
| 337 |
+
"grad_norm": 2.199946165084839,
|
| 338 |
+
"learning_rate": 0.00023541176470588232,
|
| 339 |
+
"loss": 0.4389,
|
| 340 |
+
"step": 185
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 11.18,
|
| 344 |
+
"grad_norm": 1.6292589902877808,
|
| 345 |
+
"learning_rate": 0.00023364705882352938,
|
| 346 |
+
"loss": 0.3886,
|
| 347 |
+
"step": 190
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 11.47,
|
| 351 |
+
"grad_norm": 2.2364566326141357,
|
| 352 |
+
"learning_rate": 0.00023188235294117646,
|
| 353 |
+
"loss": 0.3536,
|
| 354 |
+
"step": 195
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 11.76,
|
| 358 |
+
"grad_norm": 2.165865898132324,
|
| 359 |
+
"learning_rate": 0.00023011764705882352,
|
| 360 |
+
"loss": 0.3489,
|
| 361 |
+
"step": 200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 11.76,
|
| 365 |
+
"eval_loss": 0.3096841275691986,
|
| 366 |
+
"eval_runtime": 1.9357,
|
| 367 |
+
"eval_samples_per_second": 69.225,
|
| 368 |
+
"eval_steps_per_second": 8.782,
|
| 369 |
+
"step": 200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.06,
|
| 373 |
+
"grad_norm": 1.1357084512710571,
|
| 374 |
+
"learning_rate": 0.00022835294117647058,
|
| 375 |
+
"loss": 0.3538,
|
| 376 |
+
"step": 205
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 12.35,
|
| 380 |
+
"grad_norm": 1.3025437593460083,
|
| 381 |
+
"learning_rate": 0.0002265882352941176,
|
| 382 |
+
"loss": 0.3033,
|
| 383 |
+
"step": 210
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 12.65,
|
| 387 |
+
"grad_norm": 1.7671643495559692,
|
| 388 |
+
"learning_rate": 0.00022482352941176467,
|
| 389 |
+
"loss": 0.3734,
|
| 390 |
+
"step": 215
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 12.94,
|
| 394 |
+
"grad_norm": 2.1980714797973633,
|
| 395 |
+
"learning_rate": 0.00022305882352941176,
|
| 396 |
+
"loss": 0.3942,
|
| 397 |
+
"step": 220
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 12.94,
|
| 401 |
+
"eval_loss": 0.3041135370731354,
|
| 402 |
+
"eval_runtime": 1.9467,
|
| 403 |
+
"eval_samples_per_second": 68.835,
|
| 404 |
+
"eval_steps_per_second": 8.733,
|
| 405 |
+
"step": 220
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.24,
|
| 409 |
+
"grad_norm": 1.5232170820236206,
|
| 410 |
+
"learning_rate": 0.00022129411764705881,
|
| 411 |
+
"loss": 0.3196,
|
| 412 |
+
"step": 225
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 13.53,
|
| 416 |
+
"grad_norm": 1.3355060815811157,
|
| 417 |
+
"learning_rate": 0.00021952941176470587,
|
| 418 |
+
"loss": 0.3504,
|
| 419 |
+
"step": 230
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 13.82,
|
| 423 |
+
"grad_norm": 1.7420495748519897,
|
| 424 |
+
"learning_rate": 0.0002177647058823529,
|
| 425 |
+
"loss": 0.3633,
|
| 426 |
+
"step": 235
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 14.12,
|
| 430 |
+
"grad_norm": 1.2982964515686035,
|
| 431 |
+
"learning_rate": 0.00021599999999999996,
|
| 432 |
+
"loss": 0.3953,
|
| 433 |
+
"step": 240
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 14.12,
|
| 437 |
+
"eval_loss": 0.30998367071151733,
|
| 438 |
+
"eval_runtime": 1.9386,
|
| 439 |
+
"eval_samples_per_second": 69.123,
|
| 440 |
+
"eval_steps_per_second": 8.769,
|
| 441 |
+
"step": 240
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 14.41,
|
| 445 |
+
"grad_norm": 1.4662508964538574,
|
| 446 |
+
"learning_rate": 0.00021423529411764705,
|
| 447 |
+
"loss": 0.3218,
|
| 448 |
+
"step": 245
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 14.71,
|
| 452 |
+
"grad_norm": 5.769560813903809,
|
| 453 |
+
"learning_rate": 0.0002124705882352941,
|
| 454 |
+
"loss": 0.3529,
|
| 455 |
+
"step": 250
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 15.0,
|
| 459 |
+
"grad_norm": 1.21450936794281,
|
| 460 |
+
"learning_rate": 0.00021070588235294117,
|
| 461 |
+
"loss": 0.3709,
|
| 462 |
+
"step": 255
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 15.29,
|
| 466 |
+
"grad_norm": 1.1447687149047852,
|
| 467 |
+
"learning_rate": 0.0002089411764705882,
|
| 468 |
+
"loss": 0.3181,
|
| 469 |
+
"step": 260
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 15.29,
|
| 473 |
+
"eval_loss": 0.3001173138618469,
|
| 474 |
+
"eval_runtime": 1.9398,
|
| 475 |
+
"eval_samples_per_second": 69.078,
|
| 476 |
+
"eval_steps_per_second": 8.764,
|
| 477 |
+
"step": 260
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 15.59,
|
| 481 |
+
"grad_norm": 1.2628802061080933,
|
| 482 |
+
"learning_rate": 0.00020717647058823526,
|
| 483 |
+
"loss": 0.3276,
|
| 484 |
+
"step": 265
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 15.88,
|
| 488 |
+
"grad_norm": 1.5145180225372314,
|
| 489 |
+
"learning_rate": 0.00020541176470588232,
|
| 490 |
+
"loss": 0.3494,
|
| 491 |
+
"step": 270
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 16.18,
|
| 495 |
+
"grad_norm": 0.9314962029457092,
|
| 496 |
+
"learning_rate": 0.0002036470588235294,
|
| 497 |
+
"loss": 0.3023,
|
| 498 |
+
"step": 275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 16.47,
|
| 502 |
+
"grad_norm": 1.3280673027038574,
|
| 503 |
+
"learning_rate": 0.00020188235294117646,
|
| 504 |
+
"loss": 0.3252,
|
| 505 |
+
"step": 280
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 16.47,
|
| 509 |
+
"eval_loss": 0.3047679364681244,
|
| 510 |
+
"eval_runtime": 1.9398,
|
| 511 |
+
"eval_samples_per_second": 69.08,
|
| 512 |
+
"eval_steps_per_second": 8.764,
|
| 513 |
+
"step": 280
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 16.76,
|
| 517 |
+
"grad_norm": 12.369646072387695,
|
| 518 |
+
"learning_rate": 0.00020011764705882352,
|
| 519 |
+
"loss": 0.3628,
|
| 520 |
+
"step": 285
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 17.06,
|
| 524 |
+
"grad_norm": 0.9423893690109253,
|
| 525 |
+
"learning_rate": 0.00019835294117647055,
|
| 526 |
+
"loss": 0.3365,
|
| 527 |
+
"step": 290
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 17.35,
|
| 531 |
+
"grad_norm": 1.1777836084365845,
|
| 532 |
+
"learning_rate": 0.00019658823529411761,
|
| 533 |
+
"loss": 0.3145,
|
| 534 |
+
"step": 295
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 17.65,
|
| 538 |
+
"grad_norm": 1.1752514839172363,
|
| 539 |
+
"learning_rate": 0.0001948235294117647,
|
| 540 |
+
"loss": 0.3433,
|
| 541 |
+
"step": 300
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 17.65,
|
| 545 |
+
"eval_loss": 0.2916710674762726,
|
| 546 |
+
"eval_runtime": 1.949,
|
| 547 |
+
"eval_samples_per_second": 68.752,
|
| 548 |
+
"eval_steps_per_second": 8.722,
|
| 549 |
+
"step": 300
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 17.94,
|
| 553 |
+
"grad_norm": 0.9878242611885071,
|
| 554 |
+
"learning_rate": 0.00019305882352941176,
|
| 555 |
+
"loss": 0.3349,
|
| 556 |
+
"step": 305
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 18.24,
|
| 560 |
+
"grad_norm": 0.836021900177002,
|
| 561 |
+
"learning_rate": 0.00019129411764705882,
|
| 562 |
+
"loss": 0.3016,
|
| 563 |
+
"step": 310
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 18.53,
|
| 567 |
+
"grad_norm": 0.9070651531219482,
|
| 568 |
+
"learning_rate": 0.00018952941176470585,
|
| 569 |
+
"loss": 0.3042,
|
| 570 |
+
"step": 315
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 18.82,
|
| 574 |
+
"grad_norm": 0.9631121754646301,
|
| 575 |
+
"learning_rate": 0.0001877647058823529,
|
| 576 |
+
"loss": 0.3359,
|
| 577 |
+
"step": 320
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 18.82,
|
| 581 |
+
"eval_loss": 0.2895776033401489,
|
| 582 |
+
"eval_runtime": 1.9409,
|
| 583 |
+
"eval_samples_per_second": 69.042,
|
| 584 |
+
"eval_steps_per_second": 8.759,
|
| 585 |
+
"step": 320
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 19.12,
|
| 589 |
+
"grad_norm": 0.9133499264717102,
|
| 590 |
+
"learning_rate": 0.000186,
|
| 591 |
+
"loss": 0.3066,
|
| 592 |
+
"step": 325
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 19.41,
|
| 596 |
+
"grad_norm": 0.9856986403465271,
|
| 597 |
+
"learning_rate": 0.00018423529411764705,
|
| 598 |
+
"loss": 0.2968,
|
| 599 |
+
"step": 330
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 19.71,
|
| 603 |
+
"grad_norm": 0.8035317659378052,
|
| 604 |
+
"learning_rate": 0.0001824705882352941,
|
| 605 |
+
"loss": 0.293,
|
| 606 |
+
"step": 335
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 20.0,
|
| 610 |
+
"grad_norm": 1.5814510583877563,
|
| 611 |
+
"learning_rate": 0.00018070588235294114,
|
| 612 |
+
"loss": 0.3671,
|
| 613 |
+
"step": 340
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 20.0,
|
| 617 |
+
"eval_loss": 0.2835056781768799,
|
| 618 |
+
"eval_runtime": 1.9399,
|
| 619 |
+
"eval_samples_per_second": 69.076,
|
| 620 |
+
"eval_steps_per_second": 8.763,
|
| 621 |
+
"step": 340
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 20.29,
|
| 625 |
+
"grad_norm": 0.9612240791320801,
|
| 626 |
+
"learning_rate": 0.0001789411764705882,
|
| 627 |
+
"loss": 0.2899,
|
| 628 |
+
"step": 345
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 20.59,
|
| 632 |
+
"grad_norm": 0.8361384272575378,
|
| 633 |
+
"learning_rate": 0.00017717647058823526,
|
| 634 |
+
"loss": 0.3003,
|
| 635 |
+
"step": 350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 20.88,
|
| 639 |
+
"grad_norm": 1.1012054681777954,
|
| 640 |
+
"learning_rate": 0.00017541176470588235,
|
| 641 |
+
"loss": 0.3166,
|
| 642 |
+
"step": 355
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 21.18,
|
| 646 |
+
"grad_norm": 0.9163299202919006,
|
| 647 |
+
"learning_rate": 0.0001736470588235294,
|
| 648 |
+
"loss": 0.2974,
|
| 649 |
+
"step": 360
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 21.18,
|
| 653 |
+
"eval_loss": 0.2791600525379181,
|
| 654 |
+
"eval_runtime": 1.941,
|
| 655 |
+
"eval_samples_per_second": 69.038,
|
| 656 |
+
"eval_steps_per_second": 8.759,
|
| 657 |
+
"step": 360
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 21.47,
|
| 661 |
+
"grad_norm": 0.8624510765075684,
|
| 662 |
+
"learning_rate": 0.00017188235294117647,
|
| 663 |
+
"loss": 0.2861,
|
| 664 |
+
"step": 365
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 21.76,
|
| 668 |
+
"grad_norm": 1.293444275856018,
|
| 669 |
+
"learning_rate": 0.0001701176470588235,
|
| 670 |
+
"loss": 0.3208,
|
| 671 |
+
"step": 370
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 22.06,
|
| 675 |
+
"grad_norm": 0.6756078004837036,
|
| 676 |
+
"learning_rate": 0.00016835294117647056,
|
| 677 |
+
"loss": 0.3121,
|
| 678 |
+
"step": 375
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 22.35,
|
| 682 |
+
"grad_norm": 0.9174789190292358,
|
| 683 |
+
"learning_rate": 0.00016658823529411764,
|
| 684 |
+
"loss": 0.2957,
|
| 685 |
+
"step": 380
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 22.35,
|
| 689 |
+
"eval_loss": 0.28055718541145325,
|
| 690 |
+
"eval_runtime": 1.9416,
|
| 691 |
+
"eval_samples_per_second": 69.014,
|
| 692 |
+
"eval_steps_per_second": 8.755,
|
| 693 |
+
"step": 380
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 22.65,
|
| 697 |
+
"grad_norm": 0.8151916861534119,
|
| 698 |
+
"learning_rate": 0.0001648235294117647,
|
| 699 |
+
"loss": 0.2977,
|
| 700 |
+
"step": 385
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 22.94,
|
| 704 |
+
"grad_norm": 0.8723404407501221,
|
| 705 |
+
"learning_rate": 0.00016305882352941176,
|
| 706 |
+
"loss": 0.3042,
|
| 707 |
+
"step": 390
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 23.24,
|
| 711 |
+
"grad_norm": 0.9448694586753845,
|
| 712 |
+
"learning_rate": 0.0001612941176470588,
|
| 713 |
+
"loss": 0.2725,
|
| 714 |
+
"step": 395
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 23.53,
|
| 718 |
+
"grad_norm": 1.0331761837005615,
|
| 719 |
+
"learning_rate": 0.00015952941176470585,
|
| 720 |
+
"loss": 0.307,
|
| 721 |
+
"step": 400
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 23.53,
|
| 725 |
+
"eval_loss": 0.2780434191226959,
|
| 726 |
+
"eval_runtime": 1.9423,
|
| 727 |
+
"eval_samples_per_second": 68.99,
|
| 728 |
+
"eval_steps_per_second": 8.752,
|
| 729 |
+
"step": 400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 23.82,
|
| 733 |
+
"grad_norm": 1.0633246898651123,
|
| 734 |
+
"learning_rate": 0.00015776470588235294,
|
| 735 |
+
"loss": 0.3015,
|
| 736 |
+
"step": 405
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 24.12,
|
| 740 |
+
"grad_norm": 0.7136632800102234,
|
| 741 |
+
"learning_rate": 0.000156,
|
| 742 |
+
"loss": 0.2915,
|
| 743 |
+
"step": 410
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 24.41,
|
| 747 |
+
"grad_norm": 0.7327393293380737,
|
| 748 |
+
"learning_rate": 0.00015423529411764706,
|
| 749 |
+
"loss": 0.2882,
|
| 750 |
+
"step": 415
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 24.71,
|
| 754 |
+
"grad_norm": 0.7720869779586792,
|
| 755 |
+
"learning_rate": 0.0001524705882352941,
|
| 756 |
+
"loss": 0.2905,
|
| 757 |
+
"step": 420
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 24.71,
|
| 761 |
+
"eval_loss": 0.27704769372940063,
|
| 762 |
+
"eval_runtime": 1.9407,
|
| 763 |
+
"eval_samples_per_second": 69.046,
|
| 764 |
+
"eval_steps_per_second": 8.76,
|
| 765 |
+
"step": 420
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 25.0,
|
| 769 |
+
"grad_norm": 0.8705993890762329,
|
| 770 |
+
"learning_rate": 0.00015070588235294115,
|
| 771 |
+
"loss": 0.3195,
|
| 772 |
+
"step": 425
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 25.29,
|
| 776 |
+
"grad_norm": 0.8639763593673706,
|
| 777 |
+
"learning_rate": 0.0001489411764705882,
|
| 778 |
+
"loss": 0.2838,
|
| 779 |
+
"step": 430
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 25.59,
|
| 783 |
+
"grad_norm": 0.9361162185668945,
|
| 784 |
+
"learning_rate": 0.0001471764705882353,
|
| 785 |
+
"loss": 0.2748,
|
| 786 |
+
"step": 435
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 25.88,
|
| 790 |
+
"grad_norm": 1.0659866333007812,
|
| 791 |
+
"learning_rate": 0.00014541176470588232,
|
| 792 |
+
"loss": 0.3256,
|
| 793 |
+
"step": 440
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 25.88,
|
| 797 |
+
"eval_loss": 0.27406755089759827,
|
| 798 |
+
"eval_runtime": 1.9407,
|
| 799 |
+
"eval_samples_per_second": 69.046,
|
| 800 |
+
"eval_steps_per_second": 8.76,
|
| 801 |
+
"step": 440
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 26.18,
|
| 805 |
+
"grad_norm": 0.6408669352531433,
|
| 806 |
+
"learning_rate": 0.0001436470588235294,
|
| 807 |
+
"loss": 0.2793,
|
| 808 |
+
"step": 445
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 26.47,
|
| 812 |
+
"grad_norm": 0.7933536767959595,
|
| 813 |
+
"learning_rate": 0.00014188235294117647,
|
| 814 |
+
"loss": 0.2871,
|
| 815 |
+
"step": 450
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 26.76,
|
| 819 |
+
"grad_norm": 0.8687612414360046,
|
| 820 |
+
"learning_rate": 0.0001401176470588235,
|
| 821 |
+
"loss": 0.3059,
|
| 822 |
+
"step": 455
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 27.06,
|
| 826 |
+
"grad_norm": 0.9702476859092712,
|
| 827 |
+
"learning_rate": 0.0001383529411764706,
|
| 828 |
+
"loss": 0.2966,
|
| 829 |
+
"step": 460
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 27.06,
|
| 833 |
+
"eval_loss": 0.2723328769207001,
|
| 834 |
+
"eval_runtime": 1.9411,
|
| 835 |
+
"eval_samples_per_second": 69.035,
|
| 836 |
+
"eval_steps_per_second": 8.758,
|
| 837 |
+
"step": 460
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 27.35,
|
| 841 |
+
"grad_norm": 0.6730605959892273,
|
| 842 |
+
"learning_rate": 0.00013658823529411765,
|
| 843 |
+
"loss": 0.2638,
|
| 844 |
+
"step": 465
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 27.65,
|
| 848 |
+
"grad_norm": 0.6563217639923096,
|
| 849 |
+
"learning_rate": 0.0001348235294117647,
|
| 850 |
+
"loss": 0.3059,
|
| 851 |
+
"step": 470
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 27.94,
|
| 855 |
+
"grad_norm": 0.686863362789154,
|
| 856 |
+
"learning_rate": 0.00013305882352941176,
|
| 857 |
+
"loss": 0.2938,
|
| 858 |
+
"step": 475
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 28.24,
|
| 862 |
+
"grad_norm": 1.0649175643920898,
|
| 863 |
+
"learning_rate": 0.0001312941176470588,
|
| 864 |
+
"loss": 0.312,
|
| 865 |
+
"step": 480
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 28.24,
|
| 869 |
+
"eval_loss": 0.27256956696510315,
|
| 870 |
+
"eval_runtime": 1.9432,
|
| 871 |
+
"eval_samples_per_second": 68.957,
|
| 872 |
+
"eval_steps_per_second": 8.748,
|
| 873 |
+
"step": 480
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 28.53,
|
| 877 |
+
"grad_norm": 0.746249258518219,
|
| 878 |
+
"learning_rate": 0.00012952941176470588,
|
| 879 |
+
"loss": 0.2788,
|
| 880 |
+
"step": 485
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 28.82,
|
| 884 |
+
"grad_norm": 0.7490785717964172,
|
| 885 |
+
"learning_rate": 0.00012776470588235294,
|
| 886 |
+
"loss": 0.2766,
|
| 887 |
+
"step": 490
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 29.12,
|
| 891 |
+
"grad_norm": 0.967271625995636,
|
| 892 |
+
"learning_rate": 0.00012599999999999997,
|
| 893 |
+
"loss": 0.2848,
|
| 894 |
+
"step": 495
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 29.41,
|
| 898 |
+
"grad_norm": 0.7683994770050049,
|
| 899 |
+
"learning_rate": 0.00012423529411764706,
|
| 900 |
+
"loss": 0.2886,
|
| 901 |
+
"step": 500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 29.41,
|
| 905 |
+
"eval_loss": 0.2728249728679657,
|
| 906 |
+
"eval_runtime": 1.9475,
|
| 907 |
+
"eval_samples_per_second": 68.808,
|
| 908 |
+
"eval_steps_per_second": 8.729,
|
| 909 |
+
"step": 500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 29.71,
|
| 913 |
+
"grad_norm": 0.8643724918365479,
|
| 914 |
+
"learning_rate": 0.00012247058823529412,
|
| 915 |
+
"loss": 0.2887,
|
| 916 |
+
"step": 505
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 30.0,
|
| 920 |
+
"grad_norm": 1.343279242515564,
|
| 921 |
+
"learning_rate": 0.00012070588235294116,
|
| 922 |
+
"loss": 0.2992,
|
| 923 |
+
"step": 510
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 30.29,
|
| 927 |
+
"grad_norm": 0.905185341835022,
|
| 928 |
+
"learning_rate": 0.00011894117647058822,
|
| 929 |
+
"loss": 0.2755,
|
| 930 |
+
"step": 515
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 30.59,
|
| 934 |
+
"grad_norm": 0.708074152469635,
|
| 935 |
+
"learning_rate": 0.00011717647058823528,
|
| 936 |
+
"loss": 0.3067,
|
| 937 |
+
"step": 520
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 30.59,
|
| 941 |
+
"eval_loss": 0.27262699604034424,
|
| 942 |
+
"eval_runtime": 1.9441,
|
| 943 |
+
"eval_samples_per_second": 68.925,
|
| 944 |
+
"eval_steps_per_second": 8.744,
|
| 945 |
+
"step": 520
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 30.88,
|
| 949 |
+
"grad_norm": 0.9293233156204224,
|
| 950 |
+
"learning_rate": 0.00011541176470588234,
|
| 951 |
+
"loss": 0.2789,
|
| 952 |
+
"step": 525
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 31.18,
|
| 956 |
+
"grad_norm": 0.5454906225204468,
|
| 957 |
+
"learning_rate": 0.00011364705882352941,
|
| 958 |
+
"loss": 0.279,
|
| 959 |
+
"step": 530
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 31.47,
|
| 963 |
+
"grad_norm": 0.7660827040672302,
|
| 964 |
+
"learning_rate": 0.00011188235294117646,
|
| 965 |
+
"loss": 0.29,
|
| 966 |
+
"step": 535
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 31.76,
|
| 970 |
+
"grad_norm": 0.8223424553871155,
|
| 971 |
+
"learning_rate": 0.00011011764705882352,
|
| 972 |
+
"loss": 0.2854,
|
| 973 |
+
"step": 540
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 31.76,
|
| 977 |
+
"eval_loss": 0.2715389132499695,
|
| 978 |
+
"eval_runtime": 1.9416,
|
| 979 |
+
"eval_samples_per_second": 69.013,
|
| 980 |
+
"eval_steps_per_second": 8.755,
|
| 981 |
+
"step": 540
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 32.06,
|
| 985 |
+
"grad_norm": 0.6093394160270691,
|
| 986 |
+
"learning_rate": 0.00010835294117647059,
|
| 987 |
+
"loss": 0.2945,
|
| 988 |
+
"step": 545
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 32.35,
|
| 992 |
+
"grad_norm": 0.7865052223205566,
|
| 993 |
+
"learning_rate": 0.00010658823529411764,
|
| 994 |
+
"loss": 0.2748,
|
| 995 |
+
"step": 550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 32.65,
|
| 999 |
+
"grad_norm": 0.6309812664985657,
|
| 1000 |
+
"learning_rate": 0.0001048235294117647,
|
| 1001 |
+
"loss": 0.282,
|
| 1002 |
+
"step": 555
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 32.94,
|
| 1006 |
+
"grad_norm": 0.7672943472862244,
|
| 1007 |
+
"learning_rate": 0.00010305882352941175,
|
| 1008 |
+
"loss": 0.2944,
|
| 1009 |
+
"step": 560
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 32.94,
|
| 1013 |
+
"eval_loss": 0.2701457440853119,
|
| 1014 |
+
"eval_runtime": 1.9433,
|
| 1015 |
+
"eval_samples_per_second": 68.956,
|
| 1016 |
+
"eval_steps_per_second": 8.748,
|
| 1017 |
+
"step": 560
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 33.24,
|
| 1021 |
+
"grad_norm": 0.7916382551193237,
|
| 1022 |
+
"learning_rate": 0.00010129411764705881,
|
| 1023 |
+
"loss": 0.2797,
|
| 1024 |
+
"step": 565
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 33.53,
|
| 1028 |
+
"grad_norm": 0.8927915692329407,
|
| 1029 |
+
"learning_rate": 9.952941176470588e-05,
|
| 1030 |
+
"loss": 0.2912,
|
| 1031 |
+
"step": 570
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 33.82,
|
| 1035 |
+
"grad_norm": 0.7179085612297058,
|
| 1036 |
+
"learning_rate": 9.776470588235293e-05,
|
| 1037 |
+
"loss": 0.2905,
|
| 1038 |
+
"step": 575
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 34.12,
|
| 1042 |
+
"grad_norm": 1.0066139698028564,
|
| 1043 |
+
"learning_rate": 9.599999999999999e-05,
|
| 1044 |
+
"loss": 0.293,
|
| 1045 |
+
"step": 580
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 34.12,
|
| 1049 |
+
"eval_loss": 0.26910731196403503,
|
| 1050 |
+
"eval_runtime": 1.9434,
|
| 1051 |
+
"eval_samples_per_second": 68.95,
|
| 1052 |
+
"eval_steps_per_second": 8.747,
|
| 1053 |
+
"step": 580
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 34.41,
|
| 1057 |
+
"grad_norm": 0.5777180790901184,
|
| 1058 |
+
"learning_rate": 9.423529411764706e-05,
|
| 1059 |
+
"loss": 0.2577,
|
| 1060 |
+
"step": 585
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 34.71,
|
| 1064 |
+
"grad_norm": 0.7130693793296814,
|
| 1065 |
+
"learning_rate": 9.247058823529411e-05,
|
| 1066 |
+
"loss": 0.2807,
|
| 1067 |
+
"step": 590
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 35.0,
|
| 1071 |
+
"grad_norm": 1.32589852809906,
|
| 1072 |
+
"learning_rate": 9.070588235294118e-05,
|
| 1073 |
+
"loss": 0.3171,
|
| 1074 |
+
"step": 595
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 35.29,
|
| 1078 |
+
"grad_norm": 0.7349640727043152,
|
| 1079 |
+
"learning_rate": 8.894117647058822e-05,
|
| 1080 |
+
"loss": 0.2739,
|
| 1081 |
+
"step": 600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 35.29,
|
| 1085 |
+
"eval_loss": 0.2687808871269226,
|
| 1086 |
+
"eval_runtime": 1.943,
|
| 1087 |
+
"eval_samples_per_second": 68.967,
|
| 1088 |
+
"eval_steps_per_second": 8.75,
|
| 1089 |
+
"step": 600
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 35.59,
|
| 1093 |
+
"grad_norm": 0.8435064554214478,
|
| 1094 |
+
"learning_rate": 8.717647058823528e-05,
|
| 1095 |
+
"loss": 0.297,
|
| 1096 |
+
"step": 605
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 35.88,
|
| 1100 |
+
"grad_norm": 0.9483019113540649,
|
| 1101 |
+
"learning_rate": 8.541176470588236e-05,
|
| 1102 |
+
"loss": 0.278,
|
| 1103 |
+
"step": 610
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 36.18,
|
| 1107 |
+
"grad_norm": 0.7475037574768066,
|
| 1108 |
+
"learning_rate": 8.36470588235294e-05,
|
| 1109 |
+
"loss": 0.279,
|
| 1110 |
+
"step": 615
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 36.47,
|
| 1114 |
+
"grad_norm": 0.6387231349945068,
|
| 1115 |
+
"learning_rate": 8.188235294117646e-05,
|
| 1116 |
+
"loss": 0.2816,
|
| 1117 |
+
"step": 620
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 36.47,
|
| 1121 |
+
"eval_loss": 0.26973241567611694,
|
| 1122 |
+
"eval_runtime": 1.9418,
|
| 1123 |
+
"eval_samples_per_second": 69.008,
|
| 1124 |
+
"eval_steps_per_second": 8.755,
|
| 1125 |
+
"step": 620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 36.76,
|
| 1129 |
+
"grad_norm": 0.7511037588119507,
|
| 1130 |
+
"learning_rate": 8.011764705882352e-05,
|
| 1131 |
+
"loss": 0.2884,
|
| 1132 |
+
"step": 625
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 37.06,
|
| 1136 |
+
"grad_norm": 0.7197074890136719,
|
| 1137 |
+
"learning_rate": 7.835294117647058e-05,
|
| 1138 |
+
"loss": 0.2907,
|
| 1139 |
+
"step": 630
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 37.35,
|
| 1143 |
+
"grad_norm": 0.8565782308578491,
|
| 1144 |
+
"learning_rate": 7.658823529411765e-05,
|
| 1145 |
+
"loss": 0.277,
|
| 1146 |
+
"step": 635
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 37.65,
|
| 1150 |
+
"grad_norm": 0.8459848761558533,
|
| 1151 |
+
"learning_rate": 7.48235294117647e-05,
|
| 1152 |
+
"loss": 0.2756,
|
| 1153 |
+
"step": 640
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 37.65,
|
| 1157 |
+
"eval_loss": 0.2685478627681732,
|
| 1158 |
+
"eval_runtime": 1.9444,
|
| 1159 |
+
"eval_samples_per_second": 68.917,
|
| 1160 |
+
"eval_steps_per_second": 8.743,
|
| 1161 |
+
"step": 640
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 37.94,
|
| 1165 |
+
"grad_norm": 0.8671796917915344,
|
| 1166 |
+
"learning_rate": 7.305882352941176e-05,
|
| 1167 |
+
"loss": 0.2778,
|
| 1168 |
+
"step": 645
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 38.24,
|
| 1172 |
+
"grad_norm": 0.8741558790206909,
|
| 1173 |
+
"learning_rate": 7.129411764705881e-05,
|
| 1174 |
+
"loss": 0.283,
|
| 1175 |
+
"step": 650
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 38.53,
|
| 1179 |
+
"grad_norm": 0.9461960792541504,
|
| 1180 |
+
"learning_rate": 6.952941176470587e-05,
|
| 1181 |
+
"loss": 0.2773,
|
| 1182 |
+
"step": 655
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 38.82,
|
| 1186 |
+
"grad_norm": 0.9360217452049255,
|
| 1187 |
+
"learning_rate": 6.776470588235293e-05,
|
| 1188 |
+
"loss": 0.2871,
|
| 1189 |
+
"step": 660
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 38.82,
|
| 1193 |
+
"eval_loss": 0.26918286085128784,
|
| 1194 |
+
"eval_runtime": 1.9403,
|
| 1195 |
+
"eval_samples_per_second": 69.063,
|
| 1196 |
+
"eval_steps_per_second": 8.762,
|
| 1197 |
+
"step": 660
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 39.12,
|
| 1201 |
+
"grad_norm": 0.953507125377655,
|
| 1202 |
+
"learning_rate": 6.599999999999999e-05,
|
| 1203 |
+
"loss": 0.2872,
|
| 1204 |
+
"step": 665
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 39.41,
|
| 1208 |
+
"grad_norm": 0.8516682386398315,
|
| 1209 |
+
"learning_rate": 6.423529411764705e-05,
|
| 1210 |
+
"loss": 0.2754,
|
| 1211 |
+
"step": 670
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 39.71,
|
| 1215 |
+
"grad_norm": 0.8544163107872009,
|
| 1216 |
+
"learning_rate": 6.247058823529411e-05,
|
| 1217 |
+
"loss": 0.2841,
|
| 1218 |
+
"step": 675
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 40.0,
|
| 1222 |
+
"grad_norm": 1.3582571744918823,
|
| 1223 |
+
"learning_rate": 6.0705882352941175e-05,
|
| 1224 |
+
"loss": 0.282,
|
| 1225 |
+
"step": 680
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 40.0,
|
| 1229 |
+
"eval_loss": 0.26776203513145447,
|
| 1230 |
+
"eval_runtime": 1.9501,
|
| 1231 |
+
"eval_samples_per_second": 68.716,
|
| 1232 |
+
"eval_steps_per_second": 8.718,
|
| 1233 |
+
"step": 680
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 40.29,
|
| 1237 |
+
"grad_norm": 0.8032355904579163,
|
| 1238 |
+
"learning_rate": 5.894117647058823e-05,
|
| 1239 |
+
"loss": 0.2634,
|
| 1240 |
+
"step": 685
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 40.59,
|
| 1244 |
+
"grad_norm": 0.7542455792427063,
|
| 1245 |
+
"learning_rate": 5.7176470588235286e-05,
|
| 1246 |
+
"loss": 0.279,
|
| 1247 |
+
"step": 690
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 40.88,
|
| 1251 |
+
"grad_norm": 0.835426390171051,
|
| 1252 |
+
"learning_rate": 5.5411764705882345e-05,
|
| 1253 |
+
"loss": 0.2864,
|
| 1254 |
+
"step": 695
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 41.18,
|
| 1258 |
+
"grad_norm": 0.8475760817527771,
|
| 1259 |
+
"learning_rate": 5.364705882352941e-05,
|
| 1260 |
+
"loss": 0.2979,
|
| 1261 |
+
"step": 700
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 41.18,
|
| 1265 |
+
"eval_loss": 0.26696136593818665,
|
| 1266 |
+
"eval_runtime": 1.9422,
|
| 1267 |
+
"eval_samples_per_second": 68.995,
|
| 1268 |
+
"eval_steps_per_second": 8.753,
|
| 1269 |
+
"step": 700
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 41.47,
|
| 1273 |
+
"grad_norm": 0.8202780485153198,
|
| 1274 |
+
"learning_rate": 5.188235294117646e-05,
|
| 1275 |
+
"loss": 0.2752,
|
| 1276 |
+
"step": 705
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 41.76,
|
| 1280 |
+
"grad_norm": 0.8360605835914612,
|
| 1281 |
+
"learning_rate": 5.011764705882352e-05,
|
| 1282 |
+
"loss": 0.2813,
|
| 1283 |
+
"step": 710
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 42.06,
|
| 1287 |
+
"grad_norm": 0.767460823059082,
|
| 1288 |
+
"learning_rate": 4.835294117647058e-05,
|
| 1289 |
+
"loss": 0.2656,
|
| 1290 |
+
"step": 715
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 42.35,
|
| 1294 |
+
"grad_norm": 0.6413666605949402,
|
| 1295 |
+
"learning_rate": 4.658823529411765e-05,
|
| 1296 |
+
"loss": 0.2629,
|
| 1297 |
+
"step": 720
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 42.35,
|
| 1301 |
+
"eval_loss": 0.2672065198421478,
|
| 1302 |
+
"eval_runtime": 1.9441,
|
| 1303 |
+
"eval_samples_per_second": 68.926,
|
| 1304 |
+
"eval_steps_per_second": 8.744,
|
| 1305 |
+
"step": 720
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 42.65,
|
| 1309 |
+
"grad_norm": 0.9078086018562317,
|
| 1310 |
+
"learning_rate": 4.48235294117647e-05,
|
| 1311 |
+
"loss": 0.2959,
|
| 1312 |
+
"step": 725
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 42.94,
|
| 1316 |
+
"grad_norm": 0.7576885223388672,
|
| 1317 |
+
"learning_rate": 4.305882352941176e-05,
|
| 1318 |
+
"loss": 0.2664,
|
| 1319 |
+
"step": 730
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 43.24,
|
| 1323 |
+
"grad_norm": 0.7104106545448303,
|
| 1324 |
+
"learning_rate": 4.129411764705882e-05,
|
| 1325 |
+
"loss": 0.2562,
|
| 1326 |
+
"step": 735
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 43.53,
|
| 1330 |
+
"grad_norm": 0.8250320553779602,
|
| 1331 |
+
"learning_rate": 3.952941176470588e-05,
|
| 1332 |
+
"loss": 0.2596,
|
| 1333 |
+
"step": 740
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 43.53,
|
| 1337 |
+
"eval_loss": 0.2670022249221802,
|
| 1338 |
+
"eval_runtime": 1.9446,
|
| 1339 |
+
"eval_samples_per_second": 68.907,
|
| 1340 |
+
"eval_steps_per_second": 8.742,
|
| 1341 |
+
"step": 740
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 43.82,
|
| 1345 |
+
"grad_norm": 0.8341289162635803,
|
| 1346 |
+
"learning_rate": 3.776470588235294e-05,
|
| 1347 |
+
"loss": 0.2809,
|
| 1348 |
+
"step": 745
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 44.12,
|
| 1352 |
+
"grad_norm": 0.6533918380737305,
|
| 1353 |
+
"learning_rate": 3.5999999999999994e-05,
|
| 1354 |
+
"loss": 0.2823,
|
| 1355 |
+
"step": 750
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 44.41,
|
| 1359 |
+
"grad_norm": 0.773414671421051,
|
| 1360 |
+
"learning_rate": 3.423529411764706e-05,
|
| 1361 |
+
"loss": 0.2944,
|
| 1362 |
+
"step": 755
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 44.71,
|
| 1366 |
+
"grad_norm": 0.9755772948265076,
|
| 1367 |
+
"learning_rate": 3.247058823529411e-05,
|
| 1368 |
+
"loss": 0.2833,
|
| 1369 |
+
"step": 760
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 44.71,
|
| 1373 |
+
"eval_loss": 0.26673921942710876,
|
| 1374 |
+
"eval_runtime": 1.9452,
|
| 1375 |
+
"eval_samples_per_second": 68.887,
|
| 1376 |
+
"eval_steps_per_second": 8.739,
|
| 1377 |
+
"step": 760
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 45.0,
|
| 1381 |
+
"grad_norm": 0.8540541529655457,
|
| 1382 |
+
"learning_rate": 3.070588235294118e-05,
|
| 1383 |
+
"loss": 0.2717,
|
| 1384 |
+
"step": 765
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 45.29,
|
| 1388 |
+
"grad_norm": 0.7504986524581909,
|
| 1389 |
+
"learning_rate": 2.894117647058823e-05,
|
| 1390 |
+
"loss": 0.2685,
|
| 1391 |
+
"step": 770
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 45.59,
|
| 1395 |
+
"grad_norm": 0.7057090997695923,
|
| 1396 |
+
"learning_rate": 2.7176470588235292e-05,
|
| 1397 |
+
"loss": 0.2669,
|
| 1398 |
+
"step": 775
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 45.88,
|
| 1402 |
+
"grad_norm": 0.9183229207992554,
|
| 1403 |
+
"learning_rate": 2.5411764705882348e-05,
|
| 1404 |
+
"loss": 0.2747,
|
| 1405 |
+
"step": 780
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 45.88,
|
| 1409 |
+
"eval_loss": 0.26657456159591675,
|
| 1410 |
+
"eval_runtime": 1.9434,
|
| 1411 |
+
"eval_samples_per_second": 68.95,
|
| 1412 |
+
"eval_steps_per_second": 8.747,
|
| 1413 |
+
"step": 780
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 46.18,
|
| 1417 |
+
"grad_norm": 0.9822715520858765,
|
| 1418 |
+
"learning_rate": 2.364705882352941e-05,
|
| 1419 |
+
"loss": 0.2844,
|
| 1420 |
+
"step": 785
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 46.47,
|
| 1424 |
+
"grad_norm": 0.6618647575378418,
|
| 1425 |
+
"learning_rate": 2.1882352941176466e-05,
|
| 1426 |
+
"loss": 0.2534,
|
| 1427 |
+
"step": 790
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 46.76,
|
| 1431 |
+
"grad_norm": 0.8773749470710754,
|
| 1432 |
+
"learning_rate": 2.011764705882353e-05,
|
| 1433 |
+
"loss": 0.2634,
|
| 1434 |
+
"step": 795
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 47.06,
|
| 1438 |
+
"grad_norm": 0.7959761619567871,
|
| 1439 |
+
"learning_rate": 1.8352941176470587e-05,
|
| 1440 |
+
"loss": 0.3073,
|
| 1441 |
+
"step": 800
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 47.06,
|
| 1445 |
+
"eval_loss": 0.2664162814617157,
|
| 1446 |
+
"eval_runtime": 1.9451,
|
| 1447 |
+
"eval_samples_per_second": 68.891,
|
| 1448 |
+
"eval_steps_per_second": 8.74,
|
| 1449 |
+
"step": 800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 47.35,
|
| 1453 |
+
"grad_norm": 0.8709791302680969,
|
| 1454 |
+
"learning_rate": 1.6588235294117646e-05,
|
| 1455 |
+
"loss": 0.2852,
|
| 1456 |
+
"step": 805
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 47.65,
|
| 1460 |
+
"grad_norm": 0.7862871289253235,
|
| 1461 |
+
"learning_rate": 1.4823529411764704e-05,
|
| 1462 |
+
"loss": 0.2687,
|
| 1463 |
+
"step": 810
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 47.94,
|
| 1467 |
+
"grad_norm": 0.8266788721084595,
|
| 1468 |
+
"learning_rate": 1.3058823529411763e-05,
|
| 1469 |
+
"loss": 0.2736,
|
| 1470 |
+
"step": 815
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 48.24,
|
| 1474 |
+
"grad_norm": 0.926347553730011,
|
| 1475 |
+
"learning_rate": 1.1294117647058822e-05,
|
| 1476 |
+
"loss": 0.2535,
|
| 1477 |
+
"step": 820
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 48.24,
|
| 1481 |
+
"eval_loss": 0.2662106454372406,
|
| 1482 |
+
"eval_runtime": 1.9448,
|
| 1483 |
+
"eval_samples_per_second": 68.903,
|
| 1484 |
+
"eval_steps_per_second": 8.741,
|
| 1485 |
+
"step": 820
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 48.53,
|
| 1489 |
+
"grad_norm": 1.0417717695236206,
|
| 1490 |
+
"learning_rate": 9.52941176470588e-06,
|
| 1491 |
+
"loss": 0.2793,
|
| 1492 |
+
"step": 825
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 48.82,
|
| 1496 |
+
"grad_norm": 0.71202152967453,
|
| 1497 |
+
"learning_rate": 7.764705882352941e-06,
|
| 1498 |
+
"loss": 0.2736,
|
| 1499 |
+
"step": 830
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 49.12,
|
| 1503 |
+
"grad_norm": 0.8569315671920776,
|
| 1504 |
+
"learning_rate": 5.999999999999999e-06,
|
| 1505 |
+
"loss": 0.2717,
|
| 1506 |
+
"step": 835
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 49.41,
|
| 1510 |
+
"grad_norm": 0.8434327840805054,
|
| 1511 |
+
"learning_rate": 4.235294117647058e-06,
|
| 1512 |
+
"loss": 0.2713,
|
| 1513 |
+
"step": 840
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 49.41,
|
| 1517 |
+
"eval_loss": 0.2660675048828125,
|
| 1518 |
+
"eval_runtime": 1.9443,
|
| 1519 |
+
"eval_samples_per_second": 68.92,
|
| 1520 |
+
"eval_steps_per_second": 8.744,
|
| 1521 |
+
"step": 840
|
| 1522 |
+
}
|
| 1523 |
+
],
|
| 1524 |
+
"logging_steps": 5,
|
| 1525 |
+
"max_steps": 850,
|
| 1526 |
+
"num_input_tokens_seen": 0,
|
| 1527 |
+
"num_train_epochs": 50,
|
| 1528 |
+
"save_steps": 20,
|
| 1529 |
+
"total_flos": 7554290335088640.0,
|
| 1530 |
+
"train_batch_size": 4,
|
| 1531 |
+
"trial_name": null,
|
| 1532 |
+
"trial_params": null
|
| 1533 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43433281d9ff055bfecbaed56ac74c2fc38ba6e0c553077df8c74c1c1010d11a
|
| 3 |
+
size 5048
|